Add lead scoring FlowDefinition example

* Enhance JSON crew project handling and validation

- Updated `create_json_crew.py` to specify input files with a brief path.
- Refactored `crew_loader.py` to improve agent and task loading logic, including the introduction of a `build_agent` function and better handling of task classes.
- Enhanced `json_loader.py` with additional validation for agent and task definitions, including support for Python references and conditional tasks.
- Added tests in `test_crew_loader.py` and `test_json_loader.py` to ensure proper loading of agents, tasks, and validation of project structures, including custom types and conditional tasks.
- Improved error handling and validation safety across the project loading process.

* Enhance JSON crew configuration options in create_json_crew.py

- Added optional fields for custom agent subclasses and advanced task options, including condition checks and output specifications.
- Improved documentation comments for better clarity on agent and task configurations.
- Updated JSON crew handling to support additional callbacks for pre- and post-execution processes.

* Enhance JSON crew template tests in test_create_crew.py

- Added assertions for new optional fields in crew and agent templates, including conditional tasks, custom converters, and input file specifications.
- Improved validation checks for manager agents and callback references to ensure proper configuration in JSON crew definitions.
- Expanded documentation references within the tests to provide clearer guidance on the expected structure and usage of crew templates.

* Fix JSON crew PR review issues

.gitignore

@@ -31,3 +31,5 @@ chromadb-*.lock
 blogs/*
 secrets/*
 UNKNOWN.egg-info/
+demos/*
+.crewai/*

docs/ar/changelog.mdx

@@ -4,6 +4,55 @@ description: "تحديثات المنتج والتحسينات وإصلاحات
 icon: "clock"
 mode: "wide"
 ---
+<Update label="11 يونيو 2026">
+  ## v1.14.7
+
+  [عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7)
+
+  ## ما الذي تغير
+
+  ### الميزات
+  - إضافة واجهات خلفية افتراضية قابلة للتوصيل للذاكرة، والمعرفة، وrag، وflow.
+  - عرض السبب الحقيقي للإنهاء، ومعلمات العينة، وresponse.id في أحداث LLM.
+  - تصنيف مشغلات DSL كزخارف واعية للمسار.
+  - إضافة واجهة برمجة تطبيقات الدردشة لتدفقات المحادثة.
+  - جعل واجهة القفل قابلة للتجاوز.
+  - بناء FlowDefinition من بيانات التعريف الخاصة بـ Flow DSL.
+  - إضافة مزود LLM من Snowflake Cortex الأصلي.
+  - إضافة دعم لملفات الوكلاء المدربين من crew.
+
+  ### إصلاحات الأخطاء
+  - إصلاح نقطة التحقق لإعادة بناء BaseLLM مخصص كـ LLM ملموس عند الاستعادة.
+  - تقييد الاستعادة على علامة لمنع اللقطات الحية من إعادة التشغيل كاستئناف.
+  - تحديد حالة وقت التشغيل لكل تشغيل للحد من النمو وعزل التشغيل المتزامن.
+  - إصلاح إعدادات التتبع على crewai-login.
+  - احترام suppress_flow_events لأحداث تنفيذ الطريقة.
+  - استعادة [project.scripts] في حزمة crewai لتثبيت أداة uv.
+  - حل مشكلات CVE الخاصة بـ pip-audit لـ aiohttp وdocling وdocling-core.
+  - إصلاح إدخال الملفات الذي لا يعمل بشكل موثوق.
+  - إصلاح تاريخ نتائج أدوات Snowflake Claude غير المكتملة.
+
+  ### الوثائق
+  - تحديث سجل التغييرات والإصدار لـ v1.14.7.
+  - تحديث وثائق جامع OpenTelemetry.
+  - تحديث دليل NVIDIA Nemotron LLM.
+  - إضافة دليل تكامل Databricks.
+  - إضافة دليل تكامل Snowflake.
+
+  ### الأداء
+  - تحسين سرعة استيراد crewai من خلال تحميل مستندات docling بشكل كسول.
+
+  ### إعادة الهيكلة
+  - تبسيط تقييم شروط التدفق ليكون بلا حالة لكل حدث.
+  - فصل منطق المحادثة عن وقت التشغيل وإضافة تعريف المحادثة.
+  - تقسيم `flow.py` إلى DSL، وتعريف، ووقت تشغيل.
+
+  ## المساهمون
+
+  @Luzk, @alex-clawd, @devin-ai-integration[bot], @greysonlalonde, @gvieira, @jessemiller, @lorenzejay, @lucasgomide, @mattatcha, @vinibrsl
+
+</Update>
+
 <Update label="10 يونيو 2026">
   ## v1.14.7rc2
 

docs/ar/concepts/flows.mdx

@@ -226,6 +226,48 @@ counter=2 message='Hello from first_method - updated by second_method'
 من خلال ضمان إعادة مخرجات الدالة الأخيرة وتوفير الوصول إلى الحالة، تجعل تدفقات CrewAI من السهل دمج نتائج سير عمل الذكاء الاصطناعي في التطبيقات أو الأنظمة الأكبر،
 مع الحفاظ على الوصول إلى الحالة طوال تنفيذ التدفق.
 
+## مقاييس استخدام التدفق
+
+بعد اكتمال تنفيذ التدفق، يمكنك الوصول إلى الخاصية `usage_metrics` لعرض إجمالي استخدام التوكنات عبر **كل استدعاء لنموذج اللغة** يتم خلال التشغيل — بما في ذلك الاستدعاءات من كل فريق (Crew) ينظمه التدفق، والاستدعاءات داخل أدوات الـ Agents، والاستدعاءات المباشرة لـ `LLM.call(...)` من دوال التدفق. هذا هو المكافئ على جانب الـ SDK للإجماليات المعروضة في واجهة CrewAI Enterprise.
+
+```python Code
+from crewai import LLM
+from crewai.flow.flow import Flow, listen, start
+
+class UsageMetricsFlow(Flow):
+    @start()
+    def run_first_crew(self):
+        self.state.first_result = FirstCrew().crew().kickoff()
+
+    @listen(run_first_crew)
+    def call_llm_directly(self):
+        # استدعاء مباشر لنموذج اللغة — يُحسب أيضًا ضمن flow.usage_metrics
+        llm = LLM(model="openai/gpt-4o-mini")
+        self.state.summary = llm.call("لخّص النقاط الرئيسية.")
+
+    @listen(call_llm_directly)
+    def run_second_crew(self):
+        self.state.second_result = SecondCrew().crew().kickoff()
+
+flow = UsageMetricsFlow()
+flow.kickoff()
+
+print(flow.usage_metrics)
+# UsageMetrics(total_tokens=8579, prompt_tokens=6210, completion_tokens=2369,
+#              cached_prompt_tokens=0, reasoning_tokens=0,
+#              cache_creation_tokens=0, successful_requests=5)
+```
+
+<Note>
+  `flow.usage_metrics` **ليست** نفس `flow.kickoff().token_usage`. هذه الأخيرة
+  ترجع فقط `CrewOutput.token_usage` لـ **آخر** دالة `@listen` أعادت
+  `CrewOutput`، مما يعني أنها تعكس فقط الفريق الأخير وتتجاهل الفرق السابقة
+  وكذلك أي استدعاءات مباشرة لـ `LLM.call(...)`. استخدم `flow.usage_metrics`
+  كلما احتجت إلى الإجمالي **الكامل** للتوكنات لتنفيذ التدفق.
+</Note>
+
+كل حقل في [`UsageMetrics`](https://github.com/crewAIInc/crewAI/blob/main/lib/crewai/src/crewai/types/usage_metrics.py) المُعاد هو مجموع جميع استدعاءات نموذج اللغة التي حدثت خلال استدعاء واحد لـ `flow.kickoff()`. تتم إعادة تعيين العدادات عند الاستدعاء التالي لـ `kickoff()` (وفي كل تكرار من `kickoff_for_each`)، لذلك لن تتكرر العدّات عبر التشغيلات المتتالية. يمكن قراءة هذه الخاصية بأمان في أي وقت بعد اكتمال `kickoff()`؛ قراءتها أثناء التنفيذ تُرجع المجموع الجزئي المتراكم حتى تلك اللحظة.
+
 ## إدارة حالة التدفق
 
 إدارة الحالة بفعالية أمر بالغ الأهمية لبناء سير عمل ذكاء اصطناعي موثوق وقابل للصيانة. توفر تدفقات CrewAI آليات قوية لإدارة الحالة غير المهيكلة والمهيكلة،

docs/en/changelog.mdx

@@ -4,6 +4,55 @@ description: "Product updates, improvements, and bug fixes for CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="Jun 11, 2026">
+  ## v1.14.7
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7)
+
+  ## What's Changed
+
+  ### Features
+  - Add pluggable default backends for memory, knowledge, rag, and flow.
+  - Surface real finish_reason, sampling params, and response.id on LLM events.
+  - Type DSL triggers as route-aware decorators.
+  - Add chat API for conversational flows.
+  - Make locking backend overridable.
+  - Build FlowDefinition from Flow DSL metadata.
+  - Add native Snowflake Cortex LLM provider.
+  - Add crew trained agents file support.
+
+  ### Bug Fixes
+  - Fix checkpoint to rebuild custom BaseLLM as concrete LLM on restore.
+  - Gate restore on a flag to prevent live snapshots from replaying as resume.
+  - Scope runtime state per run to bound growth and isolate concurrent runs.
+  - Fix telemetry setup on crewai-login.
+  - Respect suppress_flow_events for method-execution events.
+  - Restore [project.scripts] in crewai package for uv tool install.
+  - Resolve pip-audit CVEs for aiohttp, docling, and docling-core.
+  - Fix file input not working reliably.
+  - Fix Snowflake Claude incomplete tool result histories.
+
+  ### Documentation
+  - Update changelog and version for v1.14.7.
+  - Update OpenTelemetry collector documentation.
+  - Update NVIDIA Nemotron LLM guide.
+  - Add Databricks integration guide.
+  - Add Snowflake integration guide.
+
+  ### Performance
+  - Improve crewai import speed by lazy-loading docling imports.
+
+  ### Refactoring
+  - Simplify flow condition evaluation to be stateless per event.
+  - Decouple convo logic from runtime and add a conversational_definition.
+  - Split `flow.py` into DSL, definition, and runtime.
+
+  ## Contributors
+
+  @Luzk, @alex-clawd, @devin-ai-integration[bot], @greysonlalonde, @gvieira, @jessemiller, @lorenzejay, @lucasgomide, @mattatcha, @vinibrsl
+
+</Update>
+
 <Update label="Jun 10, 2026">
   ## v1.14.7rc2
 

docs/en/concepts/flows.mdx

@@ -226,6 +226,49 @@ After the Flow has run, you can access the final state to see the updates made b
 By ensuring that the final method's output is returned and providing access to the state, CrewAI Flows make it easy to integrate the results of your AI workflows into larger applications or systems,
 while also maintaining and accessing the state throughout the Flow's execution.
 
+## Flow Usage Metrics
+
+After a Flow execution completes, you can access the `usage_metrics` property to view aggregated token usage across **every LLM call** made during the run — including calls from every Crew the Flow orchestrated, calls inside Agent tools, and bare `LLM.call(...)` invocations from Flow methods. This is the SDK-side equivalent of the totals shown in the CrewAI Enterprise UI.
+
+```python Code
+from crewai import LLM
+from crewai.flow.flow import Flow, listen, start
+
+class UsageMetricsFlow(Flow):
+    @start()
+    def run_first_crew(self):
+        self.state.first_result = FirstCrew().crew().kickoff()
+
+    @listen(run_first_crew)
+    def call_llm_directly(self):
+        # Bare LLM call — still counted by flow.usage_metrics
+        llm = LLM(model="openai/gpt-4o-mini")
+        self.state.summary = llm.call("Summarize the key takeaways.")
+
+    @listen(call_llm_directly)
+    def run_second_crew(self):
+        self.state.second_result = SecondCrew().crew().kickoff()
+
+flow = UsageMetricsFlow()
+flow.kickoff()
+
+print(flow.usage_metrics)
+# UsageMetrics(total_tokens=8579, prompt_tokens=6210, completion_tokens=2369,
+#              cached_prompt_tokens=0, reasoning_tokens=0,
+#              cache_creation_tokens=0, successful_requests=5)
+```
+
+<Note>
+  `flow.usage_metrics` is **not** the same as `flow.kickoff().token_usage`. The
+  latter returns the `CrewOutput.token_usage` of the **last** `@listen` method
+  that returned a `CrewOutput`, which means it only reflects the final Crew and
+  ignores prior Crews and bare `LLM.call(...)` invocations entirely. Use
+  `flow.usage_metrics` whenever you need the **full** token rollup for the Flow
+  execution.
+</Note>
+
+Each entry in the returned [`UsageMetrics`](https://github.com/crewAIInc/crewAI/blob/main/lib/crewai/src/crewai/types/usage_metrics.py) is the sum across all LLM calls made within a single `flow.kickoff()` invocation. Counters reset on the next `kickoff()` call (or on each iteration of `kickoff_for_each`), so successive runs don't double-count. The property is safe to read at any point after `kickoff()` completes; reading it during execution returns the partial total accumulated so far.
+
 ## Flow State Management
 
 Managing state effectively is crucial for building reliable and maintainable AI workflows. CrewAI Flows provides robust mechanisms for both unstructured and structured state management,

docs/en/concepts/memory.mdx

@@ -101,7 +101,7 @@ crew = Crew(
 )
 ```
 
-When `memory=True`, the crew creates a default `Memory()` and passes the crew's `embedder` configuration through automatically. All agents in the crew share the crew's memory unless an agent has its own.
+When `memory=True`, the crew creates a default `Memory()` and passes the crew's `embedder` configuration through automatically. All agents in the crew share the crew's memory unless an agent has its own. Without a custom `embedder`, memory uses OpenAI `text-embedding-3-large` embeddings.
 
 After each task, the crew automatically extracts discrete facts from the task output and stores them. Before each task, the agent recalls relevant context from memory and injects it into the task prompt.
 
@@ -515,7 +515,11 @@ memory = Memory(
 
 ## Embedder Configuration
 
-Memory needs an embedding model to convert text into vectors for semantic search. You can configure this in three ways.
+Memory needs an embedding model to convert text into vectors for semantic search. By default, `Memory()` uses OpenAI `text-embedding-3-large` embeddings, which produce 3072-dimensional vectors. Set `OPENAI_API_KEY` for the default path, or configure a custom embedder in one of three ways.
+
+<Warning>
+Existing local memory stores created with 1536-dimensional embeddings, such as `text-embedding-3-small` or `text-embedding-ada-002`, may not be compatible with the `text-embedding-3-large` default. This applies to both the OpenAI and Azure OpenAI providers — Azure's default embedding model also changed from `text-embedding-ada-002` to `text-embedding-3-large`. If local testing fails with an embedding dimension mismatch, reset memory with `crewai reset-memories -m`, delete the local memory storage directory, or explicitly configure the older embedder model until you migrate.
+</Warning>
 
 ### Passing to Memory Directly
 
@@ -523,7 +527,7 @@ Memory needs an embedding model to convert text into vectors for semantic search
 from crewai import Memory
 
 # As a config dict
-memory = Memory(embedder={"provider": "openai", "config": {"model_name": "text-embedding-3-small"}})
+memory = Memory(embedder={"provider": "openai", "config": {"model_name": "text-embedding-3-large"}})
 
 # As a pre-built callable
 from crewai.rag.embeddings.factory import build_embedder
@@ -542,7 +546,7 @@ crew = Crew(
     agents=[...],
     tasks=[...],
     memory=True,
-    embedder={"provider": "openai", "config": {"model_name": "text-embedding-3-small"}},
+    embedder={"provider": "openai", "config": {"model_name": "text-embedding-3-large"}},
 )
 ```
 
@@ -554,7 +558,7 @@ crew = Crew(
 memory = Memory(embedder={
     "provider": "openai",
     "config": {
-        "model_name": "text-embedding-3-small",
+        "model_name": "text-embedding-3-large",
         # "api_key": "sk-...",  # or set OPENAI_API_KEY env var
     },
 })
@@ -701,9 +705,9 @@ memory = Memory(embedder=my_embedder)
 
 | Provider | Key | Typical Model | Notes |
 | :--- | :--- | :--- | :--- |
-| OpenAI | `openai` | `text-embedding-3-small` | Default. Set `OPENAI_API_KEY`. |
+| OpenAI | `openai` | `text-embedding-3-large` | Default. Set `OPENAI_API_KEY`. |
 | Ollama | `ollama` | `mxbai-embed-large` | Local, no API key needed. |
-| Azure OpenAI | `azure` | `text-embedding-ada-002` | Requires `deployment_id`. |
+| Azure OpenAI | `azure` | `text-embedding-3-large` | Default model. Requires `deployment_id`. |
 | Google AI | `google-generativeai` | `gemini-embedding-001` | Set `GOOGLE_API_KEY`. |
 | Google Vertex | `google-vertex` | `gemini-embedding-001` | Requires `project_id`. |
 | Cohere | `cohere` | `embed-english-v3.0` | Strong multilingual support. |
@@ -836,6 +840,9 @@ class MemoryMonitor(BaseEventListener):
 **Background save errors in logs?**
 - Memory saves run in a background thread. Errors are emitted as `MemorySaveFailedEvent` but don't crash the agent. Check logs for the root cause (usually LLM or embedder connection issues).
 
+**Embedding dimension mismatch?**
+- Existing local memory stores may have been created with a different embedding model. The default OpenAI memory embedder is now `text-embedding-3-large` (3072 dimensions), while older stores commonly used 1536-dimensional embeddings. For local testing, run `crewai reset-memories -m`, delete the local memory storage directory, or configure the previous embedder model explicitly.
+
 **Concurrent write conflicts?**
 - LanceDB operations are serialized with a shared lock and retried automatically on conflict. This handles multiple `Memory` instances pointing at the same database (e.g. agent memory + crew memory). No action needed.
 
@@ -862,7 +869,7 @@ All configuration is passed as keyword arguments to `Memory(...)`. Every paramet
 | :--- | :--- | :--- |
 | `llm` | `"gpt-4o-mini"` | LLM for analysis (model name or `BaseLLM` instance). |
 | `storage` | `"lancedb"` | Storage backend (`"lancedb"`, a path string, or a `StorageBackend` instance). |
-| `embedder` | `None` (OpenAI default) | Embedder (config dict, callable, or `None` for default OpenAI). |
+| `embedder` | `None` (OpenAI `text-embedding-3-large`) | Embedder (config dict, callable, or `None` for default OpenAI). |
 | `recency_weight` | `0.3` | Weight for recency in composite score. |
 | `semantic_weight` | `0.5` | Weight for semantic similarity in composite score. |
 | `importance_weight` | `0.2` | Weight for importance in composite score. |

docs/en/guides/migration/upgrading-crewai.mdx

@@ -141,7 +141,7 @@ crew = Crew(
     process=Process.sequential,   # or Process.hierarchical
     memory=True,
     cache=True,
-    embedder={"provider": "openai", "config": {"model": "text-embedding-3-small"}},
+    embedder={"provider": "openai", "config": {"model": "text-embedding-3-large"}},
 )
 ```
 
@@ -173,7 +173,7 @@ write = Task(
 
 ### Memory & embedder config {#memory-embedder-config}
 
-If `memory=True` and you're not using the default OpenAI embeddings, you must pass an `embedder`:
+If `memory=True` and you're not using the default OpenAI `text-embedding-3-large` embeddings, you must pass an `embedder`:
 
 ```python
 crew = Crew(
@@ -187,4 +187,4 @@ crew = Crew(
 )
 ```
 
-Set the relevant provider credentials (`OPENAI_API_KEY`, `OLLAMA_HOST`, etc.) in your `.env` file. Memory storage paths are project-local by default — delete the project's memory directory if you change embedders, since dimensions don't mix.
+Set the relevant provider credentials (`OPENAI_API_KEY`, `OLLAMA_HOST`, etc.) in your `.env` file. Memory storage paths are project-local by default. Existing local memory stores created with 1536-dimensional embeddings may not be compatible with the default OpenAI `text-embedding-3-large` embedder, which uses 3072 dimensions. If you hit a dimension mismatch, delete the project's memory directory, run `crewai reset-memories -m`, or explicitly configure the older embedder model until you migrate.

docs/ko/changelog.mdx

@@ -4,6 +4,55 @@ description: "CrewAI의 제품 업데이트, 개선 사항 및 버그 수정"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="2026년 6월 11일">
+  ## v1.14.7
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7)
+
+  ## 변경 사항
+
+  ### 기능
+  - 메모리, 지식, RAG 및 흐름에 대한 플러그 가능한 기본 백엔드를 추가했습니다.
+  - LLM 이벤트에서 실제 finish_reason, 샘플링 매개변수 및 response.id를 표시합니다.
+  - 경로 인식 장식자로서의 타입 DSL 트리거를 설정합니다.
+  - 대화 흐름을 위한 채팅 API를 추가했습니다.
+  - 잠금 백엔드를 재정의 가능하도록 만듭니다.
+  - Flow DSL 메타데이터에서 FlowDefinition을 빌드합니다.
+  - 네이티브 Snowflake Cortex LLM 공급자를 추가했습니다.
+  - 훈련된 에이전트 파일 지원을 추가했습니다.
+
+  ### 버그 수정
+  - 복원 시 사용자 정의 BaseLLM을 구체적인 LLM으로 재구성하도록 체크포인트를 수정했습니다.
+  - 라이브 스냅샷이 재개로 재생되지 않도록 플래그를 사용하여 복원을 제한합니다.
+  - 실행마다 런타임 상태의 범위를 설정하여 성장을 제한하고 동시 실행을 격리합니다.
+  - crewai-login에서 텔레메트리 설정을 수정했습니다.
+  - 메서드 실행 이벤트에 대해 suppress_flow_events를 존중합니다.
+  - uv 도구 설치를 위해 crewai 패키지에서 [project.scripts]를 복원합니다.
+  - aiohttp, docling 및 docling-core에 대한 pip-audit CVE를 해결합니다.
+  - 파일 입력이 신뢰할 수 없게 작동하는 문제를 수정했습니다.
+  - Snowflake Claude의 불완전한 도구 결과 기록을 수정했습니다.
+
+  ### 문서
+  - v1.14.7에 대한 변경 로그 및 버전을 업데이트했습니다.
+  - OpenTelemetry 수집기 문서를 업데이트했습니다.
+  - NVIDIA Nemotron LLM 가이드를 업데이트했습니다.
+  - Databricks 통합 가이드를 추가했습니다.
+  - Snowflake 통합 가이드를 추가했습니다.
+
+  ### 성능
+  - docling 가져오기를 지연 로딩하여 crewai 가져오기 속도를 개선했습니다.
+
+  ### 리팩토링
+  - 흐름 조건 평가를 이벤트별로 상태 비저장으로 단순화했습니다.
+  - 대화 논리를 런타임에서 분리하고 conversational_definition을 추가했습니다.
+  - `flow.py`를 DSL, 정의 및 런타임으로 분리했습니다.
+
+  ## 기여자
+
+  @Luzk, @alex-clawd, @devin-ai-integration[bot], @greysonlalonde, @gvieira, @jessemiller, @lorenzejay, @lucasgomide, @mattatcha, @vinibrsl
+
+</Update>
+
 <Update label="2026년 6월 10일">
   ## v1.14.7rc2
 

docs/ko/concepts/flows.mdx

@@ -221,6 +221,48 @@ Flow가 실행된 후, 이러한 메소드들에 의해 수행된 업데이트
 최종 메소드의 출력이 반환되고 상태에 접근할 수 있도록 함으로써, CrewAI Flow는 AI 워크플로우의 결과를 더 큰 애플리케이션이나 시스템에 쉽게 통합할 수 있게 하며,
 Flow 실행 과정 전반에 걸쳐 상태를 유지하고 접근하면서도 이를 용이하게 만듭니다.
 
+## 플로우 사용 메트릭
+
+Flow 실행이 완료된 후, `usage_metrics` 속성에 접근하여 실행 동안 발생한 **모든 LLM 호출**의 토큰 사용량 집계를 확인할 수 있습니다. 여기에는 Flow가 오케스트레이션한 모든 Crew의 호출, Agent의 도구 내부에서 발생한 호출, 그리고 Flow 메서드에서 직접 호출한 `LLM.call(...)`이 모두 포함됩니다. 이는 CrewAI Enterprise UI에 표시되는 총량과 동등한 SDK 측 값입니다.
+
+```python Code
+from crewai import LLM
+from crewai.flow.flow import Flow, listen, start
+
+class UsageMetricsFlow(Flow):
+    @start()
+    def run_first_crew(self):
+        self.state.first_result = FirstCrew().crew().kickoff()
+
+    @listen(run_first_crew)
+    def call_llm_directly(self):
+        # 직접 LLM 호출 — flow.usage_metrics에서도 집계됩니다
+        llm = LLM(model="openai/gpt-4o-mini")
+        self.state.summary = llm.call("핵심 내용을 요약해 주세요.")
+
+    @listen(call_llm_directly)
+    def run_second_crew(self):
+        self.state.second_result = SecondCrew().crew().kickoff()
+
+flow = UsageMetricsFlow()
+flow.kickoff()
+
+print(flow.usage_metrics)
+# UsageMetrics(total_tokens=8579, prompt_tokens=6210, completion_tokens=2369,
+#              cached_prompt_tokens=0, reasoning_tokens=0,
+#              cache_creation_tokens=0, successful_requests=5)
+```
+
+<Note>
+  `flow.usage_metrics`는 `flow.kickoff().token_usage`와 **동일하지 않습니다**.
+  후자는 `CrewOutput`을 반환한 **마지막** `@listen` 메서드의
+  `CrewOutput.token_usage`만 반환하므로, 이전에 실행된 Crew들과 Flow 메서드에서
+  직접 호출한 `LLM.call(...)`은 전혀 포함되지 않습니다. Flow 실행에 대한
+  **전체** 토큰 집계가 필요할 때는 항상 `flow.usage_metrics`를 사용하십시오.
+</Note>
+
+반환되는 [`UsageMetrics`](https://github.com/crewAIInc/crewAI/blob/main/lib/crewai/src/crewai/types/usage_metrics.py)의 각 항목은 단일 `flow.kickoff()` 실행 동안 발생한 모든 LLM 호출의 합계입니다. 다음 `kickoff()` 호출(및 `kickoff_for_each`의 각 반복)에서 카운터가 초기화되므로 연속 실행이 이중으로 집계되지 않습니다. 이 속성은 `kickoff()` 완료 후 언제든지 안전하게 읽을 수 있으며, 실행 중에 읽으면 그 시점까지 누적된 부분 합계를 반환합니다.
+
 ## 플로우 상태 관리
 
 상태를 효과적으로 관리하는 것은 신뢰할 수 있고 유지 보수가 용이한 AI 워크플로를 구축하는 데 매우 중요합니다. CrewAI 플로우는 비정형 및 정형 상태 관리를 위한 강력한 메커니즘을 제공하여, 개발자가 자신의 애플리케이션에 가장 적합한 접근 방식을 선택할 수 있도록 합니다.

docs/pt-BR/changelog.mdx

@@ -4,6 +4,55 @@ description: "Atualizações de produto, melhorias e correções do CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="11 jun 2026">
+  ## v1.14.7
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7)
+
+  ## O que Mudou
+
+  ### Recursos
+  - Adicionar backends padrão plugáveis para memória, conhecimento, rag e fluxo.
+  - Exibir o verdadeiro finish_reason, parâmetros de amostragem e response.id em eventos LLM.
+  - Tipar os gatilhos DSL como decoradores cientes de rotas.
+  - Adicionar API de chat para fluxos de conversa.
+  - Tornar o backend de bloqueio substituível.
+  - Construir FlowDefinition a partir de metadados Flow DSL.
+  - Adicionar provedor nativo Snowflake Cortex LLM.
+  - Adicionar suporte a arquivos de agentes treinados pela equipe.
+
+  ### Correções de Bugs
+  - Corrigir checkpoint para reconstruir BaseLLM personalizado como LLM concreto na restauração.
+  - Controlar a restauração com uma flag para evitar que snapshots ao vivo sejam reproduzidos como retomar.
+  - Escopar o estado de execução por execução para limitar o crescimento e isolar execuções concorrentes.
+  - Corrigir configuração de telemetria no crewai-login.
+  - Respeitar suppress_flow_events para eventos de execução de método.
+  - Restaurar [project.scripts] no pacote crewai para instalação da ferramenta uv.
+  - Resolver CVEs de pip-audit para aiohttp, docling e docling-core.
+  - Corrigir entrada de arquivo que não estava funcionando de forma confiável.
+  - Corrigir histórias de resultados de ferramentas incompletas do Snowflake Claude.
+
+  ### Documentação
+  - Atualizar changelog e versão para v1.14.7.
+  - Atualizar documentação do coletor OpenTelemetry.
+  - Atualizar guia do LLM NVIDIA Nemotron.
+  - Adicionar guia de integração do Databricks.
+  - Adicionar guia de integração do Snowflake.
+
+  ### Desempenho
+  - Melhorar a velocidade de importação do crewai através do carregamento preguiçoso de imports do docling.
+
+  ### Refatoração
+  - Simplificar a avaliação de condições de fluxo para ser sem estado por evento.
+  - Desacoplar a lógica de conversa da execução e adicionar uma conversational_definition.
+  - Dividir `flow.py` em DSL, definição e execução.
+
+  ## Contribuidores
+
+  @Luzk, @alex-clawd, @devin-ai-integration[bot], @greysonlalonde, @gvieira, @jessemiller, @lorenzejay, @lucasgomide, @mattatcha, @vinibrsl
+
+</Update>
+
 <Update label="10 jun 2026">
   ## v1.14.7rc2
 

docs/pt-BR/concepts/flows.mdx

@@ -219,6 +219,49 @@ Após o término da execução, é possível acessar o estado final e observar a
 Ao garantir que a saída do método final seja retornada e oferecer acesso ao estado, o CrewAI Flows facilita a integração dos resultados dos seus workflows de IA em aplicações maiores,
 além de permitir o gerenciamento e o acesso ao estado durante toda a execução do Flow.
 
+## Métricas de Uso do Flow
+
+Após a execução de um Flow, você pode acessar a propriedade `usage_metrics` para visualizar o consumo agregado de tokens em **todas as chamadas de LLM** realizadas durante a execução — incluindo chamadas das Crews orquestradas pelo Flow, chamadas dentro de tools de Agents, e invocações diretas de `LLM.call(...)` feitas a partir de métodos do Flow. Esse é o equivalente, do lado do SDK, ao total exibido na interface do CrewAI Enterprise.
+
+```python Code
+from crewai import LLM
+from crewai.flow.flow import Flow, listen, start
+
+class UsageMetricsFlow(Flow):
+    @start()
+    def run_first_crew(self):
+        self.state.first_result = FirstCrew().crew().kickoff()
+
+    @listen(run_first_crew)
+    def call_llm_directly(self):
+        # Chamada direta de LLM — também contabilizada por flow.usage_metrics
+        llm = LLM(model="openai/gpt-4o-mini")
+        self.state.summary = llm.call("Resuma os principais pontos.")
+
+    @listen(call_llm_directly)
+    def run_second_crew(self):
+        self.state.second_result = SecondCrew().crew().kickoff()
+
+flow = UsageMetricsFlow()
+flow.kickoff()
+
+print(flow.usage_metrics)
+# UsageMetrics(total_tokens=8579, prompt_tokens=6210, completion_tokens=2369,
+#              cached_prompt_tokens=0, reasoning_tokens=0,
+#              cache_creation_tokens=0, successful_requests=5)
+```
+
+<Note>
+  `flow.usage_metrics` **não** é o mesmo que `flow.kickoff().token_usage`. Este
+  último retorna apenas o `CrewOutput.token_usage` do **último** método
+  `@listen` que retornou um `CrewOutput`, ou seja, reflete somente a Crew
+  final e ignora completamente as Crews anteriores e quaisquer chamadas
+  diretas de `LLM.call(...)`. Use `flow.usage_metrics` sempre que precisar do
+  rollup **completo** de tokens da execução do Flow.
+</Note>
+
+Cada campo do [`UsageMetrics`](https://github.com/crewAIInc/crewAI/blob/main/lib/crewai/src/crewai/types/usage_metrics.py) retornado representa a soma de todas as chamadas de LLM feitas em uma única invocação de `flow.kickoff()`. Os contadores são resetados a cada novo `kickoff()` (e em cada iteração de `kickoff_for_each`), de modo que execuções sucessivas não duplicam o total. A propriedade é segura para ser lida em qualquer momento após o `kickoff()`; lê-la durante a execução retorna o total parcial acumulado até aquele instante.
+
 ## Gerenciamento de Estado em Flows
 
 Gerenciar o estado de forma eficaz é fundamental para construir fluxos de trabalho de IA confiáveis e de fácil manutenção. O CrewAI Flows oferece mecanismos robustos para o gerenciamento de estado tanto não estruturado quanto estruturado,

lib/cli/pyproject.toml

@@ -8,7 +8,7 @@ authors = [
 ]
 requires-python = ">=3.10, <3.14"
 dependencies = [
-    "crewai-core==1.14.7rc2",
+    "crewai-core==1.14.7",
     "click>=8.1.7,<9",
     "pydantic>=2.11.9,<2.13",
     "pydantic-settings~=2.10.1",

lib/cli/src/crewai_cli/__init__.py

@@ -1 +1 @@
-__version__ = "1.14.7rc2"
+__version__ = "1.14.7"

lib/cli/src/crewai_cli/cli.py

@@ -3,41 +3,94 @@ from __future__ import annotations
 from importlib.metadata import version as get_version
 import os
 import subprocess
-from typing import Any
+from typing import TYPE_CHECKING, Any
 
 import click
 from crewai_core.token_manager import TokenManager
 
-from crewai_cli.add_crew_to_flow import add_crew_to_flow
-from crewai_cli.authentication.main import AuthenticationCommand
 from crewai_cli.config import Settings
-from crewai_cli.create_crew import create_crew
-from crewai_cli.create_flow import create_flow
-from crewai_cli.crew_chat import run_chat
-from crewai_cli.deploy.main import DeployCommand
-from crewai_cli.enterprise.main import EnterpriseConfigureCommand
-from crewai_cli.evaluate_crew import evaluate_crew
-from crewai_cli.experimental.skills.main import SkillCommand
-from crewai_cli.install_crew import install_crew
-from crewai_cli.kickoff_flow import kickoff_flow
-from crewai_cli.organization.main import OrganizationCommand
-from crewai_cli.plot_flow import plot_flow
-from crewai_cli.remote_template.main import TemplateCommand
-from crewai_cli.replay_from_task import replay_task_command
-from crewai_cli.reset_memories_command import reset_memories_command
-from crewai_cli.run_crew import run_crew
-from crewai_cli.settings.main import SettingsCommand
-from crewai_cli.task_outputs import load_task_outputs
-from crewai_cli.tools.main import ToolCommand
-from crewai_cli.train_crew import train_crew
-from crewai_cli.triggers.main import TriggersCommand
-from crewai_cli.update_crew import update_crew
 from crewai_cli.user_data import (
     _load_user_data,
     is_tracing_enabled,
     update_user_data,
 )
-from crewai_cli.utils import build_env_with_all_tool_credentials, read_toml
+from crewai_cli.utils import (
+    build_env_with_all_tool_credentials,
+    enable_prompt_line_editing,
+    read_toml,
+)
+
+
+def train_crew(*args: Any, **kwargs: Any) -> Any:
+    from crewai_cli.train_crew import train_crew as _train_crew
+
+    return _train_crew(*args, **kwargs)
+
+
+def evaluate_crew(*args: Any, **kwargs: Any) -> Any:
+    from crewai_cli.evaluate_crew import evaluate_crew as _evaluate_crew
+
+    return _evaluate_crew(*args, **kwargs)
+
+
+def replay_task_command(*args: Any, **kwargs: Any) -> Any:
+    from crewai_cli.replay_from_task import replay_task_command as _replay_task_command
+
+    return _replay_task_command(*args, **kwargs)
+
+
+def run_flow_definition(*args: Any, **kwargs: Any) -> Any:
+    from crewai_cli.run_flow_definition import (
+        run_flow_definition as _run_flow_definition,
+    )
+
+    return _run_flow_definition(*args, **kwargs)
+
+
+def run_crew(*args: Any, **kwargs: Any) -> Any:
+    from crewai_cli.run_crew import run_crew as _run_crew
+
+    return _run_crew(*args, **kwargs)
+
+
+if TYPE_CHECKING:
+    # mypy sees the real classes; at runtime the shims below defer the
+    # heavy imports until a command actually instantiates them.
+    from crewai_cli.authentication.main import AuthenticationCommand
+    from crewai_cli.deploy.main import DeployCommand
+    from crewai_cli.organization.main import OrganizationCommand
+    from crewai_cli.remote_template.main import TemplateCommand
+else:
+
+    class AuthenticationCommand:
+        def __new__(cls, *args: Any, **kwargs: Any) -> Any:
+            from crewai_cli.authentication.main import (
+                AuthenticationCommand as _AuthenticationCommand,
+            )
+
+            return _AuthenticationCommand(*args, **kwargs)
+
+    class DeployCommand:
+        def __new__(cls, *args: Any, **kwargs: Any) -> Any:
+            from crewai_cli.deploy.main import DeployCommand as _DeployCommand
+
+            return _DeployCommand(*args, **kwargs)
+
+    class TemplateCommand:
+        def __new__(cls, *args: Any, **kwargs: Any) -> Any:
+            from crewai_cli.remote_template.main import (
+                TemplateCommand as _TemplateCommand,
+            )
+
+            return _TemplateCommand(*args, **kwargs)
+
+    class OrganizationCommand:
+        def __new__(cls, *args: Any, **kwargs: Any) -> Any:
+            from crewai_cli.organization.main import (
+                OrganizationCommand as _OrganizationCommand,
+            )
+
+            return _OrganizationCommand(*args, **kwargs)
 
 
 def _get_cli_version() -> str:
@@ -90,17 +143,57 @@ def uv(uv_args: tuple[str, ...]) -> None:
 
 
 @crewai.command()
-@click.argument("type", type=click.Choice(["crew", "flow"]))
-@click.argument("name")
+@click.argument(
+    "type", required=False, default=None, type=click.Choice(["crew", "flow"])
+)
+@click.argument("name", required=False, default=None)
 @click.option("--provider", type=str, help="The provider to use for the crew")
 @click.option("--skip_provider", is_flag=True, help="Skip provider validation")
+@click.option(
+    "--classic",
+    is_flag=True,
+    help="Use classic Python/YAML project structure instead of JSON",
+)
 def create(
-    type: str, name: str, provider: str | None, skip_provider: bool = False
+    type: str | None,
+    name: str | None,
+    provider: str | None,
+    skip_provider: bool = False,
+    classic: bool = False,
 ) -> None:
     """Create a new crew, or flow."""
+    if not type:
+        from crewai_cli.tui_picker import pick
+
+        options = [
+            ("crew", "A team of AI agents working together"),
+            (
+                "flow",
+                "A deterministic workflow with full control over agents and crews",
+            ),
+        ]
+        type = pick("What would you like to create?", options)
+        if type is None:
+            raise SystemExit(0)
+        click.echo()
+    if not name:
+        enable_prompt_line_editing()
+        name = click.prompt(
+            click.style(f"  Name of your {type}", fg="cyan", bold=True),
+            prompt_suffix=click.style(" › ", fg="bright_white"),  # noqa: RUF001
+        )
     if type == "crew":
-        create_crew(name, provider, skip_provider)
+        if classic:
+            from crewai_cli.create_crew import create_crew
+
+            create_crew(name, provider, skip_provider)
+        else:
+            from crewai_cli.create_json_crew import create_json_crew
+
+            create_json_crew(name, provider, skip_provider)
     elif type == "flow":
+        from crewai_cli.create_flow import create_flow
+
         create_flow(name)
     else:
         click.secho("Error: Invalid type. Must be 'crew' or 'flow'.", fg="red")
@@ -185,6 +278,8 @@ def replay(task_id: str, trained_agents_file: str | None) -> None:
 def log_tasks_outputs() -> None:
     """Retrieve your latest crew.kickoff() task outputs."""
     try:
+        from crewai_cli.task_outputs import load_task_outputs
+
         tasks = load_task_outputs()
 
         if not tasks:
@@ -273,6 +368,8 @@ def reset_memories(
                 "Please specify at least one memory type to reset using the appropriate flags."
             )
             return
+        from crewai_cli.reset_memories_command import reset_memories_command
+
         reset_memories_command(memory, knowledge, agent_knowledge, kickoff_outputs, all)
     except Exception as e:
         click.echo(f"An error occurred while resetting memories: {e}", err=True)
@@ -295,7 +392,7 @@ def reset_memories(
     "--embedder-model",
     type=str,
     default=None,
-    help="Embedder model name (e.g. text-embedding-3-small, gemini-embedding-001).",
+    help="Embedder model name (e.g. text-embedding-3-large, gemini-embedding-001).",
 )
 @click.option(
     "--embedder-config",
@@ -350,7 +447,7 @@ def memory(
     "-m",
     "--model",
     type=str,
-    default="gpt-4o-mini",
+    default="gpt-5.4-mini",
     help="LLM Model to run the tests on the Crew. For now only accepting only OpenAI models.",
 )
 @click.option(
@@ -381,6 +478,8 @@ def test(n_iterations: int, model: str, trained_agents_file: str | None) -> None
 @click.pass_context
 def install(context: click.Context) -> None:
     """Install the Crew."""
+    from crewai_cli.install_crew import install_crew
+
     install_crew(context.args)
 
 
@@ -398,14 +497,46 @@ def install(context: click.Context) -> None:
         "CREWAI_TRAINED_AGENTS_FILE."
     ),
 )
-def run(trained_agents_file: str | None) -> None:
-    """Run the Crew."""
+@click.option(
+    "--definition",
+    type=str,
+    default=None,
+    help=(
+        "Experimental: path to a Flow Definition YAML/JSON file, "
+        "or an inline YAML/JSON string."
+    ),
+)
+@click.option(
+    "--inputs",
+    type=str,
+    default=None,
+    help='Experimental: JSON object passed to flow.kickoff(), e.g. \'{"topic":"AI"}\'.',
+)
+def run(
+    trained_agents_file: str | None,
+    definition: str | None,
+    inputs: str | None,
+) -> None:
+    """Run the Crew or Flow."""
+    if inputs is not None and definition is None:
+        raise click.UsageError("--inputs requires --definition")
+
+    if definition is not None:
+        click.secho(
+            "Warning: `crewai run --definition` is experimental and may change without notice.",
+            fg="yellow",
+        )
+        run_flow_definition(definition=definition, inputs=inputs)
+        return
+
     run_crew(trained_agents_file=trained_agents_file)
 
 
 @crewai.command()
 def update() -> None:
     """Update the pyproject.toml of the Crew project to use uv."""
+    from crewai_cli.update_crew import update_crew
+
     update_crew()
 
 
@@ -515,6 +646,8 @@ def tool() -> None:
 @tool.command(name="create")
 @click.argument("handle")
 def tool_create(handle: str) -> None:
+    from crewai_cli.tools.main import ToolCommand
+
     tool_cmd = ToolCommand()
     tool_cmd.create(handle)
 
@@ -522,6 +655,8 @@ def tool_create(handle: str) -> None:
 @tool.command(name="install")
 @click.argument("handle")
 def tool_install(handle: str) -> None:
+    from crewai_cli.tools.main import ToolCommand
+
     tool_cmd = ToolCommand()
     tool_cmd.login()
     tool_cmd.install(handle)
@@ -538,6 +673,8 @@ def tool_install(handle: str) -> None:
 @click.option("--public", "is_public", flag_value=True, default=False)
 @click.option("--private", "is_public", flag_value=False)
 def tool_publish(is_public: bool, force: bool) -> None:
+    from crewai_cli.tools.main import ToolCommand
+
     tool_cmd = ToolCommand()
     tool_cmd.login()
     tool_cmd.publish(is_public, force)
@@ -570,6 +707,8 @@ def skill() -> None:
     help="Create skill in current dir instead of ./skills/",
 )
 def skill_create(name: str, in_project: bool) -> None:
+    from crewai_cli.experimental.skills.main import SkillCommand
+
     skill_cmd = SkillCommand()
     skill_cmd.create(name, in_project=in_project)
 
@@ -577,6 +716,8 @@ def skill_create(name: str, in_project: bool) -> None:
 @skill.command(name="install")
 @click.argument("ref")
 def skill_install(ref: str) -> None:
+    from crewai_cli.experimental.skills.main import SkillCommand
+
     skill_cmd = SkillCommand()
     skill_cmd.install(ref)
 
@@ -593,6 +734,8 @@ def skill_install(ref: str) -> None:
 @click.option("--private", "is_public", flag_value=False)
 @click.option("--org", default=None, help="Organisation slug (overrides settings).")
 def skill_publish(is_public: bool, org: str | None, force: bool) -> None:
+    from crewai_cli.experimental.skills.main import SkillCommand
+
     skill_cmd = SkillCommand()
     skill_cmd.publish(is_public, org=org, force=force)
 
@@ -600,6 +743,8 @@ def skill_publish(is_public: bool, org: str | None, force: bool) -> None:
 @skill.command(name="list")
 def skill_list() -> None:
     """List locally installed skills."""
+    from crewai_cli.experimental.skills.main import SkillCommand
+
     skill_cmd = SkillCommand()
     skill_cmd.list_cached()
 
@@ -639,6 +784,8 @@ def flow() -> None:
 @flow.command(name="kickoff")
 def flow_run() -> None:
     """Kickoff the Flow."""
+    from crewai_cli.kickoff_flow import kickoff_flow
+
     click.echo("Running the Flow")
     kickoff_flow()
 
@@ -646,6 +793,8 @@ def flow_run() -> None:
 @flow.command(name="plot")
 def flow_plot() -> None:
     """Plot the Flow."""
+    from crewai_cli.plot_flow import plot_flow
+
     click.echo("Plotting the Flow")
     plot_flow()
 
@@ -654,6 +803,8 @@ def flow_plot() -> None:
 @click.argument("crew_name")
 def flow_add_crew(crew_name: str) -> None:
     """Add a crew to an existing flow."""
+    from crewai_cli.add_crew_to_flow import add_crew_to_flow
+
     click.echo(f"Adding crew {crew_name} to the flow")
     add_crew_to_flow(crew_name)
 
@@ -666,6 +817,8 @@ def triggers() -> None:
 @triggers.command(name="list")
 def triggers_list() -> None:
     """List all available triggers from integrations."""
+    from crewai_cli.triggers.main import TriggersCommand
+
     triggers_cmd = TriggersCommand()
     triggers_cmd.list_triggers()
 
@@ -674,6 +827,8 @@ def triggers_list() -> None:
 @click.argument("trigger_path")
 def triggers_run(trigger_path: str) -> None:
     """Execute crew with trigger payload. Format: app_slug/trigger_slug"""
+    from crewai_cli.triggers.main import TriggersCommand
+
     triggers_cmd = TriggersCommand()
     triggers_cmd.execute_with_trigger(trigger_path)
 
@@ -686,6 +841,8 @@ def chat() -> None:
     click.secho(
         "\nStarting a conversation with the Crew\nType 'exit' or Ctrl+C to quit.\n",
     )
+    from crewai_cli.crew_chat import run_chat
+
     run_chat()
 
 
@@ -725,6 +882,8 @@ def enterprise() -> None:
 @click.argument("enterprise_url")
 def enterprise_configure(enterprise_url: str) -> None:
     """Configure CrewAI AMP OAuth2 settings from the provided Enterprise URL."""
+    from crewai_cli.enterprise.main import EnterpriseConfigureCommand
+
     enterprise_command = EnterpriseConfigureCommand()
     enterprise_command.configure(enterprise_url)
 
@@ -737,6 +896,8 @@ def config() -> None:
 @config.command("list")
 def config_list() -> None:
     """List all CLI configuration parameters."""
+    from crewai_cli.settings.main import SettingsCommand
+
     config_command = SettingsCommand()
     config_command.list()
 
@@ -746,6 +907,8 @@ def config_list() -> None:
 @click.argument("value")
 def config_set(key: str, value: str) -> None:
     """Set a CLI configuration parameter."""
+    from crewai_cli.settings.main import SettingsCommand
+
     config_command = SettingsCommand()
     config_command.set(key, value)
 
@@ -753,6 +916,8 @@ def config_set(key: str, value: str) -> None:
 @config.command("reset")
 def config_reset() -> None:
     """Reset all CLI configuration parameters to default values."""
+    from crewai_cli.settings.main import SettingsCommand
+
     config_command = SettingsCommand()
     config_command.reset_all_settings()
 

lib/cli/src/crewai_cli/command.py

@@ -13,6 +13,10 @@ from crewai_cli.plus_api import PlusAPI
 console = Console()
 
 
+class AuthenticationRequiredError(SystemExit):
+    """Raised when a Plus API command needs the user to log in first."""
+
+
 class BaseCommand:
     def __init__(self) -> None:
         self._telemetry = Telemetry()
@@ -31,7 +35,7 @@ class PlusAPIMixin:
                 style="bold red",
             )
             console.print("Run 'crewai login' to sign up/login.", style="bold green")
-            raise SystemExit from None
+            raise AuthenticationRequiredError from None
 
     def _validate_response(self, response: httpx.Response) -> None:
         """Handle and display error messages from API responses.

lib/cli/src/crewai_cli/deploy/archive.py

@@ -0,0 +1,409 @@
+from __future__ import annotations
+
+from pathlib import Path
+import re
+import shutil
+import tempfile
+from typing import Any
+import zipfile
+
+from crewai_cli import git
+from crewai_cli.deploy.validate import normalize_package_name
+from crewai_cli.utils import parse_toml
+
+
+_EXCLUDED_DIRS = {
+    ".crewai",
+    ".git",
+    ".mypy_cache",
+    ".pytest_cache",
+    ".ruff_cache",
+    ".tox",
+    ".venv",
+    "__pycache__",
+    "build",
+    "dist",
+    "env",
+    "venv",
+}
+_EXCLUDED_FILES = {
+    ".DS_Store",
+    ".env",
+}
+_ALLOWED_ENV_EXAMPLES = {
+    ".env.example",
+    ".env.sample",
+}
+_EXCLUDED_SUFFIXES = {
+    ".pyc",
+    ".pyo",
+}
+_SCRIPT_KEY_PATTERN = re.compile(r"^\s*(?P<key>[A-Za-z0-9_.-]+|\"[^\"]+\"|'[^']+')\s*=")
+_SECTION_PATTERN = re.compile(r"^\s*\[[^\]]+\]\s*(?:#.*)?$")
+
+
+def create_project_zip(
+    project_name: str,
+    *,
+    project_dir: Path | None = None,
+    repository: git.Repository | None = None,
+) -> Path:
+    """Create a deployable ZIP archive for a CrewAI project."""
+    root = (project_dir or Path.cwd()).resolve()
+    files = _project_files(root, repository)
+    if not files:
+        raise ValueError("No deployable project files were found.")
+
+    staged_root = _stage_project(root, files)
+    archive_handle = tempfile.NamedTemporaryFile(
+        prefix=f"{project_name}-",
+        suffix=".zip",
+        delete=False,
+    )
+    archive_path = Path(archive_handle.name)
+    archive_handle.close()
+
+    try:
+        with zipfile.ZipFile(archive_path, "w", zipfile.ZIP_DEFLATED) as zip_file:
+            for relative_path in _walk_files(staged_root):
+                absolute_path = staged_root / relative_path
+                zip_file.write(absolute_path, relative_path.as_posix())
+    finally:
+        shutil.rmtree(staged_root, ignore_errors=True)
+
+    return archive_path
+
+
+def _project_files(root: Path, repository: git.Repository | None = None) -> list[Path]:
+    """Return project-relative files to include in the archive."""
+    if repository is not None:
+        return _repository_project_files(root, repository)
+
+    try:
+        repository = git.Repository(path=str(root), fetch=False)
+    except ValueError:
+        repository = None
+
+    if repository is not None:
+        return _repository_project_files(root, repository)
+
+    return [
+        path
+        for path in _walk_files(root)
+        if not _is_excluded(path) and _is_regular_file(root / path)
+    ]
+
+
+def _repository_project_files(root: Path, repository: git.Repository) -> list[Path]:
+    """Return deployable files from Git while applying local safety excludes."""
+    files = [Path(path) for path in repository.deployable_files()]
+    return [
+        path
+        for path in files
+        if not _is_excluded(path) and _is_regular_file(root / path)
+    ]
+
+
+def _walk_files(root: Path) -> list[Path]:
+    """List regular files below root as project-relative paths."""
+    return [
+        path.relative_to(root) for path in root.rglob("*") if _is_regular_file(path)
+    ]
+
+
+def _is_regular_file(path: Path) -> bool:
+    """Return True for regular files, excluding symlinks to files."""
+    return path.is_file() and not path.is_symlink()
+
+
+def _is_excluded(path: Path) -> bool:
+    """Return True when a file should be omitted from deployment ZIPs."""
+    parts = set(path.parts)
+    if parts.intersection(_EXCLUDED_DIRS):
+        return True
+
+    name = path.name
+    if name in _EXCLUDED_FILES:
+        return True
+    if name.startswith(".env.") and name not in _ALLOWED_ENV_EXAMPLES:
+        return True
+    return path.suffix in _EXCLUDED_SUFFIXES
+
+
+def _stage_project(root: Path, files: list[Path]) -> Path:
+    """Copy archive files into a temporary staging directory."""
+    staging_root = Path(tempfile.mkdtemp(prefix="crewai-deploy-"))
+
+    try:
+        for relative_path in files:
+            source = root / relative_path
+            if not _is_regular_file(source):
+                continue
+
+            destination = staging_root / relative_path
+            destination.parent.mkdir(parents=True, exist_ok=True)
+            shutil.copy2(source, destination)
+
+        if _is_json_crew_project(staging_root):
+            _add_json_crew_deploy_wrapper(staging_root)
+    except Exception:
+        shutil.rmtree(staging_root, ignore_errors=True)
+        raise
+    return staging_root
+
+
+def _is_json_crew_project(root: Path) -> bool:
+    """Return True for JSON crew projects that need a Python deploy wrapper."""
+    if not ((root / "crew.jsonc").is_file() or (root / "crew.json").is_file()):
+        return False
+
+    project = _read_pyproject(root)
+    tool_config = project.get("tool") or {}
+    crewai_config = tool_config.get("crewai") if isinstance(tool_config, dict) else None
+    declared_type = (
+        crewai_config.get("type") if isinstance(crewai_config, dict) else None
+    )
+    if declared_type == "flow":
+        return False
+
+    package_name = _package_name(root)
+    if package_name is None:
+        raise ValueError(
+            "Could not derive a valid Python package name from [project].name."
+        )
+
+    return not (root / "src" / package_name / "crew.py").is_file()
+
+
+def _read_pyproject(root: Path) -> dict[str, Any]:
+    """Read pyproject.toml, returning an empty mapping on missing or invalid data."""
+    pyproject_path = root / "pyproject.toml"
+    if not pyproject_path.is_file():
+        return {}
+    try:
+        pyproject = parse_toml(pyproject_path.read_text())
+    except Exception:
+        return {}
+    return pyproject if isinstance(pyproject, dict) else {}
+
+
+def _package_name(root: Path) -> str | None:
+    """Return the normalized Python package name for the project."""
+    project = _read_pyproject(root).get("project")
+    if not isinstance(project, dict):
+        return None
+
+    name = project.get("name")
+    if not isinstance(name, str) or not name.strip():
+        return None
+
+    package_name = normalize_package_name(name)
+    return package_name or None
+
+
+def _class_name(package_name: str) -> str:
+    """Return the generated wrapper class name for a package."""
+    parts = [part for part in re.split(r"[^a-zA-Z0-9]+", package_name) if part]
+    class_name = "".join(part[:1].upper() + part[1:] for part in parts)
+    if not class_name:
+        return "JsonCrew"
+    if class_name[0].isdigit():
+        return f"Crew{class_name}"
+    return class_name
+
+
+def _add_json_crew_deploy_wrapper(root: Path) -> None:
+    """Add Python wrapper files required to deploy a JSON crew project."""
+    package_name = _package_name(root)
+    if package_name is None:
+        raise ValueError(
+            "Could not derive a valid Python package name from [project].name."
+        )
+
+    package_dir = root / "src" / package_name
+    config_dir = package_dir / "config"
+    config_dir.mkdir(parents=True, exist_ok=True)
+
+    class_name = _class_name(package_name)
+    crew_filename = "crew.jsonc" if (root / "crew.jsonc").is_file() else "crew.json"
+
+    (package_dir / "__init__.py").write_text("", encoding="utf-8")
+    (config_dir / "agents.yaml").write_text("{}\n", encoding="utf-8")
+    (config_dir / "tasks.yaml").write_text("{}\n", encoding="utf-8")
+    (package_dir / "crew.py").write_text(
+        _json_crew_py(class_name, crew_filename),
+        encoding="utf-8",
+    )
+    (package_dir / "main.py").write_text(
+        _json_main_py(package_name, class_name),
+        encoding="utf-8",
+    )
+    _ensure_project_scripts(root, package_name)
+
+
+def _json_crew_py(class_name: str, crew_filename: str) -> str:
+    """Render the generated crew.py module for a JSON crew."""
+    return f'''from pathlib import Path
+
+from crewai import Crew
+from crewai.project import CrewBase, crew
+from crewai.project.crew_loader import load_crew
+
+
+def _crew_path() -> Path:
+    return Path(__file__).resolve().parents[2] / "{crew_filename}"
+
+
+@CrewBase
+class {class_name}:
+    """Compatibility wrapper for a JSON-defined CrewAI project."""
+
+    @crew
+    def crew(self) -> Crew:
+        crew_instance, default_inputs = load_crew(_crew_path())
+        self.default_inputs = default_inputs
+        return crew_instance
+'''
+
+
+def _json_main_py(package_name: str, class_name: str) -> str:
+    """Render the generated main.py entrypoints for a JSON crew."""
+    return f"""#!/usr/bin/env python
+import json
+import sys
+
+from {package_name}.crew import {class_name}
+
+
+def _load():
+    wrapper = {class_name}()
+    crew = wrapper.crew()
+    return crew, getattr(wrapper, "default_inputs", {{}})
+
+
+def run():
+    crew, inputs = _load()
+    return crew.kickoff(inputs=inputs)
+
+
+def train():
+    crew, inputs = _load()
+    return crew.train(
+        n_iterations=int(sys.argv[1]),
+        filename=sys.argv[2],
+        inputs=inputs,
+    )
+
+
+def replay():
+    crew, _ = _load()
+    return crew.replay(task_id=sys.argv[1])
+
+
+def test():
+    crew, inputs = _load()
+    return crew.test(
+        n_iterations=int(sys.argv[1]),
+        eval_llm=sys.argv[2],
+        inputs=inputs,
+    )
+
+
+def run_with_trigger():
+    if len(sys.argv) < 2:
+        raise ValueError("No trigger payload provided.")
+
+    crew, inputs = _load()
+    trigger_payload = json.loads(sys.argv[1])
+    return crew.kickoff(
+        inputs={{**inputs, "crewai_trigger_payload": trigger_payload}}
+    )
+"""
+
+
+def _ensure_project_scripts(root: Path, package_name: str) -> None:
+    """Ensure generated wrappers have project script entrypoints."""
+    pyproject_path = root / "pyproject.toml"
+    if not pyproject_path.is_file():
+        return
+
+    content = pyproject_path.read_text(encoding="utf-8")
+    entries = _project_script_entries(package_name)
+    pyproject_path.write_text(
+        _update_project_scripts(content, entries),
+        encoding="utf-8",
+    )
+
+
+def _project_script_entries(package_name: str) -> dict[str, str]:
+    """Return script entrypoints required by the generated JSON wrapper."""
+    return {
+        package_name: f"{package_name}.main:run",
+        "run_crew": f"{package_name}.main:run",
+        "train": f"{package_name}.main:train",
+        "replay": f"{package_name}.main:replay",
+        "test": f"{package_name}.main:test",
+        "run_with_trigger": f"{package_name}.main:run_with_trigger",
+    }
+
+
+def _update_project_scripts(content: str, entries: dict[str, str]) -> str:
+    """Add or replace generated script entries in pyproject.toml content."""
+    lines = content.rstrip().splitlines()
+    header_index = _project_scripts_header_index(lines)
+    if header_index is None:
+        return content.rstrip() + _project_scripts_block(entries)
+
+    end_index = _section_end_index(lines, header_index + 1)
+    seen: set[str] = set()
+    for index in range(header_index + 1, end_index):
+        key = _script_key(lines[index])
+        if key in entries:
+            lines[index] = _script_line(key, entries[key])
+            seen.add(key)
+
+    missing_lines = [
+        _script_line(key, value) for key, value in entries.items() if key not in seen
+    ]
+    lines[end_index:end_index] = missing_lines
+    return "\n".join(lines).rstrip() + "\n"
+
+
+def _project_scripts_header_index(lines: list[str]) -> int | None:
+    """Return the line index of the project scripts table, if present."""
+    for index, line in enumerate(lines):
+        if line.strip() == "[project.scripts]":
+            return index
+    return None
+
+
+def _section_end_index(lines: list[str], start_index: int) -> int:
+    """Return the exclusive end index for a TOML table section."""
+    for index in range(start_index, len(lines)):
+        if _SECTION_PATTERN.match(lines[index]):
+            return index
+    return len(lines)
+
+
+def _script_key(line: str) -> str | None:
+    """Return the script key for a pyproject script line."""
+    match = _SCRIPT_KEY_PATTERN.match(line)
+    if not match:
+        return None
+
+    key = match.group("key")
+    if key.startswith(("'", '"')) and key.endswith(("'", '"')):
+        return key[1:-1]
+    return key
+
+
+def _script_line(key: str, value: str) -> str:
+    """Render a project script TOML entry."""
+    return f'{key} = "{value}"'
+
+
+def _project_scripts_block(entries: dict[str, str]) -> str:
+    """Render a project scripts TOML table."""
+    lines = ["", "", "[project.scripts]"]
+    lines.extend(_script_line(key, value) for key, value in entries.items())
+    return "\n".join(lines) + "\n"

lib/cli/src/crewai_cli/deploy/main.py

@@ -1,3 +1,5 @@
+from pathlib import Path
+import subprocess
 from typing import Any
 
 from crewai_core.plus_api import CreateCrewPayload
@@ -5,14 +7,19 @@ from rich.console import Console
 
 from crewai_cli import git
 from crewai_cli.command import BaseCommand, PlusAPIMixin
-from crewai_cli.deploy.validate import validate_project
+from crewai_cli.deploy.archive import create_project_zip
+from crewai_cli.deploy.validate import DeployValidator, Severity, render_report
 from crewai_cli.utils import fetch_and_json_env_file, get_project_name
 
 
 console = Console()
+_MISSING_LOCKFILE_ERROR_CODES = {"missing_lockfile"}
 
 
-def _run_predeploy_validation(skip_validate: bool) -> bool:
+def _run_predeploy_validation(
+    skip_validate: bool,
+    ignored_error_codes: set[str] | None = None,
+) -> bool:
     """Run pre-deploy validation unless skipped.
 
     Returns True if deployment should proceed, False if it should abort.
@@ -24,8 +31,22 @@ def _run_predeploy_validation(skip_validate: bool) -> bool:
         return True
 
     console.print("Running pre-deploy validation...", style="bold blue")
-    validator = validate_project()
-    if not validator.ok:
+    validator = DeployValidator()
+    validator.run()
+
+    ignored_error_codes = ignored_error_codes or set()
+    visible_results = [
+        result
+        for result in validator.results
+        if result.severity is not Severity.ERROR
+        or result.code not in ignored_error_codes
+    ]
+    render_report(visible_results)
+
+    blocking_errors = [
+        result for result in validator.errors if result.code not in ignored_error_codes
+    ]
+    if blocking_errors:
         console.print(
             "\n[bold red]Pre-deploy validation failed. "
             "Fix the issues above or re-run with --skip-validate.[/bold red]"
@@ -34,6 +55,79 @@ def _run_predeploy_validation(skip_validate: bool) -> bool:
     return True
 
 
+def _display_git_repository_help() -> None:
+    """Explain how to prepare a new project for deployment."""
+    console.print(
+        "Initialized a local Git repository and created an initial commit.",
+        style="green",
+    )
+
+
+def _display_git_remote_help() -> None:
+    """Explain that ZIP deployment will be used without an origin remote."""
+    console.print(
+        "No origin remote found. Deploying from a ZIP upload instead.",
+        style="yellow",
+    )
+
+
+def _env_summary(env_vars: dict[str, str]) -> str:
+    """Return a compact description of environment variables for prompts."""
+    if not env_vars:
+        return "0 env vars"
+    keys = ", ".join(sorted(env_vars))
+    return f"{len(env_vars)} env vars: {keys}"
+
+
+def _needs_lockfile_for_deploy(project_root: Path | None = None) -> bool:
+    """Return True when deploy should create the project's first lockfile."""
+    root = project_root or Path.cwd()
+    if not (root / "pyproject.toml").is_file():
+        return False
+    return not (root / "uv.lock").is_file() and not (root / "poetry.lock").is_file()
+
+
+def _ensure_lockfile_for_deploy() -> None:
+    """Create a uv lockfile before deploy when a project has not been run yet."""
+    if not _needs_lockfile_for_deploy():
+        return
+
+    from crewai_cli.install_crew import install_crew
+
+    console.print(
+        "No lockfile found. Installing dependencies before deployment...",
+        style="bold blue",
+    )
+    try:
+        install_crew([], raise_on_error=True)
+    except subprocess.CalledProcessError as e:
+        raise SystemExit(e.returncode) from e
+    except Exception as e:
+        raise SystemExit(1) from e
+
+
+def _prepare_project_for_deploy(skip_validate: bool) -> bool:
+    """Validate deploy inputs before creating a missing lockfile."""
+    if skip_validate:
+        _run_predeploy_validation(skip_validate)
+        _ensure_lockfile_for_deploy()
+        return True
+
+    needs_lockfile = _needs_lockfile_for_deploy()
+    ignored_error_codes = _MISSING_LOCKFILE_ERROR_CODES if needs_lockfile else None
+    if not _run_predeploy_validation(
+        skip_validate,
+        ignored_error_codes=ignored_error_codes,
+    ):
+        return False
+
+    if not needs_lockfile:
+        return True
+
+    _ensure_lockfile_for_deploy()
+    return _run_predeploy_validation(skip_validate)
+
+
 class DeployCommand(BaseCommand, PlusAPIMixin):
     """
     A class to handle deployment-related operations for CrewAI projects.
@@ -92,14 +186,30 @@ class DeployCommand(BaseCommand, PlusAPIMixin):
             uuid (Optional[str]): The UUID of the crew to deploy.
             skip_validate (bool): Skip pre-deploy validation checks.
         """
-        if not _run_predeploy_validation(skip_validate):
+        if not _prepare_project_for_deploy(skip_validate):
             return
         self._telemetry.start_deployment_span(uuid)
         console.print("Starting deployment...", style="bold blue")
-        if uuid:
+        repository = self._prepare_git_repository()
+        remote_repo_url = repository.origin_url() if repository else None
+
+        if remote_repo_url and uuid:
             response = self.plus_api_client.deploy_by_uuid(uuid)
-        elif self.project_name:
+        elif remote_repo_url and self.project_name:
             response = self.plus_api_client.deploy_by_name(self.project_name)
+        elif uuid:
+            _display_git_remote_help()
+            env_vars = fetch_and_json_env_file()
+            response = self._update_crew_from_zip(uuid, repository, env_vars)
+        elif self.project_name:
+            _display_git_remote_help()
+            deployment_uuid = self._deployment_uuid_by_name()
+            env_vars = fetch_and_json_env_file()
+            response = self._update_crew_from_zip(
+                deployment_uuid,
+                repository,
+                env_vars,
+            )
         else:
             self._standard_no_param_error_message()
             return
@@ -107,6 +217,19 @@ class DeployCommand(BaseCommand, PlusAPIMixin):
         self._validate_response(response)
         self._display_deployment_info(response.json())
 
+    def _deployment_uuid_by_name(self) -> str:
+        """Resolve the current project's deployment UUID by project name."""
+        if not self.project_name:
+            raise ValueError("project_name is required to find a deployment")
+
+        response = self.plus_api_client.crew_status_by_name(self.project_name)
+        self._validate_response(response)
+        json_response = response.json()
+        uuid = json_response.get("uuid")
+        if not uuid:
+            raise ValueError("Deployment status response did not include a uuid")
+        return str(uuid)
+
     def create_crew(self, confirm: bool = False, skip_validate: bool = False) -> None:
         """
         Create a new crew deployment.
@@ -115,32 +238,143 @@ class DeployCommand(BaseCommand, PlusAPIMixin):
             confirm (bool): Whether to skip the interactive confirmation prompt.
             skip_validate (bool): Skip pre-deploy validation checks.
         """
-        if not _run_predeploy_validation(skip_validate):
+        if not _prepare_project_for_deploy(skip_validate):
             return
         self._telemetry.create_crew_deployment_span()
         console.print("Creating deployment...", style="bold blue")
         env_vars = fetch_and_json_env_file()
+        repository = self._prepare_git_repository()
+        remote_repo_url = repository.origin_url() if repository else None
 
-        try:
-            remote_repo_url = git.Repository().origin_url()
-        except ValueError:
-            remote_repo_url = None
-
-        if remote_repo_url is None:
-            console.print("No remote repository URL found.", style="bold red")
-            console.print(
-                "Please ensure your project has a valid remote repository.",
-                style="yellow",
-            )
-            return
-
-        self._confirm_input(env_vars, remote_repo_url, confirm)
-        payload = self._create_payload(env_vars, remote_repo_url)
-        response = self.plus_api_client.create_crew(payload)
+        if remote_repo_url:
+            self._confirm_input(env_vars, remote_repo_url, confirm)
+            payload = self._create_payload(env_vars, remote_repo_url)
+            response = self.plus_api_client.create_crew(payload)
+        else:
+            _display_git_remote_help()
+            response = self._create_crew_from_zip(env_vars, repository, confirm)
 
         self._validate_response(response)
         self._display_creation_success(response.json())
 
+    def _prepare_git_repository(self) -> git.Repository | None:
+        """Prepare Git for deploy while preserving remote deploy when possible."""
+        try:
+            repository = git.Repository(fetch=False)
+        except ValueError as exc:
+            if "not a Git repository" not in str(exc):
+                console.print(
+                    f"{exc} Continuing with ZIP deployment.",
+                    style="yellow",
+                )
+                return None
+
+            try:
+                repository = git.Repository.initialize()
+            except Exception as init_error:
+                console.print(
+                    "Git auto-setup did not complete. Continuing with ZIP deployment.",
+                    style="yellow",
+                )
+                console.print(str(init_error), style="dim")
+                try:
+                    return git.Repository(fetch=False)
+                except Exception as repository_error:
+                    console.print(str(repository_error), style="dim")
+                    return None
+
+            _display_git_repository_help()
+            return repository
+
+        remote_repo_url = repository.origin_url()
+        if remote_repo_url:
+            try:
+                repository.fetch()
+            except ValueError as fetch_error:
+                console.print(
+                    "Could not fetch from origin. Continuing with remote deployment.",
+                    style="yellow",
+                )
+                console.print(str(fetch_error), style="dim")
+
+            try:
+                if repository.create_initial_commit_if_needed():
+                    console.print(
+                        "Created an initial Git commit for this project.",
+                        style="green",
+                    )
+            except Exception as commit_error:
+                console.print(
+                    "Could not create an initial Git commit. "
+                    "Continuing with remote deployment.",
+                    style="yellow",
+                )
+                console.print(str(commit_error), style="dim")
+
+            return repository
+
+        try:
+            if repository.create_initial_commit_if_needed():
+                console.print(
+                    "Created an initial Git commit for this project.",
+                    style="green",
+                )
+        except Exception as commit_error:
+            console.print(
+                "Could not create an initial Git commit. "
+                "Continuing with ZIP deployment using Git file listing.",
+                style="yellow",
+            )
+            console.print(str(commit_error), style="dim")
+            return repository
+
+        return repository
+
+    def _create_crew_from_zip(
+        self,
+        env_vars: dict[str, str],
+        repository: git.Repository | None,
+        confirm: bool,
+    ) -> Any:
+        """Create a deployment by uploading a project ZIP archive."""
+        if not self.project_name:
+            raise ValueError("project_name is required to create a ZIP deployment")
+
+        console.print("Preparing project ZIP...", style="bold blue")
+        zip_file_path = create_project_zip(self.project_name, repository=repository)
+        try:
+            self._confirm_zip_input(env_vars, confirm)
+            console.print("Uploading project ZIP...", style="bold blue")
+            return self.plus_api_client.create_crew_from_zip(
+                zip_file_path,
+                name=self.project_name,
+                env=env_vars,
+            )
+        finally:
+            zip_file_path.unlink(missing_ok=True)
+
+    def _update_crew_from_zip(
+        self,
+        uuid: str,
+        repository: git.Repository | None,
+        env_vars: dict[str, str],
+    ) -> Any:
+        """Update an existing deployment by uploading a project ZIP archive."""
+        if not self.project_name:
+            raise ValueError("project_name is required to update a ZIP deployment")
+
+        console.print("Preparing project ZIP...", style="bold blue")
+        zip_file_path = create_project_zip(self.project_name, repository=repository)
+        try:
+            console.print("Uploading project ZIP...", style="bold blue")
+            return self.plus_api_client.update_crew_from_zip(
+                uuid,
+                zip_file_path,
+                env=env_vars,
+            )
+        finally:
+            zip_file_path.unlink(missing_ok=True)
+
     def _confirm_input(
         self, env_vars: dict[str, str], remote_repo_url: str, confirm: bool
     ) -> None:
@@ -153,11 +387,16 @@ class DeployCommand(BaseCommand, PlusAPIMixin):
             confirm (bool): Whether to confirm input.
         """
         if not confirm:
-            input(f"Press Enter to continue with the following Env vars: {env_vars}")
+            input(f"Press Enter to continue with {_env_summary(env_vars)}")
             input(
                 f"Press Enter to continue with the following remote repository: {remote_repo_url}\n"
             )
 
+    def _confirm_zip_input(self, env_vars: dict[str, str], confirm: bool) -> None:
+        """Prompt before ZIP upload unless confirmation was already supplied."""
+        if not confirm:
+            input(f"Press Enter to continue with {_env_summary(env_vars)}")
+
     def _create_payload(
         self,
         env_vars: dict[str, str],

lib/cli/src/crewai_cli/deploy/validate.py

@@ -38,6 +38,12 @@ import subprocess
 import sys
 from typing import Any
 
+from crewai.project.json_loader import (
+    JSONProjectValidationError,
+    find_crew_json_file,
+    find_json_project_file,
+    validate_crew_project,
+)
 from rich.console import Console
 
 from crewai_cli.utils import parse_toml
@@ -151,9 +157,33 @@ class DeployValidator:
     def ok(self) -> bool:
         return not self.errors
 
+    @property
+    def _is_json_crew(self) -> bool:
+        """True for JSON crew projects, deferring to the declared type.
+
+        A flow project that also contains a crew.json(c) file validates as
+        the flow it declares in pyproject.toml, not as a JSON crew.
+        """
+        if find_crew_json_file(self.project_root) is None:
+            return False
+        pyproject_path = self.project_root / "pyproject.toml"
+        if not pyproject_path.exists():
+            return True
+        try:
+            data = parse_toml(pyproject_path.read_text())
+        except Exception:
+            return True
+        declared_type: str | None = (
+            (data.get("tool") or {}).get("crewai", {}).get("type")
+        )
+        return declared_type != "flow"
+
     def run(self) -> list[ValidationResult]:
         """Run all checks. Later checks are skipped when earlier ones make
         them impossible (e.g. no pyproject.toml → no lockfile check)."""
+        if self._is_json_crew:
+            return self._run_json_checks()
+
         if not self._check_pyproject():
             return self.results
 
@@ -176,6 +206,110 @@ class DeployValidator:
 
         return self.results
 
+    def _run_json_checks(self) -> list[ValidationResult]:
+        """Validation suite for JSON-defined crew projects."""
+        crew_path = find_crew_json_file(self.project_root)
+        if crew_path is None:
+            return self.results
+
+        try:
+            project = validate_crew_project(crew_path, self.project_root / "agents")
+        except JSONProjectValidationError as e:
+            self._add(
+                Severity.ERROR,
+                "invalid_crew_json",
+                f"{crew_path.name} has invalid JSON crew configuration",
+                detail="\n".join(e.errors),
+                hint="Fix the JSON crew, agent, and task references before deploying.",
+            )
+            return self.results
+        except Exception as e:
+            self._add(
+                Severity.ERROR,
+                "invalid_crew_json",
+                f"Cannot parse {crew_path.name}",
+                detail=str(e),
+            )
+            return self.results
+
+        agents_dir = self.project_root / "agents"
+
+        self._check_pyproject()
+        self._check_lockfile()
+        self._check_env_vars_json(crew_path, agents_dir, project.agent_names)
+        self._check_version_vs_lockfile()
+
+        return self.results
+
+    def _check_env_vars_json(
+        self, crew_path: Path, agents_dir: Path, agent_names: list[str]
+    ) -> None:
+        """Check for env var references in JSON crew files."""
+        referenced: set[str] = set()
+        pattern = re.compile(r"\$\{?([A-Z][A-Z0-9_]+)\}?")
+
+        try:
+            referenced.update(pattern.findall(crew_path.read_text(errors="ignore")))
+        except OSError as exc:
+            logger.debug("Skipping unreadable crew file %s: %s", crew_path, exc)
+
+        for name in agent_names:
+            agent_path = find_json_project_file(agents_dir, name)
+            if agent_path is None:
+                continue
+            try:
+                referenced.update(
+                    pattern.findall(agent_path.read_text(errors="ignore"))
+                )
+            except OSError as exc:
+                logger.debug("Skipping unreadable agent file %s: %s", agent_path, exc)
+
+        for py_path in self.project_root.rglob("*.py"):
+            if ".venv" in py_path.parts:
+                continue
+            try:
+                text = py_path.read_text(encoding="utf-8", errors="ignore")
+            except OSError:
+                continue
+            env_pattern = re.compile(
+                r"""(?x)
+                (?:os\.environ\s*(?:\[\s*|\.get\s*\(\s*)
+                  |os\.getenv\s*\(\s*
+                  |getenv\s*\(\s*)
+                ['"]([A-Z][A-Z0-9_]*)['"]
+                """
+            )
+            referenced.update(env_pattern.findall(text))
+
+        env_file = self.project_root / ".env"
+        env_keys: set[str] = set()
+        if env_file.exists():
+            for line in env_file.read_text(errors="ignore").splitlines():
+                line = line.strip()
+                if not line or line.startswith("#") or "=" not in line:
+                    continue
+                env_keys.add(line.split("=", 1)[0].strip())
+
+        missing_known = sorted(
+            var
+            for var in referenced
+            if var in _KNOWN_API_KEY_HINTS
+            and var not in env_keys
+            and var not in os.environ
+        )
+        if missing_known:
+            self._add(
+                Severity.WARNING,
+                "env_vars_not_in_dotenv",
+                f"{len(missing_known)} referenced API key(s) not in .env",
+                detail=(
+                    "These env vars are referenced in your project but not set "
+                    f"locally: {', '.join(missing_known)}. Deploys will fail "
+                    "unless they are added to the deployment's Environment "
+                    "Variables in the CrewAI dashboard."
+                ),
+            )
+
     def _check_pyproject(self) -> bool:
         pyproject_path = self.project_root / "pyproject.toml"
         if not pyproject_path.exists():

lib/cli/src/crewai_cli/git.py

@@ -1,9 +1,31 @@
+from __future__ import annotations
+
 from functools import cached_property
+from pathlib import Path
 import subprocess
 
 
+_INITIAL_COMMIT_EXCLUDE_PATTERNS = [
+    ".crewai/",
+    ".env",
+    ".env.*",
+    "!.env.example",
+    "!.env.sample",
+    ".mypy_cache/",
+    ".pytest_cache/",
+    ".ruff_cache/",
+    ".tox/",
+    ".venv/",
+    "__pycache__/",
+    "build/",
+    "dist/",
+    "env/",
+    "venv/",
+]
+
+
 class Repository:
-    def __init__(self, path: str = ".") -> None:
+    def __init__(self, path: str = ".", fetch: bool = True) -> None:
         self.path = path
 
         if not self.is_git_installed():
@@ -12,7 +34,8 @@ class Repository:
         if not self.is_git_repo:
             raise ValueError(f"{self.path} is not a Git repository.")
 
-        self.fetch()
+        if fetch:
+            self.fetch()
 
     @staticmethod
     def is_git_installed() -> bool:
@@ -30,7 +53,33 @@ class Repository:
 
     def fetch(self) -> None:
         """Fetch latest updates from the remote."""
-        subprocess.run(["git", "fetch"], cwd=self.path, check=True)  # noqa: S607
+        command = ["git", "fetch"]
+        result = subprocess.run(  # noqa: S603
+            command,
+            cwd=self.path,
+            capture_output=True,
+            text=True,
+        )
+        if result.returncode == 0:
+            return
+        if "No remote repository specified" in result.stderr:
+            return
+        details = result.stderr.strip() or result.stdout.strip() or "no output"
+        raise ValueError(
+            f"Git fetch failed with exit code {result.returncode} "
+            f"for command {command!r}: {details}"
+        )
+
+    @classmethod
+    def initialize(cls, path: str = ".") -> Repository:
+        """Initialize a Git repository and create an initial commit if needed."""
+        if not cls.is_git_installed():
+            raise ValueError("Git is not installed or not found in your PATH.")
+
+        subprocess.run(["git", "init"], cwd=path, check=True)  # noqa: S607
+        repository = cls(path=path, fetch=False)
+        repository.create_initial_commit_if_needed()
+        return repository
 
     def status(self) -> str:
         """Get the git status in porcelain format."""
@@ -48,6 +97,7 @@ class Repository:
                 ["git", "rev-parse", "--is-inside-work-tree"],  # noqa: S607
                 cwd=self.path,
                 encoding="utf-8",
+                stderr=subprocess.DEVNULL,
             )
             return True
         except subprocess.CalledProcessError:
@@ -70,6 +120,74 @@ class Repository:
             return False
         return True
 
+    def has_commits(self) -> bool:
+        """Return True if the repository has at least one commit."""
+        try:
+            subprocess.run(
+                ["git", "rev-parse", "--verify", "HEAD"],  # noqa: S607
+                cwd=self.path,
+                capture_output=True,
+                check=True,
+                text=True,
+            )
+            return True
+        except subprocess.CalledProcessError:
+            return False
+
+    def create_initial_commit_if_needed(self) -> bool:
+        """Create a local initial commit when the repository has no commits."""
+        if self.has_commits():
+            return False
+
+        self._ensure_initial_commit_excludes()
+        subprocess.run(["git", "add", "."], cwd=self.path, check=True)  # noqa: S607
+        command = [
+            "git",
+            "-c",
+            "user.name=CrewAI",
+            "-c",
+            "user.email=deploy@crewai.com",
+            "commit",
+            "--allow-empty",
+            "-m",
+            "Initial crew",
+        ]
+        subprocess.run(  # noqa: S603
+            command,
+            cwd=self.path,
+            check=True,
+        )
+        return True
+
+    def _ensure_initial_commit_excludes(self) -> None:
+        """Add local-only ignore patterns before auto-staging an initial commit."""
+        exclude_file = Path(self.path) / ".git" / "info" / "exclude"
+        exclude_file.parent.mkdir(parents=True, exist_ok=True)
+        existing = exclude_file.read_text() if exclude_file.exists() else ""
+        existing_lines = set(existing.splitlines())
+        missing_patterns = [
+            pattern
+            for pattern in _INITIAL_COMMIT_EXCLUDE_PATTERNS
+            if pattern not in existing_lines
+        ]
+        if not missing_patterns:
+            return
+
+        prefix = "" if existing.endswith("\n") or not existing else "\n"
+        patterns = "\n".join(missing_patterns)
+        exclude_file.write_text(
+            f"{existing}{prefix}# CrewAI deploy auto-commit excludes\n{patterns}\n"
+        )
+
+    def deployable_files(self) -> list[str]:
+        """Return files tracked by Git or untracked and not ignored."""
+        output = subprocess.check_output(
+            ["git", "ls-files", "--cached", "--others", "--exclude-standard"],  # noqa: S607
+            cwd=self.path,
+            encoding="utf-8",
+        )
+        return [line for line in output.splitlines() if line]
+
     def origin_url(self) -> str | None:
         """Get the Git repository's remote URL."""
         try:

lib/cli/src/crewai_cli/install_crew.py

@@ -1,20 +1,77 @@
+from pathlib import Path
 import subprocess
 
 import click
 
-from crewai_cli.utils import build_env_with_all_tool_credentials
+from crewai_cli.deploy.validate import normalize_package_name
+from crewai_cli.utils import build_env_with_all_tool_credentials, parse_toml
+
+
+def _find_json_crew_file(project_root: Path | None = None) -> Path | None:
+    """Return the JSON crew definition path when present."""
+    root = project_root or Path.cwd()
+    for filename in ("crew.jsonc", "crew.json"):
+        crew_path = root / filename
+        if crew_path.is_file():
+            return crew_path
+    return None
+
+
+def _is_json_crew_project(project_root: Path | None = None) -> bool:
+    """Return True for JSON crew projects that do not need package install."""
+    root = project_root or Path.cwd()
+    if _find_json_crew_file(root) is None:
+        return False
+
+    pyproject_path = root / "pyproject.toml"
+    if not pyproject_path.is_file():
+        return True
+
+    try:
+        pyproject = parse_toml(pyproject_path.read_text())
+    except Exception:
+        return True
+    if not isinstance(pyproject, dict):
+        return True
+
+    tool_config = pyproject.get("tool") or {}
+    crewai_config = tool_config.get("crewai") if isinstance(tool_config, dict) else None
+    declared_type = (
+        crewai_config.get("type") if isinstance(crewai_config, dict) else None
+    )
+    project_config = pyproject.get("project") or {}
+    project_name = (
+        project_config.get("name") if isinstance(project_config, dict) else None
+    )
+    if isinstance(project_name, str):
+        package_name = normalize_package_name(project_name)
+        if package_name and (root / "src" / package_name / "crew.py").is_file():
+            return False
+
+    return declared_type != "flow"
 
 
 # Be mindful about changing this.
 # on some environments we don't use this command but instead uv sync directly
 # so if you expect this to support more things you will need to replicate it there
 # ask @joaomdmoura if you are unsure
-def install_crew(proxy_options: list[str]) -> None:
+def install_crew(
+    proxy_options: list[str],
+    *,
+    raise_on_error: bool = False,
+    install_project: bool | None = None,
+) -> None:
     """
     Install the crew by running the UV command to lock and install.
     """
     try:
-        command = ["uv", "sync", *proxy_options]
+        if install_project is None:
+            install_project = not _is_json_crew_project()
+
+        command = ["uv", "sync"]
+        if not install_project and "--no-install-project" not in proxy_options:
+            command.append("--no-install-project")
+        command.extend(proxy_options)
 
         # Inject tool repository credentials so uv can authenticate
         # against private package indexes (e.g. crewai tool repository).
@@ -22,11 +79,21 @@ def install_crew(proxy_options: list[str]) -> None:
         # project depends on tools from a private index.
         env = build_env_with_all_tool_credentials()
 
-        subprocess.run(command, check=True, capture_output=False, text=True, env=env)  # noqa: S603
+        subprocess.run(  # noqa: S603
+            command,
+            check=True,
+            capture_output=False,
+            text=True,
+            env=env,
+        )
 
     except subprocess.CalledProcessError as e:
         click.echo(f"An error occurred while running the crew: {e}", err=True)
         click.echo(e.output, err=True)
+        if raise_on_error:
+            raise
 
     except Exception as e:
         click.echo(f"An unexpected error occurred: {e}", err=True)
+        if raise_on_error:
+            raise

lib/cli/src/crewai_cli/plus_api.py

@@ -1,12 +1,95 @@
-"""Re-export of ``crewai_core.plus_api.PlusAPI``.
-
-Kept as a stable import path for the CLI; new code should import from
-``crewai_core.plus_api`` directly.
-"""
+"""CrewAI CLI API client extensions."""
 
 from __future__ import annotations
 
-from crewai_core.plus_api import PlusAPI as PlusAPI
+from pathlib import Path
+from typing import Any, Literal, cast
+from urllib.parse import urljoin
+
+from crewai_core.plus_api import PlusAPI as _CorePlusAPI
+import httpx
+
+
+HttpMethod = Literal["GET", "POST", "PATCH", "DELETE"]
+
+
+class PlusAPI(_CorePlusAPI):
+    """CLI API client.
+
+    The ZIP deployment methods live here as well as in newer crewai-core
+    versions so editable CLI installs still work when an older crewai-core is
+    present in the runtime environment.
+    """
+
+    def _make_multipart_request(
+        self,
+        method: HttpMethod,
+        endpoint: str,
+        *,
+        zip_file_path: str | Path,
+        data: dict[str, str] | None = None,
+        timeout: float | None = None,
+        verify: bool = True,
+    ) -> httpx.Response:
+        """Send an authenticated multipart request containing a project ZIP."""
+        url = urljoin(self.base_url, endpoint)
+        headers = dict(cast(dict[str, str], self.headers))
+        headers.pop("Content-Type", None)
+        path = Path(zip_file_path)
+        request_kwargs: dict[str, Any] = {"headers": headers}
+        if data is not None:
+            request_kwargs["data"] = data
+        if timeout is not None:
+            request_kwargs["timeout"] = timeout
+
+        with (
+            path.open("rb") as file_handle,
+            httpx.Client(trust_env=False, verify=verify) as client,
+        ):
+            files = {
+                "zip_file": (path.name, file_handle, "application/zip"),
+            }
+            return client.request(method, url, files=files, **request_kwargs)
+
+    def create_crew_from_zip(
+        self,
+        zip_file_path: str | Path,
+        *,
+        name: str | None = None,
+        env: dict[str, str] | None = None,
+    ) -> httpx.Response:
+        """Create a crew deployment from a local project ZIP archive."""
+        data: dict[str, str] = {}
+        if name:
+            data["name"] = name
+        if env:
+            data.update({f"env[{key}]": value for key, value in env.items()})
+        return self._make_multipart_request(
+            "POST",
+            f"{self.CREWS_RESOURCE}/zip",
+            zip_file_path=zip_file_path,
+            data=data or None,
+            timeout=300,
+        )
+
+    def update_crew_from_zip(
+        self,
+        uuid: str,
+        zip_file_path: str | Path,
+        *,
+        env: dict[str, str] | None = None,
+    ) -> httpx.Response:
+        """Update an existing crew deployment from a local project ZIP archive."""
+        data: dict[str, str] = {}
+        if env:
+            data.update({f"env[{key}]": value for key, value in env.items()})
+        return self._make_multipart_request(
+            "POST",
+            f"{self.CREWS_RESOURCE}/{uuid}/zip_update",
+            zip_file_path=zip_file_path,
+            data=data or None,
+            timeout=300,
+        )
 
 
 __all__ = ["PlusAPI"]

lib/cli/src/crewai_cli/run_crew.py

@@ -1,25 +1,475 @@
+from __future__ import annotations
+
+from contextlib import AbstractContextManager, nullcontext
 from enum import Enum
+import os
+from pathlib import Path
+import re
 import subprocess
+import sys
+from typing import TYPE_CHECKING, Any
 
 import click
+from crewai.project.json_loader import find_crew_json_file
 from crewai_core.constants import CREWAI_TRAINED_AGENTS_FILE_ENV
 from packaging import version
 
-from crewai_cli.utils import build_env_with_all_tool_credentials, read_toml
+from crewai_cli.utils import (
+    build_env_with_all_tool_credentials,
+    enable_prompt_line_editing,
+    read_toml,
+)
 from crewai_cli.version import get_crewai_version
 
 
+if TYPE_CHECKING:
+    from crewai_cli.crew_run_tui import CrewRunApp
+
+
 class CrewType(Enum):
     STANDARD = "standard"
     FLOW = "flow"
 
 
-def run_crew(trained_agents_file: str | None = None) -> None:
-    """Run the crew or flow by running a command in the UV environment.
+# Must accept the same names as the kickoff interpolation pattern in
+# crewai.utilities.string_utils (_VARIABLE_PATTERN), including hyphens —
+# otherwise placeholders are interpolated at runtime but never prompted for.
+_INPUT_PLACEHOLDER_RE = re.compile(r"(?<!{){([A-Za-z_][A-Za-z0-9_\-]*)}(?!})")
+_CREWAI_CLI_RUNNER_PACKAGE_DIR_ENV = "CREWAI_CLI_RUNNER_PACKAGE_DIR"
+_CREWAI_RUNNER_SOURCE_DIR_ENV = "CREWAI_RUNNER_SOURCE_DIR"
+_JSON_CREW_RUNNER_CODE = """
+import importlib.util
+import os
+from pathlib import Path
+import sys
 
-    Starting from version 0.103.0, this command can be used to run both
-    standard crews and flows. For flows, it detects the type from pyproject.toml
-    and automatically runs the appropriate command.
+source_dir = os.environ.get("CREWAI_RUNNER_SOURCE_DIR")
+if source_dir:
+    sys.path.insert(0, source_dir)
+
+package_dir = Path(os.environ["CREWAI_CLI_RUNNER_PACKAGE_DIR"])
+package_spec = importlib.util.spec_from_file_location(
+    "crewai_cli",
+    package_dir / "__init__.py",
+    submodule_search_locations=[str(package_dir)],
+)
+if package_spec is None or package_spec.loader is None:
+    raise ImportError(f"Cannot load CrewAI CLI package from {package_dir}")
+
+package = importlib.util.module_from_spec(package_spec)
+sys.modules["crewai_cli"] = package
+package_spec.loader.exec_module(package)
+
+module_path = package_dir / "run_crew.py"
+module_spec = importlib.util.spec_from_file_location("crewai_cli.run_crew", module_path)
+if module_spec is None or module_spec.loader is None:
+    raise ImportError(f"Cannot load CrewAI CLI runner from {module_path}")
+
+module = importlib.util.module_from_spec(module_spec)
+sys.modules["crewai_cli.run_crew"] = module
+module_spec.loader.exec_module(module)
+
+from crewai_core.constants import CREWAI_TRAINED_AGENTS_FILE_ENV
+
+module._run_json_crew(
+    trained_agents_file=os.getenv(CREWAI_TRAINED_AGENTS_FILE_ENV)
+)
+""".strip()
+
+
+def _has_json_crew() -> bool:
+    """Check if this is a JSON-defined crew project.
+
+    The project type declared in pyproject.toml wins: a flow project that
+    happens to contain a crew.json(c) file still runs as a flow. A missing
+    or unreadable pyproject means a bare JSON crew project.
+    """
+    if find_crew_json_file() is None:
+        return False
+    try:
+        pyproject_data = read_toml()
+    except Exception:
+        return True
+    declared_type: str | None = (
+        pyproject_data.get("tool", {}).get("crewai", {}).get("type")
+    )
+    return declared_type != "flow"
+
+
+def _extract_input_placeholders(text: str | None) -> set[str]:
+    if not text:
+        return set()
+    return set(_INPUT_PLACEHOLDER_RE.findall(text))
+
+
+def _missing_input_names(crew: Any, inputs: dict[str, Any]) -> list[str]:
+    """Return input placeholders used by a crew but not provided as defaults."""
+    placeholders: set[str] = set()
+
+    for agent in getattr(crew, "agents", []) or []:
+        placeholders.update(_extract_input_placeholders(getattr(agent, "role", None)))
+        placeholders.update(_extract_input_placeholders(getattr(agent, "goal", None)))
+        placeholders.update(
+            _extract_input_placeholders(getattr(agent, "backstory", None))
+        )
+
+    for task in getattr(crew, "tasks", []) or []:
+        placeholders.update(
+            _extract_input_placeholders(getattr(task, "description", None))
+        )
+        placeholders.update(
+            _extract_input_placeholders(getattr(task, "expected_output", None))
+        )
+        placeholders.update(
+            _extract_input_placeholders(getattr(task, "output_file", None))
+        )
+
+    return sorted(name for name in placeholders if name not in inputs)
+
+
+def _prompt_for_missing_inputs(
+    crew: Any, default_inputs: dict[str, Any]
+) -> dict[str, Any]:
+    """Ask for runtime values for placeholders that lack default inputs."""
+    inputs = dict(default_inputs or {})
+    missing = _missing_input_names(crew, inputs)
+    if not missing:
+        return inputs
+
+    enable_prompt_line_editing()
+
+    click.echo()
+    click.secho("  Runtime inputs", fg="cyan", bold=True)
+    click.secho(
+        "  Values for {placeholder} references in your agents and tasks.",
+        dim=True,
+    )
+
+    for name in missing:
+        inputs[name] = click.prompt(
+            click.style(f"  {name}", fg="cyan"),
+            prompt_suffix=click.style(" > ", fg="bright_white"),
+        )
+
+    return inputs
+
+
+def _json_loading_status(message: str) -> AbstractContextManager[Any]:
+    from rich.console import Console
+    from rich.text import Text
+
+    console = Console()
+    if not console.is_terminal:
+        return nullcontext()
+    return console.status(
+        Text(f"  {message}", style="bold #1F7982"),
+        spinner="dots",
+    )
+
+
+def _load_json_crew(crew_path: Path) -> tuple[Any, dict[str, Any]]:
+    from crewai.project.crew_loader import load_crew
+
+    return load_crew(crew_path)
+
+
+def _load_json_crew_for_tui(
+    crew_path: Path,
+) -> tuple[type[Any], Any, dict[str, Any], list[str], list[str]]:
+    with _json_loading_status("Preparing crew..."):
+        from crewai_cli.crew_run_tui import CrewRunApp
+
+        crew, default_inputs = _load_json_crew(crew_path)
+        _prepare_json_crew_for_tui(crew)
+        task_names = [
+            getattr(task, "name", "") or getattr(task, "description", "")[:40] or "Task"
+            for task in crew.tasks
+        ]
+        agent_names = [
+            getattr(agent, "role", "") or getattr(agent, "name", "") or "Agent"
+            for agent in crew.agents
+        ]
+
+    return CrewRunApp, crew, default_inputs, task_names, agent_names
+
+
+def _prepare_json_crew_for_tui(crew: Any) -> None:
+    """Apply the same quiet/streaming setup used by the TUI JSON loader."""
+    crew.verbose = False
+    for agent in crew.agents:
+        agent.verbose = False
+        if hasattr(agent, "llm") and hasattr(agent.llm, "stream"):
+            agent.llm.stream = True
+
+
+def _run_json_crew(trained_agents_file: str | None = None) -> Any:
+    """Load and run a JSON-defined crew."""
+    from dotenv import load_dotenv
+
+    env_file = Path.cwd() / ".env"
+    if env_file.exists():
+        load_dotenv(env_file, override=True)
+
+    # JSON crews run in-process, so export the trained-agents file directly
+    # instead of forwarding it to a subprocess like classic crews do.
+    if trained_agents_file:
+        os.environ[CREWAI_TRAINED_AGENTS_FILE_ENV] = trained_agents_file
+
+    crew_path = find_crew_json_file()
+    if crew_path is None:
+        raise FileNotFoundError("No crew.jsonc or crew.json found")
+
+    crew_run_app_cls, crew, default_inputs, task_names, agent_names = (
+        _load_json_crew_for_tui(crew_path)
+    )
+    runtime_inputs = _prompt_for_missing_inputs(crew, default_inputs)
+
+    app = crew_run_app_cls(
+        crew_name=crew.name or "Crew",
+        total_tasks=len(crew.tasks),
+        agent_names=agent_names,
+        task_names=task_names,
+    )
+    app._crew = crew
+    app._default_inputs = runtime_inputs
+
+    app.run()
+
+    _print_post_tui_summary(app)
+
+    if app._status == "failed":
+        # Mirror the classic subprocess path: a failed crew must produce a
+        # non-zero exit code so scripts and CI don't treat it as success.
+        raise SystemExit(1)
+
+    if app._status not in ("completed", "failed"):
+        # User quit mid-run. kickoff runs in a thread worker that cannot be
+        # force-cancelled, so end the process to stop in-flight LLM and tool
+        # work instead of letting it burn tokens in the background.
+        click.secho("\n  Run cancelled.", fg="yellow")
+        sys.stdout.flush()
+        os._exit(130)
+
+    if getattr(app, "_want_deploy", False):
+        _chain_deploy()
+
+    return app._crew_result
+
+
+def _has_lockfile(project_root: Path | None = None) -> bool:
+    """Return True when the project already has a dependency lockfile."""
+    return _has_uv_lockfile(project_root) or _has_poetry_lockfile(project_root)
+
+
+def _has_uv_lockfile(project_root: Path | None = None) -> bool:
+    """Return True when the project has a uv lockfile."""
+    root = project_root or Path.cwd()
+    return (root / "uv.lock").is_file()
+
+
+def _has_poetry_lockfile(project_root: Path | None = None) -> bool:
+    """Return True when the project has a Poetry lockfile."""
+    root = project_root or Path.cwd()
+    return (root / "poetry.lock").is_file()
+
+
+def _uses_poetry_lockfile(project_root: Path | None = None) -> bool:
+    """Return True when Poetry is the only available lock source."""
+    return _has_poetry_lockfile(project_root) and not _has_uv_lockfile(project_root)
+
+
+def _has_project_venv(project_root: Path | None = None) -> bool:
+    """Return True when the project already has a local uv environment."""
+    root = project_root or Path.cwd()
+    return (root / ".venv").is_dir()
+
+
+def _install_json_crew_dependencies_if_needed() -> None:
+    """Prepare JSON crew dependencies without mutating existing lockfiles."""
+    project_root = Path.cwd()
+    if not (project_root / "pyproject.toml").is_file():
+        return
+
+    has_uv_lockfile = _has_uv_lockfile(project_root)
+    has_lockfile = has_uv_lockfile or _has_poetry_lockfile(project_root)
+    if has_lockfile and _has_project_venv(project_root):
+        return
+    if _uses_poetry_lockfile(project_root):
+        return
+
+    from crewai_cli.install_crew import install_crew
+
+    try:
+        if has_uv_lockfile:
+            click.echo("Syncing dependencies from lockfile...")
+            install_crew(["--frozen"], raise_on_error=True)
+        else:
+            click.echo("Installing dependencies...")
+            install_crew([], raise_on_error=True)
+    except subprocess.CalledProcessError as e:
+        raise SystemExit(e.returncode) from e
+    except Exception as e:
+        raise SystemExit(1) from e
+
+
+def _find_local_crewai_source_dir() -> Path | None:
+    """Return the repo's CrewAI source dir when running from a source checkout."""
+    for parent in Path(__file__).resolve().parents:
+        candidate = parent / "lib" / "crewai" / "src"
+        if (candidate / "crewai" / "project" / "json_loader.py").is_file():
+            return candidate
+    return None
+
+
+def _json_crew_run_command(project_root: Path | None = None) -> list[str]:
+    """Return the project-environment command for running JSON crews."""
+    if _uses_poetry_lockfile(project_root):
+        return ["poetry", "run", "python", "-c", _JSON_CREW_RUNNER_CODE]
+    return ["uv", "run", "--no-sync", "python", "-c", _JSON_CREW_RUNNER_CODE]
+
+
+def _run_json_crew_in_project_env(trained_agents_file: str | None = None) -> Any:
+    """Run JSON crews from the project's uv-managed environment."""
+    if not (Path.cwd() / "pyproject.toml").is_file():
+        return _run_json_crew(trained_agents_file=trained_agents_file)
+
+    _install_json_crew_dependencies_if_needed()
+
+    command = _json_crew_run_command()
+    env = build_env_with_all_tool_credentials()
+    env[_CREWAI_CLI_RUNNER_PACKAGE_DIR_ENV] = str(Path(__file__).resolve().parent)
+    if local_crewai_source_dir := _find_local_crewai_source_dir():
+        env[_CREWAI_RUNNER_SOURCE_DIR_ENV] = str(local_crewai_source_dir)
+    if trained_agents_file:
+        env[CREWAI_TRAINED_AGENTS_FILE_ENV] = trained_agents_file
+
+    try:
+        subprocess.run(  # noqa: S603
+            command,
+            capture_output=False,
+            text=True,
+            check=True,
+            env=env,
+        )
+    except subprocess.CalledProcessError as e:
+        raise SystemExit(e.returncode) from e
+    except Exception as e:
+        click.echo(f"An unexpected error occurred while running the JSON crew: {e}")
+        raise SystemExit(1) from e
+
+    return None
+
+
+def _chain_deploy() -> None:
+    from rich.console import Console
+
+    console = Console()
+
+    def print_system_exit_failure(exc: SystemExit) -> None:
+        if isinstance(exc.code, int):
+            detail = f" with exit code {exc.code}"
+        elif exc.code:
+            detail = f": {exc.code}"
+        else:
+            detail = ""
+        console.print(f"\nDeploy failed{detail}\n", style="bold red")
+
+    try:
+        from crewai_cli.command import AuthenticationRequiredError
+        from crewai_cli.deploy.main import DeployCommand
+
+        console.print("\nStarting deployment…\n", style="bold #FF5A50")
+        DeployCommand().create_crew(confirm=True, skip_validate=True)
+    except AuthenticationRequiredError:
+        from crewai_cli.authentication.main import AuthenticationCommand
+
+        console.print()
+        AuthenticationCommand().login()
+        try:
+            DeployCommand().create_crew(confirm=True, skip_validate=True)
+        except AuthenticationRequiredError:
+            console.print(
+                "\nDeploy failed: authentication is still required.\n",
+                style="bold red",
+            )
+        except SystemExit as e:
+            print_system_exit_failure(e)
+        except Exception as e:
+            console.print(f"\nDeploy failed: {e}\n", style="bold red")
+    except SystemExit as e:
+        print_system_exit_failure(e)
+    except Exception as e:
+        console.print(f"\nDeploy failed: {e}\n", style="bold red")
+
+
+def _print_post_tui_summary(app: CrewRunApp) -> None:
+    """Print a summary to the terminal after the Textual TUI exits."""
+    import time
+
+    from rich.console import Console
+    from rich.markdown import Markdown
+    from rich.padding import Padding
+    from rich.panel import Panel
+    from rich.text import Text
+
+    console = Console()
+    elapsed = time.time() - app._start_time
+
+    out_tokens = app._output_tokens + app._live_out_tokens
+    token_parts = []
+    if app._input_tokens:
+        token_parts.append(f"↑{app._input_tokens:,}")
+    if out_tokens:
+        token_parts.append(f"↓{out_tokens:,}")
+    token_str = "  ".join(token_parts)
+    if token_str:
+        token_str += " tokens"
+
+    crewai_red = "#FF5A50"
+    crewai_teal = "#1F7982"
+
+    if app._status == "completed":
+        summary = Text()
+        summary.append(
+            f"  ✔ Completed {app._total_tasks} tasks",
+            style=f"bold {crewai_teal}",
+        )
+        summary.append(f" in {elapsed:.1f}s", style="dim")
+        if token_str:
+            summary.append(f"  {token_str}", style="dim")
+        console.print(
+            Panel(
+                summary,
+                title=f" {app._crew_name} ",
+                title_align="left",
+                border_style=crewai_teal,
+                padding=(0, 1),
+            )
+        )
+        if app._final_output:
+            console.print()
+            console.print(Text("  Final Result", style=f"bold {crewai_teal}"))
+            console.print()
+            console.print(Padding(Markdown(app._final_output), (0, 2)))
+    elif app._status == "failed":
+        content = Text()
+        content.append("  ✘ Failed", style=f"bold {crewai_red}")
+        content.append(f" after {elapsed:.1f}s\n", style="dim")
+        if app._error:
+            content.append(f"\n  {app._error}\n", style=crewai_red)
+        console.print(
+            Panel(
+                content,
+                title=f" {app._crew_name} ",
+                title_align="left",
+                border_style=crewai_red,
+                padding=(0, 1),
+            )
+        )
+
+
+def run_crew(trained_agents_file: str | None = None) -> None:
+    """Run the crew or flow.
 
     Args:
         trained_agents_file: Optional path to a trained-agents pickle produced
@@ -27,6 +477,11 @@ def run_crew(trained_agents_file: str | None = None) -> None:
             ``CREWAI_TRAINED_AGENTS_FILE`` so agents load suggestions from this
             file instead of the default ``trained_agents_data.pkl``.
     """
+    # JSON crew projects take precedence
+    if _has_json_crew():
+        _run_json_crew_in_project_env(trained_agents_file=trained_agents_file)
+        return
+
     crewai_version = get_crewai_version()
     min_required_version = "0.71.0"
     pyproject_data = read_toml()

lib/cli/src/crewai_cli/run_flow_definition.py

@@ -0,0 +1,113 @@
+from __future__ import annotations
+
+import json
+from pathlib import Path
+from typing import Any
+
+import click
+
+
+def run_flow_definition(definition: str, inputs: str | None = None) -> None:
+    """Run a flow from a Flow Definition YAML/JSON string or file path."""
+    try:
+        from crewai.flow.flow import Flow
+        from crewai.flow.flow_definition import FlowDefinition
+    except ImportError as exc:
+        click.echo(
+            "Running flows from definitions requires the full crewai package.",
+            err=True,
+        )
+        raise SystemExit(1) from exc
+
+    parsed_inputs = _parse_inputs(inputs)
+    definition_source = _read_definition_source(definition)
+
+    try:
+        flow_definition = _parse_flow_definition(FlowDefinition, definition_source)
+        flow = Flow.from_definition(flow_definition)
+        result = flow.kickoff(inputs=parsed_inputs)
+    except Exception as exc:
+        click.echo(
+            f"An error occurred while running the flow definition: {exc}", err=True
+        )
+        raise SystemExit(1) from exc
+
+    click.echo(_format_result(result))
+
+
+def _parse_inputs(inputs: str | None) -> dict[str, Any] | None:
+    if inputs is None:
+        return None
+
+    try:
+        parsed = json.loads(inputs)
+    except json.JSONDecodeError as exc:
+        click.echo(f"Invalid --inputs JSON: {exc}", err=True)
+        raise SystemExit(1) from exc
+
+    if not isinstance(parsed, dict):
+        click.echo("Invalid --inputs JSON: expected an object.", err=True)
+        raise SystemExit(1)
+
+    return parsed
+
+
+def _read_definition_source(definition: str) -> str:
+    path = Path(definition).expanduser()
+    try:
+        is_file = path.is_file()
+    except OSError as exc:
+        if _looks_like_inline_definition(definition):
+            return definition
+        click.echo(f"Invalid --definition path: {definition} ({exc})", err=True)
+        raise SystemExit(1) from exc
+
+    if is_file:
+        try:
+            return path.read_text(encoding="utf-8")
+        except (OSError, UnicodeError) as exc:
+            click.echo(
+                f"Unable to read --definition path {path}: {exc}",
+                err=True,
+            )
+            raise SystemExit(1) from exc
+
+    try:
+        if path.exists():
+            click.echo(
+                f"Invalid --definition path: {definition} is not a file.", err=True
+            )
+            raise SystemExit(1)
+    except OSError as exc:
+        click.echo(f"Invalid --definition path: {definition} ({exc})", err=True)
+        raise SystemExit(1) from exc
+
+    return definition
+
+
+def _looks_like_inline_definition(definition: str) -> bool:
+    stripped = definition.lstrip()
+    return "\n" in definition or stripped.startswith(("{", "---")) or ":" in stripped
+
+
+def _parse_flow_definition(flow_definition_cls: type[Any], source: str) -> Any:
+    if _looks_like_json(source):
+        return flow_definition_cls.from_json(source)
+
+    return flow_definition_cls.from_yaml(source)
+
+
+def _looks_like_json(source: str) -> bool:
+    stripped = source.lstrip()
+    return stripped.startswith("{")
+
+
+def _format_result(result: Any) -> str:
+    raw_result = getattr(result, "raw", result)
+    if isinstance(raw_result, str):
+        return raw_result
+
+    try:
+        return json.dumps(raw_result, default=str)
+    except TypeError:
+        return str(raw_result)

lib/cli/src/crewai_cli/templates/crew/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]==1.14.7rc2"
+    "crewai[tools]==1.14.7"
 ]
 
 [project.scripts]

lib/cli/src/crewai_cli/templates/flow/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]==1.14.7rc2"
+    "crewai[tools]==1.14.7"
 ]
 
 [project.scripts]

lib/cli/src/crewai_cli/templates/tool/pyproject.toml

@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]==1.14.7rc2"
+    "crewai[tools]==1.14.7"
 ]
 
 [tool.crewai]

lib/cli/src/crewai_cli/tui_picker.py

@@ -0,0 +1,419 @@
+"""Arrow-key interactive pickers for CLI prompts."""
+
+from __future__ import annotations
+
+from contextlib import suppress
+import sys
+from typing import overload
+
+import click
+
+
+# CrewAI brand: primary=#FF5A50 (coral), teal=#1F7982
+_CORAL = "\033[38;2;255;90;80m"  # #FF5A50
+_TEAL = "\033[38;2;31;121;130m"  # #1F7982
+_BOLD = "\033[1m"
+_DIM = "\033[2m"
+_RESET = "\033[0m"
+_HIDE_CURSOR = "\033[?25l"
+_SHOW_CURSOR = "\033[?25h"
+
+
+def _is_interactive() -> bool:
+    try:
+        return sys.stdin.isatty() and sys.stdout.isatty()
+    except Exception:
+        return False
+
+
+def _read_key() -> str:
+    if sys.platform == "win32":
+        import msvcrt
+
+        ch = msvcrt.getwch()
+        if ch in ("\x00", "\xe0"):
+            ch2 = msvcrt.getwch()
+            return {"H": "up", "P": "down"}.get(ch2, "")
+        if ch == "\r":
+            return "enter"
+        if ch == " ":
+            return "space"
+        if ch == "\x03":
+            raise KeyboardInterrupt
+        return ch
+
+    import termios
+    import tty
+
+    fd = sys.stdin.fileno()
+    old = termios.tcgetattr(fd)
+    try:
+        tty.setcbreak(fd)
+        ch = sys.stdin.read(1)
+        if ch == "\x1b":
+            seq = sys.stdin.read(2)
+            if seq == "[A":
+                return "up"
+            if seq == "[B":
+                return "down"
+            return "esc"
+        if ch in ("\r", "\n"):
+            return "enter"
+        if ch == " ":
+            return "space"
+        if ch == "\x03":
+            raise KeyboardInterrupt
+        return ch
+    finally:
+        termios.tcsetattr(fd, termios.TCSADRAIN, old)
+
+
+def _clear_lines(n: int) -> None:
+    sys.stdout.write(f"\033[{n}A")
+    for _ in range(n):
+        sys.stdout.write("\033[2K\n")
+    sys.stdout.write(f"\033[{n}A")
+    sys.stdout.flush()
+
+
+def _draw_single(labels: list[str], cursor: int, *, clear: bool = False) -> None:
+    total = len(labels)
+    if clear:
+        sys.stdout.write(f"\033[{total}A")
+    for i, label in enumerate(labels):
+        if i == cursor:
+            sys.stdout.write(f"\033[2K  {_CORAL}→{_RESET} {_BOLD}{label}{_RESET}\n")
+        else:
+            sys.stdout.write(f"\033[2K    {label}\n")
+    sys.stdout.flush()
+
+
+def _draw_multi(
+    labels: list[str],
+    cursor: int,
+    selected: set[int],
+    *,
+    action_indices: set[int] | None = None,
+    separator_indices: set[int] | None = None,
+    clear: bool = False,
+) -> None:
+    action_indices = action_indices or set()
+    separator_indices = separator_indices or set()
+    hint_text = "↑↓ navigate, space toggle, enter confirm"
+    if action_indices:
+        hint_text = "↑↓ navigate, space toggle, enter confirm, ▸ rows expand/collapse"
+    hint = f"  {_DIM}{hint_text}{_RESET}"
+    total = len(labels) + 1
+    if clear:
+        sys.stdout.write(f"\033[{total}A")
+    sys.stdout.write(f"\033[2K{hint}\n")
+    for i, label in enumerate(labels):
+        if i in separator_indices:
+            sys.stdout.write(f"\033[2K      {_TEAL}{label}{_RESET}\n")
+            continue
+        if i in action_indices:
+            check = "  "
+        elif i in selected:
+            check = f"{_CORAL}[x]{_RESET}"
+        else:
+            check = "[ ]"
+        arrow = f"{_CORAL}→{_RESET} " if i == cursor else "  "
+        bold = f"{_BOLD}{label}{_RESET}" if i == cursor else label
+        sys.stdout.write(f"\033[2K    {arrow}{check} {bold}\n")
+    sys.stdout.flush()
+
+
+def _arrow_select_one(labels: list[str]) -> int:
+    cursor = 0
+    total = len(labels)
+    sys.stdout.write(_HIDE_CURSOR)
+    sys.stdout.flush()
+    try:
+        _draw_single(labels, cursor)
+        while True:
+            key = _read_key()
+            if key == "up" and cursor > 0:
+                cursor -= 1
+                _draw_single(labels, cursor, clear=True)
+            elif key == "down" and cursor < total - 1:
+                cursor += 1
+                _draw_single(labels, cursor, clear=True)
+            elif key == "enter":
+                _clear_lines(total)
+                return cursor
+            elif key in ("esc", "q"):
+                _clear_lines(total)
+                return -1
+    finally:
+        sys.stdout.write(_SHOW_CURSOR)
+        sys.stdout.flush()
+
+
+def _arrow_select_multi(
+    labels: list[str],
+    *,
+    action_indices: set[int] | None = None,
+    separator_indices: set[int] | None = None,
+    preselected: set[int] | None = None,
+    initial_cursor: int | None = None,
+) -> tuple[list[int], int | None]:
+    total = len(labels)
+    selected: set[int] = set(preselected or ())
+    action_indices = action_indices or set()
+    separator_indices = separator_indices or set()
+    if initial_cursor is not None and 0 <= initial_cursor < total:
+        cursor = initial_cursor
+    else:
+        cursor = _first_selectable_index(total, separator_indices)
+    sys.stdout.write(_HIDE_CURSOR)
+    sys.stdout.flush()
+    try:
+        _draw_multi(
+            labels,
+            cursor,
+            selected,
+            action_indices=action_indices,
+            separator_indices=separator_indices,
+        )
+        while True:
+            key = _read_key()
+            if key == "up":
+                cursor = _next_selectable_index(cursor, -1, total, separator_indices)
+                _draw_multi(
+                    labels,
+                    cursor,
+                    selected,
+                    action_indices=action_indices,
+                    separator_indices=separator_indices,
+                    clear=True,
+                )
+            elif key == "down":
+                cursor = _next_selectable_index(cursor, 1, total, separator_indices)
+                _draw_multi(
+                    labels,
+                    cursor,
+                    selected,
+                    action_indices=action_indices,
+                    separator_indices=separator_indices,
+                    clear=True,
+                )
+            elif key == "space":
+                if cursor in action_indices:
+                    _clear_lines(total + 1)
+                    return sorted(selected), cursor
+                selected ^= {cursor}
+                _draw_multi(
+                    labels,
+                    cursor,
+                    selected,
+                    action_indices=action_indices,
+                    separator_indices=separator_indices,
+                    clear=True,
+                )
+            elif key == "enter":
+                _clear_lines(total + 1)
+                if cursor in action_indices:
+                    return sorted(selected), cursor
+                return sorted(selected), None
+            elif key in ("esc", "q"):
+                _clear_lines(total + 1)
+                return sorted(selected), None
+    finally:
+        sys.stdout.write(_SHOW_CURSOR)
+        sys.stdout.flush()
+
+
+def _numbered_select(labels: list[str]) -> int:
+    for idx, label in enumerate(labels, 1):
+        click.echo(f"    {idx}. {label}")
+    click.echo()
+    while True:
+        choice = click.prompt("  Select", type=str, default="1")
+        if choice.lower() == "q":
+            return -1
+        try:
+            num = int(choice)
+            if 1 <= num <= len(labels):
+                return num - 1
+        except ValueError:
+            # Non-numeric input falls through to the shared error message.
+            pass
+        click.secho(f"  Invalid choice. Enter 1-{len(labels)}.", fg="red")
+
+
+def _numbered_select_multi(
+    labels: list[str],
+    *,
+    action_indices: set[int] | None = None,
+    separator_indices: set[int] | None = None,
+    preselected: set[int] | None = None,
+) -> tuple[list[int], int | None]:
+    action_indices = action_indices or set()
+    separator_indices = separator_indices or set()
+    numbered_indices: list[int] = []
+    for idx, label in enumerate(labels):
+        if idx in separator_indices:
+            click.secho(f"    {label}", fg="cyan")
+            continue
+        numbered_indices.append(idx)
+        click.echo(f"    {len(numbered_indices)}. {label}")
+    click.echo()
+    raw = click.prompt(
+        "  Select (comma-separated numbers, or empty to skip)",
+        default="",
+        show_default=False,
+    )
+    if not raw.strip():
+        return sorted(preselected or ()), None
+    indices: list[int] = list(preselected or ())
+    for part in raw.split(","):
+        with suppress(ValueError):
+            num = int(part.strip())
+            if 1 <= num <= len(numbered_indices):
+                idx = numbered_indices[num - 1]
+                if idx in action_indices:
+                    return sorted(set(indices)), idx
+                indices.append(idx)
+    return sorted(set(indices)), None
+
+
+def _first_selectable_index(total: int, separator_indices: set[int]) -> int:
+    for idx in range(total):
+        if idx not in separator_indices:
+            return idx
+    return 0
+
+
+def _next_selectable_index(
+    cursor: int,
+    direction: int,
+    total: int,
+    separator_indices: set[int],
+) -> int:
+    next_cursor = cursor + direction
+    while 0 <= next_cursor < total:
+        if next_cursor not in separator_indices:
+            return next_cursor
+        next_cursor += direction
+    return cursor
+
+
+# ── Public API ──────────────────────────────────────────────────
+
+
+def pick(title: str, options: list[tuple[str, str]]) -> str | None:
+    """Arrow-key single-select picker.
+
+    Args:
+        title: Header text.
+        options: List of ``(value, description)`` tuples.
+
+    Returns:
+        The *value* of the selected option, or ``None`` if cancelled.
+    """
+    labels = [f"{value:<12s} {desc}" for value, desc in options]
+
+    click.echo()
+    click.secho(f"  {title}", fg="cyan", bold=True)
+    click.echo()
+
+    if _is_interactive():
+        try:
+            idx = _arrow_select_one(labels)
+        except Exception:
+            idx = _numbered_select(labels)
+    else:
+        idx = _numbered_select(labels)
+
+    if idx < 0:
+        return None
+
+    value, _desc = options[idx]
+    click.secho(f"  ✔ {value}", fg="green")
+    return value
+
+
+def pick_one(title: str, labels: list[str]) -> int:
+    """Arrow-key single-select from plain labels.
+
+    Returns:
+        Selected index, or ``-1`` if cancelled.
+    """
+    click.echo()
+    click.secho(f"  {title}", fg="cyan")
+
+    if _is_interactive():
+        try:
+            return _arrow_select_one(labels)
+        except Exception:
+            return _numbered_select(labels)
+    return _numbered_select(labels)
+
+
+@overload
+def pick_many(
+    title: str,
+    labels: list[str],
+    *,
+    separator_indices: set[int] | None = None,
+    preselected: set[int] | None = None,
+    initial_cursor: int | None = None,
+) -> list[int]: ...
+
+
+@overload
+def pick_many(
+    title: str,
+    labels: list[str],
+    *,
+    action_indices: set[int],
+    separator_indices: set[int] | None = None,
+    preselected: set[int] | None = None,
+    initial_cursor: int | None = None,
+) -> tuple[list[int], int | None]: ...
+
+
+def pick_many(
+    title: str,
+    labels: list[str],
+    *,
+    action_indices: set[int] | None = None,
+    separator_indices: set[int] | None = None,
+    preselected: set[int] | None = None,
+    initial_cursor: int | None = None,
+) -> list[int] | tuple[list[int], int | None]:
+    """Arrow-key multi-select with checkboxes.
+
+    Returns:
+        Sorted list of selected indices, or ``(indices, action_index)`` when
+        ``action_indices`` is provided.
+    """
+    click.echo()
+    click.secho(f"  {title}", fg="cyan")
+
+    if _is_interactive():
+        try:
+            selected, action = _arrow_select_multi(
+                labels,
+                action_indices=action_indices,
+                separator_indices=separator_indices,
+                preselected=preselected,
+                initial_cursor=initial_cursor,
+            )
+        except Exception:
+            selected, action = _numbered_select_multi(
+                labels,
+                action_indices=action_indices,
+                separator_indices=separator_indices,
+                preselected=preselected,
+            )
+    else:
+        selected, action = _numbered_select_multi(
+            labels,
+            action_indices=action_indices,
+            separator_indices=separator_indices,
+            preselected=preselected,
+        )
+    if action_indices is None:
+        return selected
+    return selected, action

lib/cli/src/crewai_cli/utils.py

@@ -24,6 +24,7 @@ __all__ = [
     "build_env_with_all_tool_credentials",
     "build_env_with_tool_repository_credentials",
     "copy_template",
+    "enable_prompt_line_editing",
     "fetch_and_json_env_file",
     "get_project_description",
     "get_project_name",
@@ -40,6 +41,19 @@ __all__ = [
 console = Console()
 
 
+def enable_prompt_line_editing() -> None:
+    """Enable cursor movement/history editing for Click text prompts when available."""
+    try:
+        import readline
+    except ImportError:
+        return
+
+    try:
+        readline.parse_and_bind("set editing-mode emacs")
+    except Exception:  # pragma: no cover - readline backends vary by platform
+        return
+
+
 def copy_template(
     src: Path, dst: Path, name: str, class_name: str, folder_name: str
 ) -> None:

lib/cli/tests/deploy/test_archive.py

@@ -0,0 +1,270 @@
+from pathlib import Path
+import subprocess
+import zipfile
+
+import pytest
+
+from crewai_cli.deploy.archive import create_project_zip
+
+
+def test_create_project_zip_excludes_local_artifacts(tmp_path: Path):
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+    (tmp_path / "uv.lock").write_text("# lock\n")
+    (tmp_path / "src").mkdir()
+    (tmp_path / "src" / "main.py").write_text("print('hello')\n")
+    (tmp_path / ".env").write_text("OPENAI_API_KEY=secret\n")
+    (tmp_path / ".env.example").write_text("OPENAI_API_KEY=\n")
+    (tmp_path / "__pycache__").mkdir()
+    (tmp_path / "__pycache__" / "main.pyc").write_bytes(b"compiled")
+    (tmp_path / ".git").mkdir()
+    (tmp_path / ".git" / "config").write_text("[core]\n")
+
+    archive_path = create_project_zip("demo", project_dir=tmp_path)
+    try:
+        with zipfile.ZipFile(archive_path) as archive:
+            names = set(archive.namelist())
+    finally:
+        archive_path.unlink(missing_ok=True)
+
+    assert names == {
+        "pyproject.toml",
+        "uv.lock",
+        "src/main.py",
+        ".env.example",
+    }
+
+
+def test_create_project_zip_uses_repository_file_list(tmp_path: Path):
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+    (tmp_path / "uv.lock").write_text("# lock\n")
+    (tmp_path / "ignored.txt").write_text("ignored\n")
+
+    class RepositoryStub:
+        def deployable_files(self) -> list[str]:
+            return ["pyproject.toml", "uv.lock"]
+
+    archive_path = create_project_zip(
+        "demo",
+        project_dir=tmp_path,
+        repository=RepositoryStub(),  # type: ignore[arg-type]
+    )
+    try:
+        with zipfile.ZipFile(archive_path) as archive:
+            names = set(archive.namelist())
+    finally:
+        archive_path.unlink(missing_ok=True)
+
+    assert names == {"pyproject.toml", "uv.lock"}
+
+
+def test_create_project_zip_without_repository_uses_git_ignore_rules(
+    tmp_path: Path,
+):
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+    (tmp_path / ".gitignore").write_text("node_modules/\nsecret.txt\n")
+    (tmp_path / "src").mkdir()
+    (tmp_path / "src" / "main.py").write_text("print('hello')\n")
+    (tmp_path / "node_modules").mkdir()
+    (tmp_path / "node_modules" / "package.json").write_text("{}\n")
+    (tmp_path / "secret.txt").write_text("secret\n")
+
+    try:
+        subprocess.run(
+            ["git", "init"],
+            cwd=tmp_path,
+            capture_output=True,
+            check=True,
+            text=True,
+        )
+    except (FileNotFoundError, subprocess.CalledProcessError) as exc:
+        pytest.skip(f"git is not available in this environment: {exc}")
+
+    archive_path = create_project_zip("demo", project_dir=tmp_path)
+    try:
+        with zipfile.ZipFile(archive_path) as archive:
+            names = set(archive.namelist())
+    finally:
+        archive_path.unlink(missing_ok=True)
+
+    assert names == {
+        ".gitignore",
+        "pyproject.toml",
+        "src/main.py",
+    }
+
+
+def test_create_project_zip_does_not_fallback_when_repository_listing_fails(
+    tmp_path: Path,
+):
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+
+    class RepositoryStub:
+        def deployable_files(self) -> list[str]:
+            raise RuntimeError("git listing failed")
+
+    with pytest.raises(RuntimeError, match="git listing failed"):
+        create_project_zip(
+            "demo",
+            project_dir=tmp_path,
+            repository=RepositoryStub(),  # type: ignore[arg-type]
+        )
+
+
+def test_create_project_zip_excludes_symlinked_files(tmp_path: Path):
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+    outside_file = tmp_path.parent / f"{tmp_path.name}-secret.txt"
+    outside_file.write_text("secret\n")
+    archive_path: Path | None = None
+    try:
+        try:
+            (tmp_path / "external-secret.txt").symlink_to(outside_file)
+        except OSError as exc:
+            pytest.skip(f"symlinks are not supported in this environment: {exc}")
+
+        archive_path = create_project_zip("demo", project_dir=tmp_path)
+        with zipfile.ZipFile(archive_path) as archive:
+            names = set(archive.namelist())
+    finally:
+        if archive_path is not None:
+            archive_path.unlink(missing_ok=True)
+        outside_file.unlink(missing_ok=True)
+
+    assert names == {"pyproject.toml"}
+
+
+def test_create_project_zip_adds_json_project_wrapper(tmp_path: Path):
+    (tmp_path / "pyproject.toml").write_text(
+        """
+[project]
+name = "json_crew"
+version = "0.1.0"
+dependencies = ["crewai[tools]>=1.15"]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.crewai]
+type = "crew"
+""".strip()
+        + "\n"
+    )
+    (tmp_path / "agents").mkdir()
+    (tmp_path / "agents" / "researcher.jsonc").write_text("{}\n")
+    (tmp_path / "crew.jsonc").write_text("{}\n")
+
+    archive_path = create_project_zip("json_crew", project_dir=tmp_path)
+    try:
+        with zipfile.ZipFile(archive_path) as archive:
+            names = set(archive.namelist())
+            crew_py = archive.read("src/json_crew/crew.py").decode()
+            main_py = archive.read("src/json_crew/main.py").decode()
+            pyproject = archive.read("pyproject.toml").decode()
+    finally:
+        archive_path.unlink(missing_ok=True)
+
+    assert "uv.lock" not in names
+    assert "crew.jsonc" in names
+    assert "agents/researcher.jsonc" in names
+    assert "src/json_crew/__init__.py" in names
+    assert "src/json_crew/crew.py" in names
+    assert "src/json_crew/main.py" in names
+    assert "src/json_crew/config/agents.yaml" in names
+    assert "src/json_crew/config/tasks.yaml" in names
+    assert "load_crew(_crew_path())" in crew_py
+    assert "JsonCrew" in crew_py
+    assert "from json_crew.crew import JsonCrew" in main_py
+    assert "run_crew = \"json_crew.main:run\"" in pyproject
+
+
+def test_create_project_zip_updates_existing_json_project_scripts(tmp_path: Path):
+    (tmp_path / "pyproject.toml").write_text(
+        """
+[project]
+name = "json_crew"
+version = "0.1.0"
+
+[project.scripts]
+json_crew = "old.module:run"
+run_crew = "old.module:run"
+custom = "custom.module:main"
+
+[tool.crewai]
+type = "crew"
+""".strip()
+        + "\n"
+    )
+    (tmp_path / "crew.jsonc").write_text("{}\n")
+
+    archive_path = create_project_zip("json_crew", project_dir=tmp_path)
+    try:
+        with zipfile.ZipFile(archive_path) as archive:
+            pyproject = archive.read("pyproject.toml").decode()
+    finally:
+        archive_path.unlink(missing_ok=True)
+
+    assert 'json_crew = "json_crew.main:run"' in pyproject
+    assert 'run_crew = "json_crew.main:run"' in pyproject
+    assert 'train = "json_crew.main:train"' in pyproject
+    assert 'replay = "json_crew.main:replay"' in pyproject
+    assert 'test = "json_crew.main:test"' in pyproject
+    assert 'run_with_trigger = "json_crew.main:run_with_trigger"' in pyproject
+    assert 'custom = "custom.module:main"' in pyproject
+    assert "old.module:run" not in pyproject
+    assert "[tool.crewai]" in pyproject
+
+
+@pytest.mark.parametrize(
+    "tool_config",
+    [
+        'tool = "invalid"\n',
+        '[tool]\ncrewai = "invalid"\n',
+    ],
+)
+def test_create_project_zip_adds_json_wrapper_for_malformed_tool_config(
+    tmp_path: Path, tool_config: str
+):
+    (tmp_path / "pyproject.toml").write_text(
+        f"""
+[project]
+name = "json_crew"
+version = "0.1.0"
+
+{tool_config}
+""".strip()
+        + "\n"
+    )
+    (tmp_path / "crew.jsonc").write_text("{}\n")
+
+    archive_path = create_project_zip("json_crew", project_dir=tmp_path)
+    try:
+        with zipfile.ZipFile(archive_path) as archive:
+            names = set(archive.namelist())
+            pyproject = archive.read("pyproject.toml").decode()
+    finally:
+        archive_path.unlink(missing_ok=True)
+
+    assert "src/json_crew/crew.py" in names
+    assert "src/json_crew/main.py" in names
+    assert "run_crew = \"json_crew.main:run\"" in pyproject
+
+
+def test_create_project_zip_rejects_empty_normalized_package_name(tmp_path: Path):
+    (tmp_path / "pyproject.toml").write_text(
+        """
+[project]
+name = "!!!"
+version = "0.1.0"
+
+[tool.crewai]
+type = "crew"
+""".strip()
+        + "\n"
+    )
+    (tmp_path / "crew.jsonc").write_text("{}\n")
+
+    with pytest.raises(
+        ValueError,
+        match=r"Could not derive a valid Python package name",
+    ):
+        create_project_zip("invalid", project_dir=tmp_path)

lib/cli/tests/deploy/test_deploy_main.py

@@ -1,16 +1,172 @@
 import sys
 import unittest
 from io import StringIO
+from pathlib import Path
+import subprocess
 from unittest.mock import MagicMock, Mock, patch
 
 import pytest
 import json
 
+import crewai_cli.deploy.main as deploy_main
 import httpx
-from crewai_cli.deploy.main import DeployCommand
+from crewai_cli.deploy.validate import Severity, ValidationResult
 from crewai_cli.utils import parse_toml
 
 
+def test_ensure_lockfile_for_deploy_runs_install_when_lock_missing(
+    monkeypatch, tmp_path: Path
+):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+    calls = []
+
+    def fake_install_crew(proxy_options, *, raise_on_error=False):
+        calls.append((proxy_options, raise_on_error))
+
+    monkeypatch.setattr("crewai_cli.install_crew.install_crew", fake_install_crew)
+
+    deploy_main._ensure_lockfile_for_deploy()
+
+    assert calls == [([], True)]
+
+
+def test_ensure_lockfile_for_deploy_skips_when_lock_exists(monkeypatch, tmp_path: Path):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+    (tmp_path / "uv.lock").write_text("# lock\n")
+    calls = []
+
+    def fake_install_crew(proxy_options, *, raise_on_error=False):
+        calls.append((proxy_options, raise_on_error))
+
+    monkeypatch.setattr("crewai_cli.install_crew.install_crew", fake_install_crew)
+
+    deploy_main._ensure_lockfile_for_deploy()
+
+    assert calls == []
+
+
+def test_ensure_lockfile_for_deploy_skips_without_pyproject(
+    monkeypatch, tmp_path: Path
+):
+    monkeypatch.chdir(tmp_path)
+    calls = []
+
+    def fake_install_crew(proxy_options, *, raise_on_error=False):
+        calls.append((proxy_options, raise_on_error))
+
+    monkeypatch.setattr("crewai_cli.install_crew.install_crew", fake_install_crew)
+
+    deploy_main._ensure_lockfile_for_deploy()
+
+    assert calls == []
+
+
+def test_ensure_lockfile_for_deploy_failure_exits_nonzero(
+    monkeypatch, tmp_path: Path
+):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+
+    def fake_install_crew(proxy_options, *, raise_on_error=False):
+        raise subprocess.CalledProcessError(42, ["uv", "sync"])
+
+    monkeypatch.setattr("crewai_cli.install_crew.install_crew", fake_install_crew)
+
+    with pytest.raises(SystemExit) as exc_info:
+        deploy_main._ensure_lockfile_for_deploy()
+
+    assert exc_info.value.code == 42
+
+
+class _FakeDeployValidator:
+    def __init__(self, results: list[ValidationResult]):
+        self.results = results
+
+    @property
+    def errors(self) -> list[ValidationResult]:
+        return [
+            result
+            for result in self.results
+            if result.severity is Severity.ERROR
+        ]
+
+    def run(self) -> list[ValidationResult]:
+        return self.results
+
+
+def test_prepare_project_for_deploy_blocks_install_when_validation_fails(
+    monkeypatch, tmp_path: Path
+):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+    install_calls = []
+    rendered_results = []
+    missing_lockfile = ValidationResult(
+        Severity.ERROR,
+        "missing_lockfile",
+        "Expected to find a lockfile",
+    )
+    invalid_config = ValidationResult(
+        Severity.ERROR,
+        "invalid_crew_json",
+        "crew.jsonc has invalid configuration",
+    )
+
+    monkeypatch.setattr(
+        deploy_main,
+        "DeployValidator",
+        lambda: _FakeDeployValidator([missing_lockfile, invalid_config]),
+    )
+    monkeypatch.setattr(deploy_main, "render_report", rendered_results.append)
+
+    def fake_install_crew(proxy_options, *, raise_on_error=False):
+        install_calls.append((proxy_options, raise_on_error))
+
+    monkeypatch.setattr("crewai_cli.install_crew.install_crew", fake_install_crew)
+
+    assert deploy_main._prepare_project_for_deploy(skip_validate=False) is False
+
+    assert install_calls == []
+    assert [[result.code for result in results] for results in rendered_results] == [
+        ["invalid_crew_json"]
+    ]
+
+
+def test_prepare_project_for_deploy_creates_missing_lock_after_validation(
+    monkeypatch, tmp_path: Path
+):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+    install_calls = []
+    missing_lockfile = ValidationResult(
+        Severity.ERROR,
+        "missing_lockfile",
+        "Expected to find a lockfile",
+    )
+    validators = [
+        _FakeDeployValidator([missing_lockfile]),
+        _FakeDeployValidator([]),
+    ]
+
+    def fake_validator():
+        return validators.pop(0)
+
+    def fake_install_crew(proxy_options, *, raise_on_error=False):
+        install_calls.append((proxy_options, raise_on_error))
+        (tmp_path / "uv.lock").write_text("# lock\n")
+
+    monkeypatch.setattr(deploy_main, "DeployValidator", fake_validator)
+    monkeypatch.setattr(deploy_main, "render_report", lambda results: None)
+    monkeypatch.setattr("crewai_cli.install_crew.install_crew", fake_install_crew)
+
+    assert deploy_main._prepare_project_for_deploy(skip_validate=False) is True
+
+    assert install_calls == [([], True)]
+    assert validators == []
+
+
 class TestDeployCommand(unittest.TestCase):
     @patch("crewai_cli.command.get_auth_token")
     @patch("crewai_cli.deploy.main.get_project_name")
@@ -28,19 +184,25 @@ class TestDeployCommand(unittest.TestCase):
         self.mock_get_auth_token.return_value = "test_token"
         self.mock_get_project_name.return_value = "test_project"
 
-        self.deploy_command = DeployCommand()
+        self.deploy_command = deploy_main.DeployCommand()
         self.mock_client = self.deploy_command.plus_api_client
 
     def test_init_success(self):
         self.assertEqual(self.deploy_command.project_name, "test_project")
         self.mock_plus_api.assert_called_once_with(api_key="test_token")
 
+    @patch("builtins.input")
+    def test_confirm_zip_input_only_confirms_env_vars(self, mock_input):
+        self.deploy_command._confirm_zip_input({"MODEL": "openai/gpt-5"}, False)
+
+        mock_input.assert_called_once_with("Press Enter to continue with 1 env vars: MODEL")
+
     @patch("crewai_cli.command.get_auth_token")
     def test_init_failure(self, mock_get_auth_token):
         mock_get_auth_token.side_effect = Exception("Auth failed")
 
         with self.assertRaises(SystemExit):
-            DeployCommand()
+            deploy_main.DeployCommand()
 
     def test_validate_response_successful_response(self):
         mock_response = Mock(spec=httpx.Response)
@@ -123,8 +285,15 @@ class TestDeployCommand(unittest.TestCase):
             )
             self.assertIn("2023-01-01 - INFO: Test log", fake_out.getvalue())
 
+    @patch("crewai_cli.deploy.main.git.Repository")
     @patch("crewai_cli.deploy.main.DeployCommand._display_deployment_info")
-    def test_deploy_with_uuid(self, mock_display):
+    def test_deploy_with_uuid(self, mock_display, mock_repository):
+        mock_repository.return_value.origin_url.return_value = (
+            "https://github.com/test/repo.git"
+        )
+        mock_repository.return_value.create_initial_commit_if_needed.return_value = (
+            False
+        )
         mock_response = MagicMock()
         mock_response.status_code = 200
         mock_response.json.return_value = {"uuid": "test-uuid"}
@@ -135,8 +304,15 @@ class TestDeployCommand(unittest.TestCase):
         self.mock_client.deploy_by_uuid.assert_called_once_with("test-uuid")
         mock_display.assert_called_once_with({"uuid": "test-uuid"})
 
+    @patch("crewai_cli.deploy.main.git.Repository")
     @patch("crewai_cli.deploy.main.DeployCommand._display_deployment_info")
-    def test_deploy_with_project_name(self, mock_display):
+    def test_deploy_with_project_name(self, mock_display, mock_repository):
+        mock_repository.return_value.origin_url.return_value = (
+            "https://github.com/test/repo.git"
+        )
+        mock_repository.return_value.create_initial_commit_if_needed.return_value = (
+            False
+        )
         mock_response = MagicMock()
         mock_response.status_code = 200
         mock_response.json.return_value = {"uuid": "test-uuid"}
@@ -147,16 +323,142 @@ class TestDeployCommand(unittest.TestCase):
         self.mock_client.deploy_by_name.assert_called_once_with("test_project")
         mock_display.assert_called_once_with({"uuid": "test-uuid"})
 
+    @patch("crewai_cli.deploy.main.create_project_zip")
+    @patch("crewai_cli.deploy.main.git.Repository")
+    @patch("crewai_cli.deploy.main.DeployCommand._display_deployment_info")
+    def test_deploy_with_remote_keeps_remote_path_when_fetch_fails(
+        self, mock_display, mock_repository, mock_create_project_zip
+    ):
+        repository = mock_repository.return_value
+        repository.origin_url.return_value = "https://github.com/test/repo.git"
+        repository.fetch.side_effect = ValueError("fetch failed")
+        repository.create_initial_commit_if_needed.return_value = False
+        mock_response = MagicMock()
+        mock_response.status_code = 200
+        mock_response.is_success = True
+        mock_response.json.return_value = {"uuid": "test-uuid"}
+        self.mock_client.deploy_by_name.return_value = mock_response
+
+        with patch("sys.stdout", new=StringIO()) as fake_out:
+            self.deploy_command.deploy(skip_validate=True)
+            output = fake_out.getvalue()
+
+        mock_repository.assert_called_once_with(fetch=False)
+        repository.fetch.assert_called_once_with()
+        self.assertIn("Continuing with remote deployment", output)
+        self.mock_client.deploy_by_name.assert_called_once_with("test_project")
+        self.mock_client.update_crew_from_zip.assert_not_called()
+        mock_create_project_zip.assert_not_called()
+        mock_display.assert_called_once_with({"uuid": "test-uuid"})
+
+    @patch("crewai_cli.deploy.main.create_project_zip")
+    @patch("crewai_cli.deploy.main.git.Repository")
+    @patch("crewai_cli.deploy.main.DeployCommand._display_deployment_info")
+    def test_deploy_with_remote_keeps_remote_path_when_initial_commit_fails(
+        self, mock_display, mock_repository, mock_create_project_zip
+    ):
+        repository = mock_repository.return_value
+        repository.origin_url.return_value = "https://github.com/test/repo.git"
+        repository.create_initial_commit_if_needed.side_effect = RuntimeError(
+            "commit failed"
+        )
+        mock_response = MagicMock()
+        mock_response.status_code = 200
+        mock_response.is_success = True
+        mock_response.json.return_value = {"uuid": "test-uuid"}
+        self.mock_client.deploy_by_name.return_value = mock_response
+
+        with patch("sys.stdout", new=StringIO()) as fake_out:
+            self.deploy_command.deploy(skip_validate=True)
+            output = fake_out.getvalue()
+
+        mock_repository.assert_called_once_with(fetch=False)
+        repository.fetch.assert_called_once_with()
+        self.assertIn("Continuing with remote deployment", output)
+        self.mock_client.deploy_by_name.assert_called_once_with("test_project")
+        self.mock_client.update_crew_from_zip.assert_not_called()
+        mock_create_project_zip.assert_not_called()
+        mock_display.assert_called_once_with({"uuid": "test-uuid"})
+
+    @patch("crewai_cli.deploy.main.create_project_zip")
     @patch("crewai_cli.deploy.main.fetch_and_json_env_file")
-    @patch("crewai_cli.deploy.main.git.Repository.origin_url")
-    @patch("builtins.input")
-    def test_create_crew(self, mock_input, mock_git_origin_url, mock_fetch_env):
+    @patch("crewai_cli.deploy.main.git.Repository")
+    @patch("crewai_cli.deploy.main.DeployCommand._display_deployment_info")
+    def test_deploy_with_uuid_without_remote_updates_from_zip(
+        self, mock_display, mock_repository, mock_fetch_env, mock_create_project_zip
+    ):
         mock_fetch_env.return_value = {"ENV_VAR": "value"}
-        mock_git_origin_url.return_value = "https://github.com/test/repo.git"
+        mock_repository.return_value.origin_url.return_value = None
+        mock_repository.return_value.create_initial_commit_if_needed.return_value = (
+            False
+        )
+        mock_create_project_zip.return_value = Path("/tmp/test_project.zip")
+        mock_response = MagicMock()
+        mock_response.status_code = 200
+        mock_response.json.return_value = {"uuid": "test-uuid"}
+        self.mock_client.update_crew_from_zip.return_value = mock_response
+
+        self.deploy_command.deploy(uuid="test-uuid", skip_validate=True)
+
+        self.mock_client.update_crew_from_zip.assert_called_once_with(
+            "test-uuid",
+            Path("/tmp/test_project.zip"),
+            env={"ENV_VAR": "value"},
+        )
+        self.mock_client.deploy_by_uuid.assert_not_called()
+        mock_display.assert_called_once_with({"uuid": "test-uuid"})
+
+    @patch("crewai_cli.deploy.main.create_project_zip")
+    @patch("crewai_cli.deploy.main.fetch_and_json_env_file")
+    @patch("crewai_cli.deploy.main.git.Repository")
+    @patch("crewai_cli.deploy.main.DeployCommand._display_deployment_info")
+    def test_deploy_with_project_name_without_remote_updates_from_zip(
+        self, mock_display, mock_repository, mock_fetch_env, mock_create_project_zip
+    ):
+        mock_fetch_env.return_value = {"ENV_VAR": "value"}
+        mock_repository.return_value.origin_url.return_value = None
+        mock_repository.return_value.create_initial_commit_if_needed.return_value = (
+            False
+        )
+        mock_create_project_zip.return_value = Path("/tmp/test_project.zip")
+        status_response = MagicMock()
+        status_response.status_code = 200
+        status_response.is_success = True
+        status_response.json.return_value = {"uuid": "test-uuid"}
+        update_response = MagicMock()
+        update_response.status_code = 200
+        update_response.json.return_value = {"uuid": "test-uuid"}
+        self.mock_client.crew_status_by_name.return_value = status_response
+        self.mock_client.update_crew_from_zip.return_value = update_response
+
+        self.deploy_command.deploy(skip_validate=True)
+
+        self.mock_client.crew_status_by_name.assert_called_once_with("test_project")
+        self.mock_client.update_crew_from_zip.assert_called_once_with(
+            "test-uuid",
+            Path("/tmp/test_project.zip"),
+            env={"ENV_VAR": "value"},
+        )
+        self.mock_client.deploy_by_name.assert_not_called()
+        mock_display.assert_called_once_with({"uuid": "test-uuid"})
+
+    @patch("crewai_cli.deploy.main.fetch_and_json_env_file")
+    @patch("crewai_cli.deploy.main.git.Repository")
+    @patch("builtins.input")
+    @pytest.mark.timeout(180)
+    def test_create_crew(self, mock_input, mock_repository, mock_fetch_env):
+        mock_fetch_env.return_value = {"ENV_VAR": "value"}
+        mock_repository.return_value.origin_url.return_value = (
+            "https://github.com/test/repo.git"
+        )
+        mock_repository.return_value.create_initial_commit_if_needed.return_value = (
+            False
+        )
         mock_input.return_value = ""
 
         mock_response = MagicMock()
         mock_response.status_code = 201
+        mock_response.is_success = True
         mock_response.json.return_value = {"uuid": "new-uuid", "status": "created"}
         self.mock_client.create_crew.return_value = mock_response
 
@@ -165,6 +467,129 @@ class TestDeployCommand(unittest.TestCase):
             self.assertIn("Deployment created successfully!", fake_out.getvalue())
             self.assertIn("new-uuid", fake_out.getvalue())
 
+    @patch("crewai_cli.deploy.main.create_project_zip")
+    @patch("crewai_cli.deploy.main.fetch_and_json_env_file")
+    @patch("crewai_cli.deploy.main.git.Repository")
+    def test_create_crew_without_git_repo_initializes_and_uses_zip(
+        self, mock_repository, mock_fetch_env, mock_create_project_zip
+    ):
+        mock_fetch_env.return_value = {"ENV_VAR": "value"}
+        mock_repository.side_effect = ValueError("not a Git repository")
+        initialized_repository = MagicMock()
+        initialized_repository.origin_url.return_value = None
+        mock_repository.initialize.return_value = initialized_repository
+        mock_create_project_zip.return_value = Path("/tmp/test_project.zip")
+        mock_response = MagicMock()
+        mock_response.status_code = 201
+        mock_response.is_success = True
+        mock_response.json.return_value = {"uuid": "zip-uuid", "status": "created"}
+        self.mock_client.create_crew_from_zip.return_value = mock_response
+
+        with patch("sys.stdout", new=StringIO()) as fake_out:
+            self.deploy_command.create_crew(confirm=True, skip_validate=True)
+            output = fake_out.getvalue()
+
+        self.assertIn("Initialized a local Git repository", output)
+        self.assertIn("Deploying from a ZIP upload", output)
+        mock_repository.initialize.assert_called_once_with()
+        mock_create_project_zip.assert_called_once_with(
+            "test_project", repository=initialized_repository
+        )
+        self.mock_client.create_crew_from_zip.assert_called_once_with(
+            Path("/tmp/test_project.zip"),
+            name="test_project",
+            env={"ENV_VAR": "value"},
+        )
+        self.mock_client.create_crew.assert_not_called()
+
+    @patch("crewai_cli.deploy.main.git.Repository")
+    def test_prepare_git_repository_returns_repo_when_init_commit_fails(
+        self, mock_repository
+    ):
+        recovered_repository = MagicMock()
+        mock_repository.side_effect = [
+            ValueError("not a Git repository"),
+            recovered_repository,
+        ]
+        mock_repository.initialize.side_effect = RuntimeError("commit failed")
+
+        with patch("sys.stdout", new=StringIO()) as fake_out:
+            repository = self.deploy_command._prepare_git_repository()
+
+        self.assertIs(repository, recovered_repository)
+        self.assertIn("Git auto-setup did not complete", fake_out.getvalue())
+        mock_repository.initialize.assert_called_once_with()
+        self.assertEqual(mock_repository.call_count, 2)
+
+    @patch("crewai_cli.deploy.main.create_project_zip")
+    @patch("crewai_cli.deploy.main.fetch_and_json_env_file")
+    @patch("crewai_cli.deploy.main.git.Repository")
+    def test_create_crew_without_remote_uses_zip(
+        self, mock_repository, mock_fetch_env, mock_create_project_zip
+    ):
+        mock_fetch_env.return_value = {"ENV_VAR": "value"}
+        mock_repository.return_value.origin_url.return_value = None
+        mock_repository.return_value.create_initial_commit_if_needed.return_value = (
+            False
+        )
+        mock_create_project_zip.return_value = Path("/tmp/test_project.zip")
+        mock_response = MagicMock()
+        mock_response.status_code = 201
+        mock_response.is_success = True
+        mock_response.json.return_value = {"uuid": "zip-uuid", "status": "created"}
+        self.mock_client.create_crew_from_zip.return_value = mock_response
+
+        with patch("sys.stdout", new=StringIO()) as fake_out:
+            self.deploy_command.create_crew(confirm=True, skip_validate=True)
+            output = fake_out.getvalue()
+
+        self.assertIn("No origin remote found.", output)
+        self.assertIn("Deploying from a ZIP upload", output)
+        mock_create_project_zip.assert_called_once_with(
+            "test_project", repository=mock_repository.return_value
+        )
+        self.mock_client.create_crew_from_zip.assert_called_once_with(
+            Path("/tmp/test_project.zip"),
+            name="test_project",
+            env={"ENV_VAR": "value"},
+        )
+        self.mock_client.create_crew.assert_not_called()
+
+    @patch("crewai_cli.deploy.main.create_project_zip")
+    @patch("crewai_cli.deploy.main.fetch_and_json_env_file")
+    @patch("crewai_cli.deploy.main.git.Repository")
+    def test_create_crew_without_remote_uses_git_file_list_when_commit_fails(
+        self, mock_repository, mock_fetch_env, mock_create_project_zip
+    ):
+        mock_fetch_env.return_value = {"ENV_VAR": "value"}
+        repository = mock_repository.return_value
+        repository.origin_url.return_value = None
+        repository.create_initial_commit_if_needed.side_effect = RuntimeError(
+            "commit failed"
+        )
+        mock_create_project_zip.return_value = Path("/tmp/test_project.zip")
+        mock_response = MagicMock()
+        mock_response.status_code = 201
+        mock_response.is_success = True
+        mock_response.json.return_value = {"uuid": "zip-uuid", "status": "created"}
+        self.mock_client.create_crew_from_zip.return_value = mock_response
+
+        with patch("sys.stdout", new=StringIO()) as fake_out:
+            self.deploy_command.create_crew(confirm=True, skip_validate=True)
+            output = fake_out.getvalue()
+
+        self.assertIn("Continuing with ZIP deployment using Git", output)
+        self.assertIn("file listing", output)
+        mock_create_project_zip.assert_called_once_with(
+            "test_project", repository=repository
+        )
+        self.mock_client.create_crew_from_zip.assert_called_once_with(
+            Path("/tmp/test_project.zip"),
+            name="test_project",
+            env={"ENV_VAR": "value"},
+        )
+        self.mock_client.create_crew.assert_not_called()
+
     def test_list_crews(self):
         mock_response = MagicMock()
         mock_response.status_code = 200

lib/cli/tests/deploy/test_validate.py

@@ -110,6 +110,45 @@ def _run_without_import_check(root: Path) -> DeployValidator:
     return v
 
 
+def _scaffold_json_crew(root: Path, *, task_agent: str = "researcher") -> None:
+    (root / "pyproject.toml").write_text(_make_pyproject(name="json_crew"))
+    (root / "uv.lock").write_text("# dummy uv lockfile\n")
+    agents_dir = root / "agents"
+    agents_dir.mkdir()
+    (agents_dir / "researcher.jsonc").write_text(
+        dedent(
+            """
+            {
+              "role": "Researcher",
+              "goal": "Research things",
+              "backstory": "Experienced researcher",
+              "llm": "openai/gpt-4o-mini"
+            }
+            """
+        ).strip()
+        + "\n"
+    )
+    (root / "crew.jsonc").write_text(
+        dedent(
+            f"""
+            {{
+              "name": "json_crew",
+              "agents": ["researcher"],
+              "tasks": [
+                {{
+                  "name": "research",
+                  "description": "Research https://example.com/a//b",
+                  "expected_output": "Findings",
+                  "agent": "{task_agent}"
+                }}
+              ]
+            }}
+            """
+        ).strip()
+        + "\n"
+    )
+
+
 @pytest.mark.parametrize(
     "project_name, expected",
     [
@@ -129,6 +168,38 @@ def test_valid_standard_crew_project_passes(tmp_path: Path) -> None:
     assert v.ok, f"expected clean run, got {v.results}"
 
 
+def test_valid_json_crew_project_passes(tmp_path: Path) -> None:
+    _scaffold_json_crew(tmp_path)
+    v = DeployValidator(project_root=tmp_path)
+    v.run()
+    assert "invalid_crew_json" not in _codes(v)
+
+
+def test_json_task_agent_mismatch_is_error(tmp_path: Path) -> None:
+    _scaffold_json_crew(tmp_path, task_agent="missing_agent")
+    v = DeployValidator(project_root=tmp_path)
+    v.run()
+    finding = next(r for r in v.results if r.code == "invalid_crew_json")
+    assert finding.severity is Severity.ERROR
+    assert "missing_agent" in finding.detail
+
+
+def test_json_runtime_fields_are_deploy_errors(tmp_path: Path) -> None:
+    _scaffold_json_crew(tmp_path)
+    crew_path = tmp_path / "crew.jsonc"
+    crew_path.write_text(
+        crew_path.read_text().replace(
+            '"name": "json_crew",',
+            '"name": "json_crew",\n  "id": "00000000-0000-4000-8000-000000000000",',
+        )
+    )
+    v = DeployValidator(project_root=tmp_path)
+    v.run()
+    finding = next(r for r in v.results if r.code == "invalid_crew_json")
+    assert finding.severity is Severity.ERROR
+    assert "runtime-only" in finding.detail
+
+
 def test_missing_pyproject_errors(tmp_path: Path) -> None:
     v = _run_without_import_check(tmp_path)
     assert "missing_pyproject" in _codes(v)
@@ -410,7 +481,7 @@ def test_modern_crewai_pin_does_not_warn(tmp_path: Path) -> None:
 
 def test_create_crew_aborts_on_validation_error(tmp_path: Path) -> None:
     """`crewai deploy create` must not contact the API when validation fails."""
-    from unittest.mock import MagicMock, patch as mock_patch
+    from unittest.mock import patch as mock_patch
 
     from crewai_cli.deploy.main import DeployCommand
 
@@ -419,11 +490,38 @@ def test_create_crew_aborts_on_validation_error(tmp_path: Path) -> None:
         mock_patch("crewai_cli.deploy.main.get_project_name", return_value="p"),
         mock_patch("crewai_cli.command.PlusAPI") as mock_api,
         mock_patch(
-            "crewai_cli.deploy.main.validate_project"
-        ) as mock_validate,
+            "crewai_cli.deploy.main._prepare_project_for_deploy",
+            return_value=False,
+        ),
     ):
-        mock_validate.return_value = MagicMock(ok=False)
         cmd = DeployCommand()
         cmd.create_crew()
         assert not cmd.plus_api_client.create_crew.called
-        del mock_api  # silence unused-var lint
+        del mock_api  # silence unused-var lint
+
+
+def test_is_json_crew_defers_to_declared_flow_type(tmp_path):
+    """A flow project with a stray crew.jsonc must validate as a flow."""
+    (tmp_path / "crew.jsonc").write_text("{}")
+    (tmp_path / "pyproject.toml").write_text(
+        '[project]\nname = "demo"\nversion = "0.1.0"\n\n'
+        '[tool.crewai]\ntype = "flow"\n'
+    )
+
+    assert DeployValidator(project_root=tmp_path)._is_json_crew is False
+
+
+def test_is_json_crew_true_for_declared_crew_type(tmp_path):
+    (tmp_path / "crew.jsonc").write_text("{}")
+    (tmp_path / "pyproject.toml").write_text(
+        '[project]\nname = "demo"\nversion = "0.1.0"\n\n'
+        '[tool.crewai]\ntype = "crew"\n'
+    )
+
+    assert DeployValidator(project_root=tmp_path)._is_json_crew is True
+
+
+def test_is_json_crew_true_without_pyproject(tmp_path):
+    (tmp_path / "crew.jsonc").write_text("{}")
+
+    assert DeployValidator(project_root=tmp_path)._is_json_crew is True

lib/cli/tests/test_cli.py

@@ -13,6 +13,7 @@ from crewai_cli.cli import (
     flow_add_crew,
     login,
     reset_memories,
+    run,
     test,
     train,
     version,
@@ -93,9 +94,9 @@ def test_version_command_with_tools(runner):
 def test_test_default_iterations(evaluate_crew, runner):
     result = runner.invoke(test)
 
-    evaluate_crew.assert_called_once_with(3, "gpt-4o-mini", trained_agents_file=None)
+    evaluate_crew.assert_called_once_with(3, "gpt-5.4-mini", trained_agents_file=None)
     assert result.exit_code == 0
-    assert "Testing the crew for 3 iterations with model gpt-4o-mini" in result.output
+    assert "Testing the crew for 3 iterations with model gpt-5.4-mini" in result.output
 
 
 @mock.patch("crewai_cli.cli.evaluate_crew")
@@ -119,6 +120,43 @@ def test_test_invalid_string_iterations(evaluate_crew, runner):
     )
 
 
+@mock.patch("crewai_cli.cli.run_crew")
+def test_run_uses_project_runner_by_default(run_crew, runner):
+    result = runner.invoke(run)
+
+    assert result.exit_code == 0
+    run_crew.assert_called_once_with(trained_agents_file=None)
+    assert "experimental" not in result.output.lower()
+
+
+@mock.patch("crewai_cli.cli.run_flow_definition")
+def test_run_with_definition_uses_definition_runner(run_flow_definition, runner):
+    result = runner.invoke(
+        run,
+        ["--definition", "flow.yaml", "--inputs", '{"topic":"AI"}'],
+    )
+
+    assert result.exit_code == 0
+    assert (
+        "Warning: `crewai run --definition` is experimental and may change without notice."
+        in result.output
+    )
+    run_flow_definition.assert_called_once_with(
+        definition="flow.yaml", inputs='{"topic":"AI"}'
+    )
+
+
+@mock.patch("crewai_cli.cli.run_crew")
+@mock.patch("crewai_cli.cli.run_flow_definition")
+def test_run_rejects_inputs_without_definition(run_flow_definition, run_crew, runner):
+    result = runner.invoke(run, ["--inputs", '{"topic":"AI"}'])
+
+    assert result.exit_code == 2
+    assert "Error: --inputs requires --definition" in result.output
+    run_flow_definition.assert_not_called()
+    run_crew.assert_not_called()
+
+
 @mock.patch("crewai_cli.cli.AuthenticationCommand")
 def test_login(command, runner):
     mock_auth = command.return_value

lib/cli/tests/test_create_crew.py

@@ -6,6 +6,8 @@ from unittest import mock
 
 import pytest
 from click.testing import CliRunner
+import crewai_cli.create_json_crew as json_crew
+import crewai_cli.tui_picker as tui_picker
 from crewai_cli.create_crew import create_crew, create_folder_structure
 
 
@@ -345,3 +347,468 @@ def test_env_vars_are_uppercased_in_env_file(
     env_file_path = crew_path / ".env"
     content = env_file_path.read_text()
     assert "MODEL=" in content
+
+
+def test_json_wizard_defaults_to_sequential_and_memory_enabled(monkeypatch):
+    monkeypatch.setattr(
+        json_crew,
+        "_wizard_agent",
+        lambda **_: {
+            "name": "researcher",
+            "role": "Researcher",
+            "goal": "Research",
+            "backstory": "Researcher",
+            "llm": "openai/gpt-5.5",
+            "tools": [],
+            "planning": False,
+            "allow_delegation": False,
+        },
+    )
+    monkeypatch.setattr(
+        json_crew,
+        "_wizard_task",
+        lambda **_: {
+            "name": "research_task",
+            "description": "Research",
+            "expected_output": "Findings",
+            "agent": "researcher",
+            "context": [],
+        },
+    )
+
+    def confirm(label: str, default: bool = False) -> bool:
+        if label == "Enable crew memory?":
+            return default
+        return False
+
+    monkeypatch.setattr(json_crew, "_confirm", confirm)
+    monkeypatch.setattr(json_crew.click, "prompt", lambda *_, **__: "")
+    monkeypatch.setattr(
+        json_crew,
+        "pick_one",
+        lambda *_args, **_kwargs: pytest.fail("process should not be prompted"),
+    )
+
+    _agents, _tasks, settings = json_crew._wizard_agents_and_tasks(
+        skip_provider=True,
+        default_llm="openai/gpt-5.5",
+    )
+
+    assert settings == {"process": "sequential", "memory": True, "inputs": {}}
+
+
+def test_json_wizard_shows_interpolation_hint(capsys):
+    json_crew._show_interpolation_hint("tasks")
+
+    output = capsys.readouterr().out
+    assert "{placeholder}" in output
+    assert "dynamic values" in output
+    assert "{topic}" not in output
+    assert "Description >" not in output
+    assert '"description"' not in output
+
+
+def test_json_wizard_text_prompt_uses_full_prompt_for_readline(monkeypatch):
+    prompts: list[str] = []
+
+    monkeypatch.setattr(
+        json_crew, "_readline_safe_prompt", lambda prompt: f"safe:{prompt}"
+    )
+    monkeypatch.setattr(
+        "builtins.input", lambda prompt: prompts.append(prompt) or "Draft content"
+    )
+
+    assert json_crew._prompt_text("Goal", spacing_before=False) == "Draft content"
+    assert len(prompts) == 1
+    assert prompts[0].startswith("safe:")
+    assert "Goal" in prompts[0]
+    assert " > " in prompts[0]
+
+
+def test_json_wizard_tool_picker_prioritizes_common_tools(monkeypatch):
+    picker_calls: list[tuple[str, list[str], dict[str, object]]] = []
+
+    def pick_many(title: str, labels: list[str], **kwargs):
+        picker_calls.append((title, labels, kwargs))
+        return [1, 3], None
+
+    monkeypatch.setattr(json_crew, "pick_many", pick_many)
+
+    tools = json_crew._select_tools()
+
+    assert tools == ["SerperDevTool", "DirectoryReadTool"]
+    assert len(picker_calls) == 1
+    labels = picker_calls[0][1]
+    assert 0 in picker_calls[0][2]["separator_indices"]
+    assert labels[0] == "── Common tools ──"
+    assert labels[1].strip().endswith("SerperDevTool")
+    assert labels[2].strip().endswith("ScrapeWebsiteTool")
+    assert labels[3].strip().endswith("DirectoryReadTool")
+    assert labels[4].strip().endswith("FileReadTool")
+    assert labels[5].strip().endswith("FileWriterTool")
+    assert labels[1].index("Google search") < labels[1].index("SerperDevTool")
+    assert "More tools" not in labels
+
+
+def test_json_wizard_tool_picker_collapses_categories_by_default(monkeypatch):
+    picker_calls: list[tuple[str, list[str], dict[str, object]]] = []
+
+    def pick_many(title: str, labels: list[str], **kwargs):
+        picker_calls.append((title, labels, kwargs))
+        return [], None
+
+    monkeypatch.setattr(json_crew, "pick_many", pick_many)
+
+    json_crew._select_tools()
+
+    labels = picker_calls[0][1]
+    action_indices = picker_calls[0][2]["action_indices"]
+    # Categories show as collapsed action rows, not separators with tools
+    assert any(label.startswith("▸ Search & Research") for label in labels)
+    assert any(label.startswith("▸ Web Scraping") for label in labels)
+    assert not any(label.strip().endswith("BraveSearchTool") for label in labels)
+    assert len(action_indices) >= 4
+    # Only the common tools section is visible beyond the category rows
+    assert len(labels) == 1 + 5 + len(action_indices)
+
+
+def test_json_wizard_tool_picker_expands_one_category_at_a_time(monkeypatch):
+    picker_calls: list[tuple[str, list[str], dict[str, object]]] = []
+
+    def find_category_row(labels: list[str], category: str) -> int:
+        return next(
+            idx for idx, label in enumerate(labels) if category in label
+        )
+
+    def pick_many(title: str, labels: list[str], **kwargs):
+        picker_calls.append((title, labels, kwargs))
+        call_num = len(picker_calls)
+        if call_num == 1:
+            return [], find_category_row(labels, "Search & Research")
+        if call_num == 2:
+            # Search & Research is expanded; select BraveSearchTool and
+            # expand Web Scraping instead
+            brave = next(
+                idx
+                for idx, label in enumerate(labels)
+                if label.strip().endswith("BraveSearchTool")
+            )
+            return [brave], find_category_row(labels, "Web Scraping")
+        return [], None
+
+    monkeypatch.setattr(json_crew, "pick_many", pick_many)
+
+    tools = json_crew._select_tools()
+
+    assert tools == ["BraveSearchTool"]
+    assert len(picker_calls) == 3
+    # Second render: Search & Research expanded, others collapsed
+    labels2 = picker_calls[1][1]
+    assert any(label.startswith("▾ Search & Research") for label in labels2)
+    assert any(label.strip().endswith("BraveSearchTool") for label in labels2)
+    assert any(label.startswith("▸ Web Scraping") for label in labels2)
+    # Third render: Web Scraping expanded, Search & Research collapsed again
+    labels3 = picker_calls[2][1]
+    assert any(label.startswith("▸ Search & Research") for label in labels3)
+    assert any(label.startswith("▾ Web Scraping") for label in labels3)
+    assert not any(label.strip().endswith("BraveSearchTool") for label in labels3)
+    # The collapsed Search & Research row reports its selection count
+    assert any(
+        "Search & Research" in label and "1 selected" in label for label in labels3
+    )
+    # Cursor returns to the toggled category row
+    assert picker_calls[2][2]["initial_cursor"] == next(
+        idx for idx, label in enumerate(labels3) if "Web Scraping" in label
+    )
+
+
+def test_json_wizard_tool_picker_preserves_selection_across_renders(monkeypatch):
+    picker_calls: list[tuple[str, list[str], dict[str, object]]] = []
+
+    def pick_many(title: str, labels: list[str], **kwargs):
+        picker_calls.append((title, labels, kwargs))
+        call_num = len(picker_calls)
+        if call_num == 1:
+            # Select a common tool, then expand a category
+            category_row = next(
+                idx for idx, label in enumerate(labels) if "Web Scraping" in label
+            )
+            return [1], category_row
+        # Confirm without touching anything else
+        return sorted(kwargs["preselected"]), None
+
+    monkeypatch.setattr(json_crew, "pick_many", pick_many)
+
+    tools = json_crew._select_tools()
+
+    # The common-tool selection survived the expand re-render via preselected
+    assert tools == ["SerperDevTool"]
+    assert 1 in picker_calls[1][2]["preselected"]
+
+
+def test_json_wizard_tool_picker_lists_builtin_tools_across_categories(monkeypatch):
+    picker_calls: list[tuple[str, list[str], dict[str, object]]] = []
+    expanded_labels: list[str] = []
+
+    def pick_many(title: str, labels: list[str], **kwargs):
+        picker_calls.append((title, labels, kwargs))
+        expanded_labels.extend(labels)
+        action_indices = sorted(kwargs["action_indices"])
+        call_num = len(picker_calls)
+        if call_num <= len(action_indices):
+            # Expand the n-th category (indices shift between renders, so
+            # recompute from this render's action rows)
+            return [], action_indices[call_num - 1]
+        return [], None
+
+    monkeypatch.setattr(json_crew, "pick_many", pick_many)
+
+    json_crew._select_tools()
+
+    tool_names = {
+        label.rsplit(maxsplit=1)[-1]
+        for label in expanded_labels
+        if not label.startswith(("▸", "▾", "──"))
+    }
+
+    assert {
+        "DirectorySearchTool",
+        "MDXSearchTool",
+        "XMLSearchTool",
+        "YoutubeVideoSearchTool",
+        "S3ReaderTool",
+        "E2BExecTool",
+        "TavilyResearchTool",
+        "SerplyNewsSearchTool",
+        "BrowserbaseLoadTool",
+        "PatronusEvalTool",
+    }.issubset(tool_names)
+    assert {
+        "MCPServerAdapter",
+        "MongoDBVectorSearchConfig",
+        "ScrapegraphScrapeToolSchema",
+        "SnowflakeConfig",
+    }.isdisjoint(tool_names)
+
+
+def test_multi_picker_skips_separator_on_initial_cursor(monkeypatch):
+    cursors: list[int] = []
+
+    monkeypatch.setattr(tui_picker, "_read_key", lambda: "enter")
+    monkeypatch.setattr(
+        tui_picker,
+        "_draw_multi",
+        lambda _labels, cursor, *_args, **_kwargs: cursors.append(cursor),
+    )
+    monkeypatch.setattr(tui_picker, "_clear_lines", lambda *_args, **_kwargs: None)
+
+    assert tui_picker._arrow_select_multi(
+        ["── Common tools ──", "Google search via Serper API SerperDevTool"],
+        separator_indices={0},
+    ) == ([], None)
+    assert cursors == [1]
+
+
+def test_json_wizard_agent_attribute_prompts_are_compact(monkeypatch):
+    prompt_calls: list[tuple[str, bool]] = []
+    prompt_values = {
+        "Role": "Senior Dev Rel",
+        "Goal": "Draft content",
+        "Backstory": "Knows developer communities",
+    }
+
+    def prompt_text(
+        label: str,
+        default: str = "",
+        *,
+        spacing_before: bool = True,
+    ) -> str:
+        prompt_calls.append((label, spacing_before))
+        return prompt_values[label]
+
+    monkeypatch.setattr(json_crew, "_prompt_text", prompt_text)
+    monkeypatch.setattr(json_crew, "_select_model", lambda: "openai/gpt-5.5")
+    monkeypatch.setattr(json_crew, "pick_many", lambda *_args, **_kwargs: ([], None))
+    monkeypatch.setattr(json_crew, "_confirm", lambda *_args, **_kwargs: False)
+
+    agent = json_crew._wizard_agent(agent_num=1, existing_names=[])
+
+    assert agent is not None
+    assert prompt_calls == [
+        ("Role", False),
+        ("Goal", False),
+        ("Backstory", False),
+    ]
+
+
+def test_json_wizard_task_attribute_prompts_are_compact(monkeypatch):
+    prompt_calls: list[tuple[str, bool]] = []
+    prompt_values = {
+        "Description": "Research latest release",
+        "Expected output": "Release summary",
+    }
+
+    def prompt_text(
+        label: str,
+        default: str = "",
+        *,
+        spacing_before: bool = True,
+    ) -> str:
+        prompt_calls.append((label, spacing_before))
+        return prompt_values[label]
+
+    monkeypatch.setattr(json_crew, "_prompt_text", prompt_text)
+
+    task = json_crew._wizard_task(
+        task_num=1,
+        agent_names=["senior_dev_rel"],
+        prior_task_names=[],
+    )
+
+    assert task is not None
+    assert prompt_calls == [
+        ("Description", False),
+        ("Expected output", False),
+    ]
+
+
+def test_json_create_provider_preselects_default_model(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with mock.patch(
+        "crewai_cli.create_json_crew._wizard_agents_and_tasks"
+    ) as mock_wizard:
+        mock_wizard.return_value = (
+            [
+                {
+                    "name": "researcher",
+                    "role": "Researcher",
+                    "goal": "Research",
+                    "backstory": "Researcher",
+                    "llm": "openai/gpt-5.5",
+                    "tools": [],
+                    "planning": False,
+                    "allow_delegation": False,
+                }
+            ],
+            [
+                {
+                    "name": "research_task",
+                    "description": "Research",
+                    "expected_output": "Findings",
+                    "agent": "researcher",
+                    "context": [],
+                }
+            ],
+            {"process": "sequential", "memory": False, "inputs": {}},
+        )
+
+        json_crew.create_json_crew("JSON Crew", provider="openai", skip_provider=True)
+
+    mock_wizard.assert_called_once_with(
+        skip_provider=True,
+        default_llm="openai/gpt-5.5",
+    )
+    assert (tmp_path / "json_crew" / "crew.jsonc").exists()
+    assert not (tmp_path / "json_crew" / "tests").exists()
+    assert not (tmp_path / "json_crew" / "config.jsonc").exists()
+
+    crew_template = (tmp_path / "json_crew" / "crew.jsonc").read_text()
+    assert (
+        '"guardrail": "Every factual claim needs context support."'
+        in crew_template
+    )
+    assert '"guardrails": [' in crew_template
+    assert '"guardrail_max_retries": 2' in crew_template
+    assert "Docs: https://docs.crewai.com/concepts/tasks" in crew_template
+    assert '"output_pydantic": null' in crew_template
+    assert '"type": "ConditionalTask"' in crew_template
+    assert '"condition": { "python": "my_project.conditions.should_run" }' in (
+        crew_template
+    )
+    assert '"output_json": { "python": "my_project.models.ReportOutput" }' in (
+        crew_template
+    )
+    assert (
+        '"converter_cls": { "python": "my_project.converters.CustomConverter" }'
+        in crew_template
+    )
+    assert '"markdown": false' in crew_template
+    assert '"input_files": { "brief": "data/brief.txt" }' in crew_template
+    assert "Docs: https://docs.crewai.com/concepts/crews" in crew_template
+    assert "manager_agent can reference an agents/<name>.jsonc file" in crew_template
+    assert '"manager_agent": "researcher"' in crew_template
+    assert (
+        '"before_kickoff_callbacks": [{"python": '
+        '"my_project.callbacks.before_kickoff"}]'
+    ) in crew_template
+    assert (
+        '"after_kickoff_callbacks": [{"python": '
+        '"my_project.callbacks.after_kickoff"}]'
+    ) in crew_template
+    assert '"output_log_file": "crew.log"' in crew_template
+    assert "Crew-level LLM fields also accept object form" in crew_template
+    assert '"chat_llm": {"model": "llama3", "provider": "ollama"' in (
+        crew_template
+    )
+    assert "Use {placeholder} in agent or task text" in crew_template
+    assert "`crewai run` prompts for any placeholders" in crew_template
+    assert "Use {placeholder} inputs here" in crew_template
+
+    agent_template = (
+        tmp_path / "json_crew" / "agents" / "researcher.jsonc"
+    ).read_text()
+    assert "You can use {placeholder} inputs in role, goal, or backstory" in (
+        agent_template
+    )
+    assert '"role": "Senior {industry} Researcher"' in agent_template
+    assert '"type": {"python": "my_project.agents.CustomAgent"}' in agent_template
+    assert "Optional agent-level guardrail" in agent_template
+    assert "Python refs must point to module-level functions/classes" in agent_template
+    assert (
+        '"step_callback": {"python": "my_project.callbacks.on_agent_step"}'
+        in agent_template
+    )
+    assert '"guardrail_max_retries": 2' in agent_template
+    assert "Docs: https://docs.crewai.com/concepts/agents" in agent_template
+    assert '"reasoning": true' in agent_template
+    assert "For custom endpoints or deployment-based providers" in agent_template
+    assert '"deployment_name": "my-deployment", "provider": "azure"' in (
+        agent_template
+    )
+    assert '"planning_config": {' in agent_template
+    assert '"llm": {"model": "deepseek-chat", "provider": "deepseek"}' in (
+        agent_template
+    )
+    assert '"knowledge_sources": []' in agent_template
+
+
+def test_json_provider_default_model_helper():
+    assert json_crew._default_model_for_provider("openai") == "openai/gpt-5.5"
+    assert json_crew._default_model_for_provider("anthropic/claude-custom") == (
+        "anthropic/claude-custom"
+    )
+    assert json_crew._default_model_for_provider("unknown") is None
+
+
+def test_json_wizard_task_reprompts_on_cancelled_agent_pick(monkeypatch):
+    """Esc on the agent picker must reprompt, not silently assign agent 0."""
+    prompts = iter(["Do the research", "A report"])
+    monkeypatch.setattr(json_crew, "_prompt_text", lambda *a, **k: next(prompts))
+
+    pick_calls: list[str] = []
+    picks = iter([-1, 1])
+
+    def fake_pick_one(title: str, labels: list[str]) -> int:
+        pick_calls.append(title)
+        return next(picks)
+
+    monkeypatch.setattr(json_crew, "pick_one", fake_pick_one)
+
+    task = json_crew._wizard_task(
+        task_num=1,
+        agent_names=["first_agent", "second_agent"],
+        prior_task_names=[],
+    )
+
+    assert len(pick_calls) == 2
+    assert task["agent"] == "second_agent"

lib/cli/tests/test_crew_run_tui.py

@@ -0,0 +1,823 @@
+from datetime import datetime
+import time
+
+import pytest
+
+from crewai.events.event_bus import crewai_event_bus
+from crewai.events.types.observation_events import (
+    GoalAchievedEarlyEvent,
+    PlanRefinementEvent,
+    PlanReplanTriggeredEvent,
+    PlanStepCompletedEvent,
+    PlanStepStartedEvent,
+    StepObservationCompletedEvent,
+    StepObservationFailedEvent,
+    StepObservationStartedEvent,
+)
+from crewai.events.types.tool_usage_events import (
+    ToolUsageErrorEvent,
+    ToolUsageFinishedEvent,
+    ToolUsageStartedEvent,
+)
+from crewai_cli.command import AuthenticationRequiredError
+from crewai_cli import run_crew
+from crewai_cli.crew_run_tui import CrewRunApp
+
+
+def _app_with_plan() -> CrewRunApp:
+    app = CrewRunApp()
+    app._plan = {
+        "plan": "Demo plan",
+        "steps": [
+            {"step_number": 1, "description": "First"},
+            {"step_number": 2, "description": "Second"},
+            {"step_number": 3, "description": "Third"},
+        ],
+    }
+    app._plan_step_status = {1: "pending", 2: "pending", 3: "pending"}
+    return app
+
+
+def _log_entry(name: str) -> dict:
+    now = time.time()
+    return {
+        "tool_name": name,
+        "status": "success",
+        "args": None,
+        "result": f"{name} result",
+        "error": None,
+        "start_time": now,
+        "duration": 1.0,
+        "task_idx": 1,
+    }
+
+
+def _emit_event(event: object) -> None:
+    future = crewai_event_bus.emit(None, event)
+    if future:
+        future.result(timeout=5)
+
+
+def test_chain_deploy_skips_validation_after_auth_retry(monkeypatch) -> None:
+    create_calls: list[dict[str, object]] = []
+    login_calls: list[bool] = []
+
+    class FakeDeployCommand:
+        attempts = 0
+
+        def create_crew(self, **kwargs) -> None:
+            create_calls.append(kwargs)
+            FakeDeployCommand.attempts += 1
+            if FakeDeployCommand.attempts == 1:
+                raise AuthenticationRequiredError
+
+    class FakeAuthenticationCommand:
+        def login(self) -> None:
+            login_calls.append(True)
+
+    monkeypatch.setattr("crewai_cli.deploy.main.DeployCommand", FakeDeployCommand)
+    monkeypatch.setattr(
+        "crewai_cli.authentication.main.AuthenticationCommand",
+        FakeAuthenticationCommand,
+    )
+
+    run_crew._chain_deploy()
+
+    assert create_calls == [
+        {"confirm": True, "skip_validate": True},
+        {"confirm": True, "skip_validate": True},
+    ]
+    assert login_calls == [True]
+
+
+def test_chain_deploy_does_not_login_for_deploy_exit(monkeypatch, capsys) -> None:
+    create_calls: list[dict[str, object]] = []
+    login_calls: list[bool] = []
+
+    class FakeDeployCommand:
+        def create_crew(self, **kwargs) -> None:
+            create_calls.append(kwargs)
+            raise SystemExit(42)
+
+    class FakeAuthenticationCommand:
+        def login(self) -> None:
+            login_calls.append(True)
+
+    monkeypatch.setattr("crewai_cli.deploy.main.DeployCommand", FakeDeployCommand)
+    monkeypatch.setattr(
+        "crewai_cli.authentication.main.AuthenticationCommand",
+        FakeAuthenticationCommand,
+    )
+
+    run_crew._chain_deploy()
+
+    assert create_calls == [{"confirm": True, "skip_validate": True}]
+    assert login_calls == []
+    assert "Deploy failed with exit code 42" in capsys.readouterr().out
+
+
+def test_plan_step_status_updates_only_the_explicit_step() -> None:
+    app = _app_with_plan()
+
+    app._set_plan_step_status(2, "done")
+
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "done",
+        3: "pending",
+    }
+
+
+def test_step_observation_events_update_the_explicit_step() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        future = crewai_event_bus.emit(
+            None,
+            StepObservationStartedEvent(
+                agent_role="Agent",
+                step_number=2,
+                step_description="Second",
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+
+        assert app._plan_step_status == {
+            1: "pending",
+            2: "active",
+            3: "pending",
+        }
+
+        future = crewai_event_bus.emit(
+            None,
+            StepObservationCompletedEvent(
+                agent_role="Agent",
+                step_number=2,
+                step_description="Second",
+                step_completed_successfully=True,
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+    finally:
+        app._unsubscribe()
+
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "done",
+        3: "pending",
+    }
+
+
+def test_plan_step_lifecycle_events_update_the_explicit_step() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        _emit_event(
+            PlanStepStartedEvent(
+                agent_role="Agent",
+                step_number=2,
+                step_description="Second",
+            )
+        )
+
+        assert app._plan_step_status == {
+            1: "pending",
+            2: "active",
+            3: "pending",
+        }
+
+        _emit_event(
+            PlanStepCompletedEvent(
+                agent_role="Agent",
+                step_number=2,
+                step_description="Second",
+                success=True,
+                result="done",
+            )
+        )
+    finally:
+        app._unsubscribe()
+
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "done",
+        3: "pending",
+    }
+
+
+def test_failed_plan_step_lifecycle_event_marks_exact_step_failed() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        _emit_event(
+            PlanStepCompletedEvent(
+                agent_role="Agent",
+                step_number=2,
+                step_description="Second",
+                success=False,
+                error="Step failed",
+            )
+        )
+    finally:
+        app._unsubscribe()
+
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "failed",
+        3: "pending",
+    }
+
+
+def test_tool_usage_events_do_not_advance_plan_steps() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        future = crewai_event_bus.emit(
+            None,
+            ToolUsageStartedEvent(tool_name="search", tool_args={"query": "CrewAI"}),
+        )
+        if future:
+            future.result(timeout=5)
+
+        now = datetime.now()
+        future = crewai_event_bus.emit(
+            None,
+            ToolUsageFinishedEvent(
+                tool_name="search",
+                tool_args={"query": "CrewAI"},
+                started_at=now,
+                finished_at=now,
+                output="result",
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+    finally:
+        app._unsubscribe()
+
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "pending",
+        3: "pending",
+    }
+
+
+def test_next_tool_does_not_mark_unfinished_tool_successful() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        _emit_event(
+            ToolUsageStartedEvent(tool_name="search", tool_args={"query": "CrewAI"}),
+        )
+        _emit_event(
+            ToolUsageStartedEvent(tool_name="scrape", tool_args={"url": "https://x"}),
+        )
+    finally:
+        app._unsubscribe()
+
+    assert app._log_entries[0]["status"] == "timeout"
+    assert app._log_entries[0]["result"] is None
+    assert app._log_entries[0]["error"] == (
+        "No result received before the next tool started"
+    )
+    assert app._log_entries[1]["status"] == "running"
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "pending",
+        3: "pending",
+    }
+
+
+def test_internal_reasoning_function_call_is_hidden_from_activity_log() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        future = crewai_event_bus.emit(
+            None,
+            ToolUsageStartedEvent(
+                tool_name="create_reasoning_plan",
+                tool_args={"plan": "Plan", "steps": [], "ready": True},
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+
+        now = datetime.now()
+        future = crewai_event_bus.emit(
+            None,
+            ToolUsageFinishedEvent(
+                tool_name="create_reasoning_plan",
+                tool_args={"plan": "Plan", "steps": [], "ready": True},
+                started_at=now,
+                finished_at=now,
+                output='{"plan":"Plan","steps":[],"ready":true}',
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+
+        future = crewai_event_bus.emit(
+            None,
+            ToolUsageErrorEvent(
+                tool_name="create_reasoning_plan",
+                tool_args={"plan": "Plan", "steps": [], "ready": True},
+                error="internal planning fallback",
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+    finally:
+        app._unsubscribe()
+
+    assert app._log_entries == []
+    assert app._current_task_steps == []
+
+
+def test_tool_failure_does_not_override_successful_plan_step_completion() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        _emit_event(
+            PlanStepStartedEvent(
+                agent_role="Agent",
+                step_number=1,
+                step_description="First",
+            )
+        )
+        _emit_event(
+            ToolUsageStartedEvent(
+                tool_name="search_the_internet_with_serper",
+                tool_args={"search_query": "CrewAI release"},
+                plan_step_number=1,
+                plan_step_description="First",
+            )
+        )
+        _emit_event(
+            ToolUsageErrorEvent(
+                tool_name="search_the_internet_with_serper",
+                tool_args={"search_query": "CrewAI release"},
+                plan_step_number=1,
+                plan_step_description="First",
+                error="No results",
+            )
+        )
+        _emit_event(
+            PlanStepCompletedEvent(
+                agent_role="Agent",
+                step_number=1,
+                step_description="First",
+                success=True,
+                result="Recovered with another source",
+            )
+        )
+    finally:
+        app._unsubscribe()
+
+    assert app._plan_step_status == {
+        1: "done",
+        2: "pending",
+        3: "pending",
+    }
+
+
+def test_tool_event_step_metadata_is_stored_in_activity_log() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        _emit_event(
+            ToolUsageStartedEvent(
+                tool_name="search_the_internet_with_serper",
+                tool_args={"search_query": "CrewAI release"},
+                plan_step_number=2,
+                plan_step_description="Second",
+            )
+        )
+        now = datetime.now()
+        _emit_event(
+            ToolUsageFinishedEvent(
+                tool_name="search_the_internet_with_serper",
+                tool_args={"search_query": "CrewAI release"},
+                plan_step_number=2,
+                plan_step_description="Second",
+                started_at=now,
+                finished_at=now,
+                output="Found official source",
+            )
+        )
+    finally:
+        app._unsubscribe()
+
+    assert app._log_entries[0]["plan_step_number"] == 2
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "pending",
+        3: "pending",
+    }
+
+
+def test_starting_next_tool_does_not_infer_plan_step_progress() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        _emit_event(
+            ToolUsageStartedEvent(
+                tool_name="search_the_internet_with_serper",
+                tool_args={"search_query": "CrewAI release"},
+            )
+        )
+        _emit_event(
+            ToolUsageErrorEvent(
+                tool_name="search_the_internet_with_serper",
+                tool_args={"search_query": "CrewAI release"},
+                error="No results",
+            )
+        )
+        _emit_event(
+            ToolUsageStartedEvent(
+                tool_name="read_website_content",
+                tool_args={"url": "https://example.com"},
+            )
+        )
+    finally:
+        app._unsubscribe()
+
+    assert app._log_entries[0]["status"] == "error"
+    assert app._log_entries[1]["status"] == "running"
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "pending",
+        3: "pending",
+    }
+
+
+@pytest.mark.asyncio
+async def test_crew_done_does_not_mark_unfinished_tool_successful() -> None:
+    app = _app_with_plan()
+
+    async with app.run_test(size=(100, 40)) as pilot:
+        app._plan_step_status = {1: "failed", 2: "done", 3: "pending"}
+        app._log_entries = [
+            {
+                "tool_name": "search",
+                "status": "running",
+                "args": '{"query": "CrewAI"}',
+                "result": None,
+                "error": None,
+                "start_time": time.time() - 2,
+                "duration": None,
+                "task_idx": 1,
+            }
+        ]
+
+        app._on_crew_done("final output")
+        await pilot.pause()
+
+    assert app._log_entries[0]["status"] == "timeout"
+    assert app._log_entries[0]["result"] is None
+    assert app._log_entries[0]["error"] == "No result received before crew completed"
+    assert app._plan_step_status == {1: "failed", 2: "done", 3: "done"}
+
+
+def test_streamed_step_observation_updates_named_step_only() -> None:
+    app = _app_with_plan()
+
+    updated = app._try_parse_step_observation(
+        '{"step_completed_successfully":true,'
+        '"key_information_learned":"Step 2 succeeded with the official source."}'
+    )
+
+    assert updated is True
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "done",
+        3: "pending",
+    }
+
+
+def test_failed_streamed_step_observation_marks_named_step_failed() -> None:
+    app = _app_with_plan()
+
+    updated = app._try_parse_step_observation(
+        '{"step_completed_successfully":false,'
+        '"key_information_learned":"Step 2 failed because the tool failed."}'
+    )
+
+    assert updated is True
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "failed",
+        3: "pending",
+    }
+
+
+def test_streamed_goal_achieved_observation_collapses_remaining_steps_done() -> None:
+    app = _app_with_plan()
+
+    updated = app._try_parse_step_observation(
+        '{"step_number":2,'
+        '"step_completed_successfully":true,'
+        '"key_information_learned":"Goal is already satisfied.",'
+        '"goal_already_achieved":true}'
+    )
+
+    assert updated is True
+    assert app._plan_step_status == {
+        1: "done",
+        2: "done",
+        3: "done",
+    }
+
+
+def test_task_completion_collapses_pending_plan_steps_but_preserves_failed() -> None:
+    app = _app_with_plan()
+    app._plan_step_status = {1: "failed", 2: "done", 3: "pending"}
+
+    app._collapse_plan_on_task_done()
+
+    assert app._plan_step_status == {1: "failed", 2: "done", 3: "done"}
+
+
+def test_observation_failure_collapses_to_done_because_executor_continues() -> None:
+    app = _app_with_plan()
+    app._plan_step_status = {1: "done", 2: "active", 3: "pending"}
+    app._subscribe()
+    try:
+        future = crewai_event_bus.emit(
+            None,
+            StepObservationFailedEvent(
+                agent_role="Agent",
+                step_number=2,
+                step_description="Second",
+                error="observer timeout",
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+    finally:
+        app._unsubscribe()
+
+    assert app._plan_step_status == {
+        1: "done",
+        2: "done",
+        3: "pending",
+    }
+
+
+def test_goal_achieved_event_collapses_remaining_steps_done() -> None:
+    app = _app_with_plan()
+    app._plan_step_status = {1: "done", 2: "active", 3: "pending"}
+    app._subscribe()
+    try:
+        future = crewai_event_bus.emit(
+            None,
+            GoalAchievedEarlyEvent(
+                agent_role="Agent",
+                step_number=2,
+                steps_completed=2,
+                steps_remaining=1,
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+    finally:
+        app._unsubscribe()
+
+    assert app._plan_step_status == {
+        1: "done",
+        2: "done",
+        3: "done",
+    }
+
+
+def test_replan_event_keeps_old_plan_until_next_streamed_plan_replaces_it() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        future = crewai_event_bus.emit(
+            None,
+            PlanReplanTriggeredEvent(
+                agent_role="Agent",
+                step_number=2,
+                replan_reason="Need updated sources",
+                replan_count=1,
+                completed_steps_preserved=1,
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+    finally:
+        app._unsubscribe()
+
+    assert app._plan is not None
+    assert app._plan_step_status == {1: "pending", 2: "pending", 3: "pending"}
+    assert app._awaiting_replan is True
+
+    app._try_parse_plan(
+        '{"plan":"Updated plan","steps":['
+        '{"step_number":1,"description":"Updated first"},'
+        '{"step_number":2,"description":"Updated second"}]}'
+    )
+
+    assert app._plan == {
+        "plan": "Updated plan",
+        "steps": [
+            {"step_number": 1, "description": "Updated first"},
+            {"step_number": 2, "description": "Updated second"},
+        ],
+    }
+    assert app._plan_step_status == {1: "pending", 2: "pending"}
+    assert app._awaiting_replan is False
+
+
+def test_plan_refinement_updates_descriptions_without_new_statuses() -> None:
+    app = _app_with_plan()
+    app._plan_step_status = {1: "done", 2: "active", 3: "pending"}
+    app._subscribe()
+    try:
+        future = crewai_event_bus.emit(
+            None,
+            PlanRefinementEvent(
+                agent_role="Agent",
+                step_number=2,
+                refined_step_count=1,
+                refinements=["Step 3: Write the final answer from verified facts"],
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+    finally:
+        app._unsubscribe()
+
+    assert app._plan_step_status == {
+        1: "done",
+        2: "done",
+        3: "pending",
+    }
+    assert app._plan["steps"][2]["description"] == (
+        "Write the final answer from verified facts"
+    )
+
+
+def test_step_observation_json_is_hidden_from_streaming_text() -> None:
+    app = _app_with_plan()
+
+    assert (
+        app._strip_step_observation_json(
+            'Visible before {"step_completed_successfully":true,'
+            '"key_information_learned":"Step 2 succeeded."} visible after'
+        )
+        == "Visible before  visible after"
+    )
+
+
+@pytest.mark.asyncio
+async def test_completed_run_keeps_activity_log_keyboard_navigation_active() -> None:
+    app = CrewRunApp()
+
+    async with app.run_test(size=(100, 40)) as pilot:
+        app._log_entries = [_log_entry("search"), _log_entry("scrape")]
+
+        app._on_crew_done("final output")
+        await pilot.pause()
+
+        assert app.focused is app.query_one("#log-panel")
+
+        await pilot.press("down", "enter")
+        await pilot.pause()
+
+        assert app._log_cursor == 1
+        assert app._log_expanded == {1}
+
+        await pilot.press("up")
+        await pilot.pause()
+
+        assert app._log_cursor == 0
+
+
+class _FakeTask:
+    fingerprint = None
+
+    def __init__(self, task_id: str, name: str) -> None:
+        self.id = task_id
+        self.name = name
+        self.description = name
+
+
+def test_async_task_completion_marks_the_right_sidebar_row() -> None:
+    """Overlapping tasks: completing task 1 while task 2 runs must not
+    mark task 2 done, and starting task 2 must not mark task 1 done."""
+    from crewai.events.types.task_events import TaskCompletedEvent, TaskStartedEvent
+    from crewai.tasks.task_output import TaskOutput
+
+    app = CrewRunApp(total_tasks=2, task_names=["first", "second"])
+    app._subscribe()
+    try:
+        task1 = _FakeTask("id-1", "first")
+        task2 = _FakeTask("id-2", "second")
+
+        for task in (task1, task2):
+            future = crewai_event_bus.emit(
+                None, TaskStartedEvent(context=None, task=task)
+            )
+            if future:
+                future.result(timeout=5)
+
+        # Both started: neither prematurely done
+        assert app._task_statuses == {1: "active", 2: "active"}
+
+        future = crewai_event_bus.emit(
+            None,
+            TaskCompletedEvent(
+                output=TaskOutput(description="first", raw="done", agent="a"),
+                task=task1,
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+
+        assert app._task_statuses == {1: "done", 2: "active"}
+    finally:
+        app._unsubscribe()
+
+
+def test_pop_task_state_falls_back_to_current_task() -> None:
+    app = CrewRunApp(total_tasks=2, task_names=["first", "second"])
+    app._current_task_idx = 2
+    app._current_task_desc = "second"
+
+    class _Evt:
+        task = None
+        task_name = "unknown"
+
+    state = app._pop_task_state(_Evt())
+    assert state["idx"] == 2
+    assert state["desc"] == "second"
+
+
+def test_overlapping_task_logs_keep_their_own_state() -> None:
+    """Task 1 completing after task 2 started must log its own description,
+    agent, and output — and must not steal or reset task 2's stream state."""
+    from crewai.events.types.task_events import TaskCompletedEvent, TaskStartedEvent
+    from crewai.tasks.task_output import TaskOutput
+
+    app = CrewRunApp(total_tasks=2, task_names=["first", "second"])
+    app._subscribe()
+    try:
+        task1 = _FakeTask("id-1", "first")
+        task2 = _FakeTask("id-2", "second")
+
+        for task in (task1, task2):
+            future = crewai_event_bus.emit(
+                None, TaskStartedEvent(context=None, task=task)
+            )
+            if future:
+                future.result(timeout=5)
+
+        # Task 2 is current and has streamed state in flight
+        app._task_full_output = "task two streaming output"
+        app._current_task_steps = [{"type": "llm", "summary": "thinking"}]
+
+        future = crewai_event_bus.emit(
+            None,
+            TaskCompletedEvent(
+                output=TaskOutput(
+                    description="first", raw="task one result", agent="a1"
+                ),
+                task=task1,
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+
+        # Task 1's entry carries its own identity and output
+        entry1 = app._task_logs[-1]
+        assert entry1["idx"] == 1
+        assert entry1["desc"] == "first"
+        assert entry1["output"] == "task one result"
+        assert entry1["steps"] == []
+
+        # Task 2's in-flight stream state was not consumed or reset
+        assert app._task_full_output == "task two streaming output"
+        assert app._current_task_steps == [{"type": "llm", "summary": "thinking"}]
+
+        future = crewai_event_bus.emit(
+            None,
+            TaskCompletedEvent(
+                output=TaskOutput(
+                    description="second", raw="task two result", agent="a2"
+                ),
+                task=task2,
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+
+        entry2 = app._task_logs[-1]
+        assert entry2["idx"] == 2
+        assert entry2["desc"] == "second"
+        assert entry2["output"] == "task two streaming output"
+        assert any(step.get("summary") == "thinking" for step in entry2["steps"])
+    finally:
+        app._unsubscribe()

lib/cli/tests/test_git.py

@@ -31,6 +31,18 @@ def test_is_git_not_installed(fp):
         Repository(path=".")
 
 
+def test_fetch_failure_raises_value_error(fp):
+    fp.register(["git", "--version"], stdout="git version 2.30.0\n")
+    fp.register(["git", "rev-parse", "--is-inside-work-tree"], stdout="true\n")
+    fp.register(["git", "fetch"], returncode=128, stderr="remote unavailable\n")
+
+    with pytest.raises(
+        ValueError,
+        match=r"Git fetch failed with exit code 128 for command \['git', 'fetch'\]: remote unavailable",
+    ):
+        Repository(path=".")
+
+
 def test_status(fp, repository):
     fp.register(
         ["git", "status", "--branch", "--porcelain"],
@@ -99,3 +111,45 @@ def test_origin_url(fp, repository):
         stdout="https://github.com/user/repo.git\n",
     )
     assert repository.origin_url() == "https://github.com/user/repo.git"
+
+
+def test_initialize_creates_initial_commit(fp, tmp_path):
+    fp.register(["git", "--version"], stdout="git version 2.30.0\n")
+    fp.register(["git", "init"], stdout="")
+    fp.register(["git", "--version"], stdout="git version 2.30.0\n")
+    fp.register(["git", "rev-parse", "--is-inside-work-tree"], stdout="true\n")
+    fp.register(["git", "rev-parse", "--verify", "HEAD"], returncode=1)
+    fp.register(["git", "add", "."], stdout="")
+    fp.register(
+        [
+            "git",
+            "-c",
+            "user.name=CrewAI",
+            "-c",
+            "user.email=deploy@crewai.com",
+            "commit",
+            "--allow-empty",
+            "-m",
+            "Initial crew",
+        ],
+        stdout="",
+    )
+
+    repo = Repository.initialize(path=str(tmp_path))
+
+    assert repo.path == str(tmp_path)
+    exclude_file = tmp_path / ".git" / "info" / "exclude"
+    exclude_text = exclude_file.read_text()
+    assert ".env" in exclude_text
+    assert "!.env.example" in exclude_text
+    assert "!.env.sample" in exclude_text
+    assert "__pycache__/" in exclude_text
+
+
+def test_deployable_files_uses_git_excludes(fp, repository):
+    fp.register(
+        ["git", "ls-files", "--cached", "--others", "--exclude-standard"],
+        stdout="pyproject.toml\nsrc/main.py\n",
+    )
+
+    assert repository.deployable_files() == ["pyproject.toml", "src/main.py"]

lib/cli/tests/test_install_crew.py

@@ -0,0 +1,102 @@
+from pathlib import Path
+import subprocess
+
+import pytest
+
+import crewai_cli.install_crew as install_crew_module
+
+
+@pytest.fixture(autouse=True)
+def _tool_credentials(monkeypatch):
+    monkeypatch.setattr(
+        install_crew_module,
+        "build_env_with_all_tool_credentials",
+        lambda: {"CREWAI_TEST": "1"},
+    )
+
+
+def test_install_crew_json_project_skips_project_install(
+    fp, monkeypatch, tmp_path: Path
+):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "pyproject.toml").write_text(
+        """
+[project]
+name = "json_crew"
+
+[tool.crewai]
+type = "crew"
+""".strip()
+    )
+    (tmp_path / "crew.jsonc").write_text("{}\n")
+    fp.register(["uv", "sync", "--no-install-project"], stdout="")
+
+    install_crew_module.install_crew([])
+
+
+def test_install_crew_json_project_with_python_package_installs_project(
+    fp, monkeypatch, tmp_path: Path
+):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "pyproject.toml").write_text(
+        """
+[project]
+name = "hybrid-crew"
+
+[tool.crewai]
+type = "crew"
+""".strip()
+    )
+    (tmp_path / "crew.jsonc").write_text("{}\n")
+    package_dir = tmp_path / "src" / "hybrid_crew"
+    package_dir.mkdir(parents=True)
+    (package_dir / "crew.py").write_text("class HybridCrew: ...\n")
+    fp.register(["uv", "sync"], stdout="")
+
+    install_crew_module.install_crew([])
+
+
+def test_install_crew_flow_project_installs_project(fp, monkeypatch, tmp_path: Path):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "pyproject.toml").write_text(
+        """
+[project]
+name = "flow_project"
+
+[tool.crewai]
+type = "flow"
+""".strip()
+    )
+    (tmp_path / "crew.jsonc").write_text("{}\n")
+    fp.register(["uv", "sync"], stdout="")
+
+    install_crew_module.install_crew([])
+
+
+def test_install_crew_classic_project_installs_project(
+    fp, monkeypatch, tmp_path: Path
+):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'classic'\n")
+    fp.register(["uv", "sync"], stdout="")
+
+    install_crew_module.install_crew([])
+
+
+def test_install_crew_install_project_false_adds_no_install_project(fp):
+    fp.register(["uv", "sync", "--no-install-project", "--frozen"], stdout="")
+
+    install_crew_module.install_crew(["--frozen"], install_project=False)
+
+
+def test_install_crew_reraises_sync_failure_when_requested(fp):
+    fp.register(["uv", "sync"], returncode=1, stderr="sync failed\n")
+
+    with pytest.raises(subprocess.CalledProcessError):
+        install_crew_module.install_crew([], raise_on_error=True)
+
+
+def test_install_crew_swallows_sync_failure_by_default(fp):
+    fp.register(["uv", "sync"], returncode=1, stderr="sync failed\n")
+
+    install_crew_module.install_crew([])

lib/cli/tests/test_plus_api.py

@@ -292,6 +292,36 @@ class TestPlusAPI(unittest.TestCase):
             "POST", "/crewai_plus/api/v1/crews", json=payload
         )
 
+    @patch("crewai_cli.plus_api.PlusAPI._make_multipart_request")
+    def test_create_crew_from_zip(self, mock_make_multipart_request):
+        self.api.create_crew_from_zip(
+            "/tmp/test.zip",
+            name="test_crew",
+            env={"ENV_VAR": "value"},
+        )
+        mock_make_multipart_request.assert_called_once_with(
+            "POST",
+            "/crewai_plus/api/v1/crews/zip",
+            zip_file_path="/tmp/test.zip",
+            data={"name": "test_crew", "env[ENV_VAR]": "value"},
+            timeout=300,
+        )
+
+    @patch("crewai_cli.plus_api.PlusAPI._make_multipart_request")
+    def test_update_crew_from_zip(self, mock_make_multipart_request):
+        self.api.update_crew_from_zip(
+            "test_uuid",
+            "/tmp/test.zip",
+            env={"ENV_VAR": "value"},
+        )
+        mock_make_multipart_request.assert_called_once_with(
+            "POST",
+            "/crewai_plus/api/v1/crews/test_uuid/zip_update",
+            zip_file_path="/tmp/test.zip",
+            data={"env[ENV_VAR]": "value"},
+            timeout=300,
+        )
+
     @patch("crewai_core.plus_api.Settings")
     @patch.dict(os.environ, {"CREWAI_PLUS_URL": ""})
     def test_custom_base_url(self, mock_settings_class):

lib/cli/tests/test_run_crew.py

@@ -0,0 +1,470 @@
+"""Tests for crewai_cli.run_crew JSON crew handling."""
+
+import os
+from pathlib import Path
+import subprocess
+import sys
+
+import pytest
+from crewai_core.constants import CREWAI_TRAINED_AGENTS_FILE_ENV
+
+import crewai_cli.run_crew as run_crew_module
+
+
+def test_run_crew_forwards_trained_agents_file_to_json_crews(monkeypatch):
+    """crewai run -f must reach JSON crews, not only classic subprocess crews."""
+    monkeypatch.setattr(run_crew_module, "_has_json_crew", lambda: True)
+    called: dict = {}
+
+    def fake_run_json_crew_in_project_env(trained_agents_file=None):
+        called["trained_agents_file"] = trained_agents_file
+
+    monkeypatch.setattr(
+        run_crew_module,
+        "_run_json_crew_in_project_env",
+        fake_run_json_crew_in_project_env,
+    )
+
+    run_crew_module.run_crew(trained_agents_file="some.pkl")
+
+    assert called == {"trained_agents_file": "some.pkl"}
+
+
+def test_json_run_uses_project_env_when_pyproject_exists(monkeypatch, tmp_path: Path):
+    """JSON crew runs should execute inside the project uv environment."""
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+    install_calls = []
+    subprocess_calls = []
+
+    monkeypatch.setattr(
+        run_crew_module,
+        "_install_json_crew_dependencies_if_needed",
+        lambda: install_calls.append(True),
+    )
+    monkeypatch.setattr(
+        run_crew_module,
+        "build_env_with_all_tool_credentials",
+        lambda: {"EXISTING": "value"},
+    )
+
+    def fake_subprocess_run(command, **kwargs):
+        subprocess_calls.append((command, kwargs))
+
+    monkeypatch.setattr(run_crew_module.subprocess, "run", fake_subprocess_run)
+
+    run_crew_module._run_json_crew_in_project_env(
+        trained_agents_file="trained.pkl"
+    )
+
+    expected_env = {
+        "EXISTING": "value",
+        run_crew_module._CREWAI_CLI_RUNNER_PACKAGE_DIR_ENV: str(
+            Path(run_crew_module.__file__).resolve().parent
+        ),
+        CREWAI_TRAINED_AGENTS_FILE_ENV: "trained.pkl",
+    }
+    if local_crewai_source_dir := run_crew_module._find_local_crewai_source_dir():
+        expected_env[run_crew_module._CREWAI_RUNNER_SOURCE_DIR_ENV] = str(
+            local_crewai_source_dir
+        )
+
+    assert install_calls == [True]
+    assert subprocess_calls == [
+        (
+            [
+                "uv",
+                "run",
+                "--no-sync",
+                "python",
+                "-c",
+                run_crew_module._JSON_CREW_RUNNER_CODE,
+            ],
+            {
+                "capture_output": False,
+                "text": True,
+                "check": True,
+                "env": expected_env,
+            },
+        )
+    ]
+
+
+def test_json_run_uses_poetry_run_for_poetry_lock_without_uv_lock(
+    monkeypatch, tmp_path: Path
+):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+    (tmp_path / "poetry.lock").write_text("# lock\n")
+    monkeypatch.setattr(
+        run_crew_module,
+        "_install_json_crew_dependencies_if_needed",
+        lambda: None,
+    )
+    monkeypatch.setattr(
+        run_crew_module,
+        "build_env_with_all_tool_credentials",
+        lambda: {},
+    )
+    subprocess_calls = []
+
+    def fake_subprocess_run(command, **kwargs):
+        subprocess_calls.append((command, kwargs))
+
+    monkeypatch.setattr(run_crew_module.subprocess, "run", fake_subprocess_run)
+
+    run_crew_module._run_json_crew_in_project_env()
+
+    expected_env = {
+        run_crew_module._CREWAI_CLI_RUNNER_PACKAGE_DIR_ENV: str(
+            Path(run_crew_module.__file__).resolve().parent
+        ),
+    }
+    if local_crewai_source_dir := run_crew_module._find_local_crewai_source_dir():
+        expected_env[run_crew_module._CREWAI_RUNNER_SOURCE_DIR_ENV] = str(
+            local_crewai_source_dir
+        )
+
+    assert subprocess_calls == [
+        (
+            [
+                "poetry",
+                "run",
+                "python",
+                "-c",
+                run_crew_module._JSON_CREW_RUNNER_CODE,
+            ],
+            {
+                "capture_output": False,
+                "text": True,
+                "check": True,
+                "env": expected_env,
+            },
+        )
+    ]
+
+
+def test_json_runner_code_loads_current_cli_package_over_project_env(tmp_path: Path):
+    old_parent = tmp_path / "old"
+    old_pkg = old_parent / "crewai_cli"
+    old_pkg.mkdir(parents=True)
+    (old_pkg / "__init__.py").write_text("")
+    (old_pkg / "run_crew.py").write_text("raise ImportError('old package used')\n")
+    old_crewai_project = old_parent / "crewai" / "project"
+    old_crewai_project.mkdir(parents=True)
+    (old_parent / "crewai" / "__init__.py").write_text("")
+    (old_crewai_project / "__init__.py").write_text("")
+    (old_crewai_project / "json_loader.py").write_text(
+        "raise ImportError('old crewai used')\n"
+    )
+
+    current_pkg = tmp_path / "current" / "crewai_cli"
+    current_pkg.mkdir(parents=True)
+    marker = tmp_path / "marker.txt"
+    (current_pkg / "__init__.py").write_text("")
+    (current_pkg / "run_crew.py").write_text(
+        "from pathlib import Path\n"
+        "from crewai.project.json_loader import SOURCE\n"
+        "def _run_json_crew(trained_agents_file=None):\n"
+        f"    Path({str(marker)!r}).write_text(SOURCE + ':' + (trained_agents_file or ''))\n"
+    )
+    current_crewai_project = tmp_path / "current_crewai_src" / "crewai" / "project"
+    current_crewai_project.mkdir(parents=True)
+    (tmp_path / "current_crewai_src" / "crewai" / "__init__.py").write_text("")
+    (current_crewai_project / "__init__.py").write_text("")
+    (current_crewai_project / "json_loader.py").write_text("SOURCE = 'current'\n")
+
+    env = os.environ.copy()
+    env["PYTHONPATH"] = str(old_parent)
+    env[run_crew_module._CREWAI_CLI_RUNNER_PACKAGE_DIR_ENV] = str(current_pkg)
+    env[run_crew_module._CREWAI_RUNNER_SOURCE_DIR_ENV] = str(
+        tmp_path / "current_crewai_src"
+    )
+    env[CREWAI_TRAINED_AGENTS_FILE_ENV] = "trained.pkl"
+
+    subprocess.run(
+        [sys.executable, "-c", run_crew_module._JSON_CREW_RUNNER_CODE],
+        check=True,
+        env=env,
+        cwd=tmp_path,
+    )
+
+    assert marker.read_text() == "current:trained.pkl"
+
+
+def test_json_run_without_pyproject_runs_in_process(monkeypatch, tmp_path: Path):
+    monkeypatch.chdir(tmp_path)
+    called: dict = {}
+
+    def fake_run_json_crew(trained_agents_file=None):
+        called["trained_agents_file"] = trained_agents_file
+        return "result"
+
+    monkeypatch.setattr(run_crew_module, "_run_json_crew", fake_run_json_crew)
+
+    assert (
+        run_crew_module._run_json_crew_in_project_env(
+            trained_agents_file="trained.pkl"
+        )
+        == "result"
+    )
+    assert called == {"trained_agents_file": "trained.pkl"}
+
+
+def test_json_project_env_run_failure_exits_nonzero(monkeypatch, tmp_path: Path):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+
+    monkeypatch.setattr(
+        run_crew_module, "_install_json_crew_dependencies_if_needed", lambda: None
+    )
+    monkeypatch.setattr(
+        run_crew_module, "build_env_with_all_tool_credentials", lambda: {}
+    )
+
+    def fake_subprocess_run(command, **kwargs):
+        raise subprocess.CalledProcessError(7, command)
+
+    monkeypatch.setattr(run_crew_module.subprocess, "run", fake_subprocess_run)
+
+    with pytest.raises(SystemExit) as exc_info:
+        run_crew_module._run_json_crew_in_project_env()
+
+    assert exc_info.value.code == 7
+
+
+def test_json_run_installs_dependencies_when_pyproject_has_no_lockfile(
+    monkeypatch, tmp_path: Path
+):
+    """JSON crew runs should lock/sync project dependencies only when needed."""
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+    calls = []
+
+    def fake_install_crew(
+        proxy_options, *, raise_on_error=False, install_project=None
+    ):
+        calls.append((proxy_options, raise_on_error, install_project))
+
+    monkeypatch.setattr("crewai_cli.install_crew.install_crew", fake_install_crew)
+
+    run_crew_module._install_json_crew_dependencies_if_needed()
+
+    assert calls == [([], True, None)]
+
+
+def test_json_run_syncs_frozen_when_uv_lock_exists_without_venv(
+    monkeypatch, tmp_path: Path
+):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+    (tmp_path / "uv.lock").write_text("# lock\n")
+    calls = []
+
+    def fake_install_crew(
+        proxy_options, *, raise_on_error=False, install_project=None
+    ):
+        calls.append((proxy_options, raise_on_error, install_project))
+
+    monkeypatch.setattr("crewai_cli.install_crew.install_crew", fake_install_crew)
+
+    run_crew_module._install_json_crew_dependencies_if_needed()
+
+    assert calls == [(["--frozen"], True, None)]
+
+
+def test_json_run_skips_uv_sync_when_only_poetry_lock_exists_without_venv(
+    monkeypatch, tmp_path: Path
+):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+    (tmp_path / "poetry.lock").write_text("# lock\n")
+    calls = []
+
+    def fake_install_crew(
+        proxy_options, *, raise_on_error=False, install_project=None
+    ):
+        calls.append((proxy_options, raise_on_error, install_project))
+
+    monkeypatch.setattr("crewai_cli.install_crew.install_crew", fake_install_crew)
+
+    run_crew_module._install_json_crew_dependencies_if_needed()
+
+    assert calls == []
+
+
+@pytest.mark.parametrize("lockfile", ["uv.lock", "poetry.lock"])
+def test_json_run_skips_dependency_install_when_lockfile_and_venv_exist(
+    monkeypatch, tmp_path: Path, lockfile: str
+):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+    (tmp_path / lockfile).write_text("# lock\n")
+    (tmp_path / ".venv").mkdir()
+    calls = []
+
+    def fake_install_crew(
+        proxy_options, *, raise_on_error=False, install_project=None
+    ):
+        calls.append((proxy_options, raise_on_error, install_project))
+
+    monkeypatch.setattr("crewai_cli.install_crew.install_crew", fake_install_crew)
+
+    run_crew_module._install_json_crew_dependencies_if_needed()
+
+    assert calls == []
+
+
+def test_json_run_skips_dependency_install_without_pyproject(
+    monkeypatch, tmp_path: Path
+):
+    monkeypatch.chdir(tmp_path)
+    calls = []
+
+    def fake_install_crew(
+        proxy_options, *, raise_on_error=False, install_project=None
+    ):
+        calls.append((proxy_options, raise_on_error))
+
+    monkeypatch.setattr("crewai_cli.install_crew.install_crew", fake_install_crew)
+
+    run_crew_module._install_json_crew_dependencies_if_needed()
+
+    assert calls == []
+
+
+def test_json_run_install_failure_exits_nonzero(monkeypatch, tmp_path: Path):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "pyproject.toml").write_text("[project]\nname = 'demo'\n")
+
+    def fake_install_crew(
+        proxy_options, *, raise_on_error=False, install_project=None
+    ):
+        raise subprocess.CalledProcessError(42, ["uv", "sync"])
+
+    monkeypatch.setattr("crewai_cli.install_crew.install_crew", fake_install_crew)
+
+    with pytest.raises(SystemExit) as exc_info:
+        run_crew_module._install_json_crew_dependencies_if_needed()
+
+    assert exc_info.value.code == 42
+
+
+def test_run_json_crew_exports_trained_agents_env(monkeypatch, tmp_path: Path):
+    """JSON crews run in-process, so the pickle path must land in the env var."""
+    monkeypatch.chdir(tmp_path)
+    monkeypatch.delenv(CREWAI_TRAINED_AGENTS_FILE_ENV, raising=False)
+
+    try:
+        # No crew.json(c) in tmp_path: the loader fails *after* the env var
+        # export, which is the part under test.
+        with pytest.raises(FileNotFoundError):
+            run_crew_module._run_json_crew(trained_agents_file="some.pkl")
+        assert os.environ[CREWAI_TRAINED_AGENTS_FILE_ENV] == "some.pkl"
+    finally:
+        os.environ.pop(CREWAI_TRAINED_AGENTS_FILE_ENV, None)
+
+
+def test_run_json_crew_leaves_env_untouched_without_flag(monkeypatch, tmp_path: Path):
+    monkeypatch.chdir(tmp_path)
+    monkeypatch.delenv(CREWAI_TRAINED_AGENTS_FILE_ENV, raising=False)
+
+    with pytest.raises(FileNotFoundError):
+        run_crew_module._run_json_crew()
+
+    assert CREWAI_TRAINED_AGENTS_FILE_ENV not in os.environ
+
+
+def test_missing_input_names_accepts_hyphenated_placeholders():
+    """The prompt regex must accept the same names kickoff interpolation does."""
+    from types import SimpleNamespace
+
+    crew = SimpleNamespace(
+        agents=[
+            SimpleNamespace(
+                role="Researcher", goal="Cover {my-topic}", backstory=""
+            )
+        ],
+        tasks=[
+            SimpleNamespace(
+                description="Write about {my-topic} for {target-audience}",
+                expected_output="Post",
+                output_file=None,
+            )
+        ],
+    )
+
+    assert run_crew_module._missing_input_names(crew, {}) == [
+        "my-topic",
+        "target-audience",
+    ]
+
+
+def _patch_tui_run(monkeypatch, status: str):
+    """Stub the TUI pieces of _run_json_crew so only exit handling runs."""
+
+    class FakeApp:
+        def __init__(self, **kwargs):
+            self._status = status
+            self._crew_result = "result" if status == "completed" else None
+            self._want_deploy = False
+
+        def run(self):
+            pass
+
+    from types import SimpleNamespace
+
+    crew = SimpleNamespace(name="Demo", tasks=[], agents=[])
+    monkeypatch.setattr(
+        run_crew_module, "find_crew_json_file", lambda: Path("crew.jsonc")
+    )
+    monkeypatch.setattr(
+        run_crew_module,
+        "_load_json_crew_for_tui",
+        lambda _path: (FakeApp, crew, {}, [], []),
+    )
+    monkeypatch.setattr(
+        run_crew_module, "_prompt_for_missing_inputs", lambda _crew, inputs: inputs
+    )
+    monkeypatch.setattr(run_crew_module, "_print_post_tui_summary", lambda _app: None)
+
+
+def test_run_json_crew_failed_status_exits_nonzero(monkeypatch, tmp_path: Path):
+    monkeypatch.chdir(tmp_path)
+    _patch_tui_run(monkeypatch, status="failed")
+
+    with pytest.raises(SystemExit) as exc_info:
+        run_crew_module._run_json_crew()
+
+    assert exc_info.value.code == 1
+
+
+def test_run_json_crew_completed_status_returns_result(monkeypatch, tmp_path: Path):
+    monkeypatch.chdir(tmp_path)
+    _patch_tui_run(monkeypatch, status="completed")
+
+    assert run_crew_module._run_json_crew() == "result"
+
+
+def test_has_json_crew_defers_to_declared_flow_type(monkeypatch, tmp_path: Path):
+    """A flow project containing a stray crew.jsonc must still run as a flow."""
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "crew.jsonc").write_text("{}")
+    (tmp_path / "pyproject.toml").write_text('[tool.crewai]\ntype = "flow"\n')
+
+    assert run_crew_module._has_json_crew() is False
+
+
+def test_has_json_crew_true_for_declared_crew_type(monkeypatch, tmp_path: Path):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "crew.jsonc").write_text("{}")
+    (tmp_path / "pyproject.toml").write_text('[tool.crewai]\ntype = "crew"\n')
+
+    assert run_crew_module._has_json_crew() is True
+
+
+def test_has_json_crew_true_without_pyproject(monkeypatch, tmp_path: Path):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "crew.jsonc").write_text("{}")
+
+    assert run_crew_module._has_json_crew() is True

lib/cli/tests/test_run_flow_definition.py

@@ -0,0 +1,156 @@
+from __future__ import annotations
+
+import json
+import sys
+import types
+
+import pytest
+import yaml
+
+from crewai_cli.run_flow_definition import run_flow_definition
+
+
+class _FakeFlow:
+    def __init__(self, definition):
+        self.definition = definition
+
+    def kickoff(self, inputs=None):
+        return {
+            "flow": self.definition["name"],
+            "inputs": inputs or {},
+        }
+
+
+class _FakeFlowFactory:
+    @classmethod
+    def from_definition(cls, definition):
+        return _FakeFlow(definition)
+
+
+class _FakeFlowDefinition:
+    @classmethod
+    def from_yaml(cls, source):
+        return yaml.safe_load(source)
+
+    @classmethod
+    def from_json(cls, source):
+        return json.loads(source)
+
+
+@pytest.fixture
+def fake_flow_runtime(monkeypatch):
+    crewai_module = types.ModuleType("crewai")
+    flow_package = types.ModuleType("crewai.flow")
+    flow_module = types.ModuleType("crewai.flow.flow")
+    flow_definition_module = types.ModuleType("crewai.flow.flow_definition")
+
+    flow_module.Flow = _FakeFlowFactory
+    flow_definition_module.FlowDefinition = _FakeFlowDefinition
+
+    monkeypatch.setitem(sys.modules, "crewai", crewai_module)
+    monkeypatch.setitem(sys.modules, "crewai.flow", flow_package)
+    monkeypatch.setitem(sys.modules, "crewai.flow.flow", flow_module)
+    monkeypatch.setitem(
+        sys.modules, "crewai.flow.flow_definition", flow_definition_module
+    )
+
+
+def _captured_json(capsys):
+    return json.loads(capsys.readouterr().out)
+
+
+def test_run_flow_definition_reads_definition_file(
+    tmp_path, capsys, fake_flow_runtime
+):
+    definition_path = tmp_path / "flow.yaml"
+    definition_path.write_text("schema: crewai.flow/v1\nname: TestFlow\n")
+
+    run_flow_definition(str(definition_path), '{"topic":"AI"}')
+
+    assert _captured_json(capsys) == {
+        "flow": "TestFlow",
+        "inputs": {"topic": "AI"},
+    }
+
+
+@pytest.mark.parametrize(
+    ("definition_source", "expected_flow_name"),
+    [
+        pytest.param(
+            "schema: crewai.flow/v1\nname: InlineFlow\n",
+            "InlineFlow",
+            id="inline-yaml",
+        ),
+        pytest.param(
+            '{"schema":"crewai.flow/v1","name":"InlineJsonFlow"}',
+            "InlineJsonFlow",
+            id="inline-json",
+        ),
+        pytest.param(
+            '{"schema":"crewai.flow/v1","name":"' + ("JsonFlow" * 500) + '"}',
+            "JsonFlow" * 500,
+            id="large-inline-json",
+        ),
+    ],
+)
+def test_run_flow_definition_accepts_inline_definitions(
+    definition_source, expected_flow_name, capsys, fake_flow_runtime
+):
+    run_flow_definition(definition_source)
+
+    assert _captured_json(capsys) == {"flow": expected_flow_name, "inputs": {}}
+
+
+@pytest.mark.parametrize(
+    ("filename", "definition_source", "expected_flow_name"),
+    [
+        pytest.param(
+            "flow.yaml",
+            "schema: crewai.flow/v1\nname: YamlFileFlow\n",
+            "YamlFileFlow",
+            id="yaml-file",
+        ),
+        pytest.param(
+            "flow.json",
+            '{"schema":"crewai.flow/v1","name":"JsonFlow"}',
+            "JsonFlow",
+            id="json-file",
+        ),
+    ],
+)
+def test_run_flow_definition_accepts_definition_files(
+    filename, definition_source, expected_flow_name, tmp_path, capsys, fake_flow_runtime
+):
+    definition_path = tmp_path / filename
+    definition_path.write_text(definition_source)
+
+    run_flow_definition(str(definition_path))
+
+    assert _captured_json(capsys) == {"flow": expected_flow_name, "inputs": {}}
+
+
+def test_run_flow_definition_rejects_non_object_inputs(fake_flow_runtime, capsys):
+    with pytest.raises(SystemExit):
+        run_flow_definition("name: TestFlow", '["not", "an", "object"]')
+
+    assert "Invalid --inputs JSON: expected an object." in capsys.readouterr().err
+
+
+def test_run_flow_definition_reports_unreadable_file(
+    monkeypatch, tmp_path, capsys, fake_flow_runtime
+):
+    definition_path = tmp_path / "flow.yaml"
+    definition_path.write_text("schema: crewai.flow/v1\nname: TestFlow\n")
+
+    def raise_permission_error(self, *args, **kwargs):
+        raise PermissionError("no access")
+
+    monkeypatch.setattr("pathlib.Path.read_text", raise_permission_error)
+
+    with pytest.raises(SystemExit):
+        run_flow_definition(str(definition_path))
+
+    err = capsys.readouterr().err
+    assert "Unable to read --definition path" in err
+    assert str(definition_path) in err
+    assert "no access" in err

lib/cli/tests/tools/test_main.py

@@ -157,14 +157,16 @@ def test_install_api_error(mock_get, capsys, tool_command):
     mock_get.assert_called_once_with("error-tool")
 
 
-@patch("crewai_cli.tools.main.git.Repository.fetch")
-@patch("crewai_cli.tools.main.git.Repository.is_synced", return_value=False)
-def test_publish_when_not_in_sync(mock_is_synced, mock_fetch, capsys, tool_command):
+@patch("crewai_cli.tools.main.git.Repository")
+def test_publish_when_not_in_sync(mock_repository, capsys, tool_command):
+    mock_repository.return_value.is_synced.return_value = False
+
     with raises(SystemExit):
         tool_command.publish(is_public=True)
 
     output = capsys.readouterr().out
     assert "Local changes need to be resolved before publishing" in output
+    mock_repository.return_value.is_synced.assert_called_once_with()
 
 
 @patch("crewai_cli.tools.main.get_project_name", return_value="sample-tool")

lib/crewai-core/src/crewai_core/__init__.py

@@ -1 +1 @@
-__version__ = "1.14.7rc2"
+__version__ = "1.14.7"

lib/crewai-core/src/crewai_core/plus_api.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import os
+from pathlib import Path
 from typing import Any, Final, Literal, TypedDict, cast
 from urllib.parse import urljoin
 
@@ -190,6 +191,36 @@ class PlusAPI:
         with httpx.Client(trust_env=False, verify=verify) as client:
             return client.request(method, url, **request_kwargs)
 
+    def _make_multipart_request(
+        self,
+        method: HttpMethod,
+        endpoint: str,
+        *,
+        zip_file_path: str | Path,
+        data: dict[str, str] | None = None,
+        timeout: float | None = None,
+        verify: bool = True,
+    ) -> httpx.Response:
+        """Send an authenticated multipart request containing a project ZIP."""
+        url = urljoin(self.base_url, endpoint)
+        headers = dict(cast(dict[str, str], self.headers))
+        headers.pop("Content-Type", None)
+        path = Path(zip_file_path)
+        request_kwargs: dict[str, Any] = {"headers": headers}
+        if data is not None:
+            request_kwargs["data"] = data
+        if timeout is not None:
+            request_kwargs["timeout"] = timeout
+
+        with (
+            path.open("rb") as file_handle,
+            httpx.Client(trust_env=False, verify=verify) as client,
+        ):
+            files = {
+                "zip_file": (path.name, file_handle, "application/zip"),
+            }
+            return client.request(method, url, files=files, **request_kwargs)
+
     def login_to_tool_repository(
         self, user_identifier: str | None = None
     ) -> httpx.Response:
@@ -312,6 +343,46 @@ class PlusAPI:
     def create_crew(self, payload: CreateCrewPayload) -> httpx.Response:
         return self._make_request("POST", self.CREWS_RESOURCE, json=payload)
 
+    def create_crew_from_zip(
+        self,
+        zip_file_path: str | Path,
+        *,
+        name: str | None = None,
+        env: dict[str, str] | None = None,
+    ) -> httpx.Response:
+        """Create a crew deployment from a local project ZIP archive."""
+        data: dict[str, str] = {}
+        if name:
+            data["name"] = name
+        if env:
+            data.update({f"env[{key}]": value for key, value in env.items()})
+        return self._make_multipart_request(
+            "POST",
+            f"{self.CREWS_RESOURCE}/zip",
+            zip_file_path=zip_file_path,
+            data=data or None,
+            timeout=300,
+        )
+
+    def update_crew_from_zip(
+        self,
+        uuid: str,
+        zip_file_path: str | Path,
+        *,
+        env: dict[str, str] | None = None,
+    ) -> httpx.Response:
+        """Update an existing crew deployment from a local project ZIP archive."""
+        data: dict[str, str] = {}
+        if env:
+            data.update({f"env[{key}]": value for key, value in env.items()})
+        return self._make_multipart_request(
+            "POST",
+            f"{self.CREWS_RESOURCE}/{uuid}/zip_update",
+            zip_file_path=zip_file_path,
+            data=data or None,
+            timeout=300,
+        )
+
     def get_organizations(self) -> httpx.Response:
         return self._make_request("GET", self.ORGANIZATIONS_RESOURCE)
 

lib/crewai-core/tests/test_smoke.py

@@ -13,8 +13,8 @@ from crewai_core import (
     user_data,
     version,
 )
-import pytest
 from opentelemetry.sdk.trace import TracerProvider
+import pytest
 
 
 def test_version_returns_string() -> None:

lib/crewai-files/src/crewai_files/__init__.py

@@ -152,4 +152,4 @@ __all__ = [
     "wrap_file_source",
 ]
 
-__version__ = "1.14.7rc2"
+__version__ = "1.14.7"

lib/crewai-files/src/crewai_files/core/sources.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 from collections.abc import AsyncIterator, Iterator
 import inspect
+import json
 import mimetypes
 from pathlib import Path
 from typing import Annotated, Any, BinaryIO, Protocol, cast, runtime_checkable
@@ -23,6 +24,9 @@ from typing_extensions import TypeIs
 from crewai_files.core.constants import DEFAULT_MAX_FILE_SIZE_BYTES, MAGIC_BUFFER_SIZE
 
 
+OCTET_STREAM = "application/octet-stream"
+
+
 @runtime_checkable
 class AsyncReadable(Protocol):
     """Protocol for async readable streams."""
@@ -56,13 +60,51 @@ class _AsyncReadableValidator:
 ValidatedAsyncReadable = Annotated[AsyncReadable, _AsyncReadableValidator()]
 
 
-def _fallback_content_type(filename: str | None) -> str:
-    """Get content type from filename extension or return default."""
+def _detect_content_type_from_bytes(data: bytes) -> str | None:
+    if data.startswith(b"\x89PNG\r\n\x1a\n"):
+        return "image/png"
+    if data.startswith(b"\xff\xd8\xff"):
+        return "image/jpeg"
+    if data.startswith(b"%PDF-"):
+        return "application/pdf"
+
+    try:
+        decoded = data.decode("utf-8")
+    except UnicodeDecodeError:
+        return None
+
+    stripped = decoded.lstrip()
+    if stripped.startswith(("{", "[")):
+        try:
+            json.loads(decoded)
+            return "application/json"
+        except json.JSONDecodeError:
+            pass
+
+    if "\x00" not in decoded:
+        return "text/plain"
+
+    return None
+
+
+def _fallback_content_type(filename: str | None, data: bytes | None = None) -> str:
+    """Get content type from filename extension, then content sniffing.
+
+    The extension lookup runs first so specific types like ``text/csv`` or
+    ``application/xml`` are not degraded to generic sniffed types such as
+    ``text/plain``; byte sniffing only covers extensionless/unknown names.
+    """
     if filename:
         mime_type, _ = mimetypes.guess_type(filename)
         if mime_type:
             return mime_type
-    return "application/octet-stream"
+
+    if data:
+        content_type = _detect_content_type_from_bytes(data)
+        if content_type:
+            return content_type
+
+    return OCTET_STREAM
 
 
 def generate_filename(content_type: str) -> str:
@@ -97,9 +139,19 @@ def detect_content_type(data: bytes, filename: str | None = None) -> str:
         import magic
 
         result: str = magic.from_buffer(data[:MAGIC_BUFFER_SIZE], mime=True)
-        return result
+        if result != OCTET_STREAM:
+            return result
+        return _fallback_content_type(filename, data)
     except ImportError:
-        return _fallback_content_type(filename)
+        return _fallback_content_type(filename, data)
+
+
+def _read_magic_header(path: Path) -> bytes | None:
+    try:
+        with path.open("rb") as file:
+            return file.read(MAGIC_BUFFER_SIZE)
+    except OSError:
+        return None
 
 
 def detect_content_type_from_path(path: Path, filename: str | None = None) -> str:
@@ -115,13 +167,16 @@ def detect_content_type_from_path(path: Path, filename: str | None = None) -> st
     Returns:
         The detected MIME type.
     """
+    fallback_filename = filename or path.name
     try:
         import magic
 
         result: str = magic.from_file(str(path), mime=True)
-        return result
+        if result != OCTET_STREAM:
+            return result
+        return _fallback_content_type(fallback_filename, _read_magic_header(path))
     except ImportError:
-        return _fallback_content_type(filename or path.name)
+        return _fallback_content_type(fallback_filename, _read_magic_header(path))
 
 
 class _BinaryIOValidator:

lib/crewai-files/src/crewai_files/resolution/resolver.py

@@ -129,6 +129,20 @@ class FileResolver:
         """
         return constraints is not None and constraints.supports_url_references
 
+    @classmethod
+    def _should_resolve_as_url_reference(
+        cls,
+        file: FileInput,
+        provider: ProviderType,
+        constraints: ProviderConstraints | None,
+    ) -> bool:
+        """Check if the provider can accept the current URL source directly."""
+        if not cls._is_url_source(file) or not cls._supports_url(constraints):
+            return False
+
+        provider_lower = provider.lower()
+        return "bedrock" not in provider_lower and "aws" not in provider_lower
+
     @staticmethod
     def _resolve_as_url(file: FileInput) -> UrlReference:
         """Resolve a URL source as UrlReference.
@@ -159,7 +173,7 @@ class FileResolver:
         """
         constraints = get_constraints_for_provider(provider)
 
-        if self._is_url_source(file) and self._supports_url(constraints):
+        if self._should_resolve_as_url_reference(file, provider, constraints):
             return self._resolve_as_url(file)
 
         context = self._build_file_context(file)
@@ -424,7 +438,7 @@ class FileResolver:
         """
         constraints = get_constraints_for_provider(provider)
 
-        if self._is_url_source(file) and self._supports_url(constraints):
+        if self._should_resolve_as_url_reference(file, provider, constraints):
             return self._resolve_as_url(file)
 
         context = self._build_file_context(file)

lib/crewai-tools/pyproject.toml

@@ -10,7 +10,7 @@ requires-python = ">=3.10, <3.14"
 dependencies = [
     "pytube~=15.0.0",
     "requests>=2.33.0,<3",
-    "crewai==1.14.7rc2",
+    "crewai==1.14.7",
     "tiktoken>=0.8.0,<0.13",
     "beautifulsoup4~=4.13.4",
     "python-docx~=1.2.0",
@@ -63,7 +63,7 @@ spider-client = [
     "spider-client>=0.1.25",
 ]
 scrapegraph-py = [
-    "scrapegraph-py>=1.9.0",
+    "scrapegraph-py>=1.9.0,<2",
 ]
 linkup-sdk = [
     "linkup-sdk>=0.2.2",

lib/crewai-tools/src/crewai_tools/__init__.py

@@ -330,4 +330,4 @@ __all__ = [
     "ZapierActionTools",
 ]
 
-__version__ = "1.14.7rc2"
+__version__ = "1.14.7"

lib/crewai-tools/src/crewai_tools/security/safe_path.py

@@ -22,6 +22,31 @@ logger = logging.getLogger(__name__)
 _UNSAFE_PATHS_ENV = "CREWAI_TOOLS_ALLOW_UNSAFE_PATHS"
 
 
+def format_path_for_display(path: str, base_dir: str | None = None) -> str:
+    """Return a path label that does not expose absolute directory prefixes."""
+    if base_dir is None:
+        base_dir = os.getcwd()
+
+    try:
+        resolved_base = os.path.realpath(base_dir)
+        resolved_path = os.path.realpath(
+            os.path.join(resolved_base, path) if not os.path.isabs(path) else path
+        )
+        if os.path.commonpath([resolved_base, resolved_path]) == resolved_base:
+            return os.path.relpath(resolved_path, resolved_base)
+    except (OSError, ValueError) as exc:
+        logger.debug("Falling back to basename for display path formatting: %s", exc)
+
+    return os.path.basename(os.path.realpath(path)) or "[redacted path]"
+
+
+def format_error_for_display(error: Exception) -> str:
+    """Return exception details without OS-added absolute path context."""
+    if isinstance(error, OSError):
+        return error.strerror or error.__class__.__name__
+    return str(error)
+
+
 def _is_escape_hatch_enabled() -> bool:
     """Check if the unsafe paths escape hatch is enabled."""
     return os.environ.get(_UNSAFE_PATHS_ENV, "").lower() in ("true", "1", "yes")
@@ -66,8 +91,8 @@ def validate_file_path(path: str, base_dir: str | None = None) -> str:
     prefix = resolved_base if resolved_base.endswith(os.sep) else resolved_base + os.sep
     if not resolved_path.startswith(prefix) and resolved_path != resolved_base:
         raise ValueError(
-            f"Path '{path}' resolves to '{resolved_path}' which is outside "
-            f"the allowed directory '{resolved_base}'. "
+            f"Path '{format_path_for_display(resolved_path, resolved_base)}' is "
+            f"outside the allowed directory. "
             f"Set {_UNSAFE_PATHS_ENV}=true to bypass this check."
         )
 

lib/crewai-tools/src/crewai_tools/tools/file_read_tool/file_read_tool.py

@@ -3,7 +3,11 @@ from typing import Any
 from crewai.tools import BaseTool
 from pydantic import BaseModel, Field
 
-from crewai_tools.security.safe_path import validate_file_path
+from crewai_tools.security.safe_path import (
+    format_error_for_display,
+    format_path_for_display,
+    validate_file_path,
+)
 
 
 class FileReadToolSchema(BaseModel):
@@ -58,8 +62,9 @@ class FileReadTool(BaseTool):
             **kwargs: Additional keyword arguments passed to BaseTool.
         """
         if file_path is not None:
+            display_path = format_path_for_display(file_path)
             kwargs["description"] = (
-                f"A tool that reads file content. The default file is {file_path}, but you can provide a different 'file_path' parameter to read another file. You can also specify 'start_line' and 'line_count' to read specific parts of the file."
+                f"A tool that reads file content. The default file is {display_path}, but you can provide a different 'file_path' parameter to read another file. You can also specify 'start_line' and 'line_count' to read specific parts of the file."
             )
 
         super().__init__(**kwargs)
@@ -78,7 +83,12 @@ class FileReadTool(BaseTool):
         if file_path is None:
             return "Error: No file path provided. Please provide a file path either in the constructor or as an argument."
 
-        file_path = validate_file_path(file_path)
+        try:
+            file_path = validate_file_path(file_path)
+        except ValueError as e:
+            return f"Error: Invalid file path: {e!s}"
+
+        display_path = format_path_for_display(file_path)
         try:
             with open(file_path, "r") as file:
                 if start_line == 1 and line_count is None:
@@ -98,8 +108,11 @@ class FileReadTool(BaseTool):
 
                 return "".join(selected_lines)
         except FileNotFoundError:
-            return f"Error: File not found at path: {file_path}"
+            return f"Error: File not found at path: {display_path}"
         except PermissionError:
-            return f"Error: Permission denied when trying to read file: {file_path}"
+            return f"Error: Permission denied when trying to read file: {display_path}"
         except Exception as e:
-            return f"Error: Failed to read file {file_path}. {e!s}"
+            return (
+                f"Error: Failed to read file {display_path}. "
+                f"{format_error_for_display(e)}"
+            )

lib/crewai-tools/src/crewai_tools/tools/file_writer_tool/file_writer_tool.py

@@ -5,6 +5,11 @@ from typing import Any
 from crewai.tools import BaseTool
 from pydantic import BaseModel
 
+from crewai_tools.security.safe_path import (
+    format_error_for_display,
+    format_path_for_display,
+)
+
 
 def strtobool(val: str | bool) -> bool:
     if isinstance(val, bool):
@@ -44,6 +49,9 @@ class FileWriterTool(BaseTool):
             # itself, since that is not a valid file target.
             real_directory = Path(directory).resolve()
             real_filepath = Path(filepath).resolve()
+            display_filepath = format_path_for_display(
+                str(real_filepath), str(real_directory)
+            )
             if (
                 not real_filepath.is_relative_to(real_directory)
                 or real_filepath == real_directory
@@ -56,15 +64,18 @@ class FileWriterTool(BaseTool):
             kwargs["overwrite"] = strtobool(kwargs["overwrite"])
 
             if os.path.exists(real_filepath) and not kwargs["overwrite"]:
-                return f"File {real_filepath} already exists and overwrite option was not passed."
+                return f"File {display_filepath} already exists and overwrite option was not passed."
 
             mode = "w" if kwargs["overwrite"] else "x"
             with open(real_filepath, mode) as file:
                 file.write(kwargs["content"])
-            return f"Content successfully written to {real_filepath}"
+            return f"Content successfully written to {display_filepath}"
         except FileExistsError:
-            return f"File {real_filepath} already exists and overwrite option was not passed."
+            return f"File {display_filepath} already exists and overwrite option was not passed."
         except KeyError as e:
             return f"An error occurred while accessing key: {e!s}"
         except Exception as e:
-            return f"An error occurred while writing to the file: {e!s}"
+            return (
+                "An error occurred while writing to the file: "
+                f"{format_error_for_display(e)}"
+            )

lib/crewai-tools/tests/file_read_tool_test.py

@@ -1,4 +1,3 @@
-import os
 from unittest.mock import mock_open, patch
 
 from crewai_tools import FileReadTool
@@ -6,21 +5,16 @@ from crewai_tools import FileReadTool
 
 def test_file_read_tool_constructor():
     """Test FileReadTool initialization with file_path."""
-    test_file = "/tmp/test_file.txt"
-    test_content = "Hello, World!"
-    with open(test_file, "w") as f:
-        f.write(test_content)
+    test_file = "test_file.txt"
 
     tool = FileReadTool(file_path=test_file)
     assert tool.file_path == test_file
     assert "test_file.txt" in tool.description
 
-    os.remove(test_file)
-
 
 def test_file_read_tool_run():
     """Test FileReadTool _run method with file_path at runtime."""
-    test_file = "/tmp/test_file.txt"
+    test_file = "test_file.txt"
     test_content = "Hello, World!"
 
     # Use mock_open to mock file operations
@@ -36,18 +30,18 @@ def test_file_read_tool_error_handling():
     result = tool._run()
     assert "Error: No file path provided" in result
 
-    result = tool._run(file_path="/nonexistent/file.txt")
+    result = tool._run(file_path="nonexistent/file.txt")
     assert "Error: File not found at path:" in result
 
     with patch("builtins.open", side_effect=PermissionError()):
-        result = tool._run(file_path="/tmp/no_permission.txt")
+        result = tool._run(file_path="no_permission.txt")
         assert "Error: Permission denied" in result
 
 
 def test_file_read_tool_constructor_and_run():
     """Test FileReadTool using both constructor and runtime file paths."""
-    test_file1 = "/tmp/test1.txt"
-    test_file2 = "/tmp/test2.txt"
+    test_file1 = "test1.txt"
+    test_file2 = "test2.txt"
     content1 = "File 1 content"
     content2 = "File 2 content"
 
@@ -64,7 +58,7 @@ def test_file_read_tool_constructor_and_run():
 
 def test_file_read_tool_chunk_reading():
     """Test FileReadTool reading specific chunks of a file."""
-    test_file = "/tmp/multiline_test.txt"
+    test_file = "multiline_test.txt"
     lines = [
         "Line 1\n",
         "Line 2\n",
@@ -104,7 +98,7 @@ def test_file_read_tool_chunk_reading():
 
 def test_file_read_tool_chunk_error_handling():
     """Test error handling for chunk reading."""
-    test_file = "/tmp/short_test.txt"
+    test_file = "short_test.txt"
     lines = ["Line 1\n", "Line 2\n", "Line 3\n"]
     file_content = "".join(lines)
 
@@ -122,7 +116,7 @@ def test_file_read_tool_chunk_error_handling():
 
 def test_file_read_tool_zero_or_negative_start_line():
     """Test that start_line values of 0 or negative read from the start of the file."""
-    test_file = "/tmp/negative_test.txt"
+    test_file = "negative_test.txt"
     lines = ["Line 1\n", "Line 2\n", "Line 3\n", "Line 4\n", "Line 5\n"]
     file_content = "".join(lines)
 
@@ -150,3 +144,45 @@ def test_file_read_tool_zero_or_negative_start_line():
         result = tool._run(file_path=test_file, start_line=-10, line_count=2)
         expected = "".join(lines[0:2])  # Should read first 2 lines
         assert result == expected
+
+
+def test_file_read_tool_error_messages_do_not_disclose_absolute_paths(
+    tmp_path, monkeypatch
+):
+    """FileReadTool should redact absolute prefixes from user-visible errors."""
+    monkeypatch.chdir(tmp_path)
+    tool = FileReadTool()
+    target = tmp_path / "secret.txt"
+
+    result = tool._run(file_path=str(target))
+    assert "secret.txt" in result
+    assert str(tmp_path) not in result
+
+    target.touch()
+    with patch("builtins.open", side_effect=PermissionError()):
+        result = tool._run(file_path=str(target))
+    assert "secret.txt" in result
+    assert str(tmp_path) not in result
+
+    with patch(
+        "builtins.open",
+        side_effect=OSError(5, "Input/output error", str(target)),
+    ):
+        result = tool._run(file_path=str(target))
+    assert "secret.txt" in result
+    assert str(tmp_path) not in result
+
+
+def test_file_read_tool_invalid_path_error_does_not_disclose_workspace(
+    tmp_path, monkeypatch
+):
+    """Validation errors should not echo the resolved workspace path."""
+    monkeypatch.chdir(tmp_path)
+    outside = tmp_path.parent / "outside.txt"
+
+    result = FileReadTool()._run(file_path=str(outside))
+
+    assert "Invalid file path" in result
+    assert "outside.txt" in result
+    assert str(tmp_path) not in result
+    assert str(tmp_path.parent) not in result

lib/crewai-tools/tests/tools/test_file_writer_tool.py

@@ -47,6 +47,8 @@ def test_basic_file_write(tool, temp_env):
     assert os.path.exists(path)
     assert read_file(path) == temp_env["test_content"]
     assert "successfully written" in result
+    assert temp_env["test_file"] in result
+    assert temp_env["temp_dir"] not in result
 
 
 def test_directory_creation(tool, temp_env):
@@ -62,6 +64,8 @@ def test_directory_creation(tool, temp_env):
     assert os.path.exists(new_dir)
     assert os.path.exists(path)
     assert "successfully written" in result
+    assert temp_env["test_file"] in result
+    assert new_dir not in result
 
 
 @pytest.mark.parametrize(
@@ -134,6 +138,8 @@ def test_file_exists_error_handling(tool, temp_env, overwrite):
     )
 
     assert "already exists and overwrite option was not passed" in result
+    assert temp_env["test_file"] in result
+    assert temp_env["temp_dir"] not in result
     assert read_file(path) == "Pre-existing content"
 
 

lib/crewai-tools/tests/utilities/test_safe_path.py

@@ -7,6 +7,7 @@ import os
 import pytest
 
 from crewai_tools.security.safe_path import (
+    format_path_for_display,
     validate_directory_path,
     validate_file_path,
     validate_url,
@@ -66,6 +67,37 @@ class TestValidateFilePath:
         result = validate_file_path("/etc/passwd", str(tmp_path))
         assert result == os.path.realpath("/etc/passwd")
 
+    def test_rejection_message_redacts_absolute_prefixes(self, tmp_path):
+        outside = tmp_path.parent / "outside.txt"
+
+        with pytest.raises(ValueError) as exc_info:
+            validate_file_path(str(outside), str(tmp_path))
+
+        message = str(exc_info.value)
+        assert "outside.txt" in message
+        assert str(tmp_path) not in message
+        assert str(tmp_path.parent) not in message
+
+
+class TestFormatPathForDisplay:
+    """Tests for user-visible path labels."""
+
+    def test_returns_relative_path_inside_base(self, tmp_path):
+        nested_file = tmp_path / "nested" / "file.txt"
+        nested_file.parent.mkdir()
+        nested_file.touch()
+
+        result = format_path_for_display(str(nested_file), str(tmp_path))
+
+        assert result == os.path.join("nested", "file.txt")
+
+    def test_redacts_absolute_prefix_outside_base(self, tmp_path):
+        outside_file = tmp_path.parent / "outside.txt"
+
+        result = format_path_for_display(str(outside_file), str(tmp_path))
+
+        assert result == "outside.txt"
+
 
 class TestValidateDirectoryPath:
     """Tests for validate_directory_path."""

lib/crewai/examples/flows/lead_flow/tools.py

@@ -0,0 +1,23 @@
+import logging
+from typing import Literal
+
+from crewai.tools import BaseTool
+from pydantic import BaseModel, Field
+
+
+logger = logging.getLogger("lead_flow")
+
+
+class LogLeadInput(BaseModel):
+    message: str = Field(description="The message to log.")
+    level: Literal["debug", "info", "warning", "error"] = "info"
+
+
+class LogLeadTool(BaseTool):
+    name: str = "log_lead"
+    description: str = "Log a message about a lead that was not pursued."
+    args_schema: type[BaseModel] = LogLeadInput
+
+    def _run(self, message: str, level: str = "info") -> str:
+        logger.log(logging.getLevelName(level.upper()), message)
+        return message

lib/crewai/examples/flows/lead_scoring_flow.yaml

@@ -0,0 +1,98 @@
+# uv run --project lib/crewai crewai run --definition lib/crewai/examples/flows/lead_scoring_flow.yaml --inputs '{"lead":{"name":"Dana Lee","company":"Acme","employees":1200}}'
+# uv run --project lib/crewai crewai run --definition lib/crewai/examples/flows/lead_scoring_flow.yaml --inputs '{"lead":{"name":"Sam Poe","company":"Tiny LLC","employees":3}}'
+
+schema: crewai.flow/v1
+name: LeadScoringFlow
+description: Score an inbound lead, then route high-scoring leads to outreach and the rest to a log tool.
+
+state:
+  type: dict
+  default:
+    lead: {}
+
+methods:
+  score_lead:
+    start: true
+    do:
+      call: crew
+      with:
+        name: lead_scoring_crew
+        verbose: true
+        agents:
+          scorer:
+            role: Lead Qualification Analyst
+            goal: Assign a 0-100 fit score to inbound lead {name} from {company}
+            backstory: >
+              A revenue-ops veteran who scores leads against a clear ideal
+              customer profile: company size is the dominant signal.
+        tasks:
+          - name: score_lead_task
+            agent: scorer
+            description: >
+              Evaluate the inbound lead {name} from {company} ({employees}
+              employees) against this rubric, where company size dominates:
+              1000+ employees scores 85-100 (hot), 200-999 scores 70-84 (warm),
+              and under 200 scores 0-69 (cold). Return an integer score with a
+              one-line rationale.
+            expected_output: >
+              A LeadScore with an integer `score` (0-100), a short `reasoning`,
+              and a `tier` of "hot", "warm", or "cold".
+            output_pydantic:
+              type: object
+              properties:
+                score:
+                  type: integer
+                reasoning:
+                  type: string
+                tier:
+                  type: string
+                  enum: [hot, warm, cold]
+              required: [score, reasoning, tier]
+        inputs:
+          name: "${state.lead.name}"
+          company: "${state.lead.company}"
+          employees: "${state.lead.employees}"
+
+  route_by_score:
+    listen: score_lead
+    router: true
+    emit: [qualified, unqualified]
+    do:
+      call: expression
+      expr: "outputs.score_lead.pydantic.score >= 80 ? 'qualified' : 'unqualified'"
+
+  run_outreach:
+    listen: qualified
+    do:
+      call: crew
+      with:
+        name: outreach_crew
+        verbose: true
+        agents:
+          sdr:
+            role: Outbound SDR
+            goal: Draft a tailored first-touch email to {name} at {company}
+            backstory: >
+              A top-performing SDR who writes concise, personalized outreach
+              that earns replies from busy buyers.
+        tasks:
+          - name: draft_outreach_task
+            agent: sdr
+            description: >
+              Write a short, personalized first-touch email to {name} at
+              {company}. Ground the hook in this qualification rationale:
+              "{reasoning}".
+            expected_output: A ready-to-send outreach email with a subject line and body.
+        inputs:
+          name: "${state.lead.name}"
+          company: "${state.lead.company}"
+          reasoning: "${outputs.score_lead.pydantic.reasoning}"
+
+  log_unqualified:
+    listen: unqualified
+    do:
+      call: tool
+      ref: lead_flow.tools:LogLeadTool
+      with:
+        message: "${'Skipped low-fit lead ' + state.lead.name + ' (score ' + string(outputs.score_lead.pydantic.score) + ')'}"
+        level: info

lib/crewai/pyproject.toml

@@ -8,8 +8,8 @@ authors = [
 ]
 requires-python = ">=3.10, <3.14"
 dependencies = [
-    "crewai-core==1.14.7rc2",
-    "crewai-cli==1.14.7rc2",
+    "crewai-core==1.14.7",
+    "crewai-cli==1.14.7",
     # Core Dependencies
     "pydantic>=2.11.9,<2.13",
     "openai>=2.30.0,<3",
@@ -33,6 +33,7 @@ dependencies = [
     "appdirs~=1.4.4",
     "jsonref~=1.1.0",
     "json-repair~=0.25.2",
+    "cel-python>=0.5.0,<0.6",
     "tomli-w~=1.1.0",
     "tomli~=2.0.2",
     "json5~=0.10.0",
@@ -54,7 +55,7 @@ Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
 tools = [
-    "crewai-tools==1.14.7rc2",
+    "crewai-tools==1.14.7",
 ]
 embeddings = [
     "tiktoken>=0.8.0,<0.13"

lib/crewai/src/crewai/__init__.py

@@ -48,7 +48,7 @@ def _suppress_pydantic_deprecation_warnings() -> None:
 
 _suppress_pydantic_deprecation_warnings()
 
-__version__ = "1.14.7rc2"
+__version__ = "1.14.7"
 
 _LAZY_IMPORTS: dict[str, tuple[str, str]] = {
     "Memory": ("crewai.memory.unified_memory", "Memory"),

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

@@ -758,6 +758,31 @@ class Agent(BaseAgent):
         self._check_execution_error(e, task)
         return await self.aexecute_task(task, context, tools)
 
+    def message(self, content: str, **kwargs: Any) -> str:
+        """Send a single message and get a response.
+
+        Creates a temporary Task + Crew, executes, and returns the raw output.
+        """
+        from crewai.crew import Crew
+        from crewai.task import Task
+        from crewai.types.streaming import CrewStreamingOutput
+
+        task = Task(
+            description=content,
+            expected_output="Respond to the user's message appropriately.",
+            agent=self,
+        )
+        crew = Crew(
+            agents=[self],
+            tasks=[task],
+            verbose=self.verbose,
+            memory=self.memory or False,
+        )
+        result = crew.kickoff()
+        if isinstance(result, CrewStreamingOutput):
+            return result.result.raw
+        return result.raw
+
     def execute_task(
         self,
         task: Task,

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

@@ -1,9 +1,10 @@
 from __future__ import annotations
 
-from typing import Literal
+from typing import Annotated, Literal
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, BeforeValidator, Field
 
+from crewai.agents.agent_builder.base_agent import _validate_llm_ref
 from crewai.llms.base_llm import BaseLLM
 
 
@@ -69,7 +70,7 @@ class PlanningConfig(BaseModel):
                 max_attempts=3,
                 max_steps=10,
                 plan_prompt="Create a focused plan for: {description}",
-                llm="gpt-4o-mini",
+                llm="gpt-5.4-mini",
             ),
         )
         ```
@@ -139,7 +140,10 @@ class PlanningConfig(BaseModel):
             "whether to continue or replan. None means no per-step timeout."
         ),
     )
-    llm: str | BaseLLM | None = Field(
+    llm: Annotated[
+        str | BaseLLM | None,
+        BeforeValidator(_validate_llm_ref),
+    ] = Field(
         default=None,
         description="LLM to use for planning. Uses agent's LLM if None.",
     )

lib/crewai/src/crewai/agents/agent_adapters/openai_agents/openai_adapter.py

@@ -81,7 +81,7 @@ class OpenAIAgentAdapter(BaseAgentAdapter):
         Raises:
             ImportError: If OpenAI agent dependencies are not installed.
         """
-        self.llm = kwargs.pop("model", "gpt-4o-mini")
+        self.llm = kwargs.pop("model", "gpt-5.4-mini")
         super().__init__(**kwargs)
         self._tool_adapter = OpenAIAgentToolAdapter(tools=kwargs.get("tools"))
         self._converter_adapter = OpenAIConverterAdapter(agent_adapter=self)

lib/crewai/src/crewai/agents/agent_builder/base_agent.py

@@ -82,16 +82,42 @@ _LLM_TYPE_REGISTRY: dict[str, str] = {
 def _validate_llm_ref(value: Any) -> Any:
     if isinstance(value, dict):
         import importlib
+        import inspect
 
         llm_type = value.get("llm_type")
-        if not llm_type or llm_type not in _LLM_TYPE_REGISTRY:
+        if not llm_type:
+            model = (
+                value.get("model")
+                or value.get("model_name")
+                or value.get("deployment_name")
+            )
+            if not model:
+                raise ValueError(
+                    "LLM config objects must include 'model', 'model_name', "
+                    "or 'deployment_name', or a serialized 'llm_type'. "
+                    f"Got keys: {list(value)}"
+                )
+            from crewai.llm import LLM
+
+            llm_kwargs = {**value, "model": model}
+            llm_kwargs.pop("model_name", None)
+            llm_kwargs.pop("deployment_name", None)
+            return LLM(**llm_kwargs)
+
+        if llm_type not in _LLM_TYPE_REGISTRY:
             raise ValueError(
-                f"Unknown or missing llm_type: {llm_type!r}. "
+                f"Unknown llm_type: {llm_type!r}. "
                 f"Expected one of {list(_LLM_TYPE_REGISTRY)}"
             )
         dotted = _LLM_TYPE_REGISTRY[llm_type]
         mod_path, cls_name = dotted.rsplit(".", 1)
         cls = getattr(importlib.import_module(mod_path), cls_name)
+        if inspect.isabstract(cls):
+            from crewai.llm import LLM
+
+            return LLM(
+                **{k: v for k, v in value.items() if v is not None and k != "llm_type"}
+            )
         return cls(**value)
     return value
 
@@ -611,7 +637,10 @@ class BaseAgent(BaseModel, ABC, metaclass=AgentMeta):
         if self.memory is True:
             from crewai.memory.unified_memory import Memory
 
-            self.memory = Memory()
+            memory_kwargs: dict[str, Any] = {}
+            if self.llm is not None:
+                memory_kwargs["llm"] = self.llm
+            self.memory = Memory(**memory_kwargs)
         elif self.memory is False:
             self.memory = None
         return self

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

@@ -53,6 +53,7 @@ from crewai.types.callback import SerializableCallable
 from crewai.utilities.agent_utils import (
     _llm_stop_words_applied,
     aget_llm_response,
+    build_text_tool_calling_fallback_message,
     convert_tools_to_openai_schema,
     enforce_rpm_limit,
     format_message_for_llm,
@@ -64,6 +65,7 @@ from crewai.utilities.agent_utils import (
     handle_unknown_error,
     has_reached_max_iterations,
     is_context_length_exceeded,
+    is_native_tool_calling_unsupported_error,
     parse_tool_call_args,
     process_llm_response,
     track_delegation_if_needed,
@@ -464,6 +466,20 @@ class CrewAgentExecutor(BaseAgentExecutor):
         self._show_logs(formatted_answer)
         return formatted_answer
 
+    def _append_text_tool_calling_fallback_message(self) -> None:
+        """Add text tool-calling instructions after native tools are rejected."""
+        if not self.tools:
+            return
+        self.messages.append(
+            format_message_for_llm(
+                build_text_tool_calling_fallback_message(
+                    self.tools_description,
+                    self.tools_names,
+                ),
+                role="user",
+            )
+        )
+
     def _invoke_loop_native_tools(self) -> AgentFinish:
         """Execute agent loop using native function calling.
 
@@ -557,6 +573,9 @@ class CrewAgentExecutor(BaseAgentExecutor):
                 return formatted_answer
 
             except Exception as e:
+                if is_native_tool_calling_unsupported_error(e):
+                    self._append_text_tool_calling_fallback_message()
+                    return self._invoke_loop_react()
                 if e.__class__.__module__.startswith("litellm"):
                     raise e
                 if is_context_length_exceeded(e):
@@ -1369,6 +1388,9 @@ class CrewAgentExecutor(BaseAgentExecutor):
                 return formatted_answer
 
             except Exception as e:
+                if is_native_tool_calling_unsupported_error(e):
+                    self._append_text_tool_calling_fallback_message()
+                    return await self._ainvoke_loop_react()
                 if e.__class__.__module__.startswith("litellm"):
                     raise e
                 if is_context_length_exceeded(e):

lib/crewai/src/crewai/agents/step_executor.py

@@ -29,14 +29,17 @@ from crewai.events.types.tool_usage_events import (
     ToolUsageStartedEvent,
 )
 from crewai.utilities.agent_utils import (
+    build_text_tool_calling_fallback_message,
     build_tool_calls_assistant_message,
     check_native_tool_support,
     enforce_rpm_limit,
     execute_single_native_tool_call,
     extract_task_section,
     format_message_for_llm,
+    is_native_tool_calling_unsupported_error,
     is_tool_call_list,
     process_llm_response,
+    render_text_description_and_args,
     setup_native_tools,
 )
 from crewai.utilities.i18n import I18N_DEFAULT
@@ -153,6 +156,7 @@ class StepExecutor:
             if self._use_native_tools:
                 result_text = self._execute_native(
                     messages,
+                    todo,
                     tool_calls_made,
                     max_step_iterations=max_step_iterations,
                     step_timeout=step_timeout,
@@ -161,6 +165,7 @@ class StepExecutor:
             else:
                 result_text = self._execute_text_parsed(
                     messages,
+                    todo,
                     tool_calls_made,
                     max_step_iterations=max_step_iterations,
                     step_timeout=step_timeout,
@@ -176,6 +181,46 @@ class StepExecutor:
                 execution_time=elapsed,
             )
         except Exception as e:
+            if self._use_native_tools and is_native_tool_calling_unsupported_error(e):
+                try:
+                    self._use_native_tools = False
+                    self._openai_tools = []
+                    self._available_functions = {}
+                    # Keep the conversation built so far (including any native
+                    # tool round-trips already appended to ``messages``) and
+                    # append the text-tooling instructions instead of
+                    # restarting the step, so completed tool calls are not
+                    # re-executed against a fresh context.
+                    messages.append(
+                        format_message_for_llm(
+                            build_text_tool_calling_fallback_message(
+                                render_text_description_and_args(self.tools),
+                                ", ".join(
+                                    sanitize_tool_name(t.name) for t in self.tools
+                                ),
+                            ),
+                            role="user",
+                        )
+                    )
+                    result_text = self._execute_text_parsed(
+                        messages,
+                        todo,
+                        tool_calls_made,
+                        max_step_iterations=max_step_iterations,
+                        step_timeout=step_timeout,
+                        start_time=start_time,
+                    )
+                    self._validate_expected_tool_usage(todo, tool_calls_made)
+                    elapsed = time.monotonic() - start_time
+                    return StepResult(
+                        success=True,
+                        result=result_text,
+                        tool_calls_made=tool_calls_made,
+                        execution_time=elapsed,
+                    )
+                except Exception as fallback_error:
+                    e = fallback_error
+
             elapsed = time.monotonic() - start_time
             return StepResult(
                 success=False,
@@ -272,6 +317,7 @@ class StepExecutor:
     def _execute_text_parsed(
         self,
         messages: list[LLMMessage],
+        todo: TodoItem,
         tool_calls_made: list[str],
         max_step_iterations: int = 15,
         step_timeout: int | None = None,
@@ -310,7 +356,7 @@ class StepExecutor:
 
             if isinstance(formatted, AgentAction):
                 tool_calls_made.append(formatted.tool)
-                tool_result = self._execute_text_tool_with_events(formatted)
+                tool_result = self._execute_text_tool_with_events(formatted, todo)
                 last_tool_result = tool_result
                 messages.append({"role": "assistant", "content": answer_str})
                 messages.append(self._build_observation_message(tool_result))
@@ -320,7 +366,9 @@ class StepExecutor:
 
         return last_tool_result
 
-    def _execute_text_tool_with_events(self, formatted: AgentAction) -> str:
+    def _execute_text_tool_with_events(
+        self, formatted: AgentAction, todo: TodoItem
+    ) -> str:
         """Execute text-parsed tool calls with tool usage events."""
         args_dict = self._parse_tool_args(formatted.tool_input)
         agent_key = getattr(self.agent, "key", "unknown") if self.agent else "unknown"
@@ -333,6 +381,8 @@ class StepExecutor:
                 from_agent=self.agent,
                 from_task=self.task,
                 agent_key=agent_key,
+                plan_step_number=todo.step_number,
+                plan_step_description=todo.description,
             ),
         )
 
@@ -368,6 +418,8 @@ class StepExecutor:
                     from_agent=self.agent,
                     from_task=self.task,
                     agent_key=agent_key,
+                    plan_step_number=todo.step_number,
+                    plan_step_description=todo.description,
                     error=e,
                 ),
             )
@@ -382,6 +434,8 @@ class StepExecutor:
                 from_agent=self.agent,
                 from_task=self.task,
                 agent_key=agent_key,
+                plan_step_number=todo.step_number,
+                plan_step_description=todo.description,
                 started_at=started_at,
                 finished_at=datetime.now(),
             ),
@@ -474,6 +528,7 @@ class StepExecutor:
     def _execute_native(
         self,
         messages: list[LLMMessage],
+        todo: TodoItem,
         tool_calls_made: list[str],
         max_step_iterations: int = 15,
         step_timeout: int | None = None,
@@ -513,7 +568,7 @@ class StepExecutor:
 
             if isinstance(answer, list) and answer and is_tool_call_list(answer):
                 result = self._execute_native_tool_calls(
-                    answer, messages, tool_calls_made
+                    answer, messages, todo, tool_calls_made
                 )
                 accumulated_results.append(result)
                 continue
@@ -526,6 +581,7 @@ class StepExecutor:
         self,
         tool_calls: list[Any],
         messages: list[LLMMessage],
+        todo: TodoItem,
         tool_calls_made: list[str],
     ) -> str:
         """Execute a batch of native tool calls and return their results.
@@ -551,6 +607,8 @@ class StepExecutor:
                 event_source=self,
                 printer=PRINTER,
                 verbose=bool(self.agent and self.agent.verbose),
+                plan_step_number=todo.step_number,
+                plan_step_description=todo.description,
             )
 
             if call_result.func_name:

lib/crewai/src/crewai/crew.py

@@ -658,7 +658,14 @@ class Crew(FlowTrackable, BaseModel):
                 from crewai.rag.embeddings.factory import build_embedder
 
                 embedder = build_embedder(cast(dict[str, Any], self.embedder))
-            self._memory = Memory(embedder=embedder, root_scope=crew_root_scope)
+            memory_kwargs: dict[str, Any] = {
+                "embedder": embedder,
+                "root_scope": crew_root_scope,
+            }
+            memory_llm = self._memory_llm()
+            if memory_llm is not None:
+                memory_kwargs["llm"] = memory_llm
+            self._memory = Memory(**memory_kwargs)
         elif self.memory:
             # User passed a Memory / MemoryScope / MemorySlice instance
             # Respect user's configuration — don't auto-set root_scope
@@ -668,6 +675,16 @@ class Crew(FlowTrackable, BaseModel):
 
         return self
 
+    def _memory_llm(self) -> str | BaseLLM | None:
+        """Return the LLM auto-created memory should use for analysis."""
+        if self.chat_llm is not None:
+            return self.chat_llm
+        for agent in self.agents:
+            agent_llm: str | BaseLLM | None = getattr(agent, "llm", None)
+            if agent_llm is not None:
+                return agent_llm
+        return None
+
     @model_validator(mode="after")
     def create_crew_knowledge(self) -> Crew:
         """Create the knowledge for the crew."""

lib/crewai/src/crewai/events/__init__.py

@@ -116,6 +116,11 @@ if TYPE_CHECKING:
         MemorySaveFailedEvent,
         MemorySaveStartedEvent,
     )
+    from crewai.events.types.observation_events import (
+        PlanStepCompletedEvent,
+        PlanStepEvent,
+        PlanStepStartedEvent,
+    )
     from crewai.events.types.reasoning_events import (
         AgentReasoningCompletedEvent,
         AgentReasoningFailedEvent,
@@ -220,6 +225,9 @@ _LAZY_EVENT_MAPPING: dict[str, str] = {
     "MemorySaveCompletedEvent": "crewai.events.types.memory_events",
     "MemorySaveFailedEvent": "crewai.events.types.memory_events",
     "MemorySaveStartedEvent": "crewai.events.types.memory_events",
+    "PlanStepCompletedEvent": "crewai.events.types.observation_events",
+    "PlanStepEvent": "crewai.events.types.observation_events",
+    "PlanStepStartedEvent": "crewai.events.types.observation_events",
     "AgentReasoningCompletedEvent": "crewai.events.types.reasoning_events",
     "AgentReasoningFailedEvent": "crewai.events.types.reasoning_events",
     "AgentReasoningStartedEvent": "crewai.events.types.reasoning_events",
@@ -349,6 +357,9 @@ __all__ = [
     "MethodExecutionFailedEvent",
     "MethodExecutionFinishedEvent",
     "MethodExecutionStartedEvent",
+    "PlanStepCompletedEvent",
+    "PlanStepEvent",
+    "PlanStepStartedEvent",
     "ReasoningEvent",
     "SkillActivatedEvent",
     "SkillDiscoveryCompletedEvent",

lib/crewai/src/crewai/events/event_listener.py

@@ -158,7 +158,6 @@ class EventListener(BaseEventListener):
             trace_listener.formatter = self.formatter
 
     def setup_listeners(self, crewai_event_bus: CrewAIEventsBus) -> None:
-
         @crewai_event_bus.on(CCEnvEvent)
         def on_cc_env(_: Any, event: CCEnvEvent) -> None:
             self._telemetry.env_context_span(event.type)

lib/crewai/src/crewai/events/event_types.py

@@ -99,6 +99,10 @@ from crewai.events.types.memory_events import (
     MemorySaveFailedEvent,
     MemorySaveStartedEvent,
 )
+from crewai.events.types.observation_events import (
+    PlanStepCompletedEvent,
+    PlanStepStartedEvent,
+)
 from crewai.events.types.reasoning_events import (
     AgentReasoningCompletedEvent,
     AgentReasoningFailedEvent,
@@ -191,6 +195,8 @@ EventTypes = (
     | MemoryRetrievalStartedEvent
     | MemoryRetrievalCompletedEvent
     | MemoryRetrievalFailedEvent
+    | PlanStepStartedEvent
+    | PlanStepCompletedEvent
     | MCPConnectionStartedEvent
     | MCPConnectionCompletedEvent
     | MCPConnectionFailedEvent

lib/crewai/src/crewai/events/listeners/tracing/trace_batch_manager.py

@@ -24,6 +24,7 @@ from crewai.events.listeners.tracing.types import TraceEvent
 from crewai.events.listeners.tracing.utils import (
     get_user_id,
     is_tracing_enabled_in_context,
+    is_tui_mode,
     should_auto_collect_first_time_traces,
 )
 from crewai.plus_api import PlusAPI
@@ -74,6 +75,7 @@ class TraceBatchManager:
         self.defer_session_finalization: bool = False
         self._batch_finalized: bool = False
         self.backend_initialized: bool = False
+        self.trace_url: str | None = None
         self.ephemeral_trace_url: str | None = None
         try:
             self.plus_api = PlusAPI(
@@ -108,7 +110,9 @@ class TraceBatchManager:
 
             self.record_start_time("execution")
 
-            if should_auto_collect_first_time_traces():
+            if should_auto_collect_first_time_traces() or (
+                is_tui_mode() and not is_tracing_enabled_in_context()
+            ):
                 self.trace_batch_id = self.current_batch.batch_id
             else:
                 self._initialize_backend_batch(
@@ -411,6 +415,7 @@ class TraceBatchManager:
                         else f"{base_url}/crewai_plus/ephemeral_trace_batches/{batch_id}?access_code={access_code}"
                     )
 
+                    self.trace_url = return_link
                     if is_ephemeral:
                         self.ephemeral_trace_url = return_link
 
@@ -428,7 +433,10 @@ class TraceBatchManager:
                         title="Trace Batch Finalization",
                         border_style="green",
                     )
-                    if not should_auto_collect_first_time_traces():
+                    if (
+                        not should_auto_collect_first_time_traces()
+                        and not is_tui_mode()
+                    ):
                         console.print(panel)
                     return True
 

lib/crewai/src/crewai/events/listeners/tracing/trace_listener.py

@@ -18,6 +18,7 @@ from crewai.events.listeners.tracing.trace_batch_manager import TraceBatchManage
 from crewai.events.listeners.tracing.types import TraceEvent
 from crewai.events.listeners.tracing.utils import (
     is_tracing_enabled_in_context,
+    is_tui_mode,
     safe_serialize_to_dict,
     should_auto_collect_first_time_traces,
     should_enable_tracing,
@@ -212,8 +213,8 @@ class TraceCollectionListener(BaseEventListener):
             not should_enable_tracing()
             and not is_tracing_enabled_in_context()
             and not should_auto_collect_first_time_traces()
+            and not is_tui_mode()
         ):
-            self._listeners_setup = True
             return
 
         self._register_flow_event_handlers(crewai_event_bus)
@@ -297,6 +298,12 @@ class TraceCollectionListener(BaseEventListener):
             if self._nested_in_flow_execution():
                 return
             if self.batch_manager.batch_owner_type == "crew":
+                if is_tui_mode():
+                    if self.first_time_handler.is_first_time:
+                        self.first_time_handler.mark_events_collected()
+                    elif is_tracing_enabled_in_context() or should_enable_tracing():
+                        self.batch_manager.finalize_batch()
+                    return
                 if self.first_time_handler.is_first_time:
                     self.first_time_handler.mark_events_collected()
                     self.first_time_handler.handle_execution_completion()
@@ -310,6 +317,12 @@ class TraceCollectionListener(BaseEventListener):
                 return
             if self._nested_in_flow_execution():
                 return
+            if is_tui_mode():
+                if self.first_time_handler.is_first_time:
+                    self.first_time_handler.mark_events_collected()
+                elif is_tracing_enabled_in_context() or should_enable_tracing():
+                    self.batch_manager.finalize_batch()
+                return
             if self.first_time_handler.is_first_time:
                 self.first_time_handler.mark_events_collected()
                 self.first_time_handler.handle_execution_completion()

lib/crewai/src/crewai/events/listeners/tracing/utils.py

@@ -42,6 +42,7 @@ __all__ = [
     "is_first_execution",
     "is_tracing_enabled",
     "is_tracing_enabled_in_context",
+    "is_tui_mode",
     "mark_first_execution_completed",
     "mark_first_execution_done",
     "on_first_execution_tracing_confirmation",
@@ -50,6 +51,7 @@ __all__ = [
     "safe_serialize_to_dict",
     "set_suppress_tracing_messages",
     "set_tracing_enabled",
+    "set_tui_mode",
     "should_auto_collect_first_time_traces",
     "should_enable_tracing",
     "should_suppress_tracing_messages",
@@ -71,6 +73,16 @@ _suppress_tracing_messages: ContextVar[bool] = ContextVar(
     "_suppress_tracing_messages", default=False
 )
 
+_tui_mode: ContextVar[bool] = ContextVar("_tui_mode", default=False)
+
+
+def set_tui_mode(enabled: bool) -> object:
+    return _tui_mode.set(enabled)
+
+
+def is_tui_mode() -> bool:
+    return _tui_mode.get()
+
 
 def set_suppress_tracing_messages(suppress: bool) -> object:
     """Set whether to suppress tracing-related console messages.

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

@@ -26,6 +26,38 @@ class ObservationEvent(BaseEvent):
         self._set_agent_params(data)
 
 
+class PlanStepEvent(BaseEvent):
+    """Base event for authoritative plan step lifecycle updates."""
+
+    type: str
+    agent_role: str
+    step_number: int
+    step_description: str = ""
+    tool_to_use: str | None = None
+    from_task: Any | None = None
+    from_agent: Any | None = None
+
+    def __init__(self, **data: Any) -> None:
+        super().__init__(**data)
+        self._set_task_params(data)
+        self._set_agent_params(data)
+
+
+class PlanStepStartedEvent(PlanStepEvent):
+    """Emitted when a concrete plan step starts executing."""
+
+    type: Literal["plan_step_started"] = "plan_step_started"
+
+
+class PlanStepCompletedEvent(PlanStepEvent):
+    """Emitted when a concrete plan step reaches a terminal state."""
+
+    type: Literal["plan_step_completed"] = "plan_step_completed"
+    success: bool = True
+    result: str | None = None
+    error: str | None = None
+
+
 class StepObservationStartedEvent(ObservationEvent):
     """Emitted when the Planner begins observing a step's result.
 

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

@@ -21,6 +21,8 @@ class ToolUsageEvent(BaseEvent):
     agent: Any | None = None
     task_name: str | None = None
     task_id: str | None = None
+    plan_step_number: int | None = None
+    plan_step_description: str | None = None
     from_task: Any | None = None
     from_agent: Any | None = None
 

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

@@ -46,6 +46,8 @@ from crewai.events.types.observation_events import (
     GoalAchievedEarlyEvent,
     PlanRefinementEvent,
     PlanReplanTriggeredEvent,
+    PlanStepCompletedEvent,
+    PlanStepStartedEvent,
 )
 from crewai.events.types.tool_usage_events import (
     ToolUsageErrorEvent,
@@ -73,6 +75,7 @@ from crewai.tools.base_tool import BaseTool
 from crewai.tools.structured_tool import CrewStructuredTool
 from crewai.utilities.agent_utils import (
     _llm_stop_words_applied,
+    build_text_tool_calling_fallback_message,
     check_native_tool_support,
     enforce_rpm_limit,
     extract_tool_call_info,
@@ -86,6 +89,7 @@ from crewai.utilities.agent_utils import (
     has_reached_max_iterations,
     is_context_length_exceeded,
     is_inside_event_loop,
+    is_native_tool_calling_unsupported_error,
     is_tool_call_list,
     parse_tool_call_args,
     process_llm_response,
@@ -241,6 +245,23 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
                 self._tool_name_mapping,
             ) = setup_native_tools(self.original_tools)
 
+    def _downgrade_to_text_tool_calling(self) -> None:
+        """Switch a running execution from native tools to text tool calls."""
+        self.state.use_native_tools = False
+        self.state.pending_tool_calls.clear()
+        self._openai_tools = []
+        self._available_functions = {}
+        if self.tools:
+            self.state.messages.append(
+                format_message_for_llm(
+                    build_text_tool_calling_fallback_message(
+                        self.tools_description,
+                        self.tools_names,
+                    ),
+                    role="user",
+                )
+            )
+
     def _is_tool_call_list(self, response: list[Any]) -> bool:
         """Check if a response is a list of tool calls."""
         return is_tool_call_list(response)
@@ -349,6 +370,84 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
 
         self.state.todos = TodoList(items=todos)
 
+    def _emit_plan_step_started(self, todo: TodoItem) -> None:
+        try:
+            crewai_event_bus.emit(
+                self.agent,
+                event=PlanStepStartedEvent(
+                    agent_role=self.agent.role,
+                    step_number=todo.step_number,
+                    step_description=todo.description,
+                    tool_to_use=todo.tool_to_use,
+                    from_task=self.task,
+                    from_agent=self.agent,
+                ),
+            )
+        except Exception:  # noqa: S110
+            pass
+
+    def _emit_plan_step_completed(
+        self,
+        todo: TodoItem,
+        *,
+        success: bool,
+        result: str | None = None,
+        error: str | None = None,
+    ) -> None:
+        try:
+            crewai_event_bus.emit(
+                self.agent,
+                event=PlanStepCompletedEvent(
+                    agent_role=self.agent.role,
+                    step_number=todo.step_number,
+                    step_description=todo.description,
+                    tool_to_use=todo.tool_to_use,
+                    success=success,
+                    result=result,
+                    error=error,
+                    from_task=self.task,
+                    from_agent=self.agent,
+                ),
+            )
+        except Exception:  # noqa: S110
+            pass
+
+    def _mark_todo_running(self, todo: TodoItem) -> None:
+        previous_status = todo.status
+        self.state.todos.mark_running(todo.step_number)
+        if previous_status != "running":
+            self._emit_plan_step_started(todo)
+
+    def _mark_todo_completed(
+        self,
+        step_number: int,
+        result: str | None = None,
+    ) -> None:
+        todo = self.state.todos.get_by_step_number(step_number)
+        previous_status = todo.status if todo else None
+        self.state.todos.mark_completed(step_number, result=result)
+        todo = self.state.todos.get_by_step_number(step_number)
+        if todo and previous_status != "completed":
+            self._emit_plan_step_completed(todo, success=True, result=result)
+
+    def _mark_todo_failed(
+        self,
+        step_number: int,
+        result: str | None = None,
+        error: str | None = None,
+    ) -> None:
+        todo = self.state.todos.get_by_step_number(step_number)
+        previous_status = todo.status if todo else None
+        self.state.todos.mark_failed(step_number, result=result)
+        todo = self.state.todos.get_by_step_number(step_number)
+        if todo and previous_status != "failed":
+            self._emit_plan_step_completed(
+                todo,
+                success=False,
+                result=result,
+                error=error,
+            )
+
     def _ensure_step_executor(self) -> Any:
         """Lazily create the StepExecutor (avoids circular imports)."""
         if self._step_executor is None:
@@ -597,8 +696,10 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
             and not observation.step_completed_successfully
             and observation.needs_full_replan
         ):
-            self.state.todos.mark_failed(
-                current_todo.step_number, result=current_todo.result
+            self._mark_todo_failed(
+                current_todo.step_number,
+                result=current_todo.result,
+                error=observation.replan_reason,
             )
             if self.agent.verbose:
                 PRINTER.print(
@@ -614,8 +715,9 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
             return "replan_now"
 
         if observation and not observation.step_completed_successfully:
-            self.state.todos.mark_failed(
-                current_todo.step_number, result=current_todo.result
+            self._mark_todo_failed(
+                current_todo.step_number,
+                result=current_todo.result,
             )
             if self.agent.verbose:
                 failed = len(self.state.todos.get_failed_todos())
@@ -629,9 +731,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
                 )
             return "continue_plan"
 
-        self.state.todos.mark_completed(
-            current_todo.step_number, result=current_todo.result
-        )
+        self._mark_todo_completed(current_todo.step_number, result=current_todo.result)
 
         if self.agent.verbose:
             completed = self.state.todos.completed_count
@@ -661,7 +761,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
 
         # If observation is missing or step succeeded — continue
         if not observation or observation.step_completed_successfully:
-            self.state.todos.mark_completed(
+            self._mark_todo_completed(
                 current_todo.step_number, result=current_todo.result
             )
             if self.agent.verbose:
@@ -676,8 +776,10 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
         # Step failed — only replan if observer explicitly requires it,
         # otherwise mark done and continue (same gate as low-effort).
         if observation.needs_full_replan:
-            self.state.todos.mark_failed(
-                current_todo.step_number, result=current_todo.result
+            self._mark_todo_failed(
+                current_todo.step_number,
+                result=current_todo.result,
+                error=observation.replan_reason,
             )
             if self.agent.verbose:
                 PRINTER.print(
@@ -694,9 +796,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
 
         # Step failed but observer does not require a full replan — mark as
         # failed (not completed) so get_failed_todos() tracks it correctly.
-        self.state.todos.mark_failed(
-            current_todo.step_number, result=current_todo.result
-        )
+        self._mark_todo_failed(current_todo.step_number, result=current_todo.result)
         if self.agent.verbose:
             failed = len(self.state.todos.get_failed_todos())
             total = len(self.state.todos.items)
@@ -731,12 +831,12 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
         observation = self.state.observations.get(current_todo.step_number)
         if not observation:
             # No observation available — default to continue
-            self.state.todos.mark_completed(current_todo.step_number)
+            self._mark_todo_completed(current_todo.step_number)
             return "continue_plan"
 
         # Goal already achieved — early termination
         if observation.goal_already_achieved:
-            self.state.todos.mark_completed(
+            self._mark_todo_completed(
                 current_todo.step_number, result=current_todo.result
             )
             if self.agent.verbose:
@@ -748,8 +848,10 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
 
         # Full replan needed
         if observation.needs_full_replan:
-            self.state.todos.mark_failed(
-                current_todo.step_number, result=current_todo.result
+            self._mark_todo_failed(
+                current_todo.step_number,
+                result=current_todo.result,
+                error=observation.replan_reason,
             )
             if self.agent.verbose:
                 PRINTER.print(
@@ -761,9 +863,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
 
         # Step failed — also trigger replan
         if not observation.step_completed_successfully:
-            self.state.todos.mark_failed(
-                current_todo.step_number, result=current_todo.result
-            )
+            self._mark_todo_failed(current_todo.step_number, result=current_todo.result)
             if self.agent.verbose:
                 PRINTER.print(
                     content="[Decide] Step failed — triggering replan",
@@ -773,7 +873,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
             return "replan_now"
 
         if observation.remaining_plan_still_valid and observation.suggested_refinements:
-            self.state.todos.mark_completed(
+            self._mark_todo_completed(
                 current_todo.step_number, result=current_todo.result
             )
             if self.agent.verbose:
@@ -783,9 +883,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
                 )
             return "refine_and_continue"
 
-        self.state.todos.mark_completed(
-            current_todo.step_number, result=current_todo.result
-        )
+        self._mark_todo_completed(current_todo.step_number, result=current_todo.result)
         if self.agent.verbose:
             completed = self.state.todos.completed_count
             total = len(self.state.todos.items)
@@ -961,7 +1059,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
             return "needs_replan"
 
         if len(ready) == 1:
-            self.state.todos.mark_running(ready[0].step_number)
+            self._mark_todo_running(ready[0])
             return "single_todo_ready"
 
         return "multiple_todos_ready"
@@ -1099,7 +1197,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
 
         # Mark all ready todos as running
         for todo in ready:
-            self.state.todos.mark_running(todo.step_number)
+            self._mark_todo_running(todo)
 
         # Build context and executor for each todo, then run in parallel
         async def _run_step(todo: TodoItem) -> tuple[TodoItem, object]:
@@ -1127,7 +1225,11 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
             if isinstance(item, BaseException):
                 error_msg = f"Error: {item!s}"
                 todo.result = error_msg
-                self.state.todos.mark_failed(todo.step_number, result=error_msg)
+                self._mark_todo_failed(
+                    todo.step_number,
+                    result=error_msg,
+                    error=error_msg,
+                )
                 if self.agent.verbose:
                     PRINTER.print(
                         content=f"Todo {todo.step_number} failed: {error_msg}",
@@ -1197,9 +1299,9 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
 
             # Mark based on observation result
             if observation.step_completed_successfully:
-                self.state.todos.mark_completed(todo.step_number, result=todo.result)
+                self._mark_todo_completed(todo.step_number, result=todo.result)
             else:
-                self.state.todos.mark_failed(todo.step_number, result=todo.result)
+                self._mark_todo_failed(todo.step_number, result=todo.result)
 
             if self.agent.verbose:
                 PRINTER.print(
@@ -1349,7 +1451,11 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
     def call_llm_native_tools(
         self,
     ) -> Literal[
-        "native_tool_calls", "native_finished", "context_error", "todo_satisfied"
+        "native_tool_calls",
+        "native_finished",
+        "context_error",
+        "todo_satisfied",
+        "continue_reasoning",
     ]:
         """Execute LLM call with native function calling.
 
@@ -1428,6 +1534,9 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
             return self._route_finish_with_todos("native_finished")
 
         except Exception as e:
+            if is_native_tool_calling_unsupported_error(e):
+                self._downgrade_to_text_tool_calling()
+                return "continue_reasoning"
             if is_context_length_exceeded(e):
                 self._last_context_error = e
                 return "context_error"
@@ -2085,7 +2194,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
             step_number: The step number to mark.
             result: The result of the todo.
         """
-        self.state.todos.mark_completed(step_number, result=result)
+        self._mark_todo_completed(step_number, result=result)
 
         if self.agent.verbose:
             completed = self.state.todos.completed_count

lib/crewai/src/crewai/experimental/conversational_mixin.py

@@ -47,7 +47,7 @@ from crewai.flow.conversation import (
     receive_user_message as _receive_user_message,
 )
 from crewai.flow.dsl import listen, start
-from crewai.flow.dsl._utils import _set_flow_method_definition
+from crewai.flow.dsl._utils import _method_action, _set_flow_method_definition
 from crewai.flow.flow_definition import FlowMethodDefinition
 from crewai.utilities.types import LLMMessage
 
@@ -78,7 +78,7 @@ def _conversation_start_router(func: Callable[..., Any]) -> Any:
     wrapper = start()(func)
     _set_flow_method_definition(
         cast(Any, wrapper),
-        FlowMethodDefinition(start=True, router=True),
+        FlowMethodDefinition(do=_method_action(func), start=True, router=True),
     )
     return wrapper
 
@@ -146,6 +146,10 @@ class _ConversationalMixin:
         def kickoff(self, *args: Any, **kwargs: Any) -> Any:
             pass
 
+        @property
+        def method_outputs(self) -> list[Any]:
+            pass
+
     def conversation_start(self) -> str | None:
         """Return the current user message for conversational route selection.
 
@@ -1033,7 +1037,8 @@ class _ConversationalMixin:
         # of warning about an empty scope stack.
         started_id = getattr(self, "_deferred_flow_started_event_id", None)
         if started_id:
-            last_output = self._method_outputs[-1] if self._method_outputs else None
+            method_outputs = self.method_outputs
+            last_output = method_outputs[-1] if method_outputs else None
             restore_event_scope(((started_id, "flow_started"),))
             try:
                 crewai_event_bus.emit(

lib/crewai/src/crewai/flow/async_feedback/__init__.py

@@ -20,7 +20,7 @@ Example:
         @human_feedback(
             message="Review this:",
             emit=["approved", "rejected"],
-            llm="gpt-4o-mini",
+            llm="gpt-5.4-mini",
             provider=SlackProvider(),
         )
         def review(self):

lib/crewai/src/crewai/flow/async_feedback/types.py

@@ -47,7 +47,7 @@ class PendingFeedbackContext:
             method_output={"title": "Draft", "body": "..."},
             message="Please review and approve or reject:",
             emit=["approved", "rejected"],
-            llm="gpt-4o-mini",
+            llm="gpt-5.4-mini",
         )
         ```
     """

lib/crewai/src/crewai/flow/dsl/_human_feedback.py

@@ -3,11 +3,10 @@ from __future__ import annotations
 from collections.abc import Callable, Sequence
 from typing import TYPE_CHECKING, Any, TypeVar
 
-from crewai.flow.flow_definition import FlowMethodDefinition
 from crewai.flow.human_feedback import (
     HumanFeedbackConfig,
     HumanFeedbackResult,
-    _build_human_feedback_runtime_decorator,
+    _validate_human_feedback_options,
 )
 
 
@@ -21,36 +20,10 @@ F = TypeVar("F", bound=Callable[..., Any])
 __all__ = ["HumanFeedbackResult", "human_feedback"]
 
 
-def _stamp_human_feedback_metadata(
-    wrapper: Any,
-    func: Callable[..., Any],
-    config: HumanFeedbackConfig,
-) -> None:
-    for attr in [
-        "__is_flow_method__",
-        "__flow_persistence_config__",
-        "__flow_method_definition__",
-    ]:
-        if hasattr(func, attr):
-            setattr(wrapper, attr, getattr(func, attr))
-
-    wrapper.__human_feedback_config__ = config
-    wrapper.__is_flow_method__ = True
-
-    if config.emit:
-        fragment = getattr(wrapper, "__flow_method_definition__", None)
-        if isinstance(fragment, FlowMethodDefinition):
-            wrapper.__flow_method_definition__ = fragment.model_copy(
-                update={"router": True, "emit": list(config.emit)}
-            )
-
-    wrapper._human_feedback_llm = config.llm
-
-
 def human_feedback(
     message: str,
     emit: Sequence[str] | None = None,
-    llm: str | BaseLLM | None = "gpt-4o-mini",
+    llm: str | BaseLLM | None = "gpt-5.4-mini",
     default_outcome: str | None = None,
     metadata: dict[str, Any] | None = None,
     provider: HumanFeedbackProvider | None = None,
@@ -58,21 +31,18 @@ def human_feedback(
     learn_source: str = "hitl",
     learn_strict: bool = False,
 ) -> Callable[[F], F]:
-    """Decorator for Flow methods that require human feedback."""
-    runtime_decorator = _build_human_feedback_runtime_decorator(
-        message=message,
-        emit=emit,
-        llm=llm,
-        default_outcome=default_outcome,
-        metadata=metadata,
-        provider=provider,
-        learn=learn,
-        learn_source=learn_source,
-        learn_strict=learn_strict,
+    """Decorator for Flow methods that require human feedback.
+
+    The decorator is a pure metadata stamper: it records the feedback
+    configuration on the method, and the Flow engine collects and routes
+    feedback after the method completes, driven by the flow's definition.
+    """
+    _validate_human_feedback_options(
+        emit=emit, llm=llm, default_outcome=default_outcome
     )
     config = HumanFeedbackConfig(
         message=message,
-        emit=emit,
+        emit=list(emit) if emit is not None else None,
         llm=llm,
         default_outcome=default_outcome,
         metadata=metadata,
@@ -83,8 +53,7 @@ def human_feedback(
     )
 
     def decorator(func: F) -> F:
-        wrapper = runtime_decorator(func)
-        _stamp_human_feedback_metadata(wrapper, func, config)
-        return wrapper
+        func.__human_feedback_config__ = config  # type: ignore[attr-defined]
+        return func
 
     return decorator

lib/crewai/src/crewai/flow/dsl/_listen.py

@@ -8,6 +8,7 @@ from crewai.flow.dsl._types import FlowMethodDecorator, FlowTrigger
 from crewai.flow.dsl._utils import (
     P,
     R,
+    _method_action,
     _set_flow_method_definition,
 )
 from crewai.flow.flow_definition import FlowMethodDefinition
@@ -45,7 +46,11 @@ def listen(condition: FlowTrigger) -> FlowMethodDecorator:
         wrapper = ListenMethod(func)
 
         _set_flow_method_definition(
-            wrapper, FlowMethodDefinition(listen=_to_definition_condition(condition))
+            wrapper,
+            FlowMethodDefinition(
+                do=_method_action(func),
+                listen=_to_definition_condition(condition),
+            ),
         )
         return wrapper
 

lib/crewai/src/crewai/flow/dsl/_router.py

@@ -19,6 +19,7 @@ from crewai.flow.dsl._types import FlowMethodDecorator, FlowTrigger
 from crewai.flow.dsl._utils import (
     P,
     R,
+    _method_action,
     _set_flow_method_definition,
 )
 from crewai.flow.flow_definition import FlowMethodDefinition
@@ -148,6 +149,7 @@ def router(
         _set_flow_method_definition(
             wrapper,
             FlowMethodDefinition(
+                do=_method_action(func),
                 listen=_to_definition_condition(condition),
                 router=True,
                 emit=router_events or None,

lib/crewai/src/crewai/flow/dsl/_start.py

@@ -8,6 +8,7 @@ from crewai.flow.dsl._types import FlowMethodDecorator, FlowTrigger
 from crewai.flow.dsl._utils import (
     P,
     R,
+    _method_action,
     _set_flow_method_definition,
 )
 from crewai.flow.flow_definition import FlowMethodDefinition
@@ -53,13 +54,17 @@ def start(
     def decorator(func: Callable[P, R]) -> StartMethod[P, R]:
         wrapper = StartMethod(func)
 
-        if condition is not None:
-            _set_flow_method_definition(
-                wrapper,
-                FlowMethodDefinition(start=_to_definition_condition(condition)),
-            )
-        else:
-            _set_flow_method_definition(wrapper, FlowMethodDefinition(start=True))
+        _set_flow_method_definition(
+            wrapper,
+            FlowMethodDefinition(
+                do=_method_action(func),
+                start=(
+                    _to_definition_condition(condition)
+                    if condition is not None
+                    else True
+                ),
+            ),
+        )
         return wrapper
 
     return cast(FlowMethodDecorator, decorator)

lib/crewai/src/crewai/flow/dsl/_utils.py

@@ -8,6 +8,8 @@ from pydantic import BaseModel
 from typing_extensions import TypeIs
 
 from crewai.flow.flow_definition import (
+    FlowActionDefinition,
+    FlowCodeActionDefinition,
     FlowConfigDefinition,
     FlowConversationalDefinition,
     FlowConversationalRouterDefinition,
@@ -17,6 +19,7 @@ from crewai.flow.flow_definition import (
     FlowMethodDefinition,
     FlowPersistenceDefinition,
     FlowStateDefinition,
+    _object_ref,
 )
 from crewai.flow.flow_wrappers import (
     FlowMethod,
@@ -34,15 +37,12 @@ _FLOW_METHOD_METADATA_ATTRS = [
     "__flow_method_definition__",
     "__flow_persistence_config__",
     "__human_feedback_config__",
-    "_human_feedback_llm",
 ]
 
 
 def is_flow_method(obj: Any) -> TypeIs[FlowMethod[Any, Any]]:
     """Check if the object carries Flow method wrapper metadata."""
-    return hasattr(obj, "__is_flow_method__") or hasattr(
-        obj, _FLOW_METHOD_DEFINITION_ATTR
-    )
+    return hasattr(obj, _FLOW_METHOD_DEFINITION_ATTR)
 
 
 def _should_include_flow_method(flow_class: type, method: Any) -> bool:
@@ -80,10 +80,13 @@ def _stamp_inherited_conversational_metadata(
     for attr in _FLOW_METHOD_METADATA_ATTRS:
         if hasattr(inherited, attr):
             setattr(method, attr, getattr(inherited, attr))
-    method.__is_flow_method__ = True
     return method
 
 
+def _method_action(method: Any) -> FlowActionDefinition:
+    return FlowCodeActionDefinition(ref=f"{method.__module__}:{method.__qualname__}")
+
+
 def _set_flow_method_definition(
     wrapper: FlowMethod[P, R],
     definition: FlowMethodDefinition,
@@ -100,13 +103,6 @@ def _get_flow_method_definition(method: Any) -> FlowMethodDefinition | None:
     return None
 
 
-def _object_ref(value: Any) -> str:
-    target = value if isinstance(value, type) else type(value)
-    module = getattr(target, "__module__", "")
-    qualname = getattr(target, "__qualname__", getattr(target, "__name__", ""))
-    return f"{module}:{qualname}" if module and qualname else repr(value)
-
-
 def _is_json_serializable(value: Any) -> bool:
     try:
         json.dumps(value)
@@ -214,16 +210,22 @@ def _build_config_definition(
 ) -> FlowConfigDefinition:
     config_field_names = set(FlowConfigDefinition.model_fields)
     field_defaults = {
-        name: field.default
+        name: field.get_default(call_default_factory=True)
         for name, field in getattr(flow_class, "model_fields", {}).items()
         if name in config_field_names
     }
     values: dict[str, Any] = {}
     for field_name, default in field_defaults.items():
         value = getattr(flow_class, field_name, default)
-        values[field_name] = _serialize_static_value(
-            value, diagnostics, f"config.{field_name}"
-        )
+        if field_name == "input_provider":
+            # A string value is already a ref; only live objects degrade.
+            values[field_name] = (
+                value if value is None or isinstance(value, str) else _object_ref(value)
+            )
+        else:
+            values[field_name] = _serialize_static_value(
+                value, diagnostics, f"config.{field_name}"
+            )
     return FlowConfigDefinition(**values)
 
 
@@ -239,38 +241,31 @@ def _build_human_feedback_definition(
     return FlowHumanFeedbackDefinition(
         message=str(config.message),
         emit=[str(value) for value in emit] if emit is not None else None,
-        llm=_serialize_static_value(
-            getattr(config, "llm", None), diagnostics, f"{path}.llm"
-        ),
+        # llm and provider stay live: the engine consumes them in-process and
+        # the contract degrades them to serializable forms at JSON dump time.
+        llm=getattr(config, "llm", None),
         default_outcome=getattr(config, "default_outcome", None),
         metadata=_serialize_static_value(
             getattr(config, "metadata", None), diagnostics, f"{path}.metadata"
         ),
-        provider=_serialize_static_value(
-            getattr(config, "provider", None), diagnostics, f"{path}.provider"
-        ),
+        provider=getattr(config, "provider", None),
         learn=bool(getattr(config, "learn", False)),
         learn_source=str(getattr(config, "learn_source", "hitl")),
         learn_strict=bool(getattr(config, "learn_strict", False)),
     )
 
 
-def _build_persistence_definition(
-    value: Any,
-    diagnostics: list[FlowDefinitionDiagnostic],
-    path: str,
-) -> FlowPersistenceDefinition | None:
+def _build_persistence_definition(value: Any) -> FlowPersistenceDefinition | None:
     config = getattr(value, "__flow_persistence_config__", None)
     if config is None:
         return None
-    persistence = getattr(config, "persistence", None)
-    verbose = bool(getattr(config, "verbose", False))
     return FlowPersistenceDefinition(
         enabled=True,
-        verbose=verbose,
-        persistence=_serialize_static_value(
-            persistence, diagnostics, f"{path}.persistence"
-        ),
+        verbose=bool(getattr(config, "verbose", False)),
+        # The backend stays live: the engine persists through the exact
+        # instance the user configured; the contract degrades it to a
+        # serialized config at JSON dump time.
+        persistence=getattr(config, "persistence", None),
     )
 
 
@@ -373,9 +368,11 @@ def _build_method_definition(
 ) -> FlowMethodDefinition:
     fragment = _get_flow_method_definition(method)
     if fragment is None:
-        method_definition = FlowMethodDefinition()
+        method_definition = FlowMethodDefinition(do=_method_action(method))
     else:
-        method_definition = fragment.model_copy(deep=True)
+        method_definition = fragment.model_copy(
+            deep=True, update={"do": _method_action(method)}
+        )
 
     human_feedback = _build_human_feedback_definition(
         method, diagnostics, f"{path}.human_feedback"
@@ -386,9 +383,7 @@ def _build_method_definition(
             method_definition.router = True
             method_definition.emit = None
 
-    method_definition.persist = _build_persistence_definition(
-        method, diagnostics, f"{path}.persist"
-    )
+    method_definition.persist = _build_persistence_definition(method)
 
     return method_definition
 
@@ -472,7 +467,7 @@ def _build_flow_definition_from_class(
         description=description,
         state=_build_state_definition(flow_class, diagnostics),
         config=_build_config_definition(flow_class, diagnostics),
-        persist=_build_persistence_definition(flow_class, diagnostics, "persist"),
+        persist=_build_persistence_definition(flow_class),
         conversational=_build_conversational_definition(flow_class, diagnostics),
         methods=methods,
         diagnostics=diagnostics,

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

@@ -11,9 +11,17 @@ from __future__ import annotations
 
 import json
 import logging
+import re
 from typing import Any, Literal as TypingLiteral
 
-from pydantic import BaseModel, ConfigDict, Field
+from pydantic import (
+    BaseModel,
+    ConfigDict,
+    Field,
+    RootModel,
+    field_serializer,
+    model_validator,
+)
 import yaml
 
 from crewai.flow.conversational_definition import (
@@ -25,21 +33,36 @@ from crewai.flow.conversational_definition import (
 logger = logging.getLogger(__name__)
 
 FlowDefinitionCondition = str | dict[str, Any]
+_STEP_NAME_PATTERN = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*$")
 
 __all__ = [
+    "FlowActionDefinition",
+    "FlowCodeActionDefinition",
     "FlowConfigDefinition",
     "FlowConversationalDefinition",
     "FlowConversationalRouterDefinition",
     "FlowDefinition",
     "FlowDefinitionCondition",
     "FlowDefinitionDiagnostic",
+    "FlowEachActionDefinition",
+    "FlowEachInnerActionDefinition",
+    "FlowExpressionActionDefinition",
     "FlowHumanFeedbackDefinition",
     "FlowMethodDefinition",
     "FlowPersistenceDefinition",
     "FlowStateDefinition",
+    "FlowToolActionDefinition",
 ]
 
 
+def _object_ref(value: Any) -> str:
+    """Format a class or instance as the canonical ``module:qualname`` ref."""
+    target = value if isinstance(value, type) else type(value)
+    module = getattr(target, "__module__", "")
+    qualname = getattr(target, "__qualname__", getattr(target, "__name__", ""))
+    return f"{module}:{qualname}" if module and qualname else repr(value)
+
+
 class FlowDefinitionDiagnostic(BaseModel):
     """A non-fatal Flow Definition build or validation diagnostic."""
 
@@ -52,9 +75,10 @@ class FlowDefinitionDiagnostic(BaseModel):
 class FlowStateDefinition(BaseModel):
     """Static description of a Flow state contract."""
 
-    type: TypingLiteral["dict", "pydantic", "unknown"] = "dict"
+    type: TypingLiteral["dict", "pydantic", "json_schema", "unknown"] = "dict"
     ref: str | None = None
-    default: Any = None
+    json_schema: dict[str, Any] | None = None
+    default: dict[str, Any] | None = None
 
 
 class FlowConfigDefinition(BaseModel):
@@ -62,22 +86,50 @@ class FlowConfigDefinition(BaseModel):
 
     tracing: bool | None = None
     stream: bool = False
-    memory: Any = None
-    input_provider: Any = None
+    memory: dict[str, Any] | None = None
+    input_provider: str | None = None
     suppress_flow_events: bool = False
     max_method_calls: int = 100
+    defer_trace_finalization: bool = False
+    checkpoint: bool | dict[str, Any] | None = None
 
 
 class FlowPersistenceDefinition(BaseModel):
-    """Static persistence configuration."""
+    """Static persistence configuration.
+
+    ``persistence`` may hold a live backend when the definition is built from
+    a decorated class — the engine then persists through the exact instance
+    the user configured; the JSON/YAML projection degrades it to its
+    serialized config.
+    """
 
     enabled: bool = False
     verbose: bool = False
     persistence: Any = None
 
+    @field_serializer("persistence", when_used="json")
+    def _serialize_persistence(self, value: Any) -> Any:
+        if value is None or isinstance(value, dict):
+            return value
+        if isinstance(value, BaseModel):
+            try:
+                return value.model_dump(mode="json")
+            except Exception:
+                logger.warning(
+                    "Persistence backend %s is not fully serializable; "
+                    "preserved import reference only.",
+                    _object_ref(value),
+                )
+        return {"ref": _object_ref(value)}
+
 
 class FlowHumanFeedbackDefinition(BaseModel):
-    """Static human feedback configuration."""
+    """Static human feedback configuration.
+
+    ``llm`` and ``provider`` may hold live Python objects when the definition
+    is built from a decorated class; the JSON/YAML projection degrades them to
+    a serialized config (``llm``) or a ``module:qualname`` ref (``provider``).
+    """
 
     message: str
     emit: list[str] | None = None
@@ -89,10 +141,111 @@ class FlowHumanFeedbackDefinition(BaseModel):
     learn_source: str = "hitl"
     learn_strict: bool = False
 
+    @field_serializer("llm", when_used="json")
+    def _serialize_llm(self, value: Any) -> dict[str, Any] | str | None:
+        if value is None or isinstance(value, (str, dict)):
+            return value
+        from crewai.flow.human_feedback import _serialize_llm_for_context
+
+        return _serialize_llm_for_context(value)
+
+    @field_serializer("provider", when_used="json")
+    def _serialize_provider(self, value: Any) -> str | None:
+        if value is None or isinstance(value, str):
+            return value
+        return _object_ref(value)
+
+
+class FlowCodeActionDefinition(BaseModel):
+    """A Flow method action that executes importable Python code."""
+
+    model_config = ConfigDict(populate_by_name=True, extra="forbid")
+
+    call: TypingLiteral["code"] = "code"
+    ref: str
+    with_: dict[str, Any] | None = Field(default=None, alias="with")
+
+
+class FlowToolActionDefinition(BaseModel):
+    """A Flow method action that invokes a CrewAI tool."""
+
+    model_config = ConfigDict(populate_by_name=True, extra="forbid")
+
+    call: TypingLiteral["tool"]
+    ref: str
+    with_: dict[str, Any] | None = Field(default=None, alias="with")
+
+
+class FlowExpressionActionDefinition(BaseModel):
+    """A Flow method action that evaluates a CEL expression."""
+
+    model_config = ConfigDict(extra="forbid")
+
+    call: TypingLiteral["expression"]
+    expr: str
+
+
+FlowInnerActionDefinition = (
+    FlowCodeActionDefinition | FlowToolActionDefinition | FlowExpressionActionDefinition
+)
+
+
+class FlowEachInnerActionDefinition(RootModel[dict[str, FlowInnerActionDefinition]]):
+    """One named action inside an ``each`` composite action."""
+
+    @model_validator(mode="after")
+    def _validate_action_mapping(self) -> FlowEachInnerActionDefinition:
+        if len(self.root) != 1:
+            raise ValueError("each.do entries must be one-key mappings")
+        _validate_step_name(self.name, field="each.do action names")
+        return self
+
+    @property
+    def name(self) -> str:
+        return next(iter(self.root))
+
+    @property
+    def action(self) -> FlowInnerActionDefinition:
+        return next(iter(self.root.values()))
+
+
+class FlowEachActionDefinition(BaseModel):
+    """A composite action that runs a sequential mini-pipeline for each item."""
+
+    model_config = ConfigDict(populate_by_name=True, extra="forbid")
+
+    call: TypingLiteral["each"]
+    in_: str = Field(alias="in")
+    do: list[FlowEachInnerActionDefinition]
+
+    @model_validator(mode="after")
+    def _validate_inner_action_list(self) -> FlowEachActionDefinition:
+        if not self.do:
+            raise ValueError("each.do must contain at least one action")
+
+        seen: set[str] = set()
+        for inner_action in self.do:
+            name = inner_action.name
+            if name in seen:
+                raise ValueError(f"each.do action names must be unique: {name!r}")
+            seen.add(name)
+
+        return self
+
+
+FlowActionDefinition = (
+    FlowCodeActionDefinition
+    | FlowToolActionDefinition
+    | FlowExpressionActionDefinition
+    | FlowEachActionDefinition
+)
+
 
 class FlowMethodDefinition(BaseModel):
     """Static definition of one Flow method and its execution roles."""
 
+    description: str | None = None
+    do: FlowActionDefinition
     start: bool | FlowDefinitionCondition | None = None
     listen: FlowDefinitionCondition | None = None
     router: bool = False
@@ -100,6 +253,16 @@ class FlowMethodDefinition(BaseModel):
     human_feedback: FlowHumanFeedbackDefinition | None = None
     persist: FlowPersistenceDefinition | None = None
 
+    @model_validator(mode="after")
+    def _canonicalize_human_feedback_routing(self) -> FlowMethodDefinition:
+        # Canonical shape: a method whose human_feedback declares emit
+        # outcomes routes like a router, regardless of how the definition
+        # was authored.
+        if self.human_feedback is not None and self.human_feedback.emit:
+            self.router = True
+            self.emit = None
+        return self
+
     @property
     def is_start(self) -> bool:
         """Whether this method is a start method.
@@ -116,7 +279,9 @@ class FlowDefinition(BaseModel):
 
     model_config = ConfigDict(populate_by_name=True, arbitrary_types_allowed=True)
 
-    schema_: str = Field(default="crewai.flow/v1", alias="schema")
+    schema_: TypingLiteral["crewai.flow/v1"] = Field(
+        default="crewai.flow/v1", alias="schema"
+    )
     name: str
     description: str | None = None
     state: FlowStateDefinition | None = None
@@ -126,6 +291,12 @@ class FlowDefinition(BaseModel):
     methods: dict[str, FlowMethodDefinition] = Field(default_factory=dict)
     diagnostics: list[FlowDefinitionDiagnostic] = Field(default_factory=list)
 
+    @model_validator(mode="after")
+    def _validate_method_names(self) -> FlowDefinition:
+        for method_name in self.methods:
+            _validate_step_name(method_name, field="Flow method names")
+        return self
+
     def to_dict(self, *, exclude_none: bool = True) -> dict[str, Any]:
         """Serialize the definition to a JSON/YAML-ready dictionary."""
         return self.model_dump(by_alias=True, exclude_none=exclude_none, mode="json")
@@ -268,6 +439,11 @@ def _deserialize_diagnostics(value: Any) -> list[FlowDefinitionDiagnostic]:
     return [FlowDefinitionDiagnostic.model_validate(item) for item in value or []]
 
 
+def _validate_step_name(name: str, *, field: str) -> None:
+    if not isinstance(name, str) or not _STEP_NAME_PATTERN.fullmatch(name):
+        raise ValueError(f"{field} must match {_STEP_NAME_PATTERN.pattern}")
+
+
 def _merge_diagnostics(
     *diagnostic_groups: list[FlowDefinitionDiagnostic],
 ) -> list[FlowDefinitionDiagnostic]:

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

@@ -83,7 +83,6 @@ class FlowMethod(Generic[P, R]):
             "__conversational_only__",  # gates registration on Flow.conversational
             "__flow_persistence_config__",
             "__flow_method_definition__",
-            "_human_feedback_llm",  # Live LLM object for HITL resume
         ]:
             if hasattr(meth, attr):
                 setattr(self, attr, getattr(meth, attr))

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

@@ -1,8 +1,11 @@
-"""Human feedback decorator for Flow methods.
+"""Human feedback support for Flow methods.
 
-This module provides the @human_feedback decorator that enables human-in-the-loop
-workflows within CrewAI Flows. It allows collecting human feedback on method outputs
-and optionally routing to different listeners based on the feedback.
+This module backs the @human_feedback decorator that enables human-in-the-loop
+workflows within CrewAI Flows. The decorator is a pure metadata stamper: it
+records a :class:`HumanFeedbackConfig` on the method, the Flow definition
+builder lifts it into ``FlowHumanFeedbackDefinition``, and the Flow engine
+collects feedback after each decorated method completes, driven by the flow's
+definition.
 
 Supports both synchronous (blocking) and asynchronous (non-blocking) feedback
 collection through the provider parameter.
@@ -17,7 +20,7 @@ Example (synchronous, default):
         @human_feedback(
             message="Please review this content:",
             emit=["approved", "rejected"],
-            llm="gpt-4o-mini",
+            llm="gpt-5.4-mini",
         )
         def generate_content(self):
             return {"title": "Article", "body": "Content..."}
@@ -45,7 +48,7 @@ Example (asynchronous with custom provider):
         @human_feedback(
             message="Review this:",
             emit=["approved", "rejected"],
-            llm="gpt-4o-mini",
+            llm="gpt-5.4-mini",
             provider=SlackProvider(),
         )
         def generate_content(self):
@@ -55,22 +58,18 @@ Example (asynchronous with custom provider):
 
 from __future__ import annotations
 
-import asyncio
 from collections.abc import Callable, Sequence
 from dataclasses import dataclass, field
 from datetime import datetime
-from functools import wraps
 import logging
 from typing import TYPE_CHECKING, Any, TypeVar
 
 from pydantic import BaseModel, Field
 
-from crewai.flow.flow_wrappers import FlowMethod
-
 
 if TYPE_CHECKING:
     from crewai.flow.async_feedback.types import HumanFeedbackProvider
-    from crewai.flow.flow import Flow
+    from crewai.flow.runtime import Flow
     from crewai.llms.base_llm import BaseLLM
 
 
@@ -160,8 +159,8 @@ class HumanFeedbackResult:
 class HumanFeedbackConfig:
     """Configuration for the @human_feedback decorator.
 
-    Stores the parameters passed to the decorator for later use during
-    method execution and for introspection by visualization tools.
+    Stores the parameters passed to the decorator for later use by the
+    Flow definition builder and for introspection by visualization tools.
 
     Attributes:
         message: The message shown to the human when requesting feedback.
@@ -174,7 +173,7 @@ class HumanFeedbackConfig:
 
     message: str
     emit: Sequence[str] | None = None
-    llm: str | BaseLLM | None = "gpt-4o-mini"
+    llm: str | BaseLLM | None = "gpt-5.4-mini"
     default_outcome: str | None = None
     metadata: dict[str, Any] | None = None
     provider: HumanFeedbackProvider | None = None
@@ -183,19 +182,6 @@ class HumanFeedbackConfig:
     learn_strict: bool = False
 
 
-class HumanFeedbackMethod(FlowMethod[Any, Any]):
-    """Wrapper for methods decorated with @human_feedback.
-
-    This wrapper extends FlowMethod to add human feedback specific attributes
-    used by the FlowDefinition builder and runtime feedback handling.
-
-    Attributes:
-        __human_feedback_config__: The HumanFeedbackConfig for this method.
-    """
-
-    __human_feedback_config__: HumanFeedbackConfig | None = None
-
-
 class PreReviewResult(BaseModel):
     """Structured output from the HITL pre-review LLM call."""
 
@@ -217,22 +203,16 @@ class DistilledLessons(BaseModel):
     )
 
 
-def _build_human_feedback_runtime_decorator(
-    message: str,
-    emit: Sequence[str] | None = None,
-    llm: str | BaseLLM | None = "gpt-4o-mini",
-    default_outcome: str | None = None,
-    metadata: dict[str, Any] | None = None,
-    provider: HumanFeedbackProvider | None = None,
-    learn: bool = False,
-    learn_source: str = "hitl",
-    learn_strict: bool = False,
-) -> Callable[[F], F]:
+def _validate_human_feedback_options(
+    emit: Sequence[str] | None,
+    llm: Any,
+    default_outcome: str | None,
+) -> None:
     if emit is not None:
         if not llm:
             raise ValueError(
                 "llm is required when emit is specified. "
-                "Provide an LLM model string (e.g., 'gpt-4o-mini') or a BaseLLM instance. "
+                "Provide an LLM model string (e.g., 'gpt-5.4-mini') or a BaseLLM instance. "
                 "See the CrewAI Human-in-the-Loop (HITL) documentation for more information: "
                 "https://docs.crewai.com/en/learn/human-feedback-in-flows"
             )
@@ -244,301 +224,145 @@ def _build_human_feedback_runtime_decorator(
     elif default_outcome is not None:
         raise ValueError("default_outcome requires emit to be specified.")
 
-    def decorator(func: F) -> F:
-        def _get_hitl_prompt(key: str) -> str:
-            from crewai.utilities.i18n import I18N_DEFAULT
 
-            return I18N_DEFAULT.slice(key)
+def _get_hitl_prompt(key: str) -> str:
+    from crewai.utilities.i18n import I18N_DEFAULT
 
-        def _resolve_llm_instance() -> Any:
-            if llm is None:
-                from crewai.llm import LLM
+    return I18N_DEFAULT.slice(key)
 
-                return LLM(model="gpt-4o-mini")
-            if isinstance(llm, str):
-                from crewai.llm import LLM
 
-                return LLM(model=llm)
-            return llm  # already a BaseLLM instance
+def _resolve_llm_instance(llm: Any) -> Any:
+    from crewai.llm import LLM
 
-        def _pre_review_with_lessons(
-            flow_instance: Flow[Any], method_output: Any
-        ) -> Any:
-            try:
-                mem = flow_instance.memory
-                if mem is None:
-                    return method_output
-                query = f"human feedback lessons for {func.__name__}: {method_output!s}"
-                matches = mem.recall(query, source=learn_source)
-                if not matches:
-                    return method_output
+    if llm is None:
+        return LLM(model="gpt-5.4-mini")
+    if isinstance(llm, str):
+        return LLM(model=llm)
+    if isinstance(llm, dict):
+        deserialized = _deserialize_llm_from_context(llm)
+        return deserialized if deserialized is not None else LLM(model="gpt-5.4-mini")
+    return llm  # already a BaseLLM instance
 
-                lessons = "\n".join(f"- {m.record.content}" for m in matches)
-                llm_inst = _resolve_llm_instance()
-                prompt = _get_hitl_prompt("hitl_pre_review_user").format(
-                    output=str(method_output),
-                    lessons=lessons,
-                )
-                messages = [
-                    {
-                        "role": "system",
-                        "content": _get_hitl_prompt("hitl_pre_review_system"),
-                    },
-                    {"role": "user", "content": prompt},
-                ]
-                if getattr(llm_inst, "supports_function_calling", lambda: False)():
-                    response = llm_inst.call(messages, response_model=PreReviewResult)
-                    if isinstance(response, PreReviewResult):
-                        return response.improved_output
-                    return PreReviewResult.model_validate(response).improved_output
-                reviewed = llm_inst.call(messages)
-                return reviewed if isinstance(reviewed, str) else str(reviewed)
-            except Exception:
-                if learn_strict:
-                    logger.warning(
-                        "HITL pre-review failed for %s; re-raising (learn_strict=True)",
-                        func.__name__,
-                        exc_info=True,
-                    )
-                    raise
-                logger.warning(
-                    "HITL pre-review failed for %s; falling back to raw output",
-                    func.__name__,
-                    exc_info=True,
-                )
-                return method_output
 
-        def _distill_and_store_lessons(
-            flow_instance: Flow[Any], method_output: Any, raw_feedback: str
-        ) -> None:
-            try:
-                mem = flow_instance.memory
-                if mem is None:
-                    return
-                llm_inst = _resolve_llm_instance()
-                prompt = _get_hitl_prompt("hitl_distill_user").format(
-                    method_name=func.__name__,
-                    output=str(method_output),
-                    feedback=raw_feedback,
-                )
-                messages = [
-                    {
-                        "role": "system",
-                        "content": _get_hitl_prompt("hitl_distill_system"),
-                    },
-                    {"role": "user", "content": prompt},
-                ]
+def _pre_review_with_lessons(
+    flow_instance: Flow[Any],
+    method_name: str,
+    method_output: Any,
+    *,
+    llm: Any,
+    learn_source: str,
+    learn_strict: bool,
+) -> Any:
+    try:
+        mem = flow_instance.memory
+        if mem is None:
+            return method_output
+        query = f"human feedback lessons for {method_name}: {method_output!s}"
+        matches = mem.recall(query, source=learn_source)
+        if not matches:
+            return method_output
 
-                lessons: list[str] = []
-                if getattr(llm_inst, "supports_function_calling", lambda: False)():
-                    response = llm_inst.call(messages, response_model=DistilledLessons)
-                    if isinstance(response, DistilledLessons):
-                        lessons = response.lessons
-                    else:
-                        lessons = DistilledLessons.model_validate(response).lessons
-                else:
-                    response = llm_inst.call(messages)
-                    if isinstance(response, str):
-                        lessons = [
-                            line.strip("- ").strip()
-                            for line in response.strip().split("\n")
-                            if line.strip() and line.strip() != "NONE"
-                        ]
-
-                if lessons:
-                    mem.remember_many(lessons, source=learn_source)  # type: ignore[union-attr]
-            except Exception:
-                if learn_strict:
-                    logger.warning(
-                        "HITL lesson distillation failed for %s; re-raising (learn_strict=True)",
-                        func.__name__,
-                        exc_info=True,
-                    )
-                    raise
-                logger.warning(
-                    "HITL lesson distillation failed for %s; no lessons stored",
-                    func.__name__,
-                    exc_info=True,
-                )
-
-        def _build_feedback_context(
-            flow_instance: Flow[Any], method_output: Any
-        ) -> tuple[Any, Any]:
-            from crewai.flow.async_feedback.types import PendingFeedbackContext
-
-            context = PendingFeedbackContext(
-                flow_id=flow_instance.flow_id or "unknown",
-                flow_class=f"{flow_instance.__class__.__module__}.{flow_instance.__class__.__name__}",
-                method_name=func.__name__,
-                method_output=method_output,
-                message=message,
-                emit=list(emit) if emit else None,
-                default_outcome=default_outcome,
-                metadata=metadata or {},
-                llm=llm if isinstance(llm, str) else _serialize_llm_for_context(llm),
+        lessons = "\n".join(f"- {m.record.content}" for m in matches)
+        llm_inst = _resolve_llm_instance(llm)
+        prompt = _get_hitl_prompt("hitl_pre_review_user").format(
+            output=str(method_output),
+            lessons=lessons,
+        )
+        messages = [
+            {
+                "role": "system",
+                "content": _get_hitl_prompt("hitl_pre_review_system"),
+            },
+            {"role": "user", "content": prompt},
+        ]
+        if getattr(llm_inst, "supports_function_calling", lambda: False)():
+            response = llm_inst.call(messages, response_model=PreReviewResult)
+            if isinstance(response, PreReviewResult):
+                return response.improved_output
+            return PreReviewResult.model_validate(response).improved_output
+        reviewed = llm_inst.call(messages)
+        return reviewed if isinstance(reviewed, str) else str(reviewed)
+    except Exception:
+        if learn_strict:
+            logger.warning(
+                "HITL pre-review failed for %s; re-raising (learn_strict=True)",
+                method_name,
+                exc_info=True,
             )
+            raise
+        logger.warning(
+            "HITL pre-review failed for %s; falling back to raw output",
+            method_name,
+            exc_info=True,
+        )
+        return method_output
 
-            effective_provider = provider
-            if effective_provider is None:
-                from crewai.flow.flow_config import flow_config
 
-                effective_provider = flow_config.hitl_provider
+def _distill_and_store_lessons(
+    flow_instance: Flow[Any],
+    method_name: str,
+    method_output: Any,
+    raw_feedback: str,
+    *,
+    llm: Any,
+    learn_source: str,
+    learn_strict: bool,
+) -> None:
+    try:
+        mem = flow_instance.memory
+        if mem is None:
+            return
+        llm_inst = _resolve_llm_instance(llm)
+        prompt = _get_hitl_prompt("hitl_distill_user").format(
+            method_name=method_name,
+            output=str(method_output),
+            feedback=raw_feedback,
+        )
+        messages = [
+            {
+                "role": "system",
+                "content": _get_hitl_prompt("hitl_distill_system"),
+            },
+            {"role": "user", "content": prompt},
+        ]
 
-            return context, effective_provider
-
-        def _request_feedback(flow_instance: Flow[Any], method_output: Any) -> str:
-            context, effective_provider = _build_feedback_context(
-                flow_instance, method_output
-            )
-
-            if effective_provider is not None:
-                feedback_result = effective_provider.request_feedback(
-                    context, flow_instance
-                )
-                if asyncio.iscoroutine(feedback_result):
-                    raise TypeError(
-                        f"Provider {type(effective_provider).__name__}.request_feedback() "
-                        "returned a coroutine in a sync flow method. Use an async flow "
-                        "method or a synchronous provider."
-                    )
-                return str(feedback_result)
-            return flow_instance._request_human_feedback(
-                message=message,
-                output=method_output,
-                metadata=metadata,
-                emit=emit,
-            )
-
-        async def _request_feedback_async(
-            flow_instance: Flow[Any], method_output: Any
-        ) -> str:
-            context, effective_provider = _build_feedback_context(
-                flow_instance, method_output
-            )
-
-            if effective_provider is not None:
-                feedback_result = effective_provider.request_feedback(
-                    context, flow_instance
-                )
-                if asyncio.iscoroutine(feedback_result):
-                    return str(await feedback_result)
-                return str(feedback_result)
-            return flow_instance._request_human_feedback(
-                message=message,
-                output=method_output,
-                metadata=metadata,
-                emit=emit,
-            )
-
-        def _process_feedback(
-            flow_instance: Flow[Any],
-            method_output: Any,
-            raw_feedback: str,
-        ) -> HumanFeedbackResult | str:
-            collapsed_outcome: str | None = None
-
-            if not raw_feedback.strip():
-                if default_outcome:
-                    collapsed_outcome = default_outcome
-                elif emit:
-                    collapsed_outcome = emit[0]
-            elif emit:
-                if llm is not None:
-                    collapsed_outcome = flow_instance._collapse_to_outcome(
-                        feedback=raw_feedback,
-                        outcomes=emit,
-                        llm=llm,
-                    )
-                else:
-                    collapsed_outcome = emit[0]
-
-            result = HumanFeedbackResult(
-                output=method_output,
-                feedback=raw_feedback,
-                outcome=collapsed_outcome,
-                timestamp=datetime.now(),
-                method_name=func.__name__,
-                metadata=metadata or {},
-            )
-
-            flow_instance.human_feedback_history.append(result)
-            flow_instance.last_human_feedback = result
-
-            if emit:
-                if collapsed_outcome is None:
-                    collapsed_outcome = default_outcome or emit[0]
-                    result.outcome = collapsed_outcome
-                return collapsed_outcome
-            return result
-
-        if asyncio.iscoroutinefunction(func):
-
-            @wraps(func)
-            async def async_wrapper(self: Flow[Any], *args: Any, **kwargs: Any) -> Any:
-                method_output = await func(self, *args, **kwargs)
-
-                if learn and getattr(self, "memory", None) is not None:
-                    method_output = _pre_review_with_lessons(self, method_output)
-
-                raw_feedback = await _request_feedback_async(self, method_output)
-                result = _process_feedback(self, method_output, raw_feedback)
-
-                if (
-                    learn
-                    and getattr(self, "memory", None) is not None
-                    and raw_feedback.strip()
-                ):
-                    _distill_and_store_lessons(self, method_output, raw_feedback)
-
-                # Stash the real method output for final flow result when emit is set:
-                # result is the collapsed outcome string for routing, but we preserve the
-                # actual method output as the flow's final result. Uses per-method dict for
-                # concurrency safety and to handle None returns.
-                if emit:
-                    self._human_feedback_method_outputs[func.__name__] = method_output
-
-                return result
-
-            wrapper: Any = async_wrapper
+        lessons: list[str] = []
+        if getattr(llm_inst, "supports_function_calling", lambda: False)():
+            response = llm_inst.call(messages, response_model=DistilledLessons)
+            if isinstance(response, DistilledLessons):
+                lessons = response.lessons
+            else:
+                lessons = DistilledLessons.model_validate(response).lessons
         else:
+            response = llm_inst.call(messages)
+            if isinstance(response, str):
+                lessons = [
+                    line.strip("- ").strip()
+                    for line in response.strip().split("\n")
+                    if line.strip() and line.strip() != "NONE"
+                ]
 
-            @wraps(func)
-            def sync_wrapper(self: Flow[Any], *args: Any, **kwargs: Any) -> Any:
-                method_output = func(self, *args, **kwargs)
-
-                if learn and getattr(self, "memory", None) is not None:
-                    method_output = _pre_review_with_lessons(self, method_output)
-
-                raw_feedback = _request_feedback(self, method_output)
-                result = _process_feedback(self, method_output, raw_feedback)
-
-                if (
-                    learn
-                    and getattr(self, "memory", None) is not None
-                    and raw_feedback.strip()
-                ):
-                    _distill_and_store_lessons(self, method_output, raw_feedback)
-
-                # Stash the real method output for final flow result when emit is set:
-                # result is the collapsed outcome string for routing, but we preserve the
-                # actual method output as the flow's final result. Uses per-method dict for
-                # concurrency safety and to handle None returns.
-                if emit:
-                    self._human_feedback_method_outputs[func.__name__] = method_output
-
-                return result
-
-            wrapper = sync_wrapper
-
-        return wrapper  # type: ignore[no-any-return]
-
-    return decorator
+        if lessons:
+            mem.remember_many(lessons, source=learn_source)  # type: ignore[union-attr]
+    except Exception:
+        if learn_strict:
+            logger.warning(
+                "HITL lesson distillation failed for %s; re-raising (learn_strict=True)",
+                method_name,
+                exc_info=True,
+            )
+            raise
+        logger.warning(
+            "HITL lesson distillation failed for %s; no lessons stored",
+            method_name,
+            exc_info=True,
+        )
 
 
 def human_feedback(
     message: str,
     emit: Sequence[str] | None = None,
-    llm: str | BaseLLM | None = "gpt-4o-mini",
+    llm: str | BaseLLM | None = "gpt-5.4-mini",
     default_outcome: str | None = None,
     metadata: dict[str, Any] | None = None,
     provider: HumanFeedbackProvider | None = None,

lib/crewai/src/crewai/flow/persistence/decorators.py

@@ -24,12 +24,10 @@ Example:
 
 from __future__ import annotations
 
-import asyncio
 from collections.abc import Callable
-import functools
 import logging
 from types import SimpleNamespace
-from typing import TYPE_CHECKING, Any, Final, TypeVar, cast
+from typing import TYPE_CHECKING, Any, Final, TypeVar
 
 from crewai_core.printer import PRINTER
 from pydantic import BaseModel
@@ -39,7 +37,7 @@ from crewai.flow.persistence.factory import default_flow_persistence
 
 
 if TYPE_CHECKING:
-    from crewai.flow.flow import Flow
+    from crewai.flow.runtime import Flow
 
 
 logger = logging.getLogger(__name__)
@@ -66,14 +64,6 @@ def _stamp_persistence_metadata(
     )
 
 
-_PRESERVED_FLOW_ATTRS: Final[tuple[str, ...]] = (
-    "__human_feedback_config__",
-    "__flow_persistence_config__",
-    "__flow_method_definition__",
-    "_human_feedback_llm",
-)
-
-
 class PersistenceDecorator:
     """Class to handle flow state persistence with consistent logging."""
 
@@ -164,6 +154,10 @@ def persist(
     states. When applied at the method level, it persists only that method's
     state.
 
+    The decorator is a pure metadata stamper: it records the persistence
+    configuration on the class or method, and the Flow engine saves state
+    after each persisted method completes, driven by the flow's definition.
+
     Args:
         persistence: Optional FlowPersistence implementation to use.
                     If not provided, uses ``default_flow_persistence()`` (the
@@ -191,122 +185,7 @@ def persist(
             persistence if persistence is not None else default_flow_persistence()
         )
 
-        if isinstance(target, type):
-            _stamp_persistence_metadata(target, actual_persistence, verbose)
-            original_init = target.__init__  # type: ignore[misc]
-
-            @functools.wraps(original_init)
-            def new_init(self: Any, *args: Any, **kwargs: Any) -> None:
-                if "persistence" not in kwargs:
-                    kwargs["persistence"] = actual_persistence
-                original_init(self, *args, **kwargs)
-
-            target.__init__ = new_init  # type: ignore[misc]
-
-            # Preserve original methods' decorators
-            original_methods = {
-                name: method
-                for name, method in target.__dict__.items()
-                if callable(method)
-                and (
-                    hasattr(method, "__is_flow_method__")
-                    or hasattr(method, "__flow_method_definition__")
-                )
-            }
-
-            for name, method in original_methods.items():
-                if asyncio.iscoroutinefunction(method):
-                    # Closure captures the current name and method
-                    def create_async_wrapper(
-                        method_name: str, original_method: Callable[..., Any]
-                    ) -> Callable[..., Any]:
-                        @functools.wraps(original_method)
-                        async def method_wrapper(
-                            self: Any, *args: Any, **kwargs: Any
-                        ) -> Any:
-                            result = await original_method(self, *args, **kwargs)
-                            PersistenceDecorator.persist_state(
-                                self, method_name, actual_persistence, verbose
-                            )
-                            return result
-
-                        return method_wrapper
-
-                    wrapped = create_async_wrapper(name, method)
-
-                    for attr in _PRESERVED_FLOW_ATTRS:
-                        if hasattr(method, attr):
-                            setattr(wrapped, attr, getattr(method, attr))
-                    wrapped.__is_flow_method__ = True  # type: ignore[attr-defined]
-
-                    setattr(target, name, wrapped)
-                else:
-
-                    def create_sync_wrapper(
-                        method_name: str, original_method: Callable[..., Any]
-                    ) -> Callable[..., Any]:
-                        @functools.wraps(original_method)
-                        def method_wrapper(self: Any, *args: Any, **kwargs: Any) -> Any:
-                            result = original_method(self, *args, **kwargs)
-                            PersistenceDecorator.persist_state(
-                                self, method_name, actual_persistence, verbose
-                            )
-                            return result
-
-                        return method_wrapper
-
-                    wrapped = create_sync_wrapper(name, method)
-
-                    for attr in _PRESERVED_FLOW_ATTRS:
-                        if hasattr(method, attr):
-                            setattr(wrapped, attr, getattr(method, attr))
-                    wrapped.__is_flow_method__ = True  # type: ignore[attr-defined]
-
-                    setattr(target, name, wrapped)
-
-            return target
-        method = target
-        method.__is_flow_method__ = True  # type: ignore[attr-defined]
-        _stamp_persistence_metadata(method, actual_persistence, verbose)
-
-        if asyncio.iscoroutinefunction(method):
-
-            @functools.wraps(method)
-            async def method_async_wrapper(
-                flow_instance: Any, *args: Any, **kwargs: Any
-            ) -> T:
-                method_coro = method(flow_instance, *args, **kwargs)
-                if asyncio.iscoroutine(method_coro):
-                    result = await method_coro
-                else:
-                    result = method_coro
-                PersistenceDecorator.persist_state(
-                    flow_instance, method.__name__, actual_persistence, verbose
-                )
-                return cast(T, result)
-
-            for attr in _PRESERVED_FLOW_ATTRS:
-                if hasattr(method, attr):
-                    setattr(method_async_wrapper, attr, getattr(method, attr))
-            method_async_wrapper.__is_flow_method__ = True  # type: ignore[attr-defined]
-            _stamp_persistence_metadata(
-                method_async_wrapper, actual_persistence, verbose
-            )
-            return cast(Callable[..., T], method_async_wrapper)
-
-        @functools.wraps(method)
-        def method_sync_wrapper(flow_instance: Any, *args: Any, **kwargs: Any) -> T:
-            result = method(flow_instance, *args, **kwargs)
-            PersistenceDecorator.persist_state(
-                flow_instance, method.__name__, actual_persistence, verbose
-            )
-            return result
-
-        for attr in _PRESERVED_FLOW_ATTRS:
-            if hasattr(method, attr):
-                setattr(method_sync_wrapper, attr, getattr(method, attr))
-        method_sync_wrapper.__is_flow_method__ = True  # type: ignore[attr-defined]
-        _stamp_persistence_metadata(method_sync_wrapper, actual_persistence, verbose)
-        return cast(Callable[..., T], method_sync_wrapper)
+        _stamp_persistence_metadata(target, actual_persistence, verbose)
+        return target
 
     return decorator

lib/crewai/src/crewai/flow/runtime/_actions.py

@@ -0,0 +1,221 @@
+"""Build FlowDefinition actions into live runtime callables."""
+
+from __future__ import annotations
+
+import asyncio
+from collections.abc import Callable
+import contextvars
+import inspect
+from typing import TYPE_CHECKING, Any, Protocol, cast
+
+from crewai.flow.flow_definition import (
+    FlowActionDefinition,
+    FlowCodeActionDefinition,
+    FlowEachActionDefinition,
+    FlowEachInnerActionDefinition,
+    FlowExpressionActionDefinition,
+    FlowToolActionDefinition,
+)
+from crewai.flow.runtime._expressions import evaluate_expression, render_with_block
+from crewai.flow.runtime._refs import InvalidRefError, resolve_ref
+
+
+if TYPE_CHECKING:
+    from crewai.flow.runtime import Flow
+
+
+__all__ = ["build_action"]
+
+LocalContext = dict[str, Any]
+_LOCAL_CONTEXT_KWARG = "__flow_definition_local_context"
+
+
+class _BuiltAction(Protocol):
+    def run(self, *args: Any, **kwargs: Any) -> Any: ...
+
+
+class _ActionType(Protocol):
+    definition_type: type[Any]
+
+    def __call__(self, flow: Flow[Any], definition: Any) -> _BuiltAction: ...
+
+
+class CodeAction:
+    definition_type = FlowCodeActionDefinition
+
+    def __init__(self, flow: Flow[Any], definition: FlowCodeActionDefinition) -> None:
+        self.flow = flow
+        self.definition = definition
+        self.handler = self._resolve_handler()
+        self.signature = inspect.signature(self.handler)
+
+    def run(self, *args: Any, **kwargs: Any) -> Any:
+        local_context = _pop_local_context(kwargs)
+        if self.definition.with_ is None:
+            return self.handler(*args, **kwargs)
+        return self.handler(
+            **render_with_block(
+                self.flow, self.definition.with_, local_context=local_context
+            )
+        )
+
+    def _resolve_handler(self) -> Callable[..., Any]:
+        ref = self.definition.ref
+        target = resolve_ref(ref, field="do")
+        if not callable(target):
+            raise InvalidRefError(f"invalid do ref {ref!r}; object is not callable")
+        handler = cast(Callable[..., Any], target)
+        if getattr(handler, "__self__", None) is None and hasattr(handler, "__get__"):
+            handler = handler.__get__(self.flow, type(self.flow))
+        return handler
+
+
+class ToolAction:
+    definition_type = FlowToolActionDefinition
+
+    def __init__(self, flow: Flow[Any], definition: FlowToolActionDefinition) -> None:
+        self.flow = flow
+        self.definition = definition
+        self.tool = self._build_tool()
+        self.kwargs = definition.with_ or {}
+
+    def run(self, *_args: Any, **kwargs: Any) -> Any:
+        local_context = _pop_local_context(kwargs)
+        return self.tool.run(
+            **render_with_block(self.flow, self.kwargs, local_context=local_context)
+        )
+
+    def _build_tool(self) -> Any:
+        target = resolve_ref(self.definition.ref, field="do")
+        from crewai.tools import BaseTool
+
+        if not (inspect.isclass(target) and issubclass(target, BaseTool)):
+            raise InvalidRefError(
+                f"invalid tool ref {self.definition.ref!r}; expected a BaseTool class"
+            )
+
+        try:
+            tool_cls = cast(Callable[[], BaseTool], target)
+            return tool_cls()
+        except Exception as e:
+            raise InvalidRefError(
+                f"cannot instantiate tool ref {self.definition.ref!r} "
+                f"without arguments: {e}"
+            ) from e
+
+
+class ExpressionAction:
+    definition_type = FlowExpressionActionDefinition
+
+    def __init__(
+        self, flow: Flow[Any], definition: FlowExpressionActionDefinition
+    ) -> None:
+        self.flow = flow
+        self.definition = definition
+
+    def run(self, *_args: Any, **kwargs: Any) -> Any:
+        local_context = _pop_local_context(kwargs)
+        return evaluate_expression(
+            self.flow, self.definition.expr, local_context=local_context
+        )
+
+
+class EachAction:
+    definition_type = FlowEachActionDefinition
+
+    def __init__(self, flow: Flow[Any], definition: FlowEachActionDefinition) -> None:
+        self.flow = flow
+        self.definition = definition
+        self.inner_actions = [
+            (inner_action.name, self._build_inner_action(inner_action))
+            for inner_action in definition.do
+        ]
+
+    async def run(self, *_args: Any, **_kwargs: Any) -> list[Any]:
+        items = evaluate_expression(self.flow, self.definition.in_)
+        if not isinstance(items, list):
+            raise ValueError("each.in must evaluate to an array")
+
+        results: list[Any] = []
+
+        for item in items:
+            local_outputs: dict[str, Any] = {}
+            last_output: Any = None
+            for name, run_inner_action in self.inner_actions:
+                last_output = await run_inner_action(
+                    {"item": item, "outputs": local_outputs}
+                )
+                local_outputs[name] = last_output
+            results.append(last_output)
+
+        return results
+
+    def _build_inner_action(
+        self, inner_action: FlowEachInnerActionDefinition
+    ) -> Callable[[LocalContext], Any]:
+        run_action = build_action(self.flow, inner_action.action)
+
+        async def run_inner_action(local_context: LocalContext) -> Any:
+            kwargs = {_LOCAL_CONTEXT_KWARG: local_context}
+            if inspect.iscoroutinefunction(run_action):
+                result = run_action(**kwargs)
+            else:
+                ctx = contextvars.copy_context()
+
+                def run_with_context() -> Any:
+                    return run_action(**kwargs)
+
+                result = await asyncio.to_thread(ctx.run, run_with_context)
+            if inspect.isawaitable(result):
+                result = await result
+            return result
+
+        return run_inner_action
+
+
+_ACTION_TYPES: tuple[_ActionType, ...] = (
+    EachAction,
+    CodeAction,
+    ToolAction,
+    ExpressionAction,
+)
+
+
+def build_action(
+    flow: Flow[Any], definition: FlowActionDefinition
+) -> Callable[..., Any]:
+    """Turn one `do:` action into the callable the flow runs for that node."""
+    for action_type in _ACTION_TYPES:
+        if isinstance(definition, action_type.definition_type):
+            return _as_flow_method(action_type(flow, definition))
+    raise ValueError(f"unknown call type {getattr(definition, 'call', None)!r}")
+
+
+def _as_flow_method(action: _BuiltAction) -> Callable[..., Any]:
+    run: Callable[..., Any]
+    if inspect.iscoroutinefunction(action.run):
+
+        async def run_async(*args: Any, **kwargs: Any) -> Any:
+            return await action.run(*args, **kwargs)
+
+        run = run_async
+    else:
+
+        def run_sync(*args: Any, **kwargs: Any) -> Any:
+            return action.run(*args, **kwargs)
+
+        run = run_sync
+
+    signature = getattr(action, "signature", None)
+    if signature is not None:
+        object.__setattr__(run, "__signature__", signature)
+    return run
+
+
+def _pop_local_context(kwargs: dict[str, Any]) -> LocalContext | None:
+    local_context = kwargs.pop(_LOCAL_CONTEXT_KWARG, None)
+    if local_context is None:
+        return None
+    if not isinstance(local_context, dict):
+        raise TypeError("flow definition local context must be a mapping")
+    return cast(LocalContext, local_context)

lib/crewai/src/crewai/flow/runtime/_expressions.py

@@ -0,0 +1,157 @@
+"""Runtime expression support for FlowDefinition CEL expressions."""
+
+from __future__ import annotations
+
+from itertools import pairwise
+import json
+import re
+from typing import TYPE_CHECKING, Any, cast
+
+from crewai.utilities.serialization import to_serializable
+
+
+if TYPE_CHECKING:
+    from crewai.flow.runtime import Flow
+
+
+_EXPRESSION_PATTERN = re.compile(r"\$\{([^{}]*)\}")
+
+__all__ = ["FlowExpressionError", "evaluate_expression", "render_with_block"]
+
+
+class FlowExpressionError(ValueError):
+    """A FlowDefinition expression failed to parse or evaluate."""
+
+
+def render_with_block(
+    flow: Flow[Any], value: Any, local_context: dict[str, Any] | None = None
+) -> Any:
+    """Render CEL expressions inside a FlowDefinition ``with:`` payload."""
+    context = _expression_context(flow, local_context=local_context)
+    return _render_value(value, context)
+
+
+def evaluate_expression(
+    flow: Flow[Any], expression: str, local_context: dict[str, Any] | None = None
+) -> Any:
+    """Evaluate a FlowDefinition CEL expression against runtime context."""
+    expression = expression.strip()
+    if not expression:
+        raise FlowExpressionError("empty CEL expression")
+    return _eval_cel(expression, _expression_context(flow, local_context=local_context))
+
+
+def _expression_context(
+    flow: Flow[Any], local_context: dict[str, Any] | None = None
+) -> dict[str, Any]:
+    outputs = _outputs_by_name(flow._method_outputs)
+    context: dict[str, Any] = {
+        "state": flow._copy_and_serialize_state(),
+        "outputs": outputs,
+    }
+    if local_context:
+        local_values = {
+            key: to_serializable(value, max_depth=0)
+            for key, value in local_context.items()
+        }
+        local_outputs = local_values.pop("outputs", None)
+        local_values.pop("state", None)
+        context.update(local_values)
+        if local_outputs is not None:
+            if not isinstance(local_outputs, dict):
+                raise TypeError("flow definition local outputs must be a mapping")
+            context["outputs"] = {**outputs, **local_outputs}
+    return context
+
+
+def _outputs_by_name(method_outputs: list[Any]) -> dict[str, Any]:
+    outputs: dict[str, Any] = {}
+    for entry in method_outputs:
+        method = ""
+        output = entry
+        if isinstance(entry, dict) and "output" in entry:
+            method = str(entry.get("method", ""))
+            output = entry["output"]
+        outputs[method] = to_serializable(output, max_depth=0)
+    return outputs
+
+
+def _render_value(value: Any, context: dict[str, Any]) -> Any:
+    if isinstance(value, str):
+        return _render_string(value, context)
+    if isinstance(value, dict):
+        return {key: _render_value(item, context) for key, item in value.items()}
+    if isinstance(value, list):
+        return [_render_value(item, context) for item in value]
+    return value
+
+
+def _render_string(value: str, context: dict[str, Any]) -> Any:
+    matches = list(_EXPRESSION_PATTERN.finditer(value))
+    if not matches:
+        _raise_for_invalid_interpolation(value)
+        return value
+
+    _raise_for_literal_braces(value[: matches[0].start()])
+    for previous, current in pairwise(matches):
+        _raise_for_literal_braces(value[previous.end() : current.start()])
+    _raise_for_literal_braces(value[matches[-1].end() :])
+
+    if len(matches) == 1 and matches[0].span() == (0, len(value)):
+        expression = matches[0].group(1).strip()
+        if not expression:
+            raise FlowExpressionError("empty CEL expression in with block")
+        return _eval_cel(expression, context)
+
+    rendered: list[str] = []
+    position = 0
+    for match in matches:
+        start, end = match.span()
+        literal = value[position:start]
+        rendered.append(literal)
+
+        expression = match.group(1).strip()
+        if not expression:
+            raise FlowExpressionError("empty CEL expression in with block")
+        result = _eval_cel(expression, context)
+        rendered.append(result if isinstance(result, str) else json.dumps(result))
+        position = end
+
+    literal = value[position:]
+    rendered.append(literal)
+
+    return "".join(rendered)
+
+
+def _raise_for_invalid_interpolation(value: str) -> None:
+    if "${" not in value:
+        return
+    raise FlowExpressionError(
+        "invalid CEL interpolation in with block: expressions must be enclosed "
+        "as ${...} and cannot contain braces"
+    )
+
+
+def _raise_for_literal_braces(value: str) -> None:
+    if "{" not in value and "}" not in value:
+        return
+    raise FlowExpressionError(
+        "invalid CEL interpolation in with block: expressions must be enclosed "
+        "as ${...} and cannot contain braces"
+    )
+
+
+def _eval_cel(expression: str, context: dict[str, Any]) -> Any:
+    try:
+        from celpy import Environment
+        from celpy.adapter import CELJSONEncoder, json_to_cel
+        from celpy.evaluation import Context
+
+        environment = Environment()
+        program = environment.program(environment.compile(expression))
+        result = program.evaluate(cast(Context, json_to_cel(context)))
+        return json.loads(json.dumps(result, cls=CELJSONEncoder))
+    except Exception as e:
+        raise FlowExpressionError(
+            f"failed to evaluate CEL expression {expression!r}: {e}"
+        ) from e

lib/crewai/src/crewai/flow/runtime/_refs.py

@@ -0,0 +1,38 @@
+"""Resolution of ``module:qualname`` refs into live Python objects."""
+
+from __future__ import annotations
+
+import importlib
+import inspect
+from operator import attrgetter
+from typing import Any
+
+
+class InvalidRefError(ValueError):
+    """A definition ref that cannot be resolved to a live object."""
+
+
+def resolve_ref(ref: str, *, field: str) -> Any:
+    """Import the object a definition's `module:qualname` ref points to."""
+    module_name, _, qualname = ref.partition(":")
+    if "<" in ref or not module_name or not qualname:
+        raise InvalidRefError(
+            f"invalid {field} ref {ref!r}; expected 'module:qualname'"
+        )
+    try:
+        return attrgetter(qualname)(importlib.import_module(module_name))
+    except (ImportError, AttributeError) as e:
+        raise InvalidRefError(f"unresolvable {field} ref {ref!r}") from e
+
+
+def resolve_instance_ref(ref: str, *, field: str) -> Any:
+    """Resolve a ref, auto-instantiating a no-arg class into an instance."""
+    target = resolve_ref(ref, field=field)
+    if not inspect.isclass(target):
+        return target
+    try:
+        return target()
+    except Exception as e:
+        raise InvalidRefError(
+            f"cannot instantiate {field} ref {ref!r} without arguments: {e}"
+        ) from e

lib/crewai/src/crewai/lite_agent.py

@@ -390,7 +390,10 @@ class LiteAgent(FlowTrackable, BaseModel):
         if self.memory is True:
             from crewai.memory.unified_memory import Memory
 
-            object.__setattr__(self, "_memory", Memory())
+            memory_kwargs: dict[str, Any] = {}
+            if self.llm is not None:
+                memory_kwargs["llm"] = self.llm
+            object.__setattr__(self, "_memory", Memory(**memory_kwargs))
         elif self.memory is not None and self.memory is not False:
             object.__setattr__(self, "_memory", self.memory)
         else:

lib/crewai/src/crewai/llm.py

@@ -68,7 +68,17 @@ if TYPE_CHECKING:
     from crewai.tools.base_tool import BaseTool
     from crewai.utilities.types import LLMMessage
 
-try:
+load_dotenv()
+logger = logging.getLogger(__name__)
+
+# litellm is lazy-loaded to avoid its module-level dotenv.load_dotenv()
+# from polluting env vars (e.g. MODEL= overriding embedder model_name).
+# The TYPE_CHECKING imports give mypy the real types; at runtime the names
+# stay None until _ensure_litellm() rebinds them.
+_litellm_loaded = False
+LITELLM_AVAILABLE = False
+
+if TYPE_CHECKING:
     import litellm
     from litellm.litellm_core_utils.get_supported_openai_params import (
         get_supported_openai_params,
@@ -85,28 +95,70 @@ try:
         StreamingChoices as LiteLLMStreamingChoices,
     )
     from litellm.utils import supports_response_schema
-
-    LITELLM_AVAILABLE = True
-except ImportError:
-    LITELLM_AVAILABLE = False
-    litellm = None  # type: ignore[assignment]
-    Choices = None  # type: ignore[assignment, misc]
-    LiteLLMDelta = None  # type: ignore[assignment, misc]
-    Message = None  # type: ignore[assignment, misc]
-    ModelResponseBase = None  # type: ignore[assignment, misc]
-    ModelResponseStream = None  # type: ignore[assignment, misc]
-    LiteLLMStreamingChoices = None  # type: ignore[assignment, misc]
-    get_supported_openai_params = None  # type: ignore[assignment]
-    ChatCompletionDeltaToolCall = None  # type: ignore[assignment, misc]
-    Function = None  # type: ignore[assignment, misc]
-    ModelResponse = None  # type: ignore[assignment, misc]
-    supports_response_schema = None  # type: ignore[assignment]
+else:
+    litellm = None
+    Choices = None
+    LiteLLMDelta = None
+    Message = None
+    ModelResponseBase = None
+    ModelResponseStream = None
+    LiteLLMStreamingChoices = None
+    get_supported_openai_params = None
+    ChatCompletionDeltaToolCall = None
+    Function = None
+    ModelResponse = None
+    supports_response_schema = None
 
 
-load_dotenv()
-logger = logging.getLogger(__name__)
-if LITELLM_AVAILABLE:
-    litellm.suppress_debug_info = True
+def _ensure_litellm() -> bool:
+    """Lazy-load litellm on first use. Returns True if available."""
+    global _litellm_loaded, LITELLM_AVAILABLE
+    global litellm, Choices, LiteLLMDelta, Message, ModelResponseBase
+    global ModelResponseStream, LiteLLMStreamingChoices, get_supported_openai_params
+    global ChatCompletionDeltaToolCall, Function
+    global ModelResponse, supports_response_schema
+
+    if _litellm_loaded:
+        return LITELLM_AVAILABLE
+    _litellm_loaded = True
+
+    try:
+        import litellm as _litellm
+        from litellm.litellm_core_utils.get_supported_openai_params import (
+            get_supported_openai_params as _get_supported_openai_params,
+        )
+        from litellm.types.utils import (
+            ChatCompletionDeltaToolCall as _ChatCompletionDeltaToolCall,
+            Choices as _Choices,
+            Delta as _LiteLLMDelta,
+            Function as _Function,
+            Message as _Message,
+            ModelResponse as _ModelResponse,
+            ModelResponseBase as _ModelResponseBase,
+            ModelResponseStream as _ModelResponseStream,
+            StreamingChoices as _LiteLLMStreamingChoices,
+        )
+        from litellm.utils import supports_response_schema as _supports_response_schema
+
+        litellm = _litellm
+        Choices = _Choices  # type: ignore[misc]
+        LiteLLMDelta = _LiteLLMDelta  # type: ignore[misc]
+        Message = _Message  # type: ignore[misc]
+        ModelResponseBase = _ModelResponseBase  # type: ignore[misc]
+        ModelResponseStream = _ModelResponseStream  # type: ignore[misc]
+        LiteLLMStreamingChoices = _LiteLLMStreamingChoices  # type: ignore[misc]
+        get_supported_openai_params = _get_supported_openai_params
+        ChatCompletionDeltaToolCall = _ChatCompletionDeltaToolCall  # type: ignore[misc]
+        Function = _Function  # type: ignore[misc]
+        ModelResponse = _ModelResponse  # type: ignore[misc]
+        supports_response_schema = _supports_response_schema
+
+        _litellm.suppress_debug_info = True
+        LITELLM_AVAILABLE = True
+    except ImportError:
+        LITELLM_AVAILABLE = False
+
+    return LITELLM_AVAILABLE
 
 
 MIN_CONTEXT: Final[int] = 1024
@@ -117,6 +169,7 @@ LLM_CONTEXT_WINDOW_SIZES: Final[dict[str, int]] = {
     "gpt-4": 8192,
     "gpt-4o": 128000,
     "gpt-4o-mini": 200000,
+    "gpt-5.4-mini": 200000,
     "gpt-4-turbo": 128000,
     "gpt-4.1": 1047576,  # Based on official docs
     "gpt-4.1-mini-2025-04-14": 1047576,
@@ -411,7 +464,8 @@ class LLM(BaseLLM):
             except Exception as e:
                 raise ImportError(f"Error importing native provider: {e}") from e
 
-        if not LITELLM_AVAILABLE:
+        # FALLBACK to LiteLLM — lazy-load on first use
+        if not _ensure_litellm():
             native_list = ", ".join(SUPPORTED_NATIVE_PROVIDERS)
             error_msg = (
                 f"Unable to initialize LLM with model '{model}'. "
@@ -632,7 +686,7 @@ class LLM(BaseLLM):
     @model_validator(mode="after")
     def _init_litellm(self) -> LLM:
         self.is_litellm = True
-        if LITELLM_AVAILABLE:
+        if _ensure_litellm():
             litellm.drop_params = True
             self.set_callbacks(self.callbacks or [])
             self.set_env_callbacks()
@@ -2290,7 +2344,8 @@ class LLM(BaseLLM):
         Note: This validation only applies to the litellm fallback path.
         Native providers have their own validation.
         """
-        if not LITELLM_AVAILABLE or supports_response_schema is None:
+        if not _ensure_litellm() or supports_response_schema is None:
+            # When litellm is not available, skip validation
             # (this path should only be reached for litellm fallback models)
             return
 
@@ -2310,7 +2365,7 @@ class LLM(BaseLLM):
         Note: This method is only used by the litellm fallback path.
         Native providers override this method with their own implementation.
         """
-        if not LITELLM_AVAILABLE:
+        if not _ensure_litellm():
             # When litellm is not available, assume function calling is supported
             # (all modern models support it)
             return True
@@ -2334,7 +2389,7 @@ class LLM(BaseLLM):
         if "gpt-5" in model_lower:
             return False
 
-        if not LITELLM_AVAILABLE or get_supported_openai_params is None:
+        if not _ensure_litellm() or get_supported_openai_params is None:
             # When litellm is not available, assume stop words are supported
             return True
 
@@ -2382,7 +2437,8 @@ class LLM(BaseLLM):
         Note: This only affects the litellm fallback path. Native providers
         don't use litellm callbacks - they emit events via base_llm.py.
         """
-        if not LITELLM_AVAILABLE:
+        if not _ensure_litellm():
+            # When litellm is not available, callbacks are still stored
             # but not registered with litellm globals
             return
 
@@ -2420,7 +2476,8 @@ class LLM(BaseLLM):
         This will set `litellm.success_callback` to ["langfuse", "langsmith"] and
         `litellm.failure_callback` to ["langfuse"].
         """
-        if not LITELLM_AVAILABLE:
+        if not _ensure_litellm():
+            # When litellm is not available, env callbacks have no effect
             return
 
         with suppress_warnings():

lib/crewai/src/crewai/llms/base_llm.py

@@ -890,41 +890,17 @@ class BaseLLM(BaseModel, ABC):
         Args:
             usage_data: Token usage data from the API response
         """
-        prompt_tokens = (
-            usage_data.get("prompt_tokens")
-            or usage_data.get("prompt_token_count")
-            or usage_data.get("input_tokens")
-            or 0
-        )
+        metrics = UsageMetrics.from_provider_dict(usage_data)
+        if metrics is None:
+            return
 
-        completion_tokens = (
-            usage_data.get("completion_tokens")
-            or usage_data.get("candidates_token_count")
-            or usage_data.get("output_tokens")
-            or 0
-        )
-
-        cached_tokens = (
-            usage_data.get("cached_tokens")
-            or usage_data.get("cached_prompt_tokens")
-            or usage_data.get("cache_read_input_tokens")
-            or 0
-        )
-        if not cached_tokens:
-            prompt_details = usage_data.get("prompt_tokens_details")
-            if isinstance(prompt_details, dict):
-                cached_tokens = prompt_details.get("cached_tokens", 0) or 0
-
-        reasoning_tokens = usage_data.get("reasoning_tokens", 0) or 0
-        cache_creation_tokens = usage_data.get("cache_creation_tokens", 0) or 0
-
-        self._token_usage["prompt_tokens"] += prompt_tokens
-        self._token_usage["completion_tokens"] += completion_tokens
-        self._token_usage["total_tokens"] += prompt_tokens + completion_tokens
-        self._token_usage["successful_requests"] += 1
-        self._token_usage["cached_prompt_tokens"] += cached_tokens
-        self._token_usage["reasoning_tokens"] += reasoning_tokens
-        self._token_usage["cache_creation_tokens"] += cache_creation_tokens
+        self._token_usage["prompt_tokens"] += metrics.prompt_tokens
+        self._token_usage["completion_tokens"] += metrics.completion_tokens
+        self._token_usage["total_tokens"] += metrics.total_tokens
+        self._token_usage["successful_requests"] += metrics.successful_requests
+        self._token_usage["cached_prompt_tokens"] += metrics.cached_prompt_tokens
+        self._token_usage["reasoning_tokens"] += metrics.reasoning_tokens
+        self._token_usage["cache_creation_tokens"] += metrics.cache_creation_tokens
 
     def get_token_usage_summary(self) -> UsageMetrics:
         """Get summary of token usage for this LLM instance.

lib/crewai/src/crewai/llms/providers/azure/completion.py

@@ -1300,6 +1300,7 @@ class AzureCompletion(BaseLLM):
             "gpt-4": 8192,
             "gpt-4o": 128000,
             "gpt-4o-mini": 200000,
+            "gpt-5.4-mini": 200000,
             "gpt-4-turbo": 128000,
             "gpt-35-turbo": 16385,
             "gpt-3.5-turbo": 16385,

lib/crewai/src/crewai/llms/providers/openai/completion.py

@@ -2406,6 +2406,7 @@ class OpenAICompletion(BaseLLM):
             "gpt-4": 8192,
             "gpt-4o": 128000,
             "gpt-4o-mini": 200000,
+            "gpt-5.4-mini": 200000,
             "gpt-4-turbo": 128000,
             "gpt-4.1": 1047576,
             "gpt-4.1-mini-2025-04-14": 1047576,

lib/crewai/src/crewai/memory/storage/backend.py

@@ -8,6 +8,39 @@ from typing import Any, Protocol, runtime_checkable
 from crewai.memory.types import MemoryRecord, ScopeInfo
 
 
+class EmbeddingDimensionMismatchError(ValueError):
+    """Raised when an embedding's dimensionality doesn't match the existing store.
+
+    The most common cause is upgrading CrewAI across the default-embedder
+    change (text-embedding-3-small, 1536 dims → text-embedding-3-large,
+    3072 dims) while keeping a local memory store created before the upgrade.
+
+    Deliberately not a ``RuntimeError``: background-save plumbing treats
+    ``RuntimeError`` as interpreter/executor shutdown and silently drops the
+    save, which would swallow this actionable migration error.
+    """
+
+    def __init__(self, stored_dim: int, new_dim: int) -> None:
+        self.stored_dim = stored_dim
+        self.new_dim = new_dim
+        super().__init__(
+            f"Embedding dimension mismatch: this memory store contains "
+            f"{stored_dim}-dimensional vectors, but the current embedder produced "
+            f"a {new_dim}-dimensional vector.\n\n"
+            "This usually means the store was created with a different embedding "
+            "model. CrewAI's default embedder changed from "
+            "text-embedding-3-small (1536 dims) to text-embedding-3-large "
+            "(3072 dims), so memory stores created before the upgrade are "
+            "incompatible with the new default.\n\n"
+            "To fix, do one of the following:\n"
+            "  - Reset local memory so it is rebuilt with the new embedder:\n"
+            "      crewai reset-memories --memory   (or crew.reset_memories())\n"
+            "  - Keep existing memories by pinning the previous embedder:\n"
+            '      embedder={"provider": "openai", '
+            '"config": {"model": "text-embedding-3-small"}}'
+        )
+
+
 @runtime_checkable
 class StorageBackend(Protocol):
     """Protocol for pluggable memory storage backends."""