feat: add list_tools() to Crew and Flow for static tool enumeration

In `_execute_task_with_a2a` and its async variant, the try body
sets `task.output_pydantic = None` before returning an A2A
response. The finally block then checks
`if task.output_pydantic is not None` before restoring the
original value — but since it was just set to None, the condition
is always False and the original value is never restored. This
permanently mutates the Task object.

Remove the guard so `output_pydantic` is unconditionally restored,
matching the unconditional restoration of `description` and
`response_model` in the same block.

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>

.github/security.md

@@ -5,7 +5,10 @@ CrewAI ecosystem.
 
 ### How to Report
 
-Please submit reports to **crewai-vdp-ess@submit.bugcrowd.com**
+Please submit reports through one of the following channels:
+
+- **crewai-vdp-ess@submit.bugcrowd.com**
+- https://security.crewai.com
 
 - **Please do not** disclose vulnerabilities via public GitHub issues, pull requests,
   or social media

.pre-commit-config.yaml

@@ -19,7 +19,7 @@ repos:
         language: system
         pass_filenames: true
         types: [python]
-        exclude: ^(lib/crewai/src/crewai/cli/templates/|lib/crewai/tests/|lib/crewai-tools/tests/|lib/crewai-files/tests/)
+        exclude: ^(lib/crewai/src/crewai/cli/templates/|lib/cli/src/crewai_cli/templates/|lib/cli/tests/|lib/crewai/tests/|lib/crewai-tools/tests/|lib/crewai-files/tests/|lib/devtools/tests/)
   - repo: https://github.com/astral-sh/uv-pre-commit
     rev: 0.11.3
     hooks:

conftest.py

@@ -54,12 +54,13 @@ _original_from_serialized_response = getattr(
 )
 
 if _original_from_serialized_response is not None:
+    _from_serialized: Any = _original_from_serialized_response
 
     def _patched_from_serialized_response(
         request: Any, serialized_response: Any, history: Any = None
     ) -> Any:
         """Patched version that ensures response._content is properly set."""
-        response = _original_from_serialized_response(request, serialized_response, history)
+        response = _from_serialized(request, serialized_response, history)
         # Explicitly set _content to avoid ResponseNotRead errors
         # The content was passed to the constructor but the mocked read() prevents
         # proper initialization of the internal state
@@ -255,7 +256,8 @@ def vcr_cassette_dir(request: Any) -> str:
 
     for parent in test_file.parents:
         if (
-            parent.name in ("crewai", "crewai-tools", "crewai-files")
+            parent.name
+            in ("crewai", "crewai-tools", "crewai-files", "cli", "crewai-core")
             and parent.parent.name == "lib"
         ):
             package_root = parent

docs/ar/api-reference/introduction.mdx

@@ -26,7 +26,7 @@ mode: "wide"
 </Step>
 
   <Step title="مراقبة التقدم">
-    استخدم `GET /{kickoff_id}/status` للتحقق من حالة التنفيذ واسترجاع النتائج.
+    استخدم `GET /status/{kickoff_id}` للتحقق من حالة التنفيذ واسترجاع النتائج.
   </Step>
 </Steps>
 
@@ -65,7 +65,7 @@ https://your-crew-name.crewai.com
 
 1. **الاكتشاف**: استدعِ `GET /inputs` لفهم ما يحتاجه طاقمك
 2. **التنفيذ**: أرسل المدخلات عبر `POST /kickoff` لبدء المعالجة
-3. **المراقبة**: استعلم عن `GET /{kickoff_id}/status` حتى الاكتمال
+3. **المراقبة**: استعلم عن `GET /status/{kickoff_id}` حتى الاكتمال
 4. **النتائج**: استخرج المخرجات النهائية من الاستجابة المكتملة
 
 ## معالجة الأخطاء

docs/ar/api-reference/status.mdx

@@ -1,6 +1,6 @@
 ---
-title: "GET /{kickoff_id}/status"
+title: "GET /status/{kickoff_id}"
 description: "الحصول على حالة التنفيذ"
-openapi: "/enterprise-api.en.yaml GET /{kickoff_id}/status"
+openapi: "/enterprise-api.en.yaml GET /status/{kickoff_id}"
 mode: "wide"
 ---

docs/ar/changelog.mdx

@@ -4,6 +4,99 @@ description: "تحديثات المنتج والتحسينات وإصلاحات
 icon: "clock"
 mode: "wide"
 ---
+<Update label="4 مايو 2026">
+  ## v1.14.5a2
+
+  [عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.5a2)
+
+  ## ما الذي تغير
+
+  ### إصلاحات الأخطاء
+  - إصلاح استعادة مخرجات المهام في كتلة finally
+  - تضمين `thoughts_token_count` في رموز الإكمال
+  - الحفاظ على مخرجات المهام عبر تفريغ دفعات غير متزامنة
+  - تمرير kwargs إلى استدعاءات المحمل في `CrewAIRagAdapter`
+  - منع `result_as_answer` من إرجاع رسالة كتلة الخطاف كإجابة نهائية
+  - منع `result_as_answer` من إرجاع خطأ كإجابة نهائية
+  - استخدام `acall` لتحويل المخرجات في المسارات غير المتزامنة
+  - منع تغيير كلمات التوقف المشتركة في LLM عبر الوكلاء
+  - التعامل مع مدخلات `BaseModel` في `convert_to_model`
+
+  ### الوثائق
+  - توثيق متغيرات البيئة الإضافية
+  - تحديث سجل التغييرات والإصدار لـ v1.14.5a1
+
+  ## المساهمون
+
+  @NIK-TIGER-BILL, @greysonlalonde, @lorenzejay, @minasami-pr, @theCyberTech, @wishhyt
+
+</Update>
+
+<Update label="1 مايو 2026">
+  ## v1.14.5a1
+
+  [عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.5a1)
+
+  ## ما الذي تغير
+
+  ### الميزات
+  - إضافة معلمة بدء `restore_from_state_id`
+  - إضافة تسليط الضوء على ExaSearchTool وإعادة تسميته من EXASearchTool
+
+  ### إصلاحات الأخطاء
+  - إصلاح المواقع المفقودة لـ crewai في تدفق الإصدار
+  - ضمان تحميل أحداث المهارات للآثار
+
+  ### الوثائق
+  - تحديث سجل التغييرات والإصدار لـ v1.14.4
+
+  ## المساهمون
+
+  @akaKuruma, @github-actions[bot], @greysonlalonde, @lorenzejay, @theishangoswami
+
+</Update>
+
+<Update label="1 مايو 2026">
+  ## v1.14.4
+
+  [عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.4)
+
+  ## ما الذي تغير
+
+  ### الميزات
+  - إضافة دعم لمفتاح الاستمرارية المخصص في @persist
+  - إضافة دعم واجهة برمجة التطبيقات للردود لمزود Azure OpenAI
+  - تمرير credential_scopes إلى عميل Azure AI Inference
+  - إضافة دليل إعداد هوية عبء العمل لـ Vertex AI
+  - إضافة Tavily Research والحصول على Research
+  - إضافة أدوات MCP من You.com للبحث، البحث، واستخراج المحتوى
+
+  ### إصلاحات الأخطاء
+  - إصلاح مشكلة السقوط عند عدم تطابق تعبير JSON regex مع JSON صالح
+  - إصلاح للحفاظ على tool_calls عندما تحتوي الاستجابة أيضًا على نص
+  - إصلاح لتمرير base_url و api_key إلى instructor.from_provider
+  - إصلاح لتحذير وإرجاع فارغ عندما لا يُرجع خادم MCP الأصلي أي أدوات
+  - إصلاح لاستخدام متغير الرسائل الموثقة في معالجات غير البث
+  - إصلاح لحماية مساعدي وصف دردشة الطاقم ضد فشل LLM
+  - إصلاح لإعادة تعيين الرسائل والتكرارات بين الاستدعاءات
+  - إصلاح لتمرير ملف trained-agents من خلال replay و test
+  - إصلاح لاحترام ملف trained-agents المخصص في الاستدلال
+  - إصلاح لربط الوكلاء المخصصين بالمهام فقط بالطاقم لملفات الإدخال متعددة الأنماط
+  - إصلاح لتسلسل callable الحواجز كـ null لتسجيل JSON
+  - إصلاح إعادة تسمية force_final_answer لتجنب توجيه ذاتي
+  - إصلاح زيادة litellm لإصلاح SSTI؛ تجاهل CVE غير القابل للإصلاح في pip
+
+  ### الوثائق
+  - تحديث سجل التغييرات والإصدار لـ v1.14.4a1
+  - إضافة صفحة أدوات E2B Sandbox
+  - إضافة وثائق أدوات صندوق Daytona
+
+  ## المساهمون
+
+  @EdwardIrby, @dependabot[bot], @factory-droid-oss, @factory-droid[bot], @greysonlalonde, @kunalk16, @lorenzejay, @lucasgomide, @manisrinivasan2k1, @mattatcha, @vinibrsl
+
+</Update>
+
 <Update label="29 أبريل 2026">
   ## v1.14.4a1
 

docs/ar/concepts/flows.mdx

@@ -380,32 +380,41 @@ class AnotherFlow(Flow[dict]):
         print("Method-level persisted runs:", self.state["runs"])
 ```
 
-### مفتاح استمرارية مخصص
+### تفرع الحالة المستمرة
 
-افتراضيًا، يستخدم `@persist` الحقل `state.id` المُولّد تلقائيًا كمفتاح للاستمرارية. إذا كان لتدفقك معرّف خاص به — مثل `conversation_id` مشترك بين عدة جلسات — يمكنك تمرير الوسيط `key` ليستخدم `@persist` تلك السمة كـ UUID للتدفق:
+يدعم `@persist` نمطين متميزين للترطيب في `kickoff` / `kickoff_async`:
+
+- `kickoff(inputs={"id": <uuid>})` — **استئناف**: يحمّل أحدث لقطة لـ UUID المقدم ويستمر في الكتابة تحت نفس `flow_uuid`. يمتد التاريخ.
+- `kickoff(restore_from_state_id=<uuid>)` — **تفرع**: يحمّل أحدث لقطة لـ UUID المقدم، يرطّب حالة التشغيل الجديد منها، ثم يعيّن `state.id` جديدًا (مولّدًا تلقائيًا، أو `inputs["id"]` إذا تم تثبيته). تذهب كتابات `@persist` للتشغيل الجديد تحت `state.id` الجديد؛ يتم الحفاظ على تاريخ تدفق المصدر.
 
 ```python
-from crewai.flow.flow import Flow, listen, start
+from crewai.flow.flow import Flow, start
 from crewai.flow.persistence import persist
 from pydantic import BaseModel
 
-class ConversationState(BaseModel):
-    conversation_id: str
-    turn: int = 0
+class CounterState(BaseModel):
+    id: str = ""
+    counter: int = 0
 
-@persist(key="conversation_id")  # استخدام حقل مخصص كمفتاح للاستمرارية
-class ConversationFlow(Flow[ConversationState]):
+@persist
+class CounterFlow(Flow[CounterState]):
     @start()
-    def begin(self):
-        self.state.turn += 1
-        print(f"Conversation {self.state.conversation_id} turn {self.state.turn}")
+    def step(self):
+        self.state.counter += 1
+        print(f"[id={self.state.id}] counter={self.state.counter}")
 
-# إعادة تشغيل المحادثة بنفس conversation_id يُعيد تحميل الحالة السابقة
-flow = ConversationFlow(conversation_id="user-42")
-flow.kickoff()
+# التشغيل 1: حالة جديدة، العداد 0 -> 1، محفوظ تحت flow_1.state.id
+flow_1 = CounterFlow()
+flow_1.kickoff()
+
+# التفرع: ترطيب من أحدث لقطة لـ flow_1، لكن باستخدام state.id جديد
+flow_2 = CounterFlow()
+flow_2.kickoff(restore_from_state_id=flow_1.state.id)
+# يبدأ flow_2.state.counter بـ 1 (مرطّب)، ثم تزيده step() إلى 2.
+# flow_2.state.id != flow_1.state.id؛ تاريخ flow_1 لم يتغيّر.
 ```
 
-يقرأ المزخرف القيمة من `state[key]` للحالات من نوع dict، ومن `getattr(state, key)` للحالات من نوع Pydantic / كائن. إذا كانت السمة المحددة غير موجودة أو قيمتها falsy عند الحفظ، يُطلق `@persist` خطأ `ValueError` مثل `Flow state is missing required persistence key 'conversation_id'`. عند حذف `key`، يظل السلوك الأصلي قائمًا ويُستخدم `state.id`.
+إذا لم يطابق `restore_from_state_id` المقدم أي حالة مستمرة، يعود kickoff بصمت إلى السلوك الافتراضي — نفس سلوك `inputs["id"]` عند عدم العثور عليه. الجمع بين `restore_from_state_id` و `from_checkpoint` يطلق `ValueError`؛ اختر مصدر ترطيب واحدًا. تثبيت `inputs["id"]` أثناء التفرع يشارك مفتاح الاستمرارية مع تدفق آخر — عادةً ما تريد استخدام `restore_from_state_id` فقط.
 
 ### كيف تعمل
 

docs/ar/concepts/production-architecture.mdx

@@ -146,15 +146,14 @@ class ProductionFlow(Flow[AppState]):
     # ...
 ```
 
-افتراضيًا، يستخدم `@persist` الحقل `state.id` المُولّد تلقائيًا كمفتاح للحالة المحفوظة. إذا كان تطبيقك يمتلك معرّفًا طبيعيًا بالفعل — مثل `conversation_id` يربط عدة تشغيلات بنفس جلسة المستخدم — مرّره كـ `key` ليستخدمه المزخرف كـ UUID للتدفق. يُطلق `ValueError` إذا كانت السمة المحددة غير موجودة أو قيمتها falsy عند الحفظ.
+افتراضيًا، يستأنف `@persist` تدفقًا عند توفير `kickoff(inputs={"id": <uuid>})`، مما يمدّ نفس تاريخ `flow_uuid`. لـ **تفرع** تدفق مستمر إلى نسبٍ جديد — ترطيب الحالة من تشغيل سابق ولكن الكتابة تحت `state.id` جديد — مرّر `restore_from_state_id`:
 
 ```python
-@persist(key="conversation_id")
-class ProductionFlow(Flow[AppState]):
-    # يجب أن يحتوي AppState على conversation_id؛ استئناف الجلسة يُعيد تحميل الحالة السابقة
-    ...
+flow.kickoff(restore_from_state_id="<previous-run-state-id>")
 ```
 
+يحصل التشغيل الجديد على `state.id` جديد (مولّد تلقائيًا، أو `inputs["id"]` إذا تم تثبيته) لذا لا تمتد كتابات `@persist` الخاصة به إلى تاريخ المصدر. الجمع مع `from_checkpoint` يطلق `ValueError`؛ اختر مصدر ترطيب واحدًا.
+
 ## الخلاصة
 
 - **ابدأ بتدفق.**

docs/ar/concepts/tools.mdx

@@ -133,7 +133,7 @@ crew.kickoff()
 | **DirectorySearchTool**          | أداة RAG للبحث في المجلدات، مفيدة للتنقل في أنظمة الملفات.       |
 | **DOCXSearchTool**               | أداة RAG للبحث في مستندات DOCX، مثالية لمعالجة ملفات Word.          |
 | **DirectoryReadTool**            | تسهّل قراءة ومعالجة هياكل المجلدات ومحتوياتها.                 |
-| **EXASearchTool**                | أداة مصممة لإجراء عمليات بحث شاملة عبر مصادر بيانات متنوعة.                |
+| **ExaSearchTool**                | أداة مصممة لإجراء عمليات بحث شاملة عبر مصادر بيانات متنوعة.                |
 | **FileReadTool**                 | تُمكّن قراءة واستخراج البيانات من الملفات، مع دعم تنسيقات ملفات متنوعة.               |
 | **FirecrawlSearchTool**          | أداة للبحث في صفحات الويب باستخدام Firecrawl وإرجاع النتائج.                              |
 | **FirecrawlCrawlWebsiteTool**    | أداة لزحف صفحات الويب باستخدام Firecrawl.                                                  |

docs/ar/guides/flows/mastering-flow-state.mdx

@@ -116,32 +116,47 @@ class PersistentCounterFlow(Flow[CounterState]):
         return self.state.value
 ```
 
-### استخدام مفتاح استمرارية مخصص
+#### تفرع الحالة المستمرة
 
-افتراضيًا، يستخدم `@persist()` الحقل `state.id` المُولّد تلقائيًا كمفتاح للحالة المحفوظة. عندما يكون لمجالك معرّف طبيعي بالفعل — مثل `conversation_id` يربط عدة تشغيلات للتدفق بنفس جلسة المستخدم — مرّره كوسيط `key` ليستخدمه `@persist` كـ UUID للتدفق بدلًا من `id`:
+يدعم `@persist` نمطين متميزين للترطيب في `kickoff` / `kickoff_async`. استخدم **استئناف** (`inputs["id"]`) لمواصلة نفس النسب؛ استخدم **تفرع** (`restore_from_state_id`) لبدء نسبٍ جديد من لقطة:
+
+| | `state.id` بعد kickoff | كتابات `@persist` تذهب إلى |
+|---|---|---|
+| `inputs["id"]` (استئناف) | المعرّف المقدم | المعرّف المقدم (يمد التاريخ) |
+| `restore_from_state_id` (تفرع) | معرّف جديد، أو `inputs["id"]` إذا ثُبّت | المعرّف الجديد (المصدر محفوظ) |
 
 ```python
-from crewai.flow.flow import Flow, listen, start
+from crewai.flow.flow import Flow, start
 from crewai.flow.persistence import persist
 from pydantic import BaseModel
 
-class ConversationState(BaseModel):
-    conversation_id: str
-    history: list[str] = []
+class CounterState(BaseModel):
+    id: str = ""
+    counter: int = 0
 
-@persist(key="conversation_id")
-class ConversationFlow(Flow[ConversationState]):
+@persist
+class CounterFlow(Flow[CounterState]):
     @start()
-    def greet(self):
-        self.state.history.append("hello")
-        return self.state.history
+    def step(self):
+        self.state.counter += 1
 
-# تشغيل ثانٍ بنفس conversation_id يُعيد تحميل الحالة السابقة
-flow = ConversationFlow(conversation_id="user-42")
-flow.kickoff()
+# التشغيل 1: حالة جديدة، العداد 0 -> 1
+flow_1 = CounterFlow()
+flow_1.kickoff()
+
+# التفرع: الترطيب من أحدث لقطة لـ flow_1، لكن الكتابة تحت state.id جديد
+flow_2 = CounterFlow()
+flow_2.kickoff(restore_from_state_id=flow_1.state.id)
+# يبدأ flow_2 بـ counter=1 (مرطّب)، ثم تزيده step() إلى 2.
+# تاريخ flow_uuid لـ flow_1 لم يتغيّر.
 ```
 
-بالنسبة للحالات من نوع dict يقرأ `@persist` القيمة من `state[key]`، ولحالات Pydantic / الكائنات يقرأها من `getattr(state, key)`. إذا كانت السمة المحددة غير موجودة أو قيمتها falsy عند حفظ الحالة، يُطلق `@persist` خطأ `ValueError` مثل `Flow state is missing required persistence key 'conversation_id'`، فيظهر الفشل فورًا بدلًا من فقد بيانات الاستمرارية بصمت. استدعاء `@persist()` بدون `key` يحافظ على السلوك الأصلي ويستخدم `state.id`.
+ملاحظات السلوك:
+
+- `restore_from_state_id` غير موجود في الاستمرارية → يعود kickoff بصمت إلى السلوك الافتراضي (يعكس سلوك `inputs["id"]` عند عدم العثور عليه). لا يُطلق أي استثناء.
+- الجمع بين `restore_from_state_id` و `from_checkpoint` يطلق `ValueError` — يستهدفان نظامي حالة مختلفين (`@persist` مقابل Checkpointing) ولا يمكن الجمع بينهما.
+- `restore_from_state_id=None` (افتراضي) متطابق بايت ببايت مع kickoff بدون المعامل.
+- تثبيت `inputs["id"]` أثناء التفرع يعني أن التشغيل الجديد يشارك مفتاح الاستمرارية مع تدفق آخر — عادةً ما تريد فقط `restore_from_state_id`.
 
 ## أنماط حالة متقدمة
 

docs/ar/tools/search-research/exasearchtool.mdx

@@ -1,11 +1,11 @@
 ---
 title: "أداة بحث Exa"
-description: "ابحث في الويب باستخدام Exa Search API للعثور على النتائج الأكثر صلة لأي استعلام، مع خيارات لمحتوى الصفحة الكامل والمقتطفات والملخصات."
+description: "ابحث في الويب باستخدام Exa Search API للعثور على النتائج الأكثر صلة لأي استعلام، مع خيارات لمحتوى الصفحة الكامل والمقتطفات."
 icon: "magnifying-glass"
 mode: "wide"
 ---
 
-تتيح أداة `EXASearchTool` لوكلاء CrewAI البحث في الويب باستخدام [Exa](https://exa.ai/) search API. تُرجع النتائج الأكثر صلة لأي استعلام، مع خيارات لمحتوى الصفحة الكامل والملخصات المولّدة بالذكاء الاصطناعي.
+تتيح أداة `ExaSearchTool` لوكلاء CrewAI البحث في الويب باستخدام [Exa](https://exa.ai/) search API. تُرجع النتائج الأكثر صلة لأي استعلام، مع خيارات لمحتوى الصفحة الكامل والمقتطفات الموفرة للرموز.
 
 ## التثبيت
 
@@ -27,15 +27,15 @@ export EXA_API_KEY='your_exa_api_key'
 
 ## مثال على الاستخدام
 
-إليك كيفية استخدام `EXASearchTool` مع وكيل CrewAI:
+إليك كيفية استخدام `ExaSearchTool` مع وكيل CrewAI:
 
 ```python
 import os
 from crewai import Agent, Task, Crew
-from crewai_tools import EXASearchTool
+from crewai_tools import ExaSearchTool
 
 # Initialize the tool
-exa_tool = EXASearchTool()
+exa_tool = ExaSearchTool()
 
 # Create an agent that uses the tool
 researcher = Agent(
@@ -66,11 +66,11 @@ print(result)
 
 ## خيارات التكوين
 
-تقبل أداة `EXASearchTool` المعاملات التالية أثناء التهيئة:
+تقبل أداة `ExaSearchTool` المعاملات التالية أثناء التهيئة:
 
 - `type` (str، اختياري): نوع البحث المستخدم. الافتراضي هو `"auto"`. الخيارات: `"auto"`، `"instant"`، `"fast"`، `"deep"`.
+- `highlights` (bool أو dict، اختياري): إرجاع مقتطفات موفرة للرموز أكثر صلة بالاستعلام بدلاً من الصفحة الكاملة. الافتراضي هو `True`. مرر قاموسًا مثل `{"max_characters": 4000}` للتكوين، أو `False` للتعطيل.
 - `content` (bool، اختياري): ما إذا كان يجب تضمين محتوى الصفحة الكامل في النتائج. الافتراضي هو `False`.
-- `summary` (bool، اختياري): ما إذا كان يجب تضمين ملخصات مولّدة بالذكاء الاصطناعي لكل نتيجة. يتطلب `content=True`. الافتراضي هو `False`.
 - `api_key` (str، اختياري): مفتاح Exa API الخاص بك. يعود إلى متغير البيئة `EXA_API_KEY` إذا لم يتم تقديمه.
 - `base_url` (str، اختياري): عنوان URL مخصص لخادم API. يعود إلى متغير البيئة `EXA_BASE_URL` إذا لم يتم تقديمه.
 
@@ -86,25 +86,52 @@ print(result)
 يمكنك تكوين الأداة بمعاملات مخصصة للحصول على نتائج أغنى:
 
 ```python
-# Get full page content with AI summaries
-exa_tool = EXASearchTool(
-    content=True,
-    summary=True,
+# Use 'deep' for thorough, multi-step searches
+exa_tool = ExaSearchTool(
+    highlights=True,
     type="deep"
 )
 
 # Use it in an agent
 agent = Agent(
     role="Deep Researcher",
-    goal="Conduct thorough research with full content and summaries",
+    goal="Conduct thorough research",
     tools=[exa_tool]
 )
 ```
 
+## استخدام Exa عبر MCP
+
+يمكنك أيضًا ربط وكيلك بخادم MCP المستضاف من Exa. مرّر مفتاح API الخاص بك عبر ترويسة `x-api-key`:
+
+```python
+from crewai import Agent
+from crewai.mcp import MCPServerHTTP
+
+agent = Agent(
+    role="Research Analyst",
+    goal="Find and analyze information on the web",
+    backstory="Expert researcher with access to Exa's tools",
+    mcps=[
+        MCPServerHTTP(
+            url="https://mcp.exa.ai/mcp",
+            headers={"x-api-key": "YOUR_EXA_API_KEY"},
+        ),
+    ],
+)
+```
+
+احصل على مفتاح API من [لوحة تحكم Exa](https://dashboard.exa.ai/api-keys). لمزيد من المعلومات حول MCP في CrewAI، راجع [نظرة عامة على MCP](/ar/mcp/overview).
+
 ## الميزات
 
+- **مقتطفات موفرة للرموز**: الحصول على المقتطفات الأكثر صلة من كل نتيجة، باستخدام رموز أقل بكثير من النص الكامل
 - **البحث الدلالي**: العثور على نتائج بناءً على المعنى، وليس الكلمات المفتاحية فقط
 - **استرجاع المحتوى الكامل**: الحصول على النص الكامل لصفحات الويب مع نتائج البحث
-- **ملخصات الذكاء الاصطناعي**: الحصول على ملخصات موجزة مولّدة بالذكاء الاصطناعي لكل نتيجة
 - **تصفية التاريخ**: تقييد النتائج لفترات زمنية محددة باستخدام فلاتر تاريخ النشر
-- **تصفية النطاقات**: تقييد عمليات البحث على نطاقات محددة
+- **تصفية النطاقات**: تقييد عمليات البحث على نطاقات محددة
+
+## موارد
+
+- [توثيق Exa](https://exa.ai/docs)
+- [لوحة تحكم Exa — إدارة مفاتيح API والاستخدام](https://dashboard.exa.ai)

docs/en/api-reference/introduction.mdx

@@ -26,7 +26,7 @@ Welcome to the CrewAI AMP API reference. This API allows you to programmatically
 </Step>
 
   <Step title="Monitor Progress">
-    Use `GET /{kickoff_id}/status` to check execution status and retrieve results.
+    Use `GET /status/{kickoff_id}` to check execution status and retrieve results.
   </Step>
 </Steps>
 
@@ -65,7 +65,7 @@ Replace `your-crew-name` with your actual crew's URL from the dashboard.
 
 1. **Discovery**: Call `GET /inputs` to understand what your crew needs
 2. **Execution**: Submit inputs via `POST /kickoff` to start processing
-3. **Monitoring**: Poll `GET /{kickoff_id}/status` until completion
+3. **Monitoring**: Poll `GET /status/{kickoff_id}` until completion
 4. **Results**: Extract the final output from the completed response
 
 ## Error Handling

docs/en/api-reference/status.mdx

@@ -1,6 +1,6 @@
 ---
-title: "GET /{kickoff_id}/status"
+title: "GET /status/{kickoff_id}"
 description: "Get execution status"
-openapi: "/enterprise-api.en.yaml GET /{kickoff_id}/status"
+openapi: "/enterprise-api.en.yaml GET /status/{kickoff_id}"
 mode: "wide"
 ---

docs/en/changelog.mdx

@@ -4,6 +4,99 @@ description: "Product updates, improvements, and bug fixes for CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="May 04, 2026">
+  ## v1.14.5a2
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.5a2)
+
+  ## What's Changed
+
+  ### Bug Fixes
+  - Fix task output restoration in finally block
+  - Include `thoughts_token_count` in completion tokens
+  - Preserve task outputs across async batch flush
+  - Forward kwargs to loader calls in `CrewAIRagAdapter`
+  - Prevent `result_as_answer` from returning hook-block message as final answer
+  - Prevent `result_as_answer` from returning error as final answer
+  - Use `acall` for output conversion in async paths
+  - Prevent shared LLM stop words mutation across agents
+  - Handle `BaseModel` input in `convert_to_model`
+
+  ### Documentation
+  - Document additional environment variables
+  - Update changelog and version for v1.14.5a1
+
+  ## Contributors
+
+  @NIK-TIGER-BILL, @greysonlalonde, @lorenzejay, @minasami-pr, @theCyberTech, @wishhyt
+
+</Update>
+
+<Update label="May 01, 2026">
+  ## v1.14.5a1
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.5a1)
+
+  ## What's Changed
+
+  ### Features
+  - Add `restore_from_state_id` kickoff parameter
+  - Add highlights to ExaSearchTool and rename from EXASearchTool
+
+  ### Bug Fixes
+  - Fix missing crewai pin sites in release flow
+  - Ensure skills loading events for traces
+
+  ### Documentation
+  - Update changelog and version for v1.14.4
+
+  ## Contributors
+
+  @akaKuruma, @github-actions[bot], @greysonlalonde, @lorenzejay, @theishangoswami
+
+</Update>
+
+<Update label="May 01, 2026">
+  ## v1.14.4
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.4)
+
+  ## What's Changed
+
+  ### Features
+  - Add support for custom persistence key in @persist
+  - Add Responses API support for Azure OpenAI provider
+  - Forward credential_scopes to Azure AI Inference client
+  - Add Vertex AI workload identity setup guide
+  - Add Tavily Research and get Research
+  - Add You.com MCP tools for search, research, and content extraction
+
+  ### Bug Fixes
+  - Fix fall through when JSON regex match isn't valid JSON
+  - Fix to preserve tool_calls when response also contains text
+  - Fix to forward base_url and api_key to instructor.from_provider
+  - Fix to warn and return empty when native MCP server returns no tools
+  - Fix to use validated messages variable in non-streaming handlers
+  - Fix to guard crew chat description helpers against LLM failures
+  - Fix to reset messages and iterations between invocations
+  - Fix to forward trained-agents file through replay and test
+  - Fix to honor custom trained-agents file at inference
+  - Fix to bind task-only agents to crew for multimodal input_files
+  - Fix to serialize guardrail callables as null for JSON checkpointing
+  - Fix renaming of force_final_answer to avoid self-referential router
+  - Fix bump of litellm for SSTI fix; ignore unfixable pip CVE
+
+  ### Documentation
+  - Update changelog and version for v1.14.4a1
+  - Add E2B Sandbox Tools page
+  - Add Daytona sandbox tools documentation
+
+  ## Contributors
+
+  @EdwardIrby, @dependabot[bot], @factory-droid-oss, @factory-droid[bot], @greysonlalonde, @kunalk16, @lorenzejay, @lucasgomide, @manisrinivasan2k1, @mattatcha, @vinibrsl
+
+</Update>
+
 <Update label="Apr 29, 2026">
   ## v1.14.4a1
 

docs/en/concepts/flows.mdx

@@ -380,32 +380,41 @@ class AnotherFlow(Flow[dict]):
         print("Method-level persisted runs:", self.state["runs"])
 ```
 
-### Custom Persistence Key
+### Forking Persisted State
 
-By default, `@persist` uses the auto-generated `state.id` field as the persistence key. If your flow models its own identifier — for example a `conversation_id` shared across sessions — you can pass a `key` argument and `@persist` will use that attribute as the flow UUID instead:
+`@persist` supports two distinct hydration modes on `kickoff` / `kickoff_async`:
+
+- `kickoff(inputs={"id": <uuid>})` — **resume**: load the latest snapshot for the supplied UUID and continue writing under the same `flow_uuid`. The history extends.
+- `kickoff(restore_from_state_id=<uuid>)` — **fork**: load the latest snapshot for the supplied UUID, hydrate the new run's state from it, and assign a fresh `state.id` (auto-generated, or `inputs["id"]` if pinned). The new run's `@persist` writes land under the new `state.id`; the source flow's history is preserved.
 
 ```python
-from crewai.flow.flow import Flow, listen, start
+from crewai.flow.flow import Flow, start
 from crewai.flow.persistence import persist
 from pydantic import BaseModel
 
-class ConversationState(BaseModel):
-    conversation_id: str
-    turn: int = 0
+class CounterState(BaseModel):
+    id: str = ""
+    counter: int = 0
 
-@persist(key="conversation_id")  # Use a custom field as the persistence key
-class ConversationFlow(Flow[ConversationState]):
+@persist
+class CounterFlow(Flow[CounterState]):
     @start()
-    def begin(self):
-        self.state.turn += 1
-        print(f"Conversation {self.state.conversation_id} turn {self.state.turn}")
+    def step(self):
+        self.state.counter += 1
+        print(f"[id={self.state.id}] counter={self.state.counter}")
 
-# Resuming the same conversation reloads its prior state by conversation_id
-flow = ConversationFlow(conversation_id="user-42")
-flow.kickoff()
+# Run 1: fresh state, counter 0 -> 1, persisted under flow_1.state.id
+flow_1 = CounterFlow()
+flow_1.kickoff()
+
+# Fork: hydrate from flow_1's latest snapshot, but use a NEW state.id
+flow_2 = CounterFlow()
+flow_2.kickoff(restore_from_state_id=flow_1.state.id)
+# flow_2.state.counter starts at 1 (hydrated), then step() bumps it to 2.
+# flow_2.state.id != flow_1.state.id; flow_1's history is unchanged.
 ```
 
-The decorator reads the value at `state[key]` for dict states, or `getattr(state, key)` for Pydantic / object states. If the named attribute is missing or falsy at save time, `@persist` raises a `ValueError` such as `Flow state is missing required persistence key 'conversation_id'`. When `key` is omitted, the existing behavior is preserved and `state.id` is used.
+If the supplied `restore_from_state_id` does not match any persisted state, the kickoff falls back silently — same as the existing `inputs["id"]` resume not-found behavior. Combining `restore_from_state_id` with `from_checkpoint` raises a `ValueError`; pick one hydration source. Pinning `inputs["id"]` while forking shares a persistence key with another flow — usually you want only `restore_from_state_id`.
 
 ### How It Works
 

docs/en/concepts/production-architecture.mdx

@@ -146,15 +146,14 @@ class ProductionFlow(Flow[AppState]):
     # ...
 ```
 
-By default `@persist` keys saved state by the auto-generated `state.id`. If your application already has a natural identifier — for example a `conversation_id` that ties multiple runs to the same user session — pass it as `key` and the decorator will use that attribute as the flow UUID. A `ValueError` is raised if the named attribute is missing or falsy at save time.
+By default, `@persist` resumes a flow when `kickoff(inputs={"id": <uuid>})` is supplied, extending the same `flow_uuid` history. To **fork** a persisted flow into a new lineage — hydrate state from a previous run but write under a fresh `state.id` — pass `restore_from_state_id`:
 
 ```python
-@persist(key="conversation_id")
-class ProductionFlow(Flow[AppState]):
-    # AppState must expose conversation_id; resuming a session reloads its prior state
-    ...
+flow.kickoff(restore_from_state_id="<previous-run-state-id>")
 ```
 
+The new run gets a fresh `state.id` (auto-generated, or `inputs["id"]` if pinned) so its `@persist` writes don't extend the source's history. Combining with `from_checkpoint` raises a `ValueError`; pick one hydration source.
+
 ## Summary
 
 - **Start with a Flow.**

docs/en/concepts/tools.mdx

@@ -133,7 +133,7 @@ Here is a list of the available tools and their descriptions:
 | **DirectorySearchTool**          | A RAG tool for searching within directories, useful for navigating through file systems.       |
 | **DOCXSearchTool**               | A RAG tool aimed at searching within DOCX documents, ideal for processing Word files.          |
 | **DirectoryReadTool**            | Facilitates reading and processing of directory structures and their contents.                 |
-| **EXASearchTool**                | A tool designed for performing exhaustive searches across various data sources.                |
+| **ExaSearchTool**                | Search the web with Exa, the fastest and most accurate web search API. Supports token-efficient highlights and full page content. |
 | **FileReadTool**                 | Enables reading and extracting data from files, supporting various file formats.               |
 | **FirecrawlSearchTool**          | A tool to search webpages using Firecrawl and return the results.                              |
 | **FirecrawlCrawlWebsiteTool**    | A tool for crawling webpages using Firecrawl.                                                  |

docs/en/guides/flows/mastering-flow-state.mdx

@@ -346,32 +346,47 @@ class SelectivePersistFlow(Flow):
         return f"Complete with count {self.state['count']}"
 ```
 
-#### Using a Custom Persistence Key
+#### Forking Persisted State
 
-By default, `@persist()` keys persisted state by the flow's auto-generated `state.id`. When your domain already has a natural identifier — for example a `conversation_id` that ties multiple flow runs to the same user session — pass it as the `key` argument and `@persist` will use that attribute as the flow UUID instead of `id`:
+`@persist` supports two distinct hydration modes on `kickoff` / `kickoff_async`. Use **resume** (`inputs["id"]`) to continue the same lineage; use **fork** (`restore_from_state_id`) to start a new lineage seeded from a snapshot:
+
+| | `state.id` after kickoff | `@persist` writes land under |
+|---|---|---|
+| `inputs["id"]` (resume) | supplied id | supplied id (extends history) |
+| `restore_from_state_id` (fork) | fresh id, or `inputs["id"]` if pinned | new id (source preserved) |
 
 ```python
-from crewai.flow.flow import Flow, listen, start
+from crewai.flow.flow import Flow, start
 from crewai.flow.persistence import persist
 from pydantic import BaseModel
 
-class ConversationState(BaseModel):
-    conversation_id: str
-    history: list[str] = []
+class CounterState(BaseModel):
+    id: str = ""
+    counter: int = 0
 
-@persist(key="conversation_id")
-class ConversationFlow(Flow[ConversationState]):
+@persist
+class CounterFlow(Flow[CounterState]):
     @start()
-    def greet(self):
-        self.state.history.append("hello")
-        return self.state.history
+    def step(self):
+        self.state.counter += 1
 
-# A second run with the same conversation_id reloads the prior state
-flow = ConversationFlow(conversation_id="user-42")
-flow.kickoff()
+# Run 1: fresh state, counter 0 -> 1
+flow_1 = CounterFlow()
+flow_1.kickoff()
+
+# Fork: hydrate from flow_1's latest snapshot, but write under a NEW state.id
+flow_2 = CounterFlow()
+flow_2.kickoff(restore_from_state_id=flow_1.state.id)
+# flow_2 starts with counter=1 (hydrated), then step() bumps it to 2.
+# flow_1's flow_uuid history is unchanged.
 ```
 
-For dict-based states `@persist` reads `state[key]`, and for Pydantic / object states it reads `getattr(state, key)`. If the named attribute is missing or falsy when state is being saved, `@persist` raises a `ValueError` like `Flow state is missing required persistence key 'conversation_id'`, so the failure surfaces immediately rather than silently dropping persisted data. Calling `@persist()` without `key` keeps the original behavior of using `state.id`.
+Behavior notes:
+
+- `restore_from_state_id` not found in persistence → the kickoff falls back silently to default behavior (mirrors the existing `inputs["id"]` resume not-found behavior). No exception is raised.
+- Combining `restore_from_state_id` with `from_checkpoint` raises a `ValueError` — they target different state systems (`@persist` vs. Checkpointing) and cannot be combined.
+- `restore_from_state_id=None` (default) is byte-identical to a kickoff without the parameter.
+- Pinning `inputs["id"]` while forking means the new run shares a persistence key with another flow — usually you want only `restore_from_state_id`.
 
 
 ## Advanced State Patterns

docs/en/tools/search-research/exasearchtool.mdx

@@ -1,11 +1,11 @@
 ---
 title: "Exa Search Tool"
-description: "Search the web using the Exa Search API to find the most relevant results for any query, with options for full page content, highlights, and summaries."
+description: "Search the web with Exa, the fastest and most accurate web search API. Get token-efficient highlights and full page content."
 icon: "magnifying-glass"
 mode: "wide"
 ---
 
-The `EXASearchTool` lets CrewAI agents search the web using the [Exa](https://exa.ai/) search API. It returns the most relevant results for any query, with options for full page content and AI-generated summaries.
+The `ExaSearchTool` lets CrewAI agents search the web using [Exa](https://exa.ai/), the fastest and most accurate web search API. It returns the most relevant results for any query, with options for token-efficient highlights and full page content.
 
 ## Installation
 
@@ -27,15 +27,15 @@ Get an API key from the [Exa dashboard](https://dashboard.exa.ai/api-keys).
 
 ## Example Usage
 
-Here's how to use the `EXASearchTool` within a CrewAI agent:
+Here's how to use the `ExaSearchTool` within a CrewAI agent:
 
 ```python
 import os
 from crewai import Agent, Task, Crew
-from crewai_tools import EXASearchTool
+from crewai_tools import ExaSearchTool
 
 # Initialize the tool
-exa_tool = EXASearchTool()
+exa_tool = ExaSearchTool()
 
 # Create an agent that uses the tool
 researcher = Agent(
@@ -66,11 +66,11 @@ print(result)
 
 ## Configuration Options
 
-The `EXASearchTool` accepts the following parameters during initialization:
+The `ExaSearchTool` accepts the following parameters during initialization:
 
 - `type` (str, optional): The search type to use. Defaults to `"auto"`. Options: `"auto"`, `"instant"`, `"fast"`, `"deep"`.
+- `highlights` (bool or dict, optional): Return token-efficient excerpts most relevant to the query instead of the full page. Defaults to `True`. Pass a dict like `{"max_characters": 4000}` to configure, or `False` to disable.
 - `content` (bool, optional): Whether to include full page content in results. Defaults to `False`.
-- `summary` (bool, optional): Whether to include AI-generated summaries of each result. Requires `content=True`. Defaults to `False`.
 - `api_key` (str, optional): Your Exa API key. Falls back to the `EXA_API_KEY` environment variable if not provided.
 - `base_url` (str, optional): Custom API server URL. Falls back to the `EXA_BASE_URL` environment variable if not provided.
 
@@ -83,28 +83,70 @@ When calling the tool (or when an agent invokes it), the following search parame
 
 ## Advanced Usage
 
-You can configure the tool with custom parameters for richer results:
+For most agent workflows we recommend `highlights` — it returns the most relevant excerpts from each result and uses far fewer tokens than full page content:
 
 ```python
-# Get full page content with AI summaries
-exa_tool = EXASearchTool(
-    content=True,
-    summary=True,
-    type="deep"
+# Get token-efficient excerpts most relevant to the query
+exa_tool = ExaSearchTool(
+    highlights=True,
+    type="auto",
 )
 
 # Use it in an agent
 agent = Agent(
-    role="Deep Researcher",
-    goal="Conduct thorough research with full content and summaries",
+    role="Researcher",
+    goal="Answer questions with current web data",
     tools=[exa_tool]
 )
 ```
 
+For thorough, multi-step searches, use `type="deep"`:
+
+```python
+exa_tool = ExaSearchTool(
+    highlights=True,
+    type="deep",
+)
+```
+
+For more on choosing between highlights and full content, see the [Exa search best practices](https://exa.ai/docs/reference/search-best-practices).
+
+## Using Exa via MCP
+
+You can also connect your agent to Exa's hosted MCP server. Pass your API key with the `x-api-key` header:
+
+```python
+from crewai import Agent
+from crewai.mcp import MCPServerHTTP
+
+agent = Agent(
+    role="Research Analyst",
+    goal="Find and analyze information on the web",
+    backstory="Expert researcher with access to Exa's tools",
+    mcps=[
+        MCPServerHTTP(
+            url="https://mcp.exa.ai/mcp",
+            headers={"x-api-key": "YOUR_EXA_API_KEY"},
+        ),
+    ],
+)
+```
+
+Get your API key from the [Exa dashboard](https://dashboard.exa.ai/api-keys). For more on MCP in CrewAI, see the [MCP overview](/en/mcp/overview).
+
 ## Features
 
+- **Token-Efficient Highlights**: Get the most relevant excerpts from each result, ~10x fewer tokens than full text
 - **Semantic Search**: Find results based on meaning, not just keywords
 - **Full Content Retrieval**: Get the full text of web pages alongside search results
-- **AI Summaries**: Get concise, AI-generated summaries of each result
 - **Date Filtering**: Limit results to specific time periods with published date filters
 - **Domain Filtering**: Restrict searches to specific domains
+
+<Note>
+`EXASearchTool` is a deprecated alias for `ExaSearchTool`. Existing imports continue to work but will emit a deprecation warning; please migrate to `ExaSearchTool`.
+</Note>
+
+## Resources
+
+- [Exa documentation](https://exa.ai/docs)
+- [Exa dashboard — manage API keys and usage](https://dashboard.exa.ai)

docs/enterprise-api.base.yaml

@@ -35,7 +35,7 @@ info:
 
     1. **Discover inputs** using `GET /inputs`
     2. **Start execution** using `POST /kickoff`
-    3. **Monitor progress** using `GET /{kickoff_id}/status`
+    3. **Monitor progress** using `GET /status/{kickoff_id}`
   version: 1.0.0
   contact:
     name: CrewAI Support
@@ -207,7 +207,7 @@ paths:
         "500":
           $ref: "#/components/responses/ServerError"
 
-  /{kickoff_id}/status:
+  /status/{kickoff_id}:
     get:
       summary: Get Execution Status
       description: |

docs/enterprise-api.en.yaml

@@ -35,7 +35,7 @@ info:
 
     1. **Discover inputs** using `GET /inputs`
     2. **Start execution** using `POST /kickoff`
-    3. **Monitor progress** using `GET /{kickoff_id}/status`
+    3. **Monitor progress** using `GET /status/{kickoff_id}`
   version: 1.0.0
   contact:
     name: CrewAI Support
@@ -207,7 +207,7 @@ paths:
         "500":
           $ref: "#/components/responses/ServerError"
 
-  /{kickoff_id}/status:
+  /status/{kickoff_id}:
     get:
       summary: Get Execution Status
       description: |

docs/enterprise-api.ko.yaml

@@ -84,7 +84,7 @@ paths:
         '500':
           $ref: '#/components/responses/ServerError'
 
-  /{kickoff_id}/status:
+  /status/{kickoff_id}:
     get:
       summary: 실행 상태 조회
       description: |

docs/enterprise-api.pt-BR.yaml

@@ -35,7 +35,7 @@ info:
 
     1. **Descubra os inputs** usando `GET /inputs`
     2. **Inicie a execução** usando `POST /kickoff`
-    3. **Monitore o progresso** usando `GET /{kickoff_id}/status`
+    3. **Monitore o progresso** usando `GET /status/{kickoff_id}`
   version: 1.0.0
   contact:
     name: CrewAI Suporte
@@ -120,7 +120,7 @@ paths:
         "500":
           $ref: "#/components/responses/ServerError"
 
-  /{kickoff_id}/status:
+  /status/{kickoff_id}:
     get:
       summary: Obter Status da Execução
       description: |

docs/ko/api-reference/introduction.mdx

@@ -26,7 +26,7 @@ CrewAI 엔터프라이즈 API 참고 자료에 오신 것을 환영합니다.
 </Step>
 
   <Step title="진행 상황 모니터링">
-    `GET /{kickoff_id}/status`를 사용하여 실행 상태를 확인하고 결과를 조회하세요.
+    `GET /status/{kickoff_id}`를 사용하여 실행 상태를 확인하고 결과를 조회하세요.
   </Step>
 </Steps>
 
@@ -65,7 +65,7 @@ https://your-crew-name.crewai.com
 
 1. **탐색**: `GET /inputs`를 호출하여 crew가 필요한 것을 파악합니다.
 2. **실행**: `POST /kickoff`를 통해 입력값을 제출하여 처리를 시작합니다.
-3. **모니터링**: 완료될 때까지 `GET /{kickoff_id}/status`를 주기적으로 조회합니다.
+3. **모니터링**: 완료될 때까지 `GET /status/{kickoff_id}`를 주기적으로 조회합니다.
 4. **결과**: 완료된 응답에서 최종 출력을 추출합니다.
 
 ## 오류 처리

docs/ko/api-reference/status.mdx

@@ -1,6 +1,6 @@
 ---
-title: "GET /{kickoff_id}/status"
+title: "GET /status/{kickoff_id}"
 description: "실행 상태 조회"
-openapi: "/enterprise-api.ko.yaml GET /{kickoff_id}/status"
+openapi: "/enterprise-api.ko.yaml GET /status/{kickoff_id}"
 mode: "wide"
 ---

docs/ko/changelog.mdx

@@ -4,6 +4,99 @@ description: "CrewAI의 제품 업데이트, 개선 사항 및 버그 수정"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="2026년 5월 4일">
+  ## v1.14.5a2
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.5a2)
+
+  ## 변경 사항
+
+  ### 버그 수정
+  - finally 블록에서 작업 출력 복원 수정
+  - 완료 토큰에 `thoughts_token_count` 포함
+  - 비동기 배치 플러시 간 작업 출력 보존
+  - `CrewAIRagAdapter`의 로더 호출에 kwargs 전달
+  - `result_as_answer`가 후크 차단 메시지를 최종 답변으로 반환하지 않도록 방지
+  - `result_as_answer`가 오류를 최종 답변으로 반환하지 않도록 방지
+  - 비동기 경로에서 출력 변환을 위해 `acall` 사용
+  - 에이전트 간 공유 LLM 중지 단어 변형 방지
+  - `convert_to_model`에서 `BaseModel` 입력 처리
+
+  ### 문서화
+  - 추가 환경 변수 문서화
+  - v1.14.5a1에 대한 변경 로그 및 버전 업데이트
+
+  ## 기여자
+
+  @NIK-TIGER-BILL, @greysonlalonde, @lorenzejay, @minasami-pr, @theCyberTech, @wishhyt
+
+</Update>
+
+<Update label="2026년 5월 1일">
+  ## v1.14.5a1
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.5a1)
+
+  ## 변경 사항
+
+  ### 기능
+  - `restore_from_state_id` 시작 매개변수 추가
+  - ExaSearchTool에 하이라이트 추가 및 EXASearchTool에서 이름 변경
+
+  ### 버그 수정
+  - 릴리스 흐름에서 crewai 핀 사이트 누락 수정
+  - 트레이스를 위한 기술 로딩 이벤트 보장
+
+  ### 문서
+  - v1.14.4에 대한 변경 로그 및 버전 업데이트
+
+  ## 기여자
+
+  @akaKuruma, @github-actions[bot], @greysonlalonde, @lorenzejay, @theishangoswami
+
+</Update>
+
+<Update label="2026년 5월 1일">
+  ## v1.14.4
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.4)
+
+  ## 변경 사항
+
+  ### 기능
+  - @persist에서 사용자 정의 지속성 키 지원 추가
+  - Azure OpenAI 공급자를 위한 응답 API 지원 추가
+  - Azure AI 추론 클라이언트에 credential_scopes 전달
+  - Vertex AI 작업 부하 신원 설정 가이드 추가
+  - Tavily Research 및 Research 가져오기 추가
+  - 검색, 연구 및 콘텐츠 추출을 위한 You.com MCP 도구 추가
+
+  ### 버그 수정
+  - JSON 정규 표현식이 유효한 JSON이 아닐 때의 fall through 수정
+  - 응답에 텍스트가 포함될 때 tool_calls를 보존하도록 수정
+  - instructor.from_provider에 base_url 및 api_key를 전달하도록 수정
+  - 기본 MCP 서버가 도구를 반환하지 않을 때 경고하고 빈 값을 반환하도록 수정
+  - 비스트리밍 핸들러에서 검증된 메시지 변수를 사용하도록 수정
+  - LLM 실패에 대한 크루 채팅 설명 도우미를 보호하도록 수정
+  - 호출 간 메시지 및 반복을 재설정하도록 수정
+  - replay 및 test를 통해 훈련된 에이전트 파일을 전달하도록 수정
+  - 추론 시 사용자 정의 훈련된 에이전트 파일을 존중하도록 수정
+  - 다중 모드 input_files에 대해 작업 전용 에이전트를 크루에 바인딩하도록 수정
+  - JSON 체크포인팅을 위해 가드레일 호출 가능 항목을 null로 직렬화하도록 수정
+  - 자기 참조 라우터를 피하기 위해 force_final_answer의 이름 변경 수정
+  - SSTI 수정을 위한 litellm 버전 증가; 수정할 수 없는 pip CVE 무시
+
+  ### 문서
+  - v1.14.4a1에 대한 변경 로그 및 버전 업데이트
+  - E2B 샌드박스 도구 페이지 추가
+  - Daytona 샌드박스 도구 문서 추가
+
+  ## 기여자
+
+  @EdwardIrby, @dependabot[bot], @factory-droid-oss, @factory-droid[bot], @greysonlalonde, @kunalk16, @lorenzejay, @lucasgomide, @manisrinivasan2k1, @mattatcha, @vinibrsl
+
+</Update>
+
 <Update label="2026년 4월 29일">
   ## v1.14.4a1
 

docs/ko/concepts/flows.mdx

@@ -373,32 +373,41 @@ class AnotherFlow(Flow[dict]):
         print("Method-level persisted runs:", self.state["runs"])
 ```
 
-### 사용자 지정 영속성 키
+### 영속 상태 포크하기
 
-기본적으로 `@persist`는 자동 생성된 `state.id` 필드를 영속성 키로 사용합니다. 여러 세션에 걸쳐 공유되는 `conversation_id`처럼 플로우에 자체 식별자가 있는 경우, `key` 인자를 전달하면 `@persist`가 해당 속성을 플로우 UUID로 사용합니다:
+`@persist`는 `kickoff` / `kickoff_async`에서 두 가지 별개의 하이드레이션 모드를 지원합니다:
+
+- `kickoff(inputs={"id": <uuid>})` — **재개(resume)**: 제공된 UUID에 대한 최신 스냅샷을 로드하고 동일한 `flow_uuid` 아래에서 계속 기록합니다. 기록이 확장됩니다.
+- `kickoff(restore_from_state_id=<uuid>)` — **포크(fork)**: 제공된 UUID에 대한 최신 스냅샷을 로드하고 새 실행의 상태를 하이드레이트한 후, 새로운 `state.id`(자동 생성, 또는 `inputs["id"]`가 고정된 경우 그 값)를 할당합니다. 새 실행의 `@persist` 기록은 새로운 `state.id` 아래에 저장되며, 원본 플로우의 기록은 보존됩니다.
 
 ```python
-from crewai.flow.flow import Flow, listen, start
+from crewai.flow.flow import Flow, start
 from crewai.flow.persistence import persist
 from pydantic import BaseModel
 
-class ConversationState(BaseModel):
-    conversation_id: str
-    turn: int = 0
+class CounterState(BaseModel):
+    id: str = ""
+    counter: int = 0
 
-@persist(key="conversation_id")  # 사용자 지정 필드를 영속성 키로 사용
-class ConversationFlow(Flow[ConversationState]):
+@persist
+class CounterFlow(Flow[CounterState]):
     @start()
-    def begin(self):
-        self.state.turn += 1
-        print(f"Conversation {self.state.conversation_id} turn {self.state.turn}")
+    def step(self):
+        self.state.counter += 1
+        print(f"[id={self.state.id}] counter={self.state.counter}")
 
-# 동일한 conversation_id로 다시 실행하면 이전 상태가 다시 로드됩니다
-flow = ConversationFlow(conversation_id="user-42")
-flow.kickoff()
+# 실행 1: 새 상태, counter 0 -> 1, flow_1.state.id 아래에 저장됨
+flow_1 = CounterFlow()
+flow_1.kickoff()
+
+# 포크: flow_1의 최신 스냅샷에서 하이드레이트하지만, 새 state.id를 사용
+flow_2 = CounterFlow()
+flow_2.kickoff(restore_from_state_id=flow_1.state.id)
+# flow_2.state.counter는 1(하이드레이트)로 시작하고, step()이 2로 증가시킵니다.
+# flow_2.state.id != flow_1.state.id; flow_1의 기록은 변경되지 않습니다.
 ```
 
-이 데코레이터는 dict 상태의 경우 `state[key]`에서, Pydantic / 객체 상태의 경우 `getattr(state, key)`에서 값을 읽습니다. 저장 시점에 지정된 속성이 없거나 falsy 값이면, `@persist`는 `Flow state is missing required persistence key 'conversation_id'`와 같은 `ValueError`를 발생시킵니다. `key`를 생략하면 기존 동작이 유지되어 `state.id`가 사용됩니다.
+제공된 `restore_from_state_id`가 어떤 영속 상태와도 일치하지 않으면, kickoff는 조용히 기본 동작으로 폴백됩니다 — 기존 `inputs["id"]`의 미발견 동작과 동일합니다. `restore_from_state_id`를 `from_checkpoint`와 결합하면 `ValueError`가 발생합니다; 하나의 하이드레이션 소스를 선택하세요. 포크 중 `inputs["id"]`를 고정하면 다른 플로우와 영속 키를 공유하게 됩니다 — 일반적으로 `restore_from_state_id`만 사용하는 것이 좋습니다.
 
 ### 작동 방식
 

docs/ko/concepts/production-architecture.mdx

@@ -146,15 +146,14 @@ class ProductionFlow(Flow[AppState]):
     # ...
 ```
 
-기본적으로 `@persist`는 자동 생성된 `state.id`를 저장된 상태의 키로 사용합니다. 애플리케이션에 이미 자연스러운 식별자가 있는 경우 — 예를 들어 같은 사용자 세션에 속한 여러 실행을 묶는 `conversation_id` — `key`로 전달하면 데코레이터가 해당 속성을 플로우 UUID로 사용합니다. 저장 시점에 지정된 속성이 없거나 falsy 값이면 `ValueError`가 발생합니다.
+기본적으로, `@persist`는 `kickoff(inputs={"id": <uuid>})`가 제공될 때 플로우를 재개하여 동일한 `flow_uuid` 기록을 확장합니다. 영속된 플로우를 새 계보로 **포크**하려면 — 이전 실행에서 상태를 하이드레이트하지만 새로운 `state.id` 아래에 기록 — `restore_from_state_id`를 전달하세요:
 
 ```python
-@persist(key="conversation_id")
-class ProductionFlow(Flow[AppState]):
-    # AppState는 conversation_id를 노출해야 합니다; 세션을 재개하면 이전 상태가 다시 로드됩니다
-    ...
+flow.kickoff(restore_from_state_id="<previous-run-state-id>")
 ```
 
+새 실행은 새로운 `state.id`(자동 생성, 또는 `inputs["id"]`가 고정된 경우 그 값)를 받아 `@persist` 기록이 원본의 기록을 확장하지 않도록 합니다. `from_checkpoint`와 결합하면 `ValueError`가 발생합니다; 하나의 하이드레이션 소스를 선택하세요.
+
 ## 요약
 
 - **Flow로 시작하세요.**

docs/ko/concepts/tools.mdx

@@ -132,7 +132,7 @@ crew.kickoff()
 | **DirectorySearchTool**           | 디렉터리 내에서 검색하는 RAG 도구로, 파일 시스템을 탐색할 때 유용합니다.                              |
 | **DOCXSearchTool**                | DOCX 문서 내에서 검색하는 데 특화된 RAG 도구로, Word 파일을 처리할 때 이상적입니다.                   |
 | **DirectoryReadTool**             | 디렉터리 구조와 그 내용을 읽고 처리하도록 지원하는 도구입니다.                                        |
-| **EXASearchTool**                 | 다양한 데이터 소스를 폭넓게 검색하기 위해 설계된 도구입니다.                                          |
+| **ExaSearchTool**                 | 다양한 데이터 소스를 폭넓게 검색하기 위해 설계된 도구입니다.                                          |
 | **FileReadTool**                  | 다양한 파일 형식을 지원하며 파일에서 데이터를 읽고 추출할 수 있는 도구입니다.                         |
 | **FirecrawlSearchTool**           | Firecrawl을 이용해 웹페이지를 검색하고 결과를 반환하는 도구입니다.                                    |
 | **FirecrawlCrawlWebsiteTool**     | Firecrawl을 사용해 웹페이지를 크롤링하는 도구입니다.                                                  |

docs/ko/guides/flows/mastering-flow-state.mdx

@@ -346,32 +346,47 @@ class SelectivePersistFlow(Flow):
         return f"Complete with count {self.state['count']}"
 ```
 
-#### 사용자 지정 영속성 키 사용하기
+#### 영속 상태 포크하기
 
-기본적으로 `@persist()`는 자동 생성된 `state.id`를 영속 상태의 키로 사용합니다. 도메인에 이미 자연스러운 식별자가 있는 경우 — 예를 들어 같은 사용자 세션에 속한 여러 플로우 실행을 묶는 `conversation_id` — `key` 인자로 전달하면 `@persist`는 `id` 대신 해당 속성을 플로우 UUID로 사용합니다:
+`@persist`는 `kickoff` / `kickoff_async`에서 두 가지 별개의 하이드레이션 모드를 지원합니다. 동일한 계보를 계속하려면 **재개**(`inputs["id"]`)를 사용하고, 스냅샷에서 시작하는 새 계보를 시작하려면 **포크**(`restore_from_state_id`)를 사용하세요:
+
+| | kickoff 후 `state.id` | `@persist` 기록 위치 |
+|---|---|---|
+| `inputs["id"]` (재개) | 제공된 id | 제공된 id (기록 확장) |
+| `restore_from_state_id` (포크) | 새 id, 또는 고정 시 `inputs["id"]` | 새 id (원본 보존) |
 
 ```python
-from crewai.flow.flow import Flow, listen, start
+from crewai.flow.flow import Flow, start
 from crewai.flow.persistence import persist
 from pydantic import BaseModel
 
-class ConversationState(BaseModel):
-    conversation_id: str
-    history: list[str] = []
+class CounterState(BaseModel):
+    id: str = ""
+    counter: int = 0
 
-@persist(key="conversation_id")
-class ConversationFlow(Flow[ConversationState]):
+@persist
+class CounterFlow(Flow[CounterState]):
     @start()
-    def greet(self):
-        self.state.history.append("hello")
-        return self.state.history
+    def step(self):
+        self.state.counter += 1
 
-# 동일한 conversation_id로 두 번째 실행 시 이전 상태가 다시 로드됩니다
-flow = ConversationFlow(conversation_id="user-42")
-flow.kickoff()
+# 실행 1: 새 상태, counter 0 -> 1
+flow_1 = CounterFlow()
+flow_1.kickoff()
+
+# 포크: flow_1의 최신 스냅샷에서 하이드레이트, 단 새 state.id에 기록
+flow_2 = CounterFlow()
+flow_2.kickoff(restore_from_state_id=flow_1.state.id)
+# flow_2는 counter=1(하이드레이트)로 시작하고, step()이 2로 증가시킵니다.
+# flow_1의 flow_uuid 기록은 변경되지 않습니다.
 ```
 
-dict 기반 상태의 경우 `@persist`는 `state[key]`를 읽고, Pydantic / 객체 상태의 경우 `getattr(state, key)`를 읽습니다. 상태가 저장될 때 지정된 속성이 없거나 falsy 값이면 `@persist`는 `Flow state is missing required persistence key 'conversation_id'`와 같은 `ValueError`를 발생시켜, 영속 데이터가 조용히 손실되는 대신 즉시 실패가 드러나도록 합니다. `key` 없이 `@persist()`를 호출하면 기존 동작대로 `state.id`가 사용됩니다.
+동작 노트:
+
+- `restore_from_state_id`가 영속에서 발견되지 않음 → kickoff는 조용히 기본 동작으로 폴백됩니다 (기존 `inputs["id"]`의 미발견 동작 미러링). 예외는 발생하지 않습니다.
+- `restore_from_state_id`를 `from_checkpoint`와 결합하면 `ValueError`가 발생합니다 — 서로 다른 상태 시스템(`@persist` 대 Checkpointing)을 대상으로 하므로 결합할 수 없습니다.
+- `restore_from_state_id=None`(기본값)은 매개변수 없는 kickoff와 바이트 단위로 동일합니다.
+- 포크 중 `inputs["id"]`를 고정하면 새 실행이 다른 플로우와 영속 키를 공유함을 의미합니다 — 일반적으로 `restore_from_state_id`만 사용하는 것이 좋습니다.
 
 ## 고급 상태 패턴
 

docs/ko/tools/search-research/exasearchtool.mdx

@@ -1,15 +1,15 @@
 ---
 title: EXA 검색 웹 로더
-description: EXASearchTool은 인터넷 전반에 걸쳐 텍스트의 내용에서 지정된 쿼리에 대한 시맨틱 검색을 수행하도록 설계되었습니다.
+description: ExaSearchTool은 인터넷 전반에 걸쳐 텍스트의 내용에서 지정된 쿼리에 대한 시맨틱 검색을 수행하도록 설계되었습니다.
 icon: globe-pointer
 mode: "wide"
 ---
 
-# `EXASearchTool`
+# `ExaSearchTool`
 
 ## 설명
 
-EXASearchTool은 텍스트의 내용을 기반으로 지정된 쿼리를 인터넷 전반에 걸쳐 의미론적으로 검색하도록 설계되었습니다.
+ExaSearchTool은 텍스트의 내용을 기반으로 지정된 쿼리를 인터넷 전반에 걸쳐 의미론적으로 검색하도록 설계되었습니다.
 사용자가 제공한 쿼리를 기반으로 가장 관련성 높은 검색 결과를 가져오고 표시하기 위해 [exa.ai](https://exa.ai/) API를 활용합니다.
 
 ## 설치
@@ -25,15 +25,15 @@ pip install 'crewai[tools]'
 다음 예제는 도구를 초기화하고 주어진 쿼리로 검색을 실행하는 방법을 보여줍니다:
 
 ```python Code
-from crewai_tools import EXASearchTool
+from crewai_tools import ExaSearchTool
 
 # Initialize the tool for internet searching capabilities
-tool = EXASearchTool()
+tool = ExaSearchTool()
 ```
 
 ## 시작 단계
 
-EXASearchTool을 효과적으로 사용하려면 다음 단계를 따르세요:
+ExaSearchTool을 효과적으로 사용하려면 다음 단계를 따르세요:
 
 <Steps>
     <Step title="패키지 설치">
@@ -47,7 +47,35 @@ EXASearchTool을 효과적으로 사용하려면 다음 단계를 따르세요:
     </Step>
 </Steps>
 
+## MCP를 통한 Exa 사용
+
+Exa가 호스팅하는 MCP 서버에 에이전트를 연결할 수도 있습니다. API 키는 `x-api-key` 헤더로 전달하세요:
+
+```python
+from crewai import Agent
+from crewai.mcp import MCPServerHTTP
+
+agent = Agent(
+    role="Research Analyst",
+    goal="Find and analyze information on the web",
+    backstory="Expert researcher with access to Exa's tools",
+    mcps=[
+        MCPServerHTTP(
+            url="https://mcp.exa.ai/mcp",
+            headers={"x-api-key": "YOUR_EXA_API_KEY"},
+        ),
+    ],
+)
+```
+
+API 키는 [Exa 대시보드](https://dashboard.exa.ai/api-keys)에서 발급받을 수 있습니다. CrewAI에서의 MCP 사용에 대한 자세한 내용은 [MCP 개요](/ko/mcp/overview)를 참고하세요.
+
 ## 결론
 
-`EXASearchTool`을 Python 프로젝트에 통합함으로써, 사용자는 애플리케이션 내에서 실시간으로 인터넷을 직접 검색할 수 있는 능력을 얻게 됩니다.
+`ExaSearchTool`을 Python 프로젝트에 통합함으로써, 사용자는 애플리케이션 내에서 실시간으로 인터넷을 직접 검색할 수 있는 능력을 얻게 됩니다.
 제공된 설정 및 사용 지침을 따르면, 이 도구를 프로젝트에 포함하는 과정이 간편하고 직관적입니다.
+
+## 참고 자료
+
+- [Exa 공식 문서](https://exa.ai/docs)
+- [Exa 대시보드 — API 키 및 사용량 관리](https://dashboard.exa.ai)

docs/pt-BR/api-reference/introduction.mdx

@@ -26,7 +26,7 @@ Bem-vindo à referência da API do CrewAI AMP. Esta API permite que você intera
 </Step>
 
   <Step title="Monitore o Progresso">
-    Use `GET /{kickoff_id}/status` para checar o status da execução e recuperar os resultados.
+    Use `GET /status/{kickoff_id}` para checar o status da execução e recuperar os resultados.
   </Step>
 </Steps>
 
@@ -65,7 +65,7 @@ Substitua `your-crew-name` pela URL real do seu crew no painel.
 
 1. **Descoberta**: Chame `GET /inputs` para entender o que seu crew precisa
 2. **Execução**: Envie os inputs via `POST /kickoff` para iniciar o processamento
-3. **Monitoramento**: Faça polling em `GET /{kickoff_id}/status` até a conclusão
+3. **Monitoramento**: Faça polling em `GET /status/{kickoff_id}` até a conclusão
 4. **Resultados**: Extraia o output final da resposta concluída
 
 ## Tratamento de Erros

docs/pt-BR/api-reference/status.mdx

@@ -1,6 +1,6 @@
 ---
-title: "GET /{kickoff_id}/status"
+title: "GET /status/{kickoff_id}"
 description: "Obter o status da execução"
-openapi: "/enterprise-api.pt-BR.yaml GET /{kickoff_id}/status"
+openapi: "/enterprise-api.pt-BR.yaml GET /status/{kickoff_id}"
 mode: "wide"
 ---

docs/pt-BR/changelog.mdx

@@ -4,6 +4,99 @@ description: "Atualizações de produto, melhorias e correções do CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="04 mai 2026">
+  ## v1.14.5a2
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.5a2)
+
+  ## O que Mudou
+
+  ### Correções de Bugs
+  - Corrigir a restauração da saída da tarefa no bloco finally
+  - Incluir `thoughts_token_count` nos tokens de conclusão
+  - Preservar as saídas das tarefas durante o descarregamento assíncrono em lote
+  - Encaminhar kwargs para chamadas de carregador em `CrewAIRagAdapter`
+  - Impedir que `result_as_answer` retorne mensagem de bloqueio de hook como resposta final
+  - Impedir que `result_as_answer` retorne erro como resposta final
+  - Usar `acall` para conversão de saída em caminhos assíncronos
+  - Prevenir a mutação de palavras de parada compartilhadas do LLM entre agentes
+  - Lidar com entrada `BaseModel` em `convert_to_model`
+
+  ### Documentação
+  - Documentar variáveis de ambiente adicionais
+  - Atualizar changelog e versão para v1.14.5a1
+
+  ## Contribuidores
+
+  @NIK-TIGER-BILL, @greysonlalonde, @lorenzejay, @minasami-pr, @theCyberTech, @wishhyt
+
+</Update>
+
+<Update label="01 mai 2026">
+  ## v1.14.5a1
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.5a1)
+
+  ## O que Mudou
+
+  ### Recursos
+  - Adicionar parâmetro de início `restore_from_state_id`
+  - Adicionar destaques ao ExaSearchTool e renomear de EXASearchTool
+
+  ### Correções de Bugs
+  - Corrigir sites de pinos do crewai ausentes no fluxo de lançamento
+  - Garantir eventos de carregamento de habilidades para rastros
+
+  ### Documentação
+  - Atualizar changelog e versão para v1.14.4
+
+  ## Contribuidores
+
+  @akaKuruma, @github-actions[bot], @greysonlalonde, @lorenzejay, @theishangoswami
+
+</Update>
+
+<Update label="01 mai 2026">
+  ## v1.14.4
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.4)
+
+  ## O que mudou
+
+  ### Recursos
+  - Adicionar suporte para chave de persistência personalizada em @persist
+  - Adicionar suporte à API de Respostas para o provedor Azure OpenAI
+  - Encaminhar credential_scopes para o cliente de Inferência da Azure AI
+  - Adicionar guia de configuração de identidade de carga de trabalho do Vertex AI
+  - Adicionar Tavily Research e obter Pesquisa
+  - Adicionar ferramentas MCP do You.com para pesquisa, pesquisa e extração de conteúdo
+
+  ### Correções de Bugs
+  - Corrigir falha quando a correspondência de regex JSON não é um JSON válido
+  - Corrigir para preservar tool_calls quando a resposta também contém texto
+  - Corrigir para encaminhar base_url e api_key para instructor.from_provider
+  - Corrigir para avisar e retornar vazio quando o servidor MCP nativo não retorna ferramentas
+  - Corrigir para usar a variável de mensagens validadas em manipuladores não-streaming
+  - Corrigir para proteger os ajudantes de descrição do chat da equipe contra falhas do LLM
+  - Corrigir para redefinir mensagens e iterações entre invocações
+  - Corrigir para encaminhar o arquivo de agentes treinados através de replay e teste
+  - Corrigir para honrar o arquivo de agentes treinados personalizados na inferência
+  - Corrigir para vincular agentes apenas de tarefa à equipe para arquivos de entrada multimodal
+  - Corrigir para serializar chamadas de guardrail como nulas para checkpointing JSON
+  - Corrigir renomeação de force_final_answer para evitar roteador autorreferencial
+  - Corrigir aumento de litellm para correção de SSTI; ignorar CVE pip não corrigível
+
+  ### Documentação
+  - Atualizar changelog e versão para v1.14.4a1
+  - Adicionar página de Ferramentas do Sandbox E2B
+  - Adicionar documentação de ferramentas do sandbox Daytona
+
+  ## Contributors
+
+  @EdwardIrby, @dependabot[bot], @factory-droid-oss, @factory-droid[bot], @greysonlalonde, @kunalk16, @lorenzejay, @lucasgomide, @manisrinivasan2k1, @mattatcha, @vinibrsl
+
+</Update>
+
 <Update label="29 abr 2026">
   ## v1.14.4a1
 

docs/pt-BR/concepts/flows.mdx

@@ -193,32 +193,41 @@ Para um controle mais granular, você pode aplicar @persist em métodos específ
 # (O código não é traduzido)
 ```
 
-### Chave de Persistência Personalizada
+### Forking de Estado Persistido
 
-Por padrão, `@persist` usa o campo `state.id` gerado automaticamente como chave de persistência. Se o seu flow já possui um identificador natural — por exemplo um `conversation_id` compartilhado entre sessões — você pode passar o argumento `key` e `@persist` usará esse atributo como UUID do flow:
+`@persist` suporta dois modos distintos de hidratação em `kickoff` / `kickoff_async`:
+
+- `kickoff(inputs={"id": <uuid>})` — **resume**: carrega o snapshot mais recente do UUID informado e continua escrevendo sob o mesmo `flow_uuid`. O histórico se estende.
+- `kickoff(restore_from_state_id=<uuid>)` — **fork**: carrega o snapshot mais recente do UUID informado, hidrata o estado da nova execução a partir dele, e atribui um novo `state.id` (auto-gerado, ou `inputs["id"]` se fixado). As escritas do `@persist` da nova execução vão para o novo `state.id`; o histórico do flow de origem é preservado.
 
 ```python
-from crewai.flow.flow import Flow, listen, start
+from crewai.flow.flow import Flow, start
 from crewai.flow.persistence import persist
 from pydantic import BaseModel
 
-class ConversationState(BaseModel):
-    conversation_id: str
-    turn: int = 0
+class CounterState(BaseModel):
+    id: str = ""
+    counter: int = 0
 
-@persist(key="conversation_id")  # Usa um campo personalizado como chave de persistência
-class ConversationFlow(Flow[ConversationState]):
+@persist
+class CounterFlow(Flow[CounterState]):
     @start()
-    def begin(self):
-        self.state.turn += 1
-        print(f"Conversa {self.state.conversation_id} turno {self.state.turn}")
+    def step(self):
+        self.state.counter += 1
+        print(f"[id={self.state.id}] counter={self.state.counter}")
 
-# Retomar a mesma conversa recarrega o estado anterior pelo conversation_id
-flow = ConversationFlow(conversation_id="user-42")
-flow.kickoff()
+# Execução 1: estado novo, counter 0 -> 1, persistido sob flow_1.state.id
+flow_1 = CounterFlow()
+flow_1.kickoff()
+
+# Fork: hidrata do snapshot mais recente de flow_1, mas usa um state.id NOVO
+flow_2 = CounterFlow()
+flow_2.kickoff(restore_from_state_id=flow_1.state.id)
+# flow_2.state.counter começa em 1 (hidratado), e step() incrementa para 2.
+# flow_2.state.id != flow_1.state.id; o histórico de flow_1 não é alterado.
 ```
 
-O decorador lê o valor em `state[key]` para estados do tipo dicionário ou `getattr(state, key)` para estados Pydantic / objetos. Se o atributo informado estiver ausente ou for *falsy* no momento de salvar, `@persist` lança um `ValueError` como `Flow state is missing required persistence key 'conversation_id'`. Quando `key` é omitido, o comportamento original é preservado e `state.id` continua sendo usado.
+Se o `restore_from_state_id` informado não corresponder a nenhum estado persistido, o kickoff retorna silenciosamente ao comportamento padrão — o mesmo comportamento do `inputs["id"]` quando não encontrado. Combinar `restore_from_state_id` com `from_checkpoint` lança um `ValueError`; escolha uma única fonte de hidratação. Fixar `inputs["id"]` durante o fork compartilha uma chave de persistência com outro flow — geralmente você quer apenas `restore_from_state_id`.
 
 ### Como Funciona
 

docs/pt-BR/concepts/production-architecture.mdx

@@ -146,15 +146,14 @@ class ProductionFlow(Flow[AppState]):
     # ...
 ```
 
-Por padrão, `@persist` usa o `state.id` gerado automaticamente como chave do estado salvo. Se a sua aplicação já tem um identificador natural — por exemplo um `conversation_id` que liga várias execuções à mesma sessão de usuário — passe-o como `key` e o decorador usará esse atributo como UUID do flow. Um `ValueError` é lançado se o atributo informado estiver ausente ou for *falsy* no momento de salvar.
+Por padrão, `@persist` retoma um flow quando `kickoff(inputs={"id": <uuid>})` é informado, estendendo o mesmo histórico do `flow_uuid`. Para **forkar** um flow persistido em uma nova linhagem — hidratar o estado a partir de uma execução anterior mas escrever sob um novo `state.id` — passe `restore_from_state_id`:
 
 ```python
-@persist(key="conversation_id")
-class ProductionFlow(Flow[AppState]):
-    # AppState precisa expor conversation_id; retomar a sessão recarrega o estado anterior
-    ...
+flow.kickoff(restore_from_state_id="<previous-run-state-id>")
 ```
 
+A nova execução recebe um novo `state.id` (auto-gerado, ou `inputs["id"]` se fixado), então suas escritas do `@persist` não estendem o histórico da origem. Combinar com `from_checkpoint` lança um `ValueError`; escolha uma única fonte de hidratação.
+
 ## Resumo
 
 - **Comece com um Flow.**

docs/pt-BR/concepts/tools.mdx

@@ -133,7 +133,7 @@ Aqui está uma lista das ferramentas disponíveis e suas descrições:
 | **DirectorySearchTool**          | Ferramenta RAG para busca em diretórios, útil para navegação em sistemas de arquivos.                |
 | **DOCXSearchTool**               | Ferramenta RAG voltada para busca em documentos DOCX, ideal para processar arquivos Word.            |
 | **DirectoryReadTool**            | Facilita a leitura e processamento de estruturas de diretórios e seus conteúdos.                     |
-| **EXASearchTool**                | Ferramenta projetada para buscas exaustivas em diversas fontes de dados.                             |
+| **ExaSearchTool**                | Ferramenta projetada para buscas exaustivas em diversas fontes de dados.                             |
 | **FileReadTool**                 | Permite a leitura e extração de dados de arquivos, suportando diversos formatos.                     |
 | **FirecrawlSearchTool**          | Ferramenta para buscar páginas web usando Firecrawl e retornar os resultados.                        |
 | **FirecrawlCrawlWebsiteTool**    | Ferramenta para rastrear páginas web utilizando o Firecrawl.                                         |

docs/pt-BR/guides/flows/mastering-flow-state.mdx

@@ -167,32 +167,47 @@ Para mais controle, você pode aplicar `@persist()` em métodos específicos:
 # código não traduzido
 ```
 
-#### Usando uma Chave de Persistência Personalizada
+#### Forking de Estado Persistido
 
-Por padrão, `@persist()` usa o `state.id` gerado automaticamente como chave do estado persistido. Quando seu domínio já possui um identificador natural — por exemplo um `conversation_id` que liga várias execuções do flow à mesma sessão de usuário — passe-o como argumento `key` e `@persist` usará esse atributo como UUID do flow em vez de `id`:
+`@persist` suporta dois modos distintos de hidratação em `kickoff` / `kickoff_async`. Use **resume** (`inputs["id"]`) para continuar a mesma linhagem; use **fork** (`restore_from_state_id`) para iniciar uma nova linhagem a partir de um snapshot:
+
+| | `state.id` após o kickoff | Escritas do `@persist` vão para |
+|---|---|---|
+| `inputs["id"]` (resume) | id informado | id informado (estende o histórico) |
+| `restore_from_state_id` (fork) | id novo, ou `inputs["id"]` se fixado | id novo (origem preservada) |
 
 ```python
-from crewai.flow.flow import Flow, listen, start
+from crewai.flow.flow import Flow, start
 from crewai.flow.persistence import persist
 from pydantic import BaseModel
 
-class ConversationState(BaseModel):
-    conversation_id: str
-    history: list[str] = []
+class CounterState(BaseModel):
+    id: str = ""
+    counter: int = 0
 
-@persist(key="conversation_id")
-class ConversationFlow(Flow[ConversationState]):
+@persist
+class CounterFlow(Flow[CounterState]):
     @start()
-    def greet(self):
-        self.state.history.append("hello")
-        return self.state.history
+    def step(self):
+        self.state.counter += 1
 
-# Uma segunda execução com o mesmo conversation_id recarrega o estado anterior
-flow = ConversationFlow(conversation_id="user-42")
-flow.kickoff()
+# Execução 1: estado novo, counter 0 -> 1
+flow_1 = CounterFlow()
+flow_1.kickoff()
+
+# Fork: hidrata do snapshot mais recente de flow_1, mas escreve sob um state.id NOVO
+flow_2 = CounterFlow()
+flow_2.kickoff(restore_from_state_id=flow_1.state.id)
+# flow_2 começa com counter=1 (hidratado), e step() incrementa para 2.
+# O histórico do flow_uuid de flow_1 não é alterado.
 ```
 
-Para estados baseados em dicionário `@persist` lê `state[key]`, e para estados Pydantic / objetos lê `getattr(state, key)`. Se o atributo informado estiver ausente ou for *falsy* no momento em que o estado for salvo, `@persist` lança um `ValueError` como `Flow state is missing required persistence key 'conversation_id'`, fazendo com que a falha apareça imediatamente em vez de descartar silenciosamente os dados persistidos. Chamar `@persist()` sem `key` mantém o comportamento original de usar `state.id`.
+Notas sobre o comportamento:
+
+- `restore_from_state_id` não encontrado na persistência → o kickoff retorna silenciosamente ao comportamento padrão (espelha o comportamento de `inputs["id"]` quando não encontrado). Nenhuma exceção é lançada.
+- Combinar `restore_from_state_id` com `from_checkpoint` lança um `ValueError` — eles miram sistemas de estado diferentes (`@persist` vs. Checkpointing) e não podem ser combinados.
+- `restore_from_state_id=None` (padrão) é byte-idêntico a um kickoff sem o parâmetro.
+- Fixar `inputs["id"]` durante o fork significa que a nova execução compartilha uma chave de persistência com outro flow — geralmente você quer apenas `restore_from_state_id`.
 
 ## Padrões Avançados de Estado
 

docs/pt-BR/tools/search-research/exasearchtool.mdx

@@ -1,15 +1,15 @@
 ---
 title: Carregador Web EXA Search
-description: O `EXASearchTool` foi projetado para realizar uma busca semântica para uma consulta especificada a partir do conteúdo de um texto em toda a internet.
+description: O `ExaSearchTool` foi projetado para realizar uma busca semântica para uma consulta especificada a partir do conteúdo de um texto em toda a internet.
 icon: globe-pointer
 mode: "wide"
 ---
 
-# `EXASearchTool`
+# `ExaSearchTool`
 
 ## Descrição
 
-O EXASearchTool foi projetado para realizar uma busca semântica para uma consulta especificada a partir do conteúdo de um texto em toda a internet.
+O ExaSearchTool foi projetado para realizar uma busca semântica para uma consulta especificada a partir do conteúdo de um texto em toda a internet.
 Ele utiliza a API da [exa.ai](https://exa.ai/) para buscar e exibir os resultados de pesquisa mais relevantes com base na consulta fornecida pelo usuário.
 
 ## Instalação
@@ -25,15 +25,15 @@ pip install 'crewai[tools]'
 O exemplo a seguir demonstra como inicializar a ferramenta e executar uma busca com uma consulta determinada:
 
 ```python Code
-from crewai_tools import EXASearchTool
+from crewai_tools import ExaSearchTool
 
 # Initialize the tool for internet searching capabilities
-tool = EXASearchTool()
+tool = ExaSearchTool()
 ```
 
 ## Etapas para Começar
 
-Para usar o EXASearchTool de forma eficaz, siga estas etapas:
+Para usar o ExaSearchTool de forma eficaz, siga estas etapas:
 
 <Steps>
     <Step title="Instalação do Pacote">
@@ -47,7 +47,35 @@ Para usar o EXASearchTool de forma eficaz, siga estas etapas:
     </Step>
 </Steps>
 
+## Usando o Exa via MCP
+
+Você também pode conectar seu agente ao servidor MCP hospedado pelo Exa. Passe sua chave de API no cabeçalho `x-api-key`:
+
+```python
+from crewai import Agent
+from crewai.mcp import MCPServerHTTP
+
+agent = Agent(
+    role="Research Analyst",
+    goal="Find and analyze information on the web",
+    backstory="Expert researcher with access to Exa's tools",
+    mcps=[
+        MCPServerHTTP(
+            url="https://mcp.exa.ai/mcp",
+            headers={"x-api-key": "YOUR_EXA_API_KEY"},
+        ),
+    ],
+)
+```
+
+Obtenha sua chave de API no [painel da Exa](https://dashboard.exa.ai/api-keys). Para mais informações sobre MCP no CrewAI, consulte a [visão geral do MCP](/pt-BR/mcp/overview).
+
 ## Conclusão
 
-Ao integrar o `EXASearchTool` em projetos Python, os usuários ganham a capacidade de realizar buscas relevantes e em tempo real pela internet diretamente de suas aplicações.
-Seguindo as orientações de configuração e uso fornecidas, a incorporação desta ferramenta em projetos torna-se simples e direta.
+Ao integrar o `ExaSearchTool` em projetos Python, os usuários ganham a capacidade de realizar buscas relevantes e em tempo real pela internet diretamente de suas aplicações.
+Seguindo as orientações de configuração e uso fornecidas, a incorporação desta ferramenta em projetos torna-se simples e direta.
+
+## Recursos
+
+- [Documentação do Exa](https://exa.ai/docs)
+- [Painel do Exa — gerenciar chaves de API e uso](https://dashboard.exa.ai)

lib/cli/README.md

@@ -0,0 +1,26 @@
+# crewai-cli
+
+CLI for CrewAI — scaffold, run, deploy and manage AI agent crews without
+installing the full framework.
+
+## Installation
+
+```bash
+pip install crewai-cli
+```
+
+This pulls in `crewai-core` (shared utilities) but not the `crewai` framework
+itself, so commands that don't need a crew loaded — `crewai version`,
+`crewai login`, `crewai org list`, `crewai config *`, `crewai traces *`,
+`crewai create`, `crewai template *` — work standalone.
+
+Commands that load a user's crew or flow (`crewai run`, `crewai train`,
+`crewai test`, `crewai chat`, `crewai replay`, `crewai reset-memories`,
+`crewai deploy push`, `crewai tool publish`) require `crewai` to be installed
+in the project's environment. They print a clear error if it is missing.
+
+To install both at once:
+
+```bash
+pip install crewai[cli]
+```

lib/cli/pyproject.toml

@@ -0,0 +1,43 @@
+[project]
+name = "crewai-cli"
+dynamic = ["version"]
+description = "CLI for CrewAI — scaffold, run, deploy and manage AI agent crews."
+readme = "README.md"
+authors = [
+    { name = "Joao Moura", email = "joao@crewai.com" }
+]
+requires-python = ">=3.10, <3.14"
+dependencies = [
+    "crewai-core>=1.14.5a2",
+    "click~=8.1.7",
+    "pydantic>=2.11.9,<2.13",
+    "pydantic-settings~=2.10.1",
+    "appdirs~=1.4.4",
+    "cryptography>=42.0",
+    "httpx~=0.28.1",
+    "pyjwt>=2.9.0,<3",
+    "rich>=13.7.1",
+    "tomli~=2.0.2",
+    "tomli-w~=1.1.0",
+    "packaging>=23.0",
+    "python-dotenv>=1.2.2,<2",
+    "uv~=0.11.6",
+]
+
+[project.urls]
+Homepage = "https://crewai.com"
+Documentation = "https://docs.crewai.com"
+Repository = "https://github.com/crewAIInc/crewAI"
+
+[project.scripts]
+crewai = "crewai_cli.cli:crewai"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.version]
+path = "src/crewai_cli/__init__.py"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/crewai_cli"]

lib/cli/src/crewai_cli/__init__.py

@@ -0,0 +1 @@
+__version__ = "1.14.5a2"

lib/cli/src/crewai_cli/add_crew_to_flow.py

@@ -1,9 +1,9 @@
 from pathlib import Path
 
 import click
+from crewai_core.printer import PRINTER
 
-from crewai.cli.utils import copy_template
-from crewai.utilities.printer import PRINTER
+from crewai_cli.utils import copy_template
 
 
 def add_crew_to_flow(crew_name: str) -> None:

lib/cli/src/crewai_cli/authentication/__init__.py

@@ -0,0 +1,8 @@
+"""CLI authentication entry point."""
+
+from __future__ import annotations
+
+from crewai_cli.authentication.main import AuthenticationCommand
+
+
+__all__ = ["AuthenticationCommand"]

lib/cli/src/crewai_cli/authentication/constants.py

@@ -0,0 +1,8 @@
+"""Re-export of authentication constants from ``crewai_core.auth.constants``."""
+
+from __future__ import annotations
+
+from crewai_core.auth.constants import ALGORITHMS as ALGORITHMS
+
+
+__all__ = ["ALGORITHMS"]

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

@@ -0,0 +1,60 @@
+"""CLI-side authentication wiring.
+
+Re-exports the OAuth2 primitives from ``crewai_core.auth`` and overrides the
+``_post_login`` hook to also log into the tool repository.
+"""
+
+from __future__ import annotations
+
+from crewai_core.auth.oauth2 import (
+    AuthenticationCommand as _BaseAuthenticationCommand,
+    Oauth2Settings as Oauth2Settings,
+    ProviderFactory as ProviderFactory,
+    console,
+)
+from crewai_core.settings import Settings
+
+
+__all__ = ["AuthenticationCommand", "Oauth2Settings", "ProviderFactory"]
+
+
+class AuthenticationCommand(_BaseAuthenticationCommand):
+    """CLI-side login that also signs the user into the tool repository."""
+
+    def _post_login(self) -> None:
+        self._login_to_tool_repository()
+
+    def _login_to_tool_repository(self) -> None:
+        from crewai_cli.tools.main import ToolCommand
+
+        try:
+            console.print(
+                "Now logging you in to the Tool Repository... ",
+                style="bold blue",
+                end="",
+            )
+
+            ToolCommand().login()
+
+            console.print(
+                "Success!\n",
+                style="bold green",
+            )
+
+            settings = Settings()
+
+            console.print(
+                f"You are now authenticated to the tool repository for organization [bold cyan]'{settings.org_name if settings.org_name else settings.org_uuid}'[/bold cyan]",
+                style="green",
+            )
+        except (Exception, SystemExit):
+            console.print(
+                "\n[bold yellow]Warning:[/bold yellow] Authentication with the Tool Repository failed.",
+                style="yellow",
+            )
+            console.print(
+                "Other features will work normally, but you may experience limitations "
+                "with downloading and publishing tools."
+                "\nRun [bold]crewai login[/bold] to try logging in again.\n",
+                style="yellow",
+            )

lib/cli/src/crewai_cli/authentication/providers/__init__.py

@@ -0,0 +1 @@
+"""OAuth2 authentication providers — re-exported from ``crewai_core.auth.providers``."""

lib/cli/src/crewai_cli/authentication/providers/auth0.py

@@ -0,0 +1,8 @@
+"""Re-export of ``Auth0Provider`` from ``crewai_core.auth.providers.auth0``."""
+
+from __future__ import annotations
+
+from crewai_core.auth.providers.auth0 import Auth0Provider as Auth0Provider
+
+
+__all__ = ["Auth0Provider"]

lib/cli/src/crewai_cli/authentication/providers/base_provider.py

@@ -0,0 +1,8 @@
+"""Re-export of ``BaseProvider`` from ``crewai_core.auth.providers.base_provider``."""
+
+from __future__ import annotations
+
+from crewai_core.auth.providers.base_provider import BaseProvider as BaseProvider
+
+
+__all__ = ["BaseProvider"]

lib/cli/src/crewai_cli/authentication/providers/entra_id.py

@@ -0,0 +1,8 @@
+"""Re-export of ``EntraIdProvider`` from ``crewai_core.auth.providers.entra_id``."""
+
+from __future__ import annotations
+
+from crewai_core.auth.providers.entra_id import EntraIdProvider as EntraIdProvider
+
+
+__all__ = ["EntraIdProvider"]

lib/cli/src/crewai_cli/authentication/providers/keycloak.py

@@ -0,0 +1,8 @@
+"""Re-export of ``KeycloakProvider`` from ``crewai_core.auth.providers.keycloak``."""
+
+from __future__ import annotations
+
+from crewai_core.auth.providers.keycloak import KeycloakProvider as KeycloakProvider
+
+
+__all__ = ["KeycloakProvider"]

lib/cli/src/crewai_cli/authentication/providers/okta.py

@@ -0,0 +1,8 @@
+"""Re-export of ``OktaProvider`` from ``crewai_core.auth.providers.okta``."""
+
+from __future__ import annotations
+
+from crewai_core.auth.providers.okta import OktaProvider as OktaProvider
+
+
+__all__ = ["OktaProvider"]

lib/cli/src/crewai_cli/authentication/providers/workos.py

@@ -0,0 +1,8 @@
+"""Re-export of ``WorkosProvider`` from ``crewai_core.auth.providers.workos``."""
+
+from __future__ import annotations
+
+from crewai_core.auth.providers.workos import WorkosProvider as WorkosProvider
+
+
+__all__ = ["WorkosProvider"]

lib/cli/src/crewai_cli/authentication/token.py

@@ -0,0 +1,11 @@
+"""Re-exports of authentication token helpers from ``crewai_core.auth.token``."""
+
+from __future__ import annotations
+
+from crewai_core.auth.token import (
+    AuthError as AuthError,
+    get_auth_token as get_auth_token,
+)
+
+
+__all__ = ["AuthError", "get_auth_token"]

lib/cli/src/crewai_cli/authentication/utils.py

@@ -0,0 +1,8 @@
+"""Re-export of ``validate_jwt_token`` from ``crewai_core.auth.utils``."""
+
+from __future__ import annotations
+
+from crewai_core.auth.utils import validate_jwt_token as validate_jwt_token
+
+
+__all__ = ["validate_jwt_token"]

lib/cli/src/crewai_cli/checkpoint_tui.py

@@ -21,7 +21,7 @@ from textual.widgets import (
     Tree,
 )
 
-from crewai.cli.checkpoint_cli import (
+from crewai_cli.checkpoint_cli import (
     _format_size,
     _is_sqlite,
     _list_json,

lib/cli/src/crewai_cli/cli.py

@@ -1,50 +1,66 @@
+from __future__ import annotations
+
 from importlib.metadata import version as get_version
 import os
 import subprocess
 from typing import 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.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.shared.token_manager import TokenManager
-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.utils import build_env_with_all_tool_credentials, read_toml
-from crewai.memory.storage.kickoff_task_outputs_storage import (
-    KickoffTaskOutputsSQLiteStorage,
+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.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
+
+
+def _get_cli_version() -> str:
+    """Return the best available version string for the CLI."""
+    # Prefer crewai version if installed (keeps existing UX)
+    try:
+        return get_version("crewai")
+    except Exception:  # noqa: S110
+        pass
+    try:
+        return get_version("crewai-cli")
+    except Exception:
+        return "unknown"
 
 
 @click.group()
-@click.version_option(get_version("crewai"))
+@click.version_option(_get_cli_version())
 def crewai() -> None:
     """Top-level command group for crewai."""
 
 
 @crewai.command(
     name="uv",
-    context_settings=dict(
-        ignore_unknown_options=True,
-    ),
+    context_settings={"ignore_unknown_options": True},
 )
 @click.argument("uv_args", nargs=-1, type=click.UNPROCESSED)
 def uv(uv_args: tuple[str, ...]) -> None:
@@ -105,7 +121,7 @@ def version(tools: bool) -> None:
 
     if tools:
         try:
-            tools_version = get_version("crewai")
+            tools_version = get_version("crewai-tools")
             click.echo(f"crewai tools version: {tools_version}")
         except Exception:
             click.echo("crewai tools not installed")
@@ -168,12 +184,9 @@ def replay(task_id: str, trained_agents_file: str | None) -> None:
 
 @crewai.command()
 def log_tasks_outputs() -> None:
-    """
-    Retrieve your latest crew.kickoff() task outputs.
-    """
+    """Retrieve your latest crew.kickoff() task outputs."""
     try:
-        storage = KickoffTaskOutputsSQLiteStorage()
-        tasks = storage.load()
+        tasks = load_task_outputs()
 
         if not tasks:
             click.echo(
@@ -231,11 +244,8 @@ def reset_memories(
     agent_knowledge: bool,
     all: bool,
 ) -> None:
-    """
-    Reset the crew memories (memory, knowledge, agent_knowledge, kickoff_outputs). This will delete all the data saved.
-    """
+    """Reset the crew memories (memory, knowledge, agent_knowledge, kickoff_outputs). This will delete all the data saved."""
     try:
-        # Treat legacy flags as --memory with a deprecation warning
         if long or short or entities:
             legacy_used = [
                 f
@@ -302,7 +312,7 @@ def memory(
 ) -> None:
     """Open the Memory TUI to browse scopes and recall memories."""
     try:
-        from crewai.cli.memory_tui import MemoryTUI
+        from crewai_cli.memory_tui import MemoryTUI
     except ImportError as exc:
         click.echo(
             "Textual is required for the memory TUI but could not be imported. "
@@ -365,10 +375,10 @@ def test(n_iterations: int, model: str, trained_agents_file: str | None) -> None
 
 
 @crewai.command(
-    context_settings=dict(
-        ignore_unknown_options=True,
-        allow_extra_args=True,
-    )
+    context_settings={
+        "ignore_unknown_options": True,
+        "allow_extra_args": True,
+    }
 )
 @click.pass_context
 def install(context: click.Context) -> None:
@@ -471,7 +481,7 @@ def deploy_validate() -> None:
     `crewai deploy push` run automatically, without contacting the platform.
     Exits non-zero if any blocking issues are found.
     """
-    from crewai.cli.deploy.validate import run_validate_command
+    from crewai_cli.deploy.validate import run_validate_command
 
     run_validate_command()
 
@@ -612,14 +622,12 @@ def triggers_run(trigger_path: str) -> None:
 
 @crewai.command()
 def chat() -> None:
-    """
-    Start a conversation with the Crew, collecting user-supplied inputs,
+    """Start a conversation with the Crew, collecting user-supplied inputs,
     and using the Chat LLM to generate responses.
     """
     click.secho(
         "\nStarting a conversation with the Crew\nType 'exit' or Ctrl+C to quit.\n",
     )
-
     run_chat()
 
 
@@ -784,16 +792,14 @@ def traces_enable() -> None:
     from rich.console import Console
     from rich.panel import Panel
 
-    from crewai.events.listeners.tracing.utils import update_user_data
-
     console = Console()
 
     update_user_data({"trace_consent": True, "first_execution_done": True})
 
     panel = Panel(
-        "✅ Trace collection has been enabled!\n\n"
+        "✅ Trace collection enabled.\n\n"
         "Your crew/flow executions will now send traces to CrewAI+.\n"
-        "Use 'crewai traces disable' to turn off trace collection.",
+        "Use 'crewai traces disable' to opt out.",
         title="Traces Enabled",
         border_style="green",
         padding=(1, 2),
@@ -807,16 +813,16 @@ def traces_disable() -> None:
     from rich.console import Console
     from rich.panel import Panel
 
-    from crewai.events.listeners.tracing.utils import update_user_data
-
     console = Console()
 
     update_user_data({"trace_consent": False, "first_execution_done": True})
 
     panel = Panel(
-        "❌ Trace collection has been disabled!\n\n"
-        "Your crew/flow executions will no longer send traces.\n"
-        "Use 'crewai traces enable' to turn trace collection back on.",
+        "❌ Trace collection disabled.\n\n"
+        "Your crew/flow executions will no longer send traces "
+        "(unless [bold]CREWAI_TRACING_ENABLED=true[/bold] is set in the environment, "
+        "which overrides the opt-out).\n"
+        "Use 'crewai traces enable' to opt back in.",
         title="Traces Disabled",
         border_style="red",
         padding=(1, 2),
@@ -832,11 +838,6 @@ def traces_status() -> None:
     from rich.panel import Panel
     from rich.table import Table
 
-    from crewai.events.listeners.tracing.utils import (
-        _load_user_data,
-        is_tracing_enabled,
-    )
-
     console = Console()
     user_data = _load_user_data()
 
@@ -883,13 +884,13 @@ def traces_status() -> None:
 @click.pass_context
 def checkpoint(ctx: click.Context, location: str) -> None:
     """Browse and inspect checkpoints. Launches a TUI when called without a subcommand."""
-    from crewai.cli.checkpoint_cli import _detect_location
+    from crewai_cli.checkpoint_cli import _detect_location
 
     location = _detect_location(location)
     ctx.ensure_object(dict)
     ctx.obj["location"] = location
     if ctx.invoked_subcommand is None:
-        from crewai.cli.checkpoint_tui import run_checkpoint_tui
+        from crewai_cli.checkpoint_tui import run_checkpoint_tui
 
         run_checkpoint_tui(location)
 
@@ -898,7 +899,7 @@ def checkpoint(ctx: click.Context, location: str) -> None:
 @click.argument("location", default="./.checkpoints")
 def checkpoint_list(location: str) -> None:
     """List checkpoints in a directory."""
-    from crewai.cli.checkpoint_cli import _detect_location, list_checkpoints
+    from crewai_cli.checkpoint_cli import _detect_location, list_checkpoints
 
     list_checkpoints(_detect_location(location))
 
@@ -907,7 +908,7 @@ def checkpoint_list(location: str) -> None:
 @click.argument("path", default="./.checkpoints")
 def checkpoint_info(path: str) -> None:
     """Show details of a checkpoint. Pass a file or directory for latest."""
-    from crewai.cli.checkpoint_cli import _detect_location, info_checkpoint
+    from crewai_cli.checkpoint_cli import _detect_location, info_checkpoint
 
     info_checkpoint(_detect_location(path))
 
@@ -917,7 +918,7 @@ def checkpoint_info(path: str) -> None:
 @click.pass_context
 def checkpoint_resume(ctx: click.Context, checkpoint_id: str | None) -> None:
     """Resume from a checkpoint. Defaults to the most recent."""
-    from crewai.cli.checkpoint_cli import resume_checkpoint
+    from crewai_cli.checkpoint_cli import resume_checkpoint
 
     resume_checkpoint(ctx.obj["location"], checkpoint_id)
 
@@ -928,7 +929,7 @@ def checkpoint_resume(ctx: click.Context, checkpoint_id: str | None) -> None:
 @click.pass_context
 def checkpoint_diff(ctx: click.Context, id1: str, id2: str) -> None:
     """Compare two checkpoints side-by-side."""
-    from crewai.cli.checkpoint_cli import diff_checkpoints
+    from crewai_cli.checkpoint_cli import diff_checkpoints
 
     diff_checkpoints(ctx.obj["location"], id1, id2)
 
@@ -950,7 +951,7 @@ def checkpoint_prune(
     ctx: click.Context, keep: int | None, older_than: str | None, dry_run: bool
 ) -> None:
     """Remove old checkpoints."""
-    from crewai.cli.checkpoint_cli import prune_checkpoints
+    from crewai_cli.checkpoint_cli import prune_checkpoints
 
     prune_checkpoints(ctx.obj["location"], keep, older_than, dry_run)
 

lib/cli/src/crewai_cli/command.py

@@ -1,11 +1,13 @@
+from __future__ import annotations
+
 import json
 
+from crewai_core.telemetry import Telemetry
 import httpx
 from rich.console import Console
 
-from crewai.cli.authentication.token import get_auth_token
-from crewai.cli.plus_api import PlusAPI
-from crewai.telemetry.telemetry import Telemetry
+from crewai_cli.authentication.token import get_auth_token
+from crewai_cli.plus_api import PlusAPI
 
 
 console = Console()
@@ -32,11 +34,10 @@ class PlusAPIMixin:
             raise SystemExit from None
 
     def _validate_response(self, response: httpx.Response) -> None:
-        """
-        Handle and display error messages from API responses.
+        """Handle and display error messages from API responses.
 
         Args:
-            response (httpx.Response): The response from the Plus API
+            response: The response from the Plus API.
         """
         try:
             json_response = response.json()

lib/cli/src/crewai_cli/config.py

@@ -0,0 +1,30 @@
+"""Re-exports of shared settings from ``crewai_core.settings``.
+
+Kept as a stable import path for the CLI; new code should import from
+``crewai_core.settings`` directly.
+"""
+
+from __future__ import annotations
+
+from crewai_core.settings import (
+    CLI_SETTINGS_KEYS as CLI_SETTINGS_KEYS,
+    DEFAULT_CLI_SETTINGS as DEFAULT_CLI_SETTINGS,
+    DEFAULT_CONFIG_PATH as DEFAULT_CONFIG_PATH,
+    HIDDEN_SETTINGS_KEYS as HIDDEN_SETTINGS_KEYS,
+    READONLY_SETTINGS_KEYS as READONLY_SETTINGS_KEYS,
+    USER_SETTINGS_KEYS as USER_SETTINGS_KEYS,
+    Settings as Settings,
+    get_writable_config_path as get_writable_config_path,
+)
+
+
+__all__ = [
+    "CLI_SETTINGS_KEYS",
+    "DEFAULT_CLI_SETTINGS",
+    "DEFAULT_CONFIG_PATH",
+    "HIDDEN_SETTINGS_KEYS",
+    "READONLY_SETTINGS_KEYS",
+    "USER_SETTINGS_KEYS",
+    "Settings",
+    "get_writable_config_path",
+]

lib/cli/src/crewai_cli/create_crew.py

@@ -5,13 +5,13 @@ import sys
 import click
 import tomli
 
-from crewai.cli.constants import ENV_VARS, MODELS
-from crewai.cli.provider import (
+from crewai_cli.constants import ENV_VARS, MODELS
+from crewai_cli.provider import (
     get_provider_data,
     select_model,
     select_provider,
 )
-from crewai.cli.utils import copy_template, load_env_vars, write_env_file
+from crewai_cli.utils import copy_template, load_env_vars, write_env_file
 
 
 def get_reserved_script_names() -> set[str]:

lib/cli/src/crewai_cli/create_flow.py

@@ -2,8 +2,7 @@ from pathlib import Path
 import shutil
 
 import click
-
-from crewai.telemetry import Telemetry
+from crewai_core.telemetry import Telemetry
 
 
 def create_flow(name: str) -> None:
@@ -18,7 +17,6 @@ def create_flow(name: str) -> None:
         click.secho(f"Error: Folder {folder_name} already exists.", fg="red")
         return
 
-    # Initialize telemetry
     telemetry = Telemetry()
     telemetry.flow_creation_span(class_name)
 

lib/cli/src/crewai_cli/crew_chat.py

@@ -0,0 +1,23 @@
+"""Wrapper for the crew chat command.
+
+Delegates to ``crewai.utilities.crew_chat.run_chat`` when the full crewai
+package is installed, otherwise prints a helpful error message.
+"""
+
+from __future__ import annotations
+
+import click
+
+
+def run_chat() -> None:
+    try:
+        from crewai.utilities.crew_chat import run_chat as _run_chat
+    except ImportError:
+        click.secho(
+            "The 'chat' command requires the full crewai package.\n"
+            "Install it with: pip install crewai",
+            fg="red",
+        )
+        raise SystemExit(1) from None
+
+    _run_chat()

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

@@ -2,10 +2,10 @@ from typing import Any
 
 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.utils import fetch_and_json_env_file, get_project_name
+from crewai_cli import git
+from crewai_cli.command import BaseCommand, PlusAPIMixin
+from crewai_cli.deploy.validate import validate_project
+from crewai_cli.utils import fetch_and_json_env_file, get_project_name
 
 
 console = Console()

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

@@ -40,7 +40,7 @@ from typing import Any
 
 from rich.console import Console
 
-from crewai.cli.utils import parse_toml
+from crewai_cli.utils import parse_toml
 
 
 console = Console()
@@ -438,7 +438,7 @@ class DeployValidator:
             "import json, sys, traceback, os\n"
             "os.chdir(sys.argv[1])\n"
             "try:\n"
-            "    from crewai.cli.utils import get_crews, get_flows\n"
+            "    from crewai.utilities.project_utils import get_crews, get_flows\n"
             "    is_flow = sys.argv[2] == 'flow'\n"
             "    if is_flow:\n"
             "        instances = get_flows()\n"

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

@@ -4,10 +4,10 @@ from typing import Any, cast
 import httpx
 from rich.console import Console
 
-from crewai.cli.authentication.main import Oauth2Settings, ProviderFactory
-from crewai.cli.command import BaseCommand
-from crewai.cli.settings.main import SettingsCommand
-from crewai.utilities.version import get_crewai_version
+from crewai_cli.authentication.main import Oauth2Settings, ProviderFactory
+from crewai_cli.command import BaseCommand
+from crewai_cli.settings.main import SettingsCommand
+from crewai_cli.version import get_crewai_version
 
 
 console = Console()

lib/cli/src/crewai_cli/evaluate_crew.py

@@ -1,9 +1,9 @@
 import subprocess
 
 import click
+from crewai_core.constants import CREWAI_TRAINED_AGENTS_FILE_ENV
 
-from crewai.cli.utils import build_env_with_all_tool_credentials
-from crewai.utilities.constants import CREWAI_TRAINED_AGENTS_FILE_ENV
+from crewai_cli.utils import build_env_with_all_tool_credentials
 
 
 def evaluate_crew(

lib/cli/src/crewai_cli/install_crew.py

@@ -2,7 +2,7 @@ import subprocess
 
 import click
 
-from crewai.cli.utils import build_env_with_all_tool_credentials
+from crewai_cli.utils import build_env_with_all_tool_credentials
 
 
 # Be mindful about changing this.

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

@@ -2,8 +2,8 @@ from httpx import HTTPStatusError
 from rich.console import Console
 from rich.table import Table
 
-from crewai.cli.command import BaseCommand, PlusAPIMixin
-from crewai.cli.config import Settings
+from crewai_cli.command import BaseCommand, PlusAPIMixin
+from crewai_cli.config import Settings
 
 
 console = Console()

lib/cli/src/crewai_cli/plus_api.py

@@ -0,0 +1,12 @@
+"""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.
+"""
+
+from __future__ import annotations
+
+from crewai_core.plus_api import PlusAPI as PlusAPI
+
+
+__all__ = ["PlusAPI"]

lib/cli/src/crewai_cli/provider.py

@@ -10,7 +10,7 @@ import certifi
 import click
 import httpx
 
-from crewai.cli.constants import JSON_URL, MODELS, PROVIDERS
+from crewai_cli.constants import JSON_URL, MODELS, PROVIDERS
 
 
 def select_choice(prompt_message: str, choices: Sequence[str]) -> str | None:

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

@@ -11,7 +11,7 @@ from rich.console import Console
 from rich.panel import Panel
 from rich.text import Text
 
-from crewai.cli.command import BaseCommand
+from crewai_cli.command import BaseCommand
 
 
 logger = logging.getLogger(__name__)

lib/cli/src/crewai_cli/replay_from_task.py

@@ -1,9 +1,9 @@
 import subprocess
 
 import click
+from crewai_core.constants import CREWAI_TRAINED_AGENTS_FILE_ENV
 
-from crewai.cli.utils import build_env_with_all_tool_credentials
-from crewai.utilities.constants import CREWAI_TRAINED_AGENTS_FILE_ENV
+from crewai_cli.utils import build_env_with_all_tool_credentials
 
 
 def replay_task_command(task_id: str, trained_agents_file: str | None = None) -> None:

lib/cli/src/crewai_cli/reset_memories_command.py

@@ -0,0 +1,31 @@
+"""Wrapper for the reset-memories command.
+
+Delegates to ``crewai.utilities.reset_memories`` when the full crewai
+package is installed, otherwise prints a helpful error message.
+"""
+
+from __future__ import annotations
+
+import click
+
+
+def reset_memories_command(
+    memory: bool,
+    knowledge: bool,
+    agent_knowledge: bool,
+    kickoff_outputs: bool,
+    all: bool,
+) -> None:
+    try:
+        from crewai.utilities.reset_memories import (
+            reset_memories_command as _reset,
+        )
+    except ImportError:
+        click.secho(
+            "The 'reset-memories' command requires the full crewai package.\n"
+            "Install it with: pip install crewai",
+            fg="red",
+        )
+        raise SystemExit(1) from None
+
+    _reset(memory, knowledge, agent_knowledge, kickoff_outputs, all)

lib/cli/src/crewai_cli/run_crew.py

@@ -2,11 +2,11 @@ from enum import Enum
 import subprocess
 
 import click
+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.utilities.constants import CREWAI_TRAINED_AGENTS_FILE_ENV
-from crewai.utilities.version import get_crewai_version
+from crewai_cli.utils import build_env_with_all_tool_credentials, read_toml
+from crewai_cli.version import get_crewai_version
 
 
 class CrewType(Enum):

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

@@ -5,9 +5,9 @@ from typing import Any
 from rich.console import Console
 from rich.table import Table
 
-from crewai.cli.command import BaseCommand
-from crewai.cli.config import HIDDEN_SETTINGS_KEYS, READONLY_SETTINGS_KEYS, Settings
-from crewai.events.listeners.tracing.utils import _load_user_data
+from crewai_cli.command import BaseCommand
+from crewai_cli.config import HIDDEN_SETTINGS_KEYS, READONLY_SETTINGS_KEYS, Settings
+from crewai_cli.user_data import _load_user_data
 
 
 console = Console()
@@ -91,7 +91,7 @@ class SettingsCommand(BaseCommand):
                 style="bold red",
             )
             console.print("Available keys:", style="yellow")
-            for field_name in Settings.model_fields.keys():
+            for field_name in Settings.model_fields:
                 if field_name not in readonly_settings:
                     console.print(f"  - {field_name}", style="yellow")
             raise SystemExit(1)

lib/cli/src/crewai_cli/shared/token_manager.py

@@ -0,0 +1,12 @@
+"""Re-export of ``crewai_core.token_manager.TokenManager``.
+
+Kept as a stable import path for the CLI; new code should import from
+``crewai_core.token_manager`` directly.
+"""
+
+from __future__ import annotations
+
+from crewai_core.token_manager import TokenManager as TokenManager
+
+
+__all__ = ["TokenManager"]

lib/cli/src/crewai_cli/task_outputs.py

@@ -0,0 +1,67 @@
+"""Lightweight SQLite reader for kickoff task outputs.
+
+Only used by the ``crewai log-tasks-outputs`` CLI command.  Depends solely on
+the standard library + *appdirs* so crewai-cli can read stored outputs without
+importing the full crewai framework.
+"""
+
+from __future__ import annotations
+
+import json
+import logging
+from pathlib import Path
+import sqlite3
+from typing import Any
+
+from crewai_cli.user_data import _db_storage_path
+
+
+logger = logging.getLogger(__name__)
+
+
+def load_task_outputs(db_path: str | None = None) -> list[dict[str, Any]]:
+    """Return all rows from the kickoff task outputs database."""
+    if db_path is None:
+        db_path = str(Path(_db_storage_path()) / "latest_kickoff_task_outputs.db")
+
+    if not Path(db_path).exists():
+        return []
+
+    try:
+        with sqlite3.connect(db_path) as conn:
+            conn.row_factory = sqlite3.Row
+            cursor = conn.cursor()
+            cursor.execute("""
+                SELECT task_id, expected_output, output, task_index,
+                       inputs, was_replayed, timestamp
+                FROM latest_kickoff_task_outputs
+                ORDER BY task_index
+            """)
+            rows = cursor.fetchall()
+    except sqlite3.Error as e:
+        logger.error("Failed to load task outputs: %s", e)
+        return []
+
+    return [
+        {
+            "task_id": row["task_id"],
+            "expected_output": row["expected_output"],
+            "output": _safe_json_loads(row["output"]),
+            "task_index": row["task_index"],
+            "inputs": _safe_json_loads(row["inputs"]),
+            "was_replayed": row["was_replayed"],
+            "timestamp": row["timestamp"],
+        }
+        for row in rows
+    ]
+
+
+def _safe_json_loads(value: str | None) -> Any:
+    """Decode a JSON column tolerantly: NULL/blank/corrupt → None."""
+    if not value:
+        return None
+    try:
+        return json.loads(value)
+    except (json.JSONDecodeError, TypeError) as e:
+        logger.warning("Failed to decode JSON column: %s", e)
+        return None

lib/cli/src/crewai_cli/templates/AGENTS.md

@@ -774,7 +774,7 @@ def calculator(expression: str) -> str:
 ```
 
 ### Built-in Tools (install with `uv add crewai-tools`)
-Web/Search: SerperDevTool, ScrapeWebsiteTool, WebsiteSearchTool, EXASearchTool, FirecrawlSearchTool
+Web/Search: SerperDevTool, ScrapeWebsiteTool, WebsiteSearchTool, ExaSearchTool, FirecrawlSearchTool
 Documents: FileReadTool, DirectoryReadTool, PDFSearchTool, DOCXSearchTool, CSVSearchTool, JSONSearchTool, XMLSearchTool, MDXSearchTool
 Code: CodeInterpreterTool, CodeDocsSearchTool, GithubSearchTool
 Media: DALL-E Tool, YoutubeChannelSearchTool, YoutubeVideoSearchTool