Merge branch 'main' of github.com:crewAIInc/crewAI into lorenze/feat/plan-execute-pattern

* supporting parallel tool use

* ensure we respect max_usage_count

* ensure result_as_answer, hooks, and cache parodity

* improve crew agent executor

* address test comments

docs/en/enterprise/features/flow-hitl-management.mdx

@@ -38,22 +38,21 @@ CrewAI Enterprise provides a comprehensive Human-in-the-Loop (HITL) management s
 Configure human review checkpoints within your Flows using the `@human_feedback` decorator. When execution reaches a review point, the system pauses, notifies the assignee via email, and waits for a response.
 
 ```python
-from crewai.flow.flow import Flow, start, listen
+from crewai.flow.flow import Flow, start, listen, or_
 from crewai.flow.human_feedback import human_feedback, HumanFeedbackResult
 
 class ContentApprovalFlow(Flow):
     @start()
     def generate_content(self):
-        # AI generates content
         return "Generated marketing copy for Q1 campaign..."
 
-    @listen(generate_content)
     @human_feedback(
         message="Please review this content for brand compliance:",
         emit=["approved", "rejected", "needs_revision"],
     )
-    def review_content(self, content):
-        return content
+    @listen(or_("generate_content", "needs_revision"))
+    def review_content(self):
+        return "Marketing copy for review..."
 
     @listen("approved")
     def publish_content(self, result: HumanFeedbackResult):
@@ -62,10 +61,6 @@ class ContentApprovalFlow(Flow):
     @listen("rejected")
     def archive_content(self, result: HumanFeedbackResult):
         print(f"Content rejected. Reason: {result.feedback}")
-
-    @listen("needs_revision")
-    def revise_content(self, result: HumanFeedbackResult):
-        print(f"Revision requested: {result.feedback}")
 ```
 
 For complete implementation details, see the [Human Feedback in Flows](/en/learn/human-feedback-in-flows) guide.

docs/en/learn/human-feedback-in-flows.mdx

@@ -98,33 +98,43 @@ def handle_feedback(self, result):
 When you specify `emit`, the decorator becomes a router. The human's free-form feedback is interpreted by an LLM and collapsed into one of the specified outcomes:
 
 ```python Code
-@start()
-@human_feedback(
-    message="Do you approve this content for publication?",
-    emit=["approved", "rejected", "needs_revision"],
-    llm="gpt-4o-mini",
-    default_outcome="needs_revision",
-)
-def review_content(self):
-    return "Draft blog post content here..."
+from crewai.flow.flow import Flow, start, listen, or_
+from crewai.flow.human_feedback import human_feedback
 
-@listen("approved")
-def publish(self, result):
-    print(f"Publishing! User said: {result.feedback}")
+class ReviewFlow(Flow):
+    @start()
+    def generate_content(self):
+        return "Draft blog post content here..."
 
-@listen("rejected")
-def discard(self, result):
-    print(f"Discarding. Reason: {result.feedback}")
+    @human_feedback(
+        message="Do you approve this content for publication?",
+        emit=["approved", "rejected", "needs_revision"],
+        llm="gpt-4o-mini",
+        default_outcome="needs_revision",
+    )
+    @listen(or_("generate_content", "needs_revision"))
+    def review_content(self):
+        return "Draft blog post content here..."
 
-@listen("needs_revision")
-def revise(self, result):
-    print(f"Revising based on: {result.feedback}")
+    @listen("approved")
+    def publish(self, result):
+        print(f"Publishing! User said: {result.feedback}")
+
+    @listen("rejected")
+    def discard(self, result):
+        print(f"Discarding. Reason: {result.feedback}")
 ```
 
+When the human says something like "needs more detail", the LLM collapses that to `"needs_revision"`, which triggers `review_content` again via `or_()` — creating a revision loop. The loop continues until the outcome is `"approved"` or `"rejected"`.
+
 <Tip>
 The LLM uses structured outputs (function calling) when available to guarantee the response is one of your specified outcomes. This makes routing reliable and predictable.
 </Tip>
 
+<Warning>
+A `@start()` method only runs once at the beginning of the flow. If you need a revision loop, separate the start method from the review method and use `@listen(or_("trigger", "revision_outcome"))` on the review method to enable the self-loop.
+</Warning>
+
 ## HumanFeedbackResult
 
 The `HumanFeedbackResult` dataclass contains all information about a human feedback interaction:
@@ -188,127 +198,183 @@ Each `HumanFeedbackResult` is appended to `human_feedback_history`, so multiple
 
 ## Complete Example: Content Approval Workflow
 
-Here's a full example implementing a content review and approval workflow:
+Here's a full example implementing a content review and approval workflow with a revision loop:
 
 <CodeGroup>
 
 ```python Code
-from crewai.flow.flow import Flow, start, listen
+from crewai.flow.flow import Flow, start, listen, or_
 from crewai.flow.human_feedback import human_feedback, HumanFeedbackResult
 from pydantic import BaseModel
 
 
 class ContentState(BaseModel):
-    topic: str = ""
     draft: str = ""
-    final_content: str = ""
     revision_count: int = 0
+    status: str = "pending"
 
 
 class ContentApprovalFlow(Flow[ContentState]):
-    """A flow that generates content and gets human approval."""
+    """A flow that generates content and loops until the human approves."""
 
     @start()
-    def get_topic(self):
-        self.state.topic = input("What topic should I write about? ")
-        return self.state.topic
-
-    @listen(get_topic)
-    def generate_draft(self, topic):
-        # In real use, this would call an LLM
-        self.state.draft = f"# {topic}\n\nThis is a draft about {topic}..."
+    def generate_draft(self):
+        self.state.draft = "# AI Safety\n\nThis is a draft about AI Safety..."
         return self.state.draft
 
-    @listen(generate_draft)
     @human_feedback(
-        message="Please review this draft. Reply 'approved', 'rejected', or provide revision feedback:",
+        message="Please review this draft. Approve, reject, or describe what needs changing:",
         emit=["approved", "rejected", "needs_revision"],
         llm="gpt-4o-mini",
         default_outcome="needs_revision",
     )
-    def review_draft(self, draft):
-        return draft
+    @listen(or_("generate_draft", "needs_revision"))
+    def review_draft(self):
+        self.state.revision_count += 1
+        return f"{self.state.draft} (v{self.state.revision_count})"
 
     @listen("approved")
     def publish_content(self, result: HumanFeedbackResult):
-        self.state.final_content = result.output
-        print("\n✅ Content approved and published!")
-        print(f"Reviewer comment: {result.feedback}")
+        self.state.status = "published"
+        print(f"Content approved and published! Reviewer said: {result.feedback}")
         return "published"
 
     @listen("rejected")
     def handle_rejection(self, result: HumanFeedbackResult):
-        print("\n❌ Content rejected")
-        print(f"Reason: {result.feedback}")
+        self.state.status = "rejected"
+        print(f"Content rejected. Reason: {result.feedback}")
         return "rejected"
 
-    @listen("needs_revision")
-    def revise_content(self, result: HumanFeedbackResult):
-        self.state.revision_count += 1
-        print(f"\n📝 Revision #{self.state.revision_count} requested")
-        print(f"Feedback: {result.feedback}")
 
-        # In a real flow, you might loop back to generate_draft
-        # For this example, we just acknowledge
-        return "revision_requested"
-
-
-# Run the flow
 flow = ContentApprovalFlow()
 result = flow.kickoff()
-print(f"\nFlow completed. Revisions requested: {flow.state.revision_count}")
+print(f"\nFlow completed. Status: {flow.state.status}, Reviews: {flow.state.revision_count}")
 ```
 
 ```text Output
-What topic should I write about? AI Safety
+==================================================
+OUTPUT FOR REVIEW:
+==================================================
+# AI Safety
+
+This is a draft about AI Safety... (v1)
+==================================================
+
+Please review this draft. Approve, reject, or describe what needs changing:
+(Press Enter to skip, or type your feedback)
+
+Your feedback: Needs more detail on alignment research
 
 ==================================================
 OUTPUT FOR REVIEW:
 ==================================================
 # AI Safety
 
-This is a draft about AI Safety...
+This is a draft about AI Safety... (v2)
 ==================================================
 
-Please review this draft. Reply 'approved', 'rejected', or provide revision feedback:
+Please review this draft. Approve, reject, or describe what needs changing:
 (Press Enter to skip, or type your feedback)
 
 Your feedback: Looks good, approved!
 
-✅ Content approved and published!
-Reviewer comment: Looks good, approved!
+Content approved and published! Reviewer said: Looks good, approved!
 
-Flow completed. Revisions requested: 0
+Flow completed. Status: published, Reviews: 2
 ```
 
 </CodeGroup>
 
+The key pattern is `@listen(or_("generate_draft", "needs_revision"))` — the review method listens to both the initial trigger and its own revision outcome, creating a self-loop that repeats until the human approves or rejects.
+
 ## Combining with Other Decorators
 
-The `@human_feedback` decorator works with other flow decorators. Place it as the innermost decorator (closest to the function):
+The `@human_feedback` decorator works with `@start()`, `@listen()`, and `or_()`. Both decorator orderings work — the framework propagates attributes in both directions — but the recommended patterns are:
 
 ```python Code
-# Correct: @human_feedback is innermost (closest to the function)
+# One-shot review at the start of a flow (no self-loop)
 @start()
-@human_feedback(message="Review this:")
+@human_feedback(message="Review this:", emit=["approved", "rejected"], llm="gpt-4o-mini")
 def my_start_method(self):
     return "content"
 
+# Linear review on a listener (no self-loop)
 @listen(other_method)
-@human_feedback(message="Review this too:")
+@human_feedback(message="Review this too:", emit=["good", "bad"], llm="gpt-4o-mini")
 def my_listener(self, data):
     return f"processed: {data}"
+
+# Self-loop: review that can loop back for revisions
+@human_feedback(message="Approve or revise?", emit=["approved", "revise"], llm="gpt-4o-mini")
+@listen(or_("upstream_method", "revise"))
+def review_with_loop(self):
+    return "content for review"
 ```
 
-<Tip>
-Place `@human_feedback` as the innermost decorator (last/closest to the function) so it wraps the method directly and can capture the return value before passing to the flow system.
-</Tip>
+### Self-loop pattern
+
+To create a revision loop, the review method must listen to **both** an upstream trigger and its own revision outcome using `or_()`:
+
+```python Code
+@start()
+def generate(self):
+    return "initial draft"
+
+@human_feedback(
+    message="Approve or request changes?",
+    emit=["revise", "approved"],
+    llm="gpt-4o-mini",
+    default_outcome="approved",
+)
+@listen(or_("generate", "revise"))
+def review(self):
+    return "content"
+
+@listen("approved")
+def publish(self):
+    return "published"
+```
+
+When the outcome is `"revise"`, the flow routes back to `review` (because it listens to `"revise"` via `or_()`). When the outcome is `"approved"`, the flow continues to `publish`. This works because the flow engine exempts routers from the "fire once" rule, allowing them to re-execute on each loop iteration.
+
+### Chained routers
+
+A listener triggered by one router's outcome can itself be a router:
+
+```python Code
+@start()
+def generate(self):
+    return "draft content"
+
+@human_feedback(message="First review:", emit=["approved", "rejected"], llm="gpt-4o-mini")
+@listen("generate")
+def first_review(self):
+    return "draft content"
+
+@human_feedback(message="Final review:", emit=["publish", "hold"], llm="gpt-4o-mini")
+@listen("approved")
+def final_review(self, prev):
+    return "final content"
+
+@listen("publish")
+def on_publish(self, prev):
+    return "published"
+
+@listen("hold")
+def on_hold(self, prev):
+    return "held for later"
+```
+
+### Limitations
+
+- **`@start()` methods run once**: A `@start()` method cannot self-loop. If you need a revision cycle, use a separate `@start()` method as the entry point and put the `@human_feedback` on a `@listen()` method.
+- **No `@start()` + `@listen()` on the same method**: This is a Flow framework constraint. A method is either a start point or a listener, not both.
 
 ## Best Practices
 
 ### 1. Write Clear Request Messages
 
-The `request` parameter is what the human sees. Make it actionable:
+The `message` parameter is what the human sees. Make it actionable:
 
 ```python Code
 # ✅ Good - clear and actionable
@@ -516,9 +582,9 @@ class ContentPipeline(Flow):
     @start()
     @human_feedback(
         message="Approve this content for publication?",
-        emit=["approved", "rejected", "needs_revision"],
+        emit=["approved", "rejected"],
         llm="gpt-4o-mini",
-        default_outcome="needs_revision",
+        default_outcome="rejected",
         provider=SlackNotificationProvider("#content-reviews"),
     )
     def generate_content(self):
@@ -534,11 +600,6 @@ class ContentPipeline(Flow):
         print(f"Archived. Reason: {result.feedback}")
         return {"status": "archived"}
 
-    @listen("needs_revision")
-    def queue_revision(self, result):
-        print(f"Queued for revision: {result.feedback}")
-        return {"status": "revision_needed"}
-
 
 # Starting the flow (will pause and wait for Slack response)
 def start_content_pipeline():
@@ -594,22 +655,22 @@ Over time, the human sees progressively better pre-reviewed output because each
 ```python Code
 class ArticleReviewFlow(Flow):
     @start()
+    def generate_article(self):
+        return self.crew.kickoff(inputs={"topic": "AI Safety"}).raw
+
     @human_feedback(
         message="Review this article draft:",
         emit=["approved", "needs_revision"],
         llm="gpt-4o-mini",
         learn=True,  # enable HITL learning
     )
-    def generate_article(self):
-        return self.crew.kickoff(inputs={"topic": "AI Safety"}).raw
+    @listen(or_("generate_article", "needs_revision"))
+    def review_article(self):
+        return self.last_human_feedback.output if self.last_human_feedback else "article draft"
 
     @listen("approved")
     def publish(self):
         print(f"Publishing: {self.last_human_feedback.output}")
-
-    @listen("needs_revision")
-    def revise(self):
-        print("Revising based on feedback...")
 ```
 
 **First run**: The human sees the raw output and says "Always include citations for factual claims." The lesson is distilled and stored in memory.

docs/ko/enterprise/features/flow-hitl-management.mdx

@@ -38,22 +38,21 @@ CrewAI Enterprise는 AI 워크플로우를 협업적인 인간-AI 프로세스
 `@human_feedback` 데코레이터를 사용하여 Flow 내에 인간 검토 체크포인트를 구성합니다. 실행이 검토 포인트에 도달하면 시스템이 일시 중지되고, 담당자에게 이메일로 알리며, 응답을 기다립니다.
 
 ```python
-from crewai.flow.flow import Flow, start, listen
+from crewai.flow.flow import Flow, start, listen, or_
 from crewai.flow.human_feedback import human_feedback, HumanFeedbackResult
 
 class ContentApprovalFlow(Flow):
     @start()
     def generate_content(self):
-        # AI가 콘텐츠 생성
         return "Q1 캠페인용 마케팅 카피 생성..."
 
-    @listen(generate_content)
     @human_feedback(
         message="브랜드 준수를 위해 이 콘텐츠를 검토해 주세요:",
         emit=["approved", "rejected", "needs_revision"],
     )
-    def review_content(self, content):
-        return content
+    @listen(or_("generate_content", "needs_revision"))
+    def review_content(self):
+        return "검토용 마케팅 카피..."
 
     @listen("approved")
     def publish_content(self, result: HumanFeedbackResult):
@@ -62,10 +61,6 @@ class ContentApprovalFlow(Flow):
     @listen("rejected")
     def archive_content(self, result: HumanFeedbackResult):
         print(f"콘텐츠 거부됨. 사유: {result.feedback}")
-
-    @listen("needs_revision")
-    def revise_content(self, result: HumanFeedbackResult):
-        print(f"수정 요청: {result.feedback}")
 ```
 
 완전한 구현 세부 사항은 [Flow에서 인간 피드백](/ko/learn/human-feedback-in-flows) 가이드를 참조하세요.

docs/ko/learn/human-feedback-in-flows.mdx

@@ -98,33 +98,43 @@ def handle_feedback(self, result):
 `emit`을 지정하면, 데코레이터는 라우터가 됩니다. 인간의 자유 형식 피드백이 LLM에 의해 해석되어 지정된 outcome 중 하나로 매핑됩니다:
 
 ```python Code
-@start()
-@human_feedback(
-    message="이 콘텐츠의 출판을 승인하시겠습니까?",
-    emit=["approved", "rejected", "needs_revision"],
-    llm="gpt-4o-mini",
-    default_outcome="needs_revision",
-)
-def review_content(self):
-    return "블로그 게시물 초안 내용..."
+from crewai.flow.flow import Flow, start, listen, or_
+from crewai.flow.human_feedback import human_feedback
 
-@listen("approved")
-def publish(self, result):
-    print(f"출판 중! 사용자 의견: {result.feedback}")
+class ReviewFlow(Flow):
+    @start()
+    def generate_content(self):
+        return "블로그 게시물 초안 내용..."
 
-@listen("rejected")
-def discard(self, result):
-    print(f"폐기됨. 이유: {result.feedback}")
+    @human_feedback(
+        message="이 콘텐츠의 출판을 승인하시겠습니까?",
+        emit=["approved", "rejected", "needs_revision"],
+        llm="gpt-4o-mini",
+        default_outcome="needs_revision",
+    )
+    @listen(or_("generate_content", "needs_revision"))
+    def review_content(self):
+        return "블로그 게시물 초안 내용..."
 
-@listen("needs_revision")
-def revise(self, result):
-    print(f"다음을 기반으로 수정 중: {result.feedback}")
+    @listen("approved")
+    def publish(self, result):
+        print(f"출판 중! 사용자 의견: {result.feedback}")
+
+    @listen("rejected")
+    def discard(self, result):
+        print(f"폐기됨. 이유: {result.feedback}")
 ```
 
+사용자가 "더 자세한 내용이 필요합니다"와 같이 말하면, LLM이 이를 `"needs_revision"`으로 매핑하고, `or_()`를 통해 `review_content`가 다시 트리거됩니다 — 수정 루프가 생성됩니다. outcome이 `"approved"` 또는 `"rejected"`가 될 때까지 루프가 계속됩니다.
+
 <Tip>
 LLM은 가능한 경우 구조화된 출력(function calling)을 사용하여 응답이 지정된 outcome 중 하나임을 보장합니다. 이로 인해 라우팅이 신뢰할 수 있고 예측 가능해집니다.
 </Tip>
 
+<Warning>
+`@start()` 메서드는 flow 시작 시 한 번만 실행됩니다. 수정 루프가 필요한 경우, start 메서드를 review 메서드와 분리하고 review 메서드에 `@listen(or_("trigger", "revision_outcome"))`를 사용하여 self-loop을 활성화하세요.
+</Warning>
+
 ## HumanFeedbackResult
 
 `HumanFeedbackResult` 데이터클래스는 인간 피드백 상호작용에 대한 모든 정보를 포함합니다:
@@ -193,116 +203,162 @@ def summarize(self):
 <CodeGroup>
 
 ```python Code
-from crewai.flow.flow import Flow, start, listen
+from crewai.flow.flow import Flow, start, listen, or_
 from crewai.flow.human_feedback import human_feedback, HumanFeedbackResult
 from pydantic import BaseModel
 
 
 class ContentState(BaseModel):
-    topic: str = ""
     draft: str = ""
-    final_content: str = ""
     revision_count: int = 0
+    status: str = "pending"
 
 
 class ContentApprovalFlow(Flow[ContentState]):
-    """콘텐츠를 생성하고 인간의 승인을 받는 Flow입니다."""
+    """콘텐츠를 생성하고 승인될 때까지 반복하는 Flow."""
 
     @start()
-    def get_topic(self):
-        self.state.topic = input("어떤 주제에 대해 글을 쓸까요? ")
-        return self.state.topic
-
-    @listen(get_topic)
-    def generate_draft(self, topic):
-        # 실제 사용에서는 LLM을 호출합니다
-        self.state.draft = f"# {topic}\n\n{topic}에 대한 초안입니다..."
+    def generate_draft(self):
+        self.state.draft = "# AI 안전\n\nAI 안전에 대한 초안..."
         return self.state.draft
 
-    @listen(generate_draft)
     @human_feedback(
-        message="이 초안을 검토해 주세요. 'approved', 'rejected'로 답하거나 수정 피드백을 제공해 주세요:",
+        message="이 초안을 검토해 주세요. 승인, 거부 또는 변경이 필요한 사항을 설명해 주세요:",
         emit=["approved", "rejected", "needs_revision"],
         llm="gpt-4o-mini",
         default_outcome="needs_revision",
     )
-    def review_draft(self, draft):
-        return draft
+    @listen(or_("generate_draft", "needs_revision"))
+    def review_draft(self):
+        self.state.revision_count += 1
+        return f"{self.state.draft} (v{self.state.revision_count})"
 
     @listen("approved")
     def publish_content(self, result: HumanFeedbackResult):
-        self.state.final_content = result.output
-        print("\n✅ 콘텐츠가 승인되어 출판되었습니다!")
-        print(f"검토자 코멘트: {result.feedback}")
+        self.state.status = "published"
+        print(f"콘텐츠 승인 및 게시! 리뷰어 의견: {result.feedback}")
         return "published"
 
     @listen("rejected")
     def handle_rejection(self, result: HumanFeedbackResult):
-        print("\n❌ 콘텐츠가 거부되었습니다")
-        print(f"이유: {result.feedback}")
+        self.state.status = "rejected"
+        print(f"콘텐츠 거부됨. 이유: {result.feedback}")
         return "rejected"
 
-    @listen("needs_revision")
-    def revise_content(self, result: HumanFeedbackResult):
-        self.state.revision_count += 1
-        print(f"\n📝 수정 #{self.state.revision_count} 요청됨")
-        print(f"피드백: {result.feedback}")
 
-        # 실제 Flow에서는 generate_draft로 돌아갈 수 있습니다
-        # 이 예제에서는 단순히 확인합니다
-        return "revision_requested"
-
-
-# Flow 실행
 flow = ContentApprovalFlow()
 result = flow.kickoff()
-print(f"\nFlow 완료. 요청된 수정: {flow.state.revision_count}")
+print(f"\nFlow 완료. 상태: {flow.state.status}, 검토 횟수: {flow.state.revision_count}")
 ```
 
 ```text Output
-어떤 주제에 대해 글을 쓸까요? AI 안전
+==================================================
+OUTPUT FOR REVIEW:
+==================================================
+# AI 안전
+
+AI 안전에 대한 초안... (v1)
+==================================================
+
+이 초안을 검토해 주세요. 승인, 거부 또는 변경이 필요한 사항을 설명해 주세요:
+(Press Enter to skip, or type your feedback)
+
+Your feedback: 더 자세한 내용이 필요합니다
 
 ==================================================
 OUTPUT FOR REVIEW:
 ==================================================
 # AI 안전
 
-AI 안전에 대한 초안입니다...
+AI 안전에 대한 초안... (v2)
 ==================================================
 
-이 초안을 검토해 주세요. 'approved', 'rejected'로 답하거나 수정 피드백을 제공해 주세요:
+이 초안을 검토해 주세요. 승인, 거부 또는 변경이 필요한 사항을 설명해 주세요:
 (Press Enter to skip, or type your feedback)
 
 Your feedback: 좋아 보입니다, 승인!
 
-✅ 콘텐츠가 승인되어 출판되었습니다!
-검토자 코멘트: 좋아 보입니다, 승인!
+콘텐츠 승인 및 게시! 리뷰어 의견: 좋아 보입니다, 승인!
 
-Flow 완료. 요청된 수정: 0
+Flow 완료. 상태: published, 검토 횟수: 2
 ```
 
 </CodeGroup>
 
 ## 다른 데코레이터와 결합하기
 
-`@human_feedback` 데코레이터는 다른 Flow 데코레이터와 함께 작동합니다. 가장 안쪽 데코레이터(함수에 가장 가까운)로 배치하세요:
+`@human_feedback` 데코레이터는 `@start()`, `@listen()`, `or_()`와 함께 작동합니다. 데코레이터 순서는 두 가지 모두 동작합니다—프레임워크가 양방향으로 속성을 전파합니다—하지만 권장 패턴은 다음과 같습니다:
 
 ```python Code
-# 올바름: @human_feedback이 가장 안쪽(함수에 가장 가까움)
+# Flow 시작 시 일회성 검토 (self-loop 없음)
 @start()
-@human_feedback(message="이것을 검토해 주세요:")
+@human_feedback(message="이것을 검토해 주세요:", emit=["approved", "rejected"], llm="gpt-4o-mini")
 def my_start_method(self):
     return "content"
 
+# 리스너에서 선형 검토 (self-loop 없음)
 @listen(other_method)
-@human_feedback(message="이것도 검토해 주세요:")
+@human_feedback(message="이것도 검토해 주세요:", emit=["good", "bad"], llm="gpt-4o-mini")
 def my_listener(self, data):
     return f"processed: {data}"
+
+# Self-loop: 수정을 위해 반복할 수 있는 검토
+@human_feedback(message="승인 또는 수정 요청?", emit=["approved", "revise"], llm="gpt-4o-mini")
+@listen(or_("upstream_method", "revise"))
+def review_with_loop(self):
+    return "content for review"
 ```
 
-<Tip>
-`@human_feedback`를 가장 안쪽 데코레이터(마지막/함수에 가장 가까움)로 배치하여 메서드를 직접 래핑하고 Flow 시스템에 전달하기 전에 반환 값을 캡처할 수 있도록 하세요.
-</Tip>
+### Self-loop 패턴
+
+수정 루프를 만들려면 `or_()`를 사용하여 검토 메서드가 **상위 트리거**와 **자체 수정 outcome**을 모두 리스닝해야 합니다:
+
+```python Code
+@start()
+def generate(self):
+    return "initial draft"
+
+@human_feedback(
+    message="승인하시겠습니까, 아니면 변경을 요청하시겠습니까?",
+    emit=["revise", "approved"],
+    llm="gpt-4o-mini",
+    default_outcome="approved",
+)
+@listen(or_("generate", "revise"))
+def review(self):
+    return "content"
+
+@listen("approved")
+def publish(self):
+    return "published"
+```
+
+outcome이 `"revise"`이면 flow가 `review`로 다시 라우팅됩니다 (`or_()`를 통해 `"revise"`를 리스닝하기 때문). outcome이 `"approved"`이면 flow가 `publish`로 계속됩니다. flow 엔진이 라우터를 "한 번만 실행" 규칙에서 제외하여 각 루프 반복마다 재실행할 수 있기 때문에 이 패턴이 동작합니다.
+
+### 체인된 라우터
+
+한 라우터의 outcome으로 트리거된 리스너가 그 자체로 라우터가 될 수 있습니다:
+
+```python Code
+@start()
+@human_feedback(message="첫 번째 검토:", emit=["approved", "rejected"], llm="gpt-4o-mini")
+def draft(self):
+    return "draft content"
+
+@listen("approved")
+@human_feedback(message="최종 검토:", emit=["publish", "revise"], llm="gpt-4o-mini")
+def final_review(self, prev):
+    return "final content"
+
+@listen("publish")
+def on_publish(self, prev):
+    return "published"
+```
+
+### 제한 사항
+
+- **`@start()` 메서드는 한 번만 실행**: `@start()` 메서드는 self-loop할 수 없습니다. 수정 주기가 필요하면 별도의 `@start()` 메서드를 진입점으로 사용하고 `@listen()` 메서드에 `@human_feedback`를 배치하세요.
+- **동일 메서드에 `@start()` + `@listen()` 불가**: 이는 Flow 프레임워크 제약입니다. 메서드는 시작점이거나 리스너여야 하며, 둘 다일 수 없습니다.
 
 ## 모범 사례
 
@@ -516,9 +572,9 @@ class ContentPipeline(Flow):
     @start()
     @human_feedback(
         message="이 콘텐츠의 출판을 승인하시겠습니까?",
-        emit=["approved", "rejected", "needs_revision"],
+        emit=["approved", "rejected"],
         llm="gpt-4o-mini",
-        default_outcome="needs_revision",
+        default_outcome="rejected",
         provider=SlackNotificationProvider("#content-reviews"),
     )
     def generate_content(self):
@@ -534,11 +590,6 @@ class ContentPipeline(Flow):
         print(f"보관됨. 이유: {result.feedback}")
         return {"status": "archived"}
 
-    @listen("needs_revision")
-    def queue_revision(self, result):
-        print(f"수정 대기열에 추가됨: {result.feedback}")
-        return {"status": "revision_needed"}
-
 
 # Flow 시작 (Slack 응답을 기다리며 일시 중지)
 def start_content_pipeline():
@@ -594,22 +645,22 @@ async def on_slack_feedback_async(flow_id: str, slack_message: str):
 ```python Code
 class ArticleReviewFlow(Flow):
     @start()
-    @human_feedback(
-        message="Review this article draft:",
-        emit=["approved", "needs_revision"],
-        llm="gpt-4o-mini",
-        learn=True,  # HITL 학습 활성화
-    )
     def generate_article(self):
         return self.crew.kickoff(inputs={"topic": "AI Safety"}).raw
 
+    @human_feedback(
+        message="이 글 초안을 검토해 주세요:",
+        emit=["approved", "needs_revision"],
+        llm="gpt-4o-mini",
+        learn=True,
+    )
+    @listen(or_("generate_article", "needs_revision"))
+    def review_article(self):
+        return self.last_human_feedback.output if self.last_human_feedback else "article draft"
+
     @listen("approved")
     def publish(self):
         print(f"Publishing: {self.last_human_feedback.output}")
-
-    @listen("needs_revision")
-    def revise(self):
-        print("Revising based on feedback...")
 ```
 
 **첫 번째 실행**: 인간이 원시 출력을 보고 "사실에 대한 주장에는 항상 인용을 포함하세요."라고 말합니다. 교훈이 추출되어 메모리에 저장됩니다.

docs/pt-BR/enterprise/features/flow-hitl-management.mdx

@@ -38,22 +38,21 @@ O CrewAI Enterprise oferece um sistema abrangente de gerenciamento Human-in-the-
 Configure checkpoints de revisão humana em seus Flows usando o decorador `@human_feedback`. Quando a execução atinge um ponto de revisão, o sistema pausa, notifica o responsável via email e aguarda uma resposta.
 
 ```python
-from crewai.flow.flow import Flow, start, listen
+from crewai.flow.flow import Flow, start, listen, or_
 from crewai.flow.human_feedback import human_feedback, HumanFeedbackResult
 
 class ContentApprovalFlow(Flow):
     @start()
     def generate_content(self):
-        # IA gera conteúdo
         return "Texto de marketing gerado para campanha Q1..."
 
-    @listen(generate_content)
     @human_feedback(
         message="Por favor, revise este conteúdo para conformidade com a marca:",
         emit=["approved", "rejected", "needs_revision"],
     )
-    def review_content(self, content):
-        return content
+    @listen(or_("generate_content", "needs_revision"))
+    def review_content(self):
+        return "Texto de marketing para revisão..."
 
     @listen("approved")
     def publish_content(self, result: HumanFeedbackResult):
@@ -62,10 +61,6 @@ class ContentApprovalFlow(Flow):
     @listen("rejected")
     def archive_content(self, result: HumanFeedbackResult):
         print(f"Conteúdo rejeitado. Motivo: {result.feedback}")
-
-    @listen("needs_revision")
-    def revise_content(self, result: HumanFeedbackResult):
-        print(f"Revisão solicitada: {result.feedback}")
 ```
 
 Para detalhes completos de implementação, consulte o guia [Feedback Humano em Flows](/pt-BR/learn/human-feedback-in-flows).

docs/pt-BR/learn/human-feedback-in-flows.mdx

@@ -98,33 +98,43 @@ def handle_feedback(self, result):
 Quando você especifica `emit`, o decorador se torna um roteador. O feedback livre do humano é interpretado por um LLM e mapeado para um dos outcomes especificados:
 
 ```python Code
-@start()
-@human_feedback(
-    message="Você aprova este conteúdo para publicação?",
-    emit=["approved", "rejected", "needs_revision"],
-    llm="gpt-4o-mini",
-    default_outcome="needs_revision",
-)
-def review_content(self):
-    return "Rascunho do post do blog aqui..."
+from crewai.flow.flow import Flow, start, listen, or_
+from crewai.flow.human_feedback import human_feedback
 
-@listen("approved")
-def publish(self, result):
-    print(f"Publicando! Usuário disse: {result.feedback}")
+class ReviewFlow(Flow):
+    @start()
+    def generate_content(self):
+        return "Rascunho do post do blog aqui..."
 
-@listen("rejected")
-def discard(self, result):
-    print(f"Descartando. Motivo: {result.feedback}")
+    @human_feedback(
+        message="Você aprova este conteúdo para publicação?",
+        emit=["approved", "rejected", "needs_revision"],
+        llm="gpt-4o-mini",
+        default_outcome="needs_revision",
+    )
+    @listen(or_("generate_content", "needs_revision"))
+    def review_content(self):
+        return "Rascunho do post do blog aqui..."
 
-@listen("needs_revision")
-def revise(self, result):
-    print(f"Revisando baseado em: {result.feedback}")
+    @listen("approved")
+    def publish(self, result):
+        print(f"Publicando! Usuário disse: {result.feedback}")
+
+    @listen("rejected")
+    def discard(self, result):
+        print(f"Descartando. Motivo: {result.feedback}")
 ```
 
+Quando o humano diz algo como "precisa de mais detalhes", o LLM mapeia para `"needs_revision"`, que dispara `review_content` novamente via `or_()` — criando um loop de revisão. O loop continua até que o outcome seja `"approved"` ou `"rejected"`.
+
 <Tip>
 O LLM usa saídas estruturadas (function calling) quando disponível para garantir que a resposta seja um dos seus outcomes especificados. Isso torna o roteamento confiável e previsível.
 </Tip>
 
+<Warning>
+Um método `@start()` só executa uma vez no início do flow. Se você precisa de um loop de revisão, separe o método start do método de revisão e use `@listen(or_("trigger", "revision_outcome"))` no método de revisão para habilitar o self-loop.
+</Warning>
+
 ## HumanFeedbackResult
 
 O dataclass `HumanFeedbackResult` contém todas as informações sobre uma interação de feedback humano:
@@ -193,116 +203,162 @@ Aqui está um exemplo completo implementando um fluxo de revisão e aprovação
 <CodeGroup>
 
 ```python Code
-from crewai.flow.flow import Flow, start, listen
+from crewai.flow.flow import Flow, start, listen, or_
 from crewai.flow.human_feedback import human_feedback, HumanFeedbackResult
 from pydantic import BaseModel
 
 
 class ContentState(BaseModel):
-    topic: str = ""
     draft: str = ""
-    final_content: str = ""
     revision_count: int = 0
+    status: str = "pending"
 
 
 class ContentApprovalFlow(Flow[ContentState]):
-    """Um flow que gera conteúdo e obtém aprovação humana."""
+    """Um flow que gera conteúdo e faz loop até o humano aprovar."""
 
     @start()
-    def get_topic(self):
-        self.state.topic = input("Sobre qual tópico devo escrever? ")
-        return self.state.topic
-
-    @listen(get_topic)
-    def generate_draft(self, topic):
-        # Em uso real, isso chamaria um LLM
-        self.state.draft = f"# {topic}\n\nEste é um rascunho sobre {topic}..."
+    def generate_draft(self):
+        self.state.draft = "# IA Segura\n\nEste é um rascunho sobre IA Segura..."
         return self.state.draft
 
-    @listen(generate_draft)
     @human_feedback(
-        message="Por favor, revise este rascunho. Responda 'approved', 'rejected', ou forneça feedback de revisão:",
+        message="Por favor, revise este rascunho. Aprove, rejeite ou descreva o que precisa mudar:",
         emit=["approved", "rejected", "needs_revision"],
         llm="gpt-4o-mini",
         default_outcome="needs_revision",
     )
-    def review_draft(self, draft):
-        return draft
+    @listen(or_("generate_draft", "needs_revision"))
+    def review_draft(self):
+        self.state.revision_count += 1
+        return f"{self.state.draft} (v{self.state.revision_count})"
 
     @listen("approved")
     def publish_content(self, result: HumanFeedbackResult):
-        self.state.final_content = result.output
-        print("\n✅ Conteúdo aprovado e publicado!")
-        print(f"Comentário do revisor: {result.feedback}")
+        self.state.status = "published"
+        print(f"Conteúdo aprovado e publicado! Revisor disse: {result.feedback}")
         return "published"
 
     @listen("rejected")
     def handle_rejection(self, result: HumanFeedbackResult):
-        print("\n❌ Conteúdo rejeitado")
-        print(f"Motivo: {result.feedback}")
+        self.state.status = "rejected"
+        print(f"Conteúdo rejeitado. Motivo: {result.feedback}")
         return "rejected"
 
-    @listen("needs_revision")
-    def revise_content(self, result: HumanFeedbackResult):
-        self.state.revision_count += 1
-        print(f"\n📝 Revisão #{self.state.revision_count} solicitada")
-        print(f"Feedback: {result.feedback}")
 
-        # Em um flow real, você pode voltar para generate_draft
-        # Para este exemplo, apenas reconhecemos
-        return "revision_requested"
-
-
-# Executar o flow
 flow = ContentApprovalFlow()
 result = flow.kickoff()
-print(f"\nFlow concluído. Revisões solicitadas: {flow.state.revision_count}")
+print(f"\nFlow finalizado. Status: {flow.state.status}, Revisões: {flow.state.revision_count}")
 ```
 
 ```text Output
-Sobre qual tópico devo escrever? Segurança em IA
+==================================================
+OUTPUT FOR REVIEW:
+==================================================
+# IA Segura
+
+Este é um rascunho sobre IA Segura... (v1)
+==================================================
+
+Por favor, revise este rascunho. Aprove, rejeite ou descreva o que precisa mudar:
+(Press Enter to skip, or type your feedback)
+
+Your feedback: Preciso de mais detalhes sobre segurança em IA.
 
 ==================================================
 OUTPUT FOR REVIEW:
 ==================================================
-# Segurança em IA
+# IA Segura
 
-Este é um rascunho sobre Segurança em IA...
+Este é um rascunho sobre IA Segura... (v2)
 ==================================================
 
-Por favor, revise este rascunho. Responda 'approved', 'rejected', ou forneça feedback de revisão:
+Por favor, revise este rascunho. Aprove, rejeite ou descreva o que precisa mudar:
 (Press Enter to skip, or type your feedback)
 
 Your feedback: Parece bom, aprovado!
 
-✅ Conteúdo aprovado e publicado!
-Comentário do revisor: Parece bom, aprovado!
+Conteúdo aprovado e publicado! Revisor disse: Parece bom, aprovado!
 
-Flow concluído. Revisões solicitadas: 0
+Flow finalizado. Status: published, Revisões: 2
 ```
 
 </CodeGroup>
 
 ## Combinando com Outros Decoradores
 
-O decorador `@human_feedback` funciona com outros decoradores de flow. Coloque-o como o decorador mais interno (mais próximo da função):
+O decorador `@human_feedback` funciona com `@start()`, `@listen()` e `or_()`. Ambas as ordens de decoradores funcionam — o framework propaga atributos em ambas as direções — mas os padrões recomendados são:
 
 ```python Code
-# Correto: @human_feedback é o mais interno (mais próximo da função)
+# Revisão única no início do flow (sem self-loop)
 @start()
-@human_feedback(message="Revise isto:")
+@human_feedback(message="Revise isto:", emit=["approved", "rejected"], llm="gpt-4o-mini")
 def my_start_method(self):
     return "content"
 
+# Revisão linear em um listener (sem self-loop)
 @listen(other_method)
-@human_feedback(message="Revise isto também:")
+@human_feedback(message="Revise isto também:", emit=["good", "bad"], llm="gpt-4o-mini")
 def my_listener(self, data):
     return f"processed: {data}"
+
+# Self-loop: revisão que pode voltar para revisões
+@human_feedback(message="Aprovar ou revisar?", emit=["approved", "revise"], llm="gpt-4o-mini")
+@listen(or_("upstream_method", "revise"))
+def review_with_loop(self):
+    return "content for review"
 ```
 
-<Tip>
-Coloque `@human_feedback` como o decorador mais interno (último/mais próximo da função) para que ele envolva o método diretamente e possa capturar o valor de retorno antes de passar para o sistema de flow.
-</Tip>
+### Padrão de self-loop
+
+Para criar um loop de revisão, o método de revisão deve escutar **ambos** um gatilho upstream e seu próprio outcome de revisão usando `or_()`:
+
+```python Code
+@start()
+def generate(self):
+    return "initial draft"
+
+@human_feedback(
+    message="Aprovar ou solicitar alterações?",
+    emit=["revise", "approved"],
+    llm="gpt-4o-mini",
+    default_outcome="approved",
+)
+@listen(or_("generate", "revise"))
+def review(self):
+    return "content"
+
+@listen("approved")
+def publish(self):
+    return "published"
+```
+
+Quando o outcome é `"revise"`, o flow roteia de volta para `review` (porque ele escuta `"revise"` via `or_()`). Quando o outcome é `"approved"`, o flow continua para `publish`. Isso funciona porque o engine de flow isenta roteadores da regra "fire once", permitindo que eles re-executem em cada iteração do loop.
+
+### Roteadores encadeados
+
+Um listener disparado pelo outcome de um roteador pode ser ele mesmo um roteador:
+
+```python Code
+@start()
+@human_feedback(message="Primeira revisão:", emit=["approved", "rejected"], llm="gpt-4o-mini")
+def draft(self):
+    return "draft content"
+
+@listen("approved")
+@human_feedback(message="Revisão final:", emit=["publish", "revise"], llm="gpt-4o-mini")
+def final_review(self, prev):
+    return "final content"
+
+@listen("publish")
+def on_publish(self, prev):
+    return "published"
+```
+
+### Limitações
+
+- **Métodos `@start()` executam uma vez**: Um método `@start()` não pode fazer self-loop. Se você precisa de um ciclo de revisão, use um método `@start()` separado como ponto de entrada e coloque o `@human_feedback` em um método `@listen()`.
+- **Sem `@start()` + `@listen()` no mesmo método**: Esta é uma restrição do framework de Flow. Um método é ou um ponto de início ou um listener, não ambos.
 
 ## Melhores Práticas
 
@@ -516,9 +572,9 @@ class ContentPipeline(Flow):
     @start()
     @human_feedback(
         message="Aprova este conteúdo para publicação?",
-        emit=["approved", "rejected", "needs_revision"],
+        emit=["approved", "rejected"],
         llm="gpt-4o-mini",
-        default_outcome="needs_revision",
+        default_outcome="rejected",
         provider=SlackNotificationProvider("#content-reviews"),
     )
     def generate_content(self):
@@ -534,11 +590,6 @@ class ContentPipeline(Flow):
         print(f"Arquivado. Motivo: {result.feedback}")
         return {"status": "archived"}
 
-    @listen("needs_revision")
-    def queue_revision(self, result):
-        print(f"Na fila para revisão: {result.feedback}")
-        return {"status": "revision_needed"}
-
 
 # Iniciando o flow (vai pausar e aguardar resposta do Slack)
 def start_content_pipeline():
@@ -594,22 +645,22 @@ Com o tempo, o humano vê saídas pré-revisadas progressivamente melhores porqu
 ```python Code
 class ArticleReviewFlow(Flow):
     @start()
+    def generate_article(self):
+        return self.crew.kickoff(inputs={"topic": "AI Safety"}).raw
+
     @human_feedback(
-        message="Review this article draft:",
+        message="Revise este rascunho do artigo:",
         emit=["approved", "needs_revision"],
         llm="gpt-4o-mini",
         learn=True,  # enable HITL learning
     )
-    def generate_article(self):
-        return self.crew.kickoff(inputs={"topic": "AI Safety"}).raw
+    @listen(or_("generate_article", "needs_revision"))
+    def review_article(self):
+        return self.last_human_feedback.output if self.last_human_feedback else "article draft"
 
     @listen("approved")
     def publish(self):
         print(f"Publishing: {self.last_human_feedback.output}")
-
-    @listen("needs_revision")
-    def revise(self):
-        print("Revising based on feedback...")
 ```
 
 **Primeira execução**: O humano vê a saída bruta e diz "Sempre inclua citações para afirmações factuais." A lição é destilada e armazenada na memória.

lib/crewai/pyproject.toml

@@ -38,6 +38,7 @@ dependencies = [
     "json5~=0.10.0",
     "portalocker~=2.7.0",
     "pydantic-settings~=2.10.1",
+    "httpx~=0.28.1",
     "mcp~=1.26.0",
     "uv~=0.9.13",
     "aiosqlite~=0.21.0",

lib/crewai/src/crewai/__init__.py

@@ -4,6 +4,7 @@ import urllib.request
 import warnings
 
 from crewai.agent.core import Agent
+from crewai.agent.planning_config import PlanningConfig
 from crewai.crew import Crew
 from crewai.crews.crew_output import CrewOutput
 from crewai.flow.flow import Flow
@@ -82,6 +83,7 @@ __all__ = [
     "Knowledge",
     "LLMGuardrail",
     "Memory",
+    "PlanningConfig",
     "Process",
     "Task",
     "TaskOutput",

lib/crewai/src/crewai/agent/core.py

@@ -24,6 +24,7 @@ from pydantic import (
 )
 from typing_extensions import Self
 
+from crewai.agent.planning_config import PlanningConfig
 from crewai.agent.utils import (
     ahandle_knowledge_retrieval,
     apply_training_data,
@@ -211,13 +212,23 @@ class Agent(BaseAgent):
         default="safe",
         description="Mode for code execution: 'safe' (using Docker) or 'unsafe' (direct execution).",
     )
-    reasoning: bool = Field(
+    planning_config: PlanningConfig | None = Field(
+        default=None,
+        description="Configuration for agent planning before task execution.",
+    )
+    planning: bool = Field(
         default=False,
         description="Whether the agent should reflect and create a plan before executing a task.",
     )
+    reasoning: bool = Field(
+        default=False,
+        description="[DEPRECATED: Use planning_config instead] Whether the agent should reflect and create a plan before executing a task.",
+        deprecated=True,
+    )
     max_reasoning_attempts: int | None = Field(
         default=None,
-        description="Maximum number of reasoning attempts before executing the task. If None, will try until ready.",
+        description="[DEPRECATED: Use planning_config.max_attempts instead] Maximum number of reasoning attempts before executing the task. If None, will try until ready.",
+        deprecated=True,
     )
     embedder: EmbedderConfig | None = Field(
         default=None,
@@ -284,8 +295,26 @@ class Agent(BaseAgent):
         if self.allow_code_execution:
             self._validate_docker_installation()
 
+        # Handle backward compatibility: convert reasoning=True to planning_config
+        if self.reasoning and self.planning_config is None:
+            import warnings
+
+            warnings.warn(
+                "The 'reasoning' parameter is deprecated. Use 'planning_config=PlanningConfig()' instead.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+            self.planning_config = PlanningConfig(
+                max_attempts=self.max_reasoning_attempts,
+            )
+
         return self
 
+    @property
+    def planning_enabled(self) -> bool:
+        """Check if planning is enabled for this agent."""
+        return self.planning_config is not None or self.planning
+
     def _setup_agent_executor(self) -> None:
         if not self.cache_handler:
             self.cache_handler = CacheHandler()
@@ -354,7 +383,11 @@ class Agent(BaseAgent):
             ValueError: If the max execution time is not a positive integer.
             RuntimeError: If the agent execution fails for other reasons.
         """
-        handle_reasoning(self, task)
+        # Only call handle_reasoning for legacy CrewAgentExecutor
+        # For AgentExecutor, planning is handled in AgentExecutor.generate_plan()
+        if self.executor_class is not AgentExecutor:
+            handle_reasoning(self, task)
+
         self._inject_date_to_task(task)
 
         if self.tools_handler:
@@ -592,7 +625,10 @@ class Agent(BaseAgent):
             ValueError: If the max execution time is not a positive integer.
             RuntimeError: If the agent execution fails for other reasons.
         """
-        handle_reasoning(self, task)
+        if self.executor_class is not AgentExecutor:
+            handle_reasoning(
+                self, task
+            )  # we need this till CrewAgentExecutor migrates to AgentExecutor
         self._inject_date_to_task(task)
 
         if self.tools_handler:

lib/crewai/src/crewai/agent/planning_config.py

@@ -0,0 +1,83 @@
+from __future__ import annotations
+
+from typing import Any
+
+from pydantic import BaseModel, Field
+
+
+class PlanningConfig(BaseModel):
+    """Configuration for agent planning/reasoning before task execution.
+
+    This allows users to customize the planning behavior including prompts,
+    iteration limits, and the LLM used for planning.
+
+    Note: To disable planning, don't pass a planning_config or set planning=False
+    on the Agent. The presence of a PlanningConfig enables planning.
+
+    Attributes:
+        max_attempts: Maximum number of planning refinement attempts.
+            If None, will continue until the agent indicates readiness.
+        max_steps: Maximum number of steps in the generated plan.
+        system_prompt: Custom system prompt for planning. Uses default if None.
+        plan_prompt: Custom prompt for creating the initial plan.
+        refine_prompt: Custom prompt for refining the plan.
+        llm: LLM to use for planning. Uses agent's LLM if None.
+
+    Example:
+        ```python
+        from crewai import Agent
+        from crewai.agent.planning_config import PlanningConfig
+
+        # Simple usage
+        agent = Agent(
+            role="Researcher",
+            goal="Research topics",
+            backstory="Expert researcher",
+            planning_config=PlanningConfig(),
+        )
+
+        # Customized planning
+        agent = Agent(
+            role="Researcher",
+            goal="Research topics",
+            backstory="Expert researcher",
+            planning_config=PlanningConfig(
+                max_attempts=3,
+                max_steps=10,
+                plan_prompt="Create a focused plan for: {description}",
+                llm="gpt-4o-mini",  # Use cheaper model for planning
+            ),
+        )
+        ```
+    """
+
+    max_attempts: int | None = Field(
+        default=None,
+        description=(
+            "Maximum number of planning refinement attempts. "
+            "If None, will continue until the agent indicates readiness."
+        ),
+    )
+    max_steps: int = Field(
+        default=20,
+        description="Maximum number of steps in the generated plan.",
+        ge=1,
+    )
+    system_prompt: str | None = Field(
+        default=None,
+        description="Custom system prompt for planning. Uses default if None.",
+    )
+    plan_prompt: str | None = Field(
+        default=None,
+        description="Custom prompt for creating the initial plan.",
+    )
+    refine_prompt: str | None = Field(
+        default=None,
+        description="Custom prompt for refining the plan.",
+    )
+    llm: str | Any | None = Field(
+        default=None,
+        description="LLM to use for planning. Uses agent's LLM if None.",
+    )
+
+    model_config = {"arbitrary_types_allowed": True}

lib/crewai/src/crewai/agent/utils.py

@@ -28,13 +28,20 @@ if TYPE_CHECKING:
 
 
 def handle_reasoning(agent: Agent, task: Task) -> None:
-    """Handle the reasoning process for an agent before task execution.
+    """Handle the reasoning/planning process for an agent before task execution.
+
+    This function checks if planning is enabled for the agent and, if so,
+    creates a plan that gets appended to the task description.
+
+    Note: This function is used by CrewAgentExecutor (legacy path).
+    For AgentExecutor, planning is handled in AgentExecutor.generate_plan().
 
     Args:
         agent: The agent performing the task.
         task: The task to execute.
     """
-    if not agent.reasoning:
+    # Check if planning is enabled using the planning_enabled property
+    if not getattr(agent, "planning_enabled", False):
         return
 
     try:
@@ -43,13 +50,13 @@ def handle_reasoning(agent: Agent, task: Task) -> None:
             AgentReasoningOutput,
         )
 
-        reasoning_handler = AgentReasoning(task=task, agent=agent)
-        reasoning_output: AgentReasoningOutput = (
-            reasoning_handler.handle_agent_reasoning()
+        planning_handler = AgentReasoning(agent=agent, task=task)
+        planning_output: AgentReasoningOutput = (
+            planning_handler.handle_agent_reasoning()
         )
-        task.description += f"\n\nReasoning Plan:\n{reasoning_output.plan.plan}"
+        task.description += f"\n\nPlanning:\n{planning_output.plan.plan}"
     except Exception as e:
-        agent._logger.log("error", f"Error during reasoning process: {e!s}")
+        agent._logger.log("error", f"Error during planning: {e!s}")
 
 
 def build_task_prompt_with_schema(task: Task, task_prompt: str, i18n: I18N) -> str:

lib/crewai/src/crewai/agents/crew_agent_executor.py

@@ -6,7 +6,10 @@ and memory management.
 
 from __future__ import annotations
 
+import asyncio
 from collections.abc import Callable
+from concurrent.futures import ThreadPoolExecutor, as_completed
+import inspect
 import logging
 from typing import TYPE_CHECKING, Any, Literal, cast
 
@@ -685,30 +688,142 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         Returns:
             AgentFinish if tool has result_as_answer=True, None otherwise.
         """
-        from datetime import datetime
-        import json
-
-        from crewai.events import crewai_event_bus
-        from crewai.events.types.tool_usage_events import (
-            ToolUsageErrorEvent,
-            ToolUsageFinishedEvent,
-            ToolUsageStartedEvent,
-        )
-
         if not tool_calls:
             return None
 
-        # Only process the FIRST tool call for sequential execution with reflection
-        tool_call = tool_calls[0]
+        parsed_calls = [
+            parsed
+            for tool_call in tool_calls
+            if (parsed := self._parse_native_tool_call(tool_call)) is not None
+        ]
+        if not parsed_calls:
+            return None
 
-        # Extract tool call info - handle OpenAI-style, Anthropic-style, and Gemini-style
+        original_tools_by_name: dict[str, Any] = {}
+        for tool in self.original_tools or []:
+            original_tools_by_name[sanitize_tool_name(tool.name)] = tool
+
+        if len(parsed_calls) > 1:
+            has_result_as_answer_in_batch = any(
+                bool(
+                    original_tools_by_name.get(func_name)
+                    and getattr(
+                        original_tools_by_name.get(func_name), "result_as_answer", False
+                    )
+                )
+                for _, func_name, _ in parsed_calls
+            )
+            has_max_usage_count_in_batch = any(
+                bool(
+                    original_tools_by_name.get(func_name)
+                    and getattr(
+                        original_tools_by_name.get(func_name),
+                        "max_usage_count",
+                        None,
+                    )
+                    is not None
+                )
+                for _, func_name, _ in parsed_calls
+            )
+
+            # Preserve historical sequential behavior for result_as_answer batches.
+            # Also avoid threading around usage counters for max_usage_count tools.
+            if has_result_as_answer_in_batch or has_max_usage_count_in_batch:
+                logger.debug(
+                    "Skipping parallel native execution because batch includes result_as_answer or max_usage_count tool"
+                )
+            else:
+                execution_plan: list[
+                    tuple[str, str, str | dict[str, Any], Any | None]
+                ] = []
+                for call_id, func_name, func_args in parsed_calls:
+                    original_tool = original_tools_by_name.get(func_name)
+                    execution_plan.append(
+                        (call_id, func_name, func_args, original_tool)
+                    )
+
+                self._append_assistant_tool_calls_message(
+                    [
+                        (call_id, func_name, func_args)
+                        for call_id, func_name, func_args, _ in execution_plan
+                    ]
+                )
+
+                max_workers = min(8, len(execution_plan))
+                ordered_results: list[dict[str, Any] | None] = [None] * len(
+                    execution_plan
+                )
+                with ThreadPoolExecutor(max_workers=max_workers) as pool:
+                    futures = {
+                        pool.submit(
+                            self._execute_single_native_tool_call,
+                            call_id=call_id,
+                            func_name=func_name,
+                            func_args=func_args,
+                            available_functions=available_functions,
+                            original_tool=original_tool,
+                            should_execute=True,
+                        ): idx
+                        for idx, (
+                            call_id,
+                            func_name,
+                            func_args,
+                            original_tool,
+                        ) in enumerate(execution_plan)
+                    }
+                    for future in as_completed(futures):
+                        idx = futures[future]
+                        ordered_results[idx] = future.result()
+
+                for execution_result in ordered_results:
+                    if not execution_result:
+                        continue
+                    tool_finish = self._append_tool_result_and_check_finality(
+                        execution_result
+                    )
+                    if tool_finish:
+                        return tool_finish
+
+                reasoning_prompt = self._i18n.slice("post_tool_reasoning")
+                reasoning_message: LLMMessage = {
+                    "role": "user",
+                    "content": reasoning_prompt,
+                }
+                self.messages.append(reasoning_message)
+                return None
+
+        # Sequential behavior: process only first tool call, then force reflection.
+        call_id, func_name, func_args = parsed_calls[0]
+        self._append_assistant_tool_calls_message([(call_id, func_name, func_args)])
+
+        execution_result = self._execute_single_native_tool_call(
+            call_id=call_id,
+            func_name=func_name,
+            func_args=func_args,
+            available_functions=available_functions,
+            original_tool=original_tools_by_name.get(func_name),
+            should_execute=True,
+        )
+        tool_finish = self._append_tool_result_and_check_finality(execution_result)
+        if tool_finish:
+            return tool_finish
+
+        reasoning_prompt = self._i18n.slice("post_tool_reasoning")
+        reasoning_message = {
+            "role": "user",
+            "content": reasoning_prompt,
+        }
+        self.messages.append(reasoning_message)
+        return None
+
+    def _parse_native_tool_call(
+        self, tool_call: Any
+    ) -> tuple[str, str, str | dict[str, Any]] | None:
         if hasattr(tool_call, "function"):
-            # OpenAI-style: has .function.name and .function.arguments
             call_id = getattr(tool_call, "id", f"call_{id(tool_call)}")
             func_name = sanitize_tool_name(tool_call.function.name)
-            func_args = tool_call.function.arguments
-        elif hasattr(tool_call, "function_call") and tool_call.function_call:
-            # Gemini-style: has .function_call.name and .function_call.args
+            return call_id, func_name, tool_call.function.arguments
+        if hasattr(tool_call, "function_call") and tool_call.function_call:
             call_id = f"call_{id(tool_call)}"
             func_name = sanitize_tool_name(tool_call.function_call.name)
             func_args = (
@@ -716,13 +831,12 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                 if tool_call.function_call.args
                 else {}
             )
-        elif hasattr(tool_call, "name") and hasattr(tool_call, "input"):
-            # Anthropic format: has .name and .input (ToolUseBlock)
+            return call_id, func_name, func_args
+        if hasattr(tool_call, "name") and hasattr(tool_call, "input"):
             call_id = getattr(tool_call, "id", f"call_{id(tool_call)}")
             func_name = sanitize_tool_name(tool_call.name)
-            func_args = tool_call.input  # Already a dict in Anthropic
-        elif isinstance(tool_call, dict):
-            # Support OpenAI "id", Bedrock "toolUseId", or generate one
+            return call_id, func_name, tool_call.input
+        if isinstance(tool_call, dict):
             call_id = (
                 tool_call.get("id")
                 or tool_call.get("toolUseId")
@@ -733,10 +847,15 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                 func_info.get("name", "") or tool_call.get("name", "")
             )
             func_args = func_info.get("arguments", "{}") or tool_call.get("input", {})
-        else:
-            return None
+            return call_id, func_name, func_args
+        return None
+
+    def _append_assistant_tool_calls_message(
+        self,
+        parsed_calls: list[tuple[str, str, str | dict[str, Any]]],
+    ) -> None:
+        import json
 
-        # Append assistant message with single tool call
         assistant_message: LLMMessage = {
             "role": "assistant",
             "content": None,
@@ -751,12 +870,30 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         else json.dumps(func_args),
                     },
                 }
+                for call_id, func_name, func_args in parsed_calls
             ],
         }
-
         self.messages.append(assistant_message)
 
-        # Parse arguments for the single tool call
+    def _execute_single_native_tool_call(
+        self,
+        *,
+        call_id: str,
+        func_name: str,
+        func_args: str | dict[str, Any],
+        available_functions: dict[str, Callable[..., Any]],
+        original_tool: Any | None = None,
+        should_execute: bool = True,
+    ) -> dict[str, Any]:
+        from datetime import datetime
+        import json
+
+        from crewai.events.types.tool_usage_events import (
+            ToolUsageErrorEvent,
+            ToolUsageFinishedEvent,
+            ToolUsageStartedEvent,
+        )
+
         if isinstance(func_args, str):
             try:
                 args_dict = json.loads(func_args)
@@ -765,28 +902,26 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         else:
             args_dict = func_args
 
-        agent_key = getattr(self.agent, "key", "unknown") if self.agent else "unknown"
+        if original_tool is None:
+            for tool in self.original_tools or []:
+                if sanitize_tool_name(tool.name) == func_name:
+                    original_tool = tool
+                    break
 
-        # Find original tool by matching sanitized name (needed for cache_function and result_as_answer)
-
-        original_tool = None
-        for tool in self.original_tools or []:
-            if sanitize_tool_name(tool.name) == func_name:
-                original_tool = tool
-                break
-
-        # Check if tool has reached max usage count
         max_usage_reached = False
-        if original_tool:
-            if (
-                hasattr(original_tool, "max_usage_count")
-                and original_tool.max_usage_count is not None
-                and original_tool.current_usage_count >= original_tool.max_usage_count
-            ):
-                max_usage_reached = True
+        if not should_execute and original_tool:
+            max_usage_reached = True
+        elif (
+            should_execute
+            and original_tool
+            and (max_count := getattr(original_tool, "max_usage_count", None))
+            is not None
+            and getattr(original_tool, "current_usage_count", 0) >= max_count
+        ):
+            max_usage_reached = True
 
-        # Check cache before executing
         from_cache = False
+        result: str = "Tool not found"
         input_str = json.dumps(args_dict) if args_dict else ""
         if self.tools_handler and self.tools_handler.cache:
             cached_result = self.tools_handler.cache.read(
@@ -800,7 +935,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                 )
                 from_cache = True
 
-        # Emit tool usage started event
+        agent_key = getattr(self.agent, "key", "unknown") if self.agent else "unknown"
         started_at = datetime.now()
         crewai_event_bus.emit(
             self,
@@ -816,14 +951,12 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
 
         track_delegation_if_needed(func_name, args_dict, self.task)
 
-        # Find the structured tool for hook context
         structured_tool: CrewStructuredTool | None = None
         for structured in self.tools or []:
             if sanitize_tool_name(structured.name) == func_name:
                 structured_tool = structured
                 break
 
-        # Execute before_tool_call hooks
         hook_blocked = False
         before_hook_context = ToolCallHookContext(
             tool_name=func_name,
@@ -847,58 +980,48 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                     color="red",
                 )
 
-        # If hook blocked execution, set result and skip tool execution
         if hook_blocked:
             result = f"Tool execution blocked by hook. Tool: {func_name}"
-        # Execute the tool (only if not cached, not at max usage, and not blocked by hook)
-        elif not from_cache and not max_usage_reached:
-            result = "Tool not found"
-            if func_name in available_functions:
-                try:
-                    tool_func = available_functions[func_name]
-                    raw_result = tool_func(**args_dict)
-
-                    # Add to cache after successful execution (before string conversion)
-                    if self.tools_handler and self.tools_handler.cache:
-                        should_cache = True
-                        if (
-                            original_tool
-                            and hasattr(original_tool, "cache_function")
-                            and callable(original_tool.cache_function)
-                        ):
-                            should_cache = original_tool.cache_function(
-                                args_dict, raw_result
-                            )
-                        if should_cache:
-                            self.tools_handler.cache.add(
-                                tool=func_name, input=input_str, output=raw_result
-                            )
-
-                    # Convert to string for message
-                    result = (
-                        str(raw_result)
-                        if not isinstance(raw_result, str)
-                        else raw_result
-                    )
-                except Exception as e:
-                    result = f"Error executing tool: {e}"
-                    if self.task:
-                        self.task.increment_tools_errors()
-                    crewai_event_bus.emit(
-                        self,
-                        event=ToolUsageErrorEvent(
-                            tool_name=func_name,
-                            tool_args=args_dict,
-                            from_agent=self.agent,
-                            from_task=self.task,
-                            agent_key=agent_key,
-                            error=e,
-                        ),
-                    )
-                    error_event_emitted = True
         elif max_usage_reached and original_tool:
-            # Return error message when max usage limit is reached
             result = f"Tool '{func_name}' has reached its usage limit of {original_tool.max_usage_count} times and cannot be used anymore."
+        elif not from_cache and func_name in available_functions:
+            try:
+                raw_result = available_functions[func_name](**args_dict)
+
+                if self.tools_handler and self.tools_handler.cache:
+                    should_cache = True
+                    if (
+                        original_tool
+                        and hasattr(original_tool, "cache_function")
+                        and callable(original_tool.cache_function)
+                    ):
+                        should_cache = original_tool.cache_function(
+                            args_dict, raw_result
+                        )
+                    if should_cache:
+                        self.tools_handler.cache.add(
+                            tool=func_name, input=input_str, output=raw_result
+                        )
+
+                result = (
+                    str(raw_result) if not isinstance(raw_result, str) else raw_result
+                )
+            except Exception as e:
+                result = f"Error executing tool: {e}"
+                if self.task:
+                    self.task.increment_tools_errors()
+                crewai_event_bus.emit(
+                    self,
+                    event=ToolUsageErrorEvent(
+                        tool_name=func_name,
+                        tool_args=args_dict,
+                        from_agent=self.agent,
+                        from_task=self.task,
+                        agent_key=agent_key,
+                        error=e,
+                    ),
+                )
+                error_event_emitted = True
 
         after_hook_context = ToolCallHookContext(
             tool_name=func_name,
@@ -938,7 +1061,23 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                 ),
             )
 
-        # Append tool result message
+        return {
+            "call_id": call_id,
+            "func_name": func_name,
+            "result": result,
+            "from_cache": from_cache,
+            "original_tool": original_tool,
+        }
+
+    def _append_tool_result_and_check_finality(
+        self, execution_result: dict[str, Any]
+    ) -> AgentFinish | None:
+        call_id = cast(str, execution_result["call_id"])
+        func_name = cast(str, execution_result["func_name"])
+        result = cast(str, execution_result["result"])
+        from_cache = cast(bool, execution_result["from_cache"])
+        original_tool = execution_result["original_tool"]
+
         tool_message: LLMMessage = {
             "role": "tool",
             "tool_call_id": call_id,
@@ -947,7 +1086,6 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         }
         self.messages.append(tool_message)
 
-        # Log the tool execution
         if self.agent and self.agent.verbose:
             cache_info = " (from cache)" if from_cache else ""
             self._printer.print(
@@ -960,20 +1098,11 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
             and hasattr(original_tool, "result_as_answer")
             and original_tool.result_as_answer
         ):
-            # Return immediately with tool result as final answer
             return AgentFinish(
                 thought="Tool result is the final answer",
                 output=result,
                 text=result,
             )
-
-        # Inject post-tool reasoning prompt to enforce analysis
-        reasoning_prompt = self._i18n.slice("post_tool_reasoning")
-        reasoning_message: LLMMessage = {
-            "role": "user",
-            "content": reasoning_prompt,
-        }
-        self.messages.append(reasoning_message)
         return None
 
     async def ainvoke(self, inputs: dict[str, Any]) -> dict[str, Any]:
@@ -1371,7 +1500,9 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
             formatted_answer: Current agent response.
         """
         if self.step_callback:
-            self.step_callback(formatted_answer)
+            cb_result = self.step_callback(formatted_answer)
+            if inspect.iscoroutine(cb_result):
+                asyncio.run(cb_result)
 
     def _append_message(
         self, text: str, role: Literal["user", "assistant", "system"] = "assistant"

lib/crewai/src/crewai/cli/authentication/main.py

@@ -2,8 +2,8 @@ import time
 from typing import TYPE_CHECKING, Any, TypeVar, cast
 import webbrowser
 
+import httpx
 from pydantic import BaseModel, Field
-import requests
 from rich.console import Console
 
 from crewai.cli.authentication.utils import validate_jwt_token
@@ -98,7 +98,7 @@ class AuthenticationCommand:
             "scope": " ".join(self.oauth2_provider.get_oauth_scopes()),
             "audience": self.oauth2_provider.get_audience(),
         }
-        response = requests.post(
+        response = httpx.post(
             url=self.oauth2_provider.get_authorize_url(),
             data=device_code_payload,
             timeout=20,
@@ -130,7 +130,7 @@ class AuthenticationCommand:
 
         attempts = 0
         while True and attempts < 10:
-            response = requests.post(
+            response = httpx.post(
                 self.oauth2_provider.get_token_url(), data=token_payload, timeout=30
             )
             token_data = response.json()
@@ -149,7 +149,7 @@ class AuthenticationCommand:
                 return
 
             if token_data["error"] not in ("authorization_pending", "slow_down"):
-                raise requests.HTTPError(
+                raise httpx.HTTPError(
                     token_data.get("error_description") or token_data.get("error")
                 )
 

lib/crewai/src/crewai/cli/command.py

@@ -1,5 +1,6 @@
-import requests
-from requests.exceptions import JSONDecodeError
+import json
+
+import httpx
 from rich.console import Console
 
 from crewai.cli.authentication.token import get_auth_token
@@ -30,16 +31,16 @@ class PlusAPIMixin:
             console.print("Run 'crewai login' to sign up/login.", style="bold green")
             raise SystemExit from None
 
-    def _validate_response(self, response: requests.Response) -> None:
+    def _validate_response(self, response: httpx.Response) -> None:
         """
         Handle and display error messages from API responses.
 
         Args:
-            response (requests.Response): The response from the Plus API
+            response (httpx.Response): The response from the Plus API
         """
         try:
             json_response = response.json()
-        except (JSONDecodeError, ValueError):
+        except (json.JSONDecodeError, ValueError):
             console.print(
                 "Failed to parse response from Enterprise API failed. Details:",
                 style="bold red",
@@ -62,7 +63,7 @@ class PlusAPIMixin:
                     )
             raise SystemExit
 
-        if not response.ok:
+        if not response.is_success:
             console.print(
                 "Request to Enterprise API failed. Details:", style="bold red"
             )

lib/crewai/src/crewai/cli/enterprise/main.py

@@ -1,7 +1,7 @@
+import json
 from typing import Any, cast
 
-import requests
-from requests.exceptions import JSONDecodeError, RequestException
+import httpx
 from rich.console import Console
 
 from crewai.cli.authentication.main import Oauth2Settings, ProviderFactory
@@ -47,12 +47,12 @@ class EnterpriseConfigureCommand(BaseCommand):
                 "User-Agent": f"CrewAI-CLI/{get_crewai_version()}",
                 "X-Crewai-Version": get_crewai_version(),
             }
-            response = requests.get(oauth_endpoint, timeout=30, headers=headers)
+            response = httpx.get(oauth_endpoint, timeout=30, headers=headers)
             response.raise_for_status()
 
             try:
                 oauth_config = response.json()
-            except JSONDecodeError as e:
+            except json.JSONDecodeError as e:
                 raise ValueError(f"Invalid JSON response from {oauth_endpoint}") from e
 
             self._validate_oauth_config(oauth_config)
@@ -62,7 +62,7 @@ class EnterpriseConfigureCommand(BaseCommand):
             )
             return cast(dict[str, Any], oauth_config)
 
-        except RequestException as e:
+        except httpx.HTTPError as e:
             raise ValueError(f"Failed to connect to enterprise URL: {e!s}") from e
         except Exception as e:
             raise ValueError(f"Error fetching OAuth2 configuration: {e!s}") from e

lib/crewai/src/crewai/cli/organization/main.py

@@ -1,4 +1,4 @@
-from requests import HTTPError
+from httpx import HTTPStatusError
 from rich.console import Console
 from rich.table import Table
 
@@ -10,11 +10,11 @@ console = Console()
 
 
 class OrganizationCommand(BaseCommand, PlusAPIMixin):
-    def __init__(self):
+    def __init__(self) -> None:
         BaseCommand.__init__(self)
         PlusAPIMixin.__init__(self, telemetry=self._telemetry)
 
-    def list(self):
+    def list(self) -> None:
         try:
             response = self.plus_api_client.get_organizations()
             response.raise_for_status()
@@ -33,7 +33,7 @@ class OrganizationCommand(BaseCommand, PlusAPIMixin):
                 table.add_row(org["name"], org["uuid"])
 
             console.print(table)
-        except HTTPError as e:
+        except HTTPStatusError as e:
             if e.response.status_code == 401:
                 console.print(
                     "You are not logged in to any organization. Use 'crewai login' to login.",
@@ -50,7 +50,7 @@ class OrganizationCommand(BaseCommand, PlusAPIMixin):
             )
             raise SystemExit(1) from e
 
-    def switch(self, org_id):
+    def switch(self, org_id: str) -> None:
         try:
             response = self.plus_api_client.get_organizations()
             response.raise_for_status()
@@ -72,7 +72,7 @@ class OrganizationCommand(BaseCommand, PlusAPIMixin):
                 f"Successfully switched to {org['name']} ({org['uuid']})",
                 style="bold green",
             )
-        except HTTPError as e:
+        except HTTPStatusError as e:
             if e.response.status_code == 401:
                 console.print(
                     "You are not logged in to any organization. Use 'crewai login' to login.",
@@ -87,7 +87,7 @@ class OrganizationCommand(BaseCommand, PlusAPIMixin):
             console.print(f"Failed to switch organization: {e!s}", style="bold red")
             raise SystemExit(1) from e
 
-    def current(self):
+    def current(self) -> None:
         settings = Settings()
         if settings.org_uuid:
             console.print(

lib/crewai/src/crewai/cli/plus_api.py

@@ -3,7 +3,6 @@ from typing import Any
 from urllib.parse import urljoin
 
 import httpx
-import requests
 
 from crewai.cli.config import Settings
 from crewai.cli.constants import DEFAULT_CREWAI_ENTERPRISE_URL
@@ -43,16 +42,16 @@ class PlusAPI:
 
     def _make_request(
         self, method: str, endpoint: str, **kwargs: Any
-    ) -> requests.Response:
+    ) -> httpx.Response:
         url = urljoin(self.base_url, endpoint)
-        session = requests.Session()
-        session.trust_env = False
-        return session.request(method, url, headers=self.headers, **kwargs)
+        verify = kwargs.pop("verify", True)
+        with httpx.Client(trust_env=False, verify=verify) as client:
+            return client.request(method, url, headers=self.headers, **kwargs)
 
-    def login_to_tool_repository(self) -> requests.Response:
+    def login_to_tool_repository(self) -> httpx.Response:
         return self._make_request("POST", f"{self.TOOLS_RESOURCE}/login")
 
-    def get_tool(self, handle: str) -> requests.Response:
+    def get_tool(self, handle: str) -> httpx.Response:
         return self._make_request("GET", f"{self.TOOLS_RESOURCE}/{handle}")
 
     async def get_agent(self, handle: str) -> httpx.Response:
@@ -68,7 +67,7 @@ class PlusAPI:
         description: str | None,
         encoded_file: str,
         available_exports: list[dict[str, Any]] | None = None,
-    ) -> requests.Response:
+    ) -> httpx.Response:
         params = {
             "handle": handle,
             "public": is_public,
@@ -79,54 +78,52 @@ class PlusAPI:
         }
         return self._make_request("POST", f"{self.TOOLS_RESOURCE}", json=params)
 
-    def deploy_by_name(self, project_name: str) -> requests.Response:
+    def deploy_by_name(self, project_name: str) -> httpx.Response:
         return self._make_request(
             "POST", f"{self.CREWS_RESOURCE}/by-name/{project_name}/deploy"
         )
 
-    def deploy_by_uuid(self, uuid: str) -> requests.Response:
+    def deploy_by_uuid(self, uuid: str) -> httpx.Response:
         return self._make_request("POST", f"{self.CREWS_RESOURCE}/{uuid}/deploy")
 
-    def crew_status_by_name(self, project_name: str) -> requests.Response:
+    def crew_status_by_name(self, project_name: str) -> httpx.Response:
         return self._make_request(
             "GET", f"{self.CREWS_RESOURCE}/by-name/{project_name}/status"
         )
 
-    def crew_status_by_uuid(self, uuid: str) -> requests.Response:
+    def crew_status_by_uuid(self, uuid: str) -> httpx.Response:
         return self._make_request("GET", f"{self.CREWS_RESOURCE}/{uuid}/status")
 
     def crew_by_name(
         self, project_name: str, log_type: str = "deployment"
-    ) -> requests.Response:
+    ) -> httpx.Response:
         return self._make_request(
             "GET", f"{self.CREWS_RESOURCE}/by-name/{project_name}/logs/{log_type}"
         )
 
-    def crew_by_uuid(
-        self, uuid: str, log_type: str = "deployment"
-    ) -> requests.Response:
+    def crew_by_uuid(self, uuid: str, log_type: str = "deployment") -> httpx.Response:
         return self._make_request(
             "GET", f"{self.CREWS_RESOURCE}/{uuid}/logs/{log_type}"
         )
 
-    def delete_crew_by_name(self, project_name: str) -> requests.Response:
+    def delete_crew_by_name(self, project_name: str) -> httpx.Response:
         return self._make_request(
             "DELETE", f"{self.CREWS_RESOURCE}/by-name/{project_name}"
         )
 
-    def delete_crew_by_uuid(self, uuid: str) -> requests.Response:
+    def delete_crew_by_uuid(self, uuid: str) -> httpx.Response:
         return self._make_request("DELETE", f"{self.CREWS_RESOURCE}/{uuid}")
 
-    def list_crews(self) -> requests.Response:
+    def list_crews(self) -> httpx.Response:
         return self._make_request("GET", self.CREWS_RESOURCE)
 
-    def create_crew(self, payload: dict[str, Any]) -> requests.Response:
+    def create_crew(self, payload: dict[str, Any]) -> httpx.Response:
         return self._make_request("POST", self.CREWS_RESOURCE, json=payload)
 
-    def get_organizations(self) -> requests.Response:
+    def get_organizations(self) -> httpx.Response:
         return self._make_request("GET", self.ORGANIZATIONS_RESOURCE)
 
-    def initialize_trace_batch(self, payload: dict[str, Any]) -> requests.Response:
+    def initialize_trace_batch(self, payload: dict[str, Any]) -> httpx.Response:
         return self._make_request(
             "POST",
             f"{self.TRACING_RESOURCE}/batches",
@@ -136,7 +133,7 @@ class PlusAPI:
 
     def initialize_ephemeral_trace_batch(
         self, payload: dict[str, Any]
-    ) -> requests.Response:
+    ) -> httpx.Response:
         return self._make_request(
             "POST",
             f"{self.EPHEMERAL_TRACING_RESOURCE}/batches",
@@ -145,7 +142,7 @@ class PlusAPI:
 
     def send_trace_events(
         self, trace_batch_id: str, payload: dict[str, Any]
-    ) -> requests.Response:
+    ) -> httpx.Response:
         return self._make_request(
             "POST",
             f"{self.TRACING_RESOURCE}/batches/{trace_batch_id}/events",
@@ -155,7 +152,7 @@ class PlusAPI:
 
     def send_ephemeral_trace_events(
         self, trace_batch_id: str, payload: dict[str, Any]
-    ) -> requests.Response:
+    ) -> httpx.Response:
         return self._make_request(
             "POST",
             f"{self.EPHEMERAL_TRACING_RESOURCE}/batches/{trace_batch_id}/events",
@@ -165,7 +162,7 @@ class PlusAPI:
 
     def finalize_trace_batch(
         self, trace_batch_id: str, payload: dict[str, Any]
-    ) -> requests.Response:
+    ) -> httpx.Response:
         return self._make_request(
             "PATCH",
             f"{self.TRACING_RESOURCE}/batches/{trace_batch_id}/finalize",
@@ -175,7 +172,7 @@ class PlusAPI:
 
     def finalize_ephemeral_trace_batch(
         self, trace_batch_id: str, payload: dict[str, Any]
-    ) -> requests.Response:
+    ) -> httpx.Response:
         return self._make_request(
             "PATCH",
             f"{self.EPHEMERAL_TRACING_RESOURCE}/batches/{trace_batch_id}/finalize",
@@ -185,7 +182,7 @@ class PlusAPI:
 
     def mark_trace_batch_as_failed(
         self, trace_batch_id: str, error_message: str
-    ) -> requests.Response:
+    ) -> httpx.Response:
         return self._make_request(
             "PATCH",
             f"{self.TRACING_RESOURCE}/batches/{trace_batch_id}",
@@ -193,13 +190,11 @@ class PlusAPI:
             timeout=30,
         )
 
-    def get_triggers(self) -> requests.Response:
+    def get_triggers(self) -> httpx.Response:
         """Get all available triggers from integrations."""
         return self._make_request("GET", f"{self.INTEGRATIONS_RESOURCE}/apps")
 
-    def get_trigger_payload(
-        self, app_slug: str, trigger_slug: str
-    ) -> requests.Response:
+    def get_trigger_payload(self, app_slug: str, trigger_slug: str) -> httpx.Response:
         """Get sample payload for a specific trigger."""
         return self._make_request(
             "GET", f"{self.INTEGRATIONS_RESOURCE}/{app_slug}/{trigger_slug}/payload"

lib/crewai/src/crewai/cli/provider.py

@@ -8,7 +8,7 @@ from typing import Any
 
 import certifi
 import click
-import requests
+import httpx
 
 from crewai.cli.constants import JSON_URL, MODELS, PROVIDERS
 
@@ -165,20 +165,20 @@ def fetch_provider_data(cache_file: Path) -> dict[str, Any] | None:
     ssl_config = os.environ["SSL_CERT_FILE"] = certifi.where()
 
     try:
-        response = requests.get(JSON_URL, stream=True, timeout=60, verify=ssl_config)
-        response.raise_for_status()
-        data = download_data(response)
-        with open(cache_file, "w") as f:
-            json.dump(data, f)
-        return data
-    except requests.RequestException as e:
+        with httpx.stream("GET", JSON_URL, timeout=60, verify=ssl_config) as response:
+            response.raise_for_status()
+            data = download_data(response)
+            with open(cache_file, "w") as f:
+                json.dump(data, f)
+            return data
+    except httpx.HTTPError as e:
         click.secho(f"Error fetching provider data: {e}", fg="red")
     except json.JSONDecodeError:
         click.secho("Error parsing provider data. Invalid JSON format.", fg="red")
     return None
 
 
-def download_data(response: requests.Response) -> dict[str, Any]:
+def download_data(response: httpx.Response) -> dict[str, Any]:
     """Downloads data from a given HTTP response and returns the JSON content.
 
     Args:
@@ -194,7 +194,7 @@ def download_data(response: requests.Response) -> dict[str, Any]:
     with click.progressbar(
         length=total_size, label="Downloading", show_pos=True
     ) as bar:
-        for chunk in response.iter_content(block_size):
+        for chunk in response.iter_bytes(block_size):
             if chunk:
                 data_chunks.append(chunk)
                 bar.update(len(chunk))

lib/crewai/src/crewai/events/types/reasoning_events.py

@@ -9,7 +9,7 @@ class ReasoningEvent(BaseEvent):
     type: str
     attempt: int = 1
     agent_role: str
-    task_id: str
+    task_id: str | None = None
     task_name: str | None = None
     from_task: Any | None = None
     agent_id: str | None = None

lib/crewai/src/crewai/experimental/agent_executor.py

@@ -1,7 +1,10 @@
 from __future__ import annotations
 
+import asyncio
 from collections.abc import Callable, Coroutine
+from concurrent.futures import ThreadPoolExecutor, as_completed
 from datetime import datetime
+import inspect
 import json
 import threading
 from typing import TYPE_CHECKING, Any, Literal, cast
@@ -68,6 +71,7 @@ from crewai.utilities.agent_utils import (
 )
 from crewai.utilities.constants import TRAINING_DATA_FILE
 from crewai.utilities.i18n import I18N, get_i18n
+from crewai.utilities.planning_types import PlanStep, TodoItem, TodoList
 from crewai.utilities.printer import Printer
 from crewai.utilities.string_utils import sanitize_tool_name
 from crewai.utilities.tool_utils import execute_tool_and_check_finality
@@ -101,6 +105,13 @@ class AgentReActState(BaseModel):
     ask_for_human_input: bool = Field(default=False)
     use_native_tools: bool = Field(default=False)
     pending_tool_calls: list[Any] = Field(default_factory=list)
+    plan: str | None = Field(default=None, description="Generated execution plan")
+    plan_ready: bool = Field(
+        default=False, description="Whether agent is ready to execute"
+    )
+    todos: TodoList = Field(
+        default_factory=TodoList, description="Todo list for tracking plan execution"
+    )
 
 
 class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
@@ -389,6 +400,67 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
         self._state.iterations = value
 
     @start()
+    def generate_plan(self) -> None:
+        """Generate execution plan if planning is enabled.
+
+        This is the entry point for the agent execution flow. If planning is
+        enabled on the agent, it generates a plan before execution begins.
+        The plan is stored in state and todos are created from the steps.
+        """
+        if not getattr(self.agent, "planning_enabled", False):
+            return
+
+        try:
+            from crewai.utilities.reasoning_handler import AgentReasoning
+
+            if self.task:
+                planning_handler = AgentReasoning(agent=self.agent, task=self.task)
+            else:
+                # For kickoff() path - use input text directly, no Task needed
+                input_text = getattr(self, "_kickoff_input", "")
+                planning_handler = AgentReasoning(
+                    agent=self.agent,
+                    description=input_text or "Complete the requested task",
+                    expected_output="Complete the task successfully",
+                )
+
+            output = planning_handler.handle_agent_reasoning()
+
+            self.state.plan = output.plan.plan
+            self.state.plan_ready = output.plan.ready
+
+            if self.state.plan_ready and output.plan.steps:
+                self._create_todos_from_plan(output.plan.steps)
+
+            # Backward compatibility: append plan to task description
+            # This can be removed in Phase 2 when plan execution is implemented
+            if self.task and self.state.plan:
+                self.task.description += f"\n\nPlanning:\n{self.state.plan}"
+
+        except Exception as e:
+            if hasattr(self.agent, "_logger"):
+                self.agent._logger.log("error", f"Error during planning: {e!s}")
+
+    def _create_todos_from_plan(self, steps: list[PlanStep]) -> None:
+        """Convert plan steps into trackable todo items.
+
+        Args:
+            steps: List of PlanStep objects from the reasoning handler.
+        """
+        todos: list[TodoItem] = []
+        for step in steps:
+            todo = TodoItem(
+                step_number=step.step_number,
+                description=step.description,
+                tool_to_use=step.tool_to_use,
+                depends_on=step.depends_on,
+                status="pending",
+            )
+            todos.append(todo)
+
+        self.state.todos = TodoList(items=todos)
+
+    @listen(generate_plan)
     def initialize_reasoning(self) -> Literal["initialized"]:
         """Initialize the reasoning flow and emit agent start logs."""
         self._show_start_logs()
@@ -668,9 +740,12 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
         if not self.state.pending_tool_calls:
             return "native_tool_completed"
 
+        pending_tool_calls = list(self.state.pending_tool_calls)
+        self.state.pending_tool_calls.clear()
+
         # Group all tool calls into a single assistant message
         tool_calls_to_report = []
-        for tool_call in self.state.pending_tool_calls:
+        for tool_call in pending_tool_calls:
             info = extract_tool_call_info(tool_call)
             if not info:
                 continue
@@ -695,202 +770,86 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
                 "content": None,
                 "tool_calls": tool_calls_to_report,
             }
-            if all(
-                type(tc).__qualname__ == "Part" for tc in self.state.pending_tool_calls
-            ):
-                assistant_message["raw_tool_call_parts"] = list(
-                    self.state.pending_tool_calls
-                )
+            if all(type(tc).__qualname__ == "Part" for tc in pending_tool_calls):
+                assistant_message["raw_tool_call_parts"] = list(pending_tool_calls)
             self.state.messages.append(assistant_message)
 
-        # Now execute each tool
-        while self.state.pending_tool_calls:
-            tool_call = self.state.pending_tool_calls.pop(0)
-            info = extract_tool_call_info(tool_call)
-            if not info:
-                continue
+        runnable_tool_calls = [
+            tool_call
+            for tool_call in pending_tool_calls
+            if extract_tool_call_info(tool_call) is not None
+        ]
+        should_parallelize = self._should_parallelize_native_tool_calls(
+            runnable_tool_calls
+        )
 
-            call_id, func_name, func_args = info
-
-            # Parse arguments
-            if isinstance(func_args, str):
-                try:
-                    args_dict = json.loads(func_args)
-                except json.JSONDecodeError:
-                    args_dict = {}
-            else:
-                args_dict = func_args
-
-            # Get agent_key for event tracking
-            agent_key = (
-                getattr(self.agent, "key", "unknown") if self.agent else "unknown"
-            )
-
-            # Find original tool by matching sanitized name (needed for cache_function and result_as_answer)
-            original_tool = None
-            for tool in self.original_tools or []:
-                if sanitize_tool_name(tool.name) == func_name:
-                    original_tool = tool
-                    break
-
-            # Check if tool has reached max usage count
-            max_usage_reached = False
-            if (
-                original_tool
-                and original_tool.max_usage_count is not None
-                and original_tool.current_usage_count >= original_tool.max_usage_count
-            ):
-                max_usage_reached = True
-
-            # Check cache before executing
-            from_cache = False
-            input_str = json.dumps(args_dict) if args_dict else ""
-            if self.tools_handler and self.tools_handler.cache:
-                cached_result = self.tools_handler.cache.read(
-                    tool=func_name, input=input_str
+        execution_results: list[dict[str, Any]] = []
+        if should_parallelize:
+            max_workers = min(8, len(runnable_tool_calls))
+            with ThreadPoolExecutor(max_workers=max_workers) as pool:
+                future_to_idx = {
+                    pool.submit(self._execute_single_native_tool_call, tool_call): idx
+                    for idx, tool_call in enumerate(runnable_tool_calls)
+                }
+                ordered_results: list[dict[str, Any] | None] = [None] * len(
+                    runnable_tool_calls
                 )
-                if cached_result is not None:
-                    result = (
-                        str(cached_result)
-                        if not isinstance(cached_result, str)
-                        else cached_result
-                    )
-                    from_cache = True
+                for future in as_completed(future_to_idx):
+                    idx = future_to_idx[future]
+                    ordered_results[idx] = future.result()
+                execution_results = [
+                    result for result in ordered_results if result is not None
+                ]
+        else:
+            # Execute sequentially so result_as_answer tools can short-circuit
+            # immediately without running remaining calls.
+            for tool_call in runnable_tool_calls:
+                execution_result = self._execute_single_native_tool_call(tool_call)
+                call_id = cast(str, execution_result["call_id"])
+                func_name = cast(str, execution_result["func_name"])
+                result = cast(str, execution_result["result"])
+                from_cache = cast(bool, execution_result["from_cache"])
+                original_tool = execution_result["original_tool"]
 
-            # Emit tool usage started event
-            started_at = datetime.now()
-            crewai_event_bus.emit(
-                self,
-                event=ToolUsageStartedEvent(
-                    tool_name=func_name,
-                    tool_args=args_dict,
-                    from_agent=self.agent,
-                    from_task=self.task,
-                    agent_key=agent_key,
-                ),
-            )
-            error_event_emitted = False
+                tool_message: LLMMessage = {
+                    "role": "tool",
+                    "tool_call_id": call_id,
+                    "name": func_name,
+                    "content": result,
+                }
+                self.state.messages.append(tool_message)
 
-            track_delegation_if_needed(func_name, args_dict, self.task)
-
-            structured_tool: CrewStructuredTool | None = None
-            for structured in self.tools or []:
-                if sanitize_tool_name(structured.name) == func_name:
-                    structured_tool = structured
-                    break
-
-            hook_blocked = False
-            before_hook_context = ToolCallHookContext(
-                tool_name=func_name,
-                tool_input=args_dict,
-                tool=structured_tool,  # type: ignore[arg-type]
-                agent=self.agent,
-                task=self.task,
-                crew=self.crew,
-            )
-            before_hooks = get_before_tool_call_hooks()
-            try:
-                for hook in before_hooks:
-                    hook_result = hook(before_hook_context)
-                    if hook_result is False:
-                        hook_blocked = True
-                        break
-            except Exception as hook_error:
-                if self.agent.verbose:
+                # Log the tool execution
+                if self.agent and self.agent.verbose:
+                    cache_info = " (from cache)" if from_cache else ""
                     self._printer.print(
-                        content=f"Error in before_tool_call hook: {hook_error}",
-                        color="red",
+                        content=f"Tool {func_name} executed with result{cache_info}: {result[:200]}...",
+                        color="green",
                     )
 
-            if hook_blocked:
-                result = f"Tool execution blocked by hook. Tool: {func_name}"
-            elif not from_cache and not max_usage_reached:
-                result = "Tool not found"
-                if func_name in self._available_functions:
-                    try:
-                        tool_func = self._available_functions[func_name]
-                        raw_result = tool_func(**args_dict)
-
-                        # Add to cache after successful execution (before string conversion)
-                        if self.tools_handler and self.tools_handler.cache:
-                            should_cache = True
-                            if original_tool:
-                                should_cache = original_tool.cache_function(
-                                    args_dict, raw_result
-                                )
-                            if should_cache:
-                                self.tools_handler.cache.add(
-                                    tool=func_name, input=input_str, output=raw_result
-                                )
-
-                        # Convert to string for message
-                        result = (
-                            str(raw_result)
-                            if not isinstance(raw_result, str)
-                            else raw_result
-                        )
-                    except Exception as e:
-                        result = f"Error executing tool: {e}"
-                        if self.task:
-                            self.task.increment_tools_errors()
-                        # Emit tool usage error event
-                        crewai_event_bus.emit(
-                            self,
-                            event=ToolUsageErrorEvent(
-                                tool_name=func_name,
-                                tool_args=args_dict,
-                                from_agent=self.agent,
-                                from_task=self.task,
-                                agent_key=agent_key,
-                                error=e,
-                            ),
-                        )
-                        error_event_emitted = True
-            elif max_usage_reached and original_tool:
-                # Return error message when max usage limit is reached
-                result = f"Tool '{func_name}' has reached its usage limit of {original_tool.max_usage_count} times and cannot be used anymore."
-
-            # Execute after_tool_call hooks (even if blocked, to allow logging/monitoring)
-            after_hook_context = ToolCallHookContext(
-                tool_name=func_name,
-                tool_input=args_dict,
-                tool=structured_tool,  # type: ignore[arg-type]
-                agent=self.agent,
-                task=self.task,
-                crew=self.crew,
-                tool_result=result,
-            )
-            after_hooks = get_after_tool_call_hooks()
-            try:
-                for after_hook in after_hooks:
-                    after_hook_result = after_hook(after_hook_context)
-                    if after_hook_result is not None:
-                        result = after_hook_result
-                        after_hook_context.tool_result = result
-            except Exception as hook_error:
-                if self.agent.verbose:
-                    self._printer.print(
-                        content=f"Error in after_tool_call hook: {hook_error}",
-                        color="red",
-                    )
-
-            if not error_event_emitted:
-                crewai_event_bus.emit(
-                    self,
-                    event=ToolUsageFinishedEvent(
+                if (
+                    original_tool
+                    and hasattr(original_tool, "result_as_answer")
+                    and original_tool.result_as_answer
+                ):
+                    self.state.current_answer = AgentFinish(
+                        thought="Tool result is the final answer",
                         output=result,
-                        tool_name=func_name,
-                        tool_args=args_dict,
-                        from_agent=self.agent,
-                        from_task=self.task,
-                        agent_key=agent_key,
-                        started_at=started_at,
-                        finished_at=datetime.now(),
-                    ),
-                )
+                        text=result,
+                    )
+                    self.state.is_finished = True
+                    return "tool_result_is_final"
 
-            # Append tool result message
-            tool_message: LLMMessage = {
+            return "native_tool_completed"
+
+        for execution_result in execution_results:
+            call_id = cast(str, execution_result["call_id"])
+            func_name = cast(str, execution_result["func_name"])
+            result = cast(str, execution_result["result"])
+            from_cache = cast(bool, execution_result["from_cache"])
+            original_tool = execution_result["original_tool"]
+
+            tool_message = {
                 "role": "tool",
                 "tool_call_id": call_id,
                 "name": func_name,
@@ -922,6 +881,224 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
 
         return "native_tool_completed"
 
+    def _should_parallelize_native_tool_calls(self, tool_calls: list[Any]) -> bool:
+        """Determine if native tool calls are safe to run in parallel."""
+        if len(tool_calls) <= 1:
+            return False
+
+        for tool_call in tool_calls:
+            info = extract_tool_call_info(tool_call)
+            if not info:
+                continue
+            _, func_name, _ = info
+
+            original_tool = None
+            for tool in self.original_tools or []:
+                if sanitize_tool_name(tool.name) == func_name:
+                    original_tool = tool
+                    break
+
+            if not original_tool:
+                continue
+
+            if getattr(original_tool, "result_as_answer", False):
+                return False
+            if getattr(original_tool, "max_usage_count", None) is not None:
+                return False
+
+        return True
+
+    def _execute_single_native_tool_call(self, tool_call: Any) -> dict[str, Any]:
+        """Execute a single native tool call and return metadata/result."""
+        info = extract_tool_call_info(tool_call)
+        if not info:
+            raise ValueError("Invalid native tool call format")
+
+        call_id, func_name, func_args = info
+
+        # Parse arguments
+        if isinstance(func_args, str):
+            try:
+                args_dict = json.loads(func_args)
+            except json.JSONDecodeError:
+                args_dict = {}
+        else:
+            args_dict = func_args
+
+        # Get agent_key for event tracking
+        agent_key = getattr(self.agent, "key", "unknown") if self.agent else "unknown"
+
+        # Find original tool by matching sanitized name (needed for cache_function and result_as_answer)
+        original_tool = None
+        for tool in self.original_tools or []:
+            if sanitize_tool_name(tool.name) == func_name:
+                original_tool = tool
+                break
+
+        # Check if tool has reached max usage count
+        max_usage_reached = False
+        if (
+            original_tool
+            and original_tool.max_usage_count is not None
+            and original_tool.current_usage_count >= original_tool.max_usage_count
+        ):
+            max_usage_reached = True
+
+        # Check cache before executing
+        from_cache = False
+        input_str = json.dumps(args_dict) if args_dict else ""
+        if self.tools_handler and self.tools_handler.cache:
+            cached_result = self.tools_handler.cache.read(
+                tool=func_name, input=input_str
+            )
+            if cached_result is not None:
+                result = (
+                    str(cached_result)
+                    if not isinstance(cached_result, str)
+                    else cached_result
+                )
+                from_cache = True
+
+        # Emit tool usage started event
+        started_at = datetime.now()
+        crewai_event_bus.emit(
+            self,
+            event=ToolUsageStartedEvent(
+                tool_name=func_name,
+                tool_args=args_dict,
+                from_agent=self.agent,
+                from_task=self.task,
+                agent_key=agent_key,
+            ),
+        )
+        error_event_emitted = False
+
+        track_delegation_if_needed(func_name, args_dict, self.task)
+
+        structured_tool: CrewStructuredTool | None = None
+        for structured in self.tools or []:
+            if sanitize_tool_name(structured.name) == func_name:
+                structured_tool = structured
+                break
+
+        hook_blocked = False
+        before_hook_context = ToolCallHookContext(
+            tool_name=func_name,
+            tool_input=args_dict,
+            tool=structured_tool,  # type: ignore[arg-type]
+            agent=self.agent,
+            task=self.task,
+            crew=self.crew,
+        )
+        before_hooks = get_before_tool_call_hooks()
+        try:
+            for hook in before_hooks:
+                hook_result = hook(before_hook_context)
+                if hook_result is False:
+                    hook_blocked = True
+                    break
+        except Exception as hook_error:
+            if self.agent.verbose:
+                self._printer.print(
+                    content=f"Error in before_tool_call hook: {hook_error}",
+                    color="red",
+                )
+
+        if hook_blocked:
+            result = f"Tool execution blocked by hook. Tool: {func_name}"
+        elif not from_cache and not max_usage_reached:
+            result = "Tool not found"
+            if func_name in self._available_functions:
+                try:
+                    tool_func = self._available_functions[func_name]
+                    raw_result = tool_func(**args_dict)
+
+                    # Add to cache after successful execution (before string conversion)
+                    if self.tools_handler and self.tools_handler.cache:
+                        should_cache = True
+                        if original_tool:
+                            should_cache = original_tool.cache_function(
+                                args_dict, raw_result
+                            )
+                        if should_cache:
+                            self.tools_handler.cache.add(
+                                tool=func_name, input=input_str, output=raw_result
+                            )
+
+                    # Convert to string for message
+                    result = (
+                        str(raw_result)
+                        if not isinstance(raw_result, str)
+                        else raw_result
+                    )
+                except Exception as e:
+                    result = f"Error executing tool: {e}"
+                    if self.task:
+                        self.task.increment_tools_errors()
+                    # Emit tool usage error event
+                    crewai_event_bus.emit(
+                        self,
+                        event=ToolUsageErrorEvent(
+                            tool_name=func_name,
+                            tool_args=args_dict,
+                            from_agent=self.agent,
+                            from_task=self.task,
+                            agent_key=agent_key,
+                            error=e,
+                        ),
+                    )
+                    error_event_emitted = True
+        elif max_usage_reached and original_tool:
+            # Return error message when max usage limit is reached
+            result = f"Tool '{func_name}' has reached its usage limit of {original_tool.max_usage_count} times and cannot be used anymore."
+
+        # Execute after_tool_call hooks (even if blocked, to allow logging/monitoring)
+        after_hook_context = ToolCallHookContext(
+            tool_name=func_name,
+            tool_input=args_dict,
+            tool=structured_tool,  # type: ignore[arg-type]
+            agent=self.agent,
+            task=self.task,
+            crew=self.crew,
+            tool_result=result,
+        )
+        after_hooks = get_after_tool_call_hooks()
+        try:
+            for after_hook in after_hooks:
+                after_hook_result = after_hook(after_hook_context)
+                if after_hook_result is not None:
+                    result = after_hook_result
+                    after_hook_context.tool_result = result
+        except Exception as hook_error:
+            if self.agent.verbose:
+                self._printer.print(
+                    content=f"Error in after_tool_call hook: {hook_error}",
+                    color="red",
+                )
+
+        if not error_event_emitted:
+            crewai_event_bus.emit(
+                self,
+                event=ToolUsageFinishedEvent(
+                    output=result,
+                    tool_name=func_name,
+                    tool_args=args_dict,
+                    from_agent=self.agent,
+                    from_task=self.task,
+                    agent_key=agent_key,
+                    started_at=started_at,
+                    finished_at=datetime.now(),
+                ),
+            )
+
+        return {
+            "call_id": call_id,
+            "func_name": func_name,
+            "result": result,
+            "from_cache": from_cache,
+            "original_tool": original_tool,
+        }
+
     def _extract_tool_name(self, tool_call: Any) -> str:
         """Extract tool name from various tool call formats."""
         if hasattr(tool_call, "function"):
@@ -1075,6 +1252,10 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
             self.state.is_finished = False
             self.state.use_native_tools = False
             self.state.pending_tool_calls = []
+            self.state.plan = None
+            self.state.plan_ready = False
+
+            self._kickoff_input = inputs.get("input", "")
 
             if "system" in self.prompt:
                 prompt = cast("SystemPromptResult", self.prompt)
@@ -1157,6 +1338,10 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
             self.state.is_finished = False
             self.state.use_native_tools = False
             self.state.pending_tool_calls = []
+            self.state.plan = None
+            self.state.plan_ready = False
+
+            self._kickoff_input = inputs.get("input", "")
 
             if "system" in self.prompt:
                 prompt = cast("SystemPromptResult", self.prompt)
@@ -1252,7 +1437,9 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
             formatted_answer: Current agent response.
         """
         if self.step_callback:
-            self.step_callback(formatted_answer)
+            cb_result = self.step_callback(formatted_answer)
+            if inspect.iscoroutine(cb_result):
+                asyncio.run(cb_result)
 
     def _append_message_to_state(
         self, text: str, role: Literal["user", "assistant", "system"] = "assistant"

lib/crewai/src/crewai/flow/flow.py

@@ -10,6 +10,7 @@ import asyncio
 from collections.abc import (
     Callable,
     ItemsView,
+    Iterable,
     Iterator,
     KeysView,
     Sequence,
@@ -17,6 +18,7 @@ from collections.abc import (
 )
 from concurrent.futures import Future
 import copy
+import enum
 import inspect
 import logging
 import threading
@@ -27,8 +29,10 @@ from typing import (
     Generic,
     Literal,
     ParamSpec,
+    SupportsIndex,
     TypeVar,
     cast,
+    overload,
 )
 from uuid import uuid4
 
@@ -77,7 +81,12 @@ from crewai.flow.flow_wrappers import (
     StartMethod,
 )
 from crewai.flow.persistence.base import FlowPersistence
-from crewai.flow.types import FlowExecutionData, FlowMethodName, InputHistoryEntry, PendingListenerKey
+from crewai.flow.types import (
+    FlowExecutionData,
+    FlowMethodName,
+    InputHistoryEntry,
+    PendingListenerKey,
+)
 from crewai.flow.utils import (
     _extract_all_methods,
     _extract_all_methods_recursive,
@@ -426,8 +435,7 @@ class LockedListProxy(list, Generic[T]):  # type: ignore[type-arg]
     """
 
     def __init__(self, lst: list[T], lock: threading.Lock) -> None:
-        # Do NOT call super().__init__() -- we don't want to copy data into
-        # the builtin list storage. All access goes through self._list.
+        super().__init__()  # empty builtin list; all access goes through self._list
         self._list = lst
         self._lock = lock
 
@@ -435,11 +443,11 @@ class LockedListProxy(list, Generic[T]):  # type: ignore[type-arg]
         with self._lock:
             self._list.append(item)
 
-    def extend(self, items: list[T]) -> None:
+    def extend(self, items: Iterable[T]) -> None:
         with self._lock:
             self._list.extend(items)
 
-    def insert(self, index: int, item: T) -> None:
+    def insert(self, index: SupportsIndex, item: T) -> None:
         with self._lock:
             self._list.insert(index, item)
 
@@ -447,7 +455,7 @@ class LockedListProxy(list, Generic[T]):  # type: ignore[type-arg]
         with self._lock:
             self._list.remove(item)
 
-    def pop(self, index: int = -1) -> T:
+    def pop(self, index: SupportsIndex = -1) -> T:
         with self._lock:
             return self._list.pop(index)
 
@@ -455,15 +463,23 @@ class LockedListProxy(list, Generic[T]):  # type: ignore[type-arg]
         with self._lock:
             self._list.clear()
 
-    def __setitem__(self, index: int, value: T) -> None:
+    @overload
+    def __setitem__(self, index: SupportsIndex, value: T) -> None: ...
+    @overload
+    def __setitem__(self, index: slice, value: Iterable[T]) -> None: ...
+    def __setitem__(self, index: Any, value: Any) -> None:
         with self._lock:
             self._list[index] = value
 
-    def __delitem__(self, index: int) -> None:
+    def __delitem__(self, index: SupportsIndex | slice) -> None:
         with self._lock:
             del self._list[index]
 
-    def __getitem__(self, index: int) -> T:
+    @overload
+    def __getitem__(self, index: SupportsIndex) -> T: ...
+    @overload
+    def __getitem__(self, index: slice) -> list[T]: ...
+    def __getitem__(self, index: Any) -> Any:
         return self._list[index]
 
     def __len__(self) -> int:
@@ -481,7 +497,7 @@ class LockedListProxy(list, Generic[T]):  # type: ignore[type-arg]
     def __bool__(self) -> bool:
         return bool(self._list)
 
-    def __eq__(self, other: object) -> bool:  # type: ignore[override]
+    def __eq__(self, other: object) -> bool:
         """Compare based on the underlying list contents."""
         if isinstance(other, LockedListProxy):
             # Avoid deadlocks by acquiring locks in a consistent order.
@@ -492,7 +508,7 @@ class LockedListProxy(list, Generic[T]):  # type: ignore[type-arg]
         with self._lock:
             return self._list == other
 
-    def __ne__(self, other: object) -> bool:  # type: ignore[override]
+    def __ne__(self, other: object) -> bool:
         return not self.__eq__(other)
 
 
@@ -505,8 +521,7 @@ class LockedDictProxy(dict, Generic[T]):  # type: ignore[type-arg]
     """
 
     def __init__(self, d: dict[str, T], lock: threading.Lock) -> None:
-        # Do NOT call super().__init__() -- we don't want to copy data into
-        # the builtin dict storage. All access goes through self._dict.
+        super().__init__()  # empty builtin dict; all access goes through self._dict
         self._dict = d
         self._lock = lock
 
@@ -518,11 +533,11 @@ class LockedDictProxy(dict, Generic[T]):  # type: ignore[type-arg]
         with self._lock:
             del self._dict[key]
 
-    def pop(self, key: str, *default: T) -> T:
+    def pop(self, key: str, *default: T) -> T:  # type: ignore[override]
         with self._lock:
             return self._dict.pop(key, *default)
 
-    def update(self, other: dict[str, T]) -> None:
+    def update(self, other: dict[str, T]) -> None:  # type: ignore[override]
         with self._lock:
             self._dict.update(other)
 
@@ -530,7 +545,7 @@ class LockedDictProxy(dict, Generic[T]):  # type: ignore[type-arg]
         with self._lock:
             self._dict.clear()
 
-    def setdefault(self, key: str, default: T) -> T:
+    def setdefault(self, key: str, default: T) -> T:  # type: ignore[override]
         with self._lock:
             return self._dict.setdefault(key, default)
 
@@ -546,16 +561,16 @@ class LockedDictProxy(dict, Generic[T]):  # type: ignore[type-arg]
     def __contains__(self, key: object) -> bool:
         return key in self._dict
 
-    def keys(self) -> KeysView[str]:
+    def keys(self) -> KeysView[str]:  # type: ignore[override]
         return self._dict.keys()
 
-    def values(self) -> ValuesView[T]:
+    def values(self) -> ValuesView[T]:  # type: ignore[override]
         return self._dict.values()
 
-    def items(self) -> ItemsView[str, T]:
+    def items(self) -> ItemsView[str, T]:  # type: ignore[override]
         return self._dict.items()
 
-    def get(self, key: str, default: T | None = None) -> T | None:
+    def get(self, key: str, default: T | None = None) -> T | None:  # type: ignore[override]
         return self._dict.get(key, default)
 
     def __repr__(self) -> str:
@@ -564,7 +579,7 @@ class LockedDictProxy(dict, Generic[T]):  # type: ignore[type-arg]
     def __bool__(self) -> bool:
         return bool(self._dict)
 
-    def __eq__(self, other: object) -> bool:  # type: ignore[override]
+    def __eq__(self, other: object) -> bool:
         """Compare based on the underlying dict contents."""
         if isinstance(other, LockedDictProxy):
             # Avoid deadlocks by acquiring locks in a consistent order.
@@ -575,7 +590,7 @@ class LockedDictProxy(dict, Generic[T]):  # type: ignore[type-arg]
         with self._lock:
             return self._dict == other
 
-    def __ne__(self, other: object) -> bool:  # type: ignore[override]
+    def __ne__(self, other: object) -> bool:
         return not self.__eq__(other)
 
 
@@ -737,7 +752,9 @@ class Flow(Generic[T], metaclass=FlowMeta):
     name: str | None = None
     tracing: bool | None = None
     stream: bool = False
-    memory: Any = None  # Memory | MemoryScope | MemorySlice | None; auto-created if not set
+    memory: Any = (
+        None  # Memory | MemoryScope | MemorySlice | None; auto-created if not set
+    )
     input_provider: Any = None  # InputProvider | None; per-flow override for self.ask()
 
     def __class_getitem__(cls: type[Flow[T]], item: type[T]) -> type[Flow[T]]:
@@ -881,7 +898,8 @@ class Flow(Generic[T], metaclass=FlowMeta):
         """
         if self.memory is None:
             raise ValueError("No memory configured for this flow")
-        return self.memory.extract_memories(content)
+        result: list[str] = self.memory.extract_memories(content)
+        return result
 
     def _mark_or_listener_fired(self, listener_name: FlowMethodName) -> bool:
         """Mark an OR listener as fired atomically.
@@ -1352,8 +1370,10 @@ class Flow(Generic[T], metaclass=FlowMeta):
             ValueError: If structured state model lacks 'id' field
             TypeError: If state is neither BaseModel nor dictionary
         """
+        init_state = self.initial_state
+
         # Handle case where initial_state is None but we have a type parameter
-        if self.initial_state is None and hasattr(self, "_initial_state_t"):
+        if init_state is None and hasattr(self, "_initial_state_t"):
             state_type = self._initial_state_t
             if isinstance(state_type, type):
                 if issubclass(state_type, FlowState):
@@ -1377,12 +1397,12 @@ class Flow(Generic[T], metaclass=FlowMeta):
                     return cast(T, {"id": str(uuid4())})
 
         # Handle case where no initial state is provided
-        if self.initial_state is None:
+        if init_state is None:
             return cast(T, {"id": str(uuid4())})
 
         # Handle case where initial_state is a type (class)
-        if isinstance(self.initial_state, type):
-            state_class: type[T] = self.initial_state
+        if isinstance(init_state, type):
+            state_class = init_state
             if issubclass(state_class, FlowState):
                 return state_class()
             if issubclass(state_class, BaseModel):
@@ -1393,19 +1413,19 @@ class Flow(Generic[T], metaclass=FlowMeta):
                 if not getattr(model_instance, "id", None):
                     object.__setattr__(model_instance, "id", str(uuid4()))
                 return model_instance
-            if self.initial_state is dict:
+            if init_state is dict:
                 return cast(T, {"id": str(uuid4())})
 
         # Handle dictionary instance case
-        if isinstance(self.initial_state, dict):
-            new_state = dict(self.initial_state)  # Copy to avoid mutations
+        if isinstance(init_state, dict):
+            new_state = dict(init_state)  # Copy to avoid mutations
             if "id" not in new_state:
                 new_state["id"] = str(uuid4())
             return cast(T, new_state)
 
         # Handle BaseModel instance case
-        if isinstance(self.initial_state, BaseModel):
-            model = cast(BaseModel, self.initial_state)
+        if isinstance(init_state, BaseModel):
+            model = cast(BaseModel, init_state)
             if not hasattr(model, "id"):
                 raise ValueError("Flow state model must have an 'id' field")
 
@@ -2178,6 +2198,8 @@ class Flow(Generic[T], metaclass=FlowMeta):
             from crewai.flow.async_feedback.types import HumanFeedbackPending
 
             if isinstance(e, HumanFeedbackPending):
+                e.context.method_name = method_name
+
                 # Auto-save pending feedback (create default persistence if needed)
                 if self._persistence is None:
                     from crewai.flow.persistence import SQLiteFlowPersistence
@@ -2277,14 +2299,23 @@ class Flow(Generic[T], metaclass=FlowMeta):
                     router_name, router_input, current_triggering_event_id
                 )
                 if router_result:  # Only add non-None results
-                    router_results.append(FlowMethodName(str(router_result)))
+                    router_result_str = (
+                        router_result.value
+                        if isinstance(router_result, enum.Enum)
+                        else str(router_result)
+                    )
+                    router_results.append(FlowMethodName(router_result_str))
                     # If this was a human_feedback router, map the outcome to the feedback
                     if self.last_human_feedback is not None:
-                        router_result_to_feedback[str(router_result)] = (
+                        router_result_to_feedback[router_result_str] = (
                             self.last_human_feedback
                         )
                 current_trigger = (
-                    FlowMethodName(str(router_result))
+                    FlowMethodName(
+                        router_result.value
+                        if isinstance(router_result, enum.Enum)
+                        else str(router_result)
+                    )
                     if router_result is not None
                     else FlowMethodName("")  # Update for next iteration of router chain
                 )
@@ -2701,7 +2732,10 @@ class Flow(Generic[T], metaclass=FlowMeta):
                     return topic
             ```
         """
-        from concurrent.futures import ThreadPoolExecutor, TimeoutError as FuturesTimeoutError
+        from concurrent.futures import (
+            ThreadPoolExecutor,
+            TimeoutError as FuturesTimeoutError,
+        )
         from datetime import datetime
 
         from crewai.events.types.flow_events import (
@@ -2770,14 +2804,16 @@ class Flow(Generic[T], metaclass=FlowMeta):
             response = None
 
         # Record in history
-        self._input_history.append({
-            "message": message,
-            "response": response,
-            "method_name": method_name,
-            "timestamp": datetime.now(),
-            "metadata": metadata,
-            "response_metadata": response_metadata,
-        })
+        self._input_history.append(
+            {
+                "message": message,
+                "response": response,
+                "method_name": method_name,
+                "timestamp": datetime.now(),
+                "metadata": metadata,
+                "response_metadata": response_metadata,
+            }
+        )
 
         # Emit input received event
         crewai_event_bus.emit(

lib/crewai/src/crewai/task.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import asyncio
 from concurrent.futures import Future
 from copy import copy as shallow_copy
 import datetime
@@ -624,11 +625,15 @@ class Task(BaseModel):
             self.end_time = datetime.datetime.now()
 
             if self.callback:
-                self.callback(self.output)
+                cb_result = self.callback(self.output)
+                if inspect.isawaitable(cb_result):
+                    await cb_result
 
             crew = self.agent.crew  # type: ignore[union-attr]
             if crew and crew.task_callback and crew.task_callback != self.callback:
-                crew.task_callback(self.output)
+                cb_result = crew.task_callback(self.output)
+                if inspect.isawaitable(cb_result):
+                    await cb_result
 
             if self.output_file:
                 content = (
@@ -722,11 +727,15 @@ class Task(BaseModel):
             self.end_time = datetime.datetime.now()
 
             if self.callback:
-                self.callback(self.output)
+                cb_result = self.callback(self.output)
+                if inspect.iscoroutine(cb_result):
+                    asyncio.run(cb_result)
 
             crew = self.agent.crew  # type: ignore[union-attr]
             if crew and crew.task_callback and crew.task_callback != self.callback:
-                crew.task_callback(self.output)
+                cb_result = crew.task_callback(self.output)
+                if inspect.iscoroutine(cb_result):
+                    asyncio.run(cb_result)
 
             if self.output_file:
                 content = (

lib/crewai/src/crewai/translations/en.json

@@ -74,9 +74,14 @@
     "consolidation_user": "New content to consider storing:\n{new_content}\n\nExisting similar memories:\n{records_summary}\n\nReturn the consolidation plan as structured output."
   },
   "reasoning": {
-    "initial_plan": "You are {role}, a professional with the following background: {backstory}\n\nYour primary goal is: {goal}\n\nAs {role}, you are creating a strategic plan for a task that requires your expertise and unique perspective.",
-    "refine_plan": "You are {role}, a professional with the following background: {backstory}\n\nYour primary goal is: {goal}\n\nAs {role}, you are refining a strategic plan for a task that requires your expertise and unique perspective.",
-    "create_plan_prompt": "You are {role} with this background: {backstory}\n\nYour primary goal is: {goal}\n\nYou have been assigned the following task:\n{description}\n\nExpected output:\n{expected_output}\n\nAvailable tools: {tools}\n\nBefore executing this task, create a detailed plan that leverages your expertise as {role} and outlines:\n1. Your understanding of the task from your professional perspective\n2. The key steps you'll take to complete it, drawing on your background and skills\n3. How you'll approach any challenges that might arise, considering your expertise\n4. How you'll strategically use the available tools based on your experience, exactly what tools to use and how to use them\n5. The expected outcome and how it aligns with your goal\n\nAfter creating your plan, assess whether you feel ready to execute the task or if you could do better.\nConclude with one of these statements:\n- \"READY: I am ready to execute the task.\"\n- \"NOT READY: I need to refine my plan because [specific reason].\"",
-    "refine_plan_prompt": "You are {role} with this background: {backstory}\n\nYour primary goal is: {goal}\n\nYou created the following plan for this task:\n{current_plan}\n\nHowever, you indicated that you're not ready to execute the task yet.\n\nPlease refine your plan further, drawing on your expertise as {role} to address any gaps or uncertainties. As you refine your plan, be specific about which available tools you will use, how you will use them, and why they are the best choices for each step. Clearly outline your tool usage strategy as part of your improved plan.\n\nAfter refining your plan, assess whether you feel ready to execute the task.\nConclude with one of these statements:\n- \"READY: I am ready to execute the task.\"\n- \"NOT READY: I need to refine my plan further because [specific reason].\""
+    "initial_plan": "You are {role}. Create a focused execution plan using only the essential steps needed.",
+    "refine_plan": "You are {role}. Refine your plan to address the specific gap while keeping it minimal.",
+    "create_plan_prompt": "You are {role}.\n\nTask: {description}\n\nExpected output: {expected_output}\n\nAvailable tools: {tools}\n\nCreate a focused plan with ONLY the essential steps needed. Most tasks require just 2-5 steps. Do NOT pad with unnecessary steps like \"review\", \"verify\", \"document\", or \"finalize\" unless explicitly required.\n\nFor each step, specify the action and which tool to use (if any).\n\nConclude with:\n- \"READY: I am ready to execute the task.\"\n- \"NOT READY: I need to refine my plan because [specific reason].\"",
+    "refine_plan_prompt": "Your plan:\n{current_plan}\n\nYou indicated you're not ready. Address the specific gap while keeping the plan minimal.\n\nConclude with READY or NOT READY."
+  },
+  "planning": {
+    "system_prompt": "You are a strategic planning assistant. Create minimal, effective execution plans. Prefer fewer steps over more.",
+    "create_plan_prompt": "Create a focused execution plan for the following task:\n\n## Task\n{description}\n\n## Expected Output\n{expected_output}\n\n## Available Tools\n{tools}\n\n## Planning Principles\nFocus on WHAT needs to be accomplished, not HOW. Group related actions into logical units. Fewer steps = better. Most tasks need 3-6 steps. Hard limit: {max_steps} steps.\n\n## Step Types (only these are valid):\n1. **Tool Step**: Uses a tool to gather information or take action\n2. **Output Step**: Synthesizes prior results into the final deliverable (usually the last step)\n\n## Rules:\n- Each step must either USE A TOOL or PRODUCE THE FINAL OUTPUT\n- Combine related tool calls: \"Research A, B, and C\" = ONE step, not three\n- Combine all synthesis into ONE final output step\n- NO standalone \"thinking\" steps (review, verify, confirm, refine, analyze) - these happen naturally between steps\n\nFor each step: State the action, specify the tool (if any), and note dependencies.\n\nAfter your plan, state READY or NOT READY.",
+    "refine_plan_prompt": "Your previous plan:\n{current_plan}\n\nYou indicated you weren't ready. Refine your plan to address the specific gap.\n\nKeep the plan minimal - only add steps that directly address the issue.\n\nConclude with READY or NOT READY as before."
   }
 }

lib/crewai/src/crewai/utilities/agent_utils.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import asyncio
 from collections.abc import Callable, Sequence
 import concurrent.futures
+import inspect
 import json
 import re
 from typing import TYPE_CHECKING, Any, Final, Literal, TypedDict
@@ -501,7 +502,9 @@ def handle_agent_action_core(
         - TODO: Remove messages parameter and its usage.
     """
     if step_callback:
-        step_callback(tool_result)
+        cb_result = step_callback(tool_result)
+        if inspect.iscoroutine(cb_result):
+            asyncio.run(cb_result)
 
     formatted_answer.text += f"\nObservation: {tool_result.result}"
     formatted_answer.result = tool_result.result

lib/crewai/src/crewai/utilities/planning_types.py

@@ -0,0 +1,103 @@
+"""Types for agent planning and todo tracking."""
+
+from __future__ import annotations
+
+from typing import Literal
+from uuid import uuid4
+
+from pydantic import BaseModel, Field
+
+
+# Todo status type
+TodoStatus = Literal["pending", "running", "completed"]
+
+
+class PlanStep(BaseModel):
+    """A single step in the reasoning plan."""
+
+    step_number: int = Field(description="Step number (1-based)")
+    description: str = Field(description="What to do in this step")
+    tool_to_use: str | None = Field(
+        default=None, description="Tool to use for this step, if any"
+    )
+    depends_on: list[int] = Field(
+        default_factory=list, description="Step numbers this step depends on"
+    )
+
+
+class TodoItem(BaseModel):
+    """A single todo item representing a step in the execution plan."""
+
+    id: str = Field(default_factory=lambda: str(uuid4()))
+    step_number: int = Field(description="Order of this step in the plan (1-based)")
+    description: str = Field(description="What needs to be done")
+    tool_to_use: str | None = Field(
+        default=None, description="Tool to use for this step, if any"
+    )
+    status: TodoStatus = Field(default="pending", description="Current status")
+    depends_on: list[int] = Field(
+        default_factory=list, description="Step numbers this depends on"
+    )
+    result: str | None = Field(
+        default=None, description="Result after completion, if any"
+    )
+
+
+class TodoList(BaseModel):
+    """Collection of todos for tracking plan execution."""
+
+    items: list[TodoItem] = Field(default_factory=list)
+
+    @property
+    def current_todo(self) -> TodoItem | None:
+        """Get the currently running todo item."""
+        for item in self.items:
+            if item.status == "running":
+                return item
+        return None
+
+    @property
+    def next_pending(self) -> TodoItem | None:
+        """Get the next pending todo item."""
+        for item in self.items:
+            if item.status == "pending":
+                return item
+        return None
+
+    @property
+    def is_complete(self) -> bool:
+        """Check if all todos are completed."""
+        return len(self.items) > 0 and all(
+            item.status == "completed" for item in self.items
+        )
+
+    @property
+    def pending_count(self) -> int:
+        """Count of pending todos."""
+        return sum(1 for item in self.items if item.status == "pending")
+
+    @property
+    def completed_count(self) -> int:
+        """Count of completed todos."""
+        return sum(1 for item in self.items if item.status == "completed")
+
+    def get_by_step_number(self, step_number: int) -> TodoItem | None:
+        """Get a todo by its step number."""
+        for item in self.items:
+            if item.step_number == step_number:
+                return item
+        return None
+
+    def mark_running(self, step_number: int) -> None:
+        """Mark a todo as running by step number."""
+        item = self.get_by_step_number(step_number)
+        if item:
+            item.status = "running"
+
+    def mark_completed(self, step_number: int, result: str | None = None) -> None:
+        """Mark a todo as completed by step number."""
+        item = self.get_by_step_number(step_number)
+        if item:
+            item.status = "completed"
+            if result:
+                item.result = result

lib/crewai/src/crewai/utilities/reasoning_handler.py

@@ -1,10 +1,13 @@
+"""Handles planning/reasoning for agents before task execution."""
+
+from __future__ import annotations
+
 import json
 import logging
-from typing import Any, Final, Literal, cast
+from typing import TYPE_CHECKING, Any, Final, Literal, cast
 
 from pydantic import BaseModel, Field
 
-from crewai.agent import Agent
 from crewai.events.event_bus import crewai_event_bus
 from crewai.events.types.reasoning_events import (
     AgentReasoningCompletedEvent,
@@ -12,14 +15,30 @@ from crewai.events.types.reasoning_events import (
     AgentReasoningStartedEvent,
 )
 from crewai.llm import LLM
-from crewai.task import Task
+from crewai.utilities.llm_utils import create_llm
+from crewai.utilities.planning_types import PlanStep
 from crewai.utilities.string_utils import sanitize_tool_name
 
 
+if TYPE_CHECKING:
+    from crewai.agent import Agent
+    from crewai.agent.planning_config import PlanningConfig
+    from crewai.task import Task
+
+
+if TYPE_CHECKING:
+    from crewai.agent import Agent
+    from crewai.agent.planning_config import PlanningConfig
+    from crewai.task import Task
+
+
 class ReasoningPlan(BaseModel):
     """Model representing a reasoning plan for a task."""
 
     plan: str = Field(description="The detailed reasoning plan for the task.")
+    steps: list[PlanStep] = Field(
+        default_factory=list, description="Structured steps to execute"
+    )
     ready: bool = Field(description="Whether the agent is ready to execute the task.")
 
 
@@ -29,24 +48,63 @@ class AgentReasoningOutput(BaseModel):
     plan: ReasoningPlan = Field(description="The reasoning plan for the task.")
 
 
+# Aliases for backward compatibility
+PlanningPlan = ReasoningPlan
+AgentPlanningOutput = AgentReasoningOutput
+
+
 FUNCTION_SCHEMA: Final[dict[str, Any]] = {
     "type": "function",
     "function": {
         "name": "create_reasoning_plan",
-        "description": "Create or refine a reasoning plan for a task",
+        "description": "Create or refine a reasoning plan for a task with structured steps",
         "parameters": {
             "type": "object",
             "properties": {
                 "plan": {
                     "type": "string",
-                    "description": "The detailed reasoning plan for the task.",
+                    "description": "A brief summary of the overall plan.",
+                },
+                "steps": {
+                    "type": "array",
+                    "description": "List of discrete steps to execute the plan",
+                    "items": {
+                        "type": "object",
+                        "properties": {
+                            "step_number": {
+                                "type": "integer",
+                                "description": "Step number (1-based)",
+                            },
+                            "description": {
+                                "type": "string",
+                                "description": "What to do in this step",
+                            },
+                            "tool_to_use": {
+                                "type": ["string", "null"],
+                                "description": "Tool to use for this step, or null if no tool needed",
+                            },
+                            "depends_on": {
+                                "type": "array",
+                                "items": {"type": "integer"},
+                                "description": "Step numbers this step depends on (empty array if none)",
+                            },
+                        },
+                        "required": [
+                            "step_number",
+                            "description",
+                            "tool_to_use",
+                            "depends_on",
+                        ],
+                        "additionalProperties": False,
+                    },
                 },
                 "ready": {
                     "type": "boolean",
                     "description": "Whether the agent is ready to execute the task.",
                 },
             },
-            "required": ["plan", "ready"],
+            "required": ["plan", "steps", "ready"],
+            "additionalProperties": False,
         },
     },
 }
@@ -54,41 +112,101 @@ FUNCTION_SCHEMA: Final[dict[str, Any]] = {
 
 class AgentReasoning:
     """
-    Handles the agent reasoning process, enabling an agent to reflect and create a plan
-    before executing a task.
+    Handles the agent planning/reasoning process, enabling an agent to reflect
+    and create a plan before executing a task.
 
     Attributes:
-        task: The task for which the agent is reasoning.
-        agent: The agent performing the reasoning.
-        llm: The language model used for reasoning.
+        task: The task for which the agent is planning (optional).
+        agent: The agent performing the planning.
+        config: The planning configuration.
+        llm: The language model used for planning.
         logger: Logger for logging events and errors.
+        description: Task description or input text for planning.
+        expected_output: Expected output description.
     """
 
-    def __init__(self, task: Task, agent: Agent) -> None:
-        """Initialize the AgentReasoning with a task and an agent.
+    def __init__(
+        self,
+        agent: Agent,
+        task: Task | None = None,
+        *,
+        description: str | None = None,
+        expected_output: str | None = None,
+    ) -> None:
+        """Initialize the AgentReasoning with an agent and optional task.
 
         Args:
-            task: The task for which the agent is reasoning.
-            agent: The agent performing the reasoning.
+            agent: The agent performing the planning.
+            task: The task for which the agent is planning (optional).
+            description: Task description or input text (used if task is None).
+            expected_output: Expected output (used if task is None).
         """
-        self.task = task
         self.agent = agent
-        self.llm = cast(LLM, agent.llm)
+        self.task = task
+        # Use task attributes if available, otherwise use provided values
+        self._description = description or (
+            task.description if task else "Complete the requested task"
+        )
+        self._expected_output = expected_output or (
+            task.expected_output if task else "Complete the task successfully"
+        )
+        self.config = self._get_planning_config()
+        self.llm = self._resolve_llm()
         self.logger = logging.getLogger(__name__)
 
-    def handle_agent_reasoning(self) -> AgentReasoningOutput:
-        """Public method for the reasoning process that creates and refines a plan for the task until the agent is ready to execute it.
+    @property
+    def description(self) -> str:
+        """Get the task/input description."""
+        return self._description
+
+    @property
+    def expected_output(self) -> str:
+        """Get the expected output."""
+        return self._expected_output
+
+    def _get_planning_config(self) -> PlanningConfig:
+        """Get the planning configuration from the agent.
 
         Returns:
-            AgentReasoningOutput: The output of the agent reasoning process.
+            The planning configuration, using defaults if not set.
         """
-        # Emit a reasoning started event (attempt 1)
+        from crewai.agent.planning_config import PlanningConfig
+
+        if self.agent.planning_config is not None:
+            return self.agent.planning_config
+        # Fallback for backward compatibility
+        return PlanningConfig(
+            max_attempts=getattr(self.agent, "max_reasoning_attempts", None),
+        )
+
+    def _resolve_llm(self) -> LLM:
+        """Resolve which LLM to use for planning.
+
+        Returns:
+            The LLM to use - either from config or the agent's LLM.
+        """
+        if self.config.llm is not None:
+            if isinstance(self.config.llm, LLM):
+                return self.config.llm
+            return create_llm(self.config.llm)
+        return cast(LLM, self.agent.llm)
+
+    def handle_agent_reasoning(self) -> AgentReasoningOutput:
+        """Public method for the planning process that creates and refines a plan
+        for the task until the agent is ready to execute it.
+
+        Returns:
+            AgentReasoningOutput: The output of the agent planning process.
+        """
+        task_id = str(self.task.id) if self.task else "kickoff"
+
+        # Emit a planning started event (attempt 1)
         try:
             crewai_event_bus.emit(
                 self.agent,
                 AgentReasoningStartedEvent(
                     agent_role=self.agent.role,
-                    task_id=str(self.task.id),
+                    task_id=task_id,
                     attempt=1,
                     from_task=self.task,
                 ),
@@ -98,13 +216,13 @@ class AgentReasoning:
             pass
 
         try:
-            output = self.__handle_agent_reasoning()
+            output = self._execute_planning()
 
             crewai_event_bus.emit(
                 self.agent,
                 AgentReasoningCompletedEvent(
                     agent_role=self.agent.role,
-                    task_id=str(self.task.id),
+                    task_id=task_id,
                     plan=output.plan.plan,
                     ready=output.plan.ready,
                     attempt=1,
@@ -115,71 +233,77 @@ class AgentReasoning:
 
             return output
         except Exception as e:
-            # Emit reasoning failed event
+            # Emit planning failed event
             try:
                 crewai_event_bus.emit(
                     self.agent,
                     AgentReasoningFailedEvent(
                         agent_role=self.agent.role,
-                        task_id=str(self.task.id),
+                        task_id=task_id,
                         error=str(e),
                         attempt=1,
                         from_task=self.task,
                         from_agent=self.agent,
                     ),
                 )
-            except Exception as e:
-                logging.error(f"Error emitting reasoning failed event: {e}")
+            except Exception as event_error:
+                logging.error(f"Error emitting planning failed event: {event_error}")
 
             raise
 
-    def __handle_agent_reasoning(self) -> AgentReasoningOutput:
-        """Private method that handles the agent reasoning process.
+    def _execute_planning(self) -> AgentReasoningOutput:
+        """Execute the planning process.
 
         Returns:
-            The output of the agent reasoning process.
+            The output of the agent planning process.
         """
-        plan, ready = self.__create_initial_plan()
+        plan, steps, ready = self._create_initial_plan()
+        plan, steps, ready = self._refine_plan_if_needed(plan, steps, ready)
 
-        plan, ready = self.__refine_plan_if_needed(plan, ready)
-
-        reasoning_plan = ReasoningPlan(plan=plan, ready=ready)
+        reasoning_plan = ReasoningPlan(plan=plan, steps=steps, ready=ready)
         return AgentReasoningOutput(plan=reasoning_plan)
 
-    def __create_initial_plan(self) -> tuple[str, bool]:
-        """Creates the initial reasoning plan for the task.
+    def _create_initial_plan(self) -> tuple[str, list[PlanStep], bool]:
+        """Creates the initial plan for the task.
 
         Returns:
-            The initial plan and whether the agent is ready to execute the task.
+            A tuple of the plan summary, list of steps, and whether the agent is ready.
         """
-        reasoning_prompt = self.__create_reasoning_prompt()
+        planning_prompt = self._create_planning_prompt()
+        planning_prompt = self._create_planning_prompt()
 
         if self.llm.supports_function_calling():
-            plan, ready = self.__call_with_function(reasoning_prompt, "initial_plan")
-            return plan, ready
-        response = _call_llm_with_reasoning_prompt(
-            llm=self.llm,
-            prompt=reasoning_prompt,
-            task=self.task,
-            reasoning_agent=self.agent,
-            backstory=self.__get_agent_backstory(),
-            plan_type="initial_plan",
+            plan, steps, ready = self._call_with_function(
+                planning_prompt, "create_plan"
+            )
+            return plan, steps, ready
+
+        response = self._call_llm_with_prompt(
+            prompt=planning_prompt,
+            plan_type="create_plan",
         )
 
-        return self.__parse_reasoning_response(str(response))
+        plan, ready = self._parse_planning_response(str(response))
+        return plan, [], ready  # No structured steps from text parsing
 
-    def __refine_plan_if_needed(self, plan: str, ready: bool) -> tuple[str, bool]:
-        """Refines the reasoning plan if the agent is not ready to execute the task.
+    def _refine_plan_if_needed(
+        self, plan: str, steps: list[PlanStep], ready: bool
+    ) -> tuple[str, list[PlanStep], bool]:
+        """Refines the plan if the agent is not ready to execute the task.
 
         Args:
-            plan: The current reasoning plan.
+            plan: The current plan.
+            steps: The current list of steps.
             ready: Whether the agent is ready to execute the task.
 
         Returns:
-            The refined plan and whether the agent is ready to execute the task.
+            The refined plan, steps, and whether the agent is ready to execute.
         """
+
         attempt = 1
-        max_attempts = self.agent.max_reasoning_attempts
+        max_attempts = self.config.max_attempts
+        task_id = str(self.task.id) if self.task else "kickoff"
+        current_attempt = attempt + 1
 
         while not ready and (max_attempts is None or attempt < max_attempts):
             # Emit event for each refinement attempt
@@ -188,62 +312,82 @@ class AgentReasoning:
                     self.agent,
                     AgentReasoningStartedEvent(
                         agent_role=self.agent.role,
-                        task_id=str(self.task.id),
-                        attempt=attempt + 1,
+                        task_id=task_id,
+                        attempt=current_attempt,
                         from_task=self.task,
                     ),
                 )
             except Exception:  # noqa: S110
                 pass
 
-            refine_prompt = self.__create_refine_prompt(plan)
+            refine_prompt = self._create_refine_prompt(plan)
+            refine_prompt = self._create_refine_prompt(plan)
 
             if self.llm.supports_function_calling():
-                plan, ready = self.__call_with_function(refine_prompt, "refine_plan")
+                plan, steps, ready = self._call_with_function(
+                    refine_prompt, "refine_plan"
+                )
             else:
-                response = _call_llm_with_reasoning_prompt(
-                    llm=self.llm,
+                response = self._call_llm_with_prompt(
                     prompt=refine_prompt,
-                    task=self.task,
-                    reasoning_agent=self.agent,
-                    backstory=self.__get_agent_backstory(),
                     plan_type="refine_plan",
                 )
-                plan, ready = self.__parse_reasoning_response(str(response))
+                plan, ready = self._parse_planning_response(str(response))
+                steps = []  # No structured steps from text parsing
+
+            # Emit completed event for this refinement attempt
+            try:
+                crewai_event_bus.emit(
+                    self.agent,
+                    AgentReasoningCompletedEvent(
+                        agent_role=self.agent.role,
+                        task_id=task_id,
+                        plan=plan,
+                        ready=ready,
+                        attempt=current_attempt,
+                        from_task=self.task,
+                        from_agent=self.agent,
+                    ),
+                )
+            except Exception:  # noqa: S110
+                pass
 
             attempt += 1
 
             if max_attempts is not None and attempt >= max_attempts:
                 self.logger.warning(
-                    f"Agent reasoning reached maximum attempts ({max_attempts}) without being ready. Proceeding with current plan."
+                    f"Agent planning reached maximum attempts ({max_attempts}) "
+                    "without being ready. Proceeding with current plan."
                 )
                 break
 
-        return plan, ready
+        return plan, steps, ready
 
-    def __call_with_function(self, prompt: str, prompt_type: str) -> tuple[str, bool]:
-        """Calls the LLM with function calling to get a reasoning plan.
+    def _call_with_function(
+        self, prompt: str, plan_type: Literal["create_plan", "refine_plan"]
+    ) -> tuple[str, list[PlanStep], bool]:
+        """Calls the LLM with function calling to get a plan.
 
         Args:
             prompt: The prompt to send to the LLM.
-            prompt_type: The type of prompt (initial_plan or refine_plan).
+            plan_type: The type of plan being created.
 
         Returns:
-            A tuple containing the plan and whether the agent is ready.
+            A tuple containing the plan summary, list of steps, and whether the agent is ready.
         """
-        self.logger.debug(f"Using function calling for {prompt_type} reasoning")
+        self.logger.debug(f"Using function calling for {plan_type} planning")
 
         try:
-            system_prompt = self.agent.i18n.retrieve("reasoning", prompt_type).format(
-                role=self.agent.role,
-                goal=self.agent.goal,
-                backstory=self.__get_agent_backstory(),
-            )
+            system_prompt = self._get_system_prompt()
 
             # Prepare a simple callable that just returns the tool arguments as JSON
-            def _create_reasoning_plan(plan: str, ready: bool = True) -> str:
-                """Return the reasoning plan result in JSON string form."""
-                return json.dumps({"plan": plan, "ready": ready})
+            def _create_reasoning_plan(
+                plan: str,
+                steps: list[dict[str, Any]] | None = None,
+                ready: bool = True,
+            ) -> str:
+                """Return the planning result in JSON string form."""
+                return json.dumps({"plan": plan, "steps": steps or [], "ready": ready})
 
             response = self.llm.call(
                 [
@@ -255,19 +399,33 @@ class AgentReasoning:
                 from_task=self.task,
                 from_agent=self.agent,
             )
-
-            self.logger.debug(f"Function calling response: {response[:100]}...")
-
             try:
                 result = json.loads(response)
                 if "plan" in result and "ready" in result:
-                    return result["plan"], result["ready"]
+                    # Parse steps from the response
+                    steps: list[PlanStep] = []
+                    raw_steps = result.get("steps", [])
+                    try:
+                        for step_data in raw_steps:
+                            step = PlanStep(
+                                step_number=step_data.get("step_number", 0),
+                                description=step_data.get("description", ""),
+                                tool_to_use=step_data.get("tool_to_use"),
+                                depends_on=step_data.get("depends_on", []),
+                            )
+                            steps.append(step)
+                    except Exception as step_error:
+                        self.logger.warning(
+                            f"Failed to parse step: {step_data}, error: {step_error}"
+                        )
+                    return result["plan"], steps, result["ready"]
             except (json.JSONDecodeError, KeyError):
                 pass
 
             response_str = str(response)
             return (
                 response_str,
+                [],
                 "READY: I am ready to execute the task." in response_str,
             )
 
@@ -277,13 +435,7 @@ class AgentReasoning:
             )
 
             try:
-                system_prompt = self.agent.i18n.retrieve(
-                    "reasoning", prompt_type
-                ).format(
-                    role=self.agent.role,
-                    goal=self.agent.goal,
-                    backstory=self.__get_agent_backstory(),
-                )
+                system_prompt = self._get_system_prompt()
 
                 fallback_response = self.llm.call(
                     [
@@ -297,78 +449,165 @@ class AgentReasoning:
                 fallback_str = str(fallback_response)
                 return (
                     fallback_str,
+                    [],
                     "READY: I am ready to execute the task." in fallback_str,
                 )
             except Exception as inner_e:
                 self.logger.error(f"Error during fallback text parsing: {inner_e!s}")
                 return (
                     "Failed to generate a plan due to an error.",
+                    [],
                     True,
                 )  # Default to ready to avoid getting stuck
 
-    def __get_agent_backstory(self) -> str:
-        """
-        Safely gets the agent's backstory, providing a default if not available.
+    def _call_llm_with_prompt(
+        self,
+        prompt: str,
+        plan_type: Literal["create_plan", "refine_plan"],
+    ) -> str:
+        """Calls the LLM with the planning prompt.
+
+        Args:
+            prompt: The prompt to send to the LLM.
+            plan_type: The type of plan being created.
 
         Returns:
-            str: The agent's backstory or a default value.
+            The LLM response.
+        """
+        system_prompt = self._get_system_prompt()
+
+        response = self.llm.call(
+            [
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": prompt},
+            ],
+            from_task=self.task,
+            from_agent=self.agent,
+        )
+        return str(response)
+
+    def _get_system_prompt(self) -> str:
+        """Get the system prompt for planning.
+
+        Returns:
+            The system prompt, either custom or from i18n.
+        """
+        if self.config.system_prompt is not None:
+            return self.config.system_prompt
+
+        # Try new "planning" section first, fall back to "reasoning" for compatibility
+        try:
+            return self.agent.i18n.retrieve("planning", "system_prompt")
+        except (KeyError, AttributeError):
+            # Fallback to reasoning section for backward compatibility
+            return self.agent.i18n.retrieve("reasoning", "initial_plan").format(
+                role=self.agent.role,
+                goal=self.agent.goal,
+                backstory=self._get_agent_backstory(),
+            )
+
+    def _get_agent_backstory(self) -> str:
+        """Safely gets the agent's backstory, providing a default if not available.
+
+        Returns:
+            The agent's backstory or a default value.
         """
         return getattr(self.agent, "backstory", "No backstory provided")
 
-    def __create_reasoning_prompt(self) -> str:
-        """
-        Creates a prompt for the agent to reason about the task.
+    def _create_planning_prompt(self) -> str:
+        """Creates a prompt for the agent to plan the task.
 
         Returns:
-            str: The reasoning prompt.
+            The planning prompt.
         """
-        available_tools = self.__format_available_tools()
+        available_tools = self._format_available_tools()
 
-        return self.agent.i18n.retrieve("reasoning", "create_plan_prompt").format(
-            role=self.agent.role,
-            goal=self.agent.goal,
-            backstory=self.__get_agent_backstory(),
-            description=self.task.description,
-            expected_output=self.task.expected_output,
-            tools=available_tools,
-        )
+        # Use custom prompt if provided
+        if self.config.plan_prompt is not None:
+            return self.config.plan_prompt.format(
+                role=self.agent.role,
+                goal=self.agent.goal,
+                backstory=self._get_agent_backstory(),
+                description=self.description,
+                expected_output=self.expected_output,
+                tools=available_tools,
+                max_steps=self.config.max_steps,
+            )
 
-    def __format_available_tools(self) -> str:
-        """
-        Formats the available tools for inclusion in the prompt.
+        # Try new "planning" section first
+        try:
+            return self.agent.i18n.retrieve("planning", "create_plan_prompt").format(
+                description=self.description,
+                expected_output=self.expected_output,
+                tools=available_tools,
+                max_steps=self.config.max_steps,
+            )
+        except (KeyError, AttributeError):
+            # Fallback to reasoning section for backward compatibility
+            return self.agent.i18n.retrieve("reasoning", "create_plan_prompt").format(
+                role=self.agent.role,
+                goal=self.agent.goal,
+                backstory=self._get_agent_backstory(),
+                description=self.description,
+                expected_output=self.expected_output,
+                tools=available_tools,
+            )
+
+    def _format_available_tools(self) -> str:
+        """Formats the available tools for inclusion in the prompt.
 
         Returns:
-            str: Comma-separated list of tool names.
+            Comma-separated list of tool names.
         """
         try:
-            return ", ".join(
-                [sanitize_tool_name(tool.name) for tool in (self.task.tools or [])]
-            )
+            # Try task tools first, then agent tools
+            tools = []
+            if self.task:
+                tools = self.task.tools or []
+            if not tools:
+                tools = getattr(self.agent, "tools", []) or []
+            if not tools:
+                return "No tools available"
+            return ", ".join([sanitize_tool_name(tool.name) for tool in tools])
         except (AttributeError, TypeError):
             return "No tools available"
 
-    def __create_refine_prompt(self, current_plan: str) -> str:
-        """
-        Creates a prompt for the agent to refine its reasoning plan.
+    def _create_refine_prompt(self, current_plan: str) -> str:
+        """Creates a prompt for the agent to refine its plan.
 
         Args:
-            current_plan: The current reasoning plan.
+            current_plan: The current plan.
 
         Returns:
-            str: The refine prompt.
+            The refine prompt.
         """
-        return self.agent.i18n.retrieve("reasoning", "refine_plan_prompt").format(
-            role=self.agent.role,
-            goal=self.agent.goal,
-            backstory=self.__get_agent_backstory(),
-            current_plan=current_plan,
-        )
+        # Use custom prompt if provided
+        if self.config.refine_prompt is not None:
+            return self.config.refine_prompt.format(
+                role=self.agent.role,
+                goal=self.agent.goal,
+                backstory=self._get_agent_backstory(),
+                current_plan=current_plan,
+                max_steps=self.config.max_steps,
+            )
+
+        # Try new "planning" section first
+        try:
+            return self.agent.i18n.retrieve("planning", "refine_plan_prompt").format(
+                current_plan=current_plan,
+            )
+        except (KeyError, AttributeError):
+            # Fallback to reasoning section for backward compatibility
+            return self.agent.i18n.retrieve("reasoning", "refine_plan_prompt").format(
+                role=self.agent.role,
+                goal=self.agent.goal,
+                backstory=self._get_agent_backstory(),
+                current_plan=current_plan,
+            )
 
     @staticmethod
-    def __parse_reasoning_response(response: str) -> tuple[str, bool]:
-        """
-        Parses the reasoning response to extract the plan and whether
-        the agent is ready to execute the task.
+    def _parse_planning_response(response: str) -> tuple[str, bool]:
+        """Parses the planning response to extract the plan and readiness.
 
         Args:
             response: The LLM response.
@@ -380,25 +619,13 @@ class AgentReasoning:
             return "No plan was generated.", False
 
         plan = response
-        ready = False
-
-        if "READY: I am ready to execute the task." in response:
-            ready = True
+        ready = "READY: I am ready to execute the task." in response
 
         return plan, ready
 
-    def _handle_agent_reasoning(self) -> AgentReasoningOutput:
-        """
-        Deprecated method for backward compatibility.
-        Use handle_agent_reasoning() instead.
 
-        Returns:
-            AgentReasoningOutput: The output of the agent reasoning process.
-        """
-        self.logger.warning(
-            "The _handle_agent_reasoning method is deprecated. Use handle_agent_reasoning instead."
-        )
-        return self.handle_agent_reasoning()
+# Alias for backward compatibility
+AgentPlanning = AgentReasoning
 
 
 def _call_llm_with_reasoning_prompt(
@@ -409,7 +636,9 @@ def _call_llm_with_reasoning_prompt(
     backstory: str,
     plan_type: Literal["initial_plan", "refine_plan"],
 ) -> str:
-    """Calls the LLM with the reasoning prompt.
+    """Deprecated: Calls the LLM with the reasoning prompt.
+
+    This function is kept for backward compatibility.
 
     Args:
         llm: The language model to use.
@@ -417,7 +646,7 @@ def _call_llm_with_reasoning_prompt(
         task: The task for which the agent is reasoning.
         reasoning_agent: The agent performing the reasoning.
         backstory: The agent's backstory.
-        plan_type: The type of plan being created ("initial_plan" or "refine_plan").
+        plan_type: The type of plan being created.
 
     Returns:
         The LLM response.

lib/crewai/tests/agents/test_agent.py

@@ -1456,7 +1456,7 @@ def test_agent_execute_task_with_tool():
     )
 
     result = agent.execute_task(task)
-    assert "you should always think about what to do" in result
+    assert "test query" in result
 
 
 @pytest.mark.vcr()
@@ -1475,9 +1475,9 @@ def test_agent_execute_task_with_custom_llm():
     )
 
     result = agent.execute_task(task)
-    assert "In circuits they thrive" in result
-    assert "Artificial minds awake" in result
-    assert "Future's coded drive" in result
+    assert "Artificial minds" in result
+    assert "Code and circuits" in result
+    assert "Future undefined" in result
 
 
 @pytest.mark.vcr()

lib/crewai/tests/agents/test_agent_executor.py

@@ -4,6 +4,7 @@ Tests the Flow-based agent executor implementation including state management,
 flow methods, routing logic, and error handling.
 """
 
+import time
 from unittest.mock import Mock, patch
 
 import pytest
@@ -25,6 +26,18 @@ class TestAgentReActState:
         assert state.current_answer is None
         assert state.is_finished is False
         assert state.ask_for_human_input is False
+        # Planning state fields
+        assert state.plan is None
+        assert state.plan_ready is False
+
+    def test_state_with_plan(self):
+        """Test AgentReActState initialization with planning fields."""
+        state = AgentReActState(
+            plan="Step 1: Do X\nStep 2: Do Y",
+            plan_ready=True,
+        )
+        assert state.plan == "Step 1: Do X\nStep 2: Do Y"
+        assert state.plan_ready is True
 
     def test_state_with_values(self):
         """Test AgentReActState initialization with values."""
@@ -462,3 +475,422 @@ class TestFlowInvoke:
 
         assert result == {"output": "Done"}
         assert len(executor.state.messages) >= 2
+
+
+class TestNativeToolExecution:
+    """Test native tool execution behavior."""
+
+    @pytest.fixture
+    def mock_dependencies(self):
+        llm = Mock()
+        llm.supports_stop_words.return_value = True
+
+        task = Mock()
+        task.name = "Test Task"
+        task.description = "Test"
+        task.human_input = False
+        task.response_model = None
+
+        crew = Mock()
+        crew._memory = None
+        crew.verbose = False
+        crew._train = False
+
+        agent = Mock()
+        agent.id = "test-agent-id"
+        agent.role = "Test Agent"
+        agent.verbose = False
+        agent.key = "test-key"
+
+        prompt = {"prompt": "Test {input} {tool_names} {tools}"}
+
+        tools_handler = Mock()
+        tools_handler.cache = None
+
+        return {
+            "llm": llm,
+            "task": task,
+            "crew": crew,
+            "agent": agent,
+            "prompt": prompt,
+            "max_iter": 10,
+            "tools": [],
+            "tools_names": "",
+            "stop_words": [],
+            "tools_description": "",
+            "tools_handler": tools_handler,
+        }
+
+    def test_execute_native_tool_runs_parallel_for_multiple_calls(
+        self, mock_dependencies
+    ):
+        executor = AgentExecutor(**mock_dependencies)
+
+        def slow_one() -> str:
+            time.sleep(0.2)
+            return "one"
+
+        def slow_two() -> str:
+            time.sleep(0.2)
+            return "two"
+
+        executor._available_functions = {"slow_one": slow_one, "slow_two": slow_two}
+        executor.state.pending_tool_calls = [
+            {
+                "id": "call_1",
+                "function": {"name": "slow_one", "arguments": "{}"},
+            },
+            {
+                "id": "call_2",
+                "function": {"name": "slow_two", "arguments": "{}"},
+            },
+        ]
+
+        started = time.perf_counter()
+        result = executor.execute_native_tool()
+        elapsed = time.perf_counter() - started
+
+        assert result == "native_tool_completed"
+        assert elapsed < 0.5
+        tool_messages = [m for m in executor.state.messages if m.get("role") == "tool"]
+        assert len(tool_messages) == 2
+        assert tool_messages[0]["tool_call_id"] == "call_1"
+        assert tool_messages[1]["tool_call_id"] == "call_2"
+
+    def test_execute_native_tool_falls_back_to_sequential_for_result_as_answer(
+        self, mock_dependencies
+    ):
+        executor = AgentExecutor(**mock_dependencies)
+
+        def slow_one() -> str:
+            time.sleep(0.2)
+            return "one"
+
+        def slow_two() -> str:
+            time.sleep(0.2)
+            return "two"
+
+        result_tool = Mock()
+        result_tool.name = "slow_one"
+        result_tool.result_as_answer = True
+        result_tool.max_usage_count = None
+        result_tool.current_usage_count = 0
+
+        executor.original_tools = [result_tool]
+        executor._available_functions = {"slow_one": slow_one, "slow_two": slow_two}
+        executor.state.pending_tool_calls = [
+            {
+                "id": "call_1",
+                "function": {"name": "slow_one", "arguments": "{}"},
+            },
+            {
+                "id": "call_2",
+                "function": {"name": "slow_two", "arguments": "{}"},
+            },
+        ]
+
+        started = time.perf_counter()
+        result = executor.execute_native_tool()
+        elapsed = time.perf_counter() - started
+
+        assert result == "tool_result_is_final"
+        assert elapsed >= 0.2
+        assert elapsed < 0.8
+        assert isinstance(executor.state.current_answer, AgentFinish)
+        assert executor.state.current_answer.output == "one"
+
+    def test_execute_native_tool_result_as_answer_short_circuits_remaining_calls(
+        self, mock_dependencies
+    ):
+        executor = AgentExecutor(**mock_dependencies)
+        call_counts = {"slow_one": 0, "slow_two": 0}
+
+        def slow_one() -> str:
+            call_counts["slow_one"] += 1
+            time.sleep(0.2)
+            return "one"
+
+        def slow_two() -> str:
+            call_counts["slow_two"] += 1
+            time.sleep(0.2)
+            return "two"
+
+        result_tool = Mock()
+        result_tool.name = "slow_one"
+        result_tool.result_as_answer = True
+        result_tool.max_usage_count = None
+        result_tool.current_usage_count = 0
+
+        executor.original_tools = [result_tool]
+        executor._available_functions = {"slow_one": slow_one, "slow_two": slow_two}
+        executor.state.pending_tool_calls = [
+            {
+                "id": "call_1",
+                "function": {"name": "slow_one", "arguments": "{}"},
+            },
+            {
+                "id": "call_2",
+                "function": {"name": "slow_two", "arguments": "{}"},
+            },
+        ]
+
+        started = time.perf_counter()
+        result = executor.execute_native_tool()
+        elapsed = time.perf_counter() - started
+
+        assert result == "tool_result_is_final"
+        assert isinstance(executor.state.current_answer, AgentFinish)
+        assert executor.state.current_answer.output == "one"
+        assert call_counts["slow_one"] == 1
+        assert call_counts["slow_two"] == 0
+        assert elapsed < 0.5
+
+        tool_messages = [m for m in executor.state.messages if m.get("role") == "tool"]
+        assert len(tool_messages) == 1
+        assert tool_messages[0]["tool_call_id"] == "call_1"
+
+
+class TestAgentExecutorPlanning:
+    """Test planning functionality in AgentExecutor with real agent kickoff."""
+
+    @pytest.mark.vcr()
+    def test_agent_kickoff_with_planning_stores_plan_in_state(self):
+        """Test that Agent.kickoff() with planning enabled stores plan in executor state."""
+        from crewai import Agent, PlanningConfig
+        from crewai.llm import LLM
+
+        llm = LLM("gpt-4o-mini")
+
+        agent = Agent(
+            role="Math Assistant",
+            goal="Help solve simple math problems",
+            backstory="A helpful assistant that solves math problems step by step",
+            llm=llm,
+            planning_config=PlanningConfig(max_attempts=1),
+            verbose=False,
+        )
+
+        # Execute kickoff with a simple task
+        result = agent.kickoff("What is 2 + 2?")
+
+        # Verify result
+        assert result is not None
+        assert "4" in str(result)
+
+    @pytest.mark.vcr()
+    def test_agent_kickoff_without_planning_skips_plan_generation(self):
+        """Test that Agent.kickoff() without planning skips planning phase."""
+        from crewai import Agent
+        from crewai.llm import LLM
+
+        llm = LLM("gpt-4o-mini")
+
+        agent = Agent(
+            role="Math Assistant",
+            goal="Help solve simple math problems",
+            backstory="A helpful assistant",
+            llm=llm,
+            # No planning_config = no planning
+            verbose=False,
+        )
+
+        # Execute kickoff
+        result = agent.kickoff("What is 3 + 3?")
+
+        # Verify we get a result
+        assert result is not None
+        assert "6" in str(result)
+
+    @pytest.mark.vcr()
+    def test_planning_disabled_skips_planning(self):
+        """Test that planning=False skips planning."""
+        from crewai import Agent
+        from crewai.llm import LLM
+
+        llm = LLM("gpt-4o-mini")
+
+        agent = Agent(
+            role="Math Assistant",
+            goal="Help solve simple math problems",
+            backstory="A helpful assistant",
+            llm=llm,
+            planning=False,  # Explicitly disable planning
+            verbose=False,
+        )
+
+        result = agent.kickoff("What is 5 + 5?")
+
+        # Should still complete successfully
+        assert result is not None
+        assert "10" in str(result)
+
+    def test_backward_compat_reasoning_true_enables_planning(self):
+        """Test that reasoning=True (deprecated) still enables planning."""
+        import warnings
+        from crewai import Agent
+        from crewai.llm import LLM
+
+        llm = LLM("gpt-4o-mini")
+
+        with warnings.catch_warnings(record=True):
+            warnings.simplefilter("always")
+            agent = Agent(
+                role="Test Agent",
+                goal="Complete tasks",
+                backstory="A helpful agent",
+                llm=llm,
+                reasoning=True,  # Deprecated but should still work
+                verbose=False,
+            )
+
+        # Should have planning_config created from reasoning=True
+        assert agent.planning_config is not None
+        assert agent.planning_enabled is True
+
+    @pytest.mark.vcr()
+    def test_executor_state_contains_plan_after_planning(self):
+        """Test that executor state contains plan after planning phase."""
+        from crewai import Agent, PlanningConfig
+        from crewai.llm import LLM
+        from crewai.experimental.agent_executor import AgentExecutor
+
+        llm = LLM("gpt-4o-mini")
+
+        agent = Agent(
+            role="Math Assistant",
+            goal="Help solve simple math problems",
+            backstory="A helpful assistant that solves math problems step by step",
+            llm=llm,
+            planning_config=PlanningConfig(max_attempts=1),
+            verbose=False,
+        )
+
+        # Track executor for inspection
+        executor_ref = [None]
+        original_invoke = AgentExecutor.invoke
+
+        def capture_executor(self, inputs):
+            executor_ref[0] = self
+            return original_invoke(self, inputs)
+
+        with patch.object(AgentExecutor, "invoke", capture_executor):
+            result = agent.kickoff("What is 7 + 7?")
+
+        # Verify result
+        assert result is not None
+
+        # If we captured an executor, check its state
+        if executor_ref[0] is not None:
+            # After planning, state should have plan info
+            assert hasattr(executor_ref[0].state, "plan")
+            assert hasattr(executor_ref[0].state, "plan_ready")
+
+    @pytest.mark.vcr()
+    def test_planning_creates_minimal_steps_for_multi_step_task(self):
+        """Test that planning creates only necessary steps for a multi-step task.
+
+        This task requires exactly 3 dependent steps:
+        1. Identify the first 3 prime numbers (2, 3, 5)
+        2. Sum them (2 + 3 + 5 = 10)
+        3. Multiply by 2 (10 * 2 = 20)
+
+        The plan should reflect these dependencies without unnecessary padding.
+        """
+        from crewai import Agent, PlanningConfig
+        from crewai.llm import LLM
+        from crewai.experimental.agent_executor import AgentExecutor
+
+        llm = LLM("gpt-4o-mini")
+
+        agent = Agent(
+            role="Math Tutor",
+            goal="Solve multi-step math problems accurately",
+            backstory="An expert math tutor who breaks down problems step by step",
+            llm=llm,
+            planning_config=PlanningConfig(max_attempts=1, max_steps=10),
+            verbose=False,
+        )
+
+        # Track the plan that gets generated
+        captured_plan = [None]
+        original_invoke = AgentExecutor.invoke
+
+        def capture_plan(self, inputs):
+            result = original_invoke(self, inputs)
+            captured_plan[0] = self.state.plan
+            return result
+
+        with patch.object(AgentExecutor, "invoke", capture_plan):
+            result = agent.kickoff(
+                "Calculate the sum of the first 3 prime numbers, then multiply that result by 2. "
+                "Show your work for each step."
+            )
+
+        # Verify result contains the correct answer (20)
+        assert result is not None
+        assert "20" in str(result)
+
+        # Verify a plan was generated
+        assert captured_plan[0] is not None
+
+        # The plan should be concise - this task needs ~3 steps, not 10+
+        plan_text = captured_plan[0]
+        # Count steps by looking for numbered items or bullet points
+        import re
+
+        step_pattern = r"^\s*\d+[\.\):]|\n\s*-\s+"
+        steps = re.findall(step_pattern, plan_text, re.MULTILINE)
+        # Plan should have roughly 3-5 steps, not fill up to max_steps
+        assert len(steps) <= 6, f"Plan has too many steps ({len(steps)}): {plan_text}"
+
+    @pytest.mark.vcr()
+    def test_planning_handles_sequential_dependency_task(self):
+        """Test planning for a task where step N depends on step N-1.
+
+        Task: Convert 100 Celsius to Fahrenheit, then round to nearest 10.
+        Step 1: Apply formula (C * 9/5 + 32) = 212
+        Step 2: Round 212 to nearest 10 = 210
+
+        This tests that the planner recognizes sequential dependencies.
+        """
+        from crewai import Agent, PlanningConfig
+        from crewai.llm import LLM
+        from crewai.experimental.agent_executor import AgentExecutor
+
+        llm = LLM("gpt-4o-mini")
+
+        agent = Agent(
+            role="Unit Converter",
+            goal="Accurately convert between units and apply transformations",
+            backstory="A precise unit conversion specialist",
+            llm=llm,
+            planning_config=PlanningConfig(max_attempts=1, max_steps=10),
+            verbose=False,
+        )
+
+        captured_plan = [None]
+        original_invoke = AgentExecutor.invoke
+
+        def capture_plan(self, inputs):
+            result = original_invoke(self, inputs)
+            captured_plan[0] = self.state.plan
+            return result
+
+        with patch.object(AgentExecutor, "invoke", capture_plan):
+            result = agent.kickoff(
+                "Convert 100 degrees Celsius to Fahrenheit, then round the result to the nearest 10."
+            )
+
+        assert result is not None
+        # 100C = 212F, rounded to nearest 10 = 210
+        assert "210" in str(result) or "212" in str(result)
+
+        # Plan should exist and be minimal (2-3 steps for this task)
+        assert captured_plan[0] is not None
+        plan_text = captured_plan[0]
+
+        import re
+
+        step_pattern = r"^\s*\d+[\.\):]|\n\s*-\s+"
+        steps = re.findall(step_pattern, plan_text, re.MULTILINE)
+        assert len(steps) <= 5, f"Plan should be minimal ({len(steps)} steps): {plan_text}"

lib/crewai/tests/agents/test_agent_reasoning.py

@@ -1,240 +1,345 @@
-"""Tests for reasoning in agents."""
+"""Tests for planning/reasoning in agents."""
 
-import json
+import warnings
 
 import pytest
 
-from crewai import Agent, Task
+from crewai import Agent, PlanningConfig, Task
 from crewai.llm import LLM
 
 
-@pytest.fixture
-def mock_llm_responses():
-    """Fixture for mock LLM responses."""
-    return {
-        "ready": "I'll solve this simple math problem.\n\nREADY: I am ready to execute the task.\n\n",
-        "not_ready": "I need to think about derivatives.\n\nNOT READY: I need to refine my plan because I'm not sure about the derivative rules.",
-        "ready_after_refine": "I'll use the power rule for derivatives where d/dx(x^n) = n*x^(n-1).\n\nREADY: I am ready to execute the task.",
-        "execution": "4",
-    }
+# =============================================================================
+# Tests for PlanningConfig configuration (no LLM calls needed)
+# =============================================================================
 
 
-def test_agent_with_reasoning(mock_llm_responses):
-    """Test agent with reasoning."""
-    llm = LLM("gpt-3.5-turbo")
+def test_planning_config_default_values():
+    """Test PlanningConfig default values."""
+    config = PlanningConfig()
+
+    assert config.max_attempts is None
+    assert config.max_steps == 20
+    assert config.system_prompt is None
+    assert config.plan_prompt is None
+    assert config.refine_prompt is None
+    assert config.llm is None
+
+
+def test_planning_config_custom_values():
+    """Test PlanningConfig with custom values."""
+    config = PlanningConfig(
+        max_attempts=5,
+        max_steps=15,
+        system_prompt="Custom system",
+        plan_prompt="Custom plan: {description}",
+        refine_prompt="Custom refine: {current_plan}",
+        llm="gpt-4",
+    )
+
+    assert config.max_attempts == 5
+    assert config.max_steps == 15
+    assert config.system_prompt == "Custom system"
+    assert config.plan_prompt == "Custom plan: {description}"
+    assert config.refine_prompt == "Custom refine: {current_plan}"
+    assert config.llm == "gpt-4"
+
+
+def test_agent_with_planning_config_custom_prompts():
+    """Test agent with PlanningConfig using custom prompts."""
+    llm = LLM("gpt-4o-mini")
+
+    custom_system_prompt = "You are a specialized planner."
+    custom_plan_prompt = "Plan this task: {description}"
+
+    agent = Agent(
+        role="Test Agent",
+        goal="To test custom prompts",
+        backstory="I am a test agent.",
+        llm=llm,
+        planning_config=PlanningConfig(
+            system_prompt=custom_system_prompt,
+            plan_prompt=custom_plan_prompt,
+            max_steps=10,
+        ),
+        verbose=False,
+    )
+
+    # Just test that the agent is created properly
+    assert agent.planning_config is not None
+    assert agent.planning_config.system_prompt == custom_system_prompt
+    assert agent.planning_config.plan_prompt == custom_plan_prompt
+    assert agent.planning_config.max_steps == 10
+
+
+def test_agent_with_planning_config_disabled():
+    """Test agent with PlanningConfig disabled."""
+    llm = LLM("gpt-4o-mini")
+
+    agent = Agent(
+        role="Test Agent",
+        goal="To test disabled planning",
+        backstory="I am a test agent.",
+        llm=llm,
+        planning=False,
+        verbose=False,
+    )
+
+    # Planning should be disabled
+    assert agent.planning_enabled is False
+
+
+def test_planning_enabled_property():
+    """Test the planning_enabled property on Agent."""
+    llm = LLM("gpt-4o-mini")
+
+    # With planning_config enabled
+    agent_with_planning = Agent(
+        role="Test Agent",
+        goal="Test",
+        backstory="Test",
+        llm=llm,
+        planning=True,
+    )
+    assert agent_with_planning.planning_enabled is True
+
+    # With planning_config disabled
+    agent_disabled = Agent(
+        role="Test Agent",
+        goal="Test",
+        backstory="Test",
+        llm=llm,
+        planning=False,
+    )
+    assert agent_disabled.planning_enabled is False
+
+    # Without planning_config
+    agent_no_planning = Agent(
+        role="Test Agent",
+        goal="Test",
+        backstory="Test",
+        llm=llm,
+    )
+    assert agent_no_planning.planning_enabled is False
+
+
+# =============================================================================
+# Tests for backward compatibility with reasoning=True (no LLM calls)
+# =============================================================================
+
+
+def test_agent_with_reasoning_backward_compat():
+    """Test agent with reasoning=True (backward compatibility)."""
+    llm = LLM("gpt-4o-mini")
+
+    # This should emit a deprecation warning
+    with warnings.catch_warnings(record=True):
+        warnings.simplefilter("always")
+        agent = Agent(
+            role="Test Agent",
+            goal="To test the reasoning feature",
+            backstory="I am a test agent created to verify the reasoning feature works correctly.",
+            llm=llm,
+            reasoning=True,
+            verbose=False,
+        )
+
+    # Should have created a PlanningConfig internally
+    assert agent.planning_config is not None
+    assert agent.planning_enabled is True
+
+
+def test_agent_with_reasoning_and_max_attempts_backward_compat():
+    """Test agent with reasoning=True and max_reasoning_attempts (backward compatibility)."""
+    llm = LLM("gpt-4o-mini")
 
     agent = Agent(
         role="Test Agent",
         goal="To test the reasoning feature",
-        backstory="I am a test agent created to verify the reasoning feature works correctly.",
+        backstory="I am a test agent.",
         llm=llm,
         reasoning=True,
-        verbose=True,
+        max_reasoning_attempts=5,
+        verbose=False,
     )
 
-    task = Task(
-        description="Simple math task: What's 2+2?",
-        expected_output="The answer should be a number.",
-        agent=agent,
-    )
-
-    agent.llm.call = lambda messages, *args, **kwargs: (
-        mock_llm_responses["ready"]
-        if any("create a detailed plan" in msg.get("content", "") for msg in messages)
-        else mock_llm_responses["execution"]
-    )
-
-    result = agent.execute_task(task)
-
-    assert result == mock_llm_responses["execution"]
-    assert "Reasoning Plan:" in task.description
+    # Should have created a PlanningConfig with max_attempts
+    assert agent.planning_config is not None
+    assert agent.planning_config.max_attempts == 5
 
 
-def test_agent_with_reasoning_not_ready_initially(mock_llm_responses):
-    """Test agent with reasoning that requires refinement."""
-    llm = LLM("gpt-3.5-turbo")
+# =============================================================================
+# Tests for Agent.kickoff() with planning (uses AgentExecutor)
+# =============================================================================
+
+
+@pytest.mark.vcr()
+def test_agent_kickoff_with_planning():
+    """Test Agent.kickoff() with planning enabled generates a plan."""
+    llm = LLM("gpt-4o-mini")
 
     agent = Agent(
-        role="Test Agent",
-        goal="To test the reasoning feature",
-        backstory="I am a test agent created to verify the reasoning feature works correctly.",
+        role="Math Assistant",
+        goal="Help solve math problems step by step",
+        backstory="A helpful math tutor",
         llm=llm,
-        reasoning=True,
-        max_reasoning_attempts=2,
-        verbose=True,
+        planning_config=PlanningConfig(max_attempts=1),
+        verbose=False,
     )
 
-    task = Task(
-        description="Complex math task: What's the derivative of x²?",
-        expected_output="The answer should be a mathematical expression.",
-        agent=agent,
-    )
+    result = agent.kickoff("What is 15 + 27?")
 
-    call_count = [0]
-
-    def mock_llm_call(messages, *args, **kwargs):
-        if any(
-            "create a detailed plan" in msg.get("content", "") for msg in messages
-        ) or any("refine your plan" in msg.get("content", "") for msg in messages):
-            call_count[0] += 1
-            if call_count[0] == 1:
-                return mock_llm_responses["not_ready"]
-            return mock_llm_responses["ready_after_refine"]
-        return "2x"
-
-    agent.llm.call = mock_llm_call
-
-    result = agent.execute_task(task)
-
-    assert result == "2x"
-    assert call_count[0] == 2  # Should have made 2 reasoning calls
-    assert "Reasoning Plan:" in task.description
+    assert result is not None
+    assert "42" in str(result)
 
 
-def test_agent_with_reasoning_max_attempts_reached():
-    """Test agent with reasoning that reaches max attempts without being ready."""
-    llm = LLM("gpt-3.5-turbo")
+@pytest.mark.vcr()
+def test_agent_kickoff_without_planning():
+    """Test Agent.kickoff() without planning skips plan generation."""
+    llm = LLM("gpt-4o-mini")
 
     agent = Agent(
-        role="Test Agent",
-        goal="To test the reasoning feature",
-        backstory="I am a test agent created to verify the reasoning feature works correctly.",
+        role="Math Assistant",
+        goal="Help solve math problems",
+        backstory="A helpful assistant",
         llm=llm,
-        reasoning=True,
-        max_reasoning_attempts=2,
-        verbose=True,
+        # No planning_config = no planning
+        verbose=False,
     )
 
-    task = Task(
-        description="Complex math task: Solve the Riemann hypothesis.",
-        expected_output="A proof or disproof of the hypothesis.",
-        agent=agent,
-    )
+    result = agent.kickoff("What is 8 * 7?")
 
-    call_count = [0]
-
-    def mock_llm_call(messages, *args, **kwargs):
-        if any(
-            "create a detailed plan" in msg.get("content", "") for msg in messages
-        ) or any("refine your plan" in msg.get("content", "") for msg in messages):
-            call_count[0] += 1
-            return f"Attempt {call_count[0]}: I need more time to think.\n\nNOT READY: I need to refine my plan further."
-        return "This is an unsolved problem in mathematics."
-
-    agent.llm.call = mock_llm_call
-
-    result = agent.execute_task(task)
-
-    assert result == "This is an unsolved problem in mathematics."
-    assert (
-        call_count[0] == 2
-    )  # Should have made exactly 2 reasoning calls (max_attempts)
-    assert "Reasoning Plan:" in task.description
+    assert result is not None
+    assert "56" in str(result)
 
 
-def test_agent_reasoning_error_handling():
-    """Test error handling during the reasoning process."""
-    llm = LLM("gpt-3.5-turbo")
+@pytest.mark.vcr()
+def test_agent_kickoff_with_planning_disabled():
+    """Test Agent.kickoff() with planning explicitly disabled via planning=False."""
+    llm = LLM("gpt-4o-mini")
 
     agent = Agent(
-        role="Test Agent",
-        goal="To test the reasoning feature",
-        backstory="I am a test agent created to verify the reasoning feature works correctly.",
+        role="Math Assistant",
+        goal="Help solve math problems",
+        backstory="A helpful assistant",
         llm=llm,
-        reasoning=True,
+        planning=False,  # Explicitly disable planning
+        verbose=False,
     )
 
-    task = Task(
-        description="Task that will cause an error",
-        expected_output="Output that will never be generated",
-        agent=agent,
-    )
+    result = agent.kickoff("What is 100 / 4?")
 
-    call_count = [0]
-
-    def mock_llm_call_error(*args, **kwargs):
-        call_count[0] += 1
-        if call_count[0] <= 2:  # First calls are for reasoning
-            raise Exception("LLM error during reasoning")
-        return "Fallback execution result"  # Return a value for task execution
-
-    agent.llm.call = mock_llm_call_error
-
-    result = agent.execute_task(task)
-
-    assert result == "Fallback execution result"
-    assert call_count[0] > 2  # Ensure we called the mock multiple times
+    assert result is not None
+    assert "25" in str(result)
 
 
-@pytest.mark.skip(reason="Test requires updates for native tool calling changes")
-def test_agent_with_function_calling():
-    """Test agent with reasoning using function calling."""
-    llm = LLM("gpt-3.5-turbo")
+@pytest.mark.vcr()
+def test_agent_kickoff_multi_step_task_with_planning():
+    """Test Agent.kickoff() with a multi-step task that benefits from planning."""
+    llm = LLM("gpt-4o-mini")
 
     agent = Agent(
-        role="Test Agent",
-        goal="To test the reasoning feature",
-        backstory="I am a test agent created to verify the reasoning feature works correctly.",
+        role="Math Tutor",
+        goal="Solve multi-step math problems",
+        backstory="An expert tutor who explains step by step",
         llm=llm,
-        reasoning=True,
-        verbose=True,
+        planning_config=PlanningConfig(max_attempts=1, max_steps=5),
+        verbose=False,
     )
 
-    task = Task(
-        description="Simple math task: What's 2+2?",
-        expected_output="The answer should be a number.",
-        agent=agent,
+    # Task requires: find primes, sum them, then double
+    result = agent.kickoff(
+        "Find the first 3 prime numbers, add them together, then multiply by 2."
     )
 
-    agent.llm.supports_function_calling = lambda: True
-
-    def mock_function_call(messages, *args, **kwargs):
-        if "tools" in kwargs:
-            return json.dumps(
-                {"plan": "I'll solve this simple math problem: 2+2=4.", "ready": True}
-            )
-        return "4"
-
-    agent.llm.call = mock_function_call
-
-    result = agent.execute_task(task)
-
-    assert result == "4"
-    assert "Reasoning Plan:" in task.description
-    assert "I'll solve this simple math problem: 2+2=4." in task.description
+    assert result is not None
+    # First 3 primes: 2, 3, 5 -> sum = 10 -> doubled = 20
+    assert "20" in str(result)
 
 
-@pytest.mark.skip(reason="Test requires updates for native tool calling changes")
-def test_agent_with_function_calling_fallback():
-    """Test agent with reasoning using function calling that falls back to text parsing."""
-    llm = LLM("gpt-3.5-turbo")
+# =============================================================================
+# Tests for Agent.execute_task() with planning (uses CrewAgentExecutor)
+# These test the legacy path via handle_reasoning()
+# =============================================================================
+
+
+@pytest.mark.vcr()
+def test_agent_execute_task_with_planning():
+    """Test Agent.execute_task() with planning via CrewAgentExecutor."""
+    llm = LLM("gpt-4o-mini")
 
     agent = Agent(
-        role="Test Agent",
-        goal="To test the reasoning feature",
-        backstory="I am a test agent created to verify the reasoning feature works correctly.",
+        role="Math Assistant",
+        goal="Help solve math problems",
+        backstory="A helpful math tutor",
         llm=llm,
-        reasoning=True,
-        verbose=True,
+        planning_config=PlanningConfig(max_attempts=1),
+        verbose=False,
     )
 
     task = Task(
-        description="Simple math task: What's 2+2?",
-        expected_output="The answer should be a number.",
+        description="What is 9 + 11?",
+        expected_output="A number",
         agent=agent,
     )
 
-    agent.llm.supports_function_calling = lambda: True
+    result = agent.execute_task(task)
 
-    def mock_function_call(messages, *args, **kwargs):
-        if "tools" in kwargs:
-            return "Invalid JSON that will trigger fallback. READY: I am ready to execute the task."
-        return "4"
+    assert result is not None
+    assert "20" in str(result)
+    # Planning should be appended to task description
+    assert "Planning:" in task.description
 
-    agent.llm.call = mock_function_call
+
+@pytest.mark.vcr()
+def test_agent_execute_task_without_planning():
+    """Test Agent.execute_task() without planning."""
+    llm = LLM("gpt-4o-mini")
+
+    agent = Agent(
+        role="Math Assistant",
+        goal="Help solve math problems",
+        backstory="A helpful assistant",
+        llm=llm,
+        verbose=False,
+    )
+
+    task = Task(
+        description="What is 12 * 3?",
+        expected_output="A number",
+        agent=agent,
+    )
 
     result = agent.execute_task(task)
 
-    assert result == "4"
-    assert "Reasoning Plan:" in task.description
-    assert "Invalid JSON that will trigger fallback" in task.description
+    assert result is not None
+    assert "36" in str(result)
+    # No planning should be added
+    assert "Planning:" not in task.description
+
+
+@pytest.mark.vcr()
+def test_agent_execute_task_with_planning_refine():
+    """Test Agent.execute_task() with planning that requires refinement."""
+    llm = LLM("gpt-4o-mini")
+
+    agent = Agent(
+        role="Math Tutor",
+        goal="Solve complex math problems step by step",
+        backstory="An expert tutor",
+        llm=llm,
+        planning_config=PlanningConfig(max_attempts=2),
+        verbose=False,
+    )
+
+    task = Task(
+        description="Calculate the area of a circle with radius 5 (use pi = 3.14)",
+        expected_output="The area as a number",
+        agent=agent,
+    )
+
+    result = agent.execute_task(task)
+
+    assert result is not None
+    # Area = pi * r^2 = 3.14 * 25 = 78.5
+    assert "78" in str(result) or "79" in str(result)
+    assert "Planning:" in task.description

lib/crewai/tests/agents/test_async_agent_executor.py

@@ -2,7 +2,7 @@
 
 import asyncio
 from typing import Any
-from unittest.mock import AsyncMock, MagicMock, patch
+from unittest.mock import AsyncMock, MagicMock, Mock, patch
 
 import pytest
 
@@ -291,6 +291,46 @@ class TestAsyncAgentExecutor:
         assert max_concurrent > 1, f"Expected concurrent execution, max concurrent was {max_concurrent}"
 
 
+class TestInvokeStepCallback:
+    """Tests for _invoke_step_callback with sync and async callbacks."""
+
+    def test_invoke_step_callback_with_sync_callback(
+        self, executor: CrewAgentExecutor
+    ) -> None:
+        """Test that a sync step callback is called normally."""
+        callback = Mock()
+        executor.step_callback = callback
+        answer = AgentFinish(thought="thinking", output="test", text="final")
+
+        executor._invoke_step_callback(answer)
+
+        callback.assert_called_once_with(answer)
+
+    def test_invoke_step_callback_with_async_callback(
+        self, executor: CrewAgentExecutor
+    ) -> None:
+        """Test that an async step callback is awaited via asyncio.run."""
+        async_callback = AsyncMock()
+        executor.step_callback = async_callback
+        answer = AgentFinish(thought="thinking", output="test", text="final")
+
+        with patch("crewai.agents.crew_agent_executor.asyncio.run") as mock_run:
+            executor._invoke_step_callback(answer)
+
+            async_callback.assert_called_once_with(answer)
+            mock_run.assert_called_once()
+
+    def test_invoke_step_callback_with_none(
+        self, executor: CrewAgentExecutor
+    ) -> None:
+        """Test that no error is raised when step_callback is None."""
+        executor.step_callback = None
+        answer = AgentFinish(thought="thinking", output="test", text="final")
+
+        # Should not raise
+        executor._invoke_step_callback(answer)
+
+
 class TestAsyncLLMResponseHelper:
     """Tests for aget_llm_response helper function."""
 

lib/crewai/tests/agents/test_native_tool_calling.py

@@ -6,13 +6,20 @@ when the LLM supports it, across multiple providers.
 
 from __future__ import annotations
 
+from collections.abc import Generator
 import os
+import threading
+import time
+from collections import Counter
 from unittest.mock import patch
 
 import pytest
 from pydantic import BaseModel, Field
 
 from crewai import Agent, Crew, Task
+from crewai.events import crewai_event_bus
+from crewai.hooks import register_after_tool_call_hook, register_before_tool_call_hook
+from crewai.hooks.tool_hooks import ToolCallHookContext
 from crewai.llm import LLM
 from crewai.tools.base_tool import BaseTool
 
@@ -64,6 +71,73 @@ class FailingTool(BaseTool):
     def _run(self) -> str:
         raise Exception("This tool always fails")
 
+
+class LocalSearchInput(BaseModel):
+    query: str = Field(description="Search query")
+
+
+class ParallelProbe:
+    """Thread-safe in-memory recorder for tool execution windows."""
+
+    _lock = threading.Lock()
+    _windows: list[tuple[str, float, float]] = []
+
+    @classmethod
+    def reset(cls) -> None:
+        with cls._lock:
+            cls._windows = []
+
+    @classmethod
+    def record(cls, tool_name: str, start: float, end: float) -> None:
+        with cls._lock:
+            cls._windows.append((tool_name, start, end))
+
+    @classmethod
+    def windows(cls) -> list[tuple[str, float, float]]:
+        with cls._lock:
+            return list(cls._windows)
+
+
+def _parallel_prompt() -> str:
+    return (
+        "This is a tool-calling compliance test. "
+        "In your next assistant turn, emit exactly 3 tool calls in the same response (parallel tool calls), in this order: "
+        "1) parallel_local_search_one(query='latest OpenAI model release notes'), "
+        "2) parallel_local_search_two(query='latest Anthropic model release notes'), "
+        "3) parallel_local_search_three(query='latest Gemini model release notes'). "
+        "Do not call any other tools and do not answer before those 3 tool calls are emitted. "
+        "After the tool results return, provide a one paragraph summary."
+    )
+
+
+def _max_concurrency(windows: list[tuple[str, float, float]]) -> int:
+    points: list[tuple[float, int]] = []
+    for _, start, end in windows:
+        points.append((start, 1))
+        points.append((end, -1))
+    points.sort(key=lambda p: (p[0], p[1]))
+
+    current = 0
+    maximum = 0
+    for _, delta in points:
+        current += delta
+        if current > maximum:
+            maximum = current
+    return maximum
+
+
+def _assert_tools_overlapped() -> None:
+    windows = ParallelProbe.windows()
+    local_windows = [
+        w
+        for w in windows
+        if w[0].startswith("parallel_local_search_")
+    ]
+
+    assert len(local_windows) >= 3, f"Expected at least 3 local tool calls, got {len(local_windows)}"
+    assert _max_concurrency(local_windows) >= 2, "Expected overlapping local tool executions"
+
+
 @pytest.fixture
 def calculator_tool() -> CalculatorTool:
     """Create a calculator tool for testing."""
@@ -82,6 +156,65 @@ def failing_tool() -> BaseTool:
 
     )
 
+
+@pytest.fixture
+def parallel_tools() -> list[BaseTool]:
+    """Create local tools used to verify native parallel execution deterministically."""
+
+    class ParallelLocalSearchOne(BaseTool):
+        name: str = "parallel_local_search_one"
+        description: str = "Local search tool #1 for concurrency testing."
+        args_schema: type[BaseModel] = LocalSearchInput
+
+        def _run(self, query: str) -> str:
+            start = time.perf_counter()
+            time.sleep(1.0)
+            end = time.perf_counter()
+            ParallelProbe.record(self.name, start, end)
+            return f"[one] {query}"
+
+    class ParallelLocalSearchTwo(BaseTool):
+        name: str = "parallel_local_search_two"
+        description: str = "Local search tool #2 for concurrency testing."
+        args_schema: type[BaseModel] = LocalSearchInput
+
+        def _run(self, query: str) -> str:
+            start = time.perf_counter()
+            time.sleep(1.0)
+            end = time.perf_counter()
+            ParallelProbe.record(self.name, start, end)
+            return f"[two] {query}"
+
+    class ParallelLocalSearchThree(BaseTool):
+        name: str = "parallel_local_search_three"
+        description: str = "Local search tool #3 for concurrency testing."
+        args_schema: type[BaseModel] = LocalSearchInput
+
+        def _run(self, query: str) -> str:
+            start = time.perf_counter()
+            time.sleep(1.0)
+            end = time.perf_counter()
+            ParallelProbe.record(self.name, start, end)
+            return f"[three] {query}"
+
+    return [
+        ParallelLocalSearchOne(),
+        ParallelLocalSearchTwo(),
+        ParallelLocalSearchThree(),
+    ]
+
+
+def _attach_parallel_probe_handler() -> None:
+    @crewai_event_bus.on(ToolUsageFinishedEvent)
+    def _capture_tool_window(_source, event: ToolUsageFinishedEvent):
+        if not event.tool_name.startswith("parallel_local_search_"):
+            return
+        ParallelProbe.record(
+            event.tool_name,
+            event.started_at.timestamp(),
+            event.finished_at.timestamp(),
+        )
+
 # =============================================================================
 # OpenAI Provider Tests
 # =============================================================================
@@ -122,7 +255,7 @@ class TestOpenAINativeToolCalling:
         self, calculator_tool: CalculatorTool
     ) -> None:
         """Test OpenAI agent kickoff with mocked LLM call."""
-        llm = LLM(model="gpt-4o-mini")
+        llm = LLM(model="gpt-5-nano")
 
         with patch.object(llm, "call", return_value="The answer is 120.") as mock_call:
             agent = Agent(
@@ -146,6 +279,174 @@ class TestOpenAINativeToolCalling:
             assert mock_call.called
             assert result is not None
 
+    @pytest.mark.vcr()
+    @pytest.mark.timeout(180)
+    def test_openai_parallel_native_tool_calling_test_crew(
+        self, parallel_tools: list[BaseTool]
+    ) -> None:
+        agent = Agent(
+            role="Parallel Tool Agent",
+            goal="Use both tools exactly as instructed",
+            backstory="You follow tool instructions precisely.",
+            tools=parallel_tools,
+            llm=LLM(model="gpt-5-nano", temperature=1),
+            verbose=False,
+            max_iter=3,
+        )
+        task = Task(
+            description=_parallel_prompt(),
+            expected_output="A one sentence summary of both tool outputs",
+            agent=agent,
+        )
+        crew = Crew(agents=[agent], tasks=[task])
+        result = crew.kickoff()
+        assert result is not None
+        _assert_tools_overlapped()
+
+    @pytest.mark.vcr()
+    @pytest.mark.timeout(180)
+    def test_openai_parallel_native_tool_calling_test_agent_kickoff(
+        self, parallel_tools: list[BaseTool]
+    ) -> None:
+        agent = Agent(
+            role="Parallel Tool Agent",
+            goal="Use both tools exactly as instructed",
+            backstory="You follow tool instructions precisely.",
+            tools=parallel_tools,
+            llm=LLM(model="gpt-4o-mini"),
+            verbose=False,
+            max_iter=3,
+        )
+        result = agent.kickoff(_parallel_prompt())
+        assert result is not None
+        _assert_tools_overlapped()
+
+    @pytest.mark.vcr()
+    @pytest.mark.timeout(180)
+    def test_openai_parallel_native_tool_calling_tool_hook_parity_crew(
+        self, parallel_tools: list[BaseTool]
+    ) -> None:
+        hook_calls: dict[str, list[dict[str, str]]] = {"before": [], "after": []}
+
+        def before_hook(context: ToolCallHookContext) -> bool | None:
+            if context.tool_name.startswith("parallel_local_search_"):
+                hook_calls["before"].append(
+                    {
+                        "tool_name": context.tool_name,
+                        "query": str(context.tool_input.get("query", "")),
+                    }
+                )
+            return None
+
+        def after_hook(context: ToolCallHookContext) -> str | None:
+            if context.tool_name.startswith("parallel_local_search_"):
+                hook_calls["after"].append(
+                    {
+                        "tool_name": context.tool_name,
+                        "query": str(context.tool_input.get("query", "")),
+                    }
+                )
+            return None
+
+        register_before_tool_call_hook(before_hook)
+        register_after_tool_call_hook(after_hook)
+
+        try:
+            agent = Agent(
+                role="Parallel Tool Agent",
+                goal="Use both tools exactly as instructed",
+                backstory="You follow tool instructions precisely.",
+                tools=parallel_tools,
+                llm=LLM(model="gpt-5-nano", temperature=1),
+                verbose=False,
+                max_iter=3,
+            )
+            task = Task(
+                description=_parallel_prompt(),
+                expected_output="A one sentence summary of both tool outputs",
+                agent=agent,
+            )
+            crew = Crew(agents=[agent], tasks=[task])
+            result = crew.kickoff()
+
+            assert result is not None
+            _assert_tools_overlapped()
+
+            before_names = [call["tool_name"] for call in hook_calls["before"]]
+            after_names = [call["tool_name"] for call in hook_calls["after"]]
+            assert len(before_names) >= 3, "Expected before hooks for all parallel calls"
+            assert Counter(before_names) == Counter(after_names)
+            assert all(call["query"] for call in hook_calls["before"])
+            assert all(call["query"] for call in hook_calls["after"])
+        finally:
+            from crewai.hooks import (
+                unregister_after_tool_call_hook,
+                unregister_before_tool_call_hook,
+            )
+
+            unregister_before_tool_call_hook(before_hook)
+            unregister_after_tool_call_hook(after_hook)
+
+    @pytest.mark.vcr()
+    @pytest.mark.timeout(180)
+    def test_openai_parallel_native_tool_calling_tool_hook_parity_agent_kickoff(
+        self, parallel_tools: list[BaseTool]
+    ) -> None:
+        hook_calls: dict[str, list[dict[str, str]]] = {"before": [], "after": []}
+
+        def before_hook(context: ToolCallHookContext) -> bool | None:
+            if context.tool_name.startswith("parallel_local_search_"):
+                hook_calls["before"].append(
+                    {
+                        "tool_name": context.tool_name,
+                        "query": str(context.tool_input.get("query", "")),
+                    }
+                )
+            return None
+
+        def after_hook(context: ToolCallHookContext) -> str | None:
+            if context.tool_name.startswith("parallel_local_search_"):
+                hook_calls["after"].append(
+                    {
+                        "tool_name": context.tool_name,
+                        "query": str(context.tool_input.get("query", "")),
+                    }
+                )
+            return None
+
+        register_before_tool_call_hook(before_hook)
+        register_after_tool_call_hook(after_hook)
+
+        try:
+            agent = Agent(
+                role="Parallel Tool Agent",
+                goal="Use both tools exactly as instructed",
+                backstory="You follow tool instructions precisely.",
+                tools=parallel_tools,
+                llm=LLM(model="gpt-5-nano", temperature=1),
+                verbose=False,
+                max_iter=3,
+            )
+            result = agent.kickoff(_parallel_prompt())
+
+            assert result is not None
+            _assert_tools_overlapped()
+
+            before_names = [call["tool_name"] for call in hook_calls["before"]]
+            after_names = [call["tool_name"] for call in hook_calls["after"]]
+            assert len(before_names) >= 3, "Expected before hooks for all parallel calls"
+            assert Counter(before_names) == Counter(after_names)
+            assert all(call["query"] for call in hook_calls["before"])
+            assert all(call["query"] for call in hook_calls["after"])
+        finally:
+            from crewai.hooks import (
+                unregister_after_tool_call_hook,
+                unregister_before_tool_call_hook,
+            )
+
+            unregister_before_tool_call_hook(before_hook)
+            unregister_after_tool_call_hook(after_hook)
+
 
 # =============================================================================
 # Anthropic Provider Tests
@@ -217,6 +518,46 @@ class TestAnthropicNativeToolCalling:
             assert mock_call.called
             assert result is not None
 
+    @pytest.mark.vcr()
+    def test_anthropic_parallel_native_tool_calling_test_crew(
+        self, parallel_tools: list[BaseTool]
+    ) -> None:
+        agent = Agent(
+            role="Parallel Tool Agent",
+            goal="Use both tools exactly as instructed",
+            backstory="You follow tool instructions precisely.",
+            tools=parallel_tools,
+            llm=LLM(model="anthropic/claude-sonnet-4-6"),
+            verbose=False,
+            max_iter=3,
+        )
+        task = Task(
+            description=_parallel_prompt(),
+            expected_output="A one sentence summary of both tool outputs",
+            agent=agent,
+        )
+        crew = Crew(agents=[agent], tasks=[task])
+        result = crew.kickoff()
+        assert result is not None
+        _assert_tools_overlapped()
+
+    @pytest.mark.vcr()
+    def test_anthropic_parallel_native_tool_calling_test_agent_kickoff(
+        self, parallel_tools: list[BaseTool]
+    ) -> None:
+        agent = Agent(
+            role="Parallel Tool Agent",
+            goal="Use both tools exactly as instructed",
+            backstory="You follow tool instructions precisely.",
+            tools=parallel_tools,
+            llm=LLM(model="anthropic/claude-sonnet-4-6"),
+            verbose=False,
+            max_iter=3,
+        )
+        result = agent.kickoff(_parallel_prompt())
+        assert result is not None
+        _assert_tools_overlapped()
+
 
 # =============================================================================
 # Google/Gemini Provider Tests
@@ -247,7 +588,7 @@ class TestGeminiNativeToolCalling:
             goal="Help users with mathematical calculations",
             backstory="You are a helpful math assistant.",
             tools=[calculator_tool],
-            llm=LLM(model="gemini/gemini-2.0-flash-exp"),
+            llm=LLM(model="gemini/gemini-2.5-flash"),
         )
 
         task = Task(
@@ -266,7 +607,7 @@ class TestGeminiNativeToolCalling:
         self, calculator_tool: CalculatorTool
     ) -> None:
         """Test Gemini agent kickoff with mocked LLM call."""
-        llm = LLM(model="gemini/gemini-2.0-flash-001")
+        llm = LLM(model="gemini/gemini-2.5-flash")
 
         with patch.object(llm, "call", return_value="The answer is 120.") as mock_call:
             agent = Agent(
@@ -290,6 +631,46 @@ class TestGeminiNativeToolCalling:
             assert mock_call.called
             assert result is not None
 
+    @pytest.mark.vcr()
+    def test_gemini_parallel_native_tool_calling_test_crew(
+        self, parallel_tools: list[BaseTool]
+    ) -> None:
+        agent = Agent(
+            role="Parallel Tool Agent",
+            goal="Use both tools exactly as instructed",
+            backstory="You follow tool instructions precisely.",
+            tools=parallel_tools,
+            llm=LLM(model="gemini/gemini-2.5-flash"),
+            verbose=False,
+            max_iter=3,
+        )
+        task = Task(
+            description=_parallel_prompt(),
+            expected_output="A one sentence summary of both tool outputs",
+            agent=agent,
+        )
+        crew = Crew(agents=[agent], tasks=[task])
+        result = crew.kickoff()
+        assert result is not None
+        _assert_tools_overlapped()
+
+    @pytest.mark.vcr()
+    def test_gemini_parallel_native_tool_calling_test_agent_kickoff(
+        self, parallel_tools: list[BaseTool]
+    ) -> None:
+        agent = Agent(
+            role="Parallel Tool Agent",
+            goal="Use both tools exactly as instructed",
+            backstory="You follow tool instructions precisely.",
+            tools=parallel_tools,
+            llm=LLM(model="gemini/gemini-2.5-flash"),
+            verbose=False,
+            max_iter=3,
+        )
+        result = agent.kickoff(_parallel_prompt())
+        assert result is not None
+        _assert_tools_overlapped()
+
 
 # =============================================================================
 # Azure Provider Tests
@@ -324,7 +705,7 @@ class TestAzureNativeToolCalling:
             goal="Help users with mathematical calculations",
             backstory="You are a helpful math assistant.",
             tools=[calculator_tool],
-            llm=LLM(model="azure/gpt-4o-mini"),
+            llm=LLM(model="azure/gpt-5-nano"),
             verbose=False,
             max_iter=3,
         )
@@ -347,7 +728,7 @@ class TestAzureNativeToolCalling:
     ) -> None:
         """Test Azure agent kickoff with mocked LLM call."""
         llm = LLM(
-            model="azure/gpt-4o-mini",
+            model="azure/gpt-5-nano",
             api_key="test-key",
             base_url="https://test.openai.azure.com",
         )
@@ -374,6 +755,46 @@ class TestAzureNativeToolCalling:
             assert mock_call.called
             assert result is not None
 
+    @pytest.mark.vcr()
+    def test_azure_parallel_native_tool_calling_test_crew(
+        self, parallel_tools: list[BaseTool]
+    ) -> None:
+        agent = Agent(
+            role="Parallel Tool Agent",
+            goal="Use both tools exactly as instructed",
+            backstory="You follow tool instructions precisely.",
+            tools=parallel_tools,
+            llm=LLM(model="azure/gpt-5-nano"),
+            verbose=False,
+            max_iter=3,
+        )
+        task = Task(
+            description=_parallel_prompt(),
+            expected_output="A one sentence summary of both tool outputs",
+            agent=agent,
+        )
+        crew = Crew(agents=[agent], tasks=[task])
+        result = crew.kickoff()
+        assert result is not None
+        _assert_tools_overlapped()
+
+    @pytest.mark.vcr()
+    def test_azure_parallel_native_tool_calling_test_agent_kickoff(
+        self, parallel_tools: list[BaseTool]
+    ) -> None:
+        agent = Agent(
+            role="Parallel Tool Agent",
+            goal="Use both tools exactly as instructed",
+            backstory="You follow tool instructions precisely.",
+            tools=parallel_tools,
+            llm=LLM(model="azure/gpt-5-nano"),
+            verbose=False,
+            max_iter=3,
+        )
+        result = agent.kickoff(_parallel_prompt())
+        assert result is not None
+        _assert_tools_overlapped()
+
 
 # =============================================================================
 # Bedrock Provider Tests
@@ -384,18 +805,30 @@ class TestBedrockNativeToolCalling:
     """Tests for native tool calling with AWS Bedrock models."""
 
     @pytest.fixture(autouse=True)
-    def mock_aws_env(self):
-        """Mock AWS environment variables for tests."""
-        env_vars = {
-        "AWS_ACCESS_KEY_ID": "test-key",
-        "AWS_SECRET_ACCESS_KEY": "test-secret",
-        "AWS_REGION": "us-east-1",
-        }
-        if "AWS_ACCESS_KEY_ID" not in os.environ:
-            with patch.dict(os.environ, env_vars):
-                yield
-        else:
-            yield
+    def validate_bedrock_credentials_for_live_recording(self):
+        """Run Bedrock tests only when explicitly enabled."""
+        run_live_bedrock = os.getenv("RUN_BEDROCK_LIVE_TESTS", "false").lower() == "true"
+
+        if not run_live_bedrock:
+            pytest.skip(
+                "Skipping Bedrock tests by default. "
+                "Set RUN_BEDROCK_LIVE_TESTS=true with valid AWS credentials to enable."
+            )
+
+        access_key = os.getenv("AWS_ACCESS_KEY_ID", "")
+        secret_key = os.getenv("AWS_SECRET_ACCESS_KEY", "")
+        if (
+            not access_key
+            or not secret_key
+            or access_key.startswith(("fake-", "test-"))
+            or secret_key.startswith(("fake-", "test-"))
+        ):
+            pytest.skip(
+                "Skipping Bedrock tests: valid AWS credentials are required when "
+                "RUN_BEDROCK_LIVE_TESTS=true."
+            )
+
+        yield
 
     @pytest.mark.vcr()
     def test_bedrock_agent_kickoff_with_tools_mocked(
@@ -427,6 +860,46 @@ class TestBedrockNativeToolCalling:
         assert result.raw is not None
         assert "120" in str(result.raw)
 
+    @pytest.mark.vcr()
+    def test_bedrock_parallel_native_tool_calling_test_crew(
+        self, parallel_tools: list[BaseTool]
+    ) -> None:
+        agent = Agent(
+            role="Parallel Tool Agent",
+            goal="Use both tools exactly as instructed",
+            backstory="You follow tool instructions precisely.",
+            tools=parallel_tools,
+            llm=LLM(model="bedrock/anthropic.claude-3-haiku-20240307-v1:0"),
+            verbose=False,
+            max_iter=3,
+        )
+        task = Task(
+            description=_parallel_prompt(),
+            expected_output="A one sentence summary of both tool outputs",
+            agent=agent,
+        )
+        crew = Crew(agents=[agent], tasks=[task])
+        result = crew.kickoff()
+        assert result is not None
+        _assert_tools_overlapped()
+
+    @pytest.mark.vcr()
+    def test_bedrock_parallel_native_tool_calling_test_agent_kickoff(
+        self, parallel_tools: list[BaseTool]
+    ) -> None:
+        agent = Agent(
+            role="Parallel Tool Agent",
+            goal="Use both tools exactly as instructed",
+            backstory="You follow tool instructions precisely.",
+            tools=parallel_tools,
+            llm=LLM(model="bedrock/anthropic.claude-3-haiku-20240307-v1:0"),
+            verbose=False,
+            max_iter=3,
+        )
+        result = agent.kickoff(_parallel_prompt())
+        assert result is not None
+        _assert_tools_overlapped()
+
 
 # =============================================================================
 # Cross-Provider Native Tool Calling Behavior Tests
@@ -439,7 +912,7 @@ class TestNativeToolCallingBehavior:
     def test_supports_function_calling_check(self) -> None:
         """Test that supports_function_calling() is properly checked."""
         # OpenAI should support function calling
-        openai_llm = LLM(model="gpt-4o-mini")
+        openai_llm = LLM(model="gpt-5-nano")
         assert hasattr(openai_llm, "supports_function_calling")
         assert openai_llm.supports_function_calling() is True
 
@@ -475,7 +948,7 @@ class TestNativeToolCallingTokenUsage:
             goal="Perform calculations efficiently",
             backstory="You calculate things.",
             tools=[calculator_tool],
-            llm=LLM(model="gpt-4o-mini"),
+            llm=LLM(model="gpt-5-nano"),
             verbose=False,
             max_iter=3,
         )
@@ -519,7 +992,7 @@ def test_native_tool_calling_error_handling(failing_tool: FailingTool):
         goal="Perform calculations efficiently",
         backstory="You calculate things.",
         tools=[failing_tool],
-        llm=LLM(model="gpt-4o-mini"),
+        llm=LLM(model="gpt-5-nano"),
         verbose=False,
         max_iter=3,
     )
@@ -578,7 +1051,7 @@ class TestMaxUsageCountWithNativeToolCalling:
             goal="Call the counting tool multiple times",
             backstory="You are an agent that counts things.",
             tools=[tool],
-            llm=LLM(model="gpt-4o-mini"),
+            llm=LLM(model="gpt-5-nano"),
             verbose=False,
             max_iter=5,
         )
@@ -606,7 +1079,7 @@ class TestMaxUsageCountWithNativeToolCalling:
             goal="Use the counting tool as many times as requested",
             backstory="You are an agent that counts things. You must try to use the tool for each value requested.",
             tools=[tool],
-            llm=LLM(model="gpt-4o-mini"),
+            llm=LLM(model="gpt-5-nano"),
             verbose=False,
             max_iter=5,
         )
@@ -638,7 +1111,7 @@ class TestMaxUsageCountWithNativeToolCalling:
             goal="Use the counting tool exactly as requested",
             backstory="You are an agent that counts things precisely.",
             tools=[tool],
-            llm=LLM(model="gpt-4o-mini"),
+            llm=LLM(model="gpt-5-nano"),
             verbose=False,
             max_iter=5,
         )
@@ -653,5 +1126,6 @@ class TestMaxUsageCountWithNativeToolCalling:
         result = crew.kickoff()
 
         assert result is not None
-        # Verify usage count was incremented for each successful call
-        assert tool.current_usage_count == 2
+        # Verify the requested calls occurred while keeping usage bounded.
+        assert tool.current_usage_count >= 2
+        assert tool.current_usage_count <= tool.max_usage_count

lib/crewai/tests/cassettes/agents/TestAgentExecutorPlanning.test_agent_kickoff_with_planning_stores_plan_in_state.yaml

@@ -0,0 +1,234 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are a strategic planning assistant.
+      Create minimal, effective execution plans. Prefer fewer steps over more."},{"role":"user","content":"Create
+      a focused execution plan for the following task:\n\n## Task\nWhat is 2 + 2?\n\n##
+      Expected Output\nComplete the task successfully\n\n## Available Tools\nNo tools
+      available\n\n## Instructions\nCreate ONLY the essential steps needed to complete
+      this task. Use the MINIMUM number of steps required - do NOT pad your plan with
+      unnecessary steps. Most tasks need only 2-5 steps.\n\nFor each step:\n- State
+      the specific action to take\n- Specify which tool to use (if any)\n\nDo NOT
+      include:\n- Setup or preparation steps that are obvious\n- Verification steps
+      unless critical\n- Documentation or cleanup steps unless explicitly required\n-
+      Generic steps like \"review results\" or \"finalize output\"\n\nAfter your plan,
+      state:\n- \"READY: I am ready to execute the task.\" if the plan is complete\n-
+      \"NOT READY: I need to refine my plan because [reason].\" if you need more thinking"}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
+      or refine a reasoning plan for a task","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"The
+      detailed reasoning plan for the task."},"ready":{"type":"boolean","description":"Whether
+      the agent is ready to execute the task."}},"required":["plan","ready"],"additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1541'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yTTAh68P65LybtqkwNI3p2HXcRv\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078147,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"## Execution Plan\\n\\n1. **Action:**
+        Perform the addition operation.  \\n   **Tool:** None (manually calculate).\\n\\n2.
+        **Action:** State the result.  \\n   **Tool:** None (manually output).\\n\\nREADY:
+        I am ready to execute the task.\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 281,\n    \"completion_tokens\":
+        56,\n    \"total_tokens\": 337,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:22:28 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '1165'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Math Assistant. A helpful
+      assistant that solves math problems step by step\nYour personal goal is: Help
+      solve simple math problems"},{"role":"user","content":"\nCurrent Task: What
+      is 2 + 2?\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '299'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yTVB9mdtq1YZrUVf1aSb6dVVQ8G\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078149,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"To solve the problem of 2 + 2, we simply
+        perform the addition:\\n\\n1. Start with the first number: 2\\n2. Add the
+        second number: + 2\\n3. Combine the two: 2 + 2 = 4\\n\\nTherefore, the answer
+        is 4.\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
+        \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+        \ \"usage\": {\n    \"prompt_tokens\": 54,\n    \"completion_tokens\": 62,\n
+        \   \"total_tokens\": 116,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:22:30 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '1300'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAgentExecutorPlanning.test_agent_kickoff_without_planning_skips_plan_generation.yaml

@@ -0,0 +1,108 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Math Assistant. A helpful
+      assistant\nYour personal goal is: Help solve simple math problems"},{"role":"user","content":"\nCurrent
+      Task: What is 3 + 3?\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '260'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yTTFxQ75llVmJv0ee902FIjXE8p\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078147,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"3 + 3 equals 6.\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        47,\n    \"completion_tokens\": 8,\n    \"total_tokens\": 55,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:22:27 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '401'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAgentExecutorPlanning.test_executor_state_contains_plan_after_planning.yaml

@@ -0,0 +1,230 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are a strategic planning assistant.
+      Create minimal, effective execution plans. Prefer fewer steps over more."},{"role":"user","content":"Create
+      a focused execution plan for the following task:\n\n## Task\nWhat is 7 + 7?\n\n##
+      Expected Output\nComplete the task successfully\n\n## Available Tools\nNo tools
+      available\n\n## Instructions\nCreate ONLY the essential steps needed to complete
+      this task. Use the MINIMUM number of steps required - do NOT pad your plan with
+      unnecessary steps. Most tasks need only 2-5 steps.\n\nFor each step:\n- State
+      the specific action to take\n- Specify which tool to use (if any)\n\nDo NOT
+      include:\n- Setup or preparation steps that are obvious\n- Verification steps
+      unless critical\n- Documentation or cleanup steps unless explicitly required\n-
+      Generic steps like \"review results\" or \"finalize output\"\n\nAfter your plan,
+      state:\n- \"READY: I am ready to execute the task.\" if the plan is complete\n-
+      \"NOT READY: I need to refine my plan because [reason].\" if you need more thinking"}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
+      or refine a reasoning plan for a task","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"The
+      detailed reasoning plan for the task."},"ready":{"type":"boolean","description":"Whether
+      the agent is ready to execute the task."}},"required":["plan","ready"],"additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1541'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yTdqlxwWowSdLncBERFrCgxTvVj\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078157,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"## Execution Plan\\n\\n1. Calculate
+        the sum of 7 and 7.\\n   \\nREADY: I am ready to execute the task.\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        281,\n    \"completion_tokens\": 28,\n    \"total_tokens\": 309,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:22:38 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '709'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Math Assistant. A helpful
+      assistant that solves math problems step by step\nYour personal goal is: Help
+      solve simple math problems"},{"role":"user","content":"\nCurrent Task: What
+      is 7 + 7?\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '299'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yTeB6Miecallw9SjSfLAXPjX2XD\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078158,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"To find the sum of 7 and 7, you simply
+        add the two numbers together:\\n\\n7 + 7 = 14\\n\\nSo, the answer is 14.\",\n
+        \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
+        null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        54,\n    \"completion_tokens\": 35,\n    \"total_tokens\": 89,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:22:38 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '733'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAgentExecutorPlanning.test_planning_config_disabled_skips_planning.yaml

@@ -0,0 +1,108 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Math Assistant. A helpful
+      assistant\nYour personal goal is: Help solve simple math problems"},{"role":"user","content":"\nCurrent
+      Task: What is 5 + 5?\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '260'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yTf8T2iADffpPCJBZhntLlaoaSy\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078159,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"5 + 5 equals 10.\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        47,\n    \"completion_tokens\": 8,\n    \"total_tokens\": 55,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:22:40 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '515'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAgentExecutorPlanning.test_planning_creates_minimal_steps_for_multi_step_task.yaml

@@ -0,0 +1,247 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are a strategic planning assistant.
+      Create minimal, effective execution plans. Prefer fewer steps over more."},{"role":"user","content":"Create
+      a focused execution plan for the following task:\n\n## Task\nCalculate the sum
+      of the first 3 prime numbers, then multiply that result by 2. Show your work
+      for each step.\n\n## Expected Output\nComplete the task successfully\n\n## Available
+      Tools\nNo tools available\n\n## Instructions\nCreate ONLY the essential steps
+      needed to complete this task. Use the MINIMUM number of steps required - do
+      NOT pad your plan with unnecessary steps. Most tasks need only 2-5 steps.\n\nFor
+      each step:\n- State the specific action to take\n- Specify which tool to use
+      (if any)\n\nDo NOT include:\n- Setup or preparation steps that are obvious\n-
+      Verification steps unless critical\n- Documentation or cleanup steps unless
+      explicitly required\n- Generic steps like \"review results\" or \"finalize output\"\n\nAfter
+      your plan, state:\n- \"READY: I am ready to execute the task.\" if the plan
+      is complete\n- \"NOT READY: I need to refine my plan because [reason].\" if
+      you need more thinking"}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
+      or refine a reasoning plan for a task","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"The
+      detailed reasoning plan for the task."},"ready":{"type":"boolean","description":"Whether
+      the agent is ready to execute the task."}},"required":["plan","ready"],"additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1636'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yTWa7FxCHkHwHF25AYXXeJDBOuY\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078150,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"## Execution Plan\\n\\n1. Identify
+        the first 3 prime numbers: 2, 3, and 5.\\n2. Calculate the sum: \\\\(2 + 3
+        + 5 = 10\\\\).\\n3. Multiply the sum by 2: \\\\(10 \\\\times 2 = 20\\\\).\\n\\nREADY:
+        I am ready to execute the task.\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 299,\n    \"completion_tokens\":
+        74,\n    \"total_tokens\": 373,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:22:32 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '1716'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Math Tutor. An expert
+      math tutor who breaks down problems step by step\nYour personal goal is: Solve
+      multi-step math problems accurately"},{"role":"user","content":"\nCurrent Task:
+      Calculate the sum of the first 3 prime numbers, then multiply that result by
+      2. Show your work for each step.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '400'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yTYJgCZf2oY7wiPMZmN4QEQhHb5\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078152,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"To solve the problem, let's break it
+        down into two main steps: \\n\\n1. Calculate the sum of the first 3 prime
+        numbers.\\n2. Multiply the result of that sum by 2.\\n\\n### Step 1: Identify
+        the first 3 prime numbers\\nPrime numbers are natural numbers greater than
+        1 that have no positive divisors other than 1 and themselves. \\n\\nThe first
+        three prime numbers are:\\n- 2\\n- 3\\n- 5\\n\\n### Step 2: Calculate the
+        sum of the first 3 prime numbers\\nNow, we add these prime numbers together:\\n\\n\\\\[\\n2
+        + 3 + 5\\n\\\\]\\n\\nCalculating this step-by-step:\\n- First, add 2 and 3:\\n
+        \ \\\\[\\n  2 + 3 = 5\\n  \\\\]\\n  \\n- Next, add this result to 5:\\n  \\\\[\\n
+        \ 5 + 5 = 10\\n  \\\\]\\n\\nSo, the sum of the first 3 prime numbers is \\\\(10\\\\).\\n\\n###
+        Step 3: Multiply the sum by 2\\nNext, we take the sum we calculated and multiply
+        it by 2:\\n\\n\\\\[\\n10 \\\\times 2\\n\\\\]\\n\\nCalculating this:\\n\\\\[\\n10
+        \\\\times 2 = 20\\n\\\\]\\n\\n### Final Answer\\nThus, the final result obtained
+        after performing all the steps is:\\n\\n\\\\[\\n\\\\boxed{20}\\n\\\\]\",\n
+        \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
+        null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        74,\n    \"completion_tokens\": 288,\n    \"total_tokens\": 362,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:22:37 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '4751'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAgentExecutorPlanning.test_planning_disabled_skips_planning.yaml

@@ -0,0 +1,108 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Math Assistant. A helpful
+      assistant\nYour personal goal is: Help solve simple math problems"},{"role":"user","content":"\nCurrent
+      Task: What is 5 + 5?\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '260'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yXGD5IrieoUDSK5hDmJyA2gJtDc\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078382,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"5 + 5 equals 10.\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        47,\n    \"completion_tokens\": 8,\n    \"total_tokens\": 55,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:26:23 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '363'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAgentExecutorPlanning.test_planning_handles_sequential_dependency_task.yaml

@@ -0,0 +1,242 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are a strategic planning assistant.
+      Create minimal, effective execution plans. Prefer fewer steps over more."},{"role":"user","content":"Create
+      a focused execution plan for the following task:\n\n## Task\nConvert 100 degrees
+      Celsius to Fahrenheit, then round the result to the nearest 10.\n\n## Expected
+      Output\nComplete the task successfully\n\n## Available Tools\nNo tools available\n\n##
+      Instructions\nCreate ONLY the essential steps needed to complete this task.
+      Use the MINIMUM number of steps required - do NOT pad your plan with unnecessary
+      steps. Most tasks need only 2-5 steps.\n\nFor each step:\n- State the specific
+      action to take\n- Specify which tool to use (if any)\n\nDo NOT include:\n- Setup
+      or preparation steps that are obvious\n- Verification steps unless critical\n-
+      Documentation or cleanup steps unless explicitly required\n- Generic steps like
+      \"review results\" or \"finalize output\"\n\nAfter your plan, state:\n- \"READY:
+      I am ready to execute the task.\" if the plan is complete\n- \"NOT READY: I
+      need to refine my plan because [reason].\" if you need more thinking"}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
+      or refine a reasoning plan for a task","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"The
+      detailed reasoning plan for the task."},"ready":{"type":"boolean","description":"Whether
+      the agent is ready to execute the task."}},"required":["plan","ready"],"additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1610'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yTN8fHOefyzzhvdUOHjxdFDR2HW\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078141,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"## Execution Plan\\n\\n1. Convert 100
+        degrees Celsius to Fahrenheit using the formula: \\\\( F = C \\\\times \\\\frac{9}{5}
+        + 32 \\\\).\\n2. Round the Fahrenheit result to the nearest 10.\\n\\nREADY:
+        I am ready to execute the task.\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 291,\n    \"completion_tokens\":
+        58,\n    \"total_tokens\": 349,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:22:22 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '1089'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Unit Converter. A precise
+      unit conversion specialist\nYour personal goal is: Accurately convert between
+      units and apply transformations"},{"role":"user","content":"\nCurrent Task:
+      Convert 100 degrees Celsius to Fahrenheit, then round the result to the nearest
+      10.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '373'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yTPQewXDyPdYHI4dHPH7YGHcRge\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078143,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"To convert degrees Celsius to Fahrenheit,
+        you can use the formula:\\n\\n\\\\[ F = \\\\left( C \\\\times \\\\frac{9}{5}
+        \\\\right) + 32 \\\\]\\n\\nPlugging in 100 degrees Celsius:\\n\\n\\\\[ F =
+        \\\\left( 100 \\\\times \\\\frac{9}{5} \\\\right) + 32 \\\\]\\n\\nCalculating
+        that step-by-step:\\n\\n1. Multiply 100 by 9: \\n   \\\\[ 100 \\\\times 9
+        = 900 \\\\]\\n\\n2. Divide by 5:\\n   \\\\[ 900 \\\\div 5 = 180 \\\\]\\n\\n3.
+        Add 32:\\n   \\\\[ 180 + 32 = 212 \\\\]\\n\\nSo, 100 degrees Celsius is equal
+        to 212 degrees Fahrenheit.\\n\\nNow, rounding 212 to the nearest 10:\\n\\nThe
+        nearest multiple of 10 to 212 is 210.\\n\\nTherefore, the final result is
+        **210 degrees Fahrenheit**.\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 63,\n    \"completion_tokens\":
+        191,\n    \"total_tokens\": 254,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:22:26 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '3736'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAnthropicNativeToolCalling.test_anthropic_parallel_native_tool_calling_test_agent_kickoff.yaml

@@ -0,0 +1,247 @@
+interactions:
+- request:
+    body: '{"max_tokens":4096,"messages":[{"role":"user","content":"\nCurrent Task:
+      This is a tool-calling compliance test. In your next assistant turn, emit exactly
+      3 tool calls in the same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary."}],"model":"claude-sonnet-4-6","stop_sequences":["\nObservation:"],"stream":false,"system":"You
+      are Parallel Tool Agent. You follow tool instructions precisely.\nYour personal
+      goal is: Use both tools exactly as instructed","tools":[{"name":"parallel_local_search_one","description":"Local
+      search tool #1 for concurrency testing.","input_schema":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}},{"name":"parallel_local_search_two","description":"Local
+      search tool #2 for concurrency testing.","input_schema":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}},{"name":"parallel_local_search_three","description":"Local
+      search tool #3 for concurrency testing.","input_schema":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      anthropic-version:
+      - '2023-06-01'
+      connection:
+      - keep-alive
+      content-length:
+      - '1639'
+      content-type:
+      - application/json
+      host:
+      - api.anthropic.com
+      x-api-key:
+      - X-API-KEY-XXX
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 0.73.0
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+      x-stainless-timeout:
+      - NOT_GIVEN
+    method: POST
+    uri: https://api.anthropic.com/v1/messages
+  response:
+    body:
+      string: '{"model":"claude-sonnet-4-6","id":"msg_01XeN1XTXZgmPyLMMGjivabb","type":"message","role":"assistant","content":[{"type":"text","text":"I''ll
+        execute all 3 parallel searches simultaneously right now!"},{"type":"tool_use","id":"toolu_01NwzvrxEz6tvT3A8ydvMtHu","name":"parallel_local_search_one","input":{"query":"latest
+        OpenAI model release notes"},"caller":{"type":"direct"}},{"type":"tool_use","id":"toolu_01YCxzSB1suk9uPVC1uwfHz9","name":"parallel_local_search_two","input":{"query":"latest
+        Anthropic model release notes"},"caller":{"type":"direct"}},{"type":"tool_use","id":"toolu_01Mauvxzv58eDY7pUt9HMKGy","name":"parallel_local_search_three","input":{"query":"latest
+        Gemini model release notes"},"caller":{"type":"direct"}}],"stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":914,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":169,"service_tier":"standard","inference_geo":"global"}}'
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Security-Policy:
+      - CSP-FILTERED
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 18 Feb 2026 23:54:43 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Robots-Tag:
+      - none
+      anthropic-organization-id:
+      - ANTHROPIC-ORGANIZATION-ID-XXX
+      anthropic-ratelimit-input-tokens-limit:
+      - ANTHROPIC-RATELIMIT-INPUT-TOKENS-LIMIT-XXX
+      anthropic-ratelimit-input-tokens-remaining:
+      - ANTHROPIC-RATELIMIT-INPUT-TOKENS-REMAINING-XXX
+      anthropic-ratelimit-input-tokens-reset:
+      - ANTHROPIC-RATELIMIT-INPUT-TOKENS-RESET-XXX
+      anthropic-ratelimit-output-tokens-limit:
+      - ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-LIMIT-XXX
+      anthropic-ratelimit-output-tokens-remaining:
+      - ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-REMAINING-XXX
+      anthropic-ratelimit-output-tokens-reset:
+      - ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-RESET-XXX
+      anthropic-ratelimit-requests-limit:
+      - '20000'
+      anthropic-ratelimit-requests-remaining:
+      - '19999'
+      anthropic-ratelimit-requests-reset:
+      - '2026-02-18T23:54:41Z'
+      anthropic-ratelimit-tokens-limit:
+      - ANTHROPIC-RATELIMIT-TOKENS-LIMIT-XXX
+      anthropic-ratelimit-tokens-remaining:
+      - ANTHROPIC-RATELIMIT-TOKENS-REMAINING-XXX
+      anthropic-ratelimit-tokens-reset:
+      - ANTHROPIC-RATELIMIT-TOKENS-RESET-XXX
+      cf-cache-status:
+      - DYNAMIC
+      request-id:
+      - REQUEST-ID-XXX
+      strict-transport-security:
+      - STS-XXX
+      x-envoy-upstream-service-time:
+      - '2099'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"max_tokens":4096,"messages":[{"role":"user","content":"\nCurrent Task:
+      This is a tool-calling compliance test. In your next assistant turn, emit exactly
+      3 tool calls in the same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary."},{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01NwzvrxEz6tvT3A8ydvMtHu","name":"parallel_local_search_one","input":{"query":"latest
+      OpenAI model release notes"}},{"type":"tool_use","id":"toolu_01YCxzSB1suk9uPVC1uwfHz9","name":"parallel_local_search_two","input":{"query":"latest
+      Anthropic model release notes"}},{"type":"tool_use","id":"toolu_01Mauvxzv58eDY7pUt9HMKGy","name":"parallel_local_search_three","input":{"query":"latest
+      Gemini model release notes"}}]},{"role":"user","content":[{"type":"tool_result","tool_use_id":"toolu_01NwzvrxEz6tvT3A8ydvMtHu","content":"[one]
+      latest OpenAI model release notes"},{"type":"tool_result","tool_use_id":"toolu_01YCxzSB1suk9uPVC1uwfHz9","content":"[two]
+      latest Anthropic model release notes"},{"type":"tool_result","tool_use_id":"toolu_01Mauvxzv58eDY7pUt9HMKGy","content":"[three]
+      latest Gemini model release notes"}]}],"model":"claude-sonnet-4-6","stop_sequences":["\nObservation:"],"stream":false,"system":"You
+      are Parallel Tool Agent. You follow tool instructions precisely.\nYour personal
+      goal is: Use both tools exactly as instructed","tools":[{"name":"parallel_local_search_one","description":"Local
+      search tool #1 for concurrency testing.","input_schema":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}},{"name":"parallel_local_search_two","description":"Local
+      search tool #2 for concurrency testing.","input_schema":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}},{"name":"parallel_local_search_three","description":"Local
+      search tool #3 for concurrency testing.","input_schema":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      anthropic-version:
+      - '2023-06-01'
+      connection:
+      - keep-alive
+      content-length:
+      - '2517'
+      content-type:
+      - application/json
+      host:
+      - api.anthropic.com
+      x-api-key:
+      - X-API-KEY-XXX
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 0.73.0
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+      x-stainless-timeout:
+      - NOT_GIVEN
+    method: POST
+    uri: https://api.anthropic.com/v1/messages
+  response:
+    body:
+      string: "{\"model\":\"claude-sonnet-4-6\",\"id\":\"msg_01PFXqwwdwwHWadPdtNU5tUZ\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":\"The
+        three parallel searches were executed successfully, each targeting the latest
+        release notes for the leading AI model families. The search results confirm
+        that queries were dispatched simultaneously to retrieve the most recent developments
+        from **OpenAI** (via tool one), **Anthropic** (via tool two), and **Google's
+        Gemini** (via tool three). While the local search tools returned placeholder
+        outputs in this test environment rather than detailed release notes, the structure
+        of the test validates that all three parallel tool calls were emitted correctly
+        and in the specified order \u2014 demonstrating proper concurrent tool-call
+        behavior with no dependencies between the three independent searches.\"}],\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"usage\":{\"input_tokens\":1197,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_tokens\":131,\"service_tier\":\"standard\",\"inference_geo\":\"global\"}}"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Security-Policy:
+      - CSP-FILTERED
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 18 Feb 2026 23:54:49 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Robots-Tag:
+      - none
+      anthropic-organization-id:
+      - ANTHROPIC-ORGANIZATION-ID-XXX
+      anthropic-ratelimit-input-tokens-limit:
+      - ANTHROPIC-RATELIMIT-INPUT-TOKENS-LIMIT-XXX
+      anthropic-ratelimit-input-tokens-remaining:
+      - ANTHROPIC-RATELIMIT-INPUT-TOKENS-REMAINING-XXX
+      anthropic-ratelimit-input-tokens-reset:
+      - ANTHROPIC-RATELIMIT-INPUT-TOKENS-RESET-XXX
+      anthropic-ratelimit-output-tokens-limit:
+      - ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-LIMIT-XXX
+      anthropic-ratelimit-output-tokens-remaining:
+      - ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-REMAINING-XXX
+      anthropic-ratelimit-output-tokens-reset:
+      - ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-RESET-XXX
+      anthropic-ratelimit-requests-limit:
+      - '20000'
+      anthropic-ratelimit-requests-remaining:
+      - '19999'
+      anthropic-ratelimit-requests-reset:
+      - '2026-02-18T23:54:44Z'
+      anthropic-ratelimit-tokens-limit:
+      - ANTHROPIC-RATELIMIT-TOKENS-LIMIT-XXX
+      anthropic-ratelimit-tokens-remaining:
+      - ANTHROPIC-RATELIMIT-TOKENS-REMAINING-XXX
+      anthropic-ratelimit-tokens-reset:
+      - ANTHROPIC-RATELIMIT-TOKENS-RESET-XXX
+      cf-cache-status:
+      - DYNAMIC
+      request-id:
+      - REQUEST-ID-XXX
+      strict-transport-security:
+      - STS-XXX
+      x-envoy-upstream-service-time:
+      - '4092'
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAnthropicNativeToolCalling.test_anthropic_parallel_native_tool_calling_test_crew.yaml

@@ -0,0 +1,254 @@
+interactions:
+- request:
+    body: '{"max_tokens":4096,"messages":[{"role":"user","content":"\nCurrent Task:
+      This is a tool-calling compliance test. In your next assistant turn, emit exactly
+      3 tool calls in the same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary.\n\nThis is the expected criteria for your final answer: A
+      one sentence summary of both tool outputs\nyou MUST return the actual complete
+      content as the final answer, not a summary."}],"model":"claude-sonnet-4-6","stop_sequences":["\nObservation:"],"stream":false,"system":"You
+      are Parallel Tool Agent. You follow tool instructions precisely.\nYour personal
+      goal is: Use both tools exactly as instructed","tools":[{"name":"parallel_local_search_one","description":"Local
+      search tool #1 for concurrency testing.","input_schema":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}},{"name":"parallel_local_search_two","description":"Local
+      search tool #2 for concurrency testing.","input_schema":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}},{"name":"parallel_local_search_three","description":"Local
+      search tool #3 for concurrency testing.","input_schema":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      anthropic-version:
+      - '2023-06-01'
+      connection:
+      - keep-alive
+      content-length:
+      - '1820'
+      content-type:
+      - application/json
+      host:
+      - api.anthropic.com
+      x-api-key:
+      - X-API-KEY-XXX
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 0.73.0
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+      x-stainless-timeout:
+      - NOT_GIVEN
+    method: POST
+    uri: https://api.anthropic.com/v1/messages
+  response:
+    body:
+      string: '{"model":"claude-sonnet-4-6","id":"msg_01RJ4CphwpmkmsJFJjeCNvXz","type":"message","role":"assistant","content":[{"type":"text","text":"I''ll
+        execute all 3 parallel tool calls simultaneously right away!"},{"type":"tool_use","id":"toolu_01YWY3cSomRuv4USmq55Prk3","name":"parallel_local_search_one","input":{"query":"latest
+        OpenAI model release notes"},"caller":{"type":"direct"}},{"type":"tool_use","id":"toolu_01Aaqj3LMXksE1nB3pscRhV5","name":"parallel_local_search_two","input":{"query":"latest
+        Anthropic model release notes"},"caller":{"type":"direct"}},{"type":"tool_use","id":"toolu_01AcYxQvy8aYmAoUg9zx9qfq","name":"parallel_local_search_three","input":{"query":"latest
+        Gemini model release notes"},"caller":{"type":"direct"}}],"stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":951,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":170,"service_tier":"standard","inference_geo":"global"}}'
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Security-Policy:
+      - CSP-FILTERED
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 18 Feb 2026 23:54:51 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Robots-Tag:
+      - none
+      anthropic-organization-id:
+      - ANTHROPIC-ORGANIZATION-ID-XXX
+      anthropic-ratelimit-input-tokens-limit:
+      - ANTHROPIC-RATELIMIT-INPUT-TOKENS-LIMIT-XXX
+      anthropic-ratelimit-input-tokens-remaining:
+      - ANTHROPIC-RATELIMIT-INPUT-TOKENS-REMAINING-XXX
+      anthropic-ratelimit-input-tokens-reset:
+      - ANTHROPIC-RATELIMIT-INPUT-TOKENS-RESET-XXX
+      anthropic-ratelimit-output-tokens-limit:
+      - ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-LIMIT-XXX
+      anthropic-ratelimit-output-tokens-remaining:
+      - ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-REMAINING-XXX
+      anthropic-ratelimit-output-tokens-reset:
+      - ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-RESET-XXX
+      anthropic-ratelimit-requests-limit:
+      - '20000'
+      anthropic-ratelimit-requests-remaining:
+      - '19999'
+      anthropic-ratelimit-requests-reset:
+      - '2026-02-18T23:54:49Z'
+      anthropic-ratelimit-tokens-limit:
+      - ANTHROPIC-RATELIMIT-TOKENS-LIMIT-XXX
+      anthropic-ratelimit-tokens-remaining:
+      - ANTHROPIC-RATELIMIT-TOKENS-REMAINING-XXX
+      anthropic-ratelimit-tokens-reset:
+      - ANTHROPIC-RATELIMIT-TOKENS-RESET-XXX
+      cf-cache-status:
+      - DYNAMIC
+      request-id:
+      - REQUEST-ID-XXX
+      strict-transport-security:
+      - STS-XXX
+      x-envoy-upstream-service-time:
+      - '1967'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"max_tokens":4096,"messages":[{"role":"user","content":"\nCurrent Task:
+      This is a tool-calling compliance test. In your next assistant turn, emit exactly
+      3 tool calls in the same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary.\n\nThis is the expected criteria for your final answer: A
+      one sentence summary of both tool outputs\nyou MUST return the actual complete
+      content as the final answer, not a summary."},{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01YWY3cSomRuv4USmq55Prk3","name":"parallel_local_search_one","input":{"query":"latest
+      OpenAI model release notes"}},{"type":"tool_use","id":"toolu_01Aaqj3LMXksE1nB3pscRhV5","name":"parallel_local_search_two","input":{"query":"latest
+      Anthropic model release notes"}},{"type":"tool_use","id":"toolu_01AcYxQvy8aYmAoUg9zx9qfq","name":"parallel_local_search_three","input":{"query":"latest
+      Gemini model release notes"}}]},{"role":"user","content":[{"type":"tool_result","tool_use_id":"toolu_01YWY3cSomRuv4USmq55Prk3","content":"[one]
+      latest OpenAI model release notes"},{"type":"tool_result","tool_use_id":"toolu_01Aaqj3LMXksE1nB3pscRhV5","content":"[two]
+      latest Anthropic model release notes"},{"type":"tool_result","tool_use_id":"toolu_01AcYxQvy8aYmAoUg9zx9qfq","content":"[three]
+      latest Gemini model release notes"}]},{"role":"user","content":"Analyze the
+      tool result. If requirements are met, provide the Final Answer. Otherwise, call
+      the next tool. Deliver only the answer without meta-commentary."}],"model":"claude-sonnet-4-6","stop_sequences":["\nObservation:"],"stream":false,"system":"You
+      are Parallel Tool Agent. You follow tool instructions precisely.\nYour personal
+      goal is: Use both tools exactly as instructed","tools":[{"name":"parallel_local_search_one","description":"Local
+      search tool #1 for concurrency testing.","input_schema":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}},{"name":"parallel_local_search_two","description":"Local
+      search tool #2 for concurrency testing.","input_schema":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}},{"name":"parallel_local_search_three","description":"Local
+      search tool #3 for concurrency testing.","input_schema":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      anthropic-version:
+      - '2023-06-01'
+      connection:
+      - keep-alive
+      content-length:
+      - '2882'
+      content-type:
+      - application/json
+      host:
+      - api.anthropic.com
+      x-api-key:
+      - X-API-KEY-XXX
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 0.73.0
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+      x-stainless-timeout:
+      - NOT_GIVEN
+    method: POST
+    uri: https://api.anthropic.com/v1/messages
+  response:
+    body:
+      string: "{\"model\":\"claude-sonnet-4-6\",\"id\":\"msg_0143MHUne1az3Tt69EoLjyZd\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":\"Here
+        is the complete content returned from all three tool calls:\\n\\n- **parallel_local_search_one**
+        result: `[one] latest OpenAI model release notes`\\n- **parallel_local_search_two**
+        result: `[two] latest Anthropic model release notes`\\n- **parallel_local_search_three**
+        result: `[three] latest Gemini model release notes`\\n\\nAll three parallel
+        tool calls were executed successfully in the same response turn, returning
+        their respective outputs: the first tool searched for the latest OpenAI model
+        release notes, the second tool searched for the latest Anthropic model release
+        notes, and the third tool searched for the latest Gemini model release notes
+        \u2014 confirming that all search queries were dispatched concurrently and
+        their results retrieved as expected.\"}],\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"usage\":{\"input_tokens\":1272,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_tokens\":172,\"service_tier\":\"standard\",\"inference_geo\":\"global\"}}"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Security-Policy:
+      - CSP-FILTERED
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 18 Feb 2026 23:54:55 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Robots-Tag:
+      - none
+      anthropic-organization-id:
+      - ANTHROPIC-ORGANIZATION-ID-XXX
+      anthropic-ratelimit-input-tokens-limit:
+      - ANTHROPIC-RATELIMIT-INPUT-TOKENS-LIMIT-XXX
+      anthropic-ratelimit-input-tokens-remaining:
+      - ANTHROPIC-RATELIMIT-INPUT-TOKENS-REMAINING-XXX
+      anthropic-ratelimit-input-tokens-reset:
+      - ANTHROPIC-RATELIMIT-INPUT-TOKENS-RESET-XXX
+      anthropic-ratelimit-output-tokens-limit:
+      - ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-LIMIT-XXX
+      anthropic-ratelimit-output-tokens-remaining:
+      - ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-REMAINING-XXX
+      anthropic-ratelimit-output-tokens-reset:
+      - ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-RESET-XXX
+      anthropic-ratelimit-requests-limit:
+      - '20000'
+      anthropic-ratelimit-requests-remaining:
+      - '19999'
+      anthropic-ratelimit-requests-reset:
+      - '2026-02-18T23:54:52Z'
+      anthropic-ratelimit-tokens-limit:
+      - ANTHROPIC-RATELIMIT-TOKENS-LIMIT-XXX
+      anthropic-ratelimit-tokens-remaining:
+      - ANTHROPIC-RATELIMIT-TOKENS-REMAINING-XXX
+      anthropic-ratelimit-tokens-reset:
+      - ANTHROPIC-RATELIMIT-TOKENS-RESET-XXX
+      cf-cache-status:
+      - DYNAMIC
+      request-id:
+      - REQUEST-ID-XXX
+      strict-transport-security:
+      - STS-XXX
+      x-envoy-upstream-service-time:
+      - '3144'
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAzureNativeToolCalling.test_azure_agent_with_native_tool_calling.yaml

@@ -5,20 +5,19 @@ interactions:
       calculations"}, {"role": "user", "content": "\nCurrent Task: Calculate what
       is 15 * 8\n\nThis is the expected criteria for your final answer: The result
       of the calculation\nyou MUST return the actual complete content as the final
-      answer, not a summary.\n\nThis is VERY important to you, your job depends on
-      it!"}], "stream": false, "stop": ["\nObservation:"], "tool_choice": "auto",
-      "tools": [{"function": {"name": "calculator", "description": "Perform mathematical
-      calculations. Use this for any math operations.", "parameters": {"properties":
-      {"expression": {"description": "Mathematical expression to evaluate", "title":
-      "Expression", "type": "string"}}, "required": ["expression"], "type": "object"}},
-      "type": "function"}]}'
+      answer, not a summary."}], "stream": false, "tool_choice": "auto", "tools":
+      [{"function": {"name": "calculator", "description": "Perform mathematical calculations.
+      Use this for any math operations.", "parameters": {"properties": {"expression":
+      {"description": "Mathematical expression to evaluate", "title": "Expression",
+      "type": "string"}}, "required": ["expression"], "type": "object", "additionalProperties":
+      false}}, "type": "function"}]}'
     headers:
       Accept:
       - application/json
       Connection:
       - keep-alive
       Content-Length:
-      - '883'
+      - '828'
       Content-Type:
       - application/json
       User-Agent:
@@ -32,20 +31,20 @@ interactions:
       x-ms-client-request-id:
       - X-MS-CLIENT-REQUEST-ID-XXX
     method: POST
-    uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-4o-mini/chat/completions?api-version=2024-12-01-preview
+    uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-5-nano/chat/completions?api-version=2024-12-01-preview
   response:
     body:
       string: '{"choices":[{"content_filter_results":{},"finish_reason":"tool_calls","index":0,"logprobs":null,"message":{"annotations":[],"content":null,"refusal":null,"role":"assistant","tool_calls":[{"function":{"arguments":"{\"expression\":\"15
-        * 8\"}","name":"calculator"},"id":"call_cJWzKh5LdBpY3Sk8GATS3eRe","type":"function"}]}}],"created":1769122114,"id":"chatcmpl-D0xlavS0V3m00B9Fsjyv39xQWUGFV","model":"gpt-4o-mini-2024-07-18","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":"fp_f97eff32c5","usage":{"completion_tokens":18,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":0,"rejected_prediction_tokens":0},"prompt_tokens":137,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":155}}
+        * 8\"}","name":"calculator"},"id":"call_Cow46pNllpDx0pxUgZFeqlh1","type":"function"}]}}],"created":1771459544,"id":"chatcmpl-DAlq4osCP9ABJ1HyXFBoYWylMg0bi","model":"gpt-5-nano-2025-08-07","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":null,"usage":{"completion_tokens":219,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":192,"rejected_prediction_tokens":0},"prompt_tokens":208,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":427}}
 
         '
     headers:
       Content-Length:
-      - '1058'
+      - '1049'
       Content-Type:
       - application/json
       Date:
-      - Thu, 22 Jan 2026 22:48:34 GMT
+      - Thu, 19 Feb 2026 00:05:45 GMT
       Strict-Transport-Security:
       - STS-XXX
       apim-request-id:
@@ -59,7 +58,7 @@ interactions:
       x-ms-client-request-id:
       - X-MS-CLIENT-REQUEST-ID-XXX
       x-ms-deployment-name:
-      - gpt-4o-mini
+      - gpt-5-nano
       x-ms-rai-invoked:
       - 'true'
       x-ms-region:
@@ -83,26 +82,25 @@ interactions:
       calculations"}, {"role": "user", "content": "\nCurrent Task: Calculate what
       is 15 * 8\n\nThis is the expected criteria for your final answer: The result
       of the calculation\nyou MUST return the actual complete content as the final
-      answer, not a summary.\n\nThis is VERY important to you, your job depends on
-      it!"}, {"role": "assistant", "content": "", "tool_calls": [{"id": "call_cJWzKh5LdBpY3Sk8GATS3eRe",
-      "type": "function", "function": {"name": "calculator", "arguments": "{\"expression\":\"15
-      * 8\"}"}}]}, {"role": "tool", "tool_call_id": "call_cJWzKh5LdBpY3Sk8GATS3eRe",
-      "content": "The result of 15 * 8 is 120"}, {"role": "user", "content": "Analyze
-      the tool result. If requirements are met, provide the Final Answer. Otherwise,
-      call the next tool. Deliver only the answer without meta-commentary."}], "stream":
-      false, "stop": ["\nObservation:"], "tool_choice": "auto", "tools": [{"function":
-      {"name": "calculator", "description": "Perform mathematical calculations. Use
-      this for any math operations.", "parameters": {"properties": {"expression":
-      {"description": "Mathematical expression to evaluate", "title": "Expression",
-      "type": "string"}}, "required": ["expression"], "type": "object"}}, "type":
-      "function"}]}'
+      answer, not a summary."}, {"role": "assistant", "content": "", "tool_calls":
+      [{"id": "call_Cow46pNllpDx0pxUgZFeqlh1", "type": "function", "function": {"name":
+      "calculator", "arguments": "{\"expression\":\"15 * 8\"}"}}]}, {"role": "tool",
+      "tool_call_id": "call_Cow46pNllpDx0pxUgZFeqlh1", "content": "The result of 15
+      * 8 is 120"}, {"role": "user", "content": "Analyze the tool result. If requirements
+      are met, provide the Final Answer. Otherwise, call the next tool. Deliver only
+      the answer without meta-commentary."}], "stream": false, "tool_choice": "auto",
+      "tools": [{"function": {"name": "calculator", "description": "Perform mathematical
+      calculations. Use this for any math operations.", "parameters": {"properties":
+      {"expression": {"description": "Mathematical expression to evaluate", "title":
+      "Expression", "type": "string"}}, "required": ["expression"], "type": "object",
+      "additionalProperties": false}}, "type": "function"}]}'
     headers:
       Accept:
       - application/json
       Connection:
       - keep-alive
       Content-Length:
-      - '1375'
+      - '1320'
       Content-Type:
       - application/json
       User-Agent:
@@ -116,20 +114,19 @@ interactions:
       x-ms-client-request-id:
       - X-MS-CLIENT-REQUEST-ID-XXX
     method: POST
-    uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-4o-mini/chat/completions?api-version=2024-12-01-preview
+    uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-5-nano/chat/completions?api-version=2024-12-01-preview
   response:
     body:
-      string: '{"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"protected_material_code":{"filtered":false,"detected":false},"protected_material_text":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"finish_reason":"stop","index":0,"logprobs":null,"message":{"annotations":[],"content":"The
-        result of the calculation is 120.","refusal":null,"role":"assistant"}}],"created":1769122115,"id":"chatcmpl-D0xlbUNVA7RVkn0GsuBGoNhgQTtac","model":"gpt-4o-mini-2024-07-18","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":"fp_f97eff32c5","usage":{"completion_tokens":11,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":0,"rejected_prediction_tokens":0},"prompt_tokens":207,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":218}}
+      string: '{"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"protected_material_code":{"filtered":false,"detected":false},"protected_material_text":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"finish_reason":"stop","index":0,"logprobs":null,"message":{"annotations":[],"content":"120","refusal":null,"role":"assistant"}}],"created":1771459547,"id":"chatcmpl-DAlq7zJimnIMoXieNww8jY5f2pIPd","model":"gpt-5-nano-2025-08-07","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":null,"usage":{"completion_tokens":203,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":192,"rejected_prediction_tokens":0},"prompt_tokens":284,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":487}}
 
         '
     headers:
       Content-Length:
-      - '1250'
+      - '1207'
       Content-Type:
       - application/json
       Date:
-      - Thu, 22 Jan 2026 22:48:34 GMT
+      - Thu, 19 Feb 2026 00:05:49 GMT
       Strict-Transport-Security:
       - STS-XXX
       apim-request-id:
@@ -143,7 +140,7 @@ interactions:
       x-ms-client-request-id:
       - X-MS-CLIENT-REQUEST-ID-XXX
       x-ms-deployment-name:
-      - gpt-4o-mini
+      - gpt-5-nano
       x-ms-rai-invoked:
       - 'true'
       x-ms-region:

lib/crewai/tests/cassettes/agents/TestAzureNativeToolCalling.test_azure_parallel_native_tool_calling_test_agent_kickoff.yaml

@@ -0,0 +1,198 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Parallel Tool Agent.
+      You follow tool instructions precisely.\nYour personal goal is: Use both tools
+      exactly as instructed"}, {"role": "user", "content": "\nCurrent Task: This is
+      a tool-calling compliance test. In your next assistant turn, emit exactly 3
+      tool calls in the same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary."}], "stream": false, "tool_choice": "auto", "tools": [{"function":
+      {"name": "parallel_local_search_one", "description": "Local search tool #1 for
+      concurrency testing.", "parameters": {"properties": {"query": {"description":
+      "Search query", "title": "Query", "type": "string"}}, "required": ["query"],
+      "type": "object", "additionalProperties": false}}, "type": "function"}, {"function":
+      {"name": "parallel_local_search_two", "description": "Local search tool #2 for
+      concurrency testing.", "parameters": {"properties": {"query": {"description":
+      "Search query", "title": "Query", "type": "string"}}, "required": ["query"],
+      "type": "object", "additionalProperties": false}}, "type": "function"}, {"function":
+      {"name": "parallel_local_search_three", "description": "Local search tool #3
+      for concurrency testing.", "parameters": {"properties": {"query": {"description":
+      "Search query", "title": "Query", "type": "string"}}, "required": ["query"],
+      "type": "object", "additionalProperties": false}}, "type": "function"}]}'
+    headers:
+      Accept:
+      - application/json
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1763'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      api-key:
+      - X-API-KEY-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+    method: POST
+    uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-5-nano/chat/completions?api-version=2024-12-01-preview
+  response:
+    body:
+      string: '{"choices":[{"content_filter_results":{},"finish_reason":"tool_calls","index":0,"logprobs":null,"message":{"annotations":[],"content":null,"refusal":null,"role":"assistant","tool_calls":[{"function":{"arguments":"{\"query\":
+        \"latest OpenAI model release notes\"}","name":"parallel_local_search_one"},"id":"call_emQmocGydKuxvESfQopNngdm","type":"function"},{"function":{"arguments":"{\"query\":
+        \"latest Anthropic model release notes\"}","name":"parallel_local_search_two"},"id":"call_eNpK9WUYFCX2ZEUPhYCKvdMs","type":"function"},{"function":{"arguments":"{\"query\":
+        \"latest Gemini model release notes\"}","name":"parallel_local_search_three"},"id":"call_Wdtl6jFxGehSUMn5I1O4Mrdx","type":"function"}]}}],"created":1771459550,"id":"chatcmpl-DAlqAyJGnQKDkNCaTcjU2T8BeJaXM","model":"gpt-5-nano-2025-08-07","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":null,"usage":{"completion_tokens":666,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":576,"rejected_prediction_tokens":0},"prompt_tokens":343,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":1009}}
+
+        '
+    headers:
+      Content-Length:
+      - '1433'
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 19 Feb 2026 00:05:55 GMT
+      Strict-Transport-Security:
+      - STS-XXX
+      apim-request-id:
+      - APIM-REQUEST-ID-XXX
+      azureml-model-session:
+      - AZUREML-MODEL-SESSION-XXX
+      x-accel-buffering:
+      - 'no'
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+      x-ms-deployment-name:
+      - gpt-5-nano
+      x-ms-rai-invoked:
+      - 'true'
+      x-ms-region:
+      - X-MS-REGION-XXX
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Parallel Tool Agent.
+      You follow tool instructions precisely.\nYour personal goal is: Use both tools
+      exactly as instructed"}, {"role": "user", "content": "\nCurrent Task: This is
+      a tool-calling compliance test. In your next assistant turn, emit exactly 3
+      tool calls in the same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary."}, {"role": "assistant", "content": "", "tool_calls": [{"id":
+      "call_emQmocGydKuxvESfQopNngdm", "type": "function", "function": {"name": "parallel_local_search_one",
+      "arguments": "{\"query\": \"latest OpenAI model release notes\"}"}}, {"id":
+      "call_eNpK9WUYFCX2ZEUPhYCKvdMs", "type": "function", "function": {"name": "parallel_local_search_two",
+      "arguments": "{\"query\": \"latest Anthropic model release notes\"}"}}, {"id":
+      "call_Wdtl6jFxGehSUMn5I1O4Mrdx", "type": "function", "function": {"name": "parallel_local_search_three",
+      "arguments": "{\"query\": \"latest Gemini model release notes\"}"}}]}, {"role":
+      "tool", "tool_call_id": "call_emQmocGydKuxvESfQopNngdm", "content": "[one] latest
+      OpenAI model release notes"}, {"role": "tool", "tool_call_id": "call_eNpK9WUYFCX2ZEUPhYCKvdMs",
+      "content": "[two] latest Anthropic model release notes"}, {"role": "tool", "tool_call_id":
+      "call_Wdtl6jFxGehSUMn5I1O4Mrdx", "content": "[three] latest Gemini model release
+      notes"}], "stream": false, "tool_choice": "auto", "tools": [{"function": {"name":
+      "parallel_local_search_one", "description": "Local search tool #1 for concurrency
+      testing.", "parameters": {"properties": {"query": {"description": "Search query",
+      "title": "Query", "type": "string"}}, "required": ["query"], "type": "object",
+      "additionalProperties": false}}, "type": "function"}, {"function": {"name":
+      "parallel_local_search_two", "description": "Local search tool #2 for concurrency
+      testing.", "parameters": {"properties": {"query": {"description": "Search query",
+      "title": "Query", "type": "string"}}, "required": ["query"], "type": "object",
+      "additionalProperties": false}}, "type": "function"}, {"function": {"name":
+      "parallel_local_search_three", "description": "Local search tool #3 for concurrency
+      testing.", "parameters": {"properties": {"query": {"description": "Search query",
+      "title": "Query", "type": "string"}}, "required": ["query"], "type": "object",
+      "additionalProperties": false}}, "type": "function"}]}'
+    headers:
+      Accept:
+      - application/json
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '2727'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      api-key:
+      - X-API-KEY-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+    method: POST
+    uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-5-nano/chat/completions?api-version=2024-12-01-preview
+  response:
+    body:
+      string: '{"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"protected_material_code":{"filtered":false,"detected":false},"protected_material_text":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"finish_reason":"stop","index":0,"logprobs":null,"message":{"annotations":[],"content":"The
+        latest release notes have been published for the OpenAI, Anthropic, and Gemini
+        models, signaling concurrent updates across the leading AI model families.
+        Each set outlines new capabilities and performance improvements, along with
+        changes to APIs, tooling, and deployment guidelines. Users should review the
+        individual notes to understand new features, adjustments to tokenization,
+        latency or throughput, safety and alignment enhancements, pricing or access
+        changes, and any breaking changes or migration steps required to adopt the
+        updated models in existing workflows.","refusal":null,"role":"assistant"}}],"created":1771459556,"id":"chatcmpl-DAlqGKWXfGNlTIbDY9F6oHQp6hbxM","model":"gpt-5-nano-2025-08-07","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":null,"usage":{"completion_tokens":747,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":640,"rejected_prediction_tokens":0},"prompt_tokens":467,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":1214}}
+
+        '
+    headers:
+      Content-Length:
+      - '1778'
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 19 Feb 2026 00:06:02 GMT
+      Strict-Transport-Security:
+      - STS-XXX
+      apim-request-id:
+      - APIM-REQUEST-ID-XXX
+      azureml-model-session:
+      - AZUREML-MODEL-SESSION-XXX
+      x-accel-buffering:
+      - 'no'
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+      x-ms-deployment-name:
+      - gpt-5-nano
+      x-ms-rai-invoked:
+      - 'true'
+      x-ms-region:
+      - X-MS-REGION-XXX
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAzureNativeToolCalling.test_azure_parallel_native_tool_calling_test_crew.yaml

@@ -0,0 +1,201 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Parallel Tool Agent.
+      You follow tool instructions precisely.\nYour personal goal is: Use both tools
+      exactly as instructed"}, {"role": "user", "content": "\nCurrent Task: This is
+      a tool-calling compliance test. In your next assistant turn, emit exactly 3
+      tool calls in the same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary.\n\nThis is the expected criteria for your final answer: A
+      one sentence summary of both tool outputs\nyou MUST return the actual complete
+      content as the final answer, not a summary."}], "stream": false, "tool_choice":
+      "auto", "tools": [{"function": {"name": "parallel_local_search_one", "description":
+      "Local search tool #1 for concurrency testing.", "parameters": {"properties":
+      {"query": {"description": "Search query", "title": "Query", "type": "string"}},
+      "required": ["query"], "type": "object", "additionalProperties": false}}, "type":
+      "function"}, {"function": {"name": "parallel_local_search_two", "description":
+      "Local search tool #2 for concurrency testing.", "parameters": {"properties":
+      {"query": {"description": "Search query", "title": "Query", "type": "string"}},
+      "required": ["query"], "type": "object", "additionalProperties": false}}, "type":
+      "function"}, {"function": {"name": "parallel_local_search_three", "description":
+      "Local search tool #3 for concurrency testing.", "parameters": {"properties":
+      {"query": {"description": "Search query", "title": "Query", "type": "string"}},
+      "required": ["query"], "type": "object", "additionalProperties": false}}, "type":
+      "function"}]}'
+    headers:
+      Accept:
+      - application/json
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1944'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      api-key:
+      - X-API-KEY-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+    method: POST
+    uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-5-nano/chat/completions?api-version=2024-12-01-preview
+  response:
+    body:
+      string: '{"choices":[{"content_filter_results":{},"finish_reason":"tool_calls","index":0,"logprobs":null,"message":{"annotations":[],"content":null,"refusal":null,"role":"assistant","tool_calls":[{"function":{"arguments":"{\"query\":
+        \"latest OpenAI model release notes\"}","name":"parallel_local_search_one"},"id":"call_NEvGoF86nhPQfXRoJd5SOyLd","type":"function"},{"function":{"arguments":"{\"query\":
+        \"latest Anthropic model release notes\"}","name":"parallel_local_search_two"},"id":"call_q8Q2du4gAMQLrGTgWgfwfbDZ","type":"function"},{"function":{"arguments":"{\"query\":
+        \"latest Gemini model release notes\"}","name":"parallel_local_search_three"},"id":"call_yTBal9ofZzuo10j0pWqhHCSj","type":"function"}]}}],"created":1771459563,"id":"chatcmpl-DAlqN7kyC5ACI5Yl1Pj63rOH5HIvI","model":"gpt-5-nano-2025-08-07","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":null,"usage":{"completion_tokens":2457,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":2368,"rejected_prediction_tokens":0},"prompt_tokens":378,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":2835}}
+
+        '
+    headers:
+      Content-Length:
+      - '1435'
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 19 Feb 2026 00:06:17 GMT
+      Strict-Transport-Security:
+      - STS-XXX
+      apim-request-id:
+      - APIM-REQUEST-ID-XXX
+      azureml-model-session:
+      - AZUREML-MODEL-SESSION-XXX
+      x-accel-buffering:
+      - 'no'
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+      x-ms-deployment-name:
+      - gpt-5-nano
+      x-ms-rai-invoked:
+      - 'true'
+      x-ms-region:
+      - X-MS-REGION-XXX
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Parallel Tool Agent.
+      You follow tool instructions precisely.\nYour personal goal is: Use both tools
+      exactly as instructed"}, {"role": "user", "content": "\nCurrent Task: This is
+      a tool-calling compliance test. In your next assistant turn, emit exactly 3
+      tool calls in the same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary.\n\nThis is the expected criteria for your final answer: A
+      one sentence summary of both tool outputs\nyou MUST return the actual complete
+      content as the final answer, not a summary."}, {"role": "assistant", "content":
+      "", "tool_calls": [{"id": "call_NEvGoF86nhPQfXRoJd5SOyLd", "type": "function",
+      "function": {"name": "parallel_local_search_one", "arguments": "{\"query\":
+      \"latest OpenAI model release notes\"}"}}, {"id": "call_q8Q2du4gAMQLrGTgWgfwfbDZ",
+      "type": "function", "function": {"name": "parallel_local_search_two", "arguments":
+      "{\"query\": \"latest Anthropic model release notes\"}"}}, {"id": "call_yTBal9ofZzuo10j0pWqhHCSj",
+      "type": "function", "function": {"name": "parallel_local_search_three", "arguments":
+      "{\"query\": \"latest Gemini model release notes\"}"}}]}, {"role": "tool", "tool_call_id":
+      "call_NEvGoF86nhPQfXRoJd5SOyLd", "content": "[one] latest OpenAI model release
+      notes"}, {"role": "tool", "tool_call_id": "call_q8Q2du4gAMQLrGTgWgfwfbDZ", "content":
+      "[two] latest Anthropic model release notes"}, {"role": "tool", "tool_call_id":
+      "call_yTBal9ofZzuo10j0pWqhHCSj", "content": "[three] latest Gemini model release
+      notes"}, {"role": "user", "content": "Analyze the tool result. If requirements
+      are met, provide the Final Answer. Otherwise, call the next tool. Deliver only
+      the answer without meta-commentary."}], "stream": false, "tool_choice": "auto",
+      "tools": [{"function": {"name": "parallel_local_search_one", "description":
+      "Local search tool #1 for concurrency testing.", "parameters": {"properties":
+      {"query": {"description": "Search query", "title": "Query", "type": "string"}},
+      "required": ["query"], "type": "object", "additionalProperties": false}}, "type":
+      "function"}, {"function": {"name": "parallel_local_search_two", "description":
+      "Local search tool #2 for concurrency testing.", "parameters": {"properties":
+      {"query": {"description": "Search query", "title": "Query", "type": "string"}},
+      "required": ["query"], "type": "object", "additionalProperties": false}}, "type":
+      "function"}, {"function": {"name": "parallel_local_search_three", "description":
+      "Local search tool #3 for concurrency testing.", "parameters": {"properties":
+      {"query": {"description": "Search query", "title": "Query", "type": "string"}},
+      "required": ["query"], "type": "object", "additionalProperties": false}}, "type":
+      "function"}]}'
+    headers:
+      Accept:
+      - application/json
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3096'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      api-key:
+      - X-API-KEY-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+    method: POST
+    uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-5-nano/chat/completions?api-version=2024-12-01-preview
+  response:
+    body:
+      string: '{"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"protected_material_code":{"filtered":false,"detected":false},"protected_material_text":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"finish_reason":"stop","index":0,"logprobs":null,"message":{"annotations":[],"content":"The
+        three tool results indicate the latest release notes are available for OpenAI
+        models, Anthropic models, and Gemini models.","refusal":null,"role":"assistant"}}],"created":1771459579,"id":"chatcmpl-DAlqdRtr8EefmFfazuh4jm7KvVxim","model":"gpt-5-nano-2025-08-07","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":null,"usage":{"completion_tokens":1826,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":1792,"rejected_prediction_tokens":0},"prompt_tokens":537,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":2363}}
+
+        '
+    headers:
+      Content-Length:
+      - '1333'
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 19 Feb 2026 00:06:31 GMT
+      Strict-Transport-Security:
+      - STS-XXX
+      apim-request-id:
+      - APIM-REQUEST-ID-XXX
+      azureml-model-session:
+      - AZUREML-MODEL-SESSION-XXX
+      x-accel-buffering:
+      - 'no'
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+      x-ms-deployment-name:
+      - gpt-5-nano
+      x-ms-rai-invoked:
+      - 'true'
+      x-ms-region:
+      - X-MS-REGION-XXX
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestBedrockNativeToolCalling.test_bedrock_parallel_native_tool_calling_test_agent_kickoff.yaml

@@ -0,0 +1,63 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": [{"text": "\nCurrent Task: This
+      is a tool-calling compliance test. In your next assistant turn, emit exactly
+      3 tool calls in the same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary."}]}], "inferenceConfig": {"stopSequences": ["\nObservation:"]},
+      "system": [{"text": "You are Parallel Tool Agent. You follow tool instructions
+      precisely.\nYour personal goal is: Use both tools exactly as instructed"}],
+      "toolConfig": {"tools": [{"toolSpec": {"name": "parallel_local_search_one",
+      "description": "Local search tool #1 for concurrency testing.", "inputSchema":
+      {"json": {"properties": {"query": {"description": "Search query", "title": "Query",
+      "type": "string"}}, "required": ["query"], "type": "object", "additionalProperties":
+      false}}}}, {"toolSpec": {"name": "parallel_local_search_two", "description":
+      "Local search tool #2 for concurrency testing.", "inputSchema": {"json": {"properties":
+      {"query": {"description": "Search query", "title": "Query", "type": "string"}},
+      "required": ["query"], "type": "object", "additionalProperties": false}}}},
+      {"toolSpec": {"name": "parallel_local_search_three", "description": "Local search
+      tool #3 for concurrency testing.", "inputSchema": {"json": {"properties": {"query":
+      {"description": "Search query", "title": "Query", "type": "string"}}, "required":
+      ["query"], "type": "object", "additionalProperties": false}}}}]}}'
+    headers:
+      Content-Length:
+      - '1773'
+      Content-Type:
+      - !!binary |
+        YXBwbGljYXRpb24vanNvbg==
+      User-Agent:
+      - X-USER-AGENT-XXX
+      amz-sdk-invocation-id:
+      - AMZ-SDK-INVOCATION-ID-XXX
+      amz-sdk-request:
+      - !!binary |
+        YXR0ZW1wdD0x
+      authorization:
+      - AUTHORIZATION-XXX
+      x-amz-date:
+      - X-AMZ-DATE-XXX
+    method: POST
+    uri: https://bedrock-runtime.us-east-1.amazonaws.com/model/anthropic.claude-3-haiku-20240307-v1%3A0/converse
+  response:
+    body:
+      string: '{"message":"The security token included in the request is invalid."}'
+    headers:
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '68'
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 19 Feb 2026 00:00:08 GMT
+      x-amzn-ErrorType:
+      - UnrecognizedClientException:http://internal.amazon.com/coral/com.amazon.coral.service/
+      x-amzn-RequestId:
+      - X-AMZN-REQUESTID-XXX
+    status:
+      code: 403
+      message: Forbidden
+version: 1

lib/crewai/tests/cassettes/agents/TestBedrockNativeToolCalling.test_bedrock_parallel_native_tool_calling_test_crew.yaml

@@ -0,0 +1,226 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": [{"text": "\nCurrent Task: This
+      is a tool-calling compliance test. In your next assistant turn, emit exactly
+      3 tool calls in the same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary.\n\nThis is the expected criteria for your final answer: A
+      one sentence summary of both tool outputs\nyou MUST return the actual complete
+      content as the final answer, not a summary."}]}], "inferenceConfig": {"stopSequences":
+      ["\nObservation:"]}, "system": [{"text": "You are Parallel Tool Agent. You follow
+      tool instructions precisely.\nYour personal goal is: Use both tools exactly
+      as instructed"}], "toolConfig": {"tools": [{"toolSpec": {"name": "parallel_local_search_one",
+      "description": "Local search tool #1 for concurrency testing.", "inputSchema":
+      {"json": {"properties": {"query": {"description": "Search query", "title": "Query",
+      "type": "string"}}, "required": ["query"], "type": "object", "additionalProperties":
+      false}}}}, {"toolSpec": {"name": "parallel_local_search_two", "description":
+      "Local search tool #2 for concurrency testing.", "inputSchema": {"json": {"properties":
+      {"query": {"description": "Search query", "title": "Query", "type": "string"}},
+      "required": ["query"], "type": "object", "additionalProperties": false}}}},
+      {"toolSpec": {"name": "parallel_local_search_three", "description": "Local search
+      tool #3 for concurrency testing.", "inputSchema": {"json": {"properties": {"query":
+      {"description": "Search query", "title": "Query", "type": "string"}}, "required":
+      ["query"], "type": "object", "additionalProperties": false}}}}]}}'
+    headers:
+      Content-Length:
+      - '1954'
+      Content-Type:
+      - !!binary |
+        YXBwbGljYXRpb24vanNvbg==
+      User-Agent:
+      - X-USER-AGENT-XXX
+      amz-sdk-invocation-id:
+      - AMZ-SDK-INVOCATION-ID-XXX
+      amz-sdk-request:
+      - !!binary |
+        YXR0ZW1wdD0x
+      authorization:
+      - AUTHORIZATION-XXX
+      x-amz-date:
+      - X-AMZ-DATE-XXX
+    method: POST
+    uri: https://bedrock-runtime.us-east-1.amazonaws.com/model/anthropic.claude-3-haiku-20240307-v1%3A0/converse
+  response:
+    body:
+      string: '{"message":"The security token included in the request is invalid."}'
+    headers:
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '68'
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 19 Feb 2026 00:00:07 GMT
+      x-amzn-ErrorType:
+      - UnrecognizedClientException:http://internal.amazon.com/coral/com.amazon.coral.service/
+      x-amzn-RequestId:
+      - X-AMZN-REQUESTID-XXX
+    status:
+      code: 403
+      message: Forbidden
+- request:
+    body: '{"messages": [{"role": "user", "content": [{"text": "\nCurrent Task: This
+      is a tool-calling compliance test. In your next assistant turn, emit exactly
+      3 tool calls in the same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary.\n\nThis is the expected criteria for your final answer: A
+      one sentence summary of both tool outputs\nyou MUST return the actual complete
+      content as the final answer, not a summary."}]}, {"role": "user", "content":
+      [{"text": "\nCurrent Task: This is a tool-calling compliance test. In your next
+      assistant turn, emit exactly 3 tool calls in the same response (parallel tool
+      calls), in this order: 1) parallel_local_search_one(query=''latest OpenAI model
+      release notes''), 2) parallel_local_search_two(query=''latest Anthropic model
+      release notes''), 3) parallel_local_search_three(query=''latest Gemini model
+      release notes''). Do not call any other tools and do not answer before those
+      3 tool calls are emitted. After the tool results return, provide a one paragraph
+      summary.\n\nThis is the expected criteria for your final answer: A one sentence
+      summary of both tool outputs\nyou MUST return the actual complete content as
+      the final answer, not a summary."}]}], "inferenceConfig": {"stopSequences":
+      ["\nObservation:"]}, "system": [{"text": "You are Parallel Tool Agent. You follow
+      tool instructions precisely.\nYour personal goal is: Use both tools exactly
+      as instructed\n\nYou are Parallel Tool Agent. You follow tool instructions precisely.\nYour
+      personal goal is: Use both tools exactly as instructed"}], "toolConfig": {"tools":
+      [{"toolSpec": {"name": "parallel_local_search_one", "description": "Local search
+      tool #1 for concurrency testing.", "inputSchema": {"json": {"properties": {"query":
+      {"description": "Search query", "title": "Query", "type": "string"}}, "required":
+      ["query"], "type": "object", "additionalProperties": false}}}}, {"toolSpec":
+      {"name": "parallel_local_search_two", "description": "Local search tool #2 for
+      concurrency testing.", "inputSchema": {"json": {"properties": {"query": {"description":
+      "Search query", "title": "Query", "type": "string"}}, "required": ["query"],
+      "type": "object", "additionalProperties": false}}}}, {"toolSpec": {"name": "parallel_local_search_three",
+      "description": "Local search tool #3 for concurrency testing.", "inputSchema":
+      {"json": {"properties": {"query": {"description": "Search query", "title": "Query",
+      "type": "string"}}, "required": ["query"], "type": "object", "additionalProperties":
+      false}}}}]}}'
+    headers:
+      Content-Length:
+      - '2855'
+      Content-Type:
+      - !!binary |
+        YXBwbGljYXRpb24vanNvbg==
+      User-Agent:
+      - X-USER-AGENT-XXX
+      amz-sdk-invocation-id:
+      - AMZ-SDK-INVOCATION-ID-XXX
+      amz-sdk-request:
+      - !!binary |
+        YXR0ZW1wdD0x
+      authorization:
+      - AUTHORIZATION-XXX
+      x-amz-date:
+      - X-AMZ-DATE-XXX
+    method: POST
+    uri: https://bedrock-runtime.us-east-1.amazonaws.com/model/anthropic.claude-3-haiku-20240307-v1%3A0/converse
+  response:
+    body:
+      string: '{"message":"The security token included in the request is invalid."}'
+    headers:
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '68'
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 19 Feb 2026 00:00:07 GMT
+      x-amzn-ErrorType:
+      - UnrecognizedClientException:http://internal.amazon.com/coral/com.amazon.coral.service/
+      x-amzn-RequestId:
+      - X-AMZN-REQUESTID-XXX
+    status:
+      code: 403
+      message: Forbidden
+- request:
+    body: '{"messages": [{"role": "user", "content": [{"text": "\nCurrent Task: This
+      is a tool-calling compliance test. In your next assistant turn, emit exactly
+      3 tool calls in the same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary.\n\nThis is the expected criteria for your final answer: A
+      one sentence summary of both tool outputs\nyou MUST return the actual complete
+      content as the final answer, not a summary."}]}, {"role": "user", "content":
+      [{"text": "\nCurrent Task: This is a tool-calling compliance test. In your next
+      assistant turn, emit exactly 3 tool calls in the same response (parallel tool
+      calls), in this order: 1) parallel_local_search_one(query=''latest OpenAI model
+      release notes''), 2) parallel_local_search_two(query=''latest Anthropic model
+      release notes''), 3) parallel_local_search_three(query=''latest Gemini model
+      release notes''). Do not call any other tools and do not answer before those
+      3 tool calls are emitted. After the tool results return, provide a one paragraph
+      summary.\n\nThis is the expected criteria for your final answer: A one sentence
+      summary of both tool outputs\nyou MUST return the actual complete content as
+      the final answer, not a summary."}]}, {"role": "user", "content": [{"text":
+      "\nCurrent Task: This is a tool-calling compliance test. In your next assistant
+      turn, emit exactly 3 tool calls in the same response (parallel tool calls),
+      in this order: 1) parallel_local_search_one(query=''latest OpenAI model release
+      notes''), 2) parallel_local_search_two(query=''latest Anthropic model release
+      notes''), 3) parallel_local_search_three(query=''latest Gemini model release
+      notes''). Do not call any other tools and do not answer before those 3 tool
+      calls are emitted. After the tool results return, provide a one paragraph summary.\n\nThis
+      is the expected criteria for your final answer: A one sentence summary of both
+      tool outputs\nyou MUST return the actual complete content as the final answer,
+      not a summary."}]}], "inferenceConfig": {"stopSequences": ["\nObservation:"]},
+      "system": [{"text": "You are Parallel Tool Agent. You follow tool instructions
+      precisely.\nYour personal goal is: Use both tools exactly as instructed\n\nYou
+      are Parallel Tool Agent. You follow tool instructions precisely.\nYour personal
+      goal is: Use both tools exactly as instructed\n\nYou are Parallel Tool Agent.
+      You follow tool instructions precisely.\nYour personal goal is: Use both tools
+      exactly as instructed"}], "toolConfig": {"tools": [{"toolSpec": {"name": "parallel_local_search_one",
+      "description": "Local search tool #1 for concurrency testing.", "inputSchema":
+      {"json": {"properties": {"query": {"description": "Search query", "title": "Query",
+      "type": "string"}}, "required": ["query"], "type": "object", "additionalProperties":
+      false}}}}, {"toolSpec": {"name": "parallel_local_search_two", "description":
+      "Local search tool #2 for concurrency testing.", "inputSchema": {"json": {"properties":
+      {"query": {"description": "Search query", "title": "Query", "type": "string"}},
+      "required": ["query"], "type": "object", "additionalProperties": false}}}},
+      {"toolSpec": {"name": "parallel_local_search_three", "description": "Local search
+      tool #3 for concurrency testing.", "inputSchema": {"json": {"properties": {"query":
+      {"description": "Search query", "title": "Query", "type": "string"}}, "required":
+      ["query"], "type": "object", "additionalProperties": false}}}}]}}'
+    headers:
+      Content-Length:
+      - '3756'
+      Content-Type:
+      - !!binary |
+        YXBwbGljYXRpb24vanNvbg==
+      User-Agent:
+      - X-USER-AGENT-XXX
+      amz-sdk-invocation-id:
+      - AMZ-SDK-INVOCATION-ID-XXX
+      amz-sdk-request:
+      - !!binary |
+        YXR0ZW1wdD0x
+      authorization:
+      - AUTHORIZATION-XXX
+      x-amz-date:
+      - X-AMZ-DATE-XXX
+    method: POST
+    uri: https://bedrock-runtime.us-east-1.amazonaws.com/model/anthropic.claude-3-haiku-20240307-v1%3A0/converse
+  response:
+    body:
+      string: '{"message":"The security token included in the request is invalid."}'
+    headers:
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '68'
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 19 Feb 2026 00:00:07 GMT
+      x-amzn-ErrorType:
+      - UnrecognizedClientException:http://internal.amazon.com/coral/com.amazon.coral.service/
+      x-amzn-RequestId:
+      - X-AMZN-REQUESTID-XXX
+    status:
+      code: 403
+      message: Forbidden
+version: 1

lib/crewai/tests/cassettes/agents/TestGeminiNativeToolCalling.test_gemini_agent_with_native_tool_calling.yaml

@@ -3,14 +3,14 @@ interactions:
     body: '{"contents": [{"parts": [{"text": "\nCurrent Task: Calculate what is 15
       * 8\n\nThis is the expected criteria for your final answer: The result of the
       calculation\nyou MUST return the actual complete content as the final answer,
-      not a summary.\n\nThis is VERY important to you, your job depends on it!"}],
-      "role": "user"}], "systemInstruction": {"parts": [{"text": "You are Math Assistant.
-      You are a helpful math assistant.\nYour personal goal is: Help users with mathematical
-      calculations"}], "role": "user"}, "tools": [{"functionDeclarations": [{"description":
-      "Perform mathematical calculations. Use this for any math operations.", "name":
-      "calculator", "parameters": {"properties": {"expression": {"description": "Mathematical
-      expression to evaluate", "title": "Expression", "type": "STRING"}}, "required":
-      ["expression"], "type": "OBJECT"}}]}], "generationConfig": {"stopSequences":
+      not a summary."}], "role": "user"}], "systemInstruction": {"parts": [{"text":
+      "You are Math Assistant. You are a helpful math assistant.\nYour personal goal
+      is: Help users with mathematical calculations"}], "role": "user"}, "tools":
+      [{"functionDeclarations": [{"description": "Perform mathematical calculations.
+      Use this for any math operations.", "name": "calculator", "parameters_json_schema":
+      {"properties": {"expression": {"description": "Mathematical expression to evaluate",
+      "title": "Expression", "type": "string"}}, "required": ["expression"], "type":
+      "object", "additionalProperties": false}}]}], "generationConfig": {"stopSequences":
       ["\nObservation:"]}}'
     headers:
       User-Agent:
@@ -22,7 +22,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '907'
+      - '892'
       content-type:
       - application/json
       host:
@@ -32,31 +32,31 @@ interactions:
       x-goog-api-key:
       - X-GOOG-API-KEY-XXX
     method: POST
-    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-exp:generateContent
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
   response:
     body:
       string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
         [\n          {\n            \"functionCall\": {\n              \"name\": \"calculator\",\n
         \             \"args\": {\n                \"expression\": \"15 * 8\"\n              }\n
-        \           }\n          }\n        ],\n        \"role\": \"model\"\n      },\n
-        \     \"finishReason\": \"STOP\",\n      \"avgLogprobs\": -0.00062879999833447594\n
-        \   }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\": 103,\n    \"candidatesTokenCount\":
-        7,\n    \"totalTokenCount\": 110,\n    \"promptTokensDetails\": [\n      {\n
-        \       \"modality\": \"TEXT\",\n        \"tokenCount\": 103\n      }\n    ],\n
-        \   \"candidatesTokensDetails\": [\n      {\n        \"modality\": \"TEXT\",\n
-        \       \"tokenCount\": 7\n      }\n    ]\n  },\n  \"modelVersion\": \"gemini-2.0-flash-exp\",\n
-        \ \"responseId\": \"PpByabfUHsih_uMPlu2ysAM\"\n}\n"
+        \           },\n            \"thoughtSignature\": \"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\"\n
+        \         }\n        ],\n        \"role\": \"model\"\n      },\n      \"finishReason\":
+        \"STOP\",\n      \"index\": 0,\n      \"finishMessage\": \"Model generated
+        function call(s).\"\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
+        115,\n    \"candidatesTokenCount\": 17,\n    \"totalTokenCount\": 227,\n    \"promptTokensDetails\":
+        [\n      {\n        \"modality\": \"TEXT\",\n        \"tokenCount\": 115\n
+        \     }\n    ],\n    \"thoughtsTokenCount\": 95\n  },\n  \"modelVersion\":
+        \"gemini-2.5-flash\",\n  \"responseId\": \"Y1KWadvNMKz1jMcPiJeJmAI\"\n}\n"
     headers:
       Alt-Svc:
       - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
       Content-Type:
       - application/json; charset=UTF-8
       Date:
-      - Thu, 22 Jan 2026 21:01:50 GMT
+      - Wed, 18 Feb 2026 23:59:32 GMT
       Server:
       - scaffolding on HTTPServer2
       Server-Timing:
-      - gfet4t7; dur=521
+      - gfet4t7; dur=956
       Transfer-Encoding:
       - chunked
       Vary:
@@ -76,18 +76,19 @@ interactions:
     body: '{"contents": [{"parts": [{"text": "\nCurrent Task: Calculate what is 15
       * 8\n\nThis is the expected criteria for your final answer: The result of the
       calculation\nyou MUST return the actual complete content as the final answer,
-      not a summary.\n\nThis is VERY important to you, your job depends on it!"}],
-      "role": "user"}, {"parts": [{"text": ""}], "role": "model"}, {"parts": [{"text":
-      "The result of 15 * 8 is 120"}], "role": "user"}, {"parts": [{"text": "Analyze
-      the tool result. If requirements are met, provide the Final Answer. Otherwise,
-      call the next tool. Deliver only the answer without meta-commentary."}], "role":
-      "user"}], "systemInstruction": {"parts": [{"text": "You are Math Assistant.
-      You are a helpful math assistant.\nYour personal goal is: Help users with mathematical
-      calculations"}], "role": "user"}, "tools": [{"functionDeclarations": [{"description":
-      "Perform mathematical calculations. Use this for any math operations.", "name":
-      "calculator", "parameters": {"properties": {"expression": {"description": "Mathematical
-      expression to evaluate", "title": "Expression", "type": "STRING"}}, "required":
-      ["expression"], "type": "OBJECT"}}]}], "generationConfig": {"stopSequences":
+      not a summary."}], "role": "user"}, {"parts": [{"functionCall": {"args": {"expression":
+      "15 * 8"}, "name": "calculator"}}], "role": "model"}, {"parts": [{"functionResponse":
+      {"name": "calculator", "response": {"result": "The result of 15 * 8 is 120"}}}],
+      "role": "user"}, {"parts": [{"text": "Analyze the tool result. If requirements
+      are met, provide the Final Answer. Otherwise, call the next tool. Deliver only
+      the answer without meta-commentary."}], "role": "user"}], "systemInstruction":
+      {"parts": [{"text": "You are Math Assistant. You are a helpful math assistant.\nYour
+      personal goal is: Help users with mathematical calculations"}], "role": "user"},
+      "tools": [{"functionDeclarations": [{"description": "Perform mathematical calculations.
+      Use this for any math operations.", "name": "calculator", "parameters_json_schema":
+      {"properties": {"expression": {"description": "Mathematical expression to evaluate",
+      "title": "Expression", "type": "string"}}, "required": ["expression"], "type":
+      "object", "additionalProperties": false}}]}], "generationConfig": {"stopSequences":
       ["\nObservation:"]}}'
     headers:
       User-Agent:
@@ -99,7 +100,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1219'
+      - '1326'
       content-type:
       - application/json
       host:
@@ -109,378 +110,28 @@ interactions:
       x-goog-api-key:
       - X-GOOG-API-KEY-XXX
     method: POST
-    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-exp:generateContent
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
   response:
     body:
       string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
-        [\n          {\n            \"functionCall\": {\n              \"name\": \"calculator\",\n
-        \             \"args\": {\n                \"expression\": \"15 * 8\"\n              }\n
-        \           }\n          }\n        ],\n        \"role\": \"model\"\n      },\n
-        \     \"finishReason\": \"STOP\",\n      \"avgLogprobs\": -0.013549212898526872\n
-        \   }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\": 149,\n    \"candidatesTokenCount\":
-        7,\n    \"totalTokenCount\": 156,\n    \"promptTokensDetails\": [\n      {\n
-        \       \"modality\": \"TEXT\",\n        \"tokenCount\": 149\n      }\n    ],\n
-        \   \"candidatesTokensDetails\": [\n      {\n        \"modality\": \"TEXT\",\n
-        \       \"tokenCount\": 7\n      }\n    ]\n  },\n  \"modelVersion\": \"gemini-2.0-flash-exp\",\n
-        \ \"responseId\": \"P5Byadc8kJT-4w_p99XQAQ\"\n}\n"
+        [\n          {\n            \"text\": \"The result of 15 * 8 is 120\"\n          }\n
+        \       ],\n        \"role\": \"model\"\n      },\n      \"finishReason\":
+        \"STOP\",\n      \"index\": 0\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
+        191,\n    \"candidatesTokenCount\": 14,\n    \"totalTokenCount\": 205,\n    \"promptTokensDetails\":
+        [\n      {\n        \"modality\": \"TEXT\",\n        \"tokenCount\": 191\n
+        \     }\n    ]\n  },\n  \"modelVersion\": \"gemini-2.5-flash\",\n  \"responseId\":
+        \"ZFKWaf2BMM6MjMcP6P--kQM\"\n}\n"
     headers:
       Alt-Svc:
       - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
       Content-Type:
       - application/json; charset=UTF-8
       Date:
-      - Thu, 22 Jan 2026 21:01:51 GMT
+      - Wed, 18 Feb 2026 23:59:33 GMT
       Server:
       - scaffolding on HTTPServer2
       Server-Timing:
-      - gfet4t7; dur=444
-      Transfer-Encoding:
-      - chunked
-      Vary:
-      - Origin
-      - X-Origin
-      - Referer
-      X-Content-Type-Options:
-      - X-CONTENT-TYPE-XXX
-      X-Frame-Options:
-      - X-FRAME-OPTIONS-XXX
-      X-XSS-Protection:
-      - '0'
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"contents": [{"parts": [{"text": "\nCurrent Task: Calculate what is 15
-      * 8\n\nThis is the expected criteria for your final answer: The result of the
-      calculation\nyou MUST return the actual complete content as the final answer,
-      not a summary.\n\nThis is VERY important to you, your job depends on it!"}],
-      "role": "user"}, {"parts": [{"text": ""}], "role": "model"}, {"parts": [{"text":
-      "The result of 15 * 8 is 120"}], "role": "user"}, {"parts": [{"text": "Analyze
-      the tool result. If requirements are met, provide the Final Answer. Otherwise,
-      call the next tool. Deliver only the answer without meta-commentary."}], "role":
-      "user"}, {"parts": [{"text": ""}], "role": "model"}, {"parts": [{"text": "The
-      result of 15 * 8 is 120"}], "role": "user"}, {"parts": [{"text": "Analyze the
-      tool result. If requirements are met, provide the Final Answer. Otherwise, call
-      the next tool. Deliver only the answer without meta-commentary."}], "role":
-      "user"}], "systemInstruction": {"parts": [{"text": "You are Math Assistant.
-      You are a helpful math assistant.\nYour personal goal is: Help users with mathematical
-      calculations"}], "role": "user"}, "tools": [{"functionDeclarations": [{"description":
-      "Perform mathematical calculations. Use this for any math operations.", "name":
-      "calculator", "parameters": {"properties": {"expression": {"description": "Mathematical
-      expression to evaluate", "title": "Expression", "type": "STRING"}}, "required":
-      ["expression"], "type": "OBJECT"}}]}], "generationConfig": {"stopSequences":
-      ["\nObservation:"]}}'
-    headers:
-      User-Agent:
-      - X-USER-AGENT-XXX
-      accept:
-      - '*/*'
-      accept-encoding:
-      - ACCEPT-ENCODING-XXX
-      connection:
-      - keep-alive
-      content-length:
-      - '1531'
-      content-type:
-      - application/json
-      host:
-      - generativelanguage.googleapis.com
-      x-goog-api-client:
-      - google-genai-sdk/1.49.0 gl-python/3.13.3
-      x-goog-api-key:
-      - X-GOOG-API-KEY-XXX
-    method: POST
-    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-exp:generateContent
-  response:
-    body:
-      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
-        [\n          {\n            \"functionCall\": {\n              \"name\": \"calculator\",\n
-        \             \"args\": {\n                \"expression\": \"15 * 8\"\n              }\n
-        \           }\n          }\n        ],\n        \"role\": \"model\"\n      },\n
-        \     \"finishReason\": \"STOP\",\n      \"avgLogprobs\": -0.0409286447933742\n
-        \   }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\": 195,\n    \"candidatesTokenCount\":
-        7,\n    \"totalTokenCount\": 202,\n    \"promptTokensDetails\": [\n      {\n
-        \       \"modality\": \"TEXT\",\n        \"tokenCount\": 195\n      }\n    ],\n
-        \   \"candidatesTokensDetails\": [\n      {\n        \"modality\": \"TEXT\",\n
-        \       \"tokenCount\": 7\n      }\n    ]\n  },\n  \"modelVersion\": \"gemini-2.0-flash-exp\",\n
-        \ \"responseId\": \"P5Byadn5HOK6_uMPnvmXwAk\"\n}\n"
-    headers:
-      Alt-Svc:
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Content-Type:
-      - application/json; charset=UTF-8
-      Date:
-      - Thu, 22 Jan 2026 21:01:51 GMT
-      Server:
-      - scaffolding on HTTPServer2
-      Server-Timing:
-      - gfet4t7; dur=503
-      Transfer-Encoding:
-      - chunked
-      Vary:
-      - Origin
-      - X-Origin
-      - Referer
-      X-Content-Type-Options:
-      - X-CONTENT-TYPE-XXX
-      X-Frame-Options:
-      - X-FRAME-OPTIONS-XXX
-      X-XSS-Protection:
-      - '0'
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"contents": [{"parts": [{"text": "\nCurrent Task: Calculate what is 15
-      * 8\n\nThis is the expected criteria for your final answer: The result of the
-      calculation\nyou MUST return the actual complete content as the final answer,
-      not a summary.\n\nThis is VERY important to you, your job depends on it!"}],
-      "role": "user"}, {"parts": [{"text": ""}], "role": "model"}, {"parts": [{"text":
-      "The result of 15 * 8 is 120"}], "role": "user"}, {"parts": [{"text": "Analyze
-      the tool result. If requirements are met, provide the Final Answer. Otherwise,
-      call the next tool. Deliver only the answer without meta-commentary."}], "role":
-      "user"}, {"parts": [{"text": ""}], "role": "model"}, {"parts": [{"text": "The
-      result of 15 * 8 is 120"}], "role": "user"}, {"parts": [{"text": "Analyze the
-      tool result. If requirements are met, provide the Final Answer. Otherwise, call
-      the next tool. Deliver only the answer without meta-commentary."}], "role":
-      "user"}, {"parts": [{"text": ""}], "role": "model"}, {"parts": [{"text": "The
-      result of 15 * 8 is 120"}], "role": "user"}, {"parts": [{"text": "Analyze the
-      tool result. If requirements are met, provide the Final Answer. Otherwise, call
-      the next tool. Deliver only the answer without meta-commentary."}], "role":
-      "user"}], "systemInstruction": {"parts": [{"text": "You are Math Assistant.
-      You are a helpful math assistant.\nYour personal goal is: Help users with mathematical
-      calculations"}], "role": "user"}, "tools": [{"functionDeclarations": [{"description":
-      "Perform mathematical calculations. Use this for any math operations.", "name":
-      "calculator", "parameters": {"properties": {"expression": {"description": "Mathematical
-      expression to evaluate", "title": "Expression", "type": "STRING"}}, "required":
-      ["expression"], "type": "OBJECT"}}]}], "generationConfig": {"stopSequences":
-      ["\nObservation:"]}}'
-    headers:
-      User-Agent:
-      - X-USER-AGENT-XXX
-      accept:
-      - '*/*'
-      accept-encoding:
-      - ACCEPT-ENCODING-XXX
-      connection:
-      - keep-alive
-      content-length:
-      - '1843'
-      content-type:
-      - application/json
-      host:
-      - generativelanguage.googleapis.com
-      x-goog-api-client:
-      - google-genai-sdk/1.49.0 gl-python/3.13.3
-      x-goog-api-key:
-      - X-GOOG-API-KEY-XXX
-    method: POST
-    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-exp:generateContent
-  response:
-    body:
-      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
-        [\n          {\n            \"functionCall\": {\n              \"name\": \"calculator\",\n
-        \             \"args\": {\n                \"expression\": \"15 * 8\"\n              }\n
-        \           }\n          }\n        ],\n        \"role\": \"model\"\n      },\n
-        \     \"finishReason\": \"STOP\",\n      \"avgLogprobs\": -0.018002046006066457\n
-        \   }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\": 241,\n    \"candidatesTokenCount\":
-        7,\n    \"totalTokenCount\": 248,\n    \"promptTokensDetails\": [\n      {\n
-        \       \"modality\": \"TEXT\",\n        \"tokenCount\": 241\n      }\n    ],\n
-        \   \"candidatesTokensDetails\": [\n      {\n        \"modality\": \"TEXT\",\n
-        \       \"tokenCount\": 7\n      }\n    ]\n  },\n  \"modelVersion\": \"gemini-2.0-flash-exp\",\n
-        \ \"responseId\": \"P5Byafi2PKbn_uMPtIbfuQI\"\n}\n"
-    headers:
-      Alt-Svc:
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Content-Type:
-      - application/json; charset=UTF-8
-      Date:
-      - Thu, 22 Jan 2026 21:01:52 GMT
-      Server:
-      - scaffolding on HTTPServer2
-      Server-Timing:
-      - gfet4t7; dur=482
-      Transfer-Encoding:
-      - chunked
-      Vary:
-      - Origin
-      - X-Origin
-      - Referer
-      X-Content-Type-Options:
-      - X-CONTENT-TYPE-XXX
-      X-Frame-Options:
-      - X-FRAME-OPTIONS-XXX
-      X-XSS-Protection:
-      - '0'
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"contents": [{"parts": [{"text": "\nCurrent Task: Calculate what is 15
-      * 8\n\nThis is the expected criteria for your final answer: The result of the
-      calculation\nyou MUST return the actual complete content as the final answer,
-      not a summary.\n\nThis is VERY important to you, your job depends on it!"}],
-      "role": "user"}, {"parts": [{"text": ""}], "role": "model"}, {"parts": [{"text":
-      "The result of 15 * 8 is 120"}], "role": "user"}, {"parts": [{"text": "Analyze
-      the tool result. If requirements are met, provide the Final Answer. Otherwise,
-      call the next tool. Deliver only the answer without meta-commentary."}], "role":
-      "user"}, {"parts": [{"text": ""}], "role": "model"}, {"parts": [{"text": "The
-      result of 15 * 8 is 120"}], "role": "user"}, {"parts": [{"text": "Analyze the
-      tool result. If requirements are met, provide the Final Answer. Otherwise, call
-      the next tool. Deliver only the answer without meta-commentary."}], "role":
-      "user"}, {"parts": [{"text": ""}], "role": "model"}, {"parts": [{"text": "The
-      result of 15 * 8 is 120"}], "role": "user"}, {"parts": [{"text": "Analyze the
-      tool result. If requirements are met, provide the Final Answer. Otherwise, call
-      the next tool. Deliver only the answer without meta-commentary."}], "role":
-      "user"}, {"parts": [{"text": ""}], "role": "model"}, {"parts": [{"text": "The
-      result of 15 * 8 is 120"}], "role": "user"}, {"parts": [{"text": "Analyze the
-      tool result. If requirements are met, provide the Final Answer. Otherwise, call
-      the next tool. Deliver only the answer without meta-commentary."}], "role":
-      "user"}], "systemInstruction": {"parts": [{"text": "You are Math Assistant.
-      You are a helpful math assistant.\nYour personal goal is: Help users with mathematical
-      calculations"}], "role": "user"}, "tools": [{"functionDeclarations": [{"description":
-      "Perform mathematical calculations. Use this for any math operations.", "name":
-      "calculator", "parameters": {"properties": {"expression": {"description": "Mathematical
-      expression to evaluate", "title": "Expression", "type": "STRING"}}, "required":
-      ["expression"], "type": "OBJECT"}}]}], "generationConfig": {"stopSequences":
-      ["\nObservation:"]}}'
-    headers:
-      User-Agent:
-      - X-USER-AGENT-XXX
-      accept:
-      - '*/*'
-      accept-encoding:
-      - ACCEPT-ENCODING-XXX
-      connection:
-      - keep-alive
-      content-length:
-      - '2155'
-      content-type:
-      - application/json
-      host:
-      - generativelanguage.googleapis.com
-      x-goog-api-client:
-      - google-genai-sdk/1.49.0 gl-python/3.13.3
-      x-goog-api-key:
-      - X-GOOG-API-KEY-XXX
-    method: POST
-    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-exp:generateContent
-  response:
-    body:
-      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
-        [\n          {\n            \"functionCall\": {\n              \"name\": \"calculator\",\n
-        \             \"args\": {\n                \"expression\": \"15 * 8\"\n              }\n
-        \           }\n          }\n        ],\n        \"role\": \"model\"\n      },\n
-        \     \"finishReason\": \"STOP\",\n      \"avgLogprobs\": -0.10329001290457589\n
-        \   }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\": 287,\n    \"candidatesTokenCount\":
-        7,\n    \"totalTokenCount\": 294,\n    \"promptTokensDetails\": [\n      {\n
-        \       \"modality\": \"TEXT\",\n        \"tokenCount\": 287\n      }\n    ],\n
-        \   \"candidatesTokensDetails\": [\n      {\n        \"modality\": \"TEXT\",\n
-        \       \"tokenCount\": 7\n      }\n    ]\n  },\n  \"modelVersion\": \"gemini-2.0-flash-exp\",\n
-        \ \"responseId\": \"QJByaamVIP_g_uMPt6mI0Qg\"\n}\n"
-    headers:
-      Alt-Svc:
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Content-Type:
-      - application/json; charset=UTF-8
-      Date:
-      - Thu, 22 Jan 2026 21:01:52 GMT
-      Server:
-      - scaffolding on HTTPServer2
-      Server-Timing:
-      - gfet4t7; dur=534
-      Transfer-Encoding:
-      - chunked
-      Vary:
-      - Origin
-      - X-Origin
-      - Referer
-      X-Content-Type-Options:
-      - X-CONTENT-TYPE-XXX
-      X-Frame-Options:
-      - X-FRAME-OPTIONS-XXX
-      X-XSS-Protection:
-      - '0'
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"contents": [{"parts": [{"text": "\nCurrent Task: Calculate what is 15
-      * 8\n\nThis is the expected criteria for your final answer: The result of the
-      calculation\nyou MUST return the actual complete content as the final answer,
-      not a summary.\n\nThis is VERY important to you, your job depends on it!"}],
-      "role": "user"}, {"parts": [{"text": ""}], "role": "model"}, {"parts": [{"text":
-      "The result of 15 * 8 is 120"}], "role": "user"}, {"parts": [{"text": "Analyze
-      the tool result. If requirements are met, provide the Final Answer. Otherwise,
-      call the next tool. Deliver only the answer without meta-commentary."}], "role":
-      "user"}, {"parts": [{"text": ""}], "role": "model"}, {"parts": [{"text": "The
-      result of 15 * 8 is 120"}], "role": "user"}, {"parts": [{"text": "Analyze the
-      tool result. If requirements are met, provide the Final Answer. Otherwise, call
-      the next tool. Deliver only the answer without meta-commentary."}], "role":
-      "user"}, {"parts": [{"text": ""}], "role": "model"}, {"parts": [{"text": "The
-      result of 15 * 8 is 120"}], "role": "user"}, {"parts": [{"text": "Analyze the
-      tool result. If requirements are met, provide the Final Answer. Otherwise, call
-      the next tool. Deliver only the answer without meta-commentary."}], "role":
-      "user"}, {"parts": [{"text": ""}], "role": "model"}, {"parts": [{"text": "The
-      result of 15 * 8 is 120"}], "role": "user"}, {"parts": [{"text": "Analyze the
-      tool result. If requirements are met, provide the Final Answer. Otherwise, call
-      the next tool. Deliver only the answer without meta-commentary."}], "role":
-      "user"}, {"parts": [{"text": ""}], "role": "model"}, {"parts": [{"text": "The
-      result of 15 * 8 is 120"}], "role": "user"}, {"parts": [{"text": "Analyze the
-      tool result. If requirements are met, provide the Final Answer. Otherwise, call
-      the next tool. Deliver only the answer without meta-commentary."}], "role":
-      "user"}], "systemInstruction": {"parts": [{"text": "You are Math Assistant.
-      You are a helpful math assistant.\nYour personal goal is: Help users with mathematical
-      calculations"}], "role": "user"}, "tools": [{"functionDeclarations": [{"description":
-      "Perform mathematical calculations. Use this for any math operations.", "name":
-      "calculator", "parameters": {"properties": {"expression": {"description": "Mathematical
-      expression to evaluate", "title": "Expression", "type": "STRING"}}, "required":
-      ["expression"], "type": "OBJECT"}}]}], "generationConfig": {"stopSequences":
-      ["\nObservation:"]}}'
-    headers:
-      User-Agent:
-      - X-USER-AGENT-XXX
-      accept:
-      - '*/*'
-      accept-encoding:
-      - ACCEPT-ENCODING-XXX
-      connection:
-      - keep-alive
-      content-length:
-      - '2467'
-      content-type:
-      - application/json
-      host:
-      - generativelanguage.googleapis.com
-      x-goog-api-client:
-      - google-genai-sdk/1.49.0 gl-python/3.13.3
-      x-goog-api-key:
-      - X-GOOG-API-KEY-XXX
-    method: POST
-    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-exp:generateContent
-  response:
-    body:
-      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
-        [\n          {\n            \"text\": \"120\\n\"\n          }\n        ],\n
-        \       \"role\": \"model\"\n      },\n      \"finishReason\": \"STOP\",\n
-        \     \"avgLogprobs\": -0.0097615998238325119\n    }\n  ],\n  \"usageMetadata\":
-        {\n    \"promptTokenCount\": 333,\n    \"candidatesTokenCount\": 4,\n    \"totalTokenCount\":
-        337,\n    \"promptTokensDetails\": [\n      {\n        \"modality\": \"TEXT\",\n
-        \       \"tokenCount\": 333\n      }\n    ],\n    \"candidatesTokensDetails\":
-        [\n      {\n        \"modality\": \"TEXT\",\n        \"tokenCount\": 4\n      }\n
-        \   ]\n  },\n  \"modelVersion\": \"gemini-2.0-flash-exp\",\n  \"responseId\":
-        \"QZByaZHABO-i_uMP58aYqAk\"\n}\n"
-    headers:
-      Alt-Svc:
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Content-Type:
-      - application/json; charset=UTF-8
-      Date:
-      - Thu, 22 Jan 2026 21:01:53 GMT
-      Server:
-      - scaffolding on HTTPServer2
-      Server-Timing:
-      - gfet4t7; dur=412
+      - gfet4t7; dur=421
       Transfer-Encoding:
       - chunked
       Vary:

lib/crewai/tests/cassettes/agents/TestGeminiNativeToolCalling.test_gemini_parallel_native_tool_calling_test_agent_kickoff.yaml

@@ -0,0 +1,188 @@
+interactions:
+- request:
+    body: '{"contents": [{"parts": [{"text": "\nCurrent Task: This is a tool-calling
+      compliance test. In your next assistant turn, emit exactly 3 tool calls in the
+      same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary."}], "role": "user"}], "systemInstruction": {"parts": [{"text":
+      "You are Parallel Tool Agent. You follow tool instructions precisely.\nYour
+      personal goal is: Use both tools exactly as instructed"}], "role": "user"},
+      "tools": [{"functionDeclarations": [{"description": "Local search tool #1 for
+      concurrency testing.", "name": "parallel_local_search_one", "parameters_json_schema":
+      {"properties": {"query": {"description": "Search query", "title": "Query", "type":
+      "string"}}, "required": ["query"], "type": "object", "additionalProperties":
+      false}}, {"description": "Local search tool #2 for concurrency testing.", "name":
+      "parallel_local_search_two", "parameters_json_schema": {"properties": {"query":
+      {"description": "Search query", "title": "Query", "type": "string"}}, "required":
+      ["query"], "type": "object", "additionalProperties": false}}, {"description":
+      "Local search tool #3 for concurrency testing.", "name": "parallel_local_search_three",
+      "parameters_json_schema": {"properties": {"query": {"description": "Search query",
+      "title": "Query", "type": "string"}}, "required": ["query"], "type": "object",
+      "additionalProperties": false}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1783'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      x-goog-api-client:
+      - google-genai-sdk/1.49.0 gl-python/3.13.3
+      x-goog-api-key:
+      - X-GOOG-API-KEY-XXX
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
+  response:
+    body:
+      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
+        [\n          {\n            \"functionCall\": {\n              \"name\": \"parallel_local_search_one\",\n
+        \             \"args\": {\n                \"query\": \"latest OpenAI model
+        release notes\"\n              }\n            },\n            \"thoughtSignature\":
+        \"CrICAb4+9vtrrkiSatPyOs7fssb9akcgCIiQdJKp/k+hcEZVNFvU/H0e4FFmLIhTCPRyHxmU+AQPtBZ5vg6y9ZCcv11RdcWgYW8rPQzCnC+YTUxPAfDzaObky1QsL5pl9+yglQqVoVM31ZcnoiH02z85pwAv6TSJxdJZEekW6XwcIrCoHNCgY3ghHFEd3y3wLJ5JWL7wmiRNTC9TCT8aJHXKFohYrb+4JMULCx8BqKVxOucZPiDHA8GsoqSlzkYEe2xCh9oSdaZpCFrxhZ9bwoVDbVmPrjaq2hj5BoJ5hNxscHJ/E0EOl4ogeKZW+hIVfdzpjAFZW9Oejkb9G4ZSLbxXsoO7x8bi4LHFRABniGrWvNuOOH0Udh4t57oXHXZO4u5NNTood/GkJGcP+aHqUAH1fwqL\"\n
+        \         },\n          {\n            \"functionCall\": {\n              \"name\":
+        \"parallel_local_search_two\",\n              \"args\": {\n                \"query\":
+        \"latest Anthropic model release notes\"\n              }\n            }\n
+        \         },\n          {\n            \"functionCall\": {\n              \"name\":
+        \"parallel_local_search_three\",\n              \"args\": {\n                \"query\":
+        \"latest Gemini model release notes\"\n              }\n            }\n          }\n
+        \       ],\n        \"role\": \"model\"\n      },\n      \"finishReason\":
+        \"STOP\",\n      \"index\": 0,\n      \"finishMessage\": \"Model generated
+        function call(s).\"\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
+        291,\n    \"candidatesTokenCount\": 70,\n    \"totalTokenCount\": 428,\n    \"promptTokensDetails\":
+        [\n      {\n        \"modality\": \"TEXT\",\n        \"tokenCount\": 291\n
+        \     }\n    ],\n    \"thoughtsTokenCount\": 67\n  },\n  \"modelVersion\":
+        \"gemini-2.5-flash\",\n  \"responseId\": \"alKWacytCLi5jMcPhISaoAI\"\n}\n"
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Wed, 18 Feb 2026 23:59:39 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=999
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      X-Frame-Options:
+      - X-FRAME-OPTIONS-XXX
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"contents": [{"parts": [{"text": "\nCurrent Task: This is a tool-calling
+      compliance test. In your next assistant turn, emit exactly 3 tool calls in the
+      same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary."}], "role": "user"}, {"parts": [{"functionCall": {"args":
+      {"query": "latest OpenAI model release notes"}, "name": "parallel_local_search_one"},
+      "thoughtSignature": "CrICAb4-9vtrrkiSatPyOs7fssb9akcgCIiQdJKp_k-hcEZVNFvU_H0e4FFmLIhTCPRyHxmU-AQPtBZ5vg6y9ZCcv11RdcWgYW8rPQzCnC-YTUxPAfDzaObky1QsL5pl9-yglQqVoVM31ZcnoiH02z85pwAv6TSJxdJZEekW6XwcIrCoHNCgY3ghHFEd3y3wLJ5JWL7wmiRNTC9TCT8aJHXKFohYrb-4JMULCx8BqKVxOucZPiDHA8GsoqSlzkYEe2xCh9oSdaZpCFrxhZ9bwoVDbVmPrjaq2hj5BoJ5hNxscHJ_E0EOl4ogeKZW-hIVfdzpjAFZW9Oejkb9G4ZSLbxXsoO7x8bi4LHFRABniGrWvNuOOH0Udh4t57oXHXZO4u5NNTood_GkJGcP-aHqUAH1fwqL"},
+      {"functionCall": {"args": {"query": "latest Anthropic model release notes"},
+      "name": "parallel_local_search_two"}}, {"functionCall": {"args": {"query": "latest
+      Gemini model release notes"}, "name": "parallel_local_search_three"}}], "role":
+      "model"}, {"parts": [{"functionResponse": {"name": "parallel_local_search_one",
+      "response": {"result": "[one] latest OpenAI model release notes"}}}], "role":
+      "user"}, {"parts": [{"functionResponse": {"name": "parallel_local_search_two",
+      "response": {"result": "[two] latest Anthropic model release notes"}}}], "role":
+      "user"}, {"parts": [{"functionResponse": {"name": "parallel_local_search_three",
+      "response": {"result": "[three] latest Gemini model release notes"}}}], "role":
+      "user"}], "systemInstruction": {"parts": [{"text": "You are Parallel Tool Agent.
+      You follow tool instructions precisely.\nYour personal goal is: Use both tools
+      exactly as instructed"}], "role": "user"}, "tools": [{"functionDeclarations":
+      [{"description": "Local search tool #1 for concurrency testing.", "name": "parallel_local_search_one",
+      "parameters_json_schema": {"properties": {"query": {"description": "Search query",
+      "title": "Query", "type": "string"}}, "required": ["query"], "type": "object",
+      "additionalProperties": false}}, {"description": "Local search tool #2 for concurrency
+      testing.", "name": "parallel_local_search_two", "parameters_json_schema": {"properties":
+      {"query": {"description": "Search query", "title": "Query", "type": "string"}},
+      "required": ["query"], "type": "object", "additionalProperties": false}}, {"description":
+      "Local search tool #3 for concurrency testing.", "name": "parallel_local_search_three",
+      "parameters_json_schema": {"properties": {"query": {"description": "Search query",
+      "title": "Query", "type": "string"}}, "required": ["query"], "type": "object",
+      "additionalProperties": false}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '3071'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      x-goog-api-client:
+      - google-genai-sdk/1.49.0 gl-python/3.13.3
+      x-goog-api-key:
+      - X-GOOG-API-KEY-XXX
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
+  response:
+    body:
+      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
+        [\n          {\n            \"text\": \"Here is a summary of the latest model
+        release notes: I have retrieved information regarding the latest OpenAI model
+        release notes, the latest Anthropic model release notes, and the latest Gemini
+        model release notes. The specific details of these release notes are available
+        through the respective tool outputs.\",\n            \"thoughtSignature\":
+        \"CsoBAb4+9vtPvWFM08lR1S4QrLN+Z1+Zpf04Y/bC8tjOpnxz3EEvHyRNEwkslUX5pftBi8J78Xk4/FUER0xjJZc8clUObTvayxLNup4h1JwJ5ZdatulInNGTEieFnF4w8KjSFB/vqNCZvXWZbiLkpzqAnsoAIf0x4VmMN11V0Ozo+3f2QftD+iBrfu3g21UI5tbG0Z+0QHxjRVKXrQOp7dmoZPzaxI0zalfDEI+A2jGpVl/VvauVNv0jQn0yItcA5tkVeWLq6717CjNoig==\"\n
+        \         }\n        ],\n        \"role\": \"model\"\n      },\n      \"finishReason\":
+        \"STOP\",\n      \"index\": 0\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
+        435,\n    \"candidatesTokenCount\": 54,\n    \"totalTokenCount\": 524,\n    \"promptTokensDetails\":
+        [\n      {\n        \"modality\": \"TEXT\",\n        \"tokenCount\": 435\n
+        \     }\n    ],\n    \"thoughtsTokenCount\": 35\n  },\n  \"modelVersion\":
+        \"gemini-2.5-flash\",\n  \"responseId\": \"bFKWaZOZCqCvjMcPvvGNgAc\"\n}\n"
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Wed, 18 Feb 2026 23:59:41 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=967
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      X-Frame-Options:
+      - X-FRAME-OPTIONS-XXX
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestGeminiNativeToolCalling.test_gemini_parallel_native_tool_calling_test_crew.yaml

@@ -0,0 +1,192 @@
+interactions:
+- request:
+    body: '{"contents": [{"parts": [{"text": "\nCurrent Task: This is a tool-calling
+      compliance test. In your next assistant turn, emit exactly 3 tool calls in the
+      same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary.\n\nThis is the expected criteria for your final answer: A
+      one sentence summary of both tool outputs\nyou MUST return the actual complete
+      content as the final answer, not a summary."}], "role": "user"}], "systemInstruction":
+      {"parts": [{"text": "You are Parallel Tool Agent. You follow tool instructions
+      precisely.\nYour personal goal is: Use both tools exactly as instructed"}],
+      "role": "user"}, "tools": [{"functionDeclarations": [{"description": "Local
+      search tool #1 for concurrency testing.", "name": "parallel_local_search_one",
+      "parameters_json_schema": {"properties": {"query": {"description": "Search query",
+      "title": "Query", "type": "string"}}, "required": ["query"], "type": "object",
+      "additionalProperties": false}}, {"description": "Local search tool #2 for concurrency
+      testing.", "name": "parallel_local_search_two", "parameters_json_schema": {"properties":
+      {"query": {"description": "Search query", "title": "Query", "type": "string"}},
+      "required": ["query"], "type": "object", "additionalProperties": false}}, {"description":
+      "Local search tool #3 for concurrency testing.", "name": "parallel_local_search_three",
+      "parameters_json_schema": {"properties": {"query": {"description": "Search query",
+      "title": "Query", "type": "string"}}, "required": ["query"], "type": "object",
+      "additionalProperties": false}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1964'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      x-goog-api-client:
+      - google-genai-sdk/1.49.0 gl-python/3.13.3
+      x-goog-api-key:
+      - X-GOOG-API-KEY-XXX
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
+  response:
+    body:
+      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
+        [\n          {\n            \"functionCall\": {\n              \"name\": \"parallel_local_search_one\",\n
+        \             \"args\": {\n                \"query\": \"latest OpenAI model
+        release notes\"\n              }\n            },\n            \"thoughtSignature\":
+        \"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\"\n
+        \         },\n          {\n            \"functionCall\": {\n              \"name\":
+        \"parallel_local_search_two\",\n              \"args\": {\n                \"query\":
+        \"latest Anthropic model release notes\"\n              }\n            }\n
+        \         },\n          {\n            \"functionCall\": {\n              \"name\":
+        \"parallel_local_search_three\",\n              \"args\": {\n                \"query\":
+        \"latest Gemini model release notes\"\n              }\n            }\n          }\n
+        \       ],\n        \"role\": \"model\"\n      },\n      \"finishReason\":
+        \"STOP\",\n      \"index\": 0,\n      \"finishMessage\": \"Model generated
+        function call(s).\"\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
+        327,\n    \"candidatesTokenCount\": 70,\n    \"totalTokenCount\": 536,\n    \"promptTokensDetails\":
+        [\n      {\n        \"modality\": \"TEXT\",\n        \"tokenCount\": 327\n
+        \     }\n    ],\n    \"thoughtsTokenCount\": 139\n  },\n  \"modelVersion\":
+        \"gemini-2.5-flash\",\n  \"responseId\": \"ZVKWabziF7bcjMcP3r2SuAg\"\n}\n"
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Wed, 18 Feb 2026 23:59:34 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=1262
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      X-Frame-Options:
+      - X-FRAME-OPTIONS-XXX
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"contents": [{"parts": [{"text": "\nCurrent Task: This is a tool-calling
+      compliance test. In your next assistant turn, emit exactly 3 tool calls in the
+      same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary.\n\nThis is the expected criteria for your final answer: A
+      one sentence summary of both tool outputs\nyou MUST return the actual complete
+      content as the final answer, not a summary."}], "role": "user"}, {"parts": [{"functionCall":
+      {"args": {"query": "latest OpenAI model release notes"}, "name": "parallel_local_search_one"}},
+      {"functionCall": {"args": {"query": "latest Anthropic model release notes"},
+      "name": "parallel_local_search_two"}}, {"functionCall": {"args": {"query": "latest
+      Gemini model release notes"}, "name": "parallel_local_search_three"}}], "role":
+      "model"}, {"parts": [{"functionResponse": {"name": "parallel_local_search_one",
+      "response": {"result": "[one] latest OpenAI model release notes"}}}], "role":
+      "user"}, {"parts": [{"functionResponse": {"name": "parallel_local_search_two",
+      "response": {"result": "[two] latest Anthropic model release notes"}}}], "role":
+      "user"}, {"parts": [{"functionResponse": {"name": "parallel_local_search_three",
+      "response": {"result": "[three] latest Gemini model release notes"}}}], "role":
+      "user"}, {"parts": [{"text": "Analyze the tool result. If requirements are met,
+      provide the Final Answer. Otherwise, call the next tool. Deliver only the answer
+      without meta-commentary."}], "role": "user"}], "systemInstruction": {"parts":
+      [{"text": "You are Parallel Tool Agent. You follow tool instructions precisely.\nYour
+      personal goal is: Use both tools exactly as instructed"}], "role": "user"},
+      "tools": [{"functionDeclarations": [{"description": "Local search tool #1 for
+      concurrency testing.", "name": "parallel_local_search_one", "parameters_json_schema":
+      {"properties": {"query": {"description": "Search query", "title": "Query", "type":
+      "string"}}, "required": ["query"], "type": "object", "additionalProperties":
+      false}}, {"description": "Local search tool #2 for concurrency testing.", "name":
+      "parallel_local_search_two", "parameters_json_schema": {"properties": {"query":
+      {"description": "Search query", "title": "Query", "type": "string"}}, "required":
+      ["query"], "type": "object", "additionalProperties": false}}, {"description":
+      "Local search tool #3 for concurrency testing.", "name": "parallel_local_search_three",
+      "parameters_json_schema": {"properties": {"query": {"description": "Search query",
+      "title": "Query", "type": "string"}}, "required": ["query"], "type": "object",
+      "additionalProperties": false}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '3014'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      x-goog-api-client:
+      - google-genai-sdk/1.49.0 gl-python/3.13.3
+      x-goog-api-key:
+      - X-GOOG-API-KEY-XXX
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
+  response:
+    body:
+      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
+        [\n          {\n            \"text\": \"The search results indicate the latest
+        model release notes for OpenAI, Anthropic, and Gemini are: [one] latest OpenAI
+        model release notes[two] latest Anthropic model release notes[three] latest
+        Gemini model release notes.\",\n            \"thoughtSignature\": \"CsUPAb4+9vs4hkuatQAakl1FSHx5DIde9nHYobJdlWs2HEzES9gHn7uwjMIlFPTzJUbnZqxpAK93hqsCofdfGANr8dwK+/IbZAiMSikpAq2ZjEbWADjfalU3ke4LcQMh6TEYFVGz1QCinjne3jZx5jOVaL8YdAtjOYnBZWA6KqdvfKjD7+Ct/BLoEqvu4LW6kxhXQgcV+D3M1QxGlr1dxpajj4wyYFI9LXchE2vCdAMPYTkPQ4WPbS3xjz0jJb6qFAwwg+BY5kGemkWWVHsvq28t09pd7FEH0bod5cEpR65qEefpJfhHsXYqmOwHDkfNePYnYC+5qmn7kvkN+fhF41SoMRZahMZGDjIo+q6vvru3eXKmZiuLsrh8AqQIks/4S3sSuxt16ogYKE+LlFxml2ygXFPww59nRAtc+xK6VW8jB2vyv9Eo5cpnG9ZBv1dOznJnmj4AWA1ddMlp+yq8AdaboTSo5dysYMwFcSXS3kuU+xi92dC+7GqZZbDr5frvnc+MnSuzYwHhNjSQqvTo5DKGit53zDwlFJT74kLBXk36BOFQp4xlfs+BpKkw11bow6qQoTvC68D023ZHami+McO1WYBDoO5CrDoosU8fAYljqaGArBoMlssF4O7VKHEaEbEZnYCr0Wxo6XP/mtPIpHQE4OyCz/GAJSJtQv1hO7DNCMzpSpkLyuemB1SOZGl3mlLQhosh3TAGP0xgqmHpKccdCSWoXGWjO48VluFuV9E1FwW1Xi++XhMRcUaljJXPZaNVjGcAG1uAxeVkUMsY8tBvQ0vaumUK2jkzbyQTWeStEWwl1yKmklI8JDXske/k6tYJOyF+8t0mF7oCEqNHSNicj7TomihpPlVjNl1Mm4l5fvwlKtAPJwiKrchCunlZB3uGN1AR0h0Hvznffutc/lV/FWFbNgFAaNJZKRs40vMk1xmRZyH2rs+Ob2fZriQ3BSwzzNeiwDLXxm0m/ytOai+K9ObFuC/IEh5fJfvQbNeo3TmiCAMCZPNXMDtlOyLqQzzKwmMFH4c53Ol+kkTiuAKECNQR1dOCufAL0U5lzEUFRxFvOq67lp6xqG8m+WzCIkbnF8QyJHfujtXVMJACaevUkM7+kAVyTwETEKQsanp0tBwzV42ieChp/h7pivcC++cFXdSG5dvR94BgkHmtpC9+jfNH32RREPLuyWfU5aBXiOkxjRs9fDexAFjrkGjM18I+jqHZNeuUR20BKe2jFsU8xJS3Fa4eXabm/YPL1t8R5jr572Ch/r4bspFp8MQ5RcFo8Nn/HiBmW8uZ2BcLEY1RPWUBvxVhfvh/hNxaRKu21x8vGz72RoiNuOjNbeADYAaBJqBGLp0MALxZ/rnXPzDLQUt6Mv07fWHAZr5p3r/skleot25lr2Tcl4qJCPM4/cfs6U0x4CY26ktBiCs4bWKqSEV1Q05nf5kpxVOIRSTgxqFOj/rWIAF3uw7mvsuRKd3YXILV5OrvEoETdQvf7BdYPbQbIQYDf7DBKhf51O8RKQgcfl6mVQswamdJ+PyqLbozTkFCjXMKI0PwJdy8tfKfCeeEe0TbOXSfeTczKQkL8WyWkBg4tS81JnWAVzfVlNjbvo/fk+wv7FyfJJS1HJGlxZ0kUlWi1369rSlldYPoSqopuekOxtYnpYpz92y/jVLNQXE1IVLqWYh9o3gTwjeyaHG7fCaWF2QRGrCUvejT8eJjevhj/sgadjPVcEP5o7Zcw5yTBCgc0+FX1j5KpCmfZ/dVvT4iIX8bOkhxjHQ8ifOx39BMM4EObgCA+g+BFN+Ra7kOf4hJ6tPNhqvJa4E4fyISlVrRiBqSt59ZkuLyWuY9SYy0nvbklP30WDUHSAvcuEwVMSuT524afHISfO/+tSgE7JAKzEPSOoVO3Z5NS9kcAqHuBSe/LL4XJbCKF9Oggm9/gwdAulnBANd4ydQ/raTPE/QUu/CGqqGhBd+wo8x0Jg/BMZWkwhz0fEzsh+OjnrEkHv4QIqZ9v/j1Rv9uc+cDeK7eGi62okGLrPFX2pNQtsZRdUM9aBSlTBUVSdCDpkvieENzLnR257EDZy1EV2HxGRfOFZVVdaW1n8XvL73pcFoQ5XABpfYuigOS8i4S8g43Qfe77GosnuXR5rcJCrL03q3hptb97K5ysKFLgumsaaWo92MBhZYKvQ6SwStgyWRlb22uQGQJYsS8OTD/uVNiQzFjOMsR/l71c9RI1Eb7SQJT6WWvL1YhA7sQw/lQf8soLKfWshoky6mMrGopjRak8xHpJe5VWbqK8PK6iXDd403JrHICyh4M3FpEja3eX2V3SN6U+EgIWKIE8lE/iQZakhLtG2KL7nNQy/cksxzIh5ElQCe5NkrQZO0fai6ek8qwbmz07RVg2FknD7F2hvmxZBqoJSXhsFVn/9+fnkcsZekEtUevFmlQQNspPc63XgO0XmpTye9uM/BbTEsNEWeHSFZTEQLLx1l+pgwsYO3NlNSIUN24/GIR7JrZFG4fAoljkDKjhrYQzr1Fiy3t5G+CmadZ0TcjRQQdDw36ETlf7cizcrQc4FNtnx5rNWEaf54vUvlsd2DD19UIkzP9omITsiuNPPcUNq0A6v1TkgnSNYfhb26nxJIg34r8MmCAhWzB2eCy54gvOHDGLFAwfFZrQdvl\"\n
+        \         }\n        ],\n        \"role\": \"model\"\n      },\n      \"finishReason\":
+        \"STOP\",\n      \"index\": 0\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
+        504,\n    \"candidatesTokenCount\": 45,\n    \"totalTokenCount\": 973,\n    \"promptTokensDetails\":
+        [\n      {\n        \"modality\": \"TEXT\",\n        \"tokenCount\": 504\n
+        \     }\n    ],\n    \"thoughtsTokenCount\": 424\n  },\n  \"modelVersion\":
+        \"gemini-2.5-flash\",\n  \"responseId\": \"Z1KWaYbTKZvnjMcP7piEoAg\"\n}\n"
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Wed, 18 Feb 2026 23:59:37 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=2283
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      X-Frame-Options:
+      - X-FRAME-OPTIONS-XXX
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestOpenAINativeToolCalling.test_openai_agent_with_native_tool_calling.yaml

@@ -5,9 +5,9 @@ interactions:
       calculations"},{"role":"user","content":"\nCurrent Task: Calculate what is 15
       * 8\n\nThis is the expected criteria for your final answer: The result of the
       calculation\nyou MUST return the actual complete content as the final answer,
-      not a summary.\n\nThis is VERY important to you, your job depends on it!"}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"calculator","description":"Perform
-      mathematical calculations. Use this for any math operations.","parameters":{"properties":{"expression":{"description":"Mathematical
-      expression to evaluate","title":"Expression","type":"string"}},"required":["expression"],"type":"object"}}}]}'
+      not a summary."}],"model":"gpt-5-nano","tool_choice":"auto","tools":[{"type":"function","function":{"name":"calculator","description":"Perform
+      mathematical calculations. Use this for any math operations.","strict":true,"parameters":{"properties":{"expression":{"description":"Mathematical
+      expression to evaluate","title":"Expression","type":"string"}},"required":["expression"],"type":"object","additionalProperties":false}}}]}'
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -20,7 +20,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '829'
+      - '813'
       content-type:
       - application/json
       host:
@@ -47,140 +47,17 @@ interactions:
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-D0vm7joOuDBPcMpfmOnftOoTCPtc8\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1769114459,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
-        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
-        \           \"id\": \"call_G73UZDvL4wC9EEdvm1UcRIRM\",\n            \"type\":
-        \"function\",\n            \"function\": {\n              \"name\": \"calculator\",\n
-        \             \"arguments\": \"{\\\"expression\\\":\\\"15 * 8\\\"}\"\n            }\n
-        \         }\n        ],\n        \"refusal\": null,\n        \"annotations\":
-        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"tool_calls\"\n
-        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 137,\n    \"completion_tokens\":
-        17,\n    \"total_tokens\": 154,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
-        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
-        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
-        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-        \"default\",\n  \"system_fingerprint\": \"fp_c4585b5b9c\"\n}\n"
-    headers:
-      CF-RAY:
-      - CF-RAY-XXX
-      Connection:
-      - keep-alive
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 22 Jan 2026 20:40:59 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - SET-COOKIE-XXX
-      Strict-Transport-Security:
-      - STS-XXX
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - X-CONTENT-TYPE-XXX
-      access-control-expose-headers:
-      - ACCESS-CONTROL-XXX
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-organization:
-      - OPENAI-ORG-XXX
-      openai-processing-ms:
-      - '761'
-      openai-project:
-      - OPENAI-PROJECT-XXX
-      openai-version:
-      - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '1080'
-      x-openai-proxy-wasm:
-      - v0.1
-      x-ratelimit-limit-requests:
-      - X-RATELIMIT-LIMIT-REQUESTS-XXX
-      x-ratelimit-limit-tokens:
-      - X-RATELIMIT-LIMIT-TOKENS-XXX
-      x-ratelimit-remaining-requests:
-      - X-RATELIMIT-REMAINING-REQUESTS-XXX
-      x-ratelimit-remaining-tokens:
-      - X-RATELIMIT-REMAINING-TOKENS-XXX
-      x-ratelimit-reset-requests:
-      - X-RATELIMIT-RESET-REQUESTS-XXX
-      x-ratelimit-reset-tokens:
-      - X-RATELIMIT-RESET-TOKENS-XXX
-      x-request-id:
-      - X-REQUEST-ID-XXX
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"messages":[{"role":"system","content":"You are Math Assistant. You are
-      a helpful math assistant.\nYour personal goal is: Help users with mathematical
-      calculations"},{"role":"user","content":"\nCurrent Task: Calculate what is 15
-      * 8\n\nThis is the expected criteria for your final answer: The result of the
-      calculation\nyou MUST return the actual complete content as the final answer,
-      not a summary.\n\nThis is VERY important to you, your job depends on it!"},{"role":"assistant","content":null,"tool_calls":[{"id":"call_G73UZDvL4wC9EEdvm1UcRIRM","type":"function","function":{"name":"calculator","arguments":"{\"expression\":\"15
-      * 8\"}"}}]},{"role":"tool","tool_call_id":"call_G73UZDvL4wC9EEdvm1UcRIRM","content":"The
-      result of 15 * 8 is 120"},{"role":"user","content":"Analyze the tool result.
-      If requirements are met, provide the Final Answer. Otherwise, call the next
-      tool. Deliver only the answer without meta-commentary."}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"calculator","description":"Perform
-      mathematical calculations. Use this for any math operations.","parameters":{"properties":{"expression":{"description":"Mathematical
-      expression to evaluate","title":"Expression","type":"string"}},"required":["expression"],"type":"object"}}}]}'
-    headers:
-      User-Agent:
-      - X-USER-AGENT-XXX
-      accept:
-      - application/json
-      accept-encoding:
-      - ACCEPT-ENCODING-XXX
-      authorization:
-      - AUTHORIZATION-XXX
-      connection:
-      - keep-alive
-      content-length:
-      - '1299'
-      content-type:
-      - application/json
-      cookie:
-      - COOKIE-XXX
-      host:
-      - api.openai.com
-      x-stainless-arch:
-      - X-STAINLESS-ARCH-XXX
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - X-STAINLESS-OS-XXX
-      x-stainless-package-version:
-      - 1.83.0
-      x-stainless-read-timeout:
-      - X-STAINLESS-READ-TIMEOUT-XXX
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.13.3
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: "{\n  \"id\": \"chatcmpl-D0vm8mUnzLxu9pf1rc7MODkrMsCmf\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1769114460,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      string: "{\n  \"id\": \"chatcmpl-DAlG9W2mJYuOgpf3FwCRgbqaiHWf3\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1771457317,\n  \"model\": \"gpt-5-nano-2025-08-07\",\n
         \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
         \"assistant\",\n        \"content\": \"120\",\n        \"refusal\": null,\n
-        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
-        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 207,\n    \"completion_tokens\":
-        2,\n    \"total_tokens\": 209,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        \       \"annotations\": []\n      },\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 208,\n    \"completion_tokens\":
+        138,\n    \"total_tokens\": 346,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
         0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
-        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        {\n      \"reasoning_tokens\": 128,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
         0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-        \"default\",\n  \"system_fingerprint\": \"fp_c4585b5b9c\"\n}\n"
+        \"default\",\n  \"system_fingerprint\": null\n}\n"
     headers:
       CF-RAY:
       - CF-RAY-XXX
@@ -189,7 +66,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 22 Jan 2026 20:41:00 GMT
+      - Wed, 18 Feb 2026 23:28:39 GMT
       Server:
       - cloudflare
       Strict-Transport-Security:
@@ -207,13 +84,13 @@ interactions:
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '262'
+      - '1869'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '496'
+      set-cookie:
+      - SET-COOKIE-XXX
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:

lib/crewai/tests/cassettes/agents/TestOpenAINativeToolCalling.test_openai_parallel_native_tool_calling_test_agent_kickoff.yaml

@@ -0,0 +1,265 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Parallel Tool Agent. You
+      follow tool instructions precisely.\nYour personal goal is: Use both tools exactly
+      as instructed"},{"role":"user","content":"\nCurrent Task: This is a tool-calling
+      compliance test. In your next assistant turn, emit exactly 3 tool calls in the
+      same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary."}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"parallel_local_search_one","description":"Local
+      search tool #1 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"parallel_local_search_two","description":"Local
+      search tool #2 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"parallel_local_search_three","description":"Local
+      search tool #3 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1733'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-DAldZHfQGVcV3FNwAJAtNooU3PAU7\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1771458769,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+        \           \"id\": \"call_kz1qLLRsugXwWiQMeH9oFAep\",\n            \"type\":
+        \"function\",\n            \"function\": {\n              \"name\": \"parallel_local_search_one\",\n
+        \             \"arguments\": \"{\\\"query\\\": \\\"latest OpenAI model release
+        notes\\\"}\"\n            }\n          },\n          {\n            \"id\":
+        \"call_yNouGq1Kv6P5W9fhTng6acZi\",\n            \"type\": \"function\",\n
+        \           \"function\": {\n              \"name\": \"parallel_local_search_two\",\n
+        \             \"arguments\": \"{\\\"query\\\": \\\"latest Anthropic model
+        release notes\\\"}\"\n            }\n          },\n          {\n            \"id\":
+        \"call_O7MqnuniDmyT6a0BS31GTunB\",\n            \"type\": \"function\",\n
+        \           \"function\": {\n              \"name\": \"parallel_local_search_three\",\n
+        \             \"arguments\": \"{\\\"query\\\": \\\"latest Gemini model release
+        notes\\\"}\"\n            }\n          }\n        ],\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"tool_calls\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        259,\n    \"completion_tokens\": 78,\n    \"total_tokens\": 337,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_414ba99a04\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 18 Feb 2026 23:52:50 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '1418'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      set-cookie:
+      - SET-COOKIE-XXX
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Parallel Tool Agent. You
+      follow tool instructions precisely.\nYour personal goal is: Use both tools exactly
+      as instructed"},{"role":"user","content":"\nCurrent Task: This is a tool-calling
+      compliance test. In your next assistant turn, emit exactly 3 tool calls in the
+      same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_kz1qLLRsugXwWiQMeH9oFAep","type":"function","function":{"name":"parallel_local_search_one","arguments":"{\"query\":
+      \"latest OpenAI model release notes\"}"}},{"id":"call_yNouGq1Kv6P5W9fhTng6acZi","type":"function","function":{"name":"parallel_local_search_two","arguments":"{\"query\":
+      \"latest Anthropic model release notes\"}"}},{"id":"call_O7MqnuniDmyT6a0BS31GTunB","type":"function","function":{"name":"parallel_local_search_three","arguments":"{\"query\":
+      \"latest Gemini model release notes\"}"}}]},{"role":"tool","tool_call_id":"call_kz1qLLRsugXwWiQMeH9oFAep","name":"parallel_local_search_one","content":"[one]
+      latest OpenAI model release notes"},{"role":"tool","tool_call_id":"call_yNouGq1Kv6P5W9fhTng6acZi","name":"parallel_local_search_two","content":"[two]
+      latest Anthropic model release notes"},{"role":"tool","tool_call_id":"call_O7MqnuniDmyT6a0BS31GTunB","name":"parallel_local_search_three","content":"[three]
+      latest Gemini model release notes"}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"parallel_local_search_one","description":"Local
+      search tool #1 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"parallel_local_search_two","description":"Local
+      search tool #2 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"parallel_local_search_three","description":"Local
+      search tool #3 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '2756'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-DAldbawkFNpOeXbaJTkTlsSi7OiII\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1771458771,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"The latest release notes for OpenAI,
+        Anthropic, and Gemini models highlight significant updates and improvements
+        in each respective technology. OpenAI's notes detail new features and optimizations
+        that enhance user interaction and performance. Anthropic's release emphasizes
+        their focus on safety and alignment in AI development, showcasing advancements
+        in responsible AI practices. Gemini's notes underline their innovative approaches
+        and cutting-edge functionalities designed to push the boundaries of current
+        AI capabilities.\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 377,\n    \"completion_tokens\":
+        85,\n    \"total_tokens\": 462,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_414ba99a04\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 18 Feb 2026 23:52:53 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '1755'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestOpenAINativeToolCalling.test_openai_parallel_native_tool_calling_test_crew.yaml

@@ -0,0 +1,265 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Parallel Tool Agent. You
+      follow tool instructions precisely.\nYour personal goal is: Use both tools exactly
+      as instructed"},{"role":"user","content":"\nCurrent Task: This is a tool-calling
+      compliance test. In your next assistant turn, emit exactly 3 tool calls in the
+      same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary.\n\nThis is the expected criteria for your final answer: A
+      one sentence summary of both tool outputs\nyou MUST return the actual complete
+      content as the final answer, not a summary."}],"model":"gpt-5-nano","temperature":1,"tool_choice":"auto","tools":[{"type":"function","function":{"name":"parallel_local_search_one","description":"Local
+      search tool #1 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"parallel_local_search_two","description":"Local
+      search tool #2 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"parallel_local_search_three","description":"Local
+      search tool #3 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1929'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-DAlddfEozIpgleBufPaffZMQWK0Hj\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1771458773,\n  \"model\": \"gpt-5-nano-2025-08-07\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+        \           \"id\": \"call_Putc2jV5GhiIZMwx8mDcI61Q\",\n            \"type\":
+        \"function\",\n            \"function\": {\n              \"name\": \"parallel_local_search_one\",\n
+        \             \"arguments\": \"{\\\"query\\\": \\\"latest OpenAI model release
+        notes\\\"}\"\n            }\n          },\n          {\n            \"id\":
+        \"call_iyjwcvkL3PdoOddxsqkHCT9T\",\n            \"type\": \"function\",\n
+        \           \"function\": {\n              \"name\": \"parallel_local_search_two\",\n
+        \             \"arguments\": \"{\\\"query\\\": \\\"latest Anthropic model
+        release notes\\\"}\"\n            }\n          },\n          {\n            \"id\":
+        \"call_G728RseEU7SbGk5YTiyyp9IH\",\n            \"type\": \"function\",\n
+        \           \"function\": {\n              \"name\": \"parallel_local_search_three\",\n
+        \             \"arguments\": \"{\\\"query\\\": \\\"latest Gemini model release
+        notes\\\"}\"\n            }\n          }\n        ],\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"finish_reason\": \"tool_calls\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 378,\n    \"completion_tokens\":
+        1497,\n    \"total_tokens\": 1875,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 1408,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 18 Feb 2026 23:53:08 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '14853'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      set-cookie:
+      - SET-COOKIE-XXX
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Parallel Tool Agent. You
+      follow tool instructions precisely.\nYour personal goal is: Use both tools exactly
+      as instructed"},{"role":"user","content":"\nCurrent Task: This is a tool-calling
+      compliance test. In your next assistant turn, emit exactly 3 tool calls in the
+      same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary.\n\nThis is the expected criteria for your final answer: A
+      one sentence summary of both tool outputs\nyou MUST return the actual complete
+      content as the final answer, not a summary."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_Putc2jV5GhiIZMwx8mDcI61Q","type":"function","function":{"name":"parallel_local_search_one","arguments":"{\"query\":
+      \"latest OpenAI model release notes\"}"}},{"id":"call_iyjwcvkL3PdoOddxsqkHCT9T","type":"function","function":{"name":"parallel_local_search_two","arguments":"{\"query\":
+      \"latest Anthropic model release notes\"}"}},{"id":"call_G728RseEU7SbGk5YTiyyp9IH","type":"function","function":{"name":"parallel_local_search_three","arguments":"{\"query\":
+      \"latest Gemini model release notes\"}"}}]},{"role":"tool","tool_call_id":"call_Putc2jV5GhiIZMwx8mDcI61Q","name":"parallel_local_search_one","content":"[one]
+      latest OpenAI model release notes"},{"role":"tool","tool_call_id":"call_iyjwcvkL3PdoOddxsqkHCT9T","name":"parallel_local_search_two","content":"[two]
+      latest Anthropic model release notes"},{"role":"tool","tool_call_id":"call_G728RseEU7SbGk5YTiyyp9IH","name":"parallel_local_search_three","content":"[three]
+      latest Gemini model release notes"},{"role":"user","content":"Analyze the tool
+      result. If requirements are met, provide the Final Answer. Otherwise, call the
+      next tool. Deliver only the answer without meta-commentary."}],"model":"gpt-5-nano","temperature":1,"tool_choice":"auto","tools":[{"type":"function","function":{"name":"parallel_local_search_one","description":"Local
+      search tool #1 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"parallel_local_search_two","description":"Local
+      search tool #2 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"parallel_local_search_three","description":"Local
+      search tool #3 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '3136'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-DAldt2BXNqiYYLPgInjHCpYKfk2VK\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1771458789,\n  \"model\": \"gpt-5-nano-2025-08-07\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"The results show the latest model release
+        notes for OpenAI, Anthropic, and Gemini.\",\n        \"refusal\": null,\n
+        \       \"annotations\": []\n      },\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 537,\n    \"completion_tokens\":
+        2011,\n    \"total_tokens\": 2548,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 1984,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 18 Feb 2026 23:53:25 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '15368'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestOpenAINativeToolCalling.test_openai_parallel_native_tool_calling_tool_hook_parity_agent_kickoff.yaml

@@ -0,0 +1,264 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Parallel Tool Agent. You
+      follow tool instructions precisely.\nYour personal goal is: Use both tools exactly
+      as instructed"},{"role":"user","content":"\nCurrent Task: This is a tool-calling
+      compliance test. In your next assistant turn, emit exactly 3 tool calls in the
+      same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary."}],"model":"gpt-5-nano","temperature":1,"tool_choice":"auto","tools":[{"type":"function","function":{"name":"parallel_local_search_one","description":"Local
+      search tool #1 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"parallel_local_search_two","description":"Local
+      search tool #2 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"parallel_local_search_three","description":"Local
+      search tool #3 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1748'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-DB244zBgA66fzl8TNcIPRWoE4lDIQ\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1771521916,\n  \"model\": \"gpt-5-nano-2025-08-07\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+        \           \"id\": \"call_D2ojRWqkng6krQ51vWQEU8wR\",\n            \"type\":
+        \"function\",\n            \"function\": {\n              \"name\": \"parallel_local_search_one\",\n
+        \             \"arguments\": \"{\\\"query\\\": \\\"latest OpenAI model release
+        notes\\\"}\"\n            }\n          },\n          {\n            \"id\":
+        \"call_v1tpTKw1sYcI75SWG1LCkAC3\",\n            \"type\": \"function\",\n
+        \           \"function\": {\n              \"name\": \"parallel_local_search_two\",\n
+        \             \"arguments\": \"{\\\"query\\\": \\\"latest Anthropic model
+        release notes\\\"}\"\n            }\n          },\n          {\n            \"id\":
+        \"call_RrbyZClymnngoNLhlkQLLpwM\",\n            \"type\": \"function\",\n
+        \           \"function\": {\n              \"name\": \"parallel_local_search_three\",\n
+        \             \"arguments\": \"{\\\"query\\\": \\\"latest Gemini model release
+        notes\\\"}\"\n            }\n          }\n        ],\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"finish_reason\": \"tool_calls\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 343,\n    \"completion_tokens\":
+        855,\n    \"total_tokens\": 1198,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 768,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 19 Feb 2026 17:25:23 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '6669'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      set-cookie:
+      - SET-COOKIE-XXX
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Parallel Tool Agent. You
+      follow tool instructions precisely.\nYour personal goal is: Use both tools exactly
+      as instructed"},{"role":"user","content":"\nCurrent Task: This is a tool-calling
+      compliance test. In your next assistant turn, emit exactly 3 tool calls in the
+      same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_D2ojRWqkng6krQ51vWQEU8wR","type":"function","function":{"name":"parallel_local_search_one","arguments":"{\"query\":
+      \"latest OpenAI model release notes\"}"}},{"id":"call_v1tpTKw1sYcI75SWG1LCkAC3","type":"function","function":{"name":"parallel_local_search_two","arguments":"{\"query\":
+      \"latest Anthropic model release notes\"}"}},{"id":"call_RrbyZClymnngoNLhlkQLLpwM","type":"function","function":{"name":"parallel_local_search_three","arguments":"{\"query\":
+      \"latest Gemini model release notes\"}"}}]},{"role":"tool","tool_call_id":"call_D2ojRWqkng6krQ51vWQEU8wR","name":"parallel_local_search_one","content":"[one]
+      latest OpenAI model release notes"},{"role":"tool","tool_call_id":"call_v1tpTKw1sYcI75SWG1LCkAC3","name":"parallel_local_search_two","content":"[two]
+      latest Anthropic model release notes"},{"role":"tool","tool_call_id":"call_RrbyZClymnngoNLhlkQLLpwM","name":"parallel_local_search_three","content":"[three]
+      latest Gemini model release notes"}],"model":"gpt-5-nano","temperature":1,"tool_choice":"auto","tools":[{"type":"function","function":{"name":"parallel_local_search_one","description":"Local
+      search tool #1 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"parallel_local_search_two","description":"Local
+      search tool #2 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"parallel_local_search_three","description":"Local
+      search tool #3 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '2771'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-DB24DjyYsIHiQJ7hHXob8tQFfeXBs\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1771521925,\n  \"model\": \"gpt-5-nano-2025-08-07\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"The three latest release-note references
+        retrieved encompass OpenAI, Anthropic, and Gemini, indicating that all three
+        major model families are actively updating their offerings. These notes typically
+        cover improvements to capabilities, safety measures, performance enhancements,
+        and any new APIs or features, suggesting a trend of ongoing refinement across
+        providers. If you\u2019d like, I can pull the full release notes or extract
+        and compare the key changes across the three sources.\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 467,\n    \"completion_tokens\":
+        1437,\n    \"total_tokens\": 1904,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 1344,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 19 Feb 2026 17:25:35 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '10369'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestOpenAINativeToolCalling.test_openai_parallel_native_tool_calling_tool_hook_parity_crew.yaml

@@ -0,0 +1,339 @@
+interactions:
+- request:
+    body: '{"trace_id": "e456cc10-ce7b-4e68-a2cc-ddb806a2e7b9", "execution_type":
+      "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null,
+      "crew_name": "crew", "flow_name": null, "crewai_version": "1.9.3", "privacy_level":
+      "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count":
+      0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2026-02-19T17:24:41.723158+00:00"},
+      "ephemeral_trace_id": "e456cc10-ce7b-4e68-a2cc-ddb806a2e7b9"}'
+    headers:
+      Accept:
+      - '*/*'
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '488'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - X-USER-AGENT-XXX
+      X-Crewai-Organization-Id:
+      - 3433f0ee-8a94-4aa4-822b-2ac71aa38b18
+      X-Crewai-Version:
+      - 1.9.3
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+    method: POST
+    uri: https://app.crewai.com/crewai_plus/api/v1/tracing/ephemeral/batches
+  response:
+    body:
+      string: '{"id":"a78f2aca-0525-47c7-8f37-b3fca0ad6672","ephemeral_trace_id":"e456cc10-ce7b-4e68-a2cc-ddb806a2e7b9","execution_type":"crew","crew_name":"crew","flow_name":null,"status":"running","duration_ms":null,"crewai_version":"1.9.3","total_events":0,"execution_context":{"crew_fingerprint":null,"crew_name":"crew","flow_name":null,"crewai_version":"1.9.3","privacy_level":"standard"},"created_at":"2026-02-19T17:24:41.989Z","updated_at":"2026-02-19T17:24:41.989Z","access_code":"TRACE-bd80d6be74","user_identifier":null}'
+    headers:
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '515'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Thu, 19 Feb 2026 17:24:41 GMT
+      cache-control:
+      - no-store
+      content-security-policy:
+      - CSP-FILTERED
+      etag:
+      - ETAG-XXX
+      expires:
+      - '0'
+      permissions-policy:
+      - PERMISSIONS-POLICY-XXX
+      pragma:
+      - no-cache
+      referrer-policy:
+      - REFERRER-POLICY-XXX
+      strict-transport-security:
+      - STS-XXX
+      vary:
+      - Accept
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+      x-frame-options:
+      - X-FRAME-OPTIONS-XXX
+      x-permitted-cross-domain-policies:
+      - X-PERMITTED-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+      x-runtime:
+      - X-RUNTIME-XXX
+      x-xss-protection:
+      - X-XSS-PROTECTION-XXX
+    status:
+      code: 201
+      message: Created
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Parallel Tool Agent. You
+      follow tool instructions precisely.\nYour personal goal is: Use both tools exactly
+      as instructed"},{"role":"user","content":"\nCurrent Task: This is a tool-calling
+      compliance test. In your next assistant turn, emit exactly 3 tool calls in the
+      same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary.\n\nThis is the expected criteria for your final answer: A
+      one sentence summary of both tool outputs\nyou MUST return the actual complete
+      content as the final answer, not a summary."}],"model":"gpt-5-nano","temperature":1,"tool_choice":"auto","tools":[{"type":"function","function":{"name":"parallel_local_search_one","description":"Local
+      search tool #1 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"parallel_local_search_two","description":"Local
+      search tool #2 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"parallel_local_search_three","description":"Local
+      search tool #3 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1929'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-DB23W8RBF6zlxweiHYGb6maVfyctt\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1771521882,\n  \"model\": \"gpt-5-nano-2025-08-07\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+        \           \"id\": \"call_sge1FXUkpmPEDe8nTOgn0tQG\",\n            \"type\":
+        \"function\",\n            \"function\": {\n              \"name\": \"parallel_local_search_one\",\n
+        \             \"arguments\": \"{\\\"query\\\": \\\"latest OpenAI model release
+        notes\\\"}\"\n            }\n          },\n          {\n            \"id\":
+        \"call_z5jRPH4DQ7Wp3HdDUlZe8gGh\",\n            \"type\": \"function\",\n
+        \           \"function\": {\n              \"name\": \"parallel_local_search_two\",\n
+        \             \"arguments\": \"{\\\"query\\\": \\\"latest Anthropic model
+        release notes\\\"}\"\n            }\n          },\n          {\n            \"id\":
+        \"call_DNlgqnadODDsyQkSuLcXZCX2\",\n            \"type\": \"function\",\n
+        \           \"function\": {\n              \"name\": \"parallel_local_search_three\",\n
+        \             \"arguments\": \"{\\\"query\\\": \\\"latest Gemini model release
+        notes\\\"}\"\n            }\n          }\n        ],\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"finish_reason\": \"tool_calls\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 378,\n    \"completion_tokens\":
+        2456,\n    \"total_tokens\": 2834,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 2368,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 19 Feb 2026 17:25:02 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '19582'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      set-cookie:
+      - SET-COOKIE-XXX
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Parallel Tool Agent. You
+      follow tool instructions precisely.\nYour personal goal is: Use both tools exactly
+      as instructed"},{"role":"user","content":"\nCurrent Task: This is a tool-calling
+      compliance test. In your next assistant turn, emit exactly 3 tool calls in the
+      same response (parallel tool calls), in this order: 1) parallel_local_search_one(query=''latest
+      OpenAI model release notes''), 2) parallel_local_search_two(query=''latest Anthropic
+      model release notes''), 3) parallel_local_search_three(query=''latest Gemini
+      model release notes''). Do not call any other tools and do not answer before
+      those 3 tool calls are emitted. After the tool results return, provide a one
+      paragraph summary.\n\nThis is the expected criteria for your final answer: A
+      one sentence summary of both tool outputs\nyou MUST return the actual complete
+      content as the final answer, not a summary."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_sge1FXUkpmPEDe8nTOgn0tQG","type":"function","function":{"name":"parallel_local_search_one","arguments":"{\"query\":
+      \"latest OpenAI model release notes\"}"}},{"id":"call_z5jRPH4DQ7Wp3HdDUlZe8gGh","type":"function","function":{"name":"parallel_local_search_two","arguments":"{\"query\":
+      \"latest Anthropic model release notes\"}"}},{"id":"call_DNlgqnadODDsyQkSuLcXZCX2","type":"function","function":{"name":"parallel_local_search_three","arguments":"{\"query\":
+      \"latest Gemini model release notes\"}"}}]},{"role":"tool","tool_call_id":"call_sge1FXUkpmPEDe8nTOgn0tQG","name":"parallel_local_search_one","content":"[one]
+      latest OpenAI model release notes"},{"role":"tool","tool_call_id":"call_z5jRPH4DQ7Wp3HdDUlZe8gGh","name":"parallel_local_search_two","content":"[two]
+      latest Anthropic model release notes"},{"role":"tool","tool_call_id":"call_DNlgqnadODDsyQkSuLcXZCX2","name":"parallel_local_search_three","content":"[three]
+      latest Gemini model release notes"},{"role":"user","content":"Analyze the tool
+      result. If requirements are met, provide the Final Answer. Otherwise, call the
+      next tool. Deliver only the answer without meta-commentary."}],"model":"gpt-5-nano","temperature":1,"tool_choice":"auto","tools":[{"type":"function","function":{"name":"parallel_local_search_one","description":"Local
+      search tool #1 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"parallel_local_search_two","description":"Local
+      search tool #2 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"parallel_local_search_three","description":"Local
+      search tool #3 for concurrency testing.","strict":true,"parameters":{"properties":{"query":{"description":"Search
+      query","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '3136'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-DB23sY0Ahpd1yAgLZ882KkA50Zljx\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1771521904,\n  \"model\": \"gpt-5-nano-2025-08-07\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Results returned three items: the latest
+        OpenAI model release notes, the latest Anthropic model release notes, and
+        the latest Gemini model release notes.\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\":
+        {\n    \"prompt_tokens\": 537,\n    \"completion_tokens\": 1383,\n    \"total_tokens\":
+        1920,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\":
+        0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
+        1344,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n
+        \     \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 19 Feb 2026 17:25:16 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '12339'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/test_agent_execute_task_basic.yaml

@@ -1,6 +1,10 @@
 interactions:
 - request:
-    body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour personal goal is: test goal\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Calculate 2 + 2\n\nThis is the expected criteria for your final answer: The result of the calculation\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4o-mini"}'
+    body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour
+      personal goal is: test goal"},{"role":"user","content":"\nCurrent Task: Calculate
+      2 + 2\n\nThis is the expected criteria for your final answer: The result of
+      the calculation\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -13,7 +17,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '797'
+      - '396'
       content-type:
       - application/json
       host:
@@ -35,13 +39,23 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.12.10
+      - 3.13.3
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-CjDsYJQa2tIYBbNloukSWecpsTvdK\",\n  \"object\": \"chat.completion\",\n  \"created\": 1764894146,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal Answer: The result of the calculation 2 + 2 is 4.\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 161,\n    \"completion_tokens\": 25,\n    \"total_tokens\": 186,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\": \"fp_11f3029f6b\"\
-        \n}\n"
+      string: "{\n  \"id\": \"chatcmpl-D5DTjYe6n92Rjo4Ox6NiZpAAdBLF0\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770135823,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"The result of the calculation 2 + 2
+        is 4.\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
+        \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+        \ \"usage\": {\n    \"prompt_tokens\": 75,\n    \"completion_tokens\": 14,\n
+        \   \"total_tokens\": 89,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
     headers:
       CF-RAY:
       - CF-RAY-XXX
@@ -50,7 +64,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 05 Dec 2025 00:22:27 GMT
+      - Tue, 03 Feb 2026 16:23:43 GMT
       Server:
       - cloudflare
       Set-Cookie:
@@ -70,13 +84,11 @@ interactions:
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '516'
+      - '636'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '529'
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:

lib/crewai/tests/cassettes/agents/test_agent_execute_task_with_context.yaml

@@ -1,6 +1,12 @@
 interactions:
 - request:
-    body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour personal goal is: test goal\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Summarize the given context in one sentence\n\nThis is the expected criteria for your final answer: A one-sentence summary\nyou MUST return the actual complete content as the final answer, not a summary.\n\nThis is the context you''re working with:\nThe quick brown fox jumps over the lazy dog. This sentence contains every letter of the alphabet.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-3.5-turbo"}'
+    body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour
+      personal goal is: test goal"},{"role":"user","content":"\nCurrent Task: Summarize
+      the given context in one sentence\n\nThis is the expected criteria for your
+      final answer: A one-sentence summary\nyou MUST return the actual complete content
+      as the final answer, not a summary.\n\nThis is the context you''re working with:\nThe
+      quick brown fox jumps over the lazy dog. This sentence contains every letter
+      of the alphabet.\n\nProvide your complete response:"}],"model":"gpt-3.5-turbo"}'
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -13,7 +19,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '963'
+      - '562'
       content-type:
       - application/json
       host:
@@ -35,13 +41,23 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.12.10
+      - 3.13.3
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-CjDtsaX0LJ0dzZz02KwKeRGYgazv1\",\n  \"object\": \"chat.completion\",\n  \"created\": 1764894228,\n  \"model\": \"gpt-3.5-turbo-0125\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"I now can give a great answer\\n\\nFinal Answer: The quick brown fox jumps over the lazy dog. This sentence contains every letter of the alphabet.\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 191,\n    \"completion_tokens\": 30,\n    \"total_tokens\": 221,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\"\
-        : \"default\",\n  \"system_fingerprint\": null\n}\n"
+      string: "{\n  \"id\": \"chatcmpl-D5DTn6yIQ7HpIn5j5Bsbag1efzXPa\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770135827,\n  \"model\": \"gpt-3.5-turbo-0125\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"The quick brown fox jumps over the
+        lazy dog. This sentence contains every letter of the alphabet.\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        105,\n    \"completion_tokens\": 19,\n    \"total_tokens\": 124,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": null\n}\n"
     headers:
       CF-RAY:
       - CF-RAY-XXX
@@ -50,7 +66,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 05 Dec 2025 00:23:49 GMT
+      - Tue, 03 Feb 2026 16:23:48 GMT
       Server:
       - cloudflare
       Set-Cookie:
@@ -70,13 +86,11 @@ interactions:
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '506'
+      - '606'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '559'
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:

lib/crewai/tests/cassettes/agents/test_agent_execute_task_with_custom_llm.yaml

@@ -1,6 +1,10 @@
 interactions:
 - request:
-    body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour personal goal is: test goal\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Write a haiku about AI\n\nThis is the expected criteria for your final answer: A haiku (3 lines, 5-7-5 syllable pattern) about AI\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-3.5-turbo","max_tokens":50,"temperature":0.7}'
+    body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour
+      personal goal is: test goal"},{"role":"user","content":"\nCurrent Task: Write
+      a haiku about AI\n\nThis is the expected criteria for your final answer: A haiku
+      (3 lines, 5-7-5 syllable pattern) about AI\nyou MUST return the actual complete
+      content as the final answer, not a summary.\n\nProvide your complete response:"}],"model":"gpt-3.5-turbo","max_tokens":50,"temperature":0.7}'
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -13,7 +17,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '861'
+      - '460'
       content-type:
       - application/json
       host:
@@ -35,13 +39,23 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.12.10
+      - 3.13.3
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-CjDqr2BmEXQ08QzZKslTZJZ5vV9lo\",\n  \"object\": \"chat.completion\",\n  \"created\": 1764894041,\n  \"model\": \"gpt-3.5-turbo-0125\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"I now can give a great answer\\n\\nFinal Answer:  \\nIn circuits they thrive,  \\nArtificial minds awake,  \\nFuture's coded drive.\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 174,\n    \"completion_tokens\": 29,\n    \"total_tokens\": 203,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\"\
-        ,\n  \"system_fingerprint\": null\n}\n"
+      string: "{\n  \"id\": \"chatcmpl-D5DTgAqxaC8RmEvikXK0UDaxmVmf9\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770135820,\n  \"model\": \"gpt-3.5-turbo-0125\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Artificial minds,\\nCode and circuits
+        intertwine,\\nFuture undefined.\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 88,\n    \"completion_tokens\":
+        13,\n    \"total_tokens\": 101,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": null\n}\n"
     headers:
       CF-RAY:
       - CF-RAY-XXX
@@ -50,7 +64,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 05 Dec 2025 00:20:41 GMT
+      - Tue, 03 Feb 2026 16:23:40 GMT
       Server:
       - cloudflare
       Set-Cookie:
@@ -70,13 +84,11 @@ interactions:
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '434'
+      - '277'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '456'
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:

lib/crewai/tests/cassettes/agents/test_agent_execute_task_with_planning.yaml

@@ -0,0 +1,231 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are a strategic planning assistant.
+      Create minimal, effective execution plans. Prefer fewer steps over more."},{"role":"user","content":"Create
+      a focused execution plan for the following task:\n\n## Task\nWhat is 9 + 11?\n\n##
+      Expected Output\nA number\n\n## Available Tools\nNo tools available\n\n## Instructions\nCreate
+      ONLY the essential steps needed to complete this task. Use the MINIMUM number
+      of steps required - do NOT pad your plan with unnecessary steps. Most tasks
+      need only 2-5 steps.\n\nFor each step:\n- State the specific action to take\n-
+      Specify which tool to use (if any)\n\nDo NOT include:\n- Setup or preparation
+      steps that are obvious\n- Verification steps unless critical\n- Documentation
+      or cleanup steps unless explicitly required\n- Generic steps like \"review results\"
+      or \"finalize output\"\n\nAfter your plan, state:\n- \"READY: I am ready to
+      execute the task.\" if the plan is complete\n- \"NOT READY: I need to refine
+      my plan because [reason].\" if you need more thinking"}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
+      or refine a reasoning plan for a task","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"The
+      detailed reasoning plan for the task."},"ready":{"type":"boolean","description":"Whether
+      the agent is ready to execute the task."}},"required":["plan","ready"],"additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1520'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yVACNTzZcghQRwt5kFYQ4HAvbgI\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078252,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"## Execution Plan\\n1. Calculate the
+        sum of 9 and 11.\\n   \\nREADY: I am ready to execute the task.\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        279,\n    \"completion_tokens\": 28,\n    \"total_tokens\": 307,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:24:13 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '951'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Math Assistant. A helpful
+      math tutor\nYour personal goal is: Help solve math problems"},{"role":"user","content":"\nCurrent
+      Task: What is 9 + 11?\n\nPlanning:\n## Execution Plan\n1. Calculate the sum
+      of 9 and 11.\n   \nREADY: I am ready to execute the task.\n\nThis is the expected
+      criteria for your final answer: A number\nyou MUST return the actual complete
+      content as the final answer, not a summary.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '513'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yVBdTCKSdfcJYlIOX9BbzrObgFI\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078253,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"9 + 11 = 20\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        105,\n    \"completion_tokens\": 7,\n    \"total_tokens\": 112,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:24:13 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '477'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/test_agent_execute_task_with_planning_refine.yaml

@@ -0,0 +1,243 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are a strategic planning assistant.
+      Create minimal, effective execution plans. Prefer fewer steps over more."},{"role":"user","content":"Create
+      a focused execution plan for the following task:\n\n## Task\nCalculate the area
+      of a circle with radius 5 (use pi = 3.14)\n\n## Expected Output\nThe area as
+      a number\n\n## Available Tools\nNo tools available\n\n## Instructions\nCreate
+      ONLY the essential steps needed to complete this task. Use the MINIMUM number
+      of steps required - do NOT pad your plan with unnecessary steps. Most tasks
+      need only 2-5 steps.\n\nFor each step:\n- State the specific action to take\n-
+      Specify which tool to use (if any)\n\nDo NOT include:\n- Setup or preparation
+      steps that are obvious\n- Verification steps unless critical\n- Documentation
+      or cleanup steps unless explicitly required\n- Generic steps like \"review results\"
+      or \"finalize output\"\n\nAfter your plan, state:\n- \"READY: I am ready to
+      execute the task.\" if the plan is complete\n- \"NOT READY: I need to refine
+      my plan because [reason].\" if you need more thinking"}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
+      or refine a reasoning plan for a task","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"The
+      detailed reasoning plan for the task."},"ready":{"type":"boolean","description":"Whether
+      the agent is ready to execute the task."}},"required":["plan","ready"],"additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1577'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yVCdA1csIzfoHSQvxkfrA4gDn4z\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078254,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"## Execution Plan\\n1. Multiply the
+        radius (5) by itself (5) to get the square of the radius.\\n2. Multiply the
+        squared radius by pi (3.14) to calculate the area.\\n\\nREADY: I am ready
+        to execute the task.\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 293,\n    \"completion_tokens\":
+        54,\n    \"total_tokens\": 347,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:24:15 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '845'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Math Tutor. An expert
+      tutor\nYour personal goal is: Solve complex math problems step by step"},{"role":"user","content":"\nCurrent
+      Task: Calculate the area of a circle with radius 5 (use pi = 3.14)\n\nPlanning:\n##
+      Execution Plan\n1. Multiply the radius (5) by itself (5) to get the square of
+      the radius.\n2. Multiply the squared radius by pi (3.14) to calculate the area.\n\nREADY:
+      I am ready to execute the task.\n\nThis is the expected criteria for your final
+      answer: The area as a number\nyou MUST return the actual complete content as
+      the final answer, not a summary.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '682'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yVDh2U2xx3qeYHcDQvbetOmVCxb\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078255,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"To calculate the area of a circle with
+        a radius of 5, we will follow the steps outlined in the execution plan.\\n\\n1.
+        **Square the radius**:\\n   \\\\[\\n   5 \\\\times 5 = 25\\n   \\\\]\\n\\n2.
+        **Multiply the squared radius by pi (using \\\\(\\\\pi \\\\approx 3.14\\\\))**:\\n
+        \  \\\\[\\n   \\\\text{Area} = \\\\pi \\\\times (\\\\text{radius})^2 = 3.14
+        \\\\times 25\\n   \\\\]\\n\\n   Now, let's perform the multiplication:\\n
+        \  \\\\[\\n   3.14 \\\\times 25 = 78.5\\n   \\\\]\\n\\nThus, the area of the
+        circle is \\\\( \\\\boxed{78.5} \\\\).\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 147,\n    \"completion_tokens\":
+        155,\n    \"total_tokens\": 302,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:24:18 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '2228'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/test_agent_execute_task_with_tool.yaml

@@ -1,7 +1,11 @@
 interactions:
 - request:
-    body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour personal goal is: test goal\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: dummy_tool\nTool Arguments: {''query'': {''description'': None, ''type'': ''str''}}\nTool Description: Useful for when you need to get a dummy result for a query.\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought: you should always think about what to do\nAction: the action to take, only one name of [dummy_tool], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce all necessary information is gathered, return the following format:\n\n```\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n```"},{"role":"user","content":"\nCurrent
-      Task: Use the dummy tool to get a result for ''test query''\n\nThis is the expected criteria for your final answer: The result from the dummy tool\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-3.5-turbo"}'
+    body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour
+      personal goal is: test goal"},{"role":"user","content":"\nCurrent Task: Use
+      the dummy tool to get a result for ''test query''\n\nThis is the expected criteria
+      for your final answer: The result from the dummy tool\nyou MUST return the actual
+      complete content as the final answer, not a summary."}],"model":"gpt-3.5-turbo","tool_choice":"auto","tools":[{"type":"function","function":{"name":"dummy_tool","description":"Useful
+      for when you need to get a dummy result for a query.","strict":true,"parameters":{"properties":{"query":{"title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}}]}'
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -14,7 +18,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1381'
+      - '712'
       content-type:
       - application/json
       host:
@@ -36,12 +40,26 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.12.10
+      - 3.13.3
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-CjDrE1Z8bFQjjxI2vDPPKgtOTm28p\",\n  \"object\": \"chat.completion\",\n  \"created\": 1764894064,\n  \"model\": \"gpt-3.5-turbo-0125\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"you should always think about what to do\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 289,\n    \"completion_tokens\": 8,\n    \"total_tokens\": 297,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\": null\n}\n"
+      string: "{\n  \"id\": \"chatcmpl-D5DTlUmKYee1DaS5AqnaUCZ6B14xV\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770135825,\n  \"model\": \"gpt-3.5-turbo-0125\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+        \           \"id\": \"call_tBCgelchfQjXXJrrM15MxqGJ\",\n            \"type\":
+        \"function\",\n            \"function\": {\n              \"name\": \"dummy_tool\",\n
+        \             \"arguments\": \"{\\\"query\\\":\\\"test query\\\"}\"\n            }\n
+        \         }\n        ],\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"tool_calls\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 122,\n    \"completion_tokens\":
+        16,\n    \"total_tokens\": 138,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": null\n}\n"
     headers:
       CF-RAY:
       - CF-RAY-XXX
@@ -50,7 +68,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 05 Dec 2025 00:21:05 GMT
+      - Tue, 03 Feb 2026 16:23:46 GMT
       Server:
       - cloudflare
       Set-Cookie:
@@ -70,13 +88,124 @@ interactions:
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '379'
+      - '694'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour
+      personal goal is: test goal"},{"role":"user","content":"\nCurrent Task: Use
+      the dummy tool to get a result for ''test query''\n\nThis is the expected criteria
+      for your final answer: The result from the dummy tool\nyou MUST return the actual
+      complete content as the final answer, not a summary."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_tBCgelchfQjXXJrrM15MxqGJ","type":"function","function":{"name":"dummy_tool","arguments":"{\"query\":\"test
+      query\"}"}}]},{"role":"tool","tool_call_id":"call_tBCgelchfQjXXJrrM15MxqGJ","name":"dummy_tool","content":"Dummy
+      result for: test query"},{"role":"user","content":"Analyze the tool result.
+      If requirements are met, provide the Final Answer. Otherwise, call the next
+      tool. Deliver only the answer without meta-commentary."}],"model":"gpt-3.5-turbo","tool_choice":"auto","tools":[{"type":"function","function":{"name":"dummy_tool","description":"Useful
+      for when you need to get a dummy result for a query.","strict":true,"parameters":{"properties":{"query":{"title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1202'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D5DTmxZJI2Ee7fHNc9dYtQkD7sIY2\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770135826,\n  \"model\": \"gpt-3.5-turbo-0125\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Dummy result for: test query\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        188,\n    \"completion_tokens\": 7,\n    \"total_tokens\": 195,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 16:23:47 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '416'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '399'
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:

lib/crewai/tests/cassettes/agents/test_agent_execute_task_without_planning.yaml

@@ -0,0 +1,110 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Math Assistant. A helpful
+      assistant\nYour personal goal is: Help solve math problems"},{"role":"user","content":"\nCurrent
+      Task: What is 12 * 3?\n\nThis is the expected criteria for your final answer:
+      A number\nyou MUST return the actual complete content as the final answer, not
+      a summary.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '400'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yVCw0CGLFmcVvniplwCCt8avtRb\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078254,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"12 * 3 = 36\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        75,\n    \"completion_tokens\": 7,\n    \"total_tokens\": 82,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:24:14 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '331'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/test_agent_kickoff_multi_step_task_with_planning.yaml

@@ -0,0 +1,243 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are a strategic planning assistant.
+      Create minimal, effective execution plans. Prefer fewer steps over more."},{"role":"user","content":"Create
+      a focused execution plan for the following task:\n\n## Task\nFind the first
+      3 prime numbers, add them together, then multiply by 2.\n\n## Expected Output\nComplete
+      the task successfully\n\n## Available Tools\nNo tools available\n\n## Instructions\nCreate
+      ONLY the essential steps needed to complete this task. Use the MINIMUM number
+      of steps required - do NOT pad your plan with unnecessary steps. Most tasks
+      need only 2-5 steps.\n\nFor each step:\n- State the specific action to take\n-
+      Specify which tool to use (if any)\n\nDo NOT include:\n- Setup or preparation
+      steps that are obvious\n- Verification steps unless critical\n- Documentation
+      or cleanup steps unless explicitly required\n- Generic steps like \"review results\"
+      or \"finalize output\"\n\nAfter your plan, state:\n- \"READY: I am ready to
+      execute the task.\" if the plan is complete\n- \"NOT READY: I need to refine
+      my plan because [reason].\" if you need more thinking"}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
+      or refine a reasoning plan for a task","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"The
+      detailed reasoning plan for the task."},"ready":{"type":"boolean","description":"Whether
+      the agent is ready to execute the task."}},"required":["plan","ready"],"additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1597'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yU0MD5GfSUjRW0R4cBmFJ6Hcjbi\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078180,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"### Execution Plan\\n1. Identify the
+        first 3 prime numbers: 2, 3, and 5.\\n2. Add the prime numbers together: 2
+        + 3 + 5 = 10.\\n3. Multiply the sum by 2: 10 * 2 = 20.\\n\\nREADY: I am ready
+        to execute the task.\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 291,\n    \"completion_tokens\":
+        73,\n    \"total_tokens\": 364,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:23:02 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '1253'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Math Tutor. An expert
+      tutor who explains step by step\nYour personal goal is: Solve multi-step math
+      problems"},{"role":"user","content":"\nCurrent Task: Find the first 3 prime
+      numbers, add them together, then multiply by 2.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '333'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yU2qY6Xqpkz2D5yVAwagQzuPpen\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078182,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"To solve the problem, let\u2019s go
+        through each step methodically.\\n\\n1. **Identify the first three prime numbers**:\\n
+        \  - **Prime numbers** are numbers greater than 1 that have no positive divisors
+        other than 1 and themselves.\\n   - The first three prime numbers are:\\n
+        \    - 2\\n     - 3\\n     - 5\\n\\n2. **Add these prime numbers together**:\\n
+        \  - We add them together:\\n     \\\\[\\n     2 + 3 + 5\\n     \\\\]\\n   -
+        Performing the addition step-by-step:\\n     - First, add 2 and 3:\\n       \\\\[\\n
+        \      2 + 3 = 5\\n       \\\\]\\n     - Then add 5 to this result:\\n       \\\\[\\n
+        \      5 + 5 = 10\\n       \\\\]\\n   - So, the sum of the first three prime
+        numbers is **10**.\\n\\n3. **Multiply the sum by 2**:\\n   - Now we multiply
+        the result by 2:\\n     \\\\[\\n     10 \\\\times 2 = 20\\n     \\\\]\\n  \\nTherefore,
+        the final answer is **20**.\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 62,\n    \"completion_tokens\":
+        236,\n    \"total_tokens\": 298,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:23:06 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '3846'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/test_agent_kickoff_with_planning.yaml

@@ -0,0 +1,238 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are a strategic planning assistant.
+      Create minimal, effective execution plans. Prefer fewer steps over more."},{"role":"user","content":"Create
+      a focused execution plan for the following task:\n\n## Task\nWhat is 15 + 27?\n\n##
+      Expected Output\nComplete the task successfully\n\n## Available Tools\nNo tools
+      available\n\n## Instructions\nCreate ONLY the essential steps needed to complete
+      this task. Use the MINIMUM number of steps required - do NOT pad your plan with
+      unnecessary steps. Most tasks need only 2-5 steps.\n\nFor each step:\n- State
+      the specific action to take\n- Specify which tool to use (if any)\n\nDo NOT
+      include:\n- Setup or preparation steps that are obvious\n- Verification steps
+      unless critical\n- Documentation or cleanup steps unless explicitly required\n-
+      Generic steps like \"review results\" or \"finalize output\"\n\nAfter your plan,
+      state:\n- \"READY: I am ready to execute the task.\" if the plan is complete\n-
+      \"NOT READY: I need to refine my plan because [reason].\" if you need more thinking"}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
+      or refine a reasoning plan for a task","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"The
+      detailed reasoning plan for the task."},"ready":{"type":"boolean","description":"Whether
+      the agent is ready to execute the task."}},"required":["plan","ready"],"additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1543'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yTrm3GkzDX47DIcce9uA3iF8kFE\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078171,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"## Execution Plan\\n\\n1. Calculate
+        the sum of 15 and 27.\\n\\nREADY: I am ready to execute the task.\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        281,\n    \"completion_tokens\": 27,\n    \"total_tokens\": 308,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:22:51 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '691'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Math Assistant. A helpful
+      math tutor\nYour personal goal is: Help solve math problems step by step"},{"role":"user","content":"\nCurrent
+      Task: What is 15 + 27?\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '269'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yTrUOvExA9fTFDwYxvG4xEgRP6L\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078171,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"To solve the problem \\\\( 15 + 27
+        \\\\), we can follow these steps:\\n\\n1. **Align the numbers**: Write them
+        one on top of the other, aligned by their rightmost digits:\\n\\n   ```\\n
+        \     15\\n   + 27\\n   ```\\n\\n2. **Add the units place**: Start from the
+        rightmost digits (units place):\\n   - \\\\( 5 + 7 = 12 \\\\)\\n   - Write
+        down 2 and carry over 1.\\n\\n3. **Add the tens place**: Now, move to the
+        next column (tens place):\\n   - \\\\( 1 + 2 + 1 \\\\) (the 1 is from the
+        carry) \\\\( = 4 \\\\)\\n\\n4. **Combine the results**: Now, combine the results
+        from the tens and units places:\\n   - The result in the tens place is 4 and
+        in the units place is 2, giving us \\\\( 42 \\\\).\\n\\nTherefore, \\\\( 15
+        + 27 = 42 \\\\).\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 50,\n    \"completion_tokens\":
+        209,\n    \"total_tokens\": 259,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:22:55 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '3263'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/test_agent_kickoff_with_planning_disabled.yaml

@@ -0,0 +1,110 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Math Assistant. A helpful
+      assistant\nYour personal goal is: Help solve math problems"},{"role":"user","content":"\nCurrent
+      Task: What is 100 / 4?\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '255'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yU6mFapBLuCx4fJtYBup52dwwrs\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078186,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"To solve the problem 100 divided by
+        4, you can perform the division as follows:\\n\\n100 \xF7 4 = 25\\n\\nSo,
+        the answer is 25.\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 46,\n    \"completion_tokens\":
+        36,\n    \"total_tokens\": 82,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:23:07 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '1098'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/test_agent_kickoff_without_planning.yaml

@@ -0,0 +1,108 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Math Assistant. A helpful
+      assistant\nYour personal goal is: Help solve math problems"},{"role":"user","content":"\nCurrent
+      Task: What is 8 * 7?\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '253'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D4yTqLFhGtfq2CyS2aPPhiZL4GjtQ\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770078170,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"8 * 7 equals 56.\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        46,\n    \"completion_tokens\": 8,\n    \"total_tokens\": 54,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 00:22:50 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '443'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/utilities/TestAzureStructuredPlanning.test_azure_research_workflow_generates_steps.yaml

@@ -0,0 +1,548 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are a strategic planning
+      assistant. Create minimal, effective execution plans. Prefer fewer steps over
+      more."}, {"role": "user", "content": "Create a focused execution plan for the
+      following task:\n\n## Task\nResearch the current state of the AI agent market:\n1.
+      Search for recent information about AI agents and their market trends\n2. Read
+      detailed content from a relevant industry source\n3. Generate a brief report
+      summarizing the key findings\n\nUse the available tools for each step.\n\n##
+      Expected Output\nComplete the task successfully\n\n## Available Tools\nweb_search,
+      read_website, generate_report\n\n## Instructions\nCreate ONLY the essential
+      steps needed to complete this task. Use the MINIMUM number of steps required
+      - do NOT pad your plan with unnecessary steps. Most tasks need only 2-5 steps.\n\nFor
+      each step:\n- State the specific action to take\n- Specify which tool to use
+      (if any)\n- Note dependencies on previous steps if this step requires their
+      output\n- If a step involves multiple items (e.g., research 3 competitors),
+      note this explicitly\n\nDo NOT include:\n- Setup or preparation steps that are
+      obvious\n- Verification steps unless critical\n- Documentation or cleanup steps
+      unless explicitly required\n- Generic steps like \"review results\" or \"finalize
+      output\"\n\nAfter your plan, state:\n- \"READY: I am ready to execute the task.\"
+      if the plan is complete\n- \"NOT READY: I need to refine my plan because [reason].\"
+      if you need more thinking"}], "stream": false, "stop": ["\nObservation:"], "tool_choice":
+      "auto", "tools": [{"function": {"name": "create_reasoning_plan", "description":
+      "Create or refine a reasoning plan for a task with structured steps", "parameters":
+      {"type": "object", "properties": {"plan": {"type": "string", "description":
+      "A brief summary of the overall plan."}, "steps": {"type": "array", "description":
+      "List of discrete steps to execute the plan", "items": {"type": "object", "properties":
+      {"step_number": {"type": "integer", "description": "Step number (1-based)"},
+      "description": {"type": "string", "description": "What to do in this step"},
+      "tool_to_use": {"type": ["string", "null"], "description": "Tool to use for
+      this step, or null if no tool needed"}, "depends_on": {"type": "array", "items":
+      {"type": "integer"}, "description": "Step numbers this step depends on (empty
+      array if none)"}}, "required": ["step_number", "description", "tool_to_use",
+      "depends_on"], "additionalProperties": false}}, "ready": {"type": "boolean",
+      "description": "Whether the agent is ready to execute the task."}}, "required":
+      ["plan", "steps", "ready"], "additionalProperties": false}}, "type": "function"}]}'
+    headers:
+      Accept:
+      - application/json
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '2711'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      api-key:
+      - X-API-KEY-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+    method: POST
+    uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2024-12-01-preview
+  response:
+    body:
+      string: '{"choices":[{"content_filter_results":{},"finish_reason":"tool_calls","index":0,"logprobs":null,"message":{"annotations":[],"content":null,"refusal":null,"role":"assistant","tool_calls":[{"function":{"arguments":"{\"plan\":\"Research
+        the current state of the AI agent market and summarize the key findings.\",\"steps\":[{\"step_number\":1,\"description\":\"Search
+        for recent information about AI agents and their market trends using web_search.\",\"tool_to_use\":\"web_search\",\"depends_on\":[]},{\"step_number\":2,\"description\":\"Read
+        detailed content from a relevant industry source using read_website, gathering
+        insights on trends and competitive analysis.\",\"tool_to_use\":\"read_website\",\"depends_on\":[1]},{\"step_number\":3,\"description\":\"Using
+        the knowledge from steps 1 and 2, generate a brief report summarizing the
+        AI agent market findings.\",\"tool_to_use\":\"generate_report\",\"depends_on\":[1,2]}],\"ready\":true}","name":"create_reasoning_plan"},"id":"call_TPmou69xLfxPqApRnPwI6zYV","type":"function"}]}}],"created":1770145131,"id":"chatcmpl-D5Ftr1QP6lTPXIemws2EtuKaWeSxt","model":"gpt-4o-2024-11-20","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"detected":false,"filtered":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":"fp_b54fe76834","usage":{"completion_tokens":157,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":0,"rejected_prediction_tokens":0},"prompt_tokens":480,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":637}}
+
+        '
+    headers:
+      Content-Length:
+      - '1762'
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 18:58:54 GMT
+      Strict-Transport-Security:
+      - STS-XXX
+      apim-request-id:
+      - APIM-REQUEST-ID-XXX
+      azureml-model-session:
+      - AZUREML-MODEL-SESSION-XXX
+      x-accel-buffering:
+      - 'no'
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+      x-ms-deployment-name:
+      - gpt-4o
+      x-ms-rai-invoked:
+      - 'true'
+      x-ms-region:
+      - X-MS-REGION-XXX
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Research Analyst.
+      An experienced analyst skilled at gathering information and synthesizing findings
+      into actionable insights.\nYour personal goal is: Conduct thorough research
+      and produce insightful reports"}, {"role": "user", "content": "\nCurrent Task:
+      Research the current state of the AI agent market:\n1. Search for recent information
+      about AI agents and their market trends\n2. Read detailed content from a relevant
+      industry source\n3. Generate a brief report summarizing the key findings\n\nUse
+      the available tools for each step."}], "stream": false, "stop": ["\nObservation:"],
+      "tool_choice": "auto", "tools": [{"function": {"name": "web_search", "description":
+      "Search the web for information on a given topic.\n\nArgs:\n    query: The search
+      query to look up.\n\nReturns:\n    Search results as a string.", "parameters":
+      {"properties": {"query": {"title": "Query", "type": "string"}}, "required":
+      ["query"], "type": "object", "additionalProperties": false}}, "type": "function"},
+      {"function": {"name": "read_website", "description": "Read and extract content
+      from a website URL.\n\nArgs:\n    url: The URL of the website to read.\n\nReturns:\n    The
+      extracted content from the website.", "parameters": {"properties": {"url": {"title":
+      "Url", "type": "string"}}, "required": ["url"], "type": "object", "additionalProperties":
+      false}}, "type": "function"}, {"function": {"name": "generate_report", "description":
+      "Generate a structured report based on research findings.\n\nArgs:\n    title:
+      The title of the report.\n    findings: The research findings to include.\n\nReturns:\n    A
+      formatted report string.", "parameters": {"properties": {"title": {"title":
+      "Title", "type": "string"}, "findings": {"title": "Findings", "type": "string"}},
+      "required": ["title", "findings"], "type": "object", "additionalProperties":
+      false}}, "type": "function"}]}'
+    headers:
+      Accept:
+      - application/json
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1912'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      api-key:
+      - X-API-KEY-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+    method: POST
+    uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2024-12-01-preview
+  response:
+    body:
+      string: '{"choices":[{"content_filter_results":{},"finish_reason":"tool_calls","index":0,"logprobs":null,"message":{"annotations":[],"content":null,"refusal":null,"role":"assistant","tool_calls":[{"function":{"arguments":"{\"query\":\"current
+        state of AI agent market 2023\"}","name":"web_search"},"id":"call_6RDgkQSr8S7luEHqqOaI734w","type":"function"}]}}],"created":1770145136,"id":"chatcmpl-D5FtwVvV3KE10L2JIOd7n8Ph1Iu3Q","model":"gpt-4o-2024-11-20","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"detected":false,"filtered":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":"fp_b54fe76834","usage":{"completion_tokens":23,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":0,"rejected_prediction_tokens":0},"prompt_tokens":267,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":290}}
+
+        '
+    headers:
+      Content-Length:
+      - '1079'
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 18:58:55 GMT
+      Strict-Transport-Security:
+      - STS-XXX
+      apim-request-id:
+      - APIM-REQUEST-ID-XXX
+      azureml-model-session:
+      - AZUREML-MODEL-SESSION-XXX
+      x-accel-buffering:
+      - 'no'
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+      x-ms-deployment-name:
+      - gpt-4o
+      x-ms-rai-invoked:
+      - 'true'
+      x-ms-region:
+      - X-MS-REGION-XXX
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Research Analyst.
+      An experienced analyst skilled at gathering information and synthesizing findings
+      into actionable insights.\nYour personal goal is: Conduct thorough research
+      and produce insightful reports"}, {"role": "user", "content": "\nCurrent Task:
+      Research the current state of the AI agent market:\n1. Search for recent information
+      about AI agents and their market trends\n2. Read detailed content from a relevant
+      industry source\n3. Generate a brief report summarizing the key findings\n\nUse
+      the available tools for each step."}, {"role": "assistant", "content": "", "tool_calls":
+      [{"id": "call_6RDgkQSr8S7luEHqqOaI734w", "type": "function", "function": {"name":
+      "web_search", "arguments": "{\"query\":\"current state of AI agent market 2023\"}"}}]},
+      {"role": "tool", "tool_call_id": "call_6RDgkQSr8S7luEHqqOaI734w", "content":
+      "Search results for ''current state of AI agent market 2023'': Found 3 relevant
+      articles about the topic including market analysis, competitor data, and industry
+      trends."}], "stream": false, "stop": ["\nObservation:"], "tool_choice": "auto",
+      "tools": [{"function": {"name": "web_search", "description": "Search the web
+      for information on a given topic.\n\nArgs:\n    query: The search query to look
+      up.\n\nReturns:\n    Search results as a string.", "parameters": {"properties":
+      {"query": {"title": "Query", "type": "string"}}, "required": ["query"], "type":
+      "object", "additionalProperties": false}}, "type": "function"}, {"function":
+      {"name": "read_website", "description": "Read and extract content from a website
+      URL.\n\nArgs:\n    url: The URL of the website to read.\n\nReturns:\n    The
+      extracted content from the website.", "parameters": {"properties": {"url": {"title":
+      "Url", "type": "string"}}, "required": ["url"], "type": "object", "additionalProperties":
+      false}}, "type": "function"}, {"function": {"name": "generate_report", "description":
+      "Generate a structured report based on research findings.\n\nArgs:\n    title:
+      The title of the report.\n    findings: The research findings to include.\n\nReturns:\n    A
+      formatted report string.", "parameters": {"properties": {"title": {"title":
+      "Title", "type": "string"}, "findings": {"title": "Findings", "type": "string"}},
+      "required": ["title", "findings"], "type": "object", "additionalProperties":
+      false}}, "type": "function"}]}'
+    headers:
+      Accept:
+      - application/json
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '2381'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      api-key:
+      - X-API-KEY-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+    method: POST
+    uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2024-12-01-preview
+  response:
+    body:
+      string: '{"choices":[{"content_filter_results":{},"finish_reason":"tool_calls","index":0,"logprobs":null,"message":{"annotations":[],"content":null,"refusal":null,"role":"assistant","tool_calls":[{"function":{"arguments":"{\"url\":
+        \"https://example.com/article1\"}","name":"read_website"},"id":"call_ie6tNHSbW9TWIqoXD9CN3MNZ","type":"function"},{"function":{"arguments":"{\"url\":
+        \"https://example.com/article2\"}","name":"read_website"},"id":"call_qxn4V4mMMpOnYSAwVuwarFkB","type":"function"},{"function":{"arguments":"{\"url\":
+        \"https://example.com/article3\"}","name":"read_website"},"id":"call_7ElzUIHHJvuciFWj6eIF5RhF","type":"function"}]}}],"created":1770145137,"id":"chatcmpl-D5Ftxnr2VyEYZd6zSpTJavdxSoE18","model":"gpt-4o-2024-11-20","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"detected":false,"filtered":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":"fp_b54fe76834","usage":{"completion_tokens":77,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":0,"rejected_prediction_tokens":0},"prompt_tokens":330,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":407}}
+
+        '
+    headers:
+      Content-Length:
+      - '1371'
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 18:58:57 GMT
+      Strict-Transport-Security:
+      - STS-XXX
+      apim-request-id:
+      - APIM-REQUEST-ID-XXX
+      azureml-model-session:
+      - AZUREML-MODEL-SESSION-XXX
+      x-accel-buffering:
+      - 'no'
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+      x-ms-deployment-name:
+      - gpt-4o
+      x-ms-rai-invoked:
+      - 'true'
+      x-ms-region:
+      - X-MS-REGION-XXX
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Research Analyst.
+      An experienced analyst skilled at gathering information and synthesizing findings
+      into actionable insights.\nYour personal goal is: Conduct thorough research
+      and produce insightful reports"}, {"role": "user", "content": "\nCurrent Task:
+      Research the current state of the AI agent market:\n1. Search for recent information
+      about AI agents and their market trends\n2. Read detailed content from a relevant
+      industry source\n3. Generate a brief report summarizing the key findings\n\nUse
+      the available tools for each step."}, {"role": "assistant", "content": "", "tool_calls":
+      [{"id": "call_6RDgkQSr8S7luEHqqOaI734w", "type": "function", "function": {"name":
+      "web_search", "arguments": "{\"query\":\"current state of AI agent market 2023\"}"}}]},
+      {"role": "tool", "tool_call_id": "call_6RDgkQSr8S7luEHqqOaI734w", "content":
+      "Search results for ''current state of AI agent market 2023'': Found 3 relevant
+      articles about the topic including market analysis, competitor data, and industry
+      trends."}, {"role": "assistant", "content": "", "tool_calls": [{"id": "call_ie6tNHSbW9TWIqoXD9CN3MNZ",
+      "type": "function", "function": {"name": "read_website", "arguments": "{\"url\":
+      \"https://example.com/article1\"}"}}, {"id": "call_qxn4V4mMMpOnYSAwVuwarFkB",
+      "type": "function", "function": {"name": "read_website", "arguments": "{\"url\":
+      \"https://example.com/article2\"}"}}, {"id": "call_7ElzUIHHJvuciFWj6eIF5RhF",
+      "type": "function", "function": {"name": "read_website", "arguments": "{\"url\":
+      \"https://example.com/article3\"}"}}]}, {"role": "tool", "tool_call_id": "call_ie6tNHSbW9TWIqoXD9CN3MNZ",
+      "content": "Content from https://example.com/article1: This article discusses
+      key insights about the topic including market size ($50B), growth rate (15%
+      YoY), and major players in the industry."}, {"role": "tool", "tool_call_id":
+      "call_qxn4V4mMMpOnYSAwVuwarFkB", "content": "Content from https://example.com/article2:
+      This article discusses key insights about the topic including market size ($50B),
+      growth rate (15% YoY), and major players in the industry."}, {"role": "tool",
+      "tool_call_id": "call_7ElzUIHHJvuciFWj6eIF5RhF", "content": "Content from https://example.com/article3:
+      This article discusses key insights about the topic including market size ($50B),
+      growth rate (15% YoY), and major players in the industry."}], "stream": false,
+      "stop": ["\nObservation:"], "tool_choice": "auto", "tools": [{"function": {"name":
+      "web_search", "description": "Search the web for information on a given topic.\n\nArgs:\n    query:
+      The search query to look up.\n\nReturns:\n    Search results as a string.",
+      "parameters": {"properties": {"query": {"title": "Query", "type": "string"}},
+      "required": ["query"], "type": "object", "additionalProperties": false}}, "type":
+      "function"}, {"function": {"name": "read_website", "description": "Read and
+      extract content from a website URL.\n\nArgs:\n    url: The URL of the website
+      to read.\n\nReturns:\n    The extracted content from the website.", "parameters":
+      {"properties": {"url": {"title": "Url", "type": "string"}}, "required": ["url"],
+      "type": "object", "additionalProperties": false}}, "type": "function"}, {"function":
+      {"name": "generate_report", "description": "Generate a structured report based
+      on research findings.\n\nArgs:\n    title: The title of the report.\n    findings:
+      The research findings to include.\n\nReturns:\n    A formatted report string.",
+      "parameters": {"properties": {"title": {"title": "Title", "type": "string"},
+      "findings": {"title": "Findings", "type": "string"}}, "required": ["title",
+      "findings"], "type": "object", "additionalProperties": false}}, "type": "function"}]}'
+    headers:
+      Accept:
+      - application/json
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3704'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      api-key:
+      - X-API-KEY-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+    method: POST
+    uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2024-12-01-preview
+  response:
+    body:
+      string: '{"choices":[{"content_filter_results":{},"finish_reason":"tool_calls","index":0,"logprobs":null,"message":{"annotations":[],"content":null,"refusal":null,"role":"assistant","tool_calls":[{"function":{"arguments":"{\"title\":\"Current
+        State of the AI Agent Market\",\"findings\":\"The AI agent market in 2023
+        is valued at $50 billion, with a growth rate of 15% YoY. Major players in
+        the market have been identified as contributing to the expansion of industry
+        capabilities. Trends point to increasing adoption across industries such as
+        healthcare and finance, where automation and intelligence are becoming central
+        to operations. Emerging competitive forces are influencing pricing and technological
+        advancements in AI agents. Existing and new entrants focus on innovation to
+        differentiate their offerings and capture market share.\"}","name":"generate_report"},"id":"call_7eE0bJbpvO6YYQNs87iTifQ3","type":"function"}]}}],"created":1770145138,"id":"chatcmpl-D5Ftys4PE1B1dkTuv6EPOQyqk0xuv","model":"gpt-4o-2024-11-20","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"detected":false,"filtered":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":"fp_b54fe76834","usage":{"completion_tokens":120,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":0,"rejected_prediction_tokens":0},"prompt_tokens":537,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":657}}
+
+        '
+    headers:
+      Content-Length:
+      - '1652'
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 18:58:59 GMT
+      Strict-Transport-Security:
+      - STS-XXX
+      apim-request-id:
+      - APIM-REQUEST-ID-XXX
+      azureml-model-session:
+      - AZUREML-MODEL-SESSION-XXX
+      x-accel-buffering:
+      - 'no'
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+      x-ms-deployment-name:
+      - gpt-4o
+      x-ms-rai-invoked:
+      - 'true'
+      x-ms-region:
+      - X-MS-REGION-XXX
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Research Analyst.
+      An experienced analyst skilled at gathering information and synthesizing findings
+      into actionable insights.\nYour personal goal is: Conduct thorough research
+      and produce insightful reports"}, {"role": "user", "content": "\nCurrent Task:
+      Research the current state of the AI agent market:\n1. Search for recent information
+      about AI agents and their market trends\n2. Read detailed content from a relevant
+      industry source\n3. Generate a brief report summarizing the key findings\n\nUse
+      the available tools for each step."}, {"role": "assistant", "content": "", "tool_calls":
+      [{"id": "call_6RDgkQSr8S7luEHqqOaI734w", "type": "function", "function": {"name":
+      "web_search", "arguments": "{\"query\":\"current state of AI agent market 2023\"}"}}]},
+      {"role": "tool", "tool_call_id": "call_6RDgkQSr8S7luEHqqOaI734w", "content":
+      "Search results for ''current state of AI agent market 2023'': Found 3 relevant
+      articles about the topic including market analysis, competitor data, and industry
+      trends."}, {"role": "assistant", "content": "", "tool_calls": [{"id": "call_ie6tNHSbW9TWIqoXD9CN3MNZ",
+      "type": "function", "function": {"name": "read_website", "arguments": "{\"url\":
+      \"https://example.com/article1\"}"}}, {"id": "call_qxn4V4mMMpOnYSAwVuwarFkB",
+      "type": "function", "function": {"name": "read_website", "arguments": "{\"url\":
+      \"https://example.com/article2\"}"}}, {"id": "call_7ElzUIHHJvuciFWj6eIF5RhF",
+      "type": "function", "function": {"name": "read_website", "arguments": "{\"url\":
+      \"https://example.com/article3\"}"}}]}, {"role": "tool", "tool_call_id": "call_ie6tNHSbW9TWIqoXD9CN3MNZ",
+      "content": "Content from https://example.com/article1: This article discusses
+      key insights about the topic including market size ($50B), growth rate (15%
+      YoY), and major players in the industry."}, {"role": "tool", "tool_call_id":
+      "call_qxn4V4mMMpOnYSAwVuwarFkB", "content": "Content from https://example.com/article2:
+      This article discusses key insights about the topic including market size ($50B),
+      growth rate (15% YoY), and major players in the industry."}, {"role": "tool",
+      "tool_call_id": "call_7ElzUIHHJvuciFWj6eIF5RhF", "content": "Content from https://example.com/article3:
+      This article discusses key insights about the topic including market size ($50B),
+      growth rate (15% YoY), and major players in the industry."}, {"role": "assistant",
+      "content": "", "tool_calls": [{"id": "call_7eE0bJbpvO6YYQNs87iTifQ3", "type":
+      "function", "function": {"name": "generate_report", "arguments": "{\"title\":\"Current
+      State of the AI Agent Market\",\"findings\":\"The AI agent market in 2023 is
+      valued at $50 billion, with a growth rate of 15% YoY. Major players in the market
+      have been identified as contributing to the expansion of industry capabilities.
+      Trends point to increasing adoption across industries such as healthcare and
+      finance, where automation and intelligence are becoming central to operations.
+      Emerging competitive forces are influencing pricing and technological advancements
+      in AI agents. Existing and new entrants focus on innovation to differentiate
+      their offerings and capture market share.\"}"}}]}, {"role": "tool", "tool_call_id":
+      "call_7eE0bJbpvO6YYQNs87iTifQ3", "content": "# Current State of the AI Agent
+      Market\n\n## Executive Summary\nThe AI agent market in 2023 is valued at $50
+      billion, with a growth rate of 15% YoY. Major players in the market have been
+      identified as contributing to the expansion of industry capabilities. Trends
+      point to increasing adoption across industries such as healthcare and finance,
+      where automation and intelligence are becoming central to operations. Emerging
+      competitive forces are influencing pricing and technological advancements in
+      AI agents. Existing and new entrants focus on innovation to differentiate their
+      offerings and capture market share.\n\n## Conclusion\nBased on the analysis,
+      the market shows strong growth potential."}], "stream": false, "stop": ["\nObservation:"],
+      "tool_choice": "auto", "tools": [{"function": {"name": "web_search", "description":
+      "Search the web for information on a given topic.\n\nArgs:\n    query: The search
+      query to look up.\n\nReturns:\n    Search results as a string.", "parameters":
+      {"properties": {"query": {"title": "Query", "type": "string"}}, "required":
+      ["query"], "type": "object", "additionalProperties": false}}, "type": "function"},
+      {"function": {"name": "read_website", "description": "Read and extract content
+      from a website URL.\n\nArgs:\n    url: The URL of the website to read.\n\nReturns:\n    The
+      extracted content from the website.", "parameters": {"properties": {"url": {"title":
+      "Url", "type": "string"}}, "required": ["url"], "type": "object", "additionalProperties":
+      false}}, "type": "function"}, {"function": {"name": "generate_report", "description":
+      "Generate a structured report based on research findings.\n\nArgs:\n    title:
+      The title of the report.\n    findings: The research findings to include.\n\nReturns:\n    A
+      formatted report string.", "parameters": {"properties": {"title": {"title":
+      "Title", "type": "string"}, "findings": {"title": "Findings", "type": "string"}},
+      "required": ["title", "findings"], "type": "object", "additionalProperties":
+      false}}, "type": "function"}]}'
+    headers:
+      Accept:
+      - application/json
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '5276'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      api-key:
+      - X-API-KEY-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+    method: POST
+    uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2024-12-01-preview
+  response:
+    body:
+      string: '{"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"protected_material_code":{"detected":false,"filtered":false},"protected_material_text":{"detected":false,"filtered":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"finish_reason":"stop","index":0,"logprobs":null,"message":{"annotations":[],"content":"The
+        report detailing the current state of the AI agent market has been generated
+        successfully. It highlights the market''s $50 billion valuation in 2023, with
+        a consistent annual growth rate of 15%. Key findings identify the role of
+        major players, impactful trends like sector adoption (healthcare and finance),
+        and the competitive dynamic driving innovation and technological advancements.","refusal":null,"role":"assistant"}}],"created":1770145141,"id":"chatcmpl-D5Fu18JFkDPGsKf10eiS2e2uI04MU","model":"gpt-4o-2024-11-20","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"detected":false,"filtered":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":"fp_b54fe76834","usage":{"completion_tokens":72,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":0,"rejected_prediction_tokens":0},"prompt_tokens":787,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":859}}
+
+        '
+    headers:
+      Content-Length:
+      - '1597'
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 18:59:01 GMT
+      Strict-Transport-Security:
+      - STS-XXX
+      apim-request-id:
+      - APIM-REQUEST-ID-XXX
+      azureml-model-session:
+      - AZUREML-MODEL-SESSION-XXX
+      x-accel-buffering:
+      - 'no'
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+      x-ms-deployment-name:
+      - gpt-4o
+      x-ms-rai-invoked:
+      - 'true'
+      x-ms-region:
+      - X-MS-REGION-XXX
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/utilities/TestGeminiStructuredPlanning.test_gemini_research_workflow_generates_steps.yaml

@@ -0,0 +1,613 @@
+interactions:
+- request:
+    body: '{"contents": [{"parts": [{"text": "Create a focused execution plan for
+      the following task:\n\n## Task\nResearch the current state of the AI agent market:\n1.
+      Search for recent information about AI agents and their market trends\n2. Read
+      detailed content from a relevant industry source\n3. Generate a brief report
+      summarizing the key findings\n\nUse the available tools for each step.\n\n##
+      Expected Output\nComplete the task successfully\n\n## Available Tools\nweb_search,
+      read_website, generate_report\n\n## Instructions\nCreate ONLY the essential
+      steps needed to complete this task. Use the MINIMUM number of steps required
+      - do NOT pad your plan with unnecessary steps. Most tasks need only 2-5 steps.\n\nFor
+      each step:\n- State the specific action to take\n- Specify which tool to use
+      (if any)\n- Note dependencies on previous steps if this step requires their
+      output\n- If a step involves multiple items (e.g., research 3 competitors),
+      note this explicitly\n\nDo NOT include:\n- Setup or preparation steps that are
+      obvious\n- Verification steps unless critical\n- Documentation or cleanup steps
+      unless explicitly required\n- Generic steps like \"review results\" or \"finalize
+      output\"\n\nAfter your plan, state:\n- \"READY: I am ready to execute the task.\"
+      if the plan is complete\n- \"NOT READY: I need to refine my plan because [reason].\"
+      if you need more thinking"}], "role": "user"}], "systemInstruction": {"parts":
+      [{"text": "You are a strategic planning assistant. Create minimal, effective
+      execution plans. Prefer fewer steps over more."}], "role": "user"}, "tools":
+      [{"functionDeclarations": [{"description": "Create or refine a reasoning plan
+      for a task with structured steps", "name": "create_reasoning_plan", "parameters_json_schema":
+      {"type": "object", "properties": {"plan": {"type": "string", "description":
+      "A brief summary of the overall plan."}, "steps": {"type": "array", "description":
+      "List of discrete steps to execute the plan", "items": {"type": "object", "properties":
+      {"step_number": {"type": "integer", "description": "Step number (1-based)"},
+      "description": {"type": "string", "description": "What to do in this step"},
+      "tool_to_use": {"type": ["string", "null"], "description": "Tool to use for
+      this step, or null if no tool needed"}, "depends_on": {"type": "array", "items":
+      {"type": "integer"}, "description": "Step numbers this step depends on (empty
+      array if none)"}}, "required": ["step_number", "description", "tool_to_use",
+      "depends_on"], "additionalProperties": false}}, "ready": {"type": "boolean",
+      "description": "Whether the agent is ready to execute the task."}}, "required":
+      ["plan", "steps", "ready"], "additionalProperties": false}}]}], "generationConfig":
+      {"stopSequences": ["\nObservation:"]}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '2747'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      x-goog-api-client:
+      - google-genai-sdk/1.49.0 gl-python/3.13.3
+      x-goog-api-key:
+      - X-GOOG-API-KEY-XXX
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
+  response:
+    body:
+      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
+        [\n          {\n            \"functionCall\": {\n              \"name\": \"create_reasoning_plan\",\n
+        \             \"args\": {\n                \"steps\": [\n                  {\n
+        \                   \"step_number\": 1,\n                    \"tool_to_use\":
+        \"web_search\",\n                    \"depends_on\": [],\n                    \"description\":
+        \"Search for recent information on AI agent market trends.\"\n                  },\n
+        \                 {\n                    \"description\": \"Read detailed
+        content from a relevant industry source found in the search results.\",\n
+        \                   \"depends_on\": [\n                      1\n                    ],\n
+        \                   \"step_number\": 2,\n                    \"tool_to_use\":
+        \"read_website\"\n                  },\n                  {\n                    \"depends_on\":
+        [\n                      2\n                    ],\n                    \"step_number\":
+        3,\n                    \"tool_to_use\": \"generate_report\",\n                    \"description\":
+        \"Generate a brief report summarizing the key findings from the researched
+        content.\"\n                  }\n                ],\n                \"plan\":
+        \"Research the current state of the AI agent market and generate a summary
+        report.\",\n                \"ready\": true\n              }\n            },\n
+        \           \"thoughtSignature\": \"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\"\n
+        \         }\n        ],\n        \"role\": \"model\"\n      },\n      \"finishReason\":
+        \"STOP\",\n      \"index\": 0,\n      \"finishMessage\": \"Model generated
+        function call(s).\"\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
+        529,\n    \"candidatesTokenCount\": 169,\n    \"totalTokenCount\": 955,\n
+        \   \"promptTokensDetails\": [\n      {\n        \"modality\": \"TEXT\",\n
+        \       \"tokenCount\": 529\n      }\n    ],\n    \"thoughtsTokenCount\":
+        257\n  },\n  \"modelVersion\": \"gemini-2.5-flash\",\n  \"responseId\": \"h0WCacqWA6WM_PUPl-niyQ0\"\n}\n"
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Tue, 03 Feb 2026 18:59:19 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=2345
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      X-Frame-Options:
+      - X-FRAME-OPTIONS-XXX
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"contents": [{"parts": [{"text": "\nCurrent Task: Research the current
+      state of the AI agent market:\n1. Search for recent information about AI agents
+      and their market trends\n2. Read detailed content from a relevant industry source\n3.
+      Generate a brief report summarizing the key findings\n\nUse the available tools
+      for each step."}], "role": "user"}], "systemInstruction": {"parts": [{"text":
+      "You are Research Analyst. An experienced analyst skilled at gathering information
+      and synthesizing findings into actionable insights.\nYour personal goal is:
+      Conduct thorough research and produce insightful reports"}], "role": "user"},
+      "tools": [{"functionDeclarations": [{"description": "Search the web for information
+      on a given topic.\n\nArgs:\n    query: The search query to look up.\n\nReturns:\n    Search
+      results as a string.", "name": "web_search", "parameters_json_schema": {"properties":
+      {"query": {"title": "Query", "type": "string"}}, "required": ["query"], "type":
+      "object", "additionalProperties": false}}, {"description": "Read and extract
+      content from a website URL.\n\nArgs:\n    url: The URL of the website to read.\n\nReturns:\n    The
+      extracted content from the website.", "name": "read_website", "parameters_json_schema":
+      {"properties": {"url": {"title": "Url", "type": "string"}}, "required": ["url"],
+      "type": "object", "additionalProperties": false}}, {"description": "Generate
+      a structured report based on research findings.\n\nArgs:\n    title: The title
+      of the report.\n    findings: The research findings to include.\n\nReturns:\n    A
+      formatted report string.", "name": "generate_report", "parameters_json_schema":
+      {"properties": {"title": {"title": "Title", "type": "string"}, "findings": {"title":
+      "Findings", "type": "string"}}, "required": ["title", "findings"], "type": "object",
+      "additionalProperties": false}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1904'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      x-goog-api-client:
+      - google-genai-sdk/1.49.0 gl-python/3.13.3
+      x-goog-api-key:
+      - X-GOOG-API-KEY-XXX
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
+  response:
+    body:
+      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
+        [\n          {\n            \"functionCall\": {\n              \"name\": \"web_search\",\n
+        \             \"args\": {\n                \"query\": \"AI agent market trends
+        2023-2024\"\n              }\n            },\n            \"thoughtSignature\":
+        \"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\"\n
+        \         }\n        ],\n        \"role\": \"model\"\n      },\n      \"finishReason\":
+        \"STOP\",\n      \"index\": 0,\n      \"finishMessage\": \"Model generated
+        function call(s).\"\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
+        319,\n    \"candidatesTokenCount\": 28,\n    \"totalTokenCount\": 461,\n    \"promptTokensDetails\":
+        [\n      {\n        \"modality\": \"TEXT\",\n        \"tokenCount\": 319\n
+        \     }\n    ],\n    \"thoughtsTokenCount\": 114\n  },\n  \"modelVersion\":
+        \"gemini-2.5-flash\",\n  \"responseId\": \"iEWCaYyJENDn_uMP4q3N8QE\"\n}\n"
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Tue, 03 Feb 2026 18:59:20 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=1193
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      X-Frame-Options:
+      - X-FRAME-OPTIONS-XXX
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"contents": [{"parts": [{"text": "\nCurrent Task: Research the current
+      state of the AI agent market:\n1. Search for recent information about AI agents
+      and their market trends\n2. Read detailed content from a relevant industry source\n3.
+      Generate a brief report summarizing the key findings\n\nUse the available tools
+      for each step."}], "role": "user"}, {"parts": [{"functionCall": {"args": {"query":
+      "AI agent market trends 2023-2024"}, "name": "web_search"}, "thoughtSignature":
+      "CoYEAXLI2nzmyDix3_QA-tMOiUwpDVoA5-RJoRW7kw3okJaVYCa5Usx7eBn4xowP7oXNynS4NfawCYqboufBXjHinq13UTcYg0Y74qIrza4KuctliGmf8G7S4QoS0Y3gqCHQKsxTdShQOg8wirnr8Rdu1eyrrhWE0XKk0HPA0Ssj7zUVoJBqHPqwyvkFyXkMtpcmtq9qXmZYfMFuSKRQnYLVLllL_BpOIL3w7MuofpviO85bvYk9gX0vsDjYWS6EdVEfC9k2BWGjhHaILXT9A1iwNPdDAg33SOC-BlPrGox0ghCr5qEKnBMZhUszqaUCykczFCq-xMIA3xDGNbTjicWb53sL_PXBYLsNty1giW3nKFe8-8eRpUsHUx7oQ82m4AUxKqk99mZjaLp8bHk-rERjFZErcw_pe_3190K0WGHH5ecB4amJCzZtVrQJ1oAZhb7_P1VZ57xmt1z_c1pQgjuvnV-cWE9blh5o6mNNFbFuzJDIO2k8qrFeeDwlCF8OOrxo8F-z1evg4yjZ1-9TLCVFTmZ0S0PI54FS5afb0RdPol2_ISNw7H_dtnO4z6LhT2NmlYqYZr8qfVoUD21rmI08NFs-f_6JW5-7eSQbax76SW-6A2IqqPPyF66MCpqtEzC-hpzVsCBcIQyRQWsdm-RNAs50gmqF6W3CcTPryWkeS7w9ORqxdiU="}],
+      "role": "model"}, {"parts": [{"functionResponse": {"name": "web_search", "response":
+      {"result": "Search results for ''AI agent market trends 2023-2024'': Found 3
+      relevant articles about the topic including market analysis, competitor data,
+      and industry trends."}}}], "role": "user"}], "systemInstruction": {"parts":
+      [{"text": "You are Research Analyst. An experienced analyst skilled at gathering
+      information and synthesizing findings into actionable insights.\nYour personal
+      goal is: Conduct thorough research and produce insightful reports"}], "role":
+      "user"}, "tools": [{"functionDeclarations": [{"description": "Search the web
+      for information on a given topic.\n\nArgs:\n    query: The search query to look
+      up.\n\nReturns:\n    Search results as a string.", "name": "web_search", "parameters_json_schema":
+      {"properties": {"query": {"title": "Query", "type": "string"}}, "required":
+      ["query"], "type": "object", "additionalProperties": false}}, {"description":
+      "Read and extract content from a website URL.\n\nArgs:\n    url: The URL of
+      the website to read.\n\nReturns:\n    The extracted content from the website.",
+      "name": "read_website", "parameters_json_schema": {"properties": {"url": {"title":
+      "Url", "type": "string"}}, "required": ["url"], "type": "object", "additionalProperties":
+      false}}, {"description": "Generate a structured report based on research findings.\n\nArgs:\n    title:
+      The title of the report.\n    findings: The research findings to include.\n\nReturns:\n    A
+      formatted report string.", "name": "generate_report", "parameters_json_schema":
+      {"properties": {"title": {"title": "Title", "type": "string"}, "findings": {"title":
+      "Findings", "type": "string"}}, "required": ["title", "findings"], "type": "object",
+      "additionalProperties": false}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '3015'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      x-goog-api-client:
+      - google-genai-sdk/1.49.0 gl-python/3.13.3
+      x-goog-api-key:
+      - X-GOOG-API-KEY-XXX
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
+  response:
+    body:
+      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
+        [\n          {\n            \"functionCall\": {\n              \"name\": \"web_search\",\n
+        \             \"args\": {\n                \"query\": \"latest reports AI
+        agent market analysis\"\n              }\n            },\n            \"thoughtSignature\":
+        \"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\"\n
+        \         }\n        ],\n        \"role\": \"model\"\n      },\n      \"finishReason\":
+        \"STOP\",\n      \"index\": 0,\n      \"finishMessage\": \"Model generated
+        function call(s).\"\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
+        400,\n    \"candidatesTokenCount\": 20,\n    \"totalTokenCount\": 589,\n    \"promptTokensDetails\":
+        [\n      {\n        \"modality\": \"TEXT\",\n        \"tokenCount\": 400\n
+        \     }\n    ],\n    \"thoughtsTokenCount\": 169\n  },\n  \"modelVersion\":
+        \"gemini-2.5-flash\",\n  \"responseId\": \"ikWCacqBG8ve_uMPj4KFyAY\"\n}\n"
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Tue, 03 Feb 2026 18:59:22 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=2125
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      X-Frame-Options:
+      - X-FRAME-OPTIONS-XXX
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"contents": [{"parts": [{"text": "\nCurrent Task: Research the current
+      state of the AI agent market:\n1. Search for recent information about AI agents
+      and their market trends\n2. Read detailed content from a relevant industry source\n3.
+      Generate a brief report summarizing the key findings\n\nUse the available tools
+      for each step."}], "role": "user"}, {"parts": [{"functionCall": {"args": {"query":
+      "AI agent market trends 2023-2024"}, "name": "web_search"}, "thoughtSignature":
+      "CoYEAXLI2nzmyDix3_QA-tMOiUwpDVoA5-RJoRW7kw3okJaVYCa5Usx7eBn4xowP7oXNynS4NfawCYqboufBXjHinq13UTcYg0Y74qIrza4KuctliGmf8G7S4QoS0Y3gqCHQKsxTdShQOg8wirnr8Rdu1eyrrhWE0XKk0HPA0Ssj7zUVoJBqHPqwyvkFyXkMtpcmtq9qXmZYfMFuSKRQnYLVLllL_BpOIL3w7MuofpviO85bvYk9gX0vsDjYWS6EdVEfC9k2BWGjhHaILXT9A1iwNPdDAg33SOC-BlPrGox0ghCr5qEKnBMZhUszqaUCykczFCq-xMIA3xDGNbTjicWb53sL_PXBYLsNty1giW3nKFe8-8eRpUsHUx7oQ82m4AUxKqk99mZjaLp8bHk-rERjFZErcw_pe_3190K0WGHH5ecB4amJCzZtVrQJ1oAZhb7_P1VZ57xmt1z_c1pQgjuvnV-cWE9blh5o6mNNFbFuzJDIO2k8qrFeeDwlCF8OOrxo8F-z1evg4yjZ1-9TLCVFTmZ0S0PI54FS5afb0RdPol2_ISNw7H_dtnO4z6LhT2NmlYqYZr8qfVoUD21rmI08NFs-f_6JW5-7eSQbax76SW-6A2IqqPPyF66MCpqtEzC-hpzVsCBcIQyRQWsdm-RNAs50gmqF6W3CcTPryWkeS7w9ORqxdiU="}],
+      "role": "model"}, {"parts": [{"functionResponse": {"name": "web_search", "response":
+      {"result": "Search results for ''AI agent market trends 2023-2024'': Found 3
+      relevant articles about the topic including market analysis, competitor data,
+      and industry trends."}}}], "role": "user"}, {"parts": [{"functionCall": {"args":
+      {"query": "latest reports AI agent market analysis"}, "name": "web_search"},
+      "thoughtSignature": "CpwGAXLI2nybmVGffIN1k-T5M2HmQNlvybZRPoo_ysgNARa-9nrPdRoBZ9RC-Dee9KSk1o7O-IU9l0sWCTirQYcroEhXon-JIQUVTed_L0s__sBOR-hJnZWoaG5ucsfJQvovAQba2Wb7uViEkdySvHfRApF0atewbC-TCKZrxDAQ6Naby8nwUTauJPKlgsBsZVnlViRfIbF7pom1zvXD-d5htjMiuJr1nOuSH0EGQWC4TUiuJD23hgockzhmIpbU_bStn8PFIQNsySEzl6H5sZdlD4auwCMCD2Q-Ur05w1uLv7n8GoSZn5dkdXLR5R7dZ-kkX-xP4w841Ih2gc6rBKT5tSedN01AuJsK65NSfOXZBwakxs58WZXDQXnIQe4d2QThAX3nPdUmhvVI6sHX-ZdtQZIrhE7hRf9j_T_wvvrUao5VDv-mxXd9bcPEV2BzSXkvkAB1SbJ-5wN7Qb2j31lkiUu5uRnZOiVxL5iCS-8Z_jEl4NjpGithbcPoNpFIDOeiE_f8kf7tQJDX-YNquPbYZRJHvIfLalVQndVGNlZVN2jXT3Wwo8So3vmzIDFVjV-pj7tSRNK8hTITm6bfHS-XUZqJdm7eHCzhonyJ7_tl7LbsstPXoZU3ZN50tNpXYOK-NzgzU7iwd9SaHVXgzQRdujWgHuBmSiSd9qNHvdaNwgARVTnMj3VYpehgIuaYMzQmgM99TdC_zmzcqHa5VZSnHKHqMIVc9gjRvVwz4DUm6VLLnKnVYFClM6gofmUI6s9fThiR5EdfimaDTlRlzh6Df33jAbRA9rUTDH6uE-DjiopCvXuHjmQqK9Smyxt2vTao9H7AYIRN7yWmdVoaG0tUSL2XQ31wIW3cEyhz7ihQwFYKJnOkQ3_CiU6KV-4ldk9UY_vKWSgItVTTE6G8Di0iviiCAkmL59Uj7vnIp80-U9rDIK7WhxpAWlrDA6cGQT2LGAXQ2liXtLa31nXyfvCezhtSS8jSVm4SHaiU-INvYtpq2Q7nXPTFbjjZooyC5FePGqAH1T-sRYbR02jaa572_NuwFgBCObTfqO8G5A=="}],
+      "role": "model"}, {"parts": [{"functionResponse": {"name": "web_search", "response":
+      {"result": "Search results for ''latest reports AI agent market analysis'':
+      Found 3 relevant articles about the topic including market analysis, competitor
+      data, and industry trends."}}}], "role": "user"}], "systemInstruction": {"parts":
+      [{"text": "You are Research Analyst. An experienced analyst skilled at gathering
+      information and synthesizing findings into actionable insights.\nYour personal
+      goal is: Conduct thorough research and produce insightful reports"}], "role":
+      "user"}, "tools": [{"functionDeclarations": [{"description": "Search the web
+      for information on a given topic.\n\nArgs:\n    query: The search query to look
+      up.\n\nReturns:\n    Search results as a string.", "name": "web_search", "parameters_json_schema":
+      {"properties": {"query": {"title": "Query", "type": "string"}}, "required":
+      ["query"], "type": "object", "additionalProperties": false}}, {"description":
+      "Read and extract content from a website URL.\n\nArgs:\n    url: The URL of
+      the website to read.\n\nReturns:\n    The extracted content from the website.",
+      "name": "read_website", "parameters_json_schema": {"properties": {"url": {"title":
+      "Url", "type": "string"}}, "required": ["url"], "type": "object", "additionalProperties":
+      false}}, {"description": "Generate a structured report based on research findings.\n\nArgs:\n    title:
+      The title of the report.\n    findings: The research findings to include.\n\nReturns:\n    A
+      formatted report string.", "name": "generate_report", "parameters_json_schema":
+      {"properties": {"title": {"title": "Title", "type": "string"}, "findings": {"title":
+      "Findings", "type": "string"}}, "required": ["title", "findings"], "type": "object",
+      "additionalProperties": false}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '4512'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      x-goog-api-client:
+      - google-genai-sdk/1.49.0 gl-python/3.13.3
+      x-goog-api-key:
+      - X-GOOG-API-KEY-XXX
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
+  response:
+    body:
+      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
+        [\n          {\n            \"functionCall\": {\n              \"name\": \"read_website\",\n
+        \             \"args\": {\n                \"url\": \"https://www.example.com/ai-agent-market-report\"\n
+        \             }\n            },\n            \"thoughtSignature\": \"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\"\n
+        \         }\n        ],\n        \"role\": \"model\"\n      },\n      \"finishReason\":
+        \"STOP\",\n      \"index\": 0,\n      \"finishMessage\": \"Model generated
+        function call(s).\"\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
+        465,\n    \"candidatesTokenCount\": 29,\n    \"totalTokenCount\": 916,\n    \"promptTokensDetails\":
+        [\n      {\n        \"modality\": \"TEXT\",\n        \"tokenCount\": 465\n
+        \     }\n    ],\n    \"thoughtsTokenCount\": 422\n  },\n  \"modelVersion\":
+        \"gemini-2.5-flash\",\n  \"responseId\": \"jUWCadDOIdi8_uMPxuOu4Ak\"\n}\n"
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Tue, 03 Feb 2026 18:59:25 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=3079
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      X-Frame-Options:
+      - X-FRAME-OPTIONS-XXX
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"contents": [{"parts": [{"text": "\nCurrent Task: Research the current
+      state of the AI agent market:\n1. Search for recent information about AI agents
+      and their market trends\n2. Read detailed content from a relevant industry source\n3.
+      Generate a brief report summarizing the key findings\n\nUse the available tools
+      for each step."}], "role": "user"}, {"parts": [{"functionCall": {"args": {"query":
+      "AI agent market trends 2023-2024"}, "name": "web_search"}, "thoughtSignature":
+      "CoYEAXLI2nzmyDix3_QA-tMOiUwpDVoA5-RJoRW7kw3okJaVYCa5Usx7eBn4xowP7oXNynS4NfawCYqboufBXjHinq13UTcYg0Y74qIrza4KuctliGmf8G7S4QoS0Y3gqCHQKsxTdShQOg8wirnr8Rdu1eyrrhWE0XKk0HPA0Ssj7zUVoJBqHPqwyvkFyXkMtpcmtq9qXmZYfMFuSKRQnYLVLllL_BpOIL3w7MuofpviO85bvYk9gX0vsDjYWS6EdVEfC9k2BWGjhHaILXT9A1iwNPdDAg33SOC-BlPrGox0ghCr5qEKnBMZhUszqaUCykczFCq-xMIA3xDGNbTjicWb53sL_PXBYLsNty1giW3nKFe8-8eRpUsHUx7oQ82m4AUxKqk99mZjaLp8bHk-rERjFZErcw_pe_3190K0WGHH5ecB4amJCzZtVrQJ1oAZhb7_P1VZ57xmt1z_c1pQgjuvnV-cWE9blh5o6mNNFbFuzJDIO2k8qrFeeDwlCF8OOrxo8F-z1evg4yjZ1-9TLCVFTmZ0S0PI54FS5afb0RdPol2_ISNw7H_dtnO4z6LhT2NmlYqYZr8qfVoUD21rmI08NFs-f_6JW5-7eSQbax76SW-6A2IqqPPyF66MCpqtEzC-hpzVsCBcIQyRQWsdm-RNAs50gmqF6W3CcTPryWkeS7w9ORqxdiU="}],
+      "role": "model"}, {"parts": [{"functionResponse": {"name": "web_search", "response":
+      {"result": "Search results for ''AI agent market trends 2023-2024'': Found 3
+      relevant articles about the topic including market analysis, competitor data,
+      and industry trends."}}}], "role": "user"}, {"parts": [{"functionCall": {"args":
+      {"query": "latest reports AI agent market analysis"}, "name": "web_search"},
+      "thoughtSignature": "CpwGAXLI2nybmVGffIN1k-T5M2HmQNlvybZRPoo_ysgNARa-9nrPdRoBZ9RC-Dee9KSk1o7O-IU9l0sWCTirQYcroEhXon-JIQUVTed_L0s__sBOR-hJnZWoaG5ucsfJQvovAQba2Wb7uViEkdySvHfRApF0atewbC-TCKZrxDAQ6Naby8nwUTauJPKlgsBsZVnlViRfIbF7pom1zvXD-d5htjMiuJr1nOuSH0EGQWC4TUiuJD23hgockzhmIpbU_bStn8PFIQNsySEzl6H5sZdlD4auwCMCD2Q-Ur05w1uLv7n8GoSZn5dkdXLR5R7dZ-kkX-xP4w841Ih2gc6rBKT5tSedN01AuJsK65NSfOXZBwakxs58WZXDQXnIQe4d2QThAX3nPdUmhvVI6sHX-ZdtQZIrhE7hRf9j_T_wvvrUao5VDv-mxXd9bcPEV2BzSXkvkAB1SbJ-5wN7Qb2j31lkiUu5uRnZOiVxL5iCS-8Z_jEl4NjpGithbcPoNpFIDOeiE_f8kf7tQJDX-YNquPbYZRJHvIfLalVQndVGNlZVN2jXT3Wwo8So3vmzIDFVjV-pj7tSRNK8hTITm6bfHS-XUZqJdm7eHCzhonyJ7_tl7LbsstPXoZU3ZN50tNpXYOK-NzgzU7iwd9SaHVXgzQRdujWgHuBmSiSd9qNHvdaNwgARVTnMj3VYpehgIuaYMzQmgM99TdC_zmzcqHa5VZSnHKHqMIVc9gjRvVwz4DUm6VLLnKnVYFClM6gofmUI6s9fThiR5EdfimaDTlRlzh6Df33jAbRA9rUTDH6uE-DjiopCvXuHjmQqK9Smyxt2vTao9H7AYIRN7yWmdVoaG0tUSL2XQ31wIW3cEyhz7ihQwFYKJnOkQ3_CiU6KV-4ldk9UY_vKWSgItVTTE6G8Di0iviiCAkmL59Uj7vnIp80-U9rDIK7WhxpAWlrDA6cGQT2LGAXQ2liXtLa31nXyfvCezhtSS8jSVm4SHaiU-INvYtpq2Q7nXPTFbjjZooyC5FePGqAH1T-sRYbR02jaa572_NuwFgBCObTfqO8G5A=="}],
+      "role": "model"}, {"parts": [{"functionResponse": {"name": "web_search", "response":
+      {"result": "Search results for ''latest reports AI agent market analysis'':
+      Found 3 relevant articles about the topic including market analysis, competitor
+      data, and industry trends."}}}], "role": "user"}, {"parts": [{"functionCall":
+      {"args": {"url": "https://www.example.com/ai-agent-market-report"}, "name":
+      "read_website"}, "thoughtSignature": "CooPAXLI2nzYy6ki8YJo4RDDzryK6qtkbIEWXCh0ZjpoRX2fgNghUrxXZUwrsrbrwEpccdvWCDpb5ZkwYMNuzMi4yRUsjfcebfd2VCwQgvWnWmitj3taAcLCUDIJX5pGt0L2O8V6ehWmrANQHGw6Qc_QVx5dMlSFeFKHtfc1M95CJz2BxZd3lnuKLCEu7LCCiqIDdd1o1y_EcGsl7OHai6WyQJg49Cvcww__Z-kfSVoAPGNedTYPIf4ImttMyofV8-yczI0IGjhFzE0Qk1Pvo84O9NyOufpPELeKY8l1yfZgSZEL0sUA6weqf1P_xzNKt6h96Rh1KpAx5iTGFtqOWJrJ8OP-ZdGJ-rA-xZQuTRtKbW_e60rC5kPgJnkhWCp1p7HTLgTGwpzzxztqL0ggURaWw8GJw8S41BcM5mFEA-a7ivMWPMLdMk6h5gr_Y8JTnLSRZFoZYHkY9bTcAFPc9gapyFlKkQDciYet_MHe2zfE7ycx0e8c0W7ISoYPHpXW_WxNekMiNdfx1eg_mEX_Y0Vjc70p-HtbnEGaBoZWJSo-cJtZdA4sNJaIuEnnVTtAdAtnoxJUOyr2jrKDAsSjHmVoeLARZO2_DuJKsEVNHzsNPMw4SrBq1DkG52Aof7KcskOfW2OyoZEUnIf23IRabKflUG_7dHGqYfLtkWRApWZYBy2eQILwsmXJ4xx27S7_02Jl0D8rX3vOQhjS7lTjrXvy8wU3biUFvbnqJuLj3ACLn7Hn1axe4dB7zIpYC1di63DDs1fQp79d2VaGRC-tVMKiQu_-yC6nCM4j8JSnpBNgvyhq3ilAr_iDHD6GkbxdBBChFbZl0KY-WkrcZpPp2g2m_beiQuzF-cM6RuaqF2W0TEjVT-OZ1ivObreXFVFWa9T5qFsTjV3E_SFlmrXdx6Kf8d0i9QeEwbzBIvvX3VNUdW1DJ95WylaUXFtljk_cqylri2j2WTPMTSV9fcM_a8UWoayUAuLzq8zgxd2Wvrm8uvGcaewAQT-yK-u5FsLFoKxaMkoakb2_1tjWfhn-MrbIoYOBIebUapUhADUJgGDTG7byEEQlbwNaa8rOZ5ZpdBrDXjtj1tsz6cqaEiCbtZWqei0myuMa0J6Z3FHoceSUgOACD_bHWSkzdW7LdKBKLxB25fKfD1hCLscE1skZ7nAEZWmrUzKz9yCiqAPfatQhHqnr3EchEB_dxbNXxCCT6IFxemhb9AsaQWjcTrlQJiuz8t4VMmu1slgEcrhweZ_PpxI_E74qvV9ljcFLcziW0BZaqepJMeBe2cLfVVki5R5kudQVuAcCEdkrwBDWAwZlO9aWTmiZ9-ggfl3F_63JzZXSM_NDc_2rJ1k65e-O-vyTzkrUwnSPnh4RPK6jeIul4SSLPgyZBwp0qHyTl4As8jpMe9Rbt0NRli6Z5eAr_IYdbicKo_pzqiupdxvu4u-jKt-F4KojU9avgWFAB01isHHO5Z1vzVJ6XDilWeah5DvHc1lkcPCXtbBGvykfFqJIBhthnFi0f_S4HV-IlOKwvKbfmL5GplD7H-DjUA5UdHjw8HoJa6uQxhbERy5dZlYqxN918aL147Afq4LuPoWUJULEsYULwUuA6HspemIKUltHacOAxZgP4OLVkB3zwssj8E6rMtU1puupHiL7J66fFaR3co71gzzlvl8R2Xi3xEQdpigxxCUAsZWMrSrITRBnKPKGF1CrFEhU6FP6bQAQ6UuhAdqLoJihwVnMTyY9fGUriwCkrQu5gK7ZQlnXyluV0J_5xWh4sOaPmwmeiUXMBPN0iGb7z24lyHaI3QXz3kGlJBnIFhseJTJo3ed66Z_LAf8I_hFC6s_sIioEmRgd4tm3Q1U05ETKrptnzo8Ac4AOTdJtbQv0uDQSkoefUbebu7x6L9Dns04VSvDPKLwlFQd81sl9DYmi9SPDxKT7S6gfG6WjJ9z35eNSR01QW1QIgAAhMU8UX4o7QQaXnUZxfZeYRMXlzu_xb4KSREvc_FeLJ-IvnPFgzryAgLi_Sipl__Eul0sjrREPYJE1GxBOIoURGa-Bsmc3yy8aWArxv_HGpbLzwjmH8TaMvB3P_4tkvT-5IjJlpe0UrR1ssqasUtwfH9yWv5-4i-EdJrJ_SJ4Hl1Vlj9zi9lEFr33Zs96kn8ZOkBHp0m7Sxr5xP-krSxQkROIpu0d02kIqQ3nob-kGbnAf0zkmH6pS3H4mG2Zksu8KcGvghx7XTl3qBOJ-ZY4vlev2cSMBfMmnbUHKvMlz4YsmTGR1JPntDguA8UJJ1UZCex4E_W3KcHwd4qvzqgMZNjdarIvGjlmnKmoL1RV7EqUsBkpk-jauY0SqoWsIIf4b6O9Y3fQRRJURLeIfGCTmlxl-df-4yjqUhxUXTaQsX2KlEJ3tZK-ZI9FdKMzqPip2oMFwf2XfLIyIuRA0NU5fDRIxqPUzYv6RQ-zhXXB1QscsAtyf1t-LsaVw__1Vfj6V3Ups4pNyiwMAZg1z9DaIHht--VfgCdqT4RLcaGI8eEDrjkOc9G_iLkLBCfOB7EZkcXT20Lc1Silxa--dZsaYp5Tni8dz6f5YWg=="}],
+      "role": "model"}, {"parts": [{"functionResponse": {"name": "read_website", "response":
+      {"result": "Content from https://www.example.com/ai-agent-market-report: This
+      article discusses key insights about the topic including market size ($50B),
+      growth rate (15% YoY), and major players in the industry."}}}], "role": "user"}],
+      "systemInstruction": {"parts": [{"text": "You are Research Analyst. An experienced
+      analyst skilled at gathering information and synthesizing findings into actionable
+      insights.\nYour personal goal is: Conduct thorough research and produce insightful
+      reports"}], "role": "user"}, "tools": [{"functionDeclarations": [{"description":
+      "Search the web for information on a given topic.\n\nArgs:\n    query: The search
+      query to look up.\n\nReturns:\n    Search results as a string.", "name": "web_search",
+      "parameters_json_schema": {"properties": {"query": {"title": "Query", "type":
+      "string"}}, "required": ["query"], "type": "object", "additionalProperties":
+      false}}, {"description": "Read and extract content from a website URL.\n\nArgs:\n    url:
+      The URL of the website to read.\n\nReturns:\n    The extracted content from
+      the website.", "name": "read_website", "parameters_json_schema": {"properties":
+      {"url": {"title": "Url", "type": "string"}}, "required": ["url"], "type": "object",
+      "additionalProperties": false}}, {"description": "Generate a structured report
+      based on research findings.\n\nArgs:\n    title: The title of the report.\n    findings:
+      The research findings to include.\n\nReturns:\n    A formatted report string.",
+      "name": "generate_report", "parameters_json_schema": {"properties": {"title":
+      {"title": "Title", "type": "string"}, "findings": {"title": "Findings", "type":
+      "string"}}, "required": ["title", "findings"], "type": "object", "additionalProperties":
+      false}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '7562'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      x-goog-api-client:
+      - google-genai-sdk/1.49.0 gl-python/3.13.3
+      x-goog-api-key:
+      - X-GOOG-API-KEY-XXX
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
+  response:
+    body:
+      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
+        [\n          {\n            \"functionCall\": {\n              \"name\": \"generate_report\",\n
+        \             \"args\": {\n                \"findings\": \"The AI agent market
+        is currently valued at $50 billion and is experiencing a strong growth rate
+        of 15% year-over-year. Key players in the industry are contributing to this
+        expansion, driven by increasing adoption across various sectors.\",\n                \"title\":
+        \"Current State of the AI Agent Market\"\n              }\n            },\n
+        \           \"thoughtSignature\": \"CuACAXLI2nzhub94iTgphfrBnaQV13Wv0+kRJj+l9jEDfxsyNg9eGnhxRfj4cued3Mgvv1CR9vkpfDV/V9x57TVWLNwPsVvsTgZKI0pwmV355sUCRKqAyfRBwDWhn0UAl9+sYNFCKUJCp8G5QBGfrar1lYLltX/z83d4O13Wn5Ugvxco9o4CdxnnPJOWkTPETRgXA/1HSdEiwGNqt0A3lKYkGRXQx+XyK54lDwmOBg+Yx4ZVgUxANXLK1z91NF/6cpmSVgoE2sL0VrIHISYs4XdUCj1fL3R7DpnZdrrZhmqnTjEgkeR1C3BR5GJeSUmg+kmqjPSPnP0NYiZo9H9SGL/ewGz3wg+GKcILAa4nD7/tfdqIMbAff8PJemwJE4ONT5zAmJ69/NFj0i1X01v04E8f2NdHewPSsKO5mptk5qzWxoW3G3uUhXccxk62EydTsESf6WRwolsmphaGgVE9AwuhzQ==\"\n
+        \         }\n        ],\n        \"role\": \"model\"\n      },\n      \"finishReason\":
+        \"STOP\",\n      \"index\": 0,\n      \"finishMessage\": \"Model generated
+        function call(s).\"\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
+        557,\n    \"candidatesTokenCount\": 73,\n    \"totalTokenCount\": 700,\n    \"cachedContentTokenCount\":
+        330,\n    \"promptTokensDetails\": [\n      {\n        \"modality\": \"TEXT\",\n
+        \       \"tokenCount\": 557\n      }\n    ],\n    \"cacheTokensDetails\":
+        [\n      {\n        \"modality\": \"TEXT\",\n        \"tokenCount\": 330\n
+        \     }\n    ],\n    \"thoughtsTokenCount\": 70\n  },\n  \"modelVersion\":
+        \"gemini-2.5-flash\",\n  \"responseId\": \"jkWCacGZMLrv_uMPibCHmQU\"\n}\n"
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Tue, 03 Feb 2026 18:59:26 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=1224
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      X-Frame-Options:
+      - X-FRAME-OPTIONS-XXX
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"contents": [{"parts": [{"text": "\nCurrent Task: Research the current
+      state of the AI agent market:\n1. Search for recent information about AI agents
+      and their market trends\n2. Read detailed content from a relevant industry source\n3.
+      Generate a brief report summarizing the key findings\n\nUse the available tools
+      for each step."}], "role": "user"}, {"parts": [{"functionCall": {"args": {"query":
+      "AI agent market trends 2023-2024"}, "name": "web_search"}, "thoughtSignature":
+      "CoYEAXLI2nzmyDix3_QA-tMOiUwpDVoA5-RJoRW7kw3okJaVYCa5Usx7eBn4xowP7oXNynS4NfawCYqboufBXjHinq13UTcYg0Y74qIrza4KuctliGmf8G7S4QoS0Y3gqCHQKsxTdShQOg8wirnr8Rdu1eyrrhWE0XKk0HPA0Ssj7zUVoJBqHPqwyvkFyXkMtpcmtq9qXmZYfMFuSKRQnYLVLllL_BpOIL3w7MuofpviO85bvYk9gX0vsDjYWS6EdVEfC9k2BWGjhHaILXT9A1iwNPdDAg33SOC-BlPrGox0ghCr5qEKnBMZhUszqaUCykczFCq-xMIA3xDGNbTjicWb53sL_PXBYLsNty1giW3nKFe8-8eRpUsHUx7oQ82m4AUxKqk99mZjaLp8bHk-rERjFZErcw_pe_3190K0WGHH5ecB4amJCzZtVrQJ1oAZhb7_P1VZ57xmt1z_c1pQgjuvnV-cWE9blh5o6mNNFbFuzJDIO2k8qrFeeDwlCF8OOrxo8F-z1evg4yjZ1-9TLCVFTmZ0S0PI54FS5afb0RdPol2_ISNw7H_dtnO4z6LhT2NmlYqYZr8qfVoUD21rmI08NFs-f_6JW5-7eSQbax76SW-6A2IqqPPyF66MCpqtEzC-hpzVsCBcIQyRQWsdm-RNAs50gmqF6W3CcTPryWkeS7w9ORqxdiU="}],
+      "role": "model"}, {"parts": [{"functionResponse": {"name": "web_search", "response":
+      {"result": "Search results for ''AI agent market trends 2023-2024'': Found 3
+      relevant articles about the topic including market analysis, competitor data,
+      and industry trends."}}}], "role": "user"}, {"parts": [{"functionCall": {"args":
+      {"query": "latest reports AI agent market analysis"}, "name": "web_search"},
+      "thoughtSignature": "CpwGAXLI2nybmVGffIN1k-T5M2HmQNlvybZRPoo_ysgNARa-9nrPdRoBZ9RC-Dee9KSk1o7O-IU9l0sWCTirQYcroEhXon-JIQUVTed_L0s__sBOR-hJnZWoaG5ucsfJQvovAQba2Wb7uViEkdySvHfRApF0atewbC-TCKZrxDAQ6Naby8nwUTauJPKlgsBsZVnlViRfIbF7pom1zvXD-d5htjMiuJr1nOuSH0EGQWC4TUiuJD23hgockzhmIpbU_bStn8PFIQNsySEzl6H5sZdlD4auwCMCD2Q-Ur05w1uLv7n8GoSZn5dkdXLR5R7dZ-kkX-xP4w841Ih2gc6rBKT5tSedN01AuJsK65NSfOXZBwakxs58WZXDQXnIQe4d2QThAX3nPdUmhvVI6sHX-ZdtQZIrhE7hRf9j_T_wvvrUao5VDv-mxXd9bcPEV2BzSXkvkAB1SbJ-5wN7Qb2j31lkiUu5uRnZOiVxL5iCS-8Z_jEl4NjpGithbcPoNpFIDOeiE_f8kf7tQJDX-YNquPbYZRJHvIfLalVQndVGNlZVN2jXT3Wwo8So3vmzIDFVjV-pj7tSRNK8hTITm6bfHS-XUZqJdm7eHCzhonyJ7_tl7LbsstPXoZU3ZN50tNpXYOK-NzgzU7iwd9SaHVXgzQRdujWgHuBmSiSd9qNHvdaNwgARVTnMj3VYpehgIuaYMzQmgM99TdC_zmzcqHa5VZSnHKHqMIVc9gjRvVwz4DUm6VLLnKnVYFClM6gofmUI6s9fThiR5EdfimaDTlRlzh6Df33jAbRA9rUTDH6uE-DjiopCvXuHjmQqK9Smyxt2vTao9H7AYIRN7yWmdVoaG0tUSL2XQ31wIW3cEyhz7ihQwFYKJnOkQ3_CiU6KV-4ldk9UY_vKWSgItVTTE6G8Di0iviiCAkmL59Uj7vnIp80-U9rDIK7WhxpAWlrDA6cGQT2LGAXQ2liXtLa31nXyfvCezhtSS8jSVm4SHaiU-INvYtpq2Q7nXPTFbjjZooyC5FePGqAH1T-sRYbR02jaa572_NuwFgBCObTfqO8G5A=="}],
+      "role": "model"}, {"parts": [{"functionResponse": {"name": "web_search", "response":
+      {"result": "Search results for ''latest reports AI agent market analysis'':
+      Found 3 relevant articles about the topic including market analysis, competitor
+      data, and industry trends."}}}], "role": "user"}, {"parts": [{"functionCall":
+      {"args": {"url": "https://www.example.com/ai-agent-market-report"}, "name":
+      "read_website"}, "thoughtSignature": "CooPAXLI2nzYy6ki8YJo4RDDzryK6qtkbIEWXCh0ZjpoRX2fgNghUrxXZUwrsrbrwEpccdvWCDpb5ZkwYMNuzMi4yRUsjfcebfd2VCwQgvWnWmitj3taAcLCUDIJX5pGt0L2O8V6ehWmrANQHGw6Qc_QVx5dMlSFeFKHtfc1M95CJz2BxZd3lnuKLCEu7LCCiqIDdd1o1y_EcGsl7OHai6WyQJg49Cvcww__Z-kfSVoAPGNedTYPIf4ImttMyofV8-yczI0IGjhFzE0Qk1Pvo84O9NyOufpPELeKY8l1yfZgSZEL0sUA6weqf1P_xzNKt6h96Rh1KpAx5iTGFtqOWJrJ8OP-ZdGJ-rA-xZQuTRtKbW_e60rC5kPgJnkhWCp1p7HTLgTGwpzzxztqL0ggURaWw8GJw8S41BcM5mFEA-a7ivMWPMLdMk6h5gr_Y8JTnLSRZFoZYHkY9bTcAFPc9gapyFlKkQDciYet_MHe2zfE7ycx0e8c0W7ISoYPHpXW_WxNekMiNdfx1eg_mEX_Y0Vjc70p-HtbnEGaBoZWJSo-cJtZdA4sNJaIuEnnVTtAdAtnoxJUOyr2jrKDAsSjHmVoeLARZO2_DuJKsEVNHzsNPMw4SrBq1DkG52Aof7KcskOfW2OyoZEUnIf23IRabKflUG_7dHGqYfLtkWRApWZYBy2eQILwsmXJ4xx27S7_02Jl0D8rX3vOQhjS7lTjrXvy8wU3biUFvbnqJuLj3ACLn7Hn1axe4dB7zIpYC1di63DDs1fQp79d2VaGRC-tVMKiQu_-yC6nCM4j8JSnpBNgvyhq3ilAr_iDHD6GkbxdBBChFbZl0KY-WkrcZpPp2g2m_beiQuzF-cM6RuaqF2W0TEjVT-OZ1ivObreXFVFWa9T5qFsTjV3E_SFlmrXdx6Kf8d0i9QeEwbzBIvvX3VNUdW1DJ95WylaUXFtljk_cqylri2j2WTPMTSV9fcM_a8UWoayUAuLzq8zgxd2Wvrm8uvGcaewAQT-yK-u5FsLFoKxaMkoakb2_1tjWfhn-MrbIoYOBIebUapUhADUJgGDTG7byEEQlbwNaa8rOZ5ZpdBrDXjtj1tsz6cqaEiCbtZWqei0myuMa0J6Z3FHoceSUgOACD_bHWSkzdW7LdKBKLxB25fKfD1hCLscE1skZ7nAEZWmrUzKz9yCiqAPfatQhHqnr3EchEB_dxbNXxCCT6IFxemhb9AsaQWjcTrlQJiuz8t4VMmu1slgEcrhweZ_PpxI_E74qvV9ljcFLcziW0BZaqepJMeBe2cLfVVki5R5kudQVuAcCEdkrwBDWAwZlO9aWTmiZ9-ggfl3F_63JzZXSM_NDc_2rJ1k65e-O-vyTzkrUwnSPnh4RPK6jeIul4SSLPgyZBwp0qHyTl4As8jpMe9Rbt0NRli6Z5eAr_IYdbicKo_pzqiupdxvu4u-jKt-F4KojU9avgWFAB01isHHO5Z1vzVJ6XDilWeah5DvHc1lkcPCXtbBGvykfFqJIBhthnFi0f_S4HV-IlOKwvKbfmL5GplD7H-DjUA5UdHjw8HoJa6uQxhbERy5dZlYqxN918aL147Afq4LuPoWUJULEsYULwUuA6HspemIKUltHacOAxZgP4OLVkB3zwssj8E6rMtU1puupHiL7J66fFaR3co71gzzlvl8R2Xi3xEQdpigxxCUAsZWMrSrITRBnKPKGF1CrFEhU6FP6bQAQ6UuhAdqLoJihwVnMTyY9fGUriwCkrQu5gK7ZQlnXyluV0J_5xWh4sOaPmwmeiUXMBPN0iGb7z24lyHaI3QXz3kGlJBnIFhseJTJo3ed66Z_LAf8I_hFC6s_sIioEmRgd4tm3Q1U05ETKrptnzo8Ac4AOTdJtbQv0uDQSkoefUbebu7x6L9Dns04VSvDPKLwlFQd81sl9DYmi9SPDxKT7S6gfG6WjJ9z35eNSR01QW1QIgAAhMU8UX4o7QQaXnUZxfZeYRMXlzu_xb4KSREvc_FeLJ-IvnPFgzryAgLi_Sipl__Eul0sjrREPYJE1GxBOIoURGa-Bsmc3yy8aWArxv_HGpbLzwjmH8TaMvB3P_4tkvT-5IjJlpe0UrR1ssqasUtwfH9yWv5-4i-EdJrJ_SJ4Hl1Vlj9zi9lEFr33Zs96kn8ZOkBHp0m7Sxr5xP-krSxQkROIpu0d02kIqQ3nob-kGbnAf0zkmH6pS3H4mG2Zksu8KcGvghx7XTl3qBOJ-ZY4vlev2cSMBfMmnbUHKvMlz4YsmTGR1JPntDguA8UJJ1UZCex4E_W3KcHwd4qvzqgMZNjdarIvGjlmnKmoL1RV7EqUsBkpk-jauY0SqoWsIIf4b6O9Y3fQRRJURLeIfGCTmlxl-df-4yjqUhxUXTaQsX2KlEJ3tZK-ZI9FdKMzqPip2oMFwf2XfLIyIuRA0NU5fDRIxqPUzYv6RQ-zhXXB1QscsAtyf1t-LsaVw__1Vfj6V3Ups4pNyiwMAZg1z9DaIHht--VfgCdqT4RLcaGI8eEDrjkOc9G_iLkLBCfOB7EZkcXT20Lc1Silxa--dZsaYp5Tni8dz6f5YWg=="}],
+      "role": "model"}, {"parts": [{"functionResponse": {"name": "read_website", "response":
+      {"result": "Content from https://www.example.com/ai-agent-market-report: This
+      article discusses key insights about the topic including market size ($50B),
+      growth rate (15% YoY), and major players in the industry."}}}], "role": "user"},
+      {"parts": [{"functionCall": {"args": {"findings": "The AI agent market is currently
+      valued at $50 billion and is experiencing a strong growth rate of 15% year-over-year.
+      Key players in the industry are contributing to this expansion, driven by increasing
+      adoption across various sectors.", "title": "Current State of the AI Agent Market"},
+      "name": "generate_report"}, "thoughtSignature": "CuACAXLI2nzhub94iTgphfrBnaQV13Wv0-kRJj-l9jEDfxsyNg9eGnhxRfj4cued3Mgvv1CR9vkpfDV_V9x57TVWLNwPsVvsTgZKI0pwmV355sUCRKqAyfRBwDWhn0UAl9-sYNFCKUJCp8G5QBGfrar1lYLltX_z83d4O13Wn5Ugvxco9o4CdxnnPJOWkTPETRgXA_1HSdEiwGNqt0A3lKYkGRXQx-XyK54lDwmOBg-Yx4ZVgUxANXLK1z91NF_6cpmSVgoE2sL0VrIHISYs4XdUCj1fL3R7DpnZdrrZhmqnTjEgkeR1C3BR5GJeSUmg-kmqjPSPnP0NYiZo9H9SGL_ewGz3wg-GKcILAa4nD7_tfdqIMbAff8PJemwJE4ONT5zAmJ69_NFj0i1X01v04E8f2NdHewPSsKO5mptk5qzWxoW3G3uUhXccxk62EydTsESf6WRwolsmphaGgVE9AwuhzQ=="}],
+      "role": "model"}, {"parts": [{"functionResponse": {"name": "generate_report",
+      "response": {"result": "# Current State of the AI Agent Market\n\n## Executive
+      Summary\nThe AI agent market is currently valued at $50 billion and is experiencing
+      a strong growth rate of 15% year-over-year. Key players in the industry are
+      contributing to this expansion, driven by increasing adoption across various
+      sectors.\n\n## Conclusion\nBased on the analysis, the market shows strong growth
+      potential."}}}], "role": "user"}], "systemInstruction": {"parts": [{"text":
+      "You are Research Analyst. An experienced analyst skilled at gathering information
+      and synthesizing findings into actionable insights.\nYour personal goal is:
+      Conduct thorough research and produce insightful reports"}], "role": "user"},
+      "tools": [{"functionDeclarations": [{"description": "Search the web for information
+      on a given topic.\n\nArgs:\n    query: The search query to look up.\n\nReturns:\n    Search
+      results as a string.", "name": "web_search", "parameters_json_schema": {"properties":
+      {"query": {"title": "Query", "type": "string"}}, "required": ["query"], "type":
+      "object", "additionalProperties": false}}, {"description": "Read and extract
+      content from a website URL.\n\nArgs:\n    url: The URL of the website to read.\n\nReturns:\n    The
+      extracted content from the website.", "name": "read_website", "parameters_json_schema":
+      {"properties": {"url": {"title": "Url", "type": "string"}}, "required": ["url"],
+      "type": "object", "additionalProperties": false}}, {"description": "Generate
+      a structured report based on research findings.\n\nArgs:\n    title: The title
+      of the report.\n    findings: The research findings to include.\n\nReturns:\n    A
+      formatted report string.", "name": "generate_report", "parameters_json_schema":
+      {"properties": {"title": {"title": "Title", "type": "string"}, "findings": {"title":
+      "Findings", "type": "string"}}, "required": ["title", "findings"], "type": "object",
+      "additionalProperties": false}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '8941'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      x-goog-api-client:
+      - google-genai-sdk/1.49.0 gl-python/3.13.3
+      x-goog-api-key:
+      - X-GOOG-API-KEY-XXX
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
+  response:
+    body:
+      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
+        [\n          {\n            \"text\": \"The research on the current state
+        of the AI agent market has been completed. A report has been generated with
+        the following key findings:\\n\\n**Current State of the AI Agent Market**\\n\\n**Executive
+        Summary**\\nThe AI agent market is currently valued at $50 billion and is
+        experiencing a strong growth rate of 15% year-over-year. Key players in the
+        industry are contributing to this expansion, driven by increasing adoption
+        across various sectors.\\n\\n**Conclusion**\\nBased on the analysis, the market
+        shows strong growth potential.\",\n            \"thoughtSignature\": \"CpIDAXLI2nwVVOjjKtAsnvvRhuJU79oCZksDIi1i7PcIr+FkXVHX8sS8kM0optXLnRQWDRKKxUDKA9C1myhIfnDfc3ef44xc4UaczwM80/TbYanden25qpZRA2kztBz9HiWEPyGjeX8M/8BGAj7mh3q6hwPtTFtmhFTzlw190YQoZLELqOyQzTSECt8roXPdWN1XhU/NbHg4x+H3IFSQ2HZKxbY/JC6tx5FYYh444tIT4798iVHI5HOUVb1pfdLfV45ju/DOD+pTONuqVcTX+jgusjoaH32pdu4Q19atg5BR6zanqwv93vkYPXx0hF4rI8FHtV9jrqwtjLqzXvh7LANtNpCvO3HG++lIoeRTy5RzfYQRkLkrfuLWW+xkGDYQh+CQ7jbeurx344pHBjzZTVDaSNTA0QMTYwDH7YUkxIsyw5Hv1F8tpVvjgoKqvJnar1d/EvrbiOwygpiEZOrmPEn/DKp4qPk2+hhFS4JpcnNGva9cFM22ObwHydIQdoXHOX3wci0nhshAZ0e8hd5u820gfrya\"\n
+        \         }\n        ],\n        \"role\": \"model\"\n      },\n      \"finishReason\":
+        \"STOP\",\n      \"index\": 0\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
+        727,\n    \"candidatesTokenCount\": 108,\n    \"totalTokenCount\": 910,\n
+        \   \"cachedContentTokenCount\": 375,\n    \"promptTokensDetails\": [\n      {\n
+        \       \"modality\": \"TEXT\",\n        \"tokenCount\": 727\n      }\n    ],\n
+        \   \"cacheTokensDetails\": [\n      {\n        \"modality\": \"TEXT\",\n
+        \       \"tokenCount\": 375\n      }\n    ],\n    \"thoughtsTokenCount\":
+        75\n  },\n  \"modelVersion\": \"gemini-2.5-flash\",\n  \"responseId\": \"kUWCabvgOafg_uMP06Ga0QI\"\n}\n"
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Tue, 03 Feb 2026 18:59:30 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=3125
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      X-Frame-Options:
+      - X-FRAME-OPTIONS-XXX
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/utilities/TestOpenAIStructuredPlanning.test_openai_research_workflow_generates_steps.yaml

@@ -0,0 +1,708 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are a strategic planning assistant.
+      Create minimal, effective execution plans. Prefer fewer steps over more."},{"role":"user","content":"Create
+      a focused execution plan for the following task:\n\n## Task\nResearch the current
+      state of the AI agent market:\n1. Search for recent information about AI agents
+      and their market trends\n2. Read detailed content from a relevant industry source\n3.
+      Generate a brief report summarizing the key findings\n\nUse the available tools
+      for each step.\n\n## Expected Output\nComplete the task successfully\n\n## Available
+      Tools\nweb_search, read_website, generate_report\n\n## Instructions\nCreate
+      ONLY the essential steps needed to complete this task. Use the MINIMUM number
+      of steps required - do NOT pad your plan with unnecessary steps. Most tasks
+      need only 2-5 steps.\n\nFor each step:\n- State the specific action to take\n-
+      Specify which tool to use (if any)\n- Note dependencies on previous steps if
+      this step requires their output\n- If a step involves multiple items (e.g.,
+      research 3 competitors), note this explicitly\n\nDo NOT include:\n- Setup or
+      preparation steps that are obvious\n- Verification steps unless critical\n-
+      Documentation or cleanup steps unless explicitly required\n- Generic steps like
+      \"review results\" or \"finalize output\"\n\nAfter your plan, state:\n- \"READY:
+      I am ready to execute the task.\" if the plan is complete\n- \"NOT READY: I
+      need to refine my plan because [reason].\" if you need more thinking"}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
+      or refine a reasoning plan for a task with structured steps","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"A
+      brief summary of the overall plan."},"steps":{"type":"array","description":"List
+      of discrete steps to execute the plan","items":{"type":"object","properties":{"step_number":{"type":"integer","description":"Step
+      number (1-based)"},"description":{"type":"string","description":"What to do
+      in this step"},"tool_to_use":{"type":["string","null"],"description":"Tool to
+      use for this step, or null if no tool needed"},"depends_on":{"type":"array","items":{"type":"integer"},"description":"Step
+      numbers this step depends on (empty array if none)"}},"required":["step_number","description","tool_to_use","depends_on"],"additionalProperties":false}},"ready":{"type":"boolean","description":"Whether
+      the agent is ready to execute the task."}},"required":["plan","steps","ready"],"additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '2619'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D5Fu3HzCCoZJXtY9WqBmBv4QA4PS8\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770145143,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+        \           \"id\": \"call_bVEiQHpiVX9FEfuWVwTe8XGj\",\n            \"type\":
+        \"function\",\n            \"function\": {\n              \"name\": \"create_reasoning_plan\",\n
+        \             \"arguments\": \"{\\\"plan\\\":\\\"Research the current state
+        of the AI agent market by gathering recent market trend data, reading in-depth
+        content from a reliable industry source, and generating a concise report.\\\",\\\"steps\\\":[{\\\"step_number\\\":1,\\\"description\\\":\\\"Search
+        for recent information about AI agents and their market trends.\\\",\\\"tool_to_use\\\":\\\"web_search\\\",\\\"depends_on\\\":[]},{\\\"step_number\\\":2,\\\"description\\\":\\\"Read
+        detailed content from a relevant industry source found during the search.\\\",\\\"tool_to_use\\\":\\\"read_website\\\",\\\"depends_on\\\":[1]},{\\\"step_number\\\":3,\\\"description\\\":\\\"Generate
+        a brief report summarizing the key findings from the gathered information.\\\",\\\"tool_to_use\\\":\\\"generate_report\\\",\\\"depends_on\\\":[1,2]}],\\\"ready\\\":true}\"\n
+        \           }\n          }\n        ],\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"tool_calls\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 480,\n    \"completion_tokens\":
+        153,\n    \"total_tokens\": 633,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_fa7f5b168b\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 18:59:05 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '2629'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. An experienced
+      analyst skilled at gathering information and synthesizing findings into actionable
+      insights.\nYour personal goal is: Conduct thorough research and produce insightful
+      reports"},{"role":"user","content":"\nCurrent Task: Research the current state
+      of the AI agent market:\n1. Search for recent information about AI agents and
+      their market trends\n2. Read detailed content from a relevant industry source\n3.
+      Generate a brief report summarizing the key findings\n\nUse the available tools
+      for each step."}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"web_search","description":"Search
+      the web for information on a given topic.\n\nArgs:\n    query: The search query
+      to look up.\n\nReturns:\n    Search results as a string.","strict":true,"parameters":{"properties":{"query":{"title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"read_website","description":"Read
+      and extract content from a website URL.\n\nArgs:\n    url: The URL of the website
+      to read.\n\nReturns:\n    The extracted content from the website.","strict":true,"parameters":{"properties":{"url":{"title":"Url","type":"string"}},"required":["url"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"generate_report","description":"Generate
+      a structured report based on research findings.\n\nArgs:\n    title: The title
+      of the report.\n    findings: The research findings to include.\n\nReturns:\n    A
+      formatted report string.","strict":true,"parameters":{"properties":{"title":{"title":"Title","type":"string"},"findings":{"title":"Findings","type":"string"}},"required":["title","findings"],"type":"object","additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1849'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D5Fu6H5Oz7CA6xtmPwoBDIAr59nyJ\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770145146,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+        \           \"id\": \"call_QlnPEA94TbaFA83eRDhOHXRY\",\n            \"type\":
+        \"function\",\n            \"function\": {\n              \"name\": \"web_search\",\n
+        \             \"arguments\": \"{\\\"query\\\":\\\"current state of AI agent
+        market 2023\\\"}\"\n            }\n          }\n        ],\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"tool_calls\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        267,\n    \"completion_tokens\": 22,\n    \"total_tokens\": 289,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_fa7f5b168b\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 18:59:07 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '752'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. An experienced
+      analyst skilled at gathering information and synthesizing findings into actionable
+      insights.\nYour personal goal is: Conduct thorough research and produce insightful
+      reports"},{"role":"user","content":"\nCurrent Task: Research the current state
+      of the AI agent market:\n1. Search for recent information about AI agents and
+      their market trends\n2. Read detailed content from a relevant industry source\n3.
+      Generate a brief report summarizing the key findings\n\nUse the available tools
+      for each step."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_QlnPEA94TbaFA83eRDhOHXRY","type":"function","function":{"name":"web_search","arguments":"{\"query\":\"current
+      state of AI agent market 2023\"}"}}]},{"role":"tool","tool_call_id":"call_QlnPEA94TbaFA83eRDhOHXRY","name":"web_search","content":"Search
+      results for ''current state of AI agent market 2023'': Found 3 relevant articles
+      about the topic including market analysis, competitor data, and industry trends."}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"web_search","description":"Search
+      the web for information on a given topic.\n\nArgs:\n    query: The search query
+      to look up.\n\nReturns:\n    Search results as a string.","strict":true,"parameters":{"properties":{"query":{"title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"read_website","description":"Read
+      and extract content from a website URL.\n\nArgs:\n    url: The URL of the website
+      to read.\n\nReturns:\n    The extracted content from the website.","strict":true,"parameters":{"properties":{"url":{"title":"Url","type":"string"}},"required":["url"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"generate_report","description":"Generate
+      a structured report based on research findings.\n\nArgs:\n    title: The title
+      of the report.\n    findings: The research findings to include.\n\nReturns:\n    A
+      formatted report string.","strict":true,"parameters":{"properties":{"title":{"title":"Title","type":"string"},"findings":{"title":"Findings","type":"string"}},"required":["title","findings"],"type":"object","additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '2320'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D5Fu7QFl2h9pGJ0uhX6g4Fi4MMzMX\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770145147,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+        \           \"id\": \"call_sOaxpAdq5dvpRhUJMAct2oNP\",\n            \"type\":
+        \"function\",\n            \"function\": {\n              \"name\": \"read_website\",\n
+        \             \"arguments\": \"{\\\"url\\\": \\\"https://www.example.com/ai-agent-market-analysis-2023\\\"}\"\n
+        \           }\n          },\n          {\n            \"id\": \"call_1GRSbggp4SYHg5WqAUQx5Dce\",\n
+        \           \"type\": \"function\",\n            \"function\": {\n              \"name\":
+        \"read_website\",\n              \"arguments\": \"{\\\"url\\\": \\\"https://www.example.com/ai-agent-competitor-data-2023\\\"}\"\n
+        \           }\n          },\n          {\n            \"id\": \"call_43s9ebATowN3hA5piPjL2z5N\",\n
+        \           \"type\": \"function\",\n            \"function\": {\n              \"name\":
+        \"read_website\",\n              \"arguments\": \"{\\\"url\\\": \\\"https://www.example.com/ai-agent-industry-trends-2023\\\"}\"\n
+        \           }\n          }\n        ],\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"tool_calls\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 330,\n    \"completion_tokens\":
+        101,\n    \"total_tokens\": 431,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_fa7f5b168b\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 18:59:09 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '1885'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. An experienced
+      analyst skilled at gathering information and synthesizing findings into actionable
+      insights.\nYour personal goal is: Conduct thorough research and produce insightful
+      reports"},{"role":"user","content":"\nCurrent Task: Research the current state
+      of the AI agent market:\n1. Search for recent information about AI agents and
+      their market trends\n2. Read detailed content from a relevant industry source\n3.
+      Generate a brief report summarizing the key findings\n\nUse the available tools
+      for each step."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_QlnPEA94TbaFA83eRDhOHXRY","type":"function","function":{"name":"web_search","arguments":"{\"query\":\"current
+      state of AI agent market 2023\"}"}}]},{"role":"tool","tool_call_id":"call_QlnPEA94TbaFA83eRDhOHXRY","name":"web_search","content":"Search
+      results for ''current state of AI agent market 2023'': Found 3 relevant articles
+      about the topic including market analysis, competitor data, and industry trends."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_sOaxpAdq5dvpRhUJMAct2oNP","type":"function","function":{"name":"read_website","arguments":"{\"url\":
+      \"https://www.example.com/ai-agent-market-analysis-2023\"}"}},{"id":"call_1GRSbggp4SYHg5WqAUQx5Dce","type":"function","function":{"name":"read_website","arguments":"{\"url\":
+      \"https://www.example.com/ai-agent-competitor-data-2023\"}"}},{"id":"call_43s9ebATowN3hA5piPjL2z5N","type":"function","function":{"name":"read_website","arguments":"{\"url\":
+      \"https://www.example.com/ai-agent-industry-trends-2023\"}"}}]},{"role":"tool","tool_call_id":"call_sOaxpAdq5dvpRhUJMAct2oNP","name":"read_website","content":"Content
+      from https://www.example.com/ai-agent-market-analysis-2023: This article discusses
+      key insights about the topic including market size ($50B), growth rate (15%
+      YoY), and major players in the industry."},{"role":"tool","tool_call_id":"call_1GRSbggp4SYHg5WqAUQx5Dce","name":"read_website","content":"Content
+      from https://www.example.com/ai-agent-competitor-data-2023: This article discusses
+      key insights about the topic including market size ($50B), growth rate (15%
+      YoY), and major players in the industry."},{"role":"tool","tool_call_id":"call_43s9ebATowN3hA5piPjL2z5N","name":"read_website","content":"Content
+      from https://www.example.com/ai-agent-industry-trends-2023: This article discusses
+      key insights about the topic including market size ($50B), growth rate (15%
+      YoY), and major players in the industry."}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"web_search","description":"Search
+      the web for information on a given topic.\n\nArgs:\n    query: The search query
+      to look up.\n\nReturns:\n    Search results as a string.","strict":true,"parameters":{"properties":{"query":{"title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"read_website","description":"Read
+      and extract content from a website URL.\n\nArgs:\n    url: The URL of the website
+      to read.\n\nReturns:\n    The extracted content from the website.","strict":true,"parameters":{"properties":{"url":{"title":"Url","type":"string"}},"required":["url"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"generate_report","description":"Generate
+      a structured report based on research findings.\n\nArgs:\n    title: The title
+      of the report.\n    findings: The research findings to include.\n\nReturns:\n    A
+      formatted report string.","strict":true,"parameters":{"properties":{"title":{"title":"Title","type":"string"},"findings":{"title":"Findings","type":"string"}},"required":["title","findings"],"type":"object","additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '3811'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D5Fu95gX9R1zxpiJUa1wSOzIGA9CL\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770145149,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+        \           \"id\": \"call_QjEKbvT6OnKkCOTvwTu0TmAK\",\n            \"type\":
+        \"function\",\n            \"function\": {\n              \"name\": \"generate_report\",\n
+        \             \"arguments\": \"{\\\"title\\\":\\\"Current State of the AI
+        Agent Market 2023\\\",\\\"findings\\\":\\\"1. Market Size: The AI agent market
+        is currently valued at $50 billion.\\\\n2. Growth Rate: The industry is experiencing
+        a growth rate of 15% year-over-year.\\\\n3. Major Players: Significant companies
+        in this space include tech giants and specialized AI startups.\\\\n4. Market
+        Trends: The demand for AI agents is being driven by improvements in machine
+        learning algorithms and increasing adoption in customer service and automation
+        processes.\\\\n5. Competitive Landscape: The market is competitive with ongoing
+        innovation and investment in developing more advanced AI capabilities.\\\\n6.
+        Future Prospects: Continued growth is expected as businesses further integrate
+        AI agents into their operations for efficiency gains and customer engagement.\\\"}\"\n
+        \           }\n          }\n        ],\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"tool_calls\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 587,\n    \"completion_tokens\":
+        163,\n    \"total_tokens\": 750,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_fa7f5b168b\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 18:59:12 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '3444'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. An experienced
+      analyst skilled at gathering information and synthesizing findings into actionable
+      insights.\nYour personal goal is: Conduct thorough research and produce insightful
+      reports"},{"role":"user","content":"\nCurrent Task: Research the current state
+      of the AI agent market:\n1. Search for recent information about AI agents and
+      their market trends\n2. Read detailed content from a relevant industry source\n3.
+      Generate a brief report summarizing the key findings\n\nUse the available tools
+      for each step."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_QlnPEA94TbaFA83eRDhOHXRY","type":"function","function":{"name":"web_search","arguments":"{\"query\":\"current
+      state of AI agent market 2023\"}"}}]},{"role":"tool","tool_call_id":"call_QlnPEA94TbaFA83eRDhOHXRY","name":"web_search","content":"Search
+      results for ''current state of AI agent market 2023'': Found 3 relevant articles
+      about the topic including market analysis, competitor data, and industry trends."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_sOaxpAdq5dvpRhUJMAct2oNP","type":"function","function":{"name":"read_website","arguments":"{\"url\":
+      \"https://www.example.com/ai-agent-market-analysis-2023\"}"}},{"id":"call_1GRSbggp4SYHg5WqAUQx5Dce","type":"function","function":{"name":"read_website","arguments":"{\"url\":
+      \"https://www.example.com/ai-agent-competitor-data-2023\"}"}},{"id":"call_43s9ebATowN3hA5piPjL2z5N","type":"function","function":{"name":"read_website","arguments":"{\"url\":
+      \"https://www.example.com/ai-agent-industry-trends-2023\"}"}}]},{"role":"tool","tool_call_id":"call_sOaxpAdq5dvpRhUJMAct2oNP","name":"read_website","content":"Content
+      from https://www.example.com/ai-agent-market-analysis-2023: This article discusses
+      key insights about the topic including market size ($50B), growth rate (15%
+      YoY), and major players in the industry."},{"role":"tool","tool_call_id":"call_1GRSbggp4SYHg5WqAUQx5Dce","name":"read_website","content":"Content
+      from https://www.example.com/ai-agent-competitor-data-2023: This article discusses
+      key insights about the topic including market size ($50B), growth rate (15%
+      YoY), and major players in the industry."},{"role":"tool","tool_call_id":"call_43s9ebATowN3hA5piPjL2z5N","name":"read_website","content":"Content
+      from https://www.example.com/ai-agent-industry-trends-2023: This article discusses
+      key insights about the topic including market size ($50B), growth rate (15%
+      YoY), and major players in the industry."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_QjEKbvT6OnKkCOTvwTu0TmAK","type":"function","function":{"name":"generate_report","arguments":"{\"title\":\"Current
+      State of the AI Agent Market 2023\",\"findings\":\"1. Market Size: The AI agent
+      market is currently valued at $50 billion.\\n2. Growth Rate: The industry is
+      experiencing a growth rate of 15% year-over-year.\\n3. Major Players: Significant
+      companies in this space include tech giants and specialized AI startups.\\n4.
+      Market Trends: The demand for AI agents is being driven by improvements in machine
+      learning algorithms and increasing adoption in customer service and automation
+      processes.\\n5. Competitive Landscape: The market is competitive with ongoing
+      innovation and investment in developing more advanced AI capabilities.\\n6.
+      Future Prospects: Continued growth is expected as businesses further integrate
+      AI agents into their operations for efficiency gains and customer engagement.\"}"}}]},{"role":"tool","tool_call_id":"call_QjEKbvT6OnKkCOTvwTu0TmAK","name":"generate_report","content":"#
+      Current State of the AI Agent Market 2023\n\n## Executive Summary\n1. Market
+      Size: The AI agent market is currently valued at $50 billion.\n2. Growth Rate:
+      The industry is experiencing a growth rate of 15% year-over-year.\n3. Major
+      Players: Significant companies in this space include tech giants and specialized
+      AI startups.\n4. Market Trends: The demand for AI agents is being driven by
+      improvements in machine learning algorithms and increasing adoption in customer
+      service and automation processes.\n5. Competitive Landscape: The market is competitive
+      with ongoing innovation and investment in developing more advanced AI capabilities.\n6.
+      Future Prospects: Continued growth is expected as businesses further integrate
+      AI agents into their operations for efficiency gains and customer engagement.\n\n##
+      Conclusion\nBased on the analysis, the market shows strong growth potential."}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"web_search","description":"Search
+      the web for information on a given topic.\n\nArgs:\n    query: The search query
+      to look up.\n\nReturns:\n    Search results as a string.","strict":true,"parameters":{"properties":{"query":{"title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"read_website","description":"Read
+      and extract content from a website URL.\n\nArgs:\n    url: The URL of the website
+      to read.\n\nReturns:\n    The extracted content from the website.","strict":true,"parameters":{"properties":{"url":{"title":"Url","type":"string"}},"required":["url"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"generate_report","description":"Generate
+      a structured report based on research findings.\n\nArgs:\n    title: The title
+      of the report.\n    findings: The research findings to include.\n\nReturns:\n    A
+      formatted report string.","strict":true,"parameters":{"properties":{"title":{"title":"Title","type":"string"},"findings":{"title":"Findings","type":"string"}},"required":["title","findings"],"type":"object","additionalProperties":false}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '5771'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D5FuCTJhAII96iBV05ECT71cV6QmJ\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1770145152,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"The research on the current state of
+        the AI agent market indicates a robust and rapidly growing industry. Here\u2019s
+        a summary of the findings:\\n\\n1. **Market Size**: The AI agent market is
+        currently valued at $50 billion.\\n2. **Growth Rate**: It is experiencing
+        a significant growth rate of 15% year-over-year.\\n3. **Major Players**: The
+        market is dominated by tech giants and specialized AI startups.\\n4. **Market
+        Trends**: The increasing adoption of machine learning algorithms and the integration
+        of AI in customer service and automation are key drivers.\\n5. **Competitive
+        Landscape**: There is substantial competition and continuous innovation in
+        AI capabilities.\\n6. **Future Prospects**: The sector is expected to keep
+        growing as businesses increasingly use AI agents for efficiency and improved
+        customer engagement.\\n\\nThis analysis highlights significant opportunities
+        in the AI agent sector, underlining its importance in future technological
+        advancements.\",\n        \"refusal\": null,\n        \"annotations\": []\n
+        \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+        \ ],\n  \"usage\": {\n    \"prompt_tokens\": 920,\n    \"completion_tokens\":
+        182,\n    \"total_tokens\": 1102,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_fa7f5b168b\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 03 Feb 2026 18:59:16 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '3456'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cli/authentication/test_auth_main.py

@@ -2,7 +2,7 @@ from datetime import datetime, timedelta
 from unittest.mock import MagicMock, call, patch
 
 import pytest
-import requests
+import httpx
 from crewai.cli.authentication.main import AuthenticationCommand
 from crewai.cli.constants import (
     CREWAI_ENTERPRISE_DEFAULT_OAUTH2_AUDIENCE,
@@ -220,7 +220,7 @@ class TestAuthenticationCommand:
         ]
         mock_console_print.assert_has_calls(expected_calls)
 
-    @patch("requests.post")
+    @patch("crewai.cli.authentication.main.httpx.post")
     def test_get_device_code(self, mock_post):
         mock_response = MagicMock()
         mock_response.json.return_value = {
@@ -256,7 +256,7 @@ class TestAuthenticationCommand:
             "verification_uri_complete": "https://example.com/auth",
         }
 
-    @patch("requests.post")
+    @patch("crewai.cli.authentication.main.httpx.post")
     @patch("crewai.cli.authentication.main.console.print")
     def test_poll_for_token_success(self, mock_console_print, mock_post):
         mock_response_success = MagicMock()
@@ -305,7 +305,7 @@ class TestAuthenticationCommand:
             ]
             mock_console_print.assert_has_calls(expected_calls)
 
-    @patch("requests.post")
+    @patch("crewai.cli.authentication.main.httpx.post")
     @patch("crewai.cli.authentication.main.console.print")
     def test_poll_for_token_timeout(self, mock_console_print, mock_post):
         mock_response_pending = MagicMock()
@@ -324,7 +324,7 @@ class TestAuthenticationCommand:
             "Timeout: Failed to get the token. Please try again.", style="bold red"
         )
 
-    @patch("requests.post")
+    @patch("crewai.cli.authentication.main.httpx.post")
     def test_poll_for_token_error(self, mock_post):
         """Test the method to poll for token (error path)."""
         # Setup mock to return error
@@ -338,5 +338,5 @@ class TestAuthenticationCommand:
 
         device_code_data = {"device_code": "test_device_code", "interval": 1}
 
-        with pytest.raises(requests.HTTPError):
+        with pytest.raises(httpx.HTTPError):
             self.auth_command._poll_for_token(device_code_data)

lib/crewai/tests/cli/deploy/test_deploy_main.py

@@ -4,10 +4,11 @@ from io import StringIO
 from unittest.mock import MagicMock, Mock, patch
 
 import pytest
-import requests
+import json
+
+import httpx
 from crewai.cli.deploy.main import DeployCommand
 from crewai.cli.utils import parse_toml
-from requests.exceptions import JSONDecodeError
 
 
 class TestDeployCommand(unittest.TestCase):
@@ -37,18 +38,18 @@ class TestDeployCommand(unittest.TestCase):
             DeployCommand()
 
     def test_validate_response_successful_response(self):
-        mock_response = Mock(spec=requests.Response)
+        mock_response = Mock(spec=httpx.Response)
         mock_response.json.return_value = {"message": "Success"}
         mock_response.status_code = 200
-        mock_response.ok = True
+        mock_response.is_success = True
 
         with patch("sys.stdout", new=StringIO()) as fake_out:
             self.deploy_command._validate_response(mock_response)
             assert fake_out.getvalue() == ""
 
     def test_validate_response_json_decode_error(self):
-        mock_response = Mock(spec=requests.Response)
-        mock_response.json.side_effect = JSONDecodeError("Decode error", "", 0)
+        mock_response = Mock(spec=httpx.Response)
+        mock_response.json.side_effect = json.JSONDecodeError("Decode error", "", 0)
         mock_response.status_code = 500
         mock_response.content = b"Invalid JSON"
 
@@ -64,13 +65,13 @@ class TestDeployCommand(unittest.TestCase):
             assert "Response:\nInvalid JSON" in output
 
     def test_validate_response_422_error(self):
-        mock_response = Mock(spec=requests.Response)
+        mock_response = Mock(spec=httpx.Response)
         mock_response.json.return_value = {
             "field1": ["Error message 1"],
             "field2": ["Error message 2"],
         }
         mock_response.status_code = 422
-        mock_response.ok = False
+        mock_response.is_success = False
 
         with patch("sys.stdout", new=StringIO()) as fake_out:
             with pytest.raises(SystemExit):
@@ -84,10 +85,10 @@ class TestDeployCommand(unittest.TestCase):
             assert "Field2 Error message 2" in output
 
     def test_validate_response_other_error(self):
-        mock_response = Mock(spec=requests.Response)
+        mock_response = Mock(spec=httpx.Response)
         mock_response.json.return_value = {"error": "Something went wrong"}
         mock_response.status_code = 500
-        mock_response.ok = False
+        mock_response.is_success = False
 
         with patch("sys.stdout", new=StringIO()) as fake_out:
             with pytest.raises(SystemExit):

lib/crewai/tests/cli/enterprise/test_main.py

@@ -3,8 +3,9 @@ import unittest
 from pathlib import Path
 from unittest.mock import Mock, patch
 
-import requests
-from requests.exceptions import JSONDecodeError
+import json
+
+import httpx
 
 from crewai.cli.enterprise.main import EnterpriseConfigureCommand
 from crewai.cli.settings.main import SettingsCommand
@@ -25,7 +26,7 @@ class TestEnterpriseConfigureCommand(unittest.TestCase):
     def tearDown(self):
         shutil.rmtree(self.test_dir)
 
-    @patch('crewai.cli.enterprise.main.requests.get')
+    @patch('crewai.cli.enterprise.main.httpx.get')
     @patch('crewai.cli.enterprise.main.get_crewai_version')
     def test_successful_configuration(self, mock_get_version, mock_requests_get):
         mock_get_version.return_value = "1.0.0"
@@ -73,19 +74,23 @@ class TestEnterpriseConfigureCommand(unittest.TestCase):
             self.assertEqual(call_args[0], key)
             self.assertEqual(call_args[1], value)
 
-    @patch('crewai.cli.enterprise.main.requests.get')
+    @patch('crewai.cli.enterprise.main.httpx.get')
     @patch('crewai.cli.enterprise.main.get_crewai_version')
     def test_http_error_handling(self, mock_get_version, mock_requests_get):
         mock_get_version.return_value = "1.0.0"
 
         mock_response = Mock()
-        mock_response.raise_for_status.side_effect = requests.HTTPError("404 Not Found")
+        mock_response.raise_for_status.side_effect = httpx.HTTPStatusError(
+            "404 Not Found",
+            request=httpx.Request("GET", "http://test"),
+            response=httpx.Response(404),
+        )
         mock_requests_get.return_value = mock_response
 
         with self.assertRaises(SystemExit):
             self.enterprise_command.configure("https://enterprise.example.com")
 
-    @patch('crewai.cli.enterprise.main.requests.get')
+    @patch('crewai.cli.enterprise.main.httpx.get')
     @patch('crewai.cli.enterprise.main.get_crewai_version')
     def test_invalid_json_response(self, mock_get_version, mock_requests_get):
         mock_get_version.return_value = "1.0.0"
@@ -93,13 +98,13 @@ class TestEnterpriseConfigureCommand(unittest.TestCase):
         mock_response = Mock()
         mock_response.status_code = 200
         mock_response.raise_for_status.return_value = None
-        mock_response.json.side_effect = JSONDecodeError("Invalid JSON", "", 0)
+        mock_response.json.side_effect = json.JSONDecodeError("Invalid JSON", "", 0)
         mock_requests_get.return_value = mock_response
 
         with self.assertRaises(SystemExit):
             self.enterprise_command.configure("https://enterprise.example.com")
 
-    @patch('crewai.cli.enterprise.main.requests.get')
+    @patch('crewai.cli.enterprise.main.httpx.get')
     @patch('crewai.cli.enterprise.main.get_crewai_version')
     def test_missing_required_fields(self, mock_get_version, mock_requests_get):
         mock_get_version.return_value = "1.0.0"
@@ -115,7 +120,7 @@ class TestEnterpriseConfigureCommand(unittest.TestCase):
         with self.assertRaises(SystemExit):
             self.enterprise_command.configure("https://enterprise.example.com")
 
-    @patch('crewai.cli.enterprise.main.requests.get')
+    @patch('crewai.cli.enterprise.main.httpx.get')
     @patch('crewai.cli.enterprise.main.get_crewai_version')
     def test_settings_update_error(self, mock_get_version, mock_requests_get):
         mock_get_version.return_value = "1.0.0"

lib/crewai/tests/cli/organization/test_main.py

@@ -3,7 +3,7 @@ from unittest.mock import MagicMock, patch, call
 
 import pytest
 from click.testing import CliRunner
-import requests
+import httpx
 
 from crewai.cli.organization.main import OrganizationCommand
 from crewai.cli.cli import org_list, switch, current
@@ -115,7 +115,7 @@ class TestOrganizationCommand(unittest.TestCase):
     def test_list_organizations_api_error(self, mock_console):
         self.org_command.plus_api_client = MagicMock()
         self.org_command.plus_api_client.get_organizations.side_effect = (
-            requests.exceptions.RequestException("API Error")
+            httpx.HTTPError("API Error")
         )
 
         with pytest.raises(SystemExit):
@@ -201,8 +201,10 @@ class TestOrganizationCommand(unittest.TestCase):
     @patch("crewai.cli.organization.main.console")
     def test_list_organizations_unauthorized(self, mock_console):
         mock_response = MagicMock()
-        mock_http_error = requests.exceptions.HTTPError(
-            "401 Client Error: Unauthorized", response=MagicMock(status_code=401)
+        mock_http_error = httpx.HTTPStatusError(
+            "401 Client Error: Unauthorized",
+            request=httpx.Request("GET", "http://test"),
+            response=httpx.Response(401),
         )
 
         mock_response.raise_for_status.side_effect = mock_http_error
@@ -219,8 +221,10 @@ class TestOrganizationCommand(unittest.TestCase):
     @patch("crewai.cli.organization.main.console")
     def test_switch_organization_unauthorized(self, mock_console):
         mock_response = MagicMock()
-        mock_http_error = requests.exceptions.HTTPError(
-            "401 Client Error: Unauthorized", response=MagicMock(status_code=401)
+        mock_http_error = httpx.HTTPStatusError(
+            "401 Client Error: Unauthorized",
+            request=httpx.Request("GET", "http://test"),
+            response=httpx.Response(401),
         )
 
         mock_response.raise_for_status.side_effect = mock_http_error

lib/crewai/tests/cli/test_plus_api.py

@@ -33,9 +33,9 @@ class TestPlusAPI(unittest.TestCase):
         self.assertEqual(response, mock_response)
 
     def assert_request_with_org_id(
-        self, mock_make_request, method: str, endpoint: str, **kwargs
+        self, mock_client_instance, method: str, endpoint: str, **kwargs
     ):
-        mock_make_request.assert_called_once_with(
+        mock_client_instance.request.assert_called_once_with(
             method,
             f"{os.getenv('CREWAI_PLUS_URL')}{endpoint}",
             headers={
@@ -49,24 +49,25 @@ class TestPlusAPI(unittest.TestCase):
         )
 
     @patch("crewai.cli.plus_api.Settings")
-    @patch("requests.Session.request")
+    @patch("crewai.cli.plus_api.httpx.Client")
     def test_login_to_tool_repository_with_org_uuid(
-        self, mock_make_request, mock_settings_class
+        self, mock_client_class, mock_settings_class
     ):
         mock_settings = MagicMock()
         mock_settings.org_uuid = self.org_uuid
         mock_settings.enterprise_base_url = os.getenv('CREWAI_PLUS_URL')
         mock_settings_class.return_value = mock_settings
-        # re-initialize Client
         self.api = PlusAPI(self.api_key)
 
+        mock_client_instance = MagicMock()
         mock_response = MagicMock()
-        mock_make_request.return_value = mock_response
+        mock_client_instance.request.return_value = mock_response
+        mock_client_class.return_value.__enter__.return_value = mock_client_instance
 
         response = self.api.login_to_tool_repository()
 
         self.assert_request_with_org_id(
-            mock_make_request, "POST", "/crewai_plus/api/v1/tools/login"
+            mock_client_instance, "POST", "/crewai_plus/api/v1/tools/login"
         )
         self.assertEqual(response, mock_response)
 
@@ -82,23 +83,23 @@ class TestPlusAPI(unittest.TestCase):
         self.assertEqual(response, mock_response)
 
     @patch("crewai.cli.plus_api.Settings")
-    @patch("requests.Session.request")
-    def test_get_tool_with_org_uuid(self, mock_make_request, mock_settings_class):
+    @patch("crewai.cli.plus_api.httpx.Client")
+    def test_get_tool_with_org_uuid(self, mock_client_class, mock_settings_class):
         mock_settings = MagicMock()
         mock_settings.org_uuid = self.org_uuid
         mock_settings.enterprise_base_url = os.getenv('CREWAI_PLUS_URL')
         mock_settings_class.return_value = mock_settings
-        # re-initialize Client
         self.api = PlusAPI(self.api_key)
 
-        # Set up mock response
+        mock_client_instance = MagicMock()
         mock_response = MagicMock()
-        mock_make_request.return_value = mock_response
+        mock_client_instance.request.return_value = mock_response
+        mock_client_class.return_value.__enter__.return_value = mock_client_instance
 
         response = self.api.get_tool("test_tool_handle")
 
         self.assert_request_with_org_id(
-            mock_make_request, "GET", "/crewai_plus/api/v1/tools/test_tool_handle"
+            mock_client_instance, "GET", "/crewai_plus/api/v1/tools/test_tool_handle"
         )
         self.assertEqual(response, mock_response)
 
@@ -130,18 +131,18 @@ class TestPlusAPI(unittest.TestCase):
         self.assertEqual(response, mock_response)
 
     @patch("crewai.cli.plus_api.Settings")
-    @patch("requests.Session.request")
-    def test_publish_tool_with_org_uuid(self, mock_make_request, mock_settings_class):
+    @patch("crewai.cli.plus_api.httpx.Client")
+    def test_publish_tool_with_org_uuid(self, mock_client_class, mock_settings_class):
         mock_settings = MagicMock()
         mock_settings.org_uuid = self.org_uuid
         mock_settings.enterprise_base_url = os.getenv('CREWAI_PLUS_URL')
         mock_settings_class.return_value = mock_settings
-        # re-initialize Client
         self.api = PlusAPI(self.api_key)
 
-        # Set up mock response
+        mock_client_instance = MagicMock()
         mock_response = MagicMock()
-        mock_make_request.return_value = mock_response
+        mock_client_instance.request.return_value = mock_response
+        mock_client_class.return_value.__enter__.return_value = mock_client_instance
 
         handle = "test_tool_handle"
         public = True
@@ -153,7 +154,6 @@ class TestPlusAPI(unittest.TestCase):
             handle, public, version, description, encoded_file
         )
 
-        # Expected params including organization_uuid
         expected_params = {
             "handle": handle,
             "public": public,
@@ -164,7 +164,7 @@ class TestPlusAPI(unittest.TestCase):
         }
 
         self.assert_request_with_org_id(
-            mock_make_request, "POST", "/crewai_plus/api/v1/tools", json=expected_params
+            mock_client_instance, "POST", "/crewai_plus/api/v1/tools", json=expected_params
         )
         self.assertEqual(response, mock_response)
 
@@ -195,20 +195,19 @@ class TestPlusAPI(unittest.TestCase):
         )
         self.assertEqual(response, mock_response)
 
-    @patch("crewai.cli.plus_api.requests.Session")
-    def test_make_request(self, mock_session):
+    @patch("crewai.cli.plus_api.httpx.Client")
+    def test_make_request(self, mock_client_class):
+        mock_client_instance = MagicMock()
         mock_response = MagicMock()
-
-        mock_session_instance = mock_session.return_value
-        mock_session_instance.request.return_value = mock_response
+        mock_client_instance.request.return_value = mock_response
+        mock_client_class.return_value.__enter__.return_value = mock_client_instance
 
         response = self.api._make_request("GET", "test_endpoint")
 
-        mock_session.assert_called_once()
-        mock_session_instance.request.assert_called_once_with(
+        mock_client_class.assert_called_once_with(trust_env=False, verify=True)
+        mock_client_instance.request.assert_called_once_with(
             "GET", f"{self.api.base_url}/test_endpoint", headers=self.api.headers
         )
-        mock_session_instance.trust_env = False
         self.assertEqual(response, mock_response)
 
     @patch("crewai.cli.plus_api.PlusAPI._make_request")

lib/crewai/tests/cli/tools/test_main.py

@@ -351,7 +351,7 @@ def test_publish_api_error(
     mock_response = MagicMock()
     mock_response.status_code = 500
     mock_response.json.return_value = {"error": "Internal Server Error"}
-    mock_response.ok = False
+    mock_response.is_success = False
     mock_publish.return_value = mock_response
 
     with raises(SystemExit):

lib/crewai/tests/cli/triggers/test_main.py

@@ -3,7 +3,7 @@ import subprocess
 import unittest
 from unittest.mock import Mock, patch
 
-import requests
+import httpx
 from crewai.cli.triggers.main import TriggersCommand
 
 
@@ -21,7 +21,7 @@ class TestTriggersCommand(unittest.TestCase):
 
     @patch("crewai.cli.triggers.main.console.print")
     def test_list_triggers_success(self, mock_console_print):
-        mock_response = Mock(spec=requests.Response)
+        mock_response = Mock(spec=httpx.Response)
         mock_response.status_code = 200
         mock_response.ok = True
         mock_response.json.return_value = {
@@ -50,7 +50,7 @@ class TestTriggersCommand(unittest.TestCase):
 
     @patch("crewai.cli.triggers.main.console.print")
     def test_list_triggers_no_apps(self, mock_console_print):
-        mock_response = Mock(spec=requests.Response)
+        mock_response = Mock(spec=httpx.Response)
         mock_response.status_code = 200
         mock_response.ok = True
         mock_response.json.return_value = {"apps": []}
@@ -81,7 +81,7 @@ class TestTriggersCommand(unittest.TestCase):
     @patch("crewai.cli.triggers.main.console.print")
     @patch.object(TriggersCommand, "_run_crew_with_payload")
     def test_execute_with_trigger_success(self, mock_run_crew, mock_console_print):
-        mock_response = Mock(spec=requests.Response)
+        mock_response = Mock(spec=httpx.Response)
         mock_response.status_code = 200
         mock_response.ok = True
         mock_response.json.return_value = {
@@ -99,7 +99,7 @@ class TestTriggersCommand(unittest.TestCase):
 
     @patch("crewai.cli.triggers.main.console.print")
     def test_execute_with_trigger_not_found(self, mock_console_print):
-        mock_response = Mock(spec=requests.Response)
+        mock_response = Mock(spec=httpx.Response)
         mock_response.status_code = 404
         mock_response.json.return_value = {"error": "Trigger not found"}
         self.mock_client.get_trigger_payload.return_value = mock_response
@@ -159,7 +159,7 @@ class TestTriggersCommand(unittest.TestCase):
 
     @patch("crewai.cli.triggers.main.console.print")
     def test_execute_with_trigger_with_default_error_message(self, mock_console_print):
-        mock_response = Mock(spec=requests.Response)
+        mock_response = Mock(spec=httpx.Response)
         mock_response.status_code = 404
         mock_response.json.return_value = {}
         self.mock_client.get_trigger_payload.return_value = mock_response

lib/crewai/tests/utilities/test_planning_types.py

@@ -0,0 +1,389 @@
+"""Tests for planning types (PlanStep, TodoItem, TodoList)."""
+
+import pytest
+from uuid import UUID
+
+from crewai.utilities.planning_types import (
+    PlanStep,
+    TodoItem,
+    TodoList,
+    TodoStatus,
+)
+
+
+class TestPlanStep:
+    """Tests for the PlanStep model."""
+
+    def test_plan_step_with_required_fields(self):
+        """Test PlanStep creation with only required fields."""
+        step = PlanStep(
+            step_number=1,
+            description="Research the topic",
+        )
+
+        assert step.step_number == 1
+        assert step.description == "Research the topic"
+        assert step.tool_to_use is None
+        assert step.depends_on == []
+
+    def test_plan_step_with_all_fields(self):
+        """Test PlanStep creation with all fields."""
+        step = PlanStep(
+            step_number=2,
+            description="Search for information",
+            tool_to_use="search_tool",
+            depends_on=[1],
+        )
+
+        assert step.step_number == 2
+        assert step.description == "Search for information"
+        assert step.tool_to_use == "search_tool"
+        assert step.depends_on == [1]
+
+    def test_plan_step_with_multiple_dependencies(self):
+        """Test PlanStep with multiple dependencies."""
+        step = PlanStep(
+            step_number=4,
+            description="Synthesize results",
+            depends_on=[1, 2, 3],
+        )
+
+        assert step.depends_on == [1, 2, 3]
+
+    def test_plan_step_requires_step_number(self):
+        """Test that step_number is required."""
+        with pytest.raises(ValueError):
+            PlanStep(description="Missing step number")
+
+    def test_plan_step_requires_description(self):
+        """Test that description is required."""
+        with pytest.raises(ValueError):
+            PlanStep(step_number=1)
+
+    def test_plan_step_serialization(self):
+        """Test PlanStep can be serialized to dict."""
+        step = PlanStep(
+            step_number=1,
+            description="Test step",
+            tool_to_use="test_tool",
+            depends_on=[],
+        )
+
+        data = step.model_dump()
+        assert data["step_number"] == 1
+        assert data["description"] == "Test step"
+        assert data["tool_to_use"] == "test_tool"
+        assert data["depends_on"] == []
+
+
+class TestTodoItem:
+    """Tests for the TodoItem model."""
+
+    def test_todo_item_with_required_fields(self):
+        """Test TodoItem creation with only required fields."""
+        todo = TodoItem(
+            step_number=1,
+            description="First task",
+        )
+
+        assert todo.step_number == 1
+        assert todo.description == "First task"
+        assert todo.status == "pending"
+        assert todo.tool_to_use is None
+        assert todo.depends_on == []
+        assert todo.result is None
+        # ID should be auto-generated
+        assert todo.id is not None
+        # Verify it's a valid UUID
+        UUID(todo.id)
+
+    def test_todo_item_with_all_fields(self):
+        """Test TodoItem creation with all fields."""
+        todo = TodoItem(
+            id="custom-id-123",
+            step_number=2,
+            description="Second task",
+            tool_to_use="search_tool",
+            status="running",
+            depends_on=[1],
+            result="Task completed",
+        )
+
+        assert todo.id == "custom-id-123"
+        assert todo.step_number == 2
+        assert todo.description == "Second task"
+        assert todo.tool_to_use == "search_tool"
+        assert todo.status == "running"
+        assert todo.depends_on == [1]
+        assert todo.result == "Task completed"
+
+    def test_todo_item_status_values(self):
+        """Test all valid status values."""
+        for status in ["pending", "running", "completed"]:
+            todo = TodoItem(
+                step_number=1,
+                description="Test",
+                status=status,
+            )
+            assert todo.status == status
+
+    def test_todo_item_auto_generates_unique_ids(self):
+        """Test that each TodoItem gets a unique auto-generated ID."""
+        todo1 = TodoItem(step_number=1, description="Task 1")
+        todo2 = TodoItem(step_number=2, description="Task 2")
+
+        assert todo1.id != todo2.id
+
+    def test_todo_item_serialization(self):
+        """Test TodoItem can be serialized to dict."""
+        todo = TodoItem(
+            step_number=1,
+            description="Test task",
+            status="pending",
+        )
+
+        data = todo.model_dump()
+        assert "id" in data
+        assert data["step_number"] == 1
+        assert data["description"] == "Test task"
+        assert data["status"] == "pending"
+
+
+class TestTodoList:
+    """Tests for the TodoList model."""
+
+    @pytest.fixture
+    def empty_todo_list(self):
+        """Create an empty TodoList."""
+        return TodoList()
+
+    @pytest.fixture
+    def sample_todo_list(self):
+        """Create a TodoList with sample items."""
+        return TodoList(
+            items=[
+                TodoItem(step_number=1, description="Step 1", status="completed"),
+                TodoItem(step_number=2, description="Step 2", status="running"),
+                TodoItem(step_number=3, description="Step 3", status="pending"),
+                TodoItem(step_number=4, description="Step 4", status="pending"),
+            ]
+        )
+
+    def test_empty_todo_list(self, empty_todo_list):
+        """Test empty TodoList properties."""
+        assert empty_todo_list.items == []
+        assert empty_todo_list.current_todo is None
+        assert empty_todo_list.next_pending is None
+        assert empty_todo_list.is_complete is False
+        assert empty_todo_list.pending_count == 0
+        assert empty_todo_list.completed_count == 0
+
+    def test_current_todo_property(self, sample_todo_list):
+        """Test current_todo returns the running item."""
+        current = sample_todo_list.current_todo
+        assert current is not None
+        assert current.step_number == 2
+        assert current.status == "running"
+
+    def test_current_todo_returns_none_when_no_running(self):
+        """Test current_todo returns None when no running items."""
+        todo_list = TodoList(
+            items=[
+                TodoItem(step_number=1, description="Step 1", status="completed"),
+                TodoItem(step_number=2, description="Step 2", status="pending"),
+            ]
+        )
+        assert todo_list.current_todo is None
+
+    def test_next_pending_property(self, sample_todo_list):
+        """Test next_pending returns the first pending item."""
+        next_item = sample_todo_list.next_pending
+        assert next_item is not None
+        assert next_item.step_number == 3
+        assert next_item.status == "pending"
+
+    def test_next_pending_returns_none_when_no_pending(self):
+        """Test next_pending returns None when no pending items."""
+        todo_list = TodoList(
+            items=[
+                TodoItem(step_number=1, description="Step 1", status="completed"),
+                TodoItem(step_number=2, description="Step 2", status="completed"),
+            ]
+        )
+        assert todo_list.next_pending is None
+
+    def test_is_complete_property_when_complete(self):
+        """Test is_complete returns True when all items completed."""
+        todo_list = TodoList(
+            items=[
+                TodoItem(step_number=1, description="Step 1", status="completed"),
+                TodoItem(step_number=2, description="Step 2", status="completed"),
+            ]
+        )
+        assert todo_list.is_complete is True
+
+    def test_is_complete_property_when_not_complete(self, sample_todo_list):
+        """Test is_complete returns False when items are pending."""
+        assert sample_todo_list.is_complete is False
+
+    def test_is_complete_false_for_empty_list(self, empty_todo_list):
+        """Test is_complete returns False for empty list."""
+        assert empty_todo_list.is_complete is False
+
+    def test_pending_count(self, sample_todo_list):
+        """Test pending_count returns correct count."""
+        assert sample_todo_list.pending_count == 2
+
+    def test_completed_count(self, sample_todo_list):
+        """Test completed_count returns correct count."""
+        assert sample_todo_list.completed_count == 1
+
+    def test_get_by_step_number(self, sample_todo_list):
+        """Test get_by_step_number returns correct item."""
+        item = sample_todo_list.get_by_step_number(3)
+        assert item is not None
+        assert item.step_number == 3
+        assert item.description == "Step 3"
+
+    def test_get_by_step_number_returns_none_for_missing(self, sample_todo_list):
+        """Test get_by_step_number returns None for non-existent step."""
+        item = sample_todo_list.get_by_step_number(99)
+        assert item is None
+
+    def test_mark_running(self, sample_todo_list):
+        """Test mark_running changes status correctly."""
+        sample_todo_list.mark_running(3)
+        item = sample_todo_list.get_by_step_number(3)
+        assert item.status == "running"
+
+    def test_mark_running_does_nothing_for_missing(self, sample_todo_list):
+        """Test mark_running handles missing step gracefully."""
+        # Should not raise an error
+        sample_todo_list.mark_running(99)
+
+    def test_mark_completed(self, sample_todo_list):
+        """Test mark_completed changes status correctly."""
+        sample_todo_list.mark_completed(3)
+        item = sample_todo_list.get_by_step_number(3)
+        assert item.status == "completed"
+        assert item.result is None
+
+    def test_mark_completed_with_result(self, sample_todo_list):
+        """Test mark_completed with result."""
+        sample_todo_list.mark_completed(3, result="Task output")
+        item = sample_todo_list.get_by_step_number(3)
+        assert item.status == "completed"
+        assert item.result == "Task output"
+
+    def test_mark_completed_does_nothing_for_missing(self, sample_todo_list):
+        """Test mark_completed handles missing step gracefully."""
+        # Should not raise an error
+        sample_todo_list.mark_completed(99, result="Some result")
+
+    def test_todo_list_workflow(self):
+        """Test a complete workflow through TodoList."""
+        # Create a todo list with 3 items
+        todo_list = TodoList(
+            items=[
+                TodoItem(
+                    step_number=1,
+                    description="Research",
+                    tool_to_use="search_tool",
+                ),
+                TodoItem(
+                    step_number=2,
+                    description="Analyze",
+                    depends_on=[1],
+                ),
+                TodoItem(
+                    step_number=3,
+                    description="Report",
+                    depends_on=[1, 2],
+                ),
+            ]
+        )
+
+        # Initial state
+        assert todo_list.pending_count == 3
+        assert todo_list.completed_count == 0
+        assert todo_list.is_complete is False
+
+        # Start first task
+        todo_list.mark_running(1)
+        assert todo_list.current_todo.step_number == 1
+        assert todo_list.next_pending.step_number == 2
+
+        # Complete first task
+        todo_list.mark_completed(1, result="Research done")
+        assert todo_list.current_todo is None
+        assert todo_list.completed_count == 1
+
+        # Start and complete second task
+        todo_list.mark_running(2)
+        todo_list.mark_completed(2, result="Analysis complete")
+        assert todo_list.completed_count == 2
+
+        # Start and complete third task
+        todo_list.mark_running(3)
+        todo_list.mark_completed(3, result="Report generated")
+
+        # Final state
+        assert todo_list.is_complete is True
+        assert todo_list.pending_count == 0
+        assert todo_list.completed_count == 3
+        assert todo_list.current_todo is None
+        assert todo_list.next_pending is None
+
+
+class TestTodoFromPlanStep:
+    """Tests for converting PlanStep to TodoItem."""
+
+    def test_convert_plan_step_to_todo_item(self):
+        """Test converting a PlanStep to TodoItem."""
+        step = PlanStep(
+            step_number=1,
+            description="Search for information",
+            tool_to_use="search_tool",
+            depends_on=[],
+        )
+
+        todo = TodoItem(
+            step_number=step.step_number,
+            description=step.description,
+            tool_to_use=step.tool_to_use,
+            depends_on=step.depends_on,
+            status="pending",
+        )
+
+        assert todo.step_number == step.step_number
+        assert todo.description == step.description
+        assert todo.tool_to_use == step.tool_to_use
+        assert todo.depends_on == step.depends_on
+        assert todo.status == "pending"
+
+    def test_convert_multiple_plan_steps_to_todo_list(self):
+        """Test converting multiple PlanSteps to a TodoList."""
+        steps = [
+            PlanStep(step_number=1, description="Step 1", tool_to_use="tool1"),
+            PlanStep(step_number=2, description="Step 2", depends_on=[1]),
+            PlanStep(step_number=3, description="Step 3", depends_on=[1, 2]),
+        ]
+
+        todos = []
+        for step in steps:
+            todo = TodoItem(
+                step_number=step.step_number,
+                description=step.description,
+                tool_to_use=step.tool_to_use,
+                depends_on=step.depends_on,
+                status="pending",
+            )
+            todos.append(todo)
+
+        todo_list = TodoList(items=todos)
+
+        assert len(todo_list.items) == 3
+        assert todo_list.pending_count == 3
+        assert todo_list.items[0].tool_to_use == "tool1"
+        assert todo_list.items[1].depends_on == [1]
+        assert todo_list.items[2].depends_on == [1, 2]

lib/crewai/tests/utilities/test_structured_planning.py

@@ -0,0 +1,698 @@
+"""Tests for structured planning with steps and todo generation.
+
+These tests verify that the planning system correctly generates structured
+PlanStep objects and converts them to TodoItems across different LLM providers.
+"""
+
+import json
+import os
+from unittest.mock import MagicMock, Mock, patch
+
+import pytest
+
+from crewai import Agent, PlanningConfig, Task
+from crewai.llm import LLM
+from crewai.utilities.planning_types import PlanStep, TodoItem, TodoList
+from crewai.utilities.reasoning_handler import (
+    FUNCTION_SCHEMA,
+    AgentReasoning,
+    ReasoningPlan,
+)
+
+
+class TestFunctionSchema:
+    """Tests for the FUNCTION_SCHEMA used in structured planning."""
+
+    def test_schema_has_required_structure(self):
+        """Test that FUNCTION_SCHEMA has the correct structure."""
+        assert FUNCTION_SCHEMA["type"] == "function"
+        assert "function" in FUNCTION_SCHEMA
+        assert FUNCTION_SCHEMA["function"]["name"] == "create_reasoning_plan"
+
+    def test_schema_parameters_structure(self):
+        """Test that parameters have correct structure."""
+        params = FUNCTION_SCHEMA["function"]["parameters"]
+        assert params["type"] == "object"
+        assert "properties" in params
+        assert "required" in params
+
+    def test_schema_has_plan_property(self):
+        """Test that schema includes plan property."""
+        props = FUNCTION_SCHEMA["function"]["parameters"]["properties"]
+        assert "plan" in props
+        assert props["plan"]["type"] == "string"
+
+    def test_schema_has_steps_property(self):
+        """Test that schema includes steps array property."""
+        props = FUNCTION_SCHEMA["function"]["parameters"]["properties"]
+        assert "steps" in props
+        assert props["steps"]["type"] == "array"
+
+    def test_schema_steps_items_structure(self):
+        """Test that steps items have correct structure."""
+        items = FUNCTION_SCHEMA["function"]["parameters"]["properties"]["steps"]["items"]
+        assert items["type"] == "object"
+        assert "properties" in items
+        assert "required" in items
+        assert "additionalProperties" in items
+        assert items["additionalProperties"] is False
+
+    def test_schema_step_properties(self):
+        """Test that step items have all required properties."""
+        step_props = FUNCTION_SCHEMA["function"]["parameters"]["properties"]["steps"]["items"]["properties"]
+
+        assert "step_number" in step_props
+        assert step_props["step_number"]["type"] == "integer"
+
+        assert "description" in step_props
+        assert step_props["description"]["type"] == "string"
+
+        assert "tool_to_use" in step_props
+        # tool_to_use should be nullable
+        assert step_props["tool_to_use"]["type"] == ["string", "null"]
+
+        assert "depends_on" in step_props
+        assert step_props["depends_on"]["type"] == "array"
+
+    def test_schema_step_required_fields(self):
+        """Test that step required fields are correct."""
+        required = FUNCTION_SCHEMA["function"]["parameters"]["properties"]["steps"]["items"]["required"]
+        assert "step_number" in required
+        assert "description" in required
+        assert "tool_to_use" in required
+        assert "depends_on" in required
+
+    def test_schema_has_ready_property(self):
+        """Test that schema includes ready property."""
+        props = FUNCTION_SCHEMA["function"]["parameters"]["properties"]
+        assert "ready" in props
+        assert props["ready"]["type"] == "boolean"
+
+    def test_schema_top_level_required(self):
+        """Test that top-level required fields are correct."""
+        required = FUNCTION_SCHEMA["function"]["parameters"]["required"]
+        assert "plan" in required
+        assert "steps" in required
+        assert "ready" in required
+
+    def test_schema_top_level_additional_properties(self):
+        """Test that additionalProperties is False at top level."""
+        params = FUNCTION_SCHEMA["function"]["parameters"]
+        assert params["additionalProperties"] is False
+
+
+class TestReasoningPlan:
+    """Tests for the ReasoningPlan model with structured steps."""
+
+    def test_reasoning_plan_with_empty_steps(self):
+        """Test ReasoningPlan can be created with empty steps."""
+        plan = ReasoningPlan(
+            plan="Simple plan",
+            steps=[],
+            ready=True,
+        )
+
+        assert plan.plan == "Simple plan"
+        assert plan.steps == []
+        assert plan.ready is True
+
+    def test_reasoning_plan_with_steps(self):
+        """Test ReasoningPlan with structured steps."""
+        steps = [
+            PlanStep(step_number=1, description="First step", tool_to_use="tool1"),
+            PlanStep(step_number=2, description="Second step", depends_on=[1]),
+        ]
+
+        plan = ReasoningPlan(
+            plan="Multi-step plan",
+            steps=steps,
+            ready=True,
+        )
+
+        assert plan.plan == "Multi-step plan"
+        assert len(plan.steps) == 2
+        assert plan.steps[0].step_number == 1
+        assert plan.steps[1].depends_on == [1]
+
+
+class TestAgentReasoningWithMockedLLM:
+    """Tests for AgentReasoning with mocked LLM responses."""
+
+    @pytest.fixture
+    def mock_agent(self):
+        """Create a mock agent for testing."""
+        agent = MagicMock()
+        agent.role = "Test Agent"
+        agent.goal = "Test goal"
+        agent.backstory = "Test backstory"
+        agent.verbose = False
+        agent.planning_config = PlanningConfig()
+        agent.i18n = MagicMock()
+        agent.i18n.retrieve.return_value = "Test prompt: {description}"
+        # Mock the llm attribute
+        agent.llm = MagicMock()
+        agent.llm.supports_function_calling.return_value = True
+        return agent
+
+    def test_parse_steps_from_function_response(self, mock_agent):
+        """Test that steps are correctly parsed from LLM function response."""
+        # Mock the LLM response with structured steps
+        mock_response = json.dumps({
+            "plan": "Research and analyze",
+            "steps": [
+                {
+                    "step_number": 1,
+                    "description": "Search for information",
+                    "tool_to_use": "search_tool",
+                    "depends_on": [],
+                },
+                {
+                    "step_number": 2,
+                    "description": "Analyze results",
+                    "tool_to_use": None,
+                    "depends_on": [1],
+                },
+            ],
+            "ready": True,
+        })
+
+        mock_agent.llm.call.return_value = mock_response
+
+        handler = AgentReasoning(
+            agent=mock_agent,
+            task=None,
+            description="Test task",
+            expected_output="Test output",
+        )
+
+        # Call the function parsing method
+        plan, steps, ready = handler._call_with_function(
+            prompt="Test prompt",
+            plan_type="create_plan",
+        )
+
+        assert plan == "Research and analyze"
+        assert len(steps) == 2
+        assert steps[0].step_number == 1
+        assert steps[0].tool_to_use == "search_tool"
+        assert steps[1].depends_on == [1]
+        assert ready is True
+
+    def test_parse_steps_handles_missing_optional_fields(self, mock_agent):
+        """Test that missing optional fields are handled correctly."""
+        mock_response = json.dumps({
+            "plan": "Simple plan",
+            "steps": [
+                {
+                    "step_number": 1,
+                    "description": "Do something",
+                    "tool_to_use": None,
+                    "depends_on": [],
+                },
+            ],
+            "ready": True,
+        })
+
+        mock_agent.llm.call.return_value = mock_response
+
+        handler = AgentReasoning(
+            agent=mock_agent,
+            task=None,
+            description="Test task",
+            expected_output="Test output",
+        )
+
+        plan, steps, ready = handler._call_with_function(
+            prompt="Test prompt",
+            plan_type="create_plan",
+        )
+
+        assert len(steps) == 1
+        assert steps[0].tool_to_use is None
+        assert steps[0].depends_on == []
+
+    def test_parse_steps_with_missing_fields_uses_defaults(self, mock_agent):
+        """Test that steps with missing fields get default values."""
+        mock_response = json.dumps({
+            "plan": "Plan with step missing fields",
+            "steps": [
+                {"step_number": 1, "description": "Valid step", "tool_to_use": None, "depends_on": []},
+                {"step_number": 2},  # Missing description, tool_to_use, depends_on
+                {"step_number": 3, "description": "Another valid", "tool_to_use": None, "depends_on": []},
+            ],
+            "ready": True,
+        })
+
+        mock_agent.llm.call.return_value = mock_response
+
+        handler = AgentReasoning(
+            agent=mock_agent,
+            task=None,
+            description="Test task",
+            expected_output="Test output",
+        )
+
+        plan, steps, ready = handler._call_with_function(
+            prompt="Test prompt",
+            plan_type="create_plan",
+        )
+
+        # All 3 steps should be parsed, with defaults for missing fields
+        assert len(steps) == 3
+        assert steps[0].step_number == 1
+        assert steps[0].description == "Valid step"
+        assert steps[1].step_number == 2
+        assert steps[1].description == ""  # Default value
+        assert steps[2].step_number == 3
+
+
+class TestTodoCreationFromPlan:
+    """Tests for converting plan steps to todo items."""
+
+    def test_create_todos_from_plan_steps(self):
+        """Test creating TodoList from PlanSteps."""
+        steps = [
+            PlanStep(
+                step_number=1,
+                description="Research competitors",
+                tool_to_use="search_tool",
+                depends_on=[],
+            ),
+            PlanStep(
+                step_number=2,
+                description="Analyze data",
+                tool_to_use=None,
+                depends_on=[1],
+            ),
+            PlanStep(
+                step_number=3,
+                description="Generate report",
+                tool_to_use="write_tool",
+                depends_on=[1, 2],
+            ),
+        ]
+
+        # Convert steps to todos (mirroring agent_executor._create_todos_from_plan)
+        todos = []
+        for step in steps:
+            todo = TodoItem(
+                step_number=step.step_number,
+                description=step.description,
+                tool_to_use=step.tool_to_use,
+                depends_on=step.depends_on,
+                status="pending",
+            )
+            todos.append(todo)
+
+        todo_list = TodoList(items=todos)
+
+        assert len(todo_list.items) == 3
+        assert todo_list.pending_count == 3
+        assert todo_list.completed_count == 0
+
+        # Verify todo properties match step properties
+        assert todo_list.items[0].description == "Research competitors"
+        assert todo_list.items[0].tool_to_use == "search_tool"
+        assert todo_list.items[1].depends_on == [1]
+        assert todo_list.items[2].depends_on == [1, 2]
+
+
+# =============================================================================
+# Provider-Specific Integration Tests (VCR recorded)
+# =============================================================================
+
+
+# Common test tools used across provider tests
+def create_research_tools():
+    """Create research tools for testing structured planning."""
+    from crewai.tools import tool
+
+    @tool
+    def web_search(query: str) -> str:
+        """Search the web for information on a given topic.
+
+        Args:
+            query: The search query to look up.
+
+        Returns:
+            Search results as a string.
+        """
+        # Simulated search results for testing
+        return f"Search results for '{query}': Found 3 relevant articles about the topic including market analysis, competitor data, and industry trends."
+
+    @tool
+    def read_website(url: str) -> str:
+        """Read and extract content from a website URL.
+
+        Args:
+            url: The URL of the website to read.
+
+        Returns:
+            The extracted content from the website.
+        """
+        # Simulated website content for testing
+        return f"Content from {url}: This article discusses key insights about the topic including market size ($50B), growth rate (15% YoY), and major players in the industry."
+
+    @tool
+    def generate_report(title: str, findings: str) -> str:
+        """Generate a structured report based on research findings.
+
+        Args:
+            title: The title of the report.
+            findings: The research findings to include.
+
+        Returns:
+            A formatted report string.
+        """
+        return f"# {title}\n\n## Executive Summary\n{findings}\n\n## Conclusion\nBased on the analysis, the market shows strong growth potential."
+
+    return web_search, read_website, generate_report
+
+
+RESEARCH_TASK = """Research the current state of the AI agent market:
+1. Search for recent information about AI agents and their market trends
+2. Read detailed content from a relevant industry source
+3. Generate a brief report summarizing the key findings
+
+Use the available tools for each step."""
+
+
+class TestOpenAIStructuredPlanning:
+    """Integration tests for OpenAI structured planning with research workflow."""
+
+    @pytest.mark.vcr()
+    def test_openai_research_workflow_generates_steps(self):
+        """Test that OpenAI generates structured plan steps for a research task."""
+        web_search, read_website, generate_report = create_research_tools()
+        llm = LLM(model="gpt-4o")
+
+        agent = Agent(
+            role="Research Analyst",
+            goal="Conduct thorough research and produce insightful reports",
+            backstory="An experienced analyst skilled at gathering information and synthesizing findings into actionable insights.",
+            llm=llm,
+            tools=[web_search, read_website, generate_report],
+            planning_config=PlanningConfig(max_attempts=1),
+            verbose=False,
+        )
+
+        result = agent.kickoff(RESEARCH_TASK)
+
+        # Verify result exists
+        assert result is not None
+        assert result.raw is not None
+        # The result should contain some report-like content
+        assert len(str(result.raw)) > 50
+
+
+class TestAnthropicStructuredPlanning:
+    """Integration tests for Anthropic structured planning with research workflow."""
+
+    @pytest.fixture(autouse=True)
+    def mock_anthropic_api_key(self):
+        """Mock API key if not set."""
+        if "ANTHROPIC_API_KEY" not in os.environ:
+            with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+                yield
+        else:
+            yield
+
+    @pytest.mark.vcr()
+    def test_anthropic_research_workflow_generates_steps(self):
+        """Test that Anthropic generates structured plan steps for a research task."""
+        web_search, read_website, generate_report = create_research_tools()
+        llm = LLM(model="anthropic/claude-sonnet-4-20250514")
+
+        agent = Agent(
+            role="Research Analyst",
+            goal="Conduct thorough research and produce insightful reports",
+            backstory="An experienced analyst skilled at gathering information and synthesizing findings into actionable insights.",
+            llm=llm,
+            tools=[web_search, read_website, generate_report],
+            planning_config=PlanningConfig(max_attempts=1),
+            verbose=False,
+        )
+
+        result = agent.kickoff(RESEARCH_TASK)
+
+        # Verify result exists
+        assert result is not None
+        assert result.raw is not None
+        # The result should contain some report-like content
+        assert len(str(result.raw)) > 50
+
+
+class TestGeminiStructuredPlanning:
+    """Integration tests for Google Gemini structured planning with research workflow."""
+
+    @pytest.fixture(autouse=True)
+    def mock_google_api_key(self):
+        """Mock API key if not set."""
+        if "GOOGLE_API_KEY" not in os.environ and "GEMINI_API_KEY" not in os.environ:
+            with patch.dict(os.environ, {"GOOGLE_API_KEY": "test-key"}):
+                yield
+        else:
+            yield
+
+    @pytest.mark.vcr()
+    def test_gemini_research_workflow_generates_steps(self):
+        """Test that Gemini generates structured plan steps for a research task."""
+        web_search, read_website, generate_report = create_research_tools()
+        llm = LLM(model="gemini/gemini-2.5-flash")
+
+        agent = Agent(
+            role="Research Analyst",
+            goal="Conduct thorough research and produce insightful reports",
+            backstory="An experienced analyst skilled at gathering information and synthesizing findings into actionable insights.",
+            llm=llm,
+            tools=[web_search, read_website, generate_report],
+            planning_config=PlanningConfig(max_attempts=1),
+            verbose=False,
+        )
+
+        result = agent.kickoff(RESEARCH_TASK)
+
+        # Verify result exists
+        assert result is not None
+        assert result.raw is not None
+        # The result should contain some report-like content
+        assert len(str(result.raw)) > 50
+
+
+class TestAzureStructuredPlanning:
+    """Integration tests for Azure OpenAI structured planning with research workflow."""
+
+    @pytest.fixture(autouse=True)
+    def mock_azure_credentials(self):
+        """Mock Azure credentials for tests."""
+        if "AZURE_API_KEY" not in os.environ:
+            with patch.dict(os.environ, {
+                "AZURE_API_KEY": "test-key",
+                "AZURE_ENDPOINT": "https://test.openai.azure.com"
+            }):
+                yield
+        else:
+            yield
+
+    @pytest.mark.vcr()
+    def test_azure_research_workflow_generates_steps(self):
+        """Test that Azure OpenAI generates structured plan steps for a research task."""
+        web_search, read_website, generate_report = create_research_tools()
+        llm = LLM(model="azure/gpt-4o")
+
+        agent = Agent(
+            role="Research Analyst",
+            goal="Conduct thorough research and produce insightful reports",
+            backstory="An experienced analyst skilled at gathering information and synthesizing findings into actionable insights.",
+            llm=llm,
+            tools=[web_search, read_website, generate_report],
+            planning_config=PlanningConfig(max_attempts=1),
+            verbose=False,
+        )
+
+        result = agent.kickoff(RESEARCH_TASK)
+
+        # Verify result exists
+        assert result is not None
+        assert result.raw is not None
+        # The result should contain some report-like content
+        assert len(str(result.raw)) > 50
+
+
+# =============================================================================
+# Unit Tests with Mocked LLM Providers
+# =============================================================================
+
+
+class TestStructuredPlanningWithMockedProviders:
+    """Unit tests with mocked LLM providers for faster execution."""
+
+    def _create_mock_plan_response(self, steps_data):
+        """Helper to create mock plan response."""
+        return json.dumps({
+            "plan": "Test plan",
+            "steps": steps_data,
+            "ready": True,
+        })
+
+    def test_openai_mock_structured_response(self):
+        """Test parsing OpenAI structured response."""
+        steps_data = [
+            {"step_number": 1, "description": "Search", "tool_to_use": "search", "depends_on": []},
+            {"step_number": 2, "description": "Analyze", "tool_to_use": None, "depends_on": [1]},
+        ]
+
+        response = self._create_mock_plan_response(steps_data)
+        parsed = json.loads(response)
+
+        assert len(parsed["steps"]) == 2
+        assert parsed["steps"][0]["tool_to_use"] == "search"
+        assert parsed["steps"][1]["depends_on"] == [1]
+
+    def test_anthropic_mock_structured_response(self):
+        """Test parsing Anthropic structured response (same format)."""
+        steps_data = [
+            {"step_number": 1, "description": "Research", "tool_to_use": "web_search", "depends_on": []},
+            {"step_number": 2, "description": "Summarize", "tool_to_use": None, "depends_on": [1]},
+            {"step_number": 3, "description": "Report", "tool_to_use": "write_file", "depends_on": [1, 2]},
+        ]
+
+        response = self._create_mock_plan_response(steps_data)
+        parsed = json.loads(response)
+
+        assert len(parsed["steps"]) == 3
+        assert parsed["steps"][2]["depends_on"] == [1, 2]
+
+    def test_gemini_mock_structured_response(self):
+        """Test parsing Gemini structured response (same format)."""
+        steps_data = [
+            {"step_number": 1, "description": "Gather data", "tool_to_use": "data_tool", "depends_on": []},
+            {"step_number": 2, "description": "Process", "tool_to_use": None, "depends_on": [1]},
+        ]
+
+        response = self._create_mock_plan_response(steps_data)
+        parsed = json.loads(response)
+
+        assert len(parsed["steps"]) == 2
+        assert parsed["ready"] is True
+
+    def test_azure_mock_structured_response(self):
+        """Test parsing Azure OpenAI structured response (same format as OpenAI)."""
+        steps_data = [
+            {"step_number": 1, "description": "Initialize", "tool_to_use": None, "depends_on": []},
+            {"step_number": 2, "description": "Execute", "tool_to_use": "executor", "depends_on": [1]},
+            {"step_number": 3, "description": "Finalize", "tool_to_use": None, "depends_on": [1, 2]},
+        ]
+
+        response = self._create_mock_plan_response(steps_data)
+        parsed = json.loads(response)
+
+        assert len(parsed["steps"]) == 3
+        assert parsed["steps"][0]["tool_to_use"] is None
+
+
+class TestTodoListIntegration:
+    """Integration tests for TodoList with plan execution simulation."""
+
+    def test_full_plan_execution_workflow(self):
+        """Test complete workflow from plan to todos to execution."""
+        # Simulate plan steps from LLM
+        plan_steps = [
+            PlanStep(
+                step_number=1,
+                description="Research the topic",
+                tool_to_use="search_tool",
+                depends_on=[],
+            ),
+            PlanStep(
+                step_number=2,
+                description="Compile findings",
+                tool_to_use=None,
+                depends_on=[1],
+            ),
+            PlanStep(
+                step_number=3,
+                description="Generate summary",
+                tool_to_use="summarize_tool",
+                depends_on=[1, 2],
+            ),
+        ]
+
+        # Convert to todos (like agent_executor._create_todos_from_plan)
+        todos = [
+            TodoItem(
+                step_number=step.step_number,
+                description=step.description,
+                tool_to_use=step.tool_to_use,
+                depends_on=step.depends_on,
+                status="pending",
+            )
+            for step in plan_steps
+        ]
+        todo_list = TodoList(items=todos)
+
+        # Verify initial state
+        assert todo_list.pending_count == 3
+        assert todo_list.is_complete is False
+
+        # Simulate execution
+        for i in range(1, 4):
+            todo_list.mark_running(i)
+            assert todo_list.current_todo.step_number == i
+            todo_list.mark_completed(i, result=f"Step {i} completed")
+
+        # Verify final state
+        assert todo_list.is_complete is True
+        assert todo_list.completed_count == 3
+        assert all(item.result is not None for item in todo_list.items)
+
+    def test_dependency_aware_execution(self):
+        """Test that dependencies are respected in execution order."""
+        steps = [
+            PlanStep(step_number=1, description="Base step", depends_on=[]),
+            PlanStep(step_number=2, description="Depends on 1", depends_on=[1]),
+            PlanStep(step_number=3, description="Depends on 1", depends_on=[1]),
+            PlanStep(step_number=4, description="Depends on 2 and 3", depends_on=[2, 3]),
+        ]
+
+        todos = [
+            TodoItem(
+                step_number=s.step_number,
+                description=s.description,
+                depends_on=s.depends_on,
+            )
+            for s in steps
+        ]
+        todo_list = TodoList(items=todos)
+
+        # Helper to check if dependencies are satisfied
+        def can_execute(todo: TodoItem) -> bool:
+            for dep in todo.depends_on:
+                dep_todo = todo_list.get_by_step_number(dep)
+                if dep_todo and dep_todo.status != "completed":
+                    return False
+            return True
+
+        # Step 1 has no dependencies
+        assert can_execute(todo_list.items[0]) is True
+
+        # Steps 2 and 3 depend on 1 (not yet done)
+        assert can_execute(todo_list.items[1]) is False
+        assert can_execute(todo_list.items[2]) is False
+
+        # Complete step 1
+        todo_list.mark_completed(1)
+
+        # Now steps 2 and 3 can execute
+        assert can_execute(todo_list.items[1]) is True
+        assert can_execute(todo_list.items[2]) is True
+
+        # Step 4 still can't (depends on 2 and 3)
+        assert can_execute(todo_list.items[3]) is False
+
+        # Complete steps 2 and 3
+        todo_list.mark_completed(2)
+        todo_list.mark_completed(3)
+
+        # Now step 4 can execute
+        assert can_execute(todo_list.items[3]) is True

uv.lock

@@ -1096,6 +1096,7 @@ dependencies = [
     { name = "appdirs" },
     { name = "chromadb" },
     { name = "click" },
+    { name = "httpx" },
     { name = "instructor" },
     { name = "json-repair" },
     { name = "json5" },
@@ -1195,6 +1196,7 @@ requires-dist = [
     { name = "crewai-tools", marker = "extra == 'tools'", editable = "lib/crewai-tools" },
     { name = "docling", marker = "extra == 'docling'", specifier = "~=2.63.0" },
     { name = "google-genai", marker = "extra == 'google-genai'", specifier = "~=1.49.0" },
+    { name = "httpx", specifier = "~=0.28.1" },
     { name = "httpx-auth", marker = "extra == 'a2a'", specifier = "~=0.23.1" },
     { name = "httpx-sse", marker = "extra == 'a2a'", specifier = "~=0.4.0" },
     { name = "ibm-watsonx-ai", marker = "extra == 'watson'", specifier = "~=1.3.39" },