fix: only treat interpolatable placeholders as crew inputs

* Migrate @listen/@router runtime to read from FlowDefinition

The runtime now resolves listener conditions, router status, and emit
values from `FlowMethodDefinition` instead of legacy method metadata and
the `_listeners`/`_routers`/`_router_emit` registries.

* Evaluate AND/OR listener conditions over the definition shape via
  `_evaluate_definition_condition`
* Drop the class registries and the `FlowMeta` extraction that built
  them; stop stamping `__trigger_methods__`, `__is_router__`,
  `__router_emit__`, and friends
* `@human_feedback` emit now lives only on its config

* Simplify conditionals DSL

conftest.py

@@ -11,7 +11,99 @@ from typing import Any
 
 from dotenv import load_dotenv
 import pytest
-from vcr.request import Request  # type: ignore[import-untyped]
+
+
+def _patch_vcrpy_aiohttp_compat() -> None:
+    """Keep vcrpy's aiohttp stub working under aiohttp 3.14.0.
+
+    aiohttp 3.14.0 (pulled in to fix GHSA-jg22-mg44-37j8 and GHSA-hg6j-4rv6-33pg):
+      * removed ``aiohttp.streams.AsyncStreamReaderMixin`` (folded into ``StreamReader``),
+        which vcrpy's ``MockStream`` still subclasses -- vcr's patch machinery then raises
+        ``AttributeError`` at collection time; and
+      * added a required ``stream_writer`` keyword-only arg to ``ClientResponse.__init__``,
+        which vcrpy's ``MockClientResponse`` does not pass -- raising ``TypeError`` at
+        cassette playback.
+
+    Restore the mixin, then rebuild ``MockClientResponse``'s ``super().__init__`` call from
+    the live ``ClientResponse`` signature (defaulting every required keyword-only arg to
+    ``None``, mirroring vcrpy's original call) so it also survives future aiohttp additions.
+    """
+    import asyncio
+    import inspect
+
+    from aiohttp import streams
+    from aiohttp.client_reqrep import ClientResponse
+
+    if not hasattr(streams, "AsyncStreamReaderMixin"):
+
+        class AsyncStreamReaderMixin:
+            __slots__ = ()
+
+            def __aiter__(self) -> streams.AsyncStreamIterator[bytes]:
+                return streams.AsyncStreamIterator(self.readline)  # type: ignore[attr-defined]
+
+            def iter_chunked(self, n: int) -> streams.AsyncStreamIterator[bytes]:
+                return streams.AsyncStreamIterator(lambda: self.read(n))  # type: ignore[attr-defined]
+
+            def iter_any(self) -> streams.AsyncStreamIterator[bytes]:
+                return streams.AsyncStreamIterator(self.readany)  # type: ignore[attr-defined]
+
+            def iter_chunks(self) -> streams.ChunkTupleAsyncStreamIterator:
+                return streams.ChunkTupleAsyncStreamIterator(self)  # type: ignore[arg-type]
+
+        streams.AsyncStreamReaderMixin = AsyncStreamReaderMixin  # type: ignore[attr-defined]
+
+    # Importing the stub builds MockStream/MockClientResponse, so it must run after the
+    # mixin is restored above.
+    import vcr.stubs.aiohttp_stubs as aiohttp_stubs  # type: ignore[import-untyped]
+
+    if getattr(aiohttp_stubs.MockClientResponse, "_crewai_aiohttp_patched", False):
+        return
+
+    keyword_only = [
+        name
+        for name, param in inspect.signature(ClientResponse.__init__).parameters.items()
+        if param.kind is inspect.Parameter.KEYWORD_ONLY
+    ]
+
+    class _NullStreamWriter:
+        # aiohttp 3.14.0 reads stream_writer.output_size in the "request already
+        # sent" branch (writer is None), so None is not enough -- supply a stub.
+        output_size = 0
+
+    fallback_loop: list[asyncio.AbstractEventLoop] = []
+
+    def _resolve_loop() -> asyncio.AbstractEventLoop:
+        # MockClientResponse is normally built inside aiohttp's running loop, so
+        # prefer that. In a sync context there is no running loop; avoid
+        # asyncio.get_event_loop(), which on 3.12+ emits a DeprecationWarning
+        # (and can RuntimeError) when no current loop is set. Use one cached
+        # loop instead -- the mock only stores it and calls loop.get_debug().
+        try:
+            return asyncio.get_running_loop()
+        except RuntimeError:
+            if not fallback_loop:
+                fallback_loop.append(asyncio.new_event_loop())
+            return fallback_loop[0]
+
+    def _mock_client_response_init(
+        self: Any, method: str, url: Any, request_info: Any = None
+    ) -> None:
+        kwargs: dict[str, Any] = dict.fromkeys(keyword_only)
+        kwargs["request_info"] = request_info
+        if "loop" in kwargs:
+            kwargs["loop"] = _resolve_loop()
+        if "stream_writer" in kwargs:
+            kwargs["stream_writer"] = _NullStreamWriter()
+        ClientResponse.__init__(self, method, url, **kwargs)
+
+    aiohttp_stubs.MockClientResponse.__init__ = _mock_client_response_init
+    aiohttp_stubs.MockClientResponse._crewai_aiohttp_patched = True
+
+
+_patch_vcrpy_aiohttp_compat()
+
+from vcr.request import Request  # type: ignore[import-untyped]  # noqa: E402
 
 
 try:

docs/ar/changelog.mdx

@@ -4,6 +4,58 @@ description: "تحديثات المنتج والتحسينات وإصلاحات
 icon: "clock"
 mode: "wide"
 ---
+<Update label="8 يونيو 2026">
+  ## v1.14.7a3
+
+  [عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7a3)
+
+  ## ما الذي تغير
+
+  ### إصلاحات الأخطاء
+  - إصلاح تعرض `ask_for_human_input` في `AgentExecutor` التجريبي
+  - حل مشكلات CVEs الخاصة بـ pip-audit لـ `aiohttp`، `docling`، `docling-core`، و `pip`
+
+  ### إعادة هيكلة
+  - نقل `@start` لقراءة من `FlowDefinition`
+
+  ### الوثائق
+  - تحديث سجل التغييرات والإصدار لـ v1.14.7a2
+
+  ## المساهمون
+
+  @greysonlalonde، @lorenzejay، @vinibrsl
+
+</Update>
+
+<Update label="5 يونيو 2026">
+  ## v1.14.7a2
+
+  [عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7a2)
+
+  ## ما الذي تغير
+
+  ### الميزات
+  - إضافة دعم تتبع تدفقات المحادثة.
+  - تحديث وثائق تدفق المحادثة لاستخدام `handle_turn`.
+  - عرض السبب الحقيقي لإنهاء المحادثة، ومعلمات العينة، و`response.id` في أحداث LLM.
+  - تصنيف مشغلات DSL كزخارف واعية بالمسار.
+  - تنفيذ واجهة برمجة التطبيقات للدردشة لتدفقات المحادثة.
+  - جعل قفل الخلفية قابلاً للتجاوز في متجر القفل.
+  - تقسيم أحادي تدفق DSL إلى وحدات زخرفية مركزة.
+  - تسطيح استخدام ذاكرة التخزين المؤقت LiteLLM/أعداد الأسباب الفرعية في `_usage_to_dict`.
+  - بناء `FlowDefinition` من بيانات التعريف الخاصة بتدفق DSL.
+
+  ### الوثائق
+  - إضافة دليل NVIDIA Nemotron LLM.
+  - توثيق عمليات نشر المونوريبو.
+  - تحديث سجل التغييرات والإصدار لـ v1.14.7a1.
+
+  ## المساهمون
+
+  @alex-clawd, @gvieira, @lorenzejay, @lucasgomide, @mattatcha, @vinibrsl
+
+</Update>
+
 <Update label="3 يونيو 2026">
   ## v1.14.7a1
 

docs/ar/enterprise/guides/deploy-to-amp.mdx

@@ -164,6 +164,12 @@ crewai deploy remove <deployment_id>
       ![اختيار المستودع](/images/enterprise/select-repo.png)
     </Frame>
 
+    <Tip>
+      إذا كان Crew أو Flow داخل مجلد فرعي في monorepo، فوسّع **Advanced**
+      وعيّن دليل عمل قبل النشر. راجع
+      [النشر من Monorepo](/ar/enterprise/guides/monorepo-deployments).
+    </Tip>
+
   </Step>
 
   <Step title="تعيين متغيرات البيئة">

docs/ar/enterprise/guides/monorepo-deployments.mdx

@@ -0,0 +1,220 @@
+---
+title: "النشر من Monorepo"
+description: "انشر Crew أو Flow من مجلد فرعي داخل مستودع أكبر"
+icon: "folder-tree"
+mode: "wide"
+---
+
+<Note>
+  استخدم دليل عمل عندما يكون Crew أو Flow داخل مستودع أكبر. يتحقق CrewAI AMP
+  من الأتمتة ويبنيها ويشغلها من ذلك المجلد الفرعي بدلاً من جذر المستودع.
+</Note>
+
+## متى تستخدم ذلك
+
+يكون النشر من monorepo مفيداً عندما يحتوي مستودع واحد على عدة أتمتات أو حزم
+مشتركة أو كود تطبيقات آخر:
+
+```text
+company-ai/
+|-- uv.lock
+|-- packages/
+|   `-- shared_tools/
+`-- crews/
+    |-- support_agent/
+    |   |-- pyproject.toml
+    |   `-- src/
+    |       `-- support_agent/
+    |           |-- main.py
+    |           `-- crew.py
+    `-- research_flow/
+        |-- pyproject.toml
+        `-- src/
+            `-- research_flow/
+                `-- main.py
+```
+
+لنشر `support_agent`، اضبط دليل العمل على:
+
+```text
+crews/support_agent
+```
+
+لا يزال AMP يجلب المستودع كاملاً أو يرفعه، لكنه يتعامل مع المجلد المحدد كجذر
+مشروع الأتمتة.
+
+## ما الذي يتحكم به دليل العمل
+
+عند تعيين دليل عمل، يستخدم AMP ذلك المجلد من أجل:
+
+- التحقق من المشروع، بما في ذلك `pyproject.toml` و`src/` ونقطة دخول Crew أو Flow
+- تثبيت الاعتماديات باستخدام `uv`
+- دليل العمل للعملية قيد التشغيل
+- متغير البيئة `CREW_ROOT_DIR`
+
+ترك الحقل فارغاً يحافظ على السلوك الحالي ويستخدم جذر المستودع.
+
+## المصادر المدعومة
+
+يمكنك تعيين دليل عمل عند إنشاء نشر من:
+
+- مستودع GitHub متصل
+- مستودع Git مكوّن في AMP
+- رفع ملف ZIP
+
+<Info>
+  اضبط أدلة العمل من واجهة AMP على الويب. لا يطلب تدفق CLI
+  `crewai deploy create` هذا الحقل.
+</Info>
+
+يمكنك أيضاً إضافة دليل العمل أو تغييره في نشر موجود من صفحة **Settings** الخاصة
+بالنشر. يسري التغيير في النشر التالي.
+
+<Warning>
+  لا يمكن استخدام أدلة العمل وauto-deploy معاً. إذا كان للنشر دليل عمل، يتم
+  تعطيل auto-deploy لذلك النشر. أوقف auto-deploy قبل تعيين دليل عمل.
+</Warning>
+
+## إعداد نشر جديد
+
+<Steps>
+  <Step title="افتح Deploy from Code">
+    في CrewAI AMP، أنشئ نشراً جديداً واختر المصدر: GitHub أو Git Repository أو
+    رفع ZIP.
+  </Step>
+
+  <Step title="اختر المستودع أو الفرع أو ملف ZIP">
+    اختر المستودع والفرع اللذين يحتويان على monorepo، أو ارفع ملف ZIP يحتوي
+    جذره على محتويات monorepo.
+  </Step>
+
+  <Step title="افتح الإعدادات المتقدمة">
+    وسّع قسم **Advanced** في نموذج النشر.
+  </Step>
+
+  <Step title="أدخل دليل العمل">
+    أدخل المسار من جذر المستودع إلى مشروع Crew أو Flow:
+
+    ```text
+    crews/support_agent
+    ```
+
+    لا تضف شرطة مائلة في البداية.
+  </Step>
+
+  <Step title="انشر">
+    أضف أي متغيرات بيئة مطلوبة، ثم ابدأ النشر.
+  </Step>
+</Steps>
+
+## إعداد نشر موجود
+
+<Steps>
+  <Step title="افتح إعدادات النشر">
+    انتقل إلى الأتمتة في AMP وافتح **Settings**.
+  </Step>
+
+  <Step title="أوقف auto-deploy إذا لزم الأمر">
+    إذا كان auto-deploy مفعلاً، أوقفه أولاً. لا يكون حقل دليل العمل متاحاً
+    أثناء تشغيل auto-deploy.
+  </Step>
+
+  <Step title="عيّن دليل العمل">
+    في **Basic settings**، أدخل مسار المجلد الفرعي، مثل:
+
+    ```text
+    crews/support_agent
+    ```
+  </Step>
+
+  <Step title="أعد النشر">
+    احفظ الإعداد وأعد نشر الأتمتة. سيتم استخدام دليل العمل الجديد في النشر
+    التالي.
+  </Step>
+</Steps>
+
+## قواعد المسار
+
+يجب أن يكون دليل العمل مساراً نسبياً داخل جذر المستودع أو ZIP.
+
+| القاعدة | المثال |
+|---------|--------|
+| استخدم مساراً نسبياً | `crews/support_agent` |
+| لا تبدأ بـ `/` | `/crews/support_agent` غير صالح |
+| لا تستخدم مقاطع المسار `.` أو `..` | `crews/../support_agent` غير صالح |
+| استخدم الأحرف والأرقام والشرطات والشرطات السفلية والنقاط والشرطات المائلة فقط | `crews/support agent` غير صالح |
+| اجعل المسار 255 حرفاً أو أقل | يتم رفض المسارات الأطول |
+
+يزيل AMP المسافات البيضاء في البداية والنهاية، ويضغط الشرطات المائلة المتكررة،
+ويزيل الشرطة المائلة النهائية. تستخدم القيمة الفارغة جذر المستودع.
+
+## ملفات القفل وUV Workspaces
+
+يجب أن يحتوي المجلد المحدد على `pyproject.toml` ودليل `src/` الخاصين بالأتمتة.
+يمكن أن يوجد ملف `uv.lock` أو `poetry.lock` إما في المجلد المحدد أو في جذر
+المستودع.
+
+يدعم هذا التخطيطين الشائعين في monorepo:
+
+<Tabs>
+  <Tab title="ملف قفل المشروع">
+    ```text
+    company-ai/
+    `-- crews/
+        `-- support_agent/
+            |-- pyproject.toml
+            |-- uv.lock
+            `-- src/
+                `-- support_agent/
+                    `-- main.py
+    ```
+  </Tab>
+
+  <Tab title="ملف قفل workspace">
+    ```text
+    company-ai/
+    |-- uv.lock
+    |-- packages/
+    |   `-- shared_tools/
+    `-- crews/
+        `-- support_agent/
+            |-- pyproject.toml
+            `-- src/
+                `-- support_agent/
+                    `-- main.py
+    ```
+  </Tab>
+</Tabs>
+
+<Tip>
+  إذا كانت الأتمتة تستورد حزماً مشتركة من مكان آخر في monorepo، فصرّح بهذه
+  الحزم في `pyproject.toml` باستخدام إعدادات UV workspace أو path أو source.
+  يشغل AMP الأتمتة من المجلد المحدد، لذلك يجب تثبيت الكود المشترك كاعتمادية
+  بدلاً من الاعتماد على وجود جذر المستودع في Python path.
+</Tip>
+
+## استكشاف الأخطاء وإصلاحها
+
+### لم يتم العثور على دليل العمل
+
+تحقق من أن المسار نسبي إلى جذر المستودع أو ZIP. بالنسبة لرفع ZIP، يجب أن
+تتضمن محتويات ZIP مسار دليل العمل تماماً كما أدخلته.
+
+### pyproject.toml مفقود
+
+يجب أن يشير دليل العمل إلى مجلد مشروع Crew أو Flow، وليس فقط إلى مجلد أب
+يحتوي على عدة مشاريع.
+
+### uv.lock أو poetry.lock مفقود
+
+اعمل commit لملف قفل إما في مجلد المشروع المحدد أو في جذر المستودع. بالنسبة
+إلى UV workspaces، يتم دعم إبقاء `uv.lock` في جذر workspace.
+
+### Auto-Deploy غير متاح
+
+يتم تعطيل auto-deploy أثناء تعيين دليل عمل. استخدم إعادة النشر اليدوية أو شغّل
+إعادة النشر من CI/CD باستخدام AMP API.
+
+<Card title="النشر على AMP" icon="rocket" href="/ar/enterprise/guides/deploy-to-amp">
+  تابع دليل النشر بعد اختيار دليل عمل monorepo.
+</Card>

docs/ar/guides/flows/conversational-flows.mdx

@@ -0,0 +1,473 @@
+---
+title: تدفقات المحادثة
+description: أنشئ تطبيقات دردشة متعددة الجولات مع kickoff لكل جولة وسجل الرسائل وتوجيه النية والتتبع وجسور WebSocket.
+icon: comments
+mode: "wide"
+---
+
+## نظرة عامة
+
+تعامل التطبيقات المحادثية مع كل سطر من المستخدم كـ **تشغيل flow جديد** بنفس **معرّف الجلسة**. توفر CrewAI مساعدات لسجل الرسائل وتصنيف النية الاختياري وتأجيل التتبع وجسور الواجهة، إضافة إلى REPL محلي `flow.chat()` للتدفقات المحادثية.
+
+| المفهوم | التنفيذ |
+|---------|---------|
+| معرّف الجلسة | `handle_turn(..., session_id=...)` → `kickoff(inputs={"id": ...})` → `state.id` |
+| سطر المستخدم | `handle_turn(message)` يضيف الرسالة إلى `state.messages` قبل تشغيل الرسم |
+| اكتمال الجولة | `FlowFinished` لهذا **التشغيل** فقط؛ تستمر المحادثة في `handle_turn` التالي |
+| تتبع الجلسة | `ConversationConfig(defer_trace_finalization=True)` + `finalize_session_traces()` |
+
+## واجهات الجولات
+
+استخدم **`flow.handle_turn(message, session_id=...)`** لكل رسالة مستخدم من REST أو WebSocket أو الاختبارات أو الواجهات المخصصة. استخدم **`flow.chat()`** عندما تريد حلقة دردشة محلية في الطرفية لـ `Flow` محادثي.
+
+لا يقبل `Flow.kickoff()` الوسيطين `user_message=` أو `session_id=`. في التدفقات المحادثية، يخزن `handle_turn()` الرسالة المعلقة ويستدعي داخلياً `kickoff(inputs={"id": session_id})`.
+
+| API | الاستخدام |
+|-----|-----------|
+| `handle_turn(message, session_id=...)` | غلاف مريح لجولة واحدة في `Flow` محادثي |
+| `chat()` | REPL محلي في الطرفية لـ `Flow` محادثي |
+| `kickoff(inputs={...})` | تشغيل متقدم للـ flow بدون معالجة جولة محادثية |
+| `ask()` | مطالبة حاجزة **داخل** خطوة واحدة |
+| `@human_feedback` | الموافقة/الرفض على **مخرجات خطوة** — وليس السطر التالي |
+| `ChatSession.handle_turn(...)` | طبقة نقل فوق `handle_turn` |
+
+## بداية سريعة
+
+```python
+from uuid import uuid4
+
+from crewai import Flow
+from crewai.flow import listen
+from crewai.experimental.conversational import (
+    ConversationConfig,
+    ConversationState,
+)
+
+
+@ConversationConfig(defer_trace_finalization=True)
+class SupportFlow(Flow[ConversationState]):
+    conversational = True
+
+    def route_turn(self, context):
+        message = (self.state.current_user_message or "").lower()
+        if "طلب" in message or "order" in message:
+            return "order"
+        if "وداع" in message or "goodbye" in message:
+            return "goodbye"
+        return "help"
+
+    @listen("order")
+    def handle_order(self):
+        reply = "طلبك في الطريق."
+        self.append_assistant_message(reply)
+        return reply
+
+    @listen("help")
+    def handle_help(self):
+        reply = "كيف يمكنني المساعدة؟"
+        self.append_assistant_message(reply)
+        return reply
+
+    @listen("goodbye")
+    def handle_goodbye(self):
+        reply = "وداعاً!"
+        self.append_assistant_message(reply)
+        return reply
+
+
+session_id = str(uuid4())
+flow = SupportFlow()
+
+try:
+    flow.handle_turn("أين طلبي؟", session_id=session_id)
+    flow.handle_turn("وماذا عن الإرجاع؟", session_id=session_id)
+finally:
+    flow.finalize_session_traces()
+```
+
+## دورة حياة الجولة
+
+كل `handle_turn` يشغّل:
+
+1. **`_configure_conversational_kickoff`** — دمج `session_id` / `user_message` في `inputs` وتطبيق `ConversationalConfig`.
+2. **استعادة الحالة** — عند وجود `inputs["id"]` و`@persist`.
+3. **`FlowStarted`** — في أول جولة للجلسة المؤجلة فقط.
+4. **`prepare_conversational_turn`** — إضافة رسالة المستخدم و`last_user_message` وتصنيف اختياري.
+5. **تنفيذ الرسم** — `@start` → `@router` → معالجات `@listen`.
+6. **نهاية التشغيل** — يُتخطى `flow_finished` والتتبع لكل جولة عند التأجيل؛ `Agent.kickoff()` / crews لا تغلق دفعة الأب.
+
+استدعِ **`append_assistant_message(reply)`** في المعالجات. سطر المستخدم محفوظ عبر `handle_turn` — لا تُضفه مرة أخرى.
+
+## `ConversationalConfig` (افتراضيات على مستوى الصنف)
+
+عيّن على صنف `Flow` كـ `conversational_config: ClassVar[ConversationalConfig | None]`.
+
+| الحقل | الافتراضي | الغرض |
+|-------|-----------|--------|
+| `default_intents` | `None` | تسميات outcome للتصنيف التلقائي قبل kickoff |
+| `intent_llm` | `None` | نموذج التصنيف (مطلوب عند وجود intents) |
+| `interactive_prompt` | `"You: "` | مطالبة `kickoff(interactive=True)` |
+| `interactive_timeout` | `None` | مهلة لكل سطر في الوضع التفاعلي |
+| `exit_commands` | `exit`, `quit` | كلمات إنهاء الوضع التفاعلي |
+| `defer_trace_finalization` | `True` | إبقاء دفعة trace واحدة مفتوحة بين الجولات |
+
+يمكن التجاوز لكل kickoff عبر `intents=` و`intent_llm=`.
+
+## `ChatState` (شكل الحالة الموصى به للحفظ)
+
+```python
+from crewai.flow import ChatState
+
+
+class MyChatState(ChatState):
+    # موروث: id, messages, last_user_message, last_intent, session_ready
+    research_turn_count: int = 0
+    custom_flag: bool = False
+```
+
+| الحقل | الدور |
+|-------|------|
+| `id` | UUID الجلسة (مثل `session_id` / `inputs["id"]`) |
+| `messages` | قائمة `{role, content}` لسجل LLM |
+| `last_user_message` | آخر سطر مستخدم في هذه الجولة |
+| `last_intent` | تسمية المسار بعد التصنيف (إن وُجد) |
+| `session_ready` | علم bootstrap لمرة واحدة |
+
+`ConversationalInputs` هو `TypedDict` لـ `kickoff(inputs={...})`: `id`, `user_message`, `last_intent`.
+
+## API المحادثة على `Flow`
+
+### معاملات `kickoff` / `kickoff_async`
+
+| المعامل | الغرض |
+|---------|--------|
+| `user_message` | نص هذه الجولة (أو `{"role": "user", "content": "..."}`) |
+| `session_id` | UUID المحادثة → `inputs["id"]` / `state.id` |
+| `intents` | تسميات outcome لـ `classify_intent` قبل kickoff |
+| `intent_llm` | LLM للتصنيف (مطلوب مع `intents`) |
+| `interactive` | حلقة CLI عبر `ask()` (للعروض المحلية فقط) |
+| `interactive_prompt` | مطالبة الوضع التفاعلي |
+| `interactive_timeout` | مهلة `ask()` لكل سطر |
+| `exit_commands` | كلمات إنهاء الوضع التفاعلي |
+| `inputs` | حقول حالة إضافية |
+| `restore_from_state_id` | استنساخ من flow محفوظ آخر |
+
+### سمات المثيل
+
+| السمة | الغرض |
+|-------|--------|
+| `conversational_config` | افتراضيات `ConversationalConfig` على مستوى الصنف |
+| `defer_trace_finalization` | علم المثيل؛ يُضبط تلقائياً من config عند kickoff |
+| `suppress_flow_events` | يخفي لوحات console؛ **التتبع يُسجّل** |
+| `stream` | بث؛ مع `ChatSession.handle_turn(..., stream=True)` |
+
+### طرق وخصائص
+
+| الاسم | الوصف |
+|------|--------|
+| `append_message(role, content, **extra)` | إضافة إلى `state.messages` |
+| `conversation_messages` | سجل للقراءة فقط لاستدعاءات LLM |
+| `classify_intent(text, outcomes, *, llm, context=None)` | تعيين outcome |
+| `receive_user_message(text, *, outcomes=None, llm=None)` | إضافة رسالة مستخدم؛ `last_intent` اختياري |
+| `finalize_session_traces()` | إصدار `flow_finished` المؤجل وإنهاء دفعة trace |
+| `_should_defer_trace_finalization()` | هل يُؤجل إنهاء trace لكل جولة |
+| `input_history` | سجل تدقيق مطالبات وردود `ask()` |
+
+### مساعدات الوحدة (`crewai.flow.conversation`)
+
+| الدالة | الوصف |
+|--------|--------|
+| `normalize_kickoff_inputs(...)` | دمج kwargs المحادثة في `inputs` |
+| `get_conversation_messages(flow)` | قراءة الرسائل من الحالة أو المخزن |
+| `append_message(flow, ...)` | مثل طريقة المثيل |
+| `prepare_conversational_turn(flow, ...)` | تهيئة الجولة (عادةً kickoff يستدعيها) |
+| `receive_user_message(flow, ...)` | مثل طريقة المثيل |
+| `set_state_field(flow, name, value)` | تعيين حقل dict أو Pydantic |
+| `get_conversational_config(flow)` | قراءة `conversational_config` |
+| `input_history_to_messages(entries)` | تحويل `input_history` لصيغة رسائل LLM |
+
+## أنماط توجيه النية
+
+### أ. تصنيف مسبق عبر `ConversationalConfig` (الأبسط)
+
+عيّن `default_intents` و`intent_llm`. كل kickoff يصنّف قبل `@router`؛ اقرأ `self.state.last_intent` في `route()`.
+
+### ب. تصنيف داخل `@router` (مطالبات أغنى)
+
+عيّن `default_intents=None` ليضيف kickoff الرسالة فقط. في `route()` استدعِ `classify_intent`:
+
+```python
+@router(bootstrap)
+def route(self):
+    intent = self.classify_intent(
+        self._routing_prompt(self.state.last_user_message),
+        ("GREETING", "ORDER", "RESEARCH", "GOODBYE"),
+        llm=self.conversational_config.intent_llm or "gpt-4o-mini",
+    )
+    self.state.last_intent = intent
+    return intent
+```
+
+للبحث على الويب أو أدوات متعددة الخطوات استخدم **`@listen("RESEARCH")`** مع `Agent.kickoff()` وأدوات — وليس `LLM.call()` فقط.
+
+## عندما ينتهي الـ flow ويستمر المستخدم
+
+`FlowFinished` يعني أن **تنفيذ الرسم هذا** اكتمل. تستمر المحادثة بـ `kickoff` آخر ونفس `session_id`. `@persist` يستعيد `messages` والأعلام والسياق.
+
+**نمط الحفظ:** يُفضّل `@persist` على **خطوة نهائية واحدة** (مثل `finalize`) وليس على صنف `Flow` بالكامل. الحفظ على مستوى الصنف بعد كل method قد يفقد تحديثات المعالجات في نفس الجولة.
+
+لا تستخدم `@human_feedback` لأسطر المتابعة في الدردشة إلا عند الحاجة لموافقة بشرية على مخرجات خطوة محددة.
+
+## `Flow` المحادثاتي (تجريبي)
+
+<Warning>
+  **ميزة تجريبية.** سطح `Flow` المحادثاتي (`conversational = True`،
+  `handle_turn`، `ConversationConfig`، `RouterConfig`،
+  `ConversationState`، الرسم البياني المدمج والمساعدات) يقع تحت
+  `crewai.experimental` وقد يتغير شكله قبل التخرج. ثبّت إصدار CrewAI إذا
+  كنت تعتمد على سلوك محدد، وراقب changelog للتحديثات الكاسرة. الملاحظات
+  والمشاكل مرحب بها.
+</Warning>
+
+فعّل الرسم المحادثاتي بتعيين `conversational = True` على صنف فرعي من `Flow`. عندئذٍ يُظهر `Flow` الأساسي رسم `@start` / `@router` / `converse_turn` / `end_conversation` مدمجاً، ويدير `state.messages`، ويُشغّل LLM التوجيه، ويبقي دفعة trace مفتوحة عبر الجولات. أنت تكتب **المسارات المخصصة** فقط؛ والإطار يتولى الباقي.
+
+استخدمه عندما تريد دردشة متعددة الجولات مع موجّه قائم على LLM ومعالجات لكل مسار دون توصيل دورة الحياة يدوياً. استخدم `Flow[ChatState]` (النمط الأدنى مستوى في الأعلى) عندما تحتاج تحكماً كاملاً.
+
+### مثال سريع
+
+```python
+from crewai import LLM, Flow
+from crewai.flow import listen
+from crewai.experimental.conversational import (
+    ConversationConfig,
+    ConversationState,
+    RouterConfig,
+)
+
+
+ROUTER_LLM = LLM(model="gpt-4o-mini")
+
+
+@ConversationConfig(
+    system_prompt="A multi-agent assistant for ordinary chat and tool-backed tasks.",
+    llm=ROUTER_LLM,
+    router=RouterConfig(),  # المسارات + الأوصاف تُكتشف تلقائياً من معالجات @listen
+)
+class SupportFlow(Flow[ConversationState]):
+    conversational = True
+
+    @listen("INTERNET_SEARCH")
+    def handle_internet_search(self) -> str:
+        """Fresh web research, current news, real-time lookups."""
+        ...
+        self.append_assistant_message(reply)
+        return reply
+
+    @listen("CREWAI_DOCS")
+    def handle_crewai_docs(self) -> str:
+        """Look up the CrewAI documentation for framework/API questions."""
+        ...
+        self.append_assistant_message(reply)
+        return reply
+
+
+flow = SupportFlow()
+try:
+    flow.handle_turn("ماذا يمكنك أن تفعل؟")                   # يوجَّه إلى converse (مدمج)
+    flow.handle_turn("ابحث في الويب عن أخبار الذكاء الاصطناعي.")  # يوجَّه إلى INTERNET_SEARCH
+    flow.handle_turn("لخص النتيجة الأولى.")                    # يعود إلى converse
+finally:
+    flow.finalize_session_traces()
+```
+
+للدردشة المحلية في الطرفية، استخدم `chat()`:
+
+```python
+def kickoff() -> None:
+    SupportFlow().chat()
+```
+
+يلف `chat()` استدعاءات `handle_turn()` داخل REPL، ويخرج عند `exit` / `quit`، ويتجاهل الأسطر الفارغة افتراضياً، ويستدعي `finalize_session_traces()` عند انتهاء الجلسة.
+
+### `ConversationConfig`
+
+مزخرف صنف يُلحق افتراضيات الدردشة على مستوى الصنف.
+
+| الحقل | الافتراضي | الغرض |
+|-------|-----------|-------|
+| `system_prompt` | `slices.conversational_system_prompt` من i18n | رسالة system يستخدمها `converse_turn` المدمج. مرر `""` للتعطيل التام. |
+| `llm` | `None` | LLM المحادثة (يستخدمه `converse_turn` وكاحتياطي للموجّه). |
+| `router` | `None` | `RouterConfig` للتوجيه عبر LLM. بدونه، يسقط الـ flow دائماً إلى `converse`. |
+| `answer_from_history_prompt` | افتراضي الإطار | رسالة system للمسار الاختياري `answer_from_history`. |
+| `answer_from_history_llm` | `None` | يُفعّل الاختصار `answer_from_history` عند تعيينه. |
+| `intent_llm` | `None` | LLM لمسار التصنيف المسبق القديم `intents=`/`default_intents`. |
+| `default_intents` | `None` | تسميات النتائج للتصنيف المسبق القديم. |
+| `visible_agent_outputs` | `None` | `"all"` أو قائمة بأسماء الـ agents الذين تُرفع مخرجاتهم من `append_agent_result()` إلى رسائل عامة. |
+| `defer_trace_finalization` | `True` | يبقي دفعة trace واحدة مفتوحة عبر استدعاءات `handle_turn()`. |
+
+### `RouterConfig` وفهرس المسارات المُولَّد تلقائياً
+
+```python
+RouterConfig(
+    prompt="تأطير اختياري للنطاق (سياسة، صوت، شخصية).",
+    response_format=MyRoute,        # اختياري؛ يُولَّد تلقائياً عند الإغفال
+    llm=ROUTER_LLM,                  # يسقط إلى ConversationConfig.llm
+    routes=["INTERNET_SEARCH", "CREWAI_DOCS"],   # اختياري؛ يُستنتج من المستمعين
+    route_descriptions={
+        "INTERNET_SEARCH": "تجاوز الـ docstring لهذا المسار فقط.",
+    },
+    default_intent="converse",       # يُستخدم عند فشل LLM أو غيابه
+    fallback_intent="converse",      # يُستخدم عندما يعيد LLM مساراً غير صالح
+    intent_field="intent",
+)
+```
+
+تُبنى رسالة الموجّه إلى LLM تلقائياً. لكل مسار يختار الإطار وصفاً بهذا الترتيب من الأولوية:
+
+1. `RouterConfig.route_descriptions[label]` — تجاوز صريح.
+2. `Flow.builtin_route_descriptions[label]` — نص جاهز من الإطار لـ `converse` و`end` و`answer_from_history` (مصاغ لـ LLM التوجيه).
+3. أول سطر غير فارغ من docstring معالج `@listen(label)`.
+4. فارغ (المسار يظهر في الفهرس بلا وصف).
+
+عملياً، **إضافة مسار جديد = `@listen("X")` + docstring من سطر واحد**:
+
+```python
+@listen("INTERNET_SEARCH")
+def handle_internet_search(self) -> str:
+    """Fresh web research, current news, real-time lookups."""
+    ...
+```
+
+…وسيرى LLM التوجيه:
+
+```
+Routes:
+- CREWAI_DOCS: Look up the CrewAI documentation for framework/API questions.
+- INTERNET_SEARCH: Fresh web research, current news, real-time lookups.
+- converse: Ordinary chat, follow-ups, summaries, clarifications…
+- end: User signals the conversation is finished (goodbye, exit, done).
+```
+
+`RouterConfig.prompt` مخصص لـ **تأطير النطاق** (شخصية المساعد، قواعد العمل، النبرة). فهرس المسارات يُبنى تلقائياً — لا تُدرج المسارات في `prompt`؛ سيختل التزامن لحظة إضافة معالج جديد.
+
+### المسارات المدمجة
+
+| المسار | المعالج | الغرض |
+|--------|---------|-------|
+| `converse` | `converse_turn` | معالج الدردشة الافتراضي. يستدعي `ConversationConfig.llm` بـ system prompt + التاريخ القانوني للرسائل. |
+| `end` | `end_conversation` | يضبط `state.ended = True` ويُصدر رد إنهاء. |
+| `answer_from_history` | `answer_from_history_turn` | اختياري. يُوجَّه إليه عندما يكون `ConversationConfig.answer_from_history_llm` مُعيَّناً ويمكن الإجابة على الرسالة من التاريخ فقط. |
+
+يمكنك تجاوز أي من هذه بتعريف معالج بنفس الاسم في الصنف الفرعي.
+
+### دلالات `handle_turn()`
+
+`flow.handle_turn(message)` يُشغّل جولة واحدة:
+
+1. يعيد ضبط تعقّب التنفيذ لكل جولة (`_completed_methods`, `_method_outputs`) ليُعاد تشغيل الرسم — بدون ذلك، استدعاءات `kickoff` المتكررة على نفس النسخة ستُحدث دائرة قصر من الجولة الثانية لأن `Flow.kickoff_async` يعتبر `inputs={"id": ...}` استعادة من نقطة تفتيش.
+2. يُلحق رسالة المستخدم بـ `state.messages` ويضبط `current_user_message` / `last_user_message`. يُحافَظ على `last_intent` **من الجولة السابقة** كي يستخدمها LLM التوجيه كإشارة.
+3. يُشغّل `conversation_start` → `route_conversation` → معالج `@listen` المختار.
+4. يخزّن الموجّه قراره في `state.last_intent` (يكون مرئياً لسياق التوجيه في الجولة التالية).
+5. إذا أعاد معالجك سلسلة نصية ولم يستدعِ `append_assistant_message`، فإن `handle_turn` يُلحقها نيابةً عنك.
+
+استدعِ `handle_turn()` لرسائل الدردشة. استدعاء `kickoff(inputs={"id": ...})` مباشرةً يشغل الرسم بدون غلاف الجولة المحادثية.
+
+### `chat()` للـ REPL المحلي
+
+`flow.chat()` هو غلاف الطرفية الجاهز فوق `handle_turn()`:
+
+```python
+flow = SupportFlow()
+flow.chat()
+```
+
+يتولى الحلقة المحلية الشائعة:
+
+1. يطلب رسالة من المستخدم.
+2. يتوقف عند `exit` / `quit` أو `EOFError` أو `KeyboardInterrupt`.
+3. يستدعي `handle_turn(message, session_id=...)`.
+4. يطبع نتيجة المساعد.
+5. ينهي traces الجلسة المؤجلة داخل كتلة `finally`.
+
+خصص سلوك الطرفية عبر I/O قابل للحقن:
+
+```python
+flow.chat(
+    session_id="demo-session",
+    prompt="You: ",
+    assistant_prefix="Assistant: ",
+    exit_commands=("exit", "quit", "bye"),
+)
+```
+
+لتطبيقات الويب والـ workers الخلفية والاختبارات ووسائط النقل المخصصة، استمر في استخدام `handle_turn()` مباشرةً.
+
+### سلوك موجّه مخصص
+
+لتشغيل آثار جانبية (إعداد ناقل أحداث، قياس عن بُعد) في كل قرار توجيه، تجاوز `route_turn`:
+
+```python
+class SupportFlow(Flow[ConversationState]):
+    conversational = True
+
+    def route_turn(self, context: dict[str, Any]) -> str | None:
+        self.event_bus = MyBus(self)
+        return super().route_turn(context)
+```
+
+لتجاوز موجّه LLM واختيار مسار برمجياً، أعد سلسلة نصية من `route_turn`؛ إعادة `None` تسقط إلى `_route_with_config(...)`.
+
+### `append_assistant_message` و`append_agent_result`
+
+داخل معالج `@listen(label)`، اختر:
+
+- `self.append_assistant_message(text)` — يضيف جولة مساعد مرئية للمستخدم إلى `state.messages`. سيراها `converse_turn` في الجولة التالية.
+- `self.append_agent_result(agent_name, result, visibility="private")` — يسجّل حدثاً منظماً في `state.events` وموضوعاً في `state.agent_threads[agent_name]`. الرؤية العامة تستدعي `append_assistant_message` أيضاً. استخدم النتائج الخاصة للعمل الجانبي الذي يجب ألا يلوث التاريخ القانوني.
+
+يمكن لـ `ConversationConfig.visible_agent_outputs` رفع النتائج الخاصة لـ agents محددين إلى عامة عالمياً (`"all"` أو قائمة بالأسماء).
+
+## التتبع عبر الجولات
+
+مع `defer_trace_finalization=True` (افتراضي في `ConversationalConfig`):
+
+- **دفعة trace واحدة** لجلسة الدردشة.
+- **`flow_started`** في الجولة الأولى فقط؛ **`flow_finished`** مرة في `finalize_session_traces()`.
+- **`kickoff` لكل جولة** لا يطبع "Trace batch finalized".
+- **العمل المتداخل** (`Agent.kickoff()`, crews, Exa) يُلحق بدفعة **الأب**؛ flow داخلي من `AgentExecutor` لا يغلق دفعة الجلسة مبكراً.
+
+```python
+flow.chat(session_id=session_id)
+```
+
+`flow.chat()` يستدعي `finalize_session_traces()` نيابةً عنك. عندما تملك الحلقة عبر `handle_turn()` أو `kickoff(...)`، استدعِ `finalize_session_traces()` عند انتهاء الجلسة.
+
+`suppress_flow_events=True` يخفي لوحات Rich فقط؛ أحداث trace والـ methods تُصدر.
+
+### دورة حياة trace لـ `Flow` المحادثاتي
+
+يستخدم [`Flow` المحادثاتي](#flow-المحادثاتي-تجريبي) التجريبي نفس دورة حياة tracing: `defer_trace_finalization` افتراضياً `True`، فيبقي كل `handle_turn()` أثر الجلسة مفتوحاً. أنهِ دوماً عند نهاية الجلسة — لُف حلقتك بـ `try/finally` واستدعِ `flow.finalize_session_traces()` عند الخروج. بدون ذلك، تبقى الدفعة مفتوحة وقد لا تُصدَّر آخر محادثة أبداً.
+
+## البث
+
+اضبط `stream = True` على صنف `Flow`. عندئذٍ يُصدر `kickoff(...)` أحداث `assistant_delta` (وما يرتبط بها) عبر ناقل الأحداث القياسي.
+
+## الاستيراد
+
+```python
+from crewai.flow import (
+    ChatState,
+    ConversationalConfig,
+    ConversationalInputs,
+    Flow,
+    listen,
+    persist,
+    router,
+    start,
+)
+```
+
+## مراجع
+
+- [إتقان إدارة حالة Flow](/ar/guides/flows/mastering-flow-state)
+- [أنشئ أول Flow](/ar/guides/flows/first-flow)
+- Demo: `lib/crewai/runner_conversational_flow_simple.py` — REPL بسيط مع `RESEARCH` ووكيل Exa

docs/ar/guides/flows/first-flow.mdx

@@ -272,6 +272,7 @@ crewai flow plot
 3. استكشف دوال `and_` و`or_` لتنفيذ متوازٍ أكثر تعقيدًا
 4. اربط Flow بواجهات API خارجية وقواعد بيانات وواجهات مستخدم
 5. ادمج عدة Crews متخصصة في Flow واحد
+6. أنشئ تطبيقات دردشة متعددة الجولات مع [تدفقات المحادثة](/ar/guides/flows/conversational-flows) (`kickoff` لكل رسالة، `ChatSession`، تأجيل التتبع)
 
 <Check>
 تهانينا! لقد بنيت بنجاح أول CrewAI Flow يجمع بين الكود العادي واستدعاءات LLM المباشرة ومعالجة Crew لإنشاء دليل شامل. هذه المهارات الأساسية تمكّنك من إنشاء تطبيقات AI متطورة بشكل متزايد.

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

@@ -20,6 +20,8 @@ mode: "wide"
 5. **توسيع تطبيقاتك** - دعم سير العمل المعقدة بتنظيم بيانات مناسب
 6. **تمكين التطبيقات الحوارية** - تخزين والوصول إلى سجل المحادثات للتفاعلات الواعية بالسياق
 
+للدردشة متعددة الجولات (`kickoff` لكل سطر مستخدم، `ChatState`، توجيه النية، تأجيل التتبع، و`ChatSession`)، راجع [تدفقات المحادثة](/ar/guides/flows/conversational-flows).
+
 ## أساسيات إدارة الحالة
 
 ### نهجان لإدارة الحالة

docs/docs.json

@@ -115,6 +115,7 @@
                         "pages": [
                           "en/guides/flows/first-flow",
                           "en/guides/flows/mastering-flow-state",
+                          "en/guides/flows/conversational-flows",
                           "en/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -509,6 +510,7 @@
                       "en/enterprise/guides/build-crew",
                       "en/enterprise/guides/prepare-for-deployment",
                       "en/enterprise/guides/deploy-to-amp",
+                      "en/enterprise/guides/monorepo-deployments",
                       "en/enterprise/guides/private-package-registry",
                       "en/enterprise/guides/kickoff-crew",
                       "en/enterprise/guides/update-crew",
@@ -1028,6 +1030,7 @@
                       "en/enterprise/guides/build-crew",
                       "en/enterprise/guides/prepare-for-deployment",
                       "en/enterprise/guides/deploy-to-amp",
+                      "en/enterprise/guides/monorepo-deployments",
                       "en/enterprise/guides/private-package-registry",
                       "en/enterprise/guides/kickoff-crew",
                       "en/enterprise/guides/update-crew",
@@ -1153,6 +1156,7 @@
                         "pages": [
                           "en/guides/flows/first-flow",
                           "en/guides/flows/mastering-flow-state",
+                          "en/guides/flows/conversational-flows",
                           "en/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -1514,6 +1518,7 @@
                       "en/enterprise/guides/build-crew",
                       "en/enterprise/guides/prepare-for-deployment",
                       "en/enterprise/guides/deploy-to-amp",
+                      "en/enterprise/guides/monorepo-deployments",
                       "en/enterprise/guides/private-package-registry",
                       "en/enterprise/guides/kickoff-crew",
                       "en/enterprise/guides/update-crew",
@@ -1639,6 +1644,7 @@
                         "pages": [
                           "en/guides/flows/first-flow",
                           "en/guides/flows/mastering-flow-state",
+                          "en/guides/flows/conversational-flows",
                           "en/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -1999,6 +2005,7 @@
                       "en/enterprise/guides/build-crew",
                       "en/enterprise/guides/prepare-for-deployment",
                       "en/enterprise/guides/deploy-to-amp",
+                      "en/enterprise/guides/monorepo-deployments",
                       "en/enterprise/guides/private-package-registry",
                       "en/enterprise/guides/kickoff-crew",
                       "en/enterprise/guides/update-crew",
@@ -2124,6 +2131,7 @@
                         "pages": [
                           "en/guides/flows/first-flow",
                           "en/guides/flows/mastering-flow-state",
+                          "en/guides/flows/conversational-flows",
                           "en/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -2484,6 +2492,7 @@
                       "en/enterprise/guides/build-crew",
                       "en/enterprise/guides/prepare-for-deployment",
                       "en/enterprise/guides/deploy-to-amp",
+                      "en/enterprise/guides/monorepo-deployments",
                       "en/enterprise/guides/private-package-registry",
                       "en/enterprise/guides/kickoff-crew",
                       "en/enterprise/guides/update-crew",
@@ -2608,6 +2617,7 @@
                         "pages": [
                           "en/guides/flows/first-flow",
                           "en/guides/flows/mastering-flow-state",
+                          "en/guides/flows/conversational-flows",
                           "en/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -2979,6 +2989,7 @@
                       "en/enterprise/guides/build-crew",
                       "en/enterprise/guides/prepare-for-deployment",
                       "en/enterprise/guides/deploy-to-amp",
+                      "en/enterprise/guides/monorepo-deployments",
                       "en/enterprise/guides/private-package-registry",
                       "en/enterprise/guides/kickoff-crew",
                       "en/enterprise/guides/update-crew",
@@ -3103,6 +3114,7 @@
                         "pages": [
                           "en/guides/flows/first-flow",
                           "en/guides/flows/mastering-flow-state",
+                          "en/guides/flows/conversational-flows",
                           "en/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -3474,6 +3486,7 @@
                       "en/enterprise/guides/build-crew",
                       "en/enterprise/guides/prepare-for-deployment",
                       "en/enterprise/guides/deploy-to-amp",
+                      "en/enterprise/guides/monorepo-deployments",
                       "en/enterprise/guides/private-package-registry",
                       "en/enterprise/guides/kickoff-crew",
                       "en/enterprise/guides/update-crew",
@@ -3598,6 +3611,7 @@
                         "pages": [
                           "en/guides/flows/first-flow",
                           "en/guides/flows/mastering-flow-state",
+                          "en/guides/flows/conversational-flows",
                           "en/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -3969,6 +3983,7 @@
                       "en/enterprise/guides/build-crew",
                       "en/enterprise/guides/prepare-for-deployment",
                       "en/enterprise/guides/deploy-to-amp",
+                      "en/enterprise/guides/monorepo-deployments",
                       "en/enterprise/guides/private-package-registry",
                       "en/enterprise/guides/kickoff-crew",
                       "en/enterprise/guides/update-crew",
@@ -4093,6 +4108,7 @@
                         "pages": [
                           "en/guides/flows/first-flow",
                           "en/guides/flows/mastering-flow-state",
+                          "en/guides/flows/conversational-flows",
                           "en/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -4464,6 +4480,7 @@
                       "en/enterprise/guides/build-crew",
                       "en/enterprise/guides/prepare-for-deployment",
                       "en/enterprise/guides/deploy-to-amp",
+                      "en/enterprise/guides/monorepo-deployments",
                       "en/enterprise/guides/private-package-registry",
                       "en/enterprise/guides/kickoff-crew",
                       "en/enterprise/guides/update-crew",
@@ -4588,6 +4605,7 @@
                         "pages": [
                           "en/guides/flows/first-flow",
                           "en/guides/flows/mastering-flow-state",
+                          "en/guides/flows/conversational-flows",
                           "en/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -4948,6 +4966,7 @@
                       "en/enterprise/guides/build-crew",
                       "en/enterprise/guides/prepare-for-deployment",
                       "en/enterprise/guides/deploy-to-amp",
+                      "en/enterprise/guides/monorepo-deployments",
                       "en/enterprise/guides/private-package-registry",
                       "en/enterprise/guides/kickoff-crew",
                       "en/enterprise/guides/update-crew",
@@ -5072,6 +5091,7 @@
                         "pages": [
                           "en/guides/flows/first-flow",
                           "en/guides/flows/mastering-flow-state",
+                          "en/guides/flows/conversational-flows",
                           "en/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -5432,6 +5452,7 @@
                       "en/enterprise/guides/build-crew",
                       "en/enterprise/guides/prepare-for-deployment",
                       "en/enterprise/guides/deploy-to-amp",
+                      "en/enterprise/guides/monorepo-deployments",
                       "en/enterprise/guides/private-package-registry",
                       "en/enterprise/guides/kickoff-crew",
                       "en/enterprise/guides/update-crew",
@@ -5556,6 +5577,7 @@
                         "pages": [
                           "en/guides/flows/first-flow",
                           "en/guides/flows/mastering-flow-state",
+                          "en/guides/flows/conversational-flows",
                           "en/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -5916,6 +5938,7 @@
                       "en/enterprise/guides/build-crew",
                       "en/enterprise/guides/prepare-for-deployment",
                       "en/enterprise/guides/deploy-to-amp",
+                      "en/enterprise/guides/monorepo-deployments",
                       "en/enterprise/guides/private-package-registry",
                       "en/enterprise/guides/kickoff-crew",
                       "en/enterprise/guides/training-crews",
@@ -6041,6 +6064,7 @@
                         "pages": [
                           "en/guides/flows/first-flow",
                           "en/guides/flows/mastering-flow-state",
+                          "en/guides/flows/conversational-flows",
                           "en/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -6402,6 +6426,7 @@
                       "en/enterprise/guides/build-crew",
                       "en/enterprise/guides/prepare-for-deployment",
                       "en/enterprise/guides/deploy-to-amp",
+                      "en/enterprise/guides/monorepo-deployments",
                       "en/enterprise/guides/private-package-registry",
                       "en/enterprise/guides/kickoff-crew",
                       "en/enterprise/guides/training-crews",
@@ -6527,6 +6552,7 @@
                         "pages": [
                           "en/guides/flows/first-flow",
                           "en/guides/flows/mastering-flow-state",
+                          "en/guides/flows/conversational-flows",
                           "en/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -6886,6 +6912,7 @@
                       "en/enterprise/guides/build-crew",
                       "en/enterprise/guides/prepare-for-deployment",
                       "en/enterprise/guides/deploy-to-amp",
+                      "en/enterprise/guides/monorepo-deployments",
                       "en/enterprise/guides/private-package-registry",
                       "en/enterprise/guides/kickoff-crew",
                       "en/enterprise/guides/training-crews",
@@ -7011,6 +7038,7 @@
                         "pages": [
                           "en/guides/flows/first-flow",
                           "en/guides/flows/mastering-flow-state",
+                          "en/guides/flows/conversational-flows",
                           "en/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -7373,6 +7401,7 @@
                       "en/enterprise/guides/build-crew",
                       "en/enterprise/guides/prepare-for-deployment",
                       "en/enterprise/guides/deploy-to-amp",
+                      "en/enterprise/guides/monorepo-deployments",
                       "en/enterprise/guides/private-package-registry",
                       "en/enterprise/guides/kickoff-crew",
                       "en/enterprise/guides/training-crews",
@@ -7528,6 +7557,7 @@
                         "pages": [
                           "pt-BR/guides/flows/first-flow",
                           "pt-BR/guides/flows/mastering-flow-state",
+                          "pt-BR/guides/flows/conversational-flows",
                           "pt-BR/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -7883,6 +7913,7 @@
                       "pt-BR/enterprise/guides/build-crew",
                       "pt-BR/enterprise/guides/prepare-for-deployment",
                       "pt-BR/enterprise/guides/deploy-to-amp",
+                      "pt-BR/enterprise/guides/monorepo-deployments",
                       "pt-BR/enterprise/guides/private-package-registry",
                       "pt-BR/enterprise/guides/kickoff-crew",
                       "pt-BR/enterprise/guides/training-crews",
@@ -8379,6 +8410,7 @@
                       "pt-BR/enterprise/guides/build-crew",
                       "pt-BR/enterprise/guides/prepare-for-deployment",
                       "pt-BR/enterprise/guides/deploy-to-amp",
+                      "pt-BR/enterprise/guides/monorepo-deployments",
                       "pt-BR/enterprise/guides/private-package-registry",
                       "pt-BR/enterprise/guides/kickoff-crew",
                       "pt-BR/enterprise/guides/training-crews",
@@ -8520,6 +8552,7 @@
                         "pages": [
                           "pt-BR/guides/flows/first-flow",
                           "pt-BR/guides/flows/mastering-flow-state",
+                          "pt-BR/guides/flows/conversational-flows",
                           "pt-BR/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -8842,6 +8875,7 @@
                       "pt-BR/enterprise/guides/build-crew",
                       "pt-BR/enterprise/guides/prepare-for-deployment",
                       "pt-BR/enterprise/guides/deploy-to-amp",
+                      "pt-BR/enterprise/guides/monorepo-deployments",
                       "pt-BR/enterprise/guides/private-package-registry",
                       "pt-BR/enterprise/guides/kickoff-crew",
                       "pt-BR/enterprise/guides/training-crews",
@@ -8983,6 +9017,7 @@
                         "pages": [
                           "pt-BR/guides/flows/first-flow",
                           "pt-BR/guides/flows/mastering-flow-state",
+                          "pt-BR/guides/flows/conversational-flows",
                           "pt-BR/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -9305,6 +9340,7 @@
                       "pt-BR/enterprise/guides/build-crew",
                       "pt-BR/enterprise/guides/prepare-for-deployment",
                       "pt-BR/enterprise/guides/deploy-to-amp",
+                      "pt-BR/enterprise/guides/monorepo-deployments",
                       "pt-BR/enterprise/guides/private-package-registry",
                       "pt-BR/enterprise/guides/kickoff-crew",
                       "pt-BR/enterprise/guides/training-crews",
@@ -9446,6 +9482,7 @@
                         "pages": [
                           "pt-BR/guides/flows/first-flow",
                           "pt-BR/guides/flows/mastering-flow-state",
+                          "pt-BR/guides/flows/conversational-flows",
                           "pt-BR/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -9767,6 +9804,7 @@
                       "pt-BR/enterprise/guides/build-crew",
                       "pt-BR/enterprise/guides/prepare-for-deployment",
                       "pt-BR/enterprise/guides/deploy-to-amp",
+                      "pt-BR/enterprise/guides/monorepo-deployments",
                       "pt-BR/enterprise/guides/private-package-registry",
                       "pt-BR/enterprise/guides/kickoff-crew",
                       "pt-BR/enterprise/guides/training-crews",
@@ -9908,6 +9946,7 @@
                         "pages": [
                           "pt-BR/guides/flows/first-flow",
                           "pt-BR/guides/flows/mastering-flow-state",
+                          "pt-BR/guides/flows/conversational-flows",
                           "pt-BR/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -10239,6 +10278,7 @@
                       "pt-BR/enterprise/guides/build-crew",
                       "pt-BR/enterprise/guides/prepare-for-deployment",
                       "pt-BR/enterprise/guides/deploy-to-amp",
+                      "pt-BR/enterprise/guides/monorepo-deployments",
                       "pt-BR/enterprise/guides/private-package-registry",
                       "pt-BR/enterprise/guides/kickoff-crew",
                       "pt-BR/enterprise/guides/training-crews",
@@ -10380,6 +10420,7 @@
                         "pages": [
                           "pt-BR/guides/flows/first-flow",
                           "pt-BR/guides/flows/mastering-flow-state",
+                          "pt-BR/guides/flows/conversational-flows",
                           "pt-BR/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -10711,6 +10752,7 @@
                       "pt-BR/enterprise/guides/build-crew",
                       "pt-BR/enterprise/guides/prepare-for-deployment",
                       "pt-BR/enterprise/guides/deploy-to-amp",
+                      "pt-BR/enterprise/guides/monorepo-deployments",
                       "pt-BR/enterprise/guides/private-package-registry",
                       "pt-BR/enterprise/guides/kickoff-crew",
                       "pt-BR/enterprise/guides/training-crews",
@@ -10852,6 +10894,7 @@
                         "pages": [
                           "pt-BR/guides/flows/first-flow",
                           "pt-BR/guides/flows/mastering-flow-state",
+                          "pt-BR/guides/flows/conversational-flows",
                           "pt-BR/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -11183,6 +11226,7 @@
                       "pt-BR/enterprise/guides/build-crew",
                       "pt-BR/enterprise/guides/prepare-for-deployment",
                       "pt-BR/enterprise/guides/deploy-to-amp",
+                      "pt-BR/enterprise/guides/monorepo-deployments",
                       "pt-BR/enterprise/guides/private-package-registry",
                       "pt-BR/enterprise/guides/kickoff-crew",
                       "pt-BR/enterprise/guides/training-crews",
@@ -11324,6 +11368,7 @@
                         "pages": [
                           "pt-BR/guides/flows/first-flow",
                           "pt-BR/guides/flows/mastering-flow-state",
+                          "pt-BR/guides/flows/conversational-flows",
                           "pt-BR/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -11655,6 +11700,7 @@
                       "pt-BR/enterprise/guides/build-crew",
                       "pt-BR/enterprise/guides/prepare-for-deployment",
                       "pt-BR/enterprise/guides/deploy-to-amp",
+                      "pt-BR/enterprise/guides/monorepo-deployments",
                       "pt-BR/enterprise/guides/private-package-registry",
                       "pt-BR/enterprise/guides/kickoff-crew",
                       "pt-BR/enterprise/guides/training-crews",
@@ -11796,6 +11842,7 @@
                         "pages": [
                           "pt-BR/guides/flows/first-flow",
                           "pt-BR/guides/flows/mastering-flow-state",
+                          "pt-BR/guides/flows/conversational-flows",
                           "pt-BR/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -12117,6 +12164,7 @@
                       "pt-BR/enterprise/guides/build-crew",
                       "pt-BR/enterprise/guides/prepare-for-deployment",
                       "pt-BR/enterprise/guides/deploy-to-amp",
+                      "pt-BR/enterprise/guides/monorepo-deployments",
                       "pt-BR/enterprise/guides/private-package-registry",
                       "pt-BR/enterprise/guides/kickoff-crew",
                       "pt-BR/enterprise/guides/training-crews",
@@ -12258,6 +12306,7 @@
                         "pages": [
                           "pt-BR/guides/flows/first-flow",
                           "pt-BR/guides/flows/mastering-flow-state",
+                          "pt-BR/guides/flows/conversational-flows",
                           "pt-BR/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -12579,6 +12628,7 @@
                       "pt-BR/enterprise/guides/build-crew",
                       "pt-BR/enterprise/guides/prepare-for-deployment",
                       "pt-BR/enterprise/guides/deploy-to-amp",
+                      "pt-BR/enterprise/guides/monorepo-deployments",
                       "pt-BR/enterprise/guides/private-package-registry",
                       "pt-BR/enterprise/guides/kickoff-crew",
                       "pt-BR/enterprise/guides/training-crews",
@@ -12720,6 +12770,7 @@
                         "pages": [
                           "pt-BR/guides/flows/first-flow",
                           "pt-BR/guides/flows/mastering-flow-state",
+                          "pt-BR/guides/flows/conversational-flows",
                           "pt-BR/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -13041,6 +13092,7 @@
                       "pt-BR/enterprise/guides/build-crew",
                       "pt-BR/enterprise/guides/prepare-for-deployment",
                       "pt-BR/enterprise/guides/deploy-to-amp",
+                      "pt-BR/enterprise/guides/monorepo-deployments",
                       "pt-BR/enterprise/guides/private-package-registry",
                       "pt-BR/enterprise/guides/kickoff-crew",
                       "pt-BR/enterprise/guides/training-crews",
@@ -13182,6 +13234,7 @@
                         "pages": [
                           "pt-BR/guides/flows/first-flow",
                           "pt-BR/guides/flows/mastering-flow-state",
+                          "pt-BR/guides/flows/conversational-flows",
                           "pt-BR/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -13502,6 +13555,7 @@
                       "pt-BR/enterprise/guides/build-crew",
                       "pt-BR/enterprise/guides/prepare-for-deployment",
                       "pt-BR/enterprise/guides/deploy-to-amp",
+                      "pt-BR/enterprise/guides/monorepo-deployments",
                       "pt-BR/enterprise/guides/private-package-registry",
                       "pt-BR/enterprise/guides/kickoff-crew",
                       "pt-BR/enterprise/guides/training-crews",
@@ -13643,6 +13697,7 @@
                         "pages": [
                           "pt-BR/guides/flows/first-flow",
                           "pt-BR/guides/flows/mastering-flow-state",
+                          "pt-BR/guides/flows/conversational-flows",
                           "pt-BR/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -13963,6 +14018,7 @@
                       "pt-BR/enterprise/guides/build-crew",
                       "pt-BR/enterprise/guides/prepare-for-deployment",
                       "pt-BR/enterprise/guides/deploy-to-amp",
+                      "pt-BR/enterprise/guides/monorepo-deployments",
                       "pt-BR/enterprise/guides/private-package-registry",
                       "pt-BR/enterprise/guides/kickoff-crew",
                       "pt-BR/enterprise/guides/training-crews",
@@ -14104,6 +14160,7 @@
                         "pages": [
                           "pt-BR/guides/flows/first-flow",
                           "pt-BR/guides/flows/mastering-flow-state",
+                          "pt-BR/guides/flows/conversational-flows",
                           "pt-BR/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -14425,6 +14482,7 @@
                       "pt-BR/enterprise/guides/build-crew",
                       "pt-BR/enterprise/guides/prepare-for-deployment",
                       "pt-BR/enterprise/guides/deploy-to-amp",
+                      "pt-BR/enterprise/guides/monorepo-deployments",
                       "pt-BR/enterprise/guides/private-package-registry",
                       "pt-BR/enterprise/guides/kickoff-crew",
                       "pt-BR/enterprise/guides/training-crews",
@@ -14596,6 +14654,7 @@
                         "pages": [
                           "ko/guides/flows/first-flow",
                           "ko/guides/flows/mastering-flow-state",
+                          "ko/guides/flows/conversational-flows",
                           "ko/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -14963,6 +15022,7 @@
                       "ko/enterprise/guides/build-crew",
                       "ko/enterprise/guides/prepare-for-deployment",
                       "ko/enterprise/guides/deploy-to-amp",
+                      "ko/enterprise/guides/monorepo-deployments",
                       "ko/enterprise/guides/private-package-registry",
                       "ko/enterprise/guides/kickoff-crew",
                       "ko/enterprise/guides/training-crews",
@@ -15471,6 +15531,7 @@
                       "ko/enterprise/guides/build-crew",
                       "ko/enterprise/guides/prepare-for-deployment",
                       "ko/enterprise/guides/deploy-to-amp",
+                      "ko/enterprise/guides/monorepo-deployments",
                       "ko/enterprise/guides/private-package-registry",
                       "ko/enterprise/guides/kickoff-crew",
                       "ko/enterprise/guides/training-crews",
@@ -15612,6 +15673,7 @@
                         "pages": [
                           "ko/guides/flows/first-flow",
                           "ko/guides/flows/mastering-flow-state",
+                          "ko/guides/flows/conversational-flows",
                           "ko/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -15946,6 +16008,7 @@
                       "ko/enterprise/guides/build-crew",
                       "ko/enterprise/guides/prepare-for-deployment",
                       "ko/enterprise/guides/deploy-to-amp",
+                      "ko/enterprise/guides/monorepo-deployments",
                       "ko/enterprise/guides/private-package-registry",
                       "ko/enterprise/guides/kickoff-crew",
                       "ko/enterprise/guides/training-crews",
@@ -16087,6 +16150,7 @@
                         "pages": [
                           "ko/guides/flows/first-flow",
                           "ko/guides/flows/mastering-flow-state",
+                          "ko/guides/flows/conversational-flows",
                           "ko/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -16421,6 +16485,7 @@
                       "ko/enterprise/guides/build-crew",
                       "ko/enterprise/guides/prepare-for-deployment",
                       "ko/enterprise/guides/deploy-to-amp",
+                      "ko/enterprise/guides/monorepo-deployments",
                       "ko/enterprise/guides/private-package-registry",
                       "ko/enterprise/guides/kickoff-crew",
                       "ko/enterprise/guides/training-crews",
@@ -16562,6 +16627,7 @@
                         "pages": [
                           "ko/guides/flows/first-flow",
                           "ko/guides/flows/mastering-flow-state",
+                          "ko/guides/flows/conversational-flows",
                           "ko/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -16896,6 +16962,7 @@
                       "ko/enterprise/guides/build-crew",
                       "ko/enterprise/guides/prepare-for-deployment",
                       "ko/enterprise/guides/deploy-to-amp",
+                      "ko/enterprise/guides/monorepo-deployments",
                       "ko/enterprise/guides/private-package-registry",
                       "ko/enterprise/guides/kickoff-crew",
                       "ko/enterprise/guides/training-crews",
@@ -17037,6 +17104,7 @@
                         "pages": [
                           "ko/guides/flows/first-flow",
                           "ko/guides/flows/mastering-flow-state",
+                          "ko/guides/flows/conversational-flows",
                           "ko/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -17381,6 +17449,7 @@
                       "ko/enterprise/guides/build-crew",
                       "ko/enterprise/guides/prepare-for-deployment",
                       "ko/enterprise/guides/deploy-to-amp",
+                      "ko/enterprise/guides/monorepo-deployments",
                       "ko/enterprise/guides/private-package-registry",
                       "ko/enterprise/guides/kickoff-crew",
                       "ko/enterprise/guides/training-crews",
@@ -17522,6 +17591,7 @@
                         "pages": [
                           "ko/guides/flows/first-flow",
                           "ko/guides/flows/mastering-flow-state",
+                          "ko/guides/flows/conversational-flows",
                           "ko/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -17866,6 +17936,7 @@
                       "ko/enterprise/guides/build-crew",
                       "ko/enterprise/guides/prepare-for-deployment",
                       "ko/enterprise/guides/deploy-to-amp",
+                      "ko/enterprise/guides/monorepo-deployments",
                       "ko/enterprise/guides/private-package-registry",
                       "ko/enterprise/guides/kickoff-crew",
                       "ko/enterprise/guides/training-crews",
@@ -18007,6 +18078,7 @@
                         "pages": [
                           "ko/guides/flows/first-flow",
                           "ko/guides/flows/mastering-flow-state",
+                          "ko/guides/flows/conversational-flows",
                           "ko/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -18351,6 +18423,7 @@
                       "ko/enterprise/guides/build-crew",
                       "ko/enterprise/guides/prepare-for-deployment",
                       "ko/enterprise/guides/deploy-to-amp",
+                      "ko/enterprise/guides/monorepo-deployments",
                       "ko/enterprise/guides/private-package-registry",
                       "ko/enterprise/guides/kickoff-crew",
                       "ko/enterprise/guides/training-crews",
@@ -18492,6 +18565,7 @@
                         "pages": [
                           "ko/guides/flows/first-flow",
                           "ko/guides/flows/mastering-flow-state",
+                          "ko/guides/flows/conversational-flows",
                           "ko/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -18836,6 +18910,7 @@
                       "ko/enterprise/guides/build-crew",
                       "ko/enterprise/guides/prepare-for-deployment",
                       "ko/enterprise/guides/deploy-to-amp",
+                      "ko/enterprise/guides/monorepo-deployments",
                       "ko/enterprise/guides/private-package-registry",
                       "ko/enterprise/guides/kickoff-crew",
                       "ko/enterprise/guides/training-crews",
@@ -18977,6 +19052,7 @@
                         "pages": [
                           "ko/guides/flows/first-flow",
                           "ko/guides/flows/mastering-flow-state",
+                          "ko/guides/flows/conversational-flows",
                           "ko/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -19311,6 +19387,7 @@
                       "ko/enterprise/guides/build-crew",
                       "ko/enterprise/guides/prepare-for-deployment",
                       "ko/enterprise/guides/deploy-to-amp",
+                      "ko/enterprise/guides/monorepo-deployments",
                       "ko/enterprise/guides/private-package-registry",
                       "ko/enterprise/guides/kickoff-crew",
                       "ko/enterprise/guides/training-crews",
@@ -19452,6 +19529,7 @@
                         "pages": [
                           "ko/guides/flows/first-flow",
                           "ko/guides/flows/mastering-flow-state",
+                          "ko/guides/flows/conversational-flows",
                           "ko/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -19786,6 +19864,7 @@
                       "ko/enterprise/guides/build-crew",
                       "ko/enterprise/guides/prepare-for-deployment",
                       "ko/enterprise/guides/deploy-to-amp",
+                      "ko/enterprise/guides/monorepo-deployments",
                       "ko/enterprise/guides/private-package-registry",
                       "ko/enterprise/guides/kickoff-crew",
                       "ko/enterprise/guides/training-crews",
@@ -19927,6 +20006,7 @@
                         "pages": [
                           "ko/guides/flows/first-flow",
                           "ko/guides/flows/mastering-flow-state",
+                          "ko/guides/flows/conversational-flows",
                           "ko/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -20261,6 +20341,7 @@
                       "ko/enterprise/guides/build-crew",
                       "ko/enterprise/guides/prepare-for-deployment",
                       "ko/enterprise/guides/deploy-to-amp",
+                      "ko/enterprise/guides/monorepo-deployments",
                       "ko/enterprise/guides/private-package-registry",
                       "ko/enterprise/guides/kickoff-crew",
                       "ko/enterprise/guides/training-crews",
@@ -20402,6 +20483,7 @@
                         "pages": [
                           "ko/guides/flows/first-flow",
                           "ko/guides/flows/mastering-flow-state",
+                          "ko/guides/flows/conversational-flows",
                           "ko/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -20735,6 +20817,7 @@
                       "ko/enterprise/guides/build-crew",
                       "ko/enterprise/guides/prepare-for-deployment",
                       "ko/enterprise/guides/deploy-to-amp",
+                      "ko/enterprise/guides/monorepo-deployments",
                       "ko/enterprise/guides/private-package-registry",
                       "ko/enterprise/guides/kickoff-crew",
                       "ko/enterprise/guides/training-crews",
@@ -20876,6 +20959,7 @@
                         "pages": [
                           "ko/guides/flows/first-flow",
                           "ko/guides/flows/mastering-flow-state",
+                          "ko/guides/flows/conversational-flows",
                           "ko/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -21209,6 +21293,7 @@
                       "ko/enterprise/guides/build-crew",
                       "ko/enterprise/guides/prepare-for-deployment",
                       "ko/enterprise/guides/deploy-to-amp",
+                      "ko/enterprise/guides/monorepo-deployments",
                       "ko/enterprise/guides/private-package-registry",
                       "ko/enterprise/guides/kickoff-crew",
                       "ko/enterprise/guides/training-crews",
@@ -21350,6 +21435,7 @@
                         "pages": [
                           "ko/guides/flows/first-flow",
                           "ko/guides/flows/mastering-flow-state",
+                          "ko/guides/flows/conversational-flows",
                           "ko/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -21684,6 +21770,7 @@
                       "ko/enterprise/guides/build-crew",
                       "ko/enterprise/guides/prepare-for-deployment",
                       "ko/enterprise/guides/deploy-to-amp",
+                      "ko/enterprise/guides/monorepo-deployments",
                       "ko/enterprise/guides/private-package-registry",
                       "ko/enterprise/guides/kickoff-crew",
                       "ko/enterprise/guides/training-crews",
@@ -21855,6 +21942,7 @@
                         "pages": [
                           "ar/guides/flows/first-flow",
                           "ar/guides/flows/mastering-flow-state",
+                          "ar/guides/flows/conversational-flows",
                           "ar/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -22222,6 +22310,7 @@
                       "ar/enterprise/guides/build-crew",
                       "ar/enterprise/guides/prepare-for-deployment",
                       "ar/enterprise/guides/deploy-to-amp",
+                      "ar/enterprise/guides/monorepo-deployments",
                       "ar/enterprise/guides/private-package-registry",
                       "ar/enterprise/guides/kickoff-crew",
                       "ar/enterprise/guides/training-crews",
@@ -22730,6 +22819,7 @@
                       "ar/enterprise/guides/build-crew",
                       "ar/enterprise/guides/prepare-for-deployment",
                       "ar/enterprise/guides/deploy-to-amp",
+                      "ar/enterprise/guides/monorepo-deployments",
                       "ar/enterprise/guides/private-package-registry",
                       "ar/enterprise/guides/kickoff-crew",
                       "ar/enterprise/guides/training-crews",
@@ -22871,6 +22961,7 @@
                         "pages": [
                           "ar/guides/flows/first-flow",
                           "ar/guides/flows/mastering-flow-state",
+                          "ar/guides/flows/conversational-flows",
                           "ar/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -23205,6 +23296,7 @@
                       "ar/enterprise/guides/build-crew",
                       "ar/enterprise/guides/prepare-for-deployment",
                       "ar/enterprise/guides/deploy-to-amp",
+                      "ar/enterprise/guides/monorepo-deployments",
                       "ar/enterprise/guides/private-package-registry",
                       "ar/enterprise/guides/kickoff-crew",
                       "ar/enterprise/guides/training-crews",
@@ -23346,6 +23438,7 @@
                         "pages": [
                           "ar/guides/flows/first-flow",
                           "ar/guides/flows/mastering-flow-state",
+                          "ar/guides/flows/conversational-flows",
                           "ar/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -23680,6 +23773,7 @@
                       "ar/enterprise/guides/build-crew",
                       "ar/enterprise/guides/prepare-for-deployment",
                       "ar/enterprise/guides/deploy-to-amp",
+                      "ar/enterprise/guides/monorepo-deployments",
                       "ar/enterprise/guides/private-package-registry",
                       "ar/enterprise/guides/kickoff-crew",
                       "ar/enterprise/guides/training-crews",
@@ -23821,6 +23915,7 @@
                         "pages": [
                           "ar/guides/flows/first-flow",
                           "ar/guides/flows/mastering-flow-state",
+                          "ar/guides/flows/conversational-flows",
                           "ar/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -24155,6 +24250,7 @@
                       "ar/enterprise/guides/build-crew",
                       "ar/enterprise/guides/prepare-for-deployment",
                       "ar/enterprise/guides/deploy-to-amp",
+                      "ar/enterprise/guides/monorepo-deployments",
                       "ar/enterprise/guides/private-package-registry",
                       "ar/enterprise/guides/kickoff-crew",
                       "ar/enterprise/guides/training-crews",
@@ -24296,6 +24392,7 @@
                         "pages": [
                           "ar/guides/flows/first-flow",
                           "ar/guides/flows/mastering-flow-state",
+                          "ar/guides/flows/conversational-flows",
                           "ar/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -24640,6 +24737,7 @@
                       "ar/enterprise/guides/build-crew",
                       "ar/enterprise/guides/prepare-for-deployment",
                       "ar/enterprise/guides/deploy-to-amp",
+                      "ar/enterprise/guides/monorepo-deployments",
                       "ar/enterprise/guides/private-package-registry",
                       "ar/enterprise/guides/kickoff-crew",
                       "ar/enterprise/guides/training-crews",
@@ -24781,6 +24879,7 @@
                         "pages": [
                           "ar/guides/flows/first-flow",
                           "ar/guides/flows/mastering-flow-state",
+                          "ar/guides/flows/conversational-flows",
                           "ar/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -25125,6 +25224,7 @@
                       "ar/enterprise/guides/build-crew",
                       "ar/enterprise/guides/prepare-for-deployment",
                       "ar/enterprise/guides/deploy-to-amp",
+                      "ar/enterprise/guides/monorepo-deployments",
                       "ar/enterprise/guides/private-package-registry",
                       "ar/enterprise/guides/kickoff-crew",
                       "ar/enterprise/guides/training-crews",
@@ -25266,6 +25366,7 @@
                         "pages": [
                           "ar/guides/flows/first-flow",
                           "ar/guides/flows/mastering-flow-state",
+                          "ar/guides/flows/conversational-flows",
                           "ar/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -25610,6 +25711,7 @@
                       "ar/enterprise/guides/build-crew",
                       "ar/enterprise/guides/prepare-for-deployment",
                       "ar/enterprise/guides/deploy-to-amp",
+                      "ar/enterprise/guides/monorepo-deployments",
                       "ar/enterprise/guides/private-package-registry",
                       "ar/enterprise/guides/kickoff-crew",
                       "ar/enterprise/guides/training-crews",
@@ -25751,6 +25853,7 @@
                         "pages": [
                           "ar/guides/flows/first-flow",
                           "ar/guides/flows/mastering-flow-state",
+                          "ar/guides/flows/conversational-flows",
                           "ar/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -26095,6 +26198,7 @@
                       "ar/enterprise/guides/build-crew",
                       "ar/enterprise/guides/prepare-for-deployment",
                       "ar/enterprise/guides/deploy-to-amp",
+                      "ar/enterprise/guides/monorepo-deployments",
                       "ar/enterprise/guides/private-package-registry",
                       "ar/enterprise/guides/kickoff-crew",
                       "ar/enterprise/guides/training-crews",
@@ -26236,6 +26340,7 @@
                         "pages": [
                           "ar/guides/flows/first-flow",
                           "ar/guides/flows/mastering-flow-state",
+                          "ar/guides/flows/conversational-flows",
                           "ar/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -26570,6 +26675,7 @@
                       "ar/enterprise/guides/build-crew",
                       "ar/enterprise/guides/prepare-for-deployment",
                       "ar/enterprise/guides/deploy-to-amp",
+                      "ar/enterprise/guides/monorepo-deployments",
                       "ar/enterprise/guides/private-package-registry",
                       "ar/enterprise/guides/kickoff-crew",
                       "ar/enterprise/guides/training-crews",
@@ -26711,6 +26817,7 @@
                         "pages": [
                           "ar/guides/flows/first-flow",
                           "ar/guides/flows/mastering-flow-state",
+                          "ar/guides/flows/conversational-flows",
                           "ar/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -27045,6 +27152,7 @@
                       "ar/enterprise/guides/build-crew",
                       "ar/enterprise/guides/prepare-for-deployment",
                       "ar/enterprise/guides/deploy-to-amp",
+                      "ar/enterprise/guides/monorepo-deployments",
                       "ar/enterprise/guides/private-package-registry",
                       "ar/enterprise/guides/kickoff-crew",
                       "ar/enterprise/guides/training-crews",
@@ -27186,6 +27294,7 @@
                         "pages": [
                           "ar/guides/flows/first-flow",
                           "ar/guides/flows/mastering-flow-state",
+                          "ar/guides/flows/conversational-flows",
                           "ar/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -27520,6 +27629,7 @@
                       "ar/enterprise/guides/build-crew",
                       "ar/enterprise/guides/prepare-for-deployment",
                       "ar/enterprise/guides/deploy-to-amp",
+                      "ar/enterprise/guides/monorepo-deployments",
                       "ar/enterprise/guides/private-package-registry",
                       "ar/enterprise/guides/kickoff-crew",
                       "ar/enterprise/guides/training-crews",
@@ -27661,6 +27771,7 @@
                         "pages": [
                           "ar/guides/flows/first-flow",
                           "ar/guides/flows/mastering-flow-state",
+                          "ar/guides/flows/conversational-flows",
                           "ar/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -27994,6 +28105,7 @@
                       "ar/enterprise/guides/build-crew",
                       "ar/enterprise/guides/prepare-for-deployment",
                       "ar/enterprise/guides/deploy-to-amp",
+                      "ar/enterprise/guides/monorepo-deployments",
                       "ar/enterprise/guides/private-package-registry",
                       "ar/enterprise/guides/kickoff-crew",
                       "ar/enterprise/guides/training-crews",
@@ -28135,6 +28247,7 @@
                         "pages": [
                           "ar/guides/flows/first-flow",
                           "ar/guides/flows/mastering-flow-state",
+                          "ar/guides/flows/conversational-flows",
                           "ar/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -28468,6 +28581,7 @@
                       "ar/enterprise/guides/build-crew",
                       "ar/enterprise/guides/prepare-for-deployment",
                       "ar/enterprise/guides/deploy-to-amp",
+                      "ar/enterprise/guides/monorepo-deployments",
                       "ar/enterprise/guides/private-package-registry",
                       "ar/enterprise/guides/kickoff-crew",
                       "ar/enterprise/guides/training-crews",
@@ -28609,6 +28723,7 @@
                         "pages": [
                           "ar/guides/flows/first-flow",
                           "ar/guides/flows/mastering-flow-state",
+                          "ar/guides/flows/conversational-flows",
                           "ar/guides/flows/inputs-id-deprecation"
                         ]
                       },
@@ -28943,6 +29058,7 @@
                       "ar/enterprise/guides/build-crew",
                       "ar/enterprise/guides/prepare-for-deployment",
                       "ar/enterprise/guides/deploy-to-amp",
+                      "ar/enterprise/guides/monorepo-deployments",
                       "ar/enterprise/guides/private-package-registry",
                       "ar/enterprise/guides/kickoff-crew",
                       "ar/enterprise/guides/training-crews",

docs/en/changelog.mdx

@@ -4,6 +4,58 @@ description: "Product updates, improvements, and bug fixes for CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="Jun 08, 2026">
+  ## v1.14.7a3
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7a3)
+
+  ## What's Changed
+
+  ### Bug Fixes
+  - Fix exposure of `ask_for_human_input` on experimental `AgentExecutor`
+  - Resolve pip-audit CVEs for `aiohttp`, `docling`, `docling-core`, and `pip`
+
+  ### Refactoring
+  - Migrate `@start` to read from `FlowDefinition`
+
+  ### Documentation
+  - Update changelog and version for v1.14.7a2
+
+  ## Contributors
+
+  @greysonlalonde, @lorenzejay, @vinibrsl
+
+</Update>
+
+<Update label="Jun 05, 2026">
+  ## v1.14.7a2
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7a2)
+
+  ## What's Changed
+
+  ### Features
+  - Add conversational flow traces support.
+  - Update conversational flow documentation to utilize `handle_turn`.
+  - Surface real `finish_reason`, sampling parameters, and `response.id` in LLM events.
+  - Type DSL triggers as route-aware decorators.
+  - Implement chat API for conversational flows.
+  - Make locking backend overridable in lock store.
+  - Split flow DSL monolith into focused decorator modules.
+  - Flatten LiteLLM cache/reasoning usage sub-counts in `_usage_to_dict`.
+  - Build `FlowDefinition` from Flow DSL metadata.
+
+  ### Documentation
+  - Add NVIDIA Nemotron LLM guide.
+  - Document monorepo deployments.
+  - Update changelog and version for v1.14.7a1.
+
+  ## Contributors
+
+  @alex-clawd, @gvieira, @lorenzejay, @lucasgomide, @mattatcha, @vinibrsl
+
+</Update>
+
 <Update label="Jun 03, 2026">
   ## v1.14.7a1
 

docs/en/concepts/llms.mdx

@@ -952,6 +952,61 @@ In this section, you'll find detailed examples that help you select, configure,
     ```
   </Accordion>
 
+  <Accordion title="NVIDIA Nemotron">
+    NVIDIA Nemotron models are designed for demanding agentic workloads, including complex reasoning, long-context analysis, tool use, multilingual tasks, and high-stakes RAG.
+
+    The `NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4` model is a frontier-scale open-weight model from NVIDIA with 550B total parameters and 55B active parameters. It uses a LatentMoE architecture that combines Mamba-2, MoE, Attention, and Multi-Token Prediction (MTP), and supports context lengths up to 1M tokens.
+
+    <Info>
+      `NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4` is a very large model. NVIDIA lists minimum serving requirements of 4x GB200, 4x B200, 4x GB300, 4x B300, or 8x H100 GPUs. For most CrewAI users, the recommended path is to use NVIDIA NIM or another OpenAI-compatible hosted endpoint rather than running it locally.
+    </Info>
+
+    **Hosted NVIDIA NIM usage:**
+    ```toml Code
+    NVIDIA_API_KEY=<your-api-key>
+    ```
+
+    ```python Code
+    from crewai import LLM
+
+    llm = LLM(
+        model="nvidia_nim/nvidia/nvidia-nemotron-3-ultra-550b-a55b",
+        temperature=0.2,
+        max_tokens=4096,
+    )
+    ```
+
+    **Self-hosted OpenAI-compatible endpoint:**
+    ```python Code
+    from crewai import LLM
+
+    llm = LLM(
+        model="openai/nvidia-nemotron-3-ultra-550b-a55b-nvfp4",
+        base_url="https://your-nemotron-endpoint.example.com/v1",
+        api_key="your-api-key",
+        temperature=0.2,
+        max_tokens=4096,
+    )
+    ```
+
+    **Model details:**
+
+    | Model | Context Window | Best For |
+    |-------|----------------|----------|
+    | `nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4` | Up to 1M tokens | Frontier reasoning, complex agentic workflows, long-context analysis, tool use, multilingual reasoning, and high-stakes RAG |
+
+    **Supported languages:** English, French, Spanish, Italian, German, Japanese, Korean, Hindi, Brazilian Portuguese, and Chinese.
+
+    **Reasoning mode:** Nemotron 3 Ultra supports configurable reasoning via its chat template using `enable_thinking=True` or `enable_thinking=False`. If you are using a hosted endpoint, check your provider's documentation for how that flag is exposed.
+
+    For model details, license, and deployment guidance, see the [NVIDIA Nemotron 3 Ultra model card](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4).
+
+    **Note:** Hosted NVIDIA NIM usage uses LiteLLM. Add it as a dependency to your project:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
+  </Accordion>
+
   <Accordion title="Local NVIDIA NIM Deployed using WSL2">
 
     NVIDIA NIM enables you to run powerful LLMs locally on your Windows machine using WSL2 (Windows Subsystem for Linux).

docs/en/enterprise/guides/deploy-to-amp.mdx

@@ -164,6 +164,12 @@ You need to push your crew to a GitHub repository. If you haven't created a crew
       ![Select Repository](/images/enterprise/select-repo.png)
     </Frame>
 
+    <Tip>
+      If your Crew or Flow is inside a monorepo subfolder, expand **Advanced**
+      and set a working directory before deploying. See
+      [Monorepo Deployments](/en/enterprise/guides/monorepo-deployments).
+    </Tip>
+
   </Step>
 
   <Step title="Set Environment Variables">

docs/en/enterprise/guides/monorepo-deployments.mdx

@@ -0,0 +1,225 @@
+---
+title: "Monorepo Deployments"
+description: "Deploy a Crew or Flow from a subfolder in a larger repository"
+icon: "folder-tree"
+mode: "wide"
+---
+
+<Note>
+  Use a working directory when your Crew or Flow lives inside a larger
+  repository. CrewAI AMP validates, builds, tests, and runs the automation from
+  that subfolder instead of the repository root.
+</Note>
+
+## When to Use This
+
+Monorepo deployments are useful when one repository contains multiple
+automations, shared packages, or other application code:
+
+```text
+company-ai/
+|-- uv.lock
+|-- packages/
+|   `-- shared_tools/
+`-- crews/
+    |-- support_agent/
+    |   |-- pyproject.toml
+    |   `-- src/
+    |       `-- support_agent/
+    |           |-- main.py
+    |           `-- crew.py
+    `-- research_flow/
+        |-- pyproject.toml
+        `-- src/
+            `-- research_flow/
+                `-- main.py
+```
+
+To deploy `support_agent`, set the working directory to:
+
+```text
+crews/support_agent
+```
+
+AMP still pulls or uploads the whole repository, but it treats the selected
+folder as the automation project root.
+
+## What the Working Directory Controls
+
+When a working directory is set, AMP uses that folder for:
+
+- Project validation, including `pyproject.toml`, `src/`, and the Crew or Flow entry point
+- Dependency installation with `uv`
+- The running process working directory
+- The `CREW_ROOT_DIR` environment variable
+
+Leaving the field empty keeps the existing behavior and uses the repository
+root.
+
+## Supported Sources
+
+You can set a working directory when creating a deployment from:
+
+- A connected GitHub repository
+- A Git repository configured in AMP
+- A ZIP upload
+
+<Info>
+  Configure working directories in the AMP web interface. The
+  `crewai deploy create` CLI flow does not prompt for this field.
+</Info>
+
+You can also add or change the working directory on an existing deployment from
+the deployment's **Settings** page. The change takes effect on the next deploy.
+
+<Warning>
+  Working directories and auto-deploy cannot be used together. If a deployment
+  has a working directory, auto-deploy is disabled for that deployment. Turn
+  auto-deploy off before setting a working directory.
+</Warning>
+
+## Configure a New Deployment
+
+<Steps>
+  <Step title="Open Deploy from Code">
+    In CrewAI AMP, create a new deployment and choose your source: GitHub, Git
+    Repository, or ZIP upload.
+  </Step>
+
+  <Step title="Select the repository, branch, or ZIP file">
+    Choose the repository and branch that contain your monorepo, or upload a ZIP
+    file whose root contains the monorepo contents.
+  </Step>
+
+  <Step title="Open Advanced settings">
+    Expand the **Advanced** section in the deploy form.
+  </Step>
+
+  <Step title="Enter the working directory">
+    Enter the path from the repository root to the Crew or Flow project:
+
+    ```text
+    crews/support_agent
+    ```
+
+    Do not include a leading slash.
+  </Step>
+
+  <Step title="Deploy">
+    Add any required environment variables, then start the deployment.
+  </Step>
+</Steps>
+
+## Configure an Existing Deployment
+
+<Steps>
+  <Step title="Open the deployment settings">
+    Go to your automation in AMP and open **Settings**.
+  </Step>
+
+  <Step title="Turn off auto-deploy if needed">
+    If auto-deploy is enabled, disable it first. The working directory field is
+    unavailable while auto-deploy is on.
+  </Step>
+
+  <Step title="Set the working directory">
+    In **Basic settings**, enter the subfolder path, such as:
+
+    ```text
+    crews/support_agent
+    ```
+  </Step>
+
+  <Step title="Redeploy">
+    Save the setting and redeploy the automation. The new working directory is
+    used on the next deploy.
+  </Step>
+</Steps>
+
+## Path Rules
+
+The working directory must be a relative path inside the repository or ZIP root.
+
+| Rule | Example |
+|------|---------|
+| Use a relative path | `crews/support_agent` |
+| Do not start with `/` | `/crews/support_agent` is invalid |
+| Do not use `.` or `..` path segments | `crews/../support_agent` is invalid |
+| Use only letters, numbers, dashes, underscores, dots, and forward slashes | `crews/support agent` is invalid |
+| Keep the path at 255 characters or fewer | Longer paths are rejected |
+
+AMP trims leading and trailing whitespace, collapses repeated slashes, and
+removes trailing slashes. A blank value uses the repository root.
+
+## Lock Files and UV Workspaces
+
+The selected folder must contain the automation's `pyproject.toml` and `src/`
+directory. A `uv.lock` or `poetry.lock` file can live either in the selected
+folder or at the repository root.
+
+This supports both common monorepo layouts:
+
+<Tabs>
+  <Tab title="Project lock file">
+    ```text
+    company-ai/
+    `-- crews/
+        `-- support_agent/
+            |-- pyproject.toml
+            |-- uv.lock
+            `-- src/
+                `-- support_agent/
+                    `-- main.py
+    ```
+  </Tab>
+
+  <Tab title="Workspace lock file">
+    ```text
+    company-ai/
+    |-- uv.lock
+    |-- packages/
+    |   `-- shared_tools/
+    `-- crews/
+        `-- support_agent/
+            |-- pyproject.toml
+            `-- src/
+                `-- support_agent/
+                    `-- main.py
+    ```
+  </Tab>
+</Tabs>
+
+<Tip>
+  If your automation imports shared packages from elsewhere in the monorepo,
+  declare those packages in `pyproject.toml` using UV workspace, path, or source
+  configuration. AMP runs the automation from the selected folder, so shared
+  code should be installed as a dependency instead of relying on the repository
+  root being on the Python path.
+</Tip>
+
+## Troubleshooting
+
+### Working Directory Not Found
+
+Check that the path is relative to the repository or ZIP root. For ZIP uploads,
+the ZIP contents must include the working directory path exactly as entered.
+
+### Missing pyproject.toml
+
+The working directory should point to the Crew or Flow project folder, not just
+to a parent folder that contains several projects.
+
+### Missing uv.lock or poetry.lock
+
+Commit a lock file either in the selected project folder or in the repository
+root. For UV workspaces, keeping `uv.lock` at the workspace root is supported.
+
+### Auto-Deploy Is Unavailable
+
+Auto-deploy is disabled while a working directory is set. Use manual redeploys
+or trigger redeployments from CI/CD with the AMP API instead.
+
+<Card title="Deploy to AMP" icon="rocket" href="/en/enterprise/guides/deploy-to-amp">
+  Continue with the deployment guide after choosing your monorepo working
+  directory.
+</Card>

docs/en/guides/concepts/evaluating-use-cases.mdx

@@ -172,7 +172,7 @@ Flows are ideal when:
 
 ```python
 # Example: Customer Support Flow with structured processing
-from crewai.flow.flow import Flow, listen, router, start
+from crewai.flow.flow import Flow, listen, or_, router, start
 from pydantic import BaseModel
 from typing import List, Dict
 
@@ -238,7 +238,7 @@ class CustomerSupportFlow(Flow[SupportTicketState]):
 
     # Additional category handlers...
 
-    @listen("billing", "account_access", "technical_issue", "feature_request", "other")
+    @listen(or_("billing", "account_access", "technical_issue", "feature_request", "other"))
     def resolve_ticket(self, resolution_info):
         # Final resolution step
         self.state.resolution = f"Issue resolved: {resolution_info}"

docs/en/guides/flows/conversational-flows.mdx

@@ -0,0 +1,501 @@
+---
+title: Conversational Flows
+description: Build multi-turn chat apps with handle_turn per turn, message history, intent routing, tracing, and WebSocket bridges.
+icon: comments
+mode: "wide"
+---
+
+## Overview
+
+Conversational apps treat each user line as a **new flow run** with the **same session id**. CrewAI adds helpers for message history, optional intent routing, deferred tracing, UI bridges, and a local `flow.chat()` REPL for conversational flows.
+
+| Concept | Implementation |
+|---------|----------------|
+| Session id | `handle_turn(..., session_id=...)` → `kickoff(inputs={"id": ...})` → `state.id` |
+| User line | `handle_turn(message)` appends to `state.messages` before the graph runs |
+| Turn complete | `FlowFinished` for **this run** only; chat continues on the next `handle_turn` |
+| Full-session trace | `ConversationConfig(defer_trace_finalization=True)` + `finalize_session_traces()` |
+
+## Turn APIs
+
+Use **`flow.handle_turn(message, session_id=...)`** for every user message from REST, WebSocket, tests, and custom UIs. Use **`flow.chat()`** when you want a local terminal chat loop for a conversational `Flow`.
+
+`Flow.kickoff()` does **not** accept `user_message=` or `session_id=` keyword arguments. For conversational flows, `handle_turn()` stores the pending message and calls `kickoff(inputs={"id": session_id})` internally after resetting per-turn execution state.
+
+| API | Use for |
+|-----|---------|
+| `handle_turn(message, session_id=...)` | Ergonomic one-turn wrapper for conversational `Flow` |
+| `chat()` | Local terminal REPL for conversational `Flow` |
+| `kickoff(inputs={...})` | Advanced flow execution without conversational turn handling |
+| `ask()` | Blocking prompt **inside** one step (wizard, clarification) |
+| `@human_feedback` | Approve/reject **a step output** — not the next chat line |
+| `ChatSession.handle_turn(...)` | Transport layer over `handle_turn` (SSE / WebSocket) |
+
+## Quick start
+
+```python
+from uuid import uuid4
+
+from crewai import Flow
+from crewai.flow import listen
+from crewai.experimental.conversational import (
+    ConversationConfig,
+    ConversationState,
+)
+
+
+@ConversationConfig(defer_trace_finalization=True)
+class SupportFlow(Flow[ConversationState]):
+    conversational = True
+
+    def route_turn(self, context):
+        message = (self.state.current_user_message or "").lower()
+        if "order" in message:
+            return "order"
+        if "bye" in message or "goodbye" in message:
+            return "goodbye"
+        return "help"
+
+    @listen("order")
+    def handle_order(self):
+        reply = "Your order is on the way."
+        self.append_assistant_message(reply)
+        return reply
+
+    @listen("help")
+    def handle_help(self):
+        reply = "How can I help?"
+        self.append_assistant_message(reply)
+        return reply
+
+    @listen("goodbye")
+    def handle_goodbye(self):
+        reply = "Goodbye!"
+        self.append_assistant_message(reply)
+        return reply
+
+
+session_id = str(uuid4())
+flow = SupportFlow()
+
+try:
+    flow.handle_turn("Where is my order?", session_id=session_id)
+    flow.handle_turn("What about returns?", session_id=session_id)
+finally:
+    flow.finalize_session_traces()  # one trace link for the whole chat
+```
+
+## Turn lifecycle
+
+Each `handle_turn` runs this pipeline:
+
+1. **Turn setup** — stores the pending user message, resolves the session id, resets per-turn execution tracking, and calls `kickoff(inputs={"id": session_id})`.
+2. **State restore** — if `inputs["id"]` exists and `@persist` is configured, loads the latest snapshot.
+3. **`FlowStarted`** — emitted on the first deferred session turn only.
+4. **Pending turn hydration** — appends the user message to `state.messages`, sets `current_user_message` / `last_user_message`, and optionally classifies when `intents` / `default_intents` + `intent_llm` are set.
+5. **Graph execution** — `conversation_start` → `route_conversation` → the selected `@listen` handler.
+6. **End of run** — per-turn `flow_finished` and trace finalization are **skipped** when deferral is enabled; nested `Agent.kickoff()` / crews do not close the parent batch either.
+
+Handlers should call **`append_assistant_message(reply)`** so the next turn’s `conversation_messages` includes assistant text. The user line is already stored by `handle_turn` — do not append it again in handlers.
+
+## `ConversationConfig` (class-level defaults)
+
+Decorate your conversational `Flow` subclass with `ConversationConfig`.
+
+| Field | Default | Purpose |
+|-------|---------|---------|
+| `system_prompt` | Framework default | System message used by the built-in `converse_turn`. |
+| `llm` | `None` | Conversation LLM used by `converse_turn` and as router fallback. |
+| `router` | `None` | `RouterConfig` for LLM-driven routing. |
+| `intent_llm` | `None` | LLM for `intents=` / `default_intents` pre-classification. |
+| `default_intents` | `None` | Outcome labels for pre-classification. |
+| `defer_trace_finalization` | `True` | Keep one trace batch open across `handle_turn()` calls. |
+
+Override pre-classification per turn with `handle_turn(..., intents=..., intent_llm=...)`.
+
+## Lower-level `ChatState` helpers
+
+`ChatState`, `ConversationalConfig`, and `crewai.flow.conversation` helpers are still importable for advanced orchestration, tests, or custom wrappers. They do not add `user_message=` or `session_id=` keyword arguments to `Flow.kickoff()`.
+
+```python
+from crewai.flow import ChatState
+
+
+class MyChatState(ChatState):
+    # Inherited: id, messages, last_user_message, last_intent, session_ready
+    research_turn_count: int = 0
+    custom_flag: bool = False
+```
+
+| Field | Role |
+|-------|------|
+| `id` | Session UUID (same as `inputs["id"]`) |
+| `messages` | `list` of `{role, content}` for LLM history |
+| `last_user_message` | Latest user line for this turn |
+| `last_intent` | Route label after classification (if used) |
+| `session_ready` | One-time bootstrap flag (permissions, caches, etc.) |
+
+`ConversationalInputs` is a `TypedDict` for conventional `kickoff(inputs={...})` keys: `id`, `user_message`, `last_intent`.
+
+## `Flow` conversational API
+
+### `handle_turn` parameters
+
+| Parameter | Purpose |
+|-----------|---------|
+| `message` | This turn’s text |
+| `session_id` | Conversation UUID → `inputs["id"]` / `state.id` |
+| `intents` | Outcome labels for pre-kickoff `classify_intent` |
+| `intent_llm` | LLM for classification (required with `intents`) |
+| `**kickoff_kwargs` | Forwarded to `kickoff()` for options like `input_files`, `from_checkpoint`, and `restore_from_state_id` |
+
+### `kickoff` parameters
+
+`Flow.kickoff()` accepts `inputs`, `input_files`, `from_checkpoint`, and `restore_from_state_id`. Pass `inputs={"id": session_id}` when you need raw flow execution, but use `handle_turn()` when the call represents a chat message.
+
+### Instance attributes
+
+| Attribute | Purpose |
+|-----------|---------|
+| `conversational` | Set to `True` to enable the conversational graph and `handle_turn()` |
+| `defer_trace_finalization` | Instance flag; set automatically from config on `handle_turn()` |
+| `suppress_flow_events` | Hides console flow panels; **tracing still records** method/flow events |
+| `stream` | Enable streaming; use with `ChatSession.handle_turn(..., stream=True)` |
+
+### Methods and properties
+
+| Name | Description |
+|------|-------------|
+| `append_assistant_message(content)` | Append a user-visible assistant reply to `state.messages` |
+| `append_message(role, content, **extra)` | Lower-level append to `state.messages` |
+| `conversation_messages` | Read-only history for LLM calls |
+| `classify_intent(text, outcomes, *, llm, context=None)` | Map text to one outcome (same collapse logic as `@human_feedback`) |
+| `receive_user_message(text, *, outcomes=None, llm=None)` | Append user message; optionally set `last_intent` |
+| `finalize_session_traces()` | Emit deferred `flow_finished` and finalize the session trace batch |
+| `_should_defer_trace_finalization()` | Whether this flow defers per-turn trace finalization |
+| `input_history` | Audit trail of `ask()` prompts and responses |
+
+### Module helpers (`crewai.flow.conversation`)
+
+Importable for tests or custom orchestration:
+
+| Function | Description |
+|----------|-------------|
+| `normalize_kickoff_inputs(inputs, user_message=..., session_id=...)` | Merge conversational kwargs into `inputs` |
+| `get_conversation_messages(flow)` | Read messages from state or internal buffer |
+| `append_message(flow, role, content, **extra)` | Same as instance method |
+| `prepare_conversational_turn(flow, user_message=..., intents=..., intent_llm=..., config=...)` | Lower-level turn hydration for custom wrappers |
+| `receive_user_message(flow, text, ...)` | Same as instance method |
+| `set_state_field(flow, name, value)` | Set a field on dict or Pydantic state |
+| `get_conversational_config(flow)` | Read class `conversational_config` |
+| `input_history_to_messages(entries)` | Convert `input_history` to LLM message format |
+
+## Intent routing patterns
+
+### A. Pre-classify via `ConversationConfig` (simplest)
+
+Set `default_intents` and `intent_llm`. Each `handle_turn()` runs classification before routing; read `self.state.last_intent` in `route_turn()`.
+
+### B. Classify inside `route_turn` (richer prompts)
+
+Set `default_intents=None` so `handle_turn()` only appends the user message. In `route_turn()`, call `classify_intent` with a custom prompt or descriptions:
+
+```python
+def route_turn(self, context):
+    intent = self.classify_intent(
+        self._routing_prompt(self.state.current_user_message),
+        ("GREETING", "ORDER", "RESEARCH", "GOODBYE"),
+        llm="gpt-4o-mini",
+    )
+    self.state.last_intent = intent
+    return intent
+```
+
+Use **`@listen("RESEARCH")`** (or similar) for steps that run `Agent.kickoff()` with tools — not bare `LLM.call()` — when you need web research or multi-step tool use.
+
+## When the flow finishes but the user keeps chatting
+
+`FlowFinished` means **this graph run** completed. The conversation continues with another `handle_turn()` and the same `session_id`. `@persist` restores `messages`, flags, and context.
+
+**Persist pattern:** prefer `@persist` on a **single terminal step** (for example `finalize`) rather than on the whole `Flow` class. Class-level persist saves after every method; `load_state` uses the latest row, which may be a mid-run snapshot (for example right after `bootstrap`) and miss handler updates from the same turn.
+
+Do **not** use `@human_feedback` for follow-up chat lines unless a human must approve a specific step output before it is shown.
+
+## Conversational `Flow` (experimental)
+
+<Warning>
+  **This is an experimental feature.** The conversational `Flow` surface
+  (`conversational = True`, `handle_turn`, `ConversationConfig`,
+  `RouterConfig`, `ConversationState`, the built-in graph + helpers) lives
+  under `crewai.experimental` and may change shape before it graduates.
+  Pin your CrewAI version if you depend on specific behavior, and watch the
+  changelog for breaking updates. Open issues / feedback welcome.
+</Warning>
+
+Opt into the conversational chat graph by setting `conversational = True` on a `Flow` subclass. The base `Flow` then ships a built-in `@start` / `@router` / `converse_turn` / `end_conversation` graph, manages `state.messages`, can drive a router LLM, and keeps the trace batch open across turns. You write the **custom routes**; the framework owns the rest.
+
+Use this when you want a multi-turn chat with a router and per-route handlers without wiring the lifecycle yourself. Use `Flow[ChatState]` (the lower-level pattern above) when you need full control.
+
+### Quick example
+
+```python
+from crewai import Flow
+from crewai.flow import listen
+from crewai.experimental.conversational import (
+    ConversationConfig,
+    ConversationState,
+)
+
+
+@ConversationConfig(defer_trace_finalization=True)
+class SupportFlow(Flow[ConversationState]):
+    conversational = True
+
+    def route_turn(self, context: dict) -> str | None:
+        message = (self.state.current_user_message or "").lower()
+        if "search" in message or "news" in message:
+            return "INTERNET_SEARCH"
+        if "docs" in message or "crewai" in message:
+            return "CREWAI_DOCS"
+        return "converse"
+
+    @listen("INTERNET_SEARCH")
+    def handle_internet_search(self) -> str:
+        """Fresh web research, current news, real-time lookups."""
+        reply = "I would run the web research route here."
+        self.append_assistant_message(reply)
+        return reply
+
+    @listen("CREWAI_DOCS")
+    def handle_crewai_docs(self) -> str:
+        """Look up the CrewAI documentation for framework/API questions."""
+        reply = "I would look up the CrewAI docs here."
+        self.append_assistant_message(reply)
+        return reply
+
+
+flow = SupportFlow()
+try:
+    flow.handle_turn("What can you do?")              # routes to converse
+    flow.handle_turn("Search the web for AI news.")   # routes to INTERNET_SEARCH
+    flow.handle_turn("Check the CrewAI docs.")         # routes to CREWAI_DOCS
+finally:
+    flow.finalize_session_traces()
+```
+
+For a local terminal chat, use `chat()`:
+
+```python
+def kickoff() -> None:
+    SupportFlow().chat()
+```
+
+`chat()` wraps `handle_turn()` in a REPL, exits on `exit` / `quit`, skips blank lines by default, and calls `finalize_session_traces()` when the session ends.
+
+### `ConversationConfig`
+
+Class decorator that attaches per-class chat defaults.
+
+| Field | Default | Purpose |
+|-------|---------|---------|
+| `system_prompt` | `slices.conversational_system_prompt` from i18n | System message used by the built-in `converse_turn`. Pass `""` to opt out entirely. |
+| `llm` | `None` | Conversation LLM (used by `converse_turn` and as router fallback). |
+| `router` | `None` | `RouterConfig` for LLM-driven routing. Without it, the flow always falls through to `converse`. |
+| `answer_from_history_prompt` | Framework default | System message for the optional `answer_from_history` route. |
+| `answer_from_history_llm` | `None` | Enables the `answer_from_history` short-circuit when set. |
+| `intent_llm` | `None` | LLM for legacy `intents=`/`default_intents` pre-classification. |
+| `default_intents` | `None` | Outcome labels for legacy pre-classification. |
+| `visible_agent_outputs` | `None` | `"all"`, or a list of agent names whose `append_agent_result()` calls should be promoted to public assistant messages. |
+| `defer_trace_finalization` | `True` | Keep one trace batch open across `handle_turn()` calls. |
+
+### `RouterConfig` and the auto-built route catalog
+
+```python
+from typing import Literal
+
+from pydantic import BaseModel
+
+from crewai import LLM
+from crewai.experimental.conversational import RouterConfig
+
+
+class MyRoute(BaseModel):
+    intent: Literal["INTERNET_SEARCH", "CREWAI_DOCS", "converse"]
+
+
+ROUTER_LLM = LLM(model="gpt-4o-mini")
+
+router_config = RouterConfig(
+    prompt="Optional domain framing (policy, voice, persona).",
+    response_format=MyRoute,        # optional; auto-generated otherwise
+    llm=ROUTER_LLM,                  # falls back to ConversationConfig.llm
+    routes=["INTERNET_SEARCH", "CREWAI_DOCS"],   # optional; inferred from listeners
+    route_descriptions={
+        "INTERNET_SEARCH": "Override the docstring for this one route.",
+    },
+    default_intent="converse",       # used when LLM call fails or no LLM available
+    fallback_intent="converse",      # used when LLM returns an invalid route
+    intent_field="intent",
+)
+```
+
+The router prompt that gets sent to the LLM is built automatically. For each route the framework picks a description with this precedence:
+
+1. `RouterConfig.route_descriptions[label]` — explicit override.
+2. `Flow.builtin_route_descriptions[label]` — framework-canned text for `converse`, `end`, `answer_from_history` (phrased for the router LLM).
+3. First non-empty line of the `@listen(label)` handler's docstring.
+4. Empty (the route is listed without a description).
+
+So in practice, **adding a new route is `@listen("X")` + a one-line docstring**:
+
+```python
+from crewai.flow import listen
+
+
+@listen("INTERNET_SEARCH")
+def handle_internet_search(self) -> str:
+    """Fresh web research, current news, real-time lookups."""
+    ...
+```
+
+…and the router LLM sees:
+
+```
+Routes:
+- CREWAI_DOCS: Look up the CrewAI documentation for framework/API questions.
+- INTERNET_SEARCH: Fresh web research, current news, real-time lookups.
+- converse: Ordinary chat, follow-ups, summaries, clarifications…
+- end: User signals the conversation is finished (goodbye, exit, done).
+```
+
+`RouterConfig.prompt` is for **domain framing** (assistant persona, business rules, voice). The route catalog is auto-built — don't list routes in `prompt`; they'll drift the moment you add a handler.
+
+### Built-in routes
+
+| Route | Handler | Purpose |
+|-------|---------|---------|
+| `converse` | `converse_turn` | Default chat handler. Calls `ConversationConfig.llm` with the system prompt + canonical message history. |
+| `end` | `end_conversation` | Sets `state.ended = True` and emits a terminator reply. |
+| `answer_from_history` | `answer_from_history_turn` | Optional. Routes here when `ConversationConfig.answer_from_history_llm` is set and the message can be answered from existing history. |
+
+You can override any of these by defining a same-named handler in your subclass.
+
+### `handle_turn()` semantics
+
+`flow.handle_turn(message)` runs one turn:
+
+1. Resets per-execution tracking (`_completed_methods`, `_method_outputs`) so the graph re-runs — without this, repeated `kickoff` calls on the same flow instance would short-circuit on turn 2+ because `Flow.kickoff_async` treats `inputs={"id": ...}` as a checkpoint restore.
+2. Appends the user message to `state.messages`, sets `current_user_message` / `last_user_message`. `last_intent` is **preserved from the prior turn** so the router LLM can use it as a signal.
+3. Runs `conversation_start` → `route_conversation` → the chosen `@listen` handler.
+4. The router stores its decision in `state.last_intent` (visible to the next turn's router context).
+5. If your handler returned a string and didn't already call `append_assistant_message`, `handle_turn` appends it for you.
+
+Call `handle_turn()` for chat messages. Calling `kickoff(inputs={"id": ...})` directly runs the flow graph without applying the conversational turn wrapper.
+
+### `chat()` for local REPLs
+
+`flow.chat()` is the batteries-included terminal wrapper around `handle_turn()`:
+
+```python
+flow = SupportFlow()
+flow.chat()
+```
+
+It handles the common local loop:
+
+1. Prompts for a user message.
+2. Stops on `exit` / `quit`, `EOFError`, or `KeyboardInterrupt`.
+3. Calls `handle_turn(message, session_id=...)`.
+4. Prints the assistant result.
+5. Finalizes deferred session traces in a `finally` block.
+
+Customize the terminal behavior with injectable I/O:
+
+```python
+flow.chat(
+    session_id="demo-session",
+    prompt="You: ",
+    assistant_prefix="Assistant: ",
+    exit_commands=("exit", "quit", "bye"),
+)
+```
+
+For web apps, background workers, tests, and custom transports, keep using `handle_turn()` directly.
+
+### Custom router behavior
+
+To run side effects (event bus setup, telemetry) on every routing decision, override `route_turn`:
+
+```python
+from typing import Any
+
+from crewai import Flow
+from crewai.experimental.conversational import ConversationState
+
+
+class SupportFlow(Flow[ConversationState]):
+    conversational = True
+
+    def route_turn(self, context: dict[str, Any]) -> str | None:
+        self.event_bus = MyBus(self)
+        return super().route_turn(context)
+```
+
+To bypass the LLM router entirely and pick a route programmatically, return a string from `route_turn`; returning `None` falls back to `_route_with_config(...)`.
+
+### `append_assistant_message` and `append_agent_result`
+
+Inside a `@listen(label)` handler, choose:
+
+- `self.append_assistant_message(text)` — adds a user-visible assistant turn to `state.messages`. The next turn's `converse_turn` sees it.
+- `self.append_agent_result(agent_name, result, visibility="private")` — records a structured event in `state.events` and a thread in `state.agent_threads[agent_name]`. Public visibility also calls `append_assistant_message` for you. Use private results for scratch work that shouldn't pollute the canonical history.
+
+`ConversationConfig.visible_agent_outputs` can promote specific agents' private results to public globally (`"all"`, or a list of agent names).
+
+## Tracing across turns
+
+With `defer_trace_finalization=True` (default in `ConversationConfig`):
+
+- **One trace batch** for the whole chat session.
+- **`flow_started`** on the first turn only; **`flow_finished`** once in `finalize_session_traces()`.
+- **Per-turn** `kickoff` does not print “Trace batch finalized”.
+- **Nested work** (`Agent.kickoff()`, crews, Exa tools) appends to the **parent** batch; inner `AgentExecutor` flows do not close the session batch early.
+
+```python
+flow.chat(session_id=session_id)
+```
+
+`flow.chat()` calls `finalize_session_traces()` for you. When you own the loop
+with `handle_turn()`, call `finalize_session_traces()` when
+the session ends.
+
+`suppress_flow_events=True` only hides Rich console panels; trace and method events still emit for observability.
+
+### Conversational `Flow` trace lifecycle
+
+The experimental [conversational `Flow`](#conversational-flow-experimental) uses the same tracing lifecycle: `defer_trace_finalization` defaults to `True`, so each `handle_turn()` keeps the session trace open. Always finalize at the end of the session — wrap your REPL/loop in `try/finally` and call `flow.finalize_session_traces()` on exit. Without it, the trace batch stays open and the final conversation may never export.
+
+## Streaming
+
+Set `stream = True` on the `Flow` class. `kickoff(...)` will then emit `assistant_delta` (and related) events through the standard event bus.
+
+## Imports
+
+```python
+from crewai.flow import (
+    ChatState,
+    ConversationalConfig,
+    ConversationalInputs,
+    Flow,
+    listen,
+    persist,
+    router,
+    start,
+)
+```
+
+## See also
+
+- [Mastering Flow State Management](/en/guides/flows/mastering-flow-state) — persistence, Pydantic state, `@persist`
+- [Build Your First Flow](/en/guides/flows/first-flow) — flow basics
+- Demo: `lib/crewai/runner_conversational_flow_simple.py` — minimal REPL with `RESEARCH` + Exa agent

docs/en/guides/flows/first-flow.mdx

@@ -617,6 +617,7 @@ Now that you've built your first flow, you can:
 3. Explore the `and_` and `or_` functions for more complex parallel execution
 4. Connect your flow to external APIs, databases, or user interfaces
 5. Combine multiple specialized crews in a single flow
+6. Build multi-turn chat apps with [Conversational Flows](/en/guides/flows/conversational-flows) (`kickoff` per message, `ChatSession`, deferred tracing)
 
 <Check>
 Congratulations! You've successfully built your first CrewAI Flow that combines regular code, direct LLM calls, and crew-based processing to create a comprehensive guide. These foundational skills enable you to create increasingly sophisticated AI applications that can tackle complex, multi-stage problems through a combination of procedural control and collaborative intelligence.

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

@@ -22,6 +22,8 @@ Effective state management enables you to:
 5. **Scale your applications** - Support complex workflows with proper data organization
 6. **Enable conversational applications** - Store and access conversation history for context-aware AI interactions
 
+For multi-turn chat (`kickoff` per user line, `ChatState`, intent routing, deferred tracing, and `ChatSession`), see [Conversational Flows](/en/guides/flows/conversational-flows).
+
 Let's explore how to leverage these capabilities effectively.
 
 ## State Management Fundamentals

docs/ko/changelog.mdx

@@ -4,6 +4,58 @@ description: "CrewAI의 제품 업데이트, 개선 사항 및 버그 수정"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="2026년 6월 8일">
+  ## v1.14.7a3
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7a3)
+
+  ## 변경 사항
+
+  ### 버그 수정
+  - 실험적인 `AgentExecutor`에서 `ask_for_human_input` 노출 문제 수정
+  - `aiohttp`, `docling`, `docling-core`, 및 `pip`에 대한 pip-audit CVE 해결
+
+  ### 리팩토링
+  - `@start`를 `FlowDefinition`에서 읽도록 마이그레이션
+
+  ### 문서화
+  - v1.14.7a2에 대한 변경 로그 및 버전 업데이트
+
+  ## 기여자
+
+  @greysonlalonde, @lorenzejay, @vinibrsl
+
+</Update>
+
+<Update label="2026년 6월 5일">
+  ## v1.14.7a2
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7a2)
+
+  ## 변경 사항
+
+  ### 기능
+  - 대화 흐름 추적 지원 추가.
+  - `handle_turn`을 활용하도록 대화 흐름 문서 업데이트.
+  - LLM 이벤트에서 실제 `finish_reason`, 샘플링 매개변수 및 `response.id` 표시.
+  - 라우트 인식 데코레이터로서 DSL 트리거 유형 지정.
+  - 대화 흐름을 위한 채팅 API 구현.
+  - 잠금 저장소에서 백엔드 잠금 오버라이드 가능하게 설정.
+  - 흐름 DSL 모놀리스를 집중된 데코레이터 모듈로 분할.
+  - `_usage_to_dict`에서 LiteLLM 캐시/추론 사용 하위 카운트 평탄화.
+  - 흐름 DSL 메타데이터에서 `FlowDefinition` 구축.
+
+  ### 문서
+  - NVIDIA Nemotron LLM 가이드 추가.
+  - 모노레포 배포 문서화.
+  - v1.14.7a1에 대한 변경 로그 및 버전 업데이트.
+
+  ## 기여자
+
+  @alex-clawd, @gvieira, @lorenzejay, @lucasgomide, @mattatcha, @vinibrsl
+
+</Update>
+
 <Update label="2026년 6월 3일">
   ## v1.14.7a1
 

docs/ko/enterprise/guides/deploy-to-amp.mdx

@@ -163,6 +163,12 @@ Crew를 GitHub 저장소에 푸시해야 합니다. 아직 Crew를 만들지 않
       ![Select Repository](/images/enterprise/select-repo.png)
     </Frame>
 
+    <Tip>
+      Crew 또는 Flow가 모노레포 하위 폴더 안에 있다면 배포 전에
+      **Advanced**를 펼치고 작업 디렉터리를 설정하세요.
+      [모노레포 배포](/ko/enterprise/guides/monorepo-deployments)를 참조하세요.
+    </Tip>
+
   </Step>
 
   <Step title="환경 변수 설정하기">
@@ -440,4 +446,4 @@ type = "flow"
 
 <Card title="도움이 필요하신가요?" icon="headset" href="mailto:support@crewai.com">
   배포 문제 또는 AMP 플랫폼에 대한 문의 사항이 있으시면 지원팀에 연락해 주세요.
-</Card>
+</Card>

docs/ko/enterprise/guides/monorepo-deployments.mdx

@@ -0,0 +1,222 @@
+---
+title: "모노레포 배포"
+description: "더 큰 저장소의 하위 폴더에서 Crew 또는 Flow 배포하기"
+icon: "folder-tree"
+mode: "wide"
+---
+
+<Note>
+  Crew 또는 Flow가 더 큰 저장소 안에 있을 때 작업 디렉터리를 사용하세요.
+  CrewAI AMP는 저장소 루트 대신 해당 하위 폴더에서 자동화를 검증, 빌드,
+  실행합니다.
+</Note>
+
+## 사용 시점
+
+모노레포 배포는 하나의 저장소에 여러 자동화, 공유 패키지 또는 다른 애플리케이션
+코드가 함께 있을 때 유용합니다:
+
+```text
+company-ai/
+|-- uv.lock
+|-- packages/
+|   `-- shared_tools/
+`-- crews/
+    |-- support_agent/
+    |   |-- pyproject.toml
+    |   `-- src/
+    |       `-- support_agent/
+    |           |-- main.py
+    |           `-- crew.py
+    `-- research_flow/
+        |-- pyproject.toml
+        `-- src/
+            `-- research_flow/
+                `-- main.py
+```
+
+`support_agent`를 배포하려면 작업 디렉터리를 다음과 같이 설정합니다:
+
+```text
+crews/support_agent
+```
+
+AMP는 여전히 전체 저장소를 가져오거나 업로드하지만, 선택한 폴더를 자동화
+프로젝트 루트로 처리합니다.
+
+## 작업 디렉터리가 제어하는 항목
+
+작업 디렉터리가 설정되면 AMP는 해당 폴더를 다음 용도로 사용합니다:
+
+- `pyproject.toml`, `src/`, Crew 또는 Flow 진입점을 포함한 프로젝트 검증
+- `uv`를 사용한 종속성 설치
+- 실행 중인 프로세스의 작업 디렉터리
+- `CREW_ROOT_DIR` 환경 변수
+
+필드를 비워 두면 기존 동작이 유지되며 저장소 루트를 사용합니다.
+
+## 지원되는 소스
+
+다음 소스에서 배포를 만들 때 작업 디렉터리를 설정할 수 있습니다:
+
+- 연결된 GitHub 저장소
+- AMP에 구성된 Git 저장소
+- ZIP 업로드
+
+<Info>
+  작업 디렉터리는 AMP 웹 인터페이스에서 구성하세요.
+  `crewai deploy create` CLI 흐름은 이 필드를 묻지 않습니다.
+</Info>
+
+기존 배포의 **Settings** 페이지에서도 작업 디렉터리를 추가하거나 변경할 수
+있습니다. 변경 사항은 다음 배포부터 적용됩니다.
+
+<Warning>
+  작업 디렉터리와 auto-deploy는 함께 사용할 수 없습니다. 배포에 작업
+  디렉터리가 설정되어 있으면 해당 배포의 auto-deploy가 비활성화됩니다.
+  작업 디렉터리를 설정하기 전에 auto-deploy를 끄세요.
+</Warning>
+
+## 새 배포 구성
+
+<Steps>
+  <Step title="Deploy from Code 열기">
+    CrewAI AMP에서 새 배포를 만들고 소스를 선택합니다: GitHub, Git
+    Repository 또는 ZIP 업로드.
+  </Step>
+
+  <Step title="저장소, 브랜치 또는 ZIP 파일 선택">
+    모노레포가 들어 있는 저장소와 브랜치를 선택하거나, 루트에 모노레포 내용이
+    포함된 ZIP 파일을 업로드합니다.
+  </Step>
+
+  <Step title="고급 설정 열기">
+    배포 양식에서 **Advanced** 섹션을 펼칩니다.
+  </Step>
+
+  <Step title="작업 디렉터리 입력">
+    저장소 루트에서 Crew 또는 Flow 프로젝트까지의 경로를 입력합니다:
+
+    ```text
+    crews/support_agent
+    ```
+
+    앞에 슬래시를 붙이지 마세요.
+  </Step>
+
+  <Step title="배포">
+    필요한 환경 변수를 추가한 다음 배포를 시작합니다.
+  </Step>
+</Steps>
+
+## 기존 배포 구성
+
+<Steps>
+  <Step title="배포 설정 열기">
+    AMP에서 자동화로 이동한 뒤 **Settings**를 엽니다.
+  </Step>
+
+  <Step title="필요한 경우 auto-deploy 끄기">
+    auto-deploy가 활성화되어 있으면 먼저 끄세요. auto-deploy가 켜져 있는
+    동안에는 작업 디렉터리 필드를 사용할 수 없습니다.
+  </Step>
+
+  <Step title="작업 디렉터리 설정">
+    **Basic settings**에서 다음과 같은 하위 폴더 경로를 입력합니다:
+
+    ```text
+    crews/support_agent
+    ```
+  </Step>
+
+  <Step title="다시 배포">
+    설정을 저장하고 자동화를 다시 배포합니다. 새 작업 디렉터리는 다음 배포부터
+    사용됩니다.
+  </Step>
+</Steps>
+
+## 경로 규칙
+
+작업 디렉터리는 저장소 또는 ZIP 루트 안의 상대 경로여야 합니다.
+
+| 규칙 | 예시 |
+|------|------|
+| 상대 경로를 사용합니다 | `crews/support_agent` |
+| `/`로 시작하지 않습니다 | `/crews/support_agent`는 유효하지 않습니다 |
+| `.` 또는 `..` 경로 세그먼트를 사용하지 않습니다 | `crews/../support_agent`는 유효하지 않습니다 |
+| 문자, 숫자, 하이픈, 밑줄, 점, 슬래시만 사용합니다 | `crews/support agent`는 유효하지 않습니다 |
+| 경로는 255자 이하로 유지합니다 | 더 긴 경로는 거부됩니다 |
+
+AMP는 앞뒤 공백을 제거하고, 반복된 슬래시를 하나로 줄이며, 끝의 슬래시를
+제거합니다. 빈 값은 저장소 루트를 사용합니다.
+
+## Lock 파일과 UV 워크스페이스
+
+선택한 폴더에는 자동화의 `pyproject.toml`과 `src/` 디렉터리가 있어야
+합니다. `uv.lock` 또는 `poetry.lock` 파일은 선택한 폴더나 저장소 루트에
+둘 수 있습니다.
+
+이 방식은 일반적인 두 가지 모노레포 레이아웃을 모두 지원합니다:
+
+<Tabs>
+  <Tab title="프로젝트 lock 파일">
+    ```text
+    company-ai/
+    `-- crews/
+        `-- support_agent/
+            |-- pyproject.toml
+            |-- uv.lock
+            `-- src/
+                `-- support_agent/
+                    `-- main.py
+    ```
+  </Tab>
+
+  <Tab title="워크스페이스 lock 파일">
+    ```text
+    company-ai/
+    |-- uv.lock
+    |-- packages/
+    |   `-- shared_tools/
+    `-- crews/
+        `-- support_agent/
+            |-- pyproject.toml
+            `-- src/
+                `-- support_agent/
+                    `-- main.py
+    ```
+  </Tab>
+</Tabs>
+
+<Tip>
+  자동화가 모노레포의 다른 위치에 있는 공유 패키지를 가져온다면, UV
+  workspace, path 또는 source 설정을 사용해 해당 패키지를 `pyproject.toml`에
+  선언하세요. AMP는 선택한 폴더에서 자동화를 실행하므로, 저장소 루트가
+  Python path에 있다고 가정하기보다 공유 코드를 종속성으로 설치해야 합니다.
+</Tip>
+
+## 문제 해결
+
+### 작업 디렉터리를 찾을 수 없음
+
+경로가 저장소 또는 ZIP 루트를 기준으로 한 상대 경로인지 확인하세요. ZIP
+업로드의 경우 ZIP 내용에 입력한 작업 디렉터리 경로가 정확히 포함되어야 합니다.
+
+### pyproject.toml 누락
+
+작업 디렉터리는 여러 프로젝트를 담은 상위 폴더가 아니라 Crew 또는 Flow 프로젝트
+폴더를 가리켜야 합니다.
+
+### uv.lock 또는 poetry.lock 누락
+
+선택한 프로젝트 폴더 또는 저장소 루트에 lock 파일을 커밋하세요. UV
+워크스페이스의 경우 `uv.lock`을 워크스페이스 루트에 두는 방식이 지원됩니다.
+
+### Auto-Deploy를 사용할 수 없음
+
+작업 디렉터리가 설정되어 있으면 auto-deploy가 비활성화됩니다. 수동 재배포를
+사용하거나 AMP API로 CI/CD에서 재배포를 트리거하세요.
+
+<Card title="AMP에 배포하기" icon="rocket" href="/ko/enterprise/guides/deploy-to-amp">
+  모노레포 작업 디렉터리를 선택한 뒤 배포 가이드를 계속 진행하세요.
+</Card>

docs/ko/guides/flows/conversational-flows.mdx

@@ -0,0 +1,474 @@
+---
+title: 대화형 Flow
+description: 턴마다 kickoff, 메시지 기록, 의도 라우팅, 트레이싱, WebSocket 브리지로 멀티턴 채팅 앱을 만듭니다.
+icon: comments
+mode: "wide"
+---
+
+## 개요
+
+대화형 앱은 각 사용자 입력을 **동일한 세션 id**로 **새 flow 실행**으로 처리합니다. CrewAI는 메시지 기록, 선택적 의도 분류, 지연 트레이싱, UI 브리지, 그리고 대화형 flow용 로컬 `flow.chat()` REPL을 제공합니다.
+
+| 개념 | 구현 |
+|------|------|
+| 세션 id | `handle_turn(..., session_id=...)` → `kickoff(inputs={"id": ...})` → `state.id` |
+| 사용자 입력 | `handle_turn(message)`가 그래프 실행 전 `state.messages`에 추가 |
+| 턴 완료 | `FlowFinished`는 **이번 실행**만 의미; 다음 `handle_turn`로 대화 계속 |
+| 세션 전체 트레이스 | `ConversationConfig(defer_trace_finalization=True)` + `finalize_session_traces()` |
+
+## 턴 API
+
+REST, WebSocket, 테스트, 커스텀 UI에서 오는 모든 사용자 메시지에는 **`flow.handle_turn(message, session_id=...)`**를 사용하세요. 대화형 `Flow`를 로컬 터미널 채팅 루프로 실행하고 싶을 때는 **`flow.chat()`**을 사용하세요.
+
+`Flow.kickoff()`는 `user_message=` 또는 `session_id=` 키워드 인자를 받지 않습니다. 대화형 flow에서는 `handle_turn()`이 보류 중인 메시지를 저장하고 내부적으로 `kickoff(inputs={"id": session_id})`를 호출합니다.
+
+| API | 용도 |
+|-----|------|
+| `handle_turn(message, session_id=...)` | 대화형 `Flow`용 한 턴 편의 래퍼 |
+| `chat()` | 대화형 `Flow`용 로컬 터미널 REPL |
+| `kickoff(inputs={...})` | 대화형 턴 처리 없이 flow를 직접 실행 |
+| `ask()` | 한 스텝 **내부** 블로킹 프롬프트 (마법사, 확인) |
+| `@human_feedback` | **스텝 출력** 승인/거부 — 다음 채팅 줄이 아님 |
+| `ChatSession.handle_turn(...)` | `handle_turn` 위의 전송 계층 (SSE / WebSocket) |
+
+## 빠른 시작
+
+```python
+from uuid import uuid4
+
+from crewai import Flow
+from crewai.flow import listen
+from crewai.experimental.conversational import (
+    ConversationConfig,
+    ConversationState,
+)
+
+
+@ConversationConfig(defer_trace_finalization=True)
+class SupportFlow(Flow[ConversationState]):
+    conversational = True
+
+    def route_turn(self, context):
+        message = self.state.current_user_message or ""
+        if "주문" in message or "order" in message.lower():
+            return "order"
+        if "안녕" in message or "goodbye" in message.lower():
+            return "goodbye"
+        return "help"
+
+    @listen("order")
+    def handle_order(self):
+        reply = "주문이 배송 중입니다."
+        self.append_assistant_message(reply)
+        return reply
+
+    @listen("help")
+    def handle_help(self):
+        reply = "무엇을 도와드릴까요?"
+        self.append_assistant_message(reply)
+        return reply
+
+    @listen("goodbye")
+    def handle_goodbye(self):
+        reply = "안녕히 가세요!"
+        self.append_assistant_message(reply)
+        return reply
+
+
+session_id = str(uuid4())
+flow = SupportFlow()
+
+try:
+    flow.handle_turn("주문 어디까지 왔나요?", session_id=session_id)
+    flow.handle_turn("반품은 어떻게 하나요?", session_id=session_id)
+finally:
+    flow.finalize_session_traces()  # 전체 대화에 대한 단일 trace 링크
+```
+
+## 턴 생명주기
+
+각 `handle_turn`은 다음 파이프라인을 실행합니다:
+
+1. **`_configure_conversational_kickoff`** — `session_id` / `user_message`를 `inputs`에 병합, `ConversationalConfig` 적용, 설정 시 지연 트레이싱 활성화.
+2. **상태 복원** — `inputs["id"]`가 있고 `@persist`가 설정되면 최신 스냅샷 로드.
+3. **`FlowStarted`** — 지연 세션의 첫 턴에서만 발생.
+4. **`prepare_conversational_turn`** — 사용자 메시지를 `state.messages`에 추가, `last_user_message` 설정, `last_intent` 초기화, `intents` / `default_intents` + `intent_llm` 설정 시 분류.
+5. **그래프 실행** — `@start` → `@router` → `@listen` 핸들러.
+6. **실행 종료** — 지연 활성화 시 턴별 `flow_finished` 및 trace 종료 **건너뜀**; 중첩 `Agent.kickoff()` / crew도 부모 batch를 닫지 않음.
+
+핸들러는 **`append_assistant_message(reply)`**를 호출해 다음 턴의 `conversation_messages`에 어시스턴트 응답이 포함되게 하세요. 사용자 입력은 `handle_turn`이 이미 저장합니다 — 핸들러에서 다시 추가하지 마세요.
+
+## `ConversationalConfig` (클래스 수준 기본값)
+
+`Flow` 서브클래스에 `conversational_config: ClassVar[ConversationalConfig | None]`로 설정합니다.
+
+| 필드 | 기본값 | 목적 |
+|------|--------|------|
+| `default_intents` | `None` | kickoff 전 자동 분류용 outcome 라벨 |
+| `intent_llm` | `None` | 분류용 모델 (intent 사용 시 필수) |
+| `interactive_prompt` | `"You: "` | `kickoff(interactive=True)` 프롬프트 |
+| `interactive_timeout` | `None` | 대화형 모드 줄 단위 타임아웃 |
+| `exit_commands` | `exit`, `quit` | 대화형 모드 종료 단어 |
+| `defer_trace_finalization` | `True` | 턴 간 하나의 trace batch 유지 |
+
+`intents=` 및 `intent_llm=` 키워드로 kickoff마다 재정의할 수 있습니다.
+
+## `ChatState` (권장 persist 형태)
+
+```python
+from crewai.flow import ChatState
+
+
+class MyChatState(ChatState):
+    # 상속: id, messages, last_user_message, last_intent, session_ready
+    research_turn_count: int = 0
+    custom_flag: bool = False
+```
+
+| 필드 | 역할 |
+|------|------|
+| `id` | 세션 UUID (`session_id` / `inputs["id"]`와 동일) |
+| `messages` | LLM 기록용 `{role, content}` 리스트 |
+| `last_user_message` | 이번 턴의 최신 사용자 입력 |
+| `last_intent` | 분류 후 라우트 라벨 (사용 시) |
+| `session_ready` | 일회성 bootstrap 플래그 |
+
+`ConversationalInputs`는 `kickoff(inputs={...})`용 `TypedDict`: `id`, `user_message`, `last_intent`.
+
+## `Flow` 대화 API
+
+### `kickoff` / `kickoff_async` 파라미터
+
+| 파라미터 | 목적 |
+|----------|------|
+| `user_message` | 이번 턴 텍스트 (또는 `{"role": "user", "content": "..."}`) |
+| `session_id` | 대화 UUID → `inputs["id"]` / `state.id` |
+| `intents` | kickoff 전 `classify_intent`용 outcome 라벨 |
+| `intent_llm` | 분류 LLM (`intents`와 함께 필수) |
+| `interactive` | `ask()` CLI 루프 (로컬 데모 전용) |
+| `interactive_prompt` | 대화형 모드 프롬프트 |
+| `interactive_timeout` | 줄 단위 `ask()` 타임아웃 |
+| `exit_commands` | 대화형 모드 종료 단어 |
+| `inputs` | 추가 상태 필드 |
+| `restore_from_state_id` | 다른 persist flow에서 fork 복원 |
+
+### 인스턴스 속성
+
+| 속성 | 목적 |
+|------|------|
+| `conversational_config` | 클래스 수준 `ConversationalConfig` |
+| `defer_trace_finalization` | 인스턴스 플래그; kickoff 시 config에서 자동 설정 |
+| `suppress_flow_events` | 콘솔 flow 패널 숨김; **트레이싱은 계속 기록** |
+| `stream` | 스트리밍; `ChatSession.handle_turn(..., stream=True)`와 함께 |
+
+### 메서드 및 프로퍼티
+
+| 이름 | 설명 |
+|------|------|
+| `append_message(role, content, **extra)` | `state.messages`에 추가 |
+| `conversation_messages` | LLM 호출용 읽기 전용 기록 |
+| `classify_intent(text, outcomes, *, llm, context=None)` | outcome 매핑 (`@human_feedback`와 동일 collapse) |
+| `receive_user_message(text, *, outcomes=None, llm=None)` | 사용자 메시지 추가; 선택적 `last_intent` |
+| `finalize_session_traces()` | 지연 `flow_finished` 발생 및 세션 trace batch 종료 |
+| `_should_defer_trace_finalization()` | 턴별 trace 종료 지연 여부 |
+| `input_history` | `ask()` 프롬프트/응답 감사 기록 |
+
+### 모듈 헬퍼 (`crewai.flow.conversation`)
+
+테스트 또는 커스텀 오케스트레이션용:
+
+| 함수 | 설명 |
+|------|------|
+| `normalize_kickoff_inputs(...)` | 대화 kwargs를 `inputs`에 병합 |
+| `get_conversation_messages(flow)` | 상태 또는 내부 버퍼에서 메시지 읽기 |
+| `append_message(flow, ...)` | 인스턴스 메서드와 동일 |
+| `prepare_conversational_turn(flow, ...)` | 턴 수화 (보통 kickoff가 호출) |
+| `receive_user_message(flow, ...)` | 인스턴스 메서드와 동일 |
+| `set_state_field(flow, name, value)` | dict 또는 Pydantic 상태 필드 설정 |
+| `get_conversational_config(flow)` | 클래스 `conversational_config` 읽기 |
+| `input_history_to_messages(entries)` | `input_history`를 LLM 메시지 형식으로 |
+
+## 의도 라우팅 패턴
+
+### A. `ConversationalConfig`로 사전 분류 (가장 단순)
+
+`default_intents`와 `intent_llm` 설정. 각 kickoff가 `@router` 전에 분류; `route()`에서 `self.state.last_intent` 읽기.
+
+### B. `@router` 내부에서 분류 (풍부한 프롬프트)
+
+`default_intents=None`으로 kickoff는 메시지만 추가. `route()`에서 커스텀 프롬프트로 `classify_intent` 호출:
+
+```python
+@router(bootstrap)
+def route(self):
+    intent = self.classify_intent(
+        self._routing_prompt(self.state.last_user_message),
+        ("GREETING", "ORDER", "RESEARCH", "GOODBYE"),
+        llm=self.conversational_config.intent_llm or "gpt-4o-mini",
+    )
+    self.state.last_intent = intent
+    return intent
+```
+
+웹 리서치나 다단계 tool이 필요하면 **`@listen("RESEARCH")`** 등에서 `Agent.kickoff()`와 tool 사용 — 단순 `LLM.call()` 대신.
+
+## flow가 끝났지만 사용자는 계속 대화할 때
+
+`FlowFinished`는 **이번 그래프 실행**이 완료됨을 의미합니다. 같은 `session_id`로 또 다른 `kickoff`로 대화가 이어집니다. `@persist`가 `messages`, 플래그, 컨텍스트를 복원합니다.
+
+**Persist 패턴:** 전체 `Flow` 클래스보다 **단일 종료 스텝**(예: `finalize`)에 `@persist`를 두는 것이 좋습니다. 클래스 수준 persist는 매 메서드 후 저장하며, `load_state`는 최신 행을 사용해 같은 턴의 핸들러 업데이트를 놓칠 수 있습니다.
+
+후속 채팅 줄에 `@human_feedback`를 쓰지 마세요. 특정 스텝 출력을 사람이 승인해야 할 때만 사용하세요.
+
+## 대화형 `Flow` (실험적)
+
+<Warning>
+  **실험적 기능입니다.** 대화형 `Flow`의 API 표면(`conversational = True`,
+  `handle_turn`, `ConversationConfig`, `RouterConfig`, `ConversationState`,
+  내장 그래프와 헬퍼)은 `crewai.experimental` 하위에 있으며 정식 출시
+  전까지 변경될 수 있습니다. 특정 동작에 의존한다면 CrewAI 버전을 고정하고
+  변경 사항이 있는지 changelog를 확인하세요. 피드백과 이슈 환영합니다.
+</Warning>
+
+`Flow` 서브클래스에 `conversational = True`를 지정하면 대화형 챗 그래프가 활성화됩니다. 베이스 `Flow`가 `@start` / `@router` / `converse_turn` / `end_conversation` 그래프를 노출하고, `state.messages`를 관리하며, router LLM을 구동하고, 턴 간 trace 배치를 열린 상태로 유지합니다. 여러분은 **커스텀 라우트**만 작성하면 되고, 나머지는 프레임워크가 담당합니다.
+
+LLM 기반 라우터와 라우트별 핸들러로 멀티턴 챗을 만들고 싶지만 라이프사이클을 직접 배선하고 싶지 않을 때 사용하세요. 완전한 제어가 필요하면 위의 `Flow[ChatState]`로 내려가세요.
+
+### 빠른 예제
+
+```python
+from crewai import LLM, Flow
+from crewai.flow import listen
+from crewai.experimental.conversational import (
+    ConversationConfig,
+    ConversationState,
+    RouterConfig,
+)
+
+
+ROUTER_LLM = LLM(model="gpt-4o-mini")
+
+
+@ConversationConfig(
+    system_prompt="A multi-agent assistant for ordinary chat and tool-backed tasks.",
+    llm=ROUTER_LLM,
+    router=RouterConfig(),  # 라우트 + 설명은 @listen 핸들러에서 자동 발견
+)
+class SupportFlow(Flow[ConversationState]):
+    conversational = True
+
+    @listen("INTERNET_SEARCH")
+    def handle_internet_search(self) -> str:
+        """Fresh web research, current news, real-time lookups."""
+        ...
+        self.append_assistant_message(reply)
+        return reply
+
+    @listen("CREWAI_DOCS")
+    def handle_crewai_docs(self) -> str:
+        """Look up the CrewAI documentation for framework/API questions."""
+        ...
+        self.append_assistant_message(reply)
+        return reply
+
+
+flow = SupportFlow()
+try:
+    flow.handle_turn("뭘 할 수 있어?")                # converse(빌트인)로 라우팅
+    flow.handle_turn("AI 뉴스를 웹에서 찾아줘.")        # INTERNET_SEARCH로 라우팅
+    flow.handle_turn("첫 번째 결과를 요약해줘.")        # 다시 converse로 라우팅
+finally:
+    flow.finalize_session_traces()
+```
+
+로컬 터미널 채팅에는 `chat()`을 사용하세요:
+
+```python
+def kickoff() -> None:
+    SupportFlow().chat()
+```
+
+`chat()`은 `handle_turn()`을 REPL로 감싸고, `exit` / `quit`에서 종료하며, 기본적으로 빈 줄을 건너뛰고, 세션이 끝날 때 `finalize_session_traces()`를 호출합니다.
+
+### `ConversationConfig`
+
+클래스 단위의 챗 기본값을 부착하는 클래스 데코레이터입니다.
+
+| 필드 | 기본값 | 목적 |
+|------|--------|------|
+| `system_prompt` | i18n `slices.conversational_system_prompt` | 빌트인 `converse_turn`이 사용하는 system 메시지. 빈 문자열(`""`)을 전달하면 system 메시지를 끕니다. |
+| `llm` | `None` | 대화용 LLM (빌트인 `converse_turn`이 사용하고 router 폴백도 됨). |
+| `router` | `None` | LLM 기반 라우팅을 위한 `RouterConfig`. 없으면 항상 `converse`로 떨어집니다. |
+| `answer_from_history_prompt` | 프레임워크 기본값 | 선택적인 `answer_from_history` 라우트용 system 메시지. |
+| `answer_from_history_llm` | `None` | 설정되면 `answer_from_history` 단축 경로가 활성화됩니다. |
+| `intent_llm` | `None` | 레거시 `intents=`/`default_intents` 사전 분류용 LLM. |
+| `default_intents` | `None` | 레거시 사전 분류용 outcome 레이블. |
+| `visible_agent_outputs` | `None` | `"all"` 또는 `append_agent_result()` 결과를 사용자에게 공개로 승격할 에이전트 이름 목록. |
+| `defer_trace_finalization` | `True` | `handle_turn()` 호출들 사이에서 하나의 trace 배치를 열어 둡니다. |
+
+### `RouterConfig`와 자동 생성되는 라우트 카탈로그
+
+```python
+RouterConfig(
+    prompt="선택적인 도메인 프레이밍 (정책, 톤, 페르소나).",
+    response_format=MyRoute,        # 선택; 없으면 자동 생성
+    llm=ROUTER_LLM,                  # ConversationConfig.llm으로 폴백
+    routes=["INTERNET_SEARCH", "CREWAI_DOCS"],   # 선택; 리스너에서 추론
+    route_descriptions={
+        "INTERNET_SEARCH": "이 라우트만 docstring 대신 사용할 설명.",
+    },
+    default_intent="converse",       # LLM 호출 실패 또는 LLM 없음일 때 사용
+    fallback_intent="converse",      # LLM이 잘못된 라우트를 반환할 때 사용
+    intent_field="intent",
+)
+```
+
+router에 전달되는 프롬프트는 자동으로 만들어집니다. 각 라우트의 설명은 다음 우선순위로 결정됩니다:
+
+1. `RouterConfig.route_descriptions[label]` — 명시적 오버라이드.
+2. `Flow.builtin_route_descriptions[label]` — `converse`, `end`, `answer_from_history`용 프레임워크 캐닝 텍스트 (router LLM용으로 다듬어진 문구).
+3. `@listen(label)` 핸들러 docstring의 첫 줄(비어있지 않은 줄).
+4. 빈 문자열 (라우트만 카탈로그에 등장하고 설명은 없음).
+
+실제 사용에서 **새 라우트를 추가하는 방법은 `@listen("X")` + 한 줄짜리 docstring**입니다:
+
+```python
+@listen("INTERNET_SEARCH")
+def handle_internet_search(self) -> str:
+    """Fresh web research, current news, real-time lookups."""
+    ...
+```
+
+…그러면 router LLM은 다음을 봅니다:
+
+```
+Routes:
+- CREWAI_DOCS: Look up the CrewAI documentation for framework/API questions.
+- INTERNET_SEARCH: Fresh web research, current news, real-time lookups.
+- converse: Ordinary chat, follow-ups, summaries, clarifications…
+- end: User signals the conversation is finished (goodbye, exit, done).
+```
+
+`RouterConfig.prompt`는 **도메인 프레이밍** (어시스턴트 페르소나, 비즈니스 규칙, 톤)을 위한 자리입니다. 라우트 카탈로그는 자동 생성되니 `prompt` 안에 라우트 목록을 넣지 마세요. 핸들러를 추가하는 순간 동기화가 깨집니다.
+
+### 빌트인 라우트
+
+| 라우트 | 핸들러 | 목적 |
+|--------|--------|------|
+| `converse` | `converse_turn` | 기본 챗 핸들러. system prompt + 정식 메시지 히스토리와 함께 `ConversationConfig.llm`을 호출합니다. |
+| `end` | `end_conversation` | `state.ended = True`로 설정하고 종료 응답을 보냅니다. |
+| `answer_from_history` | `answer_from_history_turn` | 선택적. `ConversationConfig.answer_from_history_llm`이 설정되어 있고 메시지를 히스토리만으로 답할 수 있을 때 라우팅됩니다. |
+
+서브클래스에 같은 이름의 핸들러를 정의하면 어떤 것이든 오버라이드할 수 있습니다.
+
+### `handle_turn()` 시맨틱
+
+`flow.handle_turn(message)`는 한 턴을 실행합니다:
+
+1. 그래프가 다시 실행되도록 턴 단위 실행 추적(`_completed_methods`, `_method_outputs`)을 초기화합니다 — 이게 없으면 동일 인스턴스에서 반복 `kickoff` 호출 시 `Flow.kickoff_async`가 `inputs={"id": ...}`를 체크포인트 복원으로 간주해 2번째 턴부터 단락 회로가 발생합니다.
+2. 사용자 메시지를 `state.messages`에 추가하고 `current_user_message` / `last_user_message`를 설정합니다. `last_intent`는 **이전 턴 값이 유지**되어 router LLM이 신호로 활용할 수 있습니다.
+3. `conversation_start` → `route_conversation` → 선택된 `@listen` 핸들러 순으로 실행됩니다.
+4. router는 결정을 `state.last_intent`에 저장합니다 (다음 턴의 router 컨텍스트에서 보입니다).
+5. 핸들러가 문자열을 반환했지만 `append_assistant_message`를 직접 호출하지 않았다면, `handle_turn`이 대신 추가해 줍니다.
+
+채팅 메시지에는 `handle_turn()`을 호출하세요. `kickoff(inputs={"id": ...})`를 직접 호출하면 대화형 턴 래퍼 없이 flow 그래프가 실행됩니다.
+
+### 로컬 REPL용 `chat()`
+
+`flow.chat()`은 `handle_turn()` 위에 얹은 바로 쓸 수 있는 터미널 래퍼입니다:
+
+```python
+flow = SupportFlow()
+flow.chat()
+```
+
+일반적인 로컬 루프를 처리합니다:
+
+1. 사용자 메시지를 입력받습니다.
+2. `exit` / `quit`, `EOFError`, `KeyboardInterrupt`에서 멈춥니다.
+3. `handle_turn(message, session_id=...)`를 호출합니다.
+4. 어시스턴트 결과를 출력합니다.
+5. `finally` 블록에서 지연된 세션 trace를 finalize합니다.
+
+주입 가능한 I/O로 터미널 동작을 커스터마이즈할 수 있습니다:
+
+```python
+flow.chat(
+    session_id="demo-session",
+    prompt="You: ",
+    assistant_prefix="Assistant: ",
+    exit_commands=("exit", "quit", "bye"),
+)
+```
+
+웹 앱, 백그라운드 worker, 테스트, 커스텀 transport에서는 계속 `handle_turn()`을 직접 사용하세요.
+
+### 커스텀 router 동작
+
+매 라우팅 결정마다 사이드 이펙트(이벤트 버스 셋업, 텔레메트리)를 실행하려면 `route_turn`을 오버라이드하세요:
+
+```python
+class SupportFlow(Flow[ConversationState]):
+    conversational = True
+
+    def route_turn(self, context: dict[str, Any]) -> str | None:
+        self.event_bus = MyBus(self)
+        return super().route_turn(context)
+```
+
+LLM router를 우회해 프로그램적으로 라우트를 선택하려면 `route_turn`에서 문자열을 반환하세요. `None`을 반환하면 `_route_with_config(...)`로 떨어집니다.
+
+### `append_assistant_message`와 `append_agent_result`
+
+`@listen(label)` 핸들러 안에서 두 가지 중 선택하세요:
+
+- `self.append_assistant_message(text)` — 사용자에게 보이는 어시스턴트 턴을 `state.messages`에 추가합니다. 다음 턴의 `converse_turn`이 이 내용을 보게 됩니다.
+- `self.append_agent_result(agent_name, result, visibility="private")` — 구조화된 이벤트를 `state.events`에, 스레드를 `state.agent_threads[agent_name]`에 기록합니다. public 가시성은 자동으로 `append_assistant_message`도 호출합니다. 정식 히스토리를 더럽히지 말아야 할 임시 작업에는 private을 쓰세요.
+
+`ConversationConfig.visible_agent_outputs`로 특정 에이전트의 private 결과를 전역적으로 public으로 승격할 수 있습니다 (`"all"` 또는 이름 리스트).
+
+## 턴 간 트레이싱
+
+`defer_trace_finalization=True` (`ConversationalConfig` 기본값):
+
+- 채팅 세션 전체에 **하나의 trace batch**.
+- 첫 턴에만 **`flow_started`**; `finalize_session_traces()`에서 **`flow_finished`** 한 번.
+- 턴별 `kickoff`는 “Trace batch finalized”를 출력하지 않음.
+- **중첩 작업** (`Agent.kickoff()`, crew, Exa tool)은 **부모** batch에 추가; 내부 `AgentExecutor` flow가 세션 batch를 조기 종료하지 않음.
+
+```python
+flow.chat(session_id=session_id)
+```
+
+`flow.chat()`이 `finalize_session_traces()`를 대신 호출합니다. `handle_turn()`이나 `kickoff(...)`로 직접 루프를 소유하는 경우, 세션이 끝날 때 `finalize_session_traces()`를 호출하세요.
+
+`suppress_flow_events=True`는 Rich 콘솔 패널만 숨깁니다. trace 및 method 이벤트는 계속 발생합니다.
+
+### 대화형 `Flow` trace 수명 주기
+
+실험적 [대화형 `Flow`](#대화형-flow-실험적)는 동일한 tracing 수명 주기를 따릅니다. `defer_trace_finalization` 기본값이 `True`이므로 각 `handle_turn()`이 세션 trace를 열어 둡니다. 세션 끝에서 항상 finalize하세요 — REPL/루프를 `try/finally`로 감싸고 종료 시 `flow.finalize_session_traces()`를 호출하세요. 호출하지 않으면 batch가 열린 채 남아 마지막 대화가 export되지 않을 수 있습니다.
+
+## 스트리밍
+
+`Flow` 클래스에 `stream = True`. `kickoff(...)`가 표준 이벤트 버스를 통해 `assistant_delta` 등 이벤트를 발생시킵니다.
+
+## import
+
+```python
+from crewai.flow import (
+    ChatState,
+    ConversationalConfig,
+    ConversationalInputs,
+    Flow,
+    listen,
+    persist,
+    router,
+    start,
+)
+```
+
+## 참고
+
+- [Flow 상태 관리 마스터하기](/ko/guides/flows/mastering-flow-state)
+- [첫 Flow 만들기](/ko/guides/flows/first-flow)
+- 데모: `lib/crewai/runner_conversational_flow_simple.py`

docs/ko/guides/flows/first-flow.mdx

@@ -607,6 +607,7 @@ result = ContentCrew().crew().kickoff(inputs={
 3. 더 복잡한 병렬 실행을 위해 `and_` 및 `or_` 함수를 탐색해 보세요.
 4. flow를 외부 API, 데이터베이스 또는 사용자 인터페이스에 연결해 보세요.
 5. 여러 전문화된 crew를 하나의 flow에서 결합해 보세요.
+6. [대화형 Flow](/ko/guides/flows/conversational-flows)로 멀티턴 채팅 앱 구축 (`kickoff` per message, `ChatSession`, 지연 트레이싱)
 
 <Check>
 축하합니다! 정규 코드, 직접적인 LLM 호출, crew 기반 처리를 결합하여 포괄적인 가이드를 생성하는 첫 번째 CrewAI Flow를 성공적으로 구축하셨습니다. 이러한 기초적인 역량을 바탕으로 절차적 제어와 협업적 인텔리전스를 결합하여 복잡하고 다단계의 문제를 해결할 수 있는 점점 더 정교한 AI 애플리케이션을 만들 수 있습니다.

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

@@ -22,6 +22,8 @@ State 관리는 모든 고급 AI 워크플로우의 중추입니다. CrewAI Flow
 5. **애플리케이션 확장** - 적절한 데이터 조직을 통해 복잡한 워크플로를 지원할 수 있습니다.
 6. **대화형 애플리케이션 활성화** - 컨텍스트 기반 AI 상호작용을 위해 대화 내역을 저장하고 접근할 수 있습니다.
 
+멀티턴 채팅(`kickoff` per user line, `ChatState`, 의도 라우팅, 지연 트레이싱, `ChatSession`)은 [대화형 Flow](/ko/guides/flows/conversational-flows)를 참고하세요.
+
 이러한 기능을 효과적으로 활용하는 방법을 살펴보겠습니다.
 
 ## 상태 관리 기본 사항

docs/pt-BR/changelog.mdx

@@ -4,6 +4,58 @@ description: "Atualizações de produto, melhorias e correções do CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="08 jun 2026">
+  ## v1.14.7a3
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7a3)
+
+  ## O que Mudou
+
+  ### Correções de Bugs
+  - Corrigir a exposição de `ask_for_human_input` no `AgentExecutor` experimental
+  - Resolver CVEs do pip-audit para `aiohttp`, `docling`, `docling-core` e `pip`
+
+  ### Refatoração
+  - Migrar `@start` para ler de `FlowDefinition`
+
+  ### Documentação
+  - Atualizar o changelog e a versão para v1.14.7a2
+
+  ## Contribuidores
+
+  @greysonlalonde, @lorenzejay, @vinibrsl
+
+</Update>
+
+<Update label="05 jun 2026">
+  ## v1.14.7a2
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7a2)
+
+  ## O que Mudou
+
+  ### Recursos
+  - Adicionar suporte a rastreamentos de fluxo de conversa.
+  - Atualizar a documentação do fluxo de conversa para utilizar `handle_turn`.
+  - Exibir o real `finish_reason`, parâmetros de amostragem e `response.id` em eventos LLM.
+  - Tipar os gatilhos DSL como decoradores cientes de rota.
+  - Implementar API de chat para fluxos de conversa.
+  - Tornar o backend de bloqueio substituível no armazenamento de bloqueios.
+  - Dividir o monólito DSL de fluxo em módulos de decoradores focados.
+  - Achatar os subcontagens de uso de cache/razão do LiteLLM em `_usage_to_dict`.
+  - Construir `FlowDefinition` a partir dos metadados do Flow DSL.
+
+  ### Documentação
+  - Adicionar guia do LLM NVIDIA Nemotron.
+  - Documentar implantações de monorepo.
+  - Atualizar changelog e versão para v1.14.7a1.
+
+  ## Contribuidores
+
+  @alex-clawd, @gvieira, @lorenzejay, @lucasgomide, @mattatcha, @vinibrsl
+
+</Update>
+
 <Update label="03 jun 2026">
   ## v1.14.7a1
 

docs/pt-BR/enterprise/guides/deploy-to-amp.mdx

@@ -163,6 +163,12 @@ Você precisa enviar seu crew para um repositório do GitHub. Caso ainda não te
       ![Selecionar Repositório](/images/enterprise/select-repo.png)
     </Frame>
 
+    <Tip>
+      Se seu Crew ou Flow estiver dentro de uma subpasta de monorepo, expanda
+      **Advanced** e defina um diretório de trabalho antes de implantar. Consulte
+      [Implantações em Monorepo](/pt-BR/enterprise/guides/monorepo-deployments).
+    </Tip>
+
   </Step>
 
   <Step title="Definir as Variáveis de Ambiente">
@@ -441,4 +447,4 @@ type = "flow"
 <Card title="Precisa de Ajuda?" icon="headset" href="mailto:support@crewai.com">
   Entre em contato com nossa equipe de suporte para ajuda com questões de
   implantação ou dúvidas sobre a plataforma AMP.
-</Card>
+</Card>

docs/pt-BR/enterprise/guides/monorepo-deployments.mdx

@@ -0,0 +1,230 @@
+---
+title: "Implantações em Monorepo"
+description: "Implante um Crew ou Flow a partir de uma subpasta em um repositório maior"
+icon: "folder-tree"
+mode: "wide"
+---
+
+<Note>
+  Use um diretório de trabalho quando seu Crew ou Flow estiver dentro de um
+  repositório maior. O CrewAI AMP valida, faz o build e executa a automação a
+  partir dessa subpasta em vez da raiz do repositório.
+</Note>
+
+## Quando Usar
+
+Implantações em monorepo são úteis quando um repositório contém múltiplas
+automações, pacotes compartilhados ou outro código de aplicação:
+
+```text
+company-ai/
+|-- uv.lock
+|-- packages/
+|   `-- shared_tools/
+`-- crews/
+    |-- support_agent/
+    |   |-- pyproject.toml
+    |   `-- src/
+    |       `-- support_agent/
+    |           |-- main.py
+    |           `-- crew.py
+    `-- research_flow/
+        |-- pyproject.toml
+        `-- src/
+            `-- research_flow/
+                `-- main.py
+```
+
+Para implantar `support_agent`, defina o diretório de trabalho como:
+
+```text
+crews/support_agent
+```
+
+O AMP ainda baixa ou recebe o repositório inteiro, mas trata a pasta
+selecionada como a raiz do projeto da automação.
+
+## O Que o Diretório de Trabalho Controla
+
+Quando um diretório de trabalho é definido, o AMP usa essa pasta para:
+
+- Validação do projeto, incluindo `pyproject.toml`, `src/` e o ponto de entrada do Crew ou Flow
+- Instalação de dependências com `uv`
+- O diretório de trabalho do processo em execução
+- A variável de ambiente `CREW_ROOT_DIR`
+
+Deixar o campo vazio mantém o comportamento existente e usa a raiz do
+repositório.
+
+## Fontes Suportadas
+
+Você pode definir um diretório de trabalho ao criar uma implantação a partir de:
+
+- Um repositório GitHub conectado
+- Um repositório Git configurado no AMP
+- Um upload de ZIP
+
+<Info>
+  Configure diretórios de trabalho na interface web do AMP. O fluxo
+  `crewai deploy create` da CLI não solicita esse campo.
+</Info>
+
+Você também pode adicionar ou alterar o diretório de trabalho de uma implantação
+existente pela página **Settings** da implantação. A alteração passa a valer no
+próximo deploy.
+
+<Warning>
+  Diretórios de trabalho e auto-deploy não podem ser usados juntos. Se uma
+  implantação tiver um diretório de trabalho, o auto-deploy fica desabilitado
+  para ela. Desative o auto-deploy antes de definir um diretório de trabalho.
+</Warning>
+
+## Configurar uma Nova Implantação
+
+<Steps>
+  <Step title="Abra Deploy from Code">
+    No CrewAI AMP, crie uma nova implantação e escolha sua fonte: GitHub, Git
+    Repository ou upload de ZIP.
+  </Step>
+
+  <Step title="Selecione o repositório, branch ou arquivo ZIP">
+    Escolha o repositório e a branch que contêm seu monorepo, ou envie um ZIP
+    cuja raiz contenha os arquivos do monorepo.
+  </Step>
+
+  <Step title="Abra as configurações avançadas">
+    Expanda a seção **Advanced** no formulário de deploy.
+  </Step>
+
+  <Step title="Informe o diretório de trabalho">
+    Informe o caminho da raiz do repositório até o projeto Crew ou Flow:
+
+    ```text
+    crews/support_agent
+    ```
+
+    Não inclua uma barra inicial.
+  </Step>
+
+  <Step title="Implante">
+    Adicione as variáveis de ambiente necessárias e inicie a implantação.
+  </Step>
+</Steps>
+
+## Configurar uma Implantação Existente
+
+<Steps>
+  <Step title="Abra as configurações da implantação">
+    Acesse sua automação no AMP e abra **Settings**.
+  </Step>
+
+  <Step title="Desative o auto-deploy, se necessário">
+    Se o auto-deploy estiver habilitado, desative-o primeiro. O campo de
+    diretório de trabalho fica indisponível enquanto o auto-deploy está ativo.
+  </Step>
+
+  <Step title="Defina o diretório de trabalho">
+    Em **Basic settings**, informe o caminho da subpasta, como:
+
+    ```text
+    crews/support_agent
+    ```
+  </Step>
+
+  <Step title="Reimplante">
+    Salve a configuração e reimplante a automação. O novo diretório de trabalho
+    será usado no próximo deploy.
+  </Step>
+</Steps>
+
+## Regras de Caminho
+
+O diretório de trabalho deve ser um caminho relativo dentro da raiz do
+repositório ou do ZIP.
+
+| Regra | Exemplo |
+|-------|---------|
+| Use um caminho relativo | `crews/support_agent` |
+| Não comece com `/` | `/crews/support_agent` é inválido |
+| Não use segmentos de caminho `.` ou `..` | `crews/../support_agent` é inválido |
+| Use apenas letras, números, hifens, underscores, pontos e barras | `crews/support agent` é inválido |
+| Mantenha o caminho com 255 caracteres ou menos | Caminhos maiores são rejeitados |
+
+O AMP remove espaços em branco no início e no fim, reduz barras repetidas e
+remove barras finais. Um valor em branco usa a raiz do repositório.
+
+## Arquivos Lock e Workspaces UV
+
+A pasta selecionada deve conter o `pyproject.toml` e o diretório `src/` da
+automação. Um arquivo `uv.lock` ou `poetry.lock` pode ficar na pasta selecionada
+ou na raiz do repositório.
+
+Isso oferece suporte aos dois layouts comuns de monorepo:
+
+<Tabs>
+  <Tab title="Arquivo lock do projeto">
+    ```text
+    company-ai/
+    `-- crews/
+        `-- support_agent/
+            |-- pyproject.toml
+            |-- uv.lock
+            `-- src/
+                `-- support_agent/
+                    `-- main.py
+    ```
+  </Tab>
+
+  <Tab title="Arquivo lock do workspace">
+    ```text
+    company-ai/
+    |-- uv.lock
+    |-- packages/
+    |   `-- shared_tools/
+    `-- crews/
+        `-- support_agent/
+            |-- pyproject.toml
+            `-- src/
+                `-- support_agent/
+                    `-- main.py
+    ```
+  </Tab>
+</Tabs>
+
+<Tip>
+  Se sua automação importar pacotes compartilhados de outro lugar do monorepo,
+  declare esses pacotes no `pyproject.toml` usando configuração de workspace,
+  caminho ou source do UV. O AMP executa a automação a partir da pasta
+  selecionada, então o código compartilhado deve ser instalado como dependência
+  em vez de depender da raiz do repositório no Python path.
+</Tip>
+
+## Solução de Problemas
+
+### Diretório de Trabalho Não Encontrado
+
+Verifique se o caminho é relativo à raiz do repositório ou do ZIP. Para uploads
+de ZIP, o conteúdo do ZIP deve incluir exatamente o caminho informado como
+diretório de trabalho.
+
+### pyproject.toml Ausente
+
+O diretório de trabalho deve apontar para a pasta do projeto Crew ou Flow, não
+apenas para uma pasta pai que contém vários projetos.
+
+### uv.lock ou poetry.lock Ausente
+
+Faça commit de um arquivo lock na pasta do projeto selecionada ou na raiz do
+repositório. Para workspaces UV, manter `uv.lock` na raiz do workspace é
+suportado.
+
+### Auto-Deploy Indisponível
+
+O auto-deploy fica desabilitado enquanto um diretório de trabalho está definido.
+Use reimplantações manuais ou acione reimplantações a partir de CI/CD com a API
+do AMP.
+
+<Card title="Deploy para AMP" icon="rocket" href="/pt-BR/enterprise/guides/deploy-to-amp">
+  Continue com o guia de implantação depois de escolher o diretório de trabalho
+  do monorepo.
+</Card>

docs/pt-BR/guides/flows/conversational-flows.mdx

@@ -0,0 +1,475 @@
+---
+title: Flows Conversacionais
+description: Crie apps de chat multi-turno com kickoff por turno, histórico de mensagens, roteamento de intenção, tracing e pontes WebSocket.
+icon: comments
+mode: "wide"
+---
+
+## Visão geral
+
+Apps conversacionais tratam cada linha do usuário como uma **nova execução do flow** com o **mesmo id de sessão**. A CrewAI oferece helpers para histórico de mensagens, classificação opcional de intenção, tracing adiado, pontes para UI e um REPL local `flow.chat()` para flows conversacionais.
+
+| Conceito | Implementação |
+|---------|----------------|
+| Id de sessão | `handle_turn(..., session_id=...)` → `kickoff(inputs={"id": ...})` → `state.id` |
+| Linha do usuário | `handle_turn(message)` acrescenta em `state.messages` antes do grafo rodar |
+| Fim do turno | `FlowFinished` só para **esta execução**; o chat segue no próximo `handle_turn` |
+| Trace da sessão | `ConversationConfig(defer_trace_finalization=True)` + `finalize_session_traces()` |
+
+## APIs de turno
+
+Use **`flow.handle_turn(message, session_id=...)`** para cada mensagem de usuário em REST, WebSocket, testes e UIs customizadas. Use **`flow.chat()`** quando quiser um loop de chat local no terminal para um `Flow` conversacional.
+
+`Flow.kickoff()` não aceita os argumentos nomeados `user_message=` ou `session_id=`. Para flows conversacionais, `handle_turn()` guarda a mensagem pendente e chama `kickoff(inputs={"id": session_id})` internamente.
+
+| API | Uso |
+|-----|-----|
+| `handle_turn(message, session_id=...)` | Wrapper ergonômico de um turno para `Flow` conversacional |
+| `chat()` | REPL local no terminal para `Flow` conversacional |
+| `kickoff(inputs={...})` | Execução avançada do flow sem tratamento de turno conversacional |
+| `ask()` | Prompt bloqueante **dentro** de um passo (wizard, esclarecimento) |
+| `@human_feedback` | Aprovar/rejeitar **saída de um passo** — não a próxima linha do chat |
+| `ChatSession.handle_turn(...)` | Camada de transporte sobre `handle_turn` (SSE / WebSocket) |
+
+## Início rápido
+
+```python
+from uuid import uuid4
+
+from crewai import Flow
+from crewai.flow import listen
+from crewai.experimental.conversational import (
+    ConversationConfig,
+    ConversationState,
+)
+
+
+@ConversationConfig(defer_trace_finalization=True)
+class SupportFlow(Flow[ConversationState]):
+    conversational = True
+
+    def route_turn(self, context):
+        message = (self.state.current_user_message or "").lower()
+        if "pedido" in message or "order" in message:
+            return "order"
+        if "tchau" in message or "goodbye" in message:
+            return "goodbye"
+        return "help"
+
+    @listen("order")
+    def handle_order(self):
+        reply = "Seu pedido está a caminho."
+        self.append_assistant_message(reply)
+        return reply
+
+    @listen("help")
+    def handle_help(self):
+        reply = "Como posso ajudar?"
+        self.append_assistant_message(reply)
+        return reply
+
+    @listen("goodbye")
+    def handle_goodbye(self):
+        reply = "Até logo!"
+        self.append_assistant_message(reply)
+        return reply
+
+
+session_id = str(uuid4())
+flow = SupportFlow()
+
+try:
+    flow.handle_turn("Onde está meu pedido?", session_id=session_id)
+    flow.handle_turn("E as devoluções?", session_id=session_id)
+finally:
+    flow.finalize_session_traces()  # um link de trace para o chat inteiro
+```
+
+## Ciclo de vida do turno
+
+Cada `handle_turn` executa este pipeline:
+
+1. **`_configure_conversational_kickoff`** — mescla `session_id` / `user_message` em `inputs`, aplica `ConversationalConfig`, habilita tracing adiado quando configurado.
+2. **Restauração de estado** — se `inputs["id"]` existe e `@persist` está configurado, carrega o snapshot mais recente.
+3. **`FlowStarted`** — emitido apenas no primeiro turno da sessão adiada.
+4. **`prepare_conversational_turn`** — acrescenta a mensagem do usuário em `state.messages`, define `last_user_message`, limpa `last_intent`, classifica opcionalmente quando `intents` / `default_intents` + `intent_llm` estão definidos.
+5. **Execução do grafo** — `@start` → `@router` → handlers `@listen`.
+6. **Fim da execução** — `flow_finished` por turno e finalização de trace são **ignorados** com adiamento; `Agent.kickoff()` / crews aninhados também não fecham o batch pai.
+
+Os handlers devem chamar **`append_assistant_message(reply)`** para que o próximo turno inclua a resposta do assistente. A linha do usuário já é salva por `handle_turn` — não acrescente de novo nos handlers.
+
+## `ConversationalConfig` (padrões em nível de classe)
+
+Defina na subclasse de `Flow` como `conversational_config: ClassVar[ConversationalConfig | None]`.
+
+| Campo | Padrão | Propósito |
+|-------|---------|-----------|
+| `default_intents` | `None` | Rótulos de outcome para classificação automática antes do kickoff |
+| `intent_llm` | `None` | Modelo para classificação (obrigatório quando há intents) |
+| `interactive_prompt` | `"You: "` | Prompt para `kickoff(interactive=True)` |
+| `interactive_timeout` | `None` | Timeout por linha no modo interativo |
+| `exit_commands` | `exit`, `quit` | Palavras que encerram o modo interativo |
+| `defer_trace_finalization` | `True` | Manter um batch de trace aberto entre turnos |
+
+Sobrescreva por kickoff com `intents=` e `intent_llm=`.
+
+## `ChatState` (formato persistido recomendado)
+
+```python
+from crewai.flow import ChatState
+
+
+class MyChatState(ChatState):
+    # Herdados: id, messages, last_user_message, last_intent, session_ready
+    research_turn_count: int = 0
+    custom_flag: bool = False
+```
+
+| Campo | Função |
+|-------|--------|
+| `id` | UUID da sessão (igual a `session_id` / `inputs["id"]`) |
+| `messages` | `list` de `{role, content}` para histórico de LLM |
+| `last_user_message` | Última linha do usuário neste turno |
+| `last_intent` | Rótulo de rota após classificação (se usado) |
+| `session_ready` | Flag de bootstrap único (permissões, caches, etc.) |
+
+`ConversationalInputs` é um `TypedDict` para `kickoff(inputs={...})`: `id`, `user_message`, `last_intent`.
+
+## API conversacional em `Flow`
+
+### Parâmetros de `kickoff` / `kickoff_async`
+
+| Parâmetro | Propósito |
+|-----------|-----------|
+| `user_message` | Texto deste turno (ou `{"role": "user", "content": "..."}`) |
+| `session_id` | UUID da conversa → `inputs["id"]` / `state.id` |
+| `intents` | Rótulos de outcome para `classify_intent` antes do kickoff |
+| `intent_llm` | LLM para classificação (obrigatório com `intents`) |
+| `interactive` | Loop CLI via `ask()` (só demos locais) |
+| `interactive_prompt` | Prompt no modo interativo |
+| `interactive_timeout` | Timeout de `ask()` por linha |
+| `exit_commands` | Palavras que encerram o modo interativo |
+| `inputs` | Campos extras de estado (mesclados com chaves conversacionais) |
+| `restore_from_state_id` | Hidratação fork de outro flow persistido |
+
+### Atributos de instância
+
+| Atributo | Propósito |
+|-----------|-----------|
+| `conversational_config` | Padrões `ConversationalConfig` em nível de classe |
+| `defer_trace_finalization` | Flag de instância; definida automaticamente a partir do config no kickoff |
+| `suppress_flow_events` | Oculta painéis Rich no console; **tracing ainda registra** eventos |
+| `stream` | Habilita streaming; use com `ChatSession.handle_turn(..., stream=True)` |
+
+### Métodos e propriedades
+
+| Nome | Descrição |
+|------|-------------|
+| `append_message(role, content, **extra)` | Acrescenta em `state.messages` (roles: `user`, `assistant`, `system`, `tool`) |
+| `conversation_messages` | Histórico somente leitura para chamadas LLM |
+| `classify_intent(text, outcomes, *, llm, context=None)` | Mapeia texto a um outcome (mesma lógica de `@human_feedback`) |
+| `receive_user_message(text, *, outcomes=None, llm=None)` | Acrescenta mensagem do usuário; opcionalmente define `last_intent` |
+| `finalize_session_traces()` | Emite `flow_finished` adiado e finaliza o batch de trace da sessão |
+| `_should_defer_trace_finalization()` | Se este flow adia finalização de trace por turno |
+| `input_history` | Trilha de auditoria de prompts e respostas de `ask()` |
+
+### Helpers do módulo (`crewai.flow.conversation`)
+
+Importáveis para testes ou orquestração customizada:
+
+| Função | Descrição |
+|----------|-------------|
+| `normalize_kickoff_inputs(inputs, user_message=..., session_id=...)` | Mescla kwargs conversacionais em `inputs` |
+| `get_conversation_messages(flow)` | Lê mensagens do estado ou buffer interno |
+| `append_message(flow, role, content, **extra)` | Igual ao método de instância |
+| `prepare_conversational_turn(flow, ...)` | Hidratação do turno (geralmente chamado pelo kickoff) |
+| `receive_user_message(flow, text, ...)` | Igual ao método de instância |
+| `set_state_field(flow, name, value)` | Define campo em estado dict ou Pydantic |
+| `get_conversational_config(flow)` | Lê `conversational_config` da classe |
+| `input_history_to_messages(entries)` | Converte `input_history` para formato de mensagens LLM |
+
+## Padrões de roteamento de intenção
+
+### A. Pré-classificar via `ConversationalConfig` (mais simples)
+
+Defina `default_intents` e `intent_llm`. Cada kickoff classifica antes do `@router`; leia `self.state.last_intent` em `route()`.
+
+### B. Classificar dentro do `@router` (prompts mais ricos)
+
+Defina `default_intents=None` para o kickoff só acrescentar a mensagem. Em `route()`, chame `classify_intent` com prompt ou descrições customizadas:
+
+```python
+@router(bootstrap)
+def route(self):
+    intent = self.classify_intent(
+        self._routing_prompt(self.state.last_user_message),
+        ("GREETING", "ORDER", "RESEARCH", "GOODBYE"),
+        llm=self.conversational_config.intent_llm or "gpt-4o-mini",
+    )
+    self.state.last_intent = intent
+    return intent
+```
+
+Use **`@listen("RESEARCH")`** (ou similar) para passos com `Agent.kickoff()` e ferramentas — não `LLM.call()` puro — quando precisar de pesquisa web ou uso multi-etapa de tools.
+
+## Quando o flow termina mas o usuário continua conversando
+
+`FlowFinished` significa que **esta execução do grafo** terminou. A conversa segue com outro `kickoff` e o mesmo `session_id`. `@persist` restaura `messages`, flags e contexto.
+
+**Padrão de persistência:** prefira `@persist` em um **único passo terminal** (por exemplo `finalize`) em vez de na classe `Flow` inteira. Persist em nível de classe salva após cada método; `load_state` usa a linha mais recente, que pode ser snapshot no meio da execução e perder atualizações dos handlers no mesmo turno.
+
+Não use `@human_feedback` para linhas de chat de follow-up, a menos que um humano precise aprovar uma saída específica antes de exibi-la.
+
+## `Flow` conversacional (experimental)
+
+<Warning>
+  **Funcionalidade experimental.** A superfície do `Flow` conversacional
+  (`conversational = True`, `handle_turn`, `ConversationConfig`,
+  `RouterConfig`, `ConversationState`, o grafo embutido + helpers) vive em
+  `crewai.experimental` e pode mudar de formato antes de graduar. Fixe a
+  versão do CrewAI se depende de comportamento específico e acompanhe o
+  changelog para mudanças quebradoras. Feedback / issues bem-vindos.
+</Warning>
+
+Habilite o grafo conversacional definindo `conversational = True` em uma subclasse de `Flow`. O `Flow` base passa a expor um grafo embutido `@start` / `@router` / `converse_turn` / `end_conversation`, gerencia `state.messages`, dirige o LLM de roteamento e mantém o batch de trace aberto entre os turnos. Você escreve as **rotas customizadas**; o framework cuida do resto.
+
+Use isto quando quiser um chat multi-turno com router LLM e handlers por rota sem cablar o ciclo de vida na mão. Use `Flow[ChatState]` (o padrão de mais baixo nível acima) quando precisar de controle total.
+
+### Exemplo rápido
+
+```python
+from crewai import LLM, Flow
+from crewai.flow import listen
+from crewai.experimental.conversational import (
+    ConversationConfig,
+    ConversationState,
+    RouterConfig,
+)
+
+
+ROUTER_LLM = LLM(model="gpt-4o-mini")
+
+
+@ConversationConfig(
+    system_prompt="A multi-agent assistant for ordinary chat and tool-backed tasks.",
+    llm=ROUTER_LLM,
+    router=RouterConfig(),  # rotas + descrições auto-descobertas pelos handlers @listen
+)
+class SupportFlow(Flow[ConversationState]):
+    conversational = True
+
+    @listen("INTERNET_SEARCH")
+    def handle_internet_search(self) -> str:
+        """Fresh web research, current news, real-time lookups."""
+        ...
+        self.append_assistant_message(reply)
+        return reply
+
+    @listen("CREWAI_DOCS")
+    def handle_crewai_docs(self) -> str:
+        """Look up the CrewAI documentation for framework/API questions."""
+        ...
+        self.append_assistant_message(reply)
+        return reply
+
+
+flow = SupportFlow()
+try:
+    flow.handle_turn("O que você pode fazer?")               # roteia para converse (built-in)
+    flow.handle_turn("Pesquise na web por notícias de IA.")  # roteia para INTERNET_SEARCH
+    flow.handle_turn("Resuma o primeiro resultado.")         # volta para converse
+finally:
+    flow.finalize_session_traces()
+```
+
+Para um chat local no terminal, use `chat()`:
+
+```python
+def kickoff() -> None:
+    SupportFlow().chat()
+```
+
+`chat()` envolve `handle_turn()` em um REPL, sai com `exit` / `quit`, ignora linhas em branco por padrão e chama `finalize_session_traces()` quando a sessão termina.
+
+### `ConversationConfig`
+
+Decorador de classe que anexa os defaults de chat por classe.
+
+| Campo | Padrão | Propósito |
+|-------|--------|-----------|
+| `system_prompt` | `slices.conversational_system_prompt` (i18n) | System message usado pelo `converse_turn` embutido. Passe `""` para desativar totalmente. |
+| `llm` | `None` | LLM de conversa (usado pelo `converse_turn` e como fallback do router). |
+| `router` | `None` | `RouterConfig` para roteamento por LLM. Sem ele, o flow sempre cai em `converse`. |
+| `answer_from_history_prompt` | padrão do framework | System message para a rota opcional `answer_from_history`. |
+| `answer_from_history_llm` | `None` | Habilita o atalho `answer_from_history` quando definido. |
+| `intent_llm` | `None` | LLM para o caminho legado `intents=`/`default_intents`. |
+| `default_intents` | `None` | Labels de outcome para pré-classificação legada. |
+| `visible_agent_outputs` | `None` | `"all"` ou lista de nomes de agentes cujos `append_agent_result()` devem virar mensagens públicas. |
+| `defer_trace_finalization` | `True` | Mantém um único batch de trace aberto entre chamadas de `handle_turn()`. |
+
+### `RouterConfig` e o catálogo de rotas auto-gerado
+
+```python
+RouterConfig(
+    prompt="Enquadramento de domínio opcional (política, voz, persona).",
+    response_format=MyRoute,        # opcional; auto-gerado caso contrário
+    llm=ROUTER_LLM,                  # usa ConversationConfig.llm como fallback
+    routes=["INTERNET_SEARCH", "CREWAI_DOCS"],   # opcional; inferido dos listeners
+    route_descriptions={
+        "INTERNET_SEARCH": "Sobrescreve a docstring só desta rota.",
+    },
+    default_intent="converse",       # usado quando a chamada ao LLM falha ou não há LLM
+    fallback_intent="converse",      # usado quando o LLM retorna rota inválida
+    intent_field="intent",
+)
+```
+
+O prompt do router é montado automaticamente. Para cada rota o framework escolhe a descrição nesta precedência:
+
+1. `RouterConfig.route_descriptions[label]` — override explícito.
+2. `Flow.builtin_route_descriptions[label]` — texto canônico do framework para `converse`, `end`, `answer_from_history` (otimizado para o LLM de routing).
+3. Primeira linha não vazia da docstring do handler `@listen(label)`.
+4. Vazio (a rota aparece no catálogo sem descrição).
+
+Na prática, **adicionar uma rota é `@listen("X")` + uma docstring de uma linha**:
+
+```python
+@listen("INTERNET_SEARCH")
+def handle_internet_search(self) -> str:
+    """Fresh web research, current news, real-time lookups."""
+    ...
+```
+
+…e o LLM de routing vê:
+
+```
+Routes:
+- CREWAI_DOCS: Look up the CrewAI documentation for framework/API questions.
+- INTERNET_SEARCH: Fresh web research, current news, real-time lookups.
+- converse: Ordinary chat, follow-ups, summaries, clarifications…
+- end: User signals the conversation is finished (goodbye, exit, done).
+```
+
+`RouterConfig.prompt` é para **enquadramento de domínio** (persona do assistente, regras de negócio, voz). O catálogo de rotas é auto-gerado — não liste rotas em `prompt`; elas vão sair de sincronia assim que você adicionar um handler.
+
+### Rotas embutidas
+
+| Rota | Handler | Propósito |
+|------|---------|-----------|
+| `converse` | `converse_turn` | Handler de chat padrão. Chama `ConversationConfig.llm` com o system prompt + histórico canônico. |
+| `end` | `end_conversation` | Define `state.ended = True` e emite uma resposta de encerramento. |
+| `answer_from_history` | `answer_from_history_turn` | Opcional. Cai aqui quando `ConversationConfig.answer_from_history_llm` está definido e a mensagem pode ser respondida só pelo histórico. |
+
+Você pode sobrescrever qualquer uma definindo um handler com o mesmo nome na subclasse.
+
+### Semântica de `handle_turn()`
+
+`flow.handle_turn(message)` roda um turno:
+
+1. Reseta o tracking por execução (`_completed_methods`, `_method_outputs`) para o grafo re-rodar — sem isso, chamadas repetidas de `kickoff` na mesma instância dariam curto-circuito no turno 2+ porque `Flow.kickoff_async` trata `inputs={"id": ...}` como restauração de checkpoint.
+2. Anexa a mensagem do usuário em `state.messages`, define `current_user_message` / `last_user_message`. `last_intent` é **preservado do turno anterior** para que o LLM de routing possa usá-lo como sinal.
+3. Roda `conversation_start` → `route_conversation` → o handler `@listen` escolhido.
+4. O router grava sua decisão em `state.last_intent` (visível para o contexto de routing do próximo turno).
+5. Se seu handler retornou uma string e ainda não chamou `append_assistant_message`, `handle_turn` anexa para você.
+
+Chame `handle_turn()` para mensagens de chat. Chamar `kickoff(inputs={"id": ...})` diretamente executa o grafo sem aplicar o wrapper de turno conversacional.
+
+### `chat()` para REPLs locais
+
+`flow.chat()` é o wrapper de terminal pronto para uso em cima de `handle_turn()`:
+
+```python
+flow = SupportFlow()
+flow.chat()
+```
+
+Ele cobre o loop local comum:
+
+1. Solicita uma mensagem do usuário.
+2. Para com `exit` / `quit`, `EOFError` ou `KeyboardInterrupt`.
+3. Chama `handle_turn(message, session_id=...)`.
+4. Imprime o resultado do assistente.
+5. Finaliza traces de sessão adiados em um bloco `finally`.
+
+Customize o comportamento do terminal com I/O injetável:
+
+```python
+flow.chat(
+    session_id="demo-session",
+    prompt="You: ",
+    assistant_prefix="Assistant: ",
+    exit_commands=("exit", "quit", "bye"),
+)
+```
+
+Para apps web, workers em background, testes e transportes customizados, continue usando `handle_turn()` diretamente.
+
+### Comportamento customizado do router
+
+Para rodar efeitos colaterais (setup de event bus, telemetria) em toda decisão de routing, sobrescreva `route_turn`:
+
+```python
+class SupportFlow(Flow[ConversationState]):
+    conversational = True
+
+    def route_turn(self, context: dict[str, Any]) -> str | None:
+        self.event_bus = MyBus(self)
+        return super().route_turn(context)
+```
+
+Para ignorar o router LLM e escolher uma rota programaticamente, retorne uma string de `route_turn`; retornar `None` cai no `_route_with_config(...)`.
+
+### `append_assistant_message` e `append_agent_result`
+
+Dentro de um handler `@listen(label)`, escolha:
+
+- `self.append_assistant_message(text)` — adiciona um turno de assistente visível ao usuário em `state.messages`. O `converse_turn` do próximo turno vai vê-lo.
+- `self.append_agent_result(agent_name, result, visibility="private")` — registra um evento estruturado em `state.events` e uma thread em `state.agent_threads[agent_name]`. Visibilidade pública também chama `append_assistant_message` automaticamente. Use resultados privados para trabalho de bastidor que não deve poluir o histórico canônico.
+
+`ConversationConfig.visible_agent_outputs` pode promover globalmente os resultados privados de agentes específicos para públicos (`"all"` ou lista de nomes).
+
+## Tracing entre turnos
+
+Com `defer_trace_finalization=True` (padrão em `ConversationalConfig`):
+
+- **Um batch de trace** para toda a sessão de chat.
+- **`flow_started`** só no primeiro turno; **`flow_finished`** uma vez em `finalize_session_traces()`.
+- **`kickoff` por turno** não exibe “Trace batch finalized”.
+- **Trabalho aninhado** (`Agent.kickoff()`, crews, tools Exa) acrescenta ao batch **pai**; flows internos de `AgentExecutor` não fecham o batch da sessão cedo.
+
+```python
+flow.chat(session_id=session_id)
+```
+
+`flow.chat()` chama `finalize_session_traces()` para você. Quando você controla o loop com `handle_turn()` ou `kickoff(...)`, chame `finalize_session_traces()` quando a sessão terminar.
+
+`suppress_flow_events=True` só oculta painéis do console; eventos de trace e método ainda são emitidos.
+
+### Ciclo de vida de trace do `Flow` conversacional
+
+O [`Flow` conversacional](#flow-conversacional-experimental) experimental usa o mesmo ciclo de vida de tracing: `defer_trace_finalization` é `True` por padrão, então cada `handle_turn()` mantém o trace da sessão aberto. Sempre finalize ao fim da sessão — envolva seu loop em `try/finally` e chame `flow.finalize_session_traces()` na saída. Sem isso, o batch fica aberto e a última conversa pode nunca ser exportada.
+
+## Streaming
+
+Defina `stream = True` na classe `Flow`. `kickoff(...)` então emitirá `assistant_delta` (e eventos relacionados) pelo event bus padrão.
+
+## Imports
+
+```python
+from crewai.flow import (
+    ChatState,
+    ConversationalConfig,
+    ConversationalInputs,
+    Flow,
+    listen,
+    persist,
+    router,
+    start,
+)
+```
+
+## Veja também
+
+- [Dominando o Gerenciamento de Estado em Flows](/pt-BR/guides/flows/mastering-flow-state) — persistência, estado Pydantic, `@persist`
+- [Construa Seu Primeiro Flow](/pt-BR/guides/flows/first-flow) — fundamentos de flow
+- Demo: `lib/crewai/runner_conversational_flow_simple.py` — REPL mínimo com `RESEARCH` + agente Exa

docs/pt-BR/guides/flows/first-flow.mdx

@@ -614,6 +614,7 @@ Agora que você construiu seu primeiro flow, pode:
 3. Explorar as funções `and_` e `or_` para execuções paralelas e mais complexas
 4. Conectar seu flow a APIs externas, bancos de dados ou interfaces de usuário
 5. Combinar múltiplos crews especializados em um único flow
+6. Criar apps de chat multi-turn com [Flows conversacionais](/pt-BR/guides/flows/conversational-flows) (`kickoff` por mensagem, `ChatSession`, tracing adiado)
 
 <Check>
 Parabéns! Você construiu seu primeiro CrewAI Flow que combina código regular, chamadas diretas a LLM e processamento baseado em crews para criar um guia abrangente. Essas habilidades fundamentais permitem criar aplicações de IA cada vez mais sofisticadas, capazes de resolver problemas complexos de múltiplas etapas por meio de controle procedural e inteligência colaborativa.

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

@@ -22,6 +22,8 @@ Um gerenciamento de estado efetivo possibilita que você:
 5. **Escalone suas aplicações** – Ofereça suporte a workflows complexos com organização apropriada dos dados
 6. **Habilite aplicações conversacionais** – Armazene e acesse o histórico da conversa para interações de IA com contexto
 
+Para chat multi-turn (`kickoff` por linha do usuário, `ChatState`, roteamento por intenção, tracing adiado e `ChatSession`), veja [Flows conversacionais](/pt-BR/guides/flows/conversational-flows).
+
 Vamos explorar como aproveitar essas capacidades de forma eficiente.
 
 ## Fundamentos do Gerenciamento de Estado

lib/cli/pyproject.toml

@@ -8,7 +8,7 @@ authors = [
 ]
 requires-python = ">=3.10, <3.14"
 dependencies = [
-    "crewai-core==1.14.7a1",
+    "crewai-core==1.14.7a3",
     "click>=8.1.7,<9",
     "pydantic>=2.11.9,<2.13",
     "pydantic-settings~=2.10.1",

lib/cli/src/crewai_cli/__init__.py

@@ -1 +1 @@
-__version__ = "1.14.7a1"
+__version__ = "1.14.7a3"

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

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]==1.14.7a1"
+    "crewai[tools]==1.14.7a3"
 ]
 
 [project.scripts]

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

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]==1.14.7a1"
+    "crewai[tools]==1.14.7a3"
 ]
 
 [project.scripts]

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

@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]==1.14.7a1"
+    "crewai[tools]==1.14.7a3"
 ]
 
 [tool.crewai]

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

@@ -1 +1 @@
-__version__ = "1.14.7a1"
+__version__ = "1.14.7a3"

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

@@ -1,14 +1,18 @@
 """Centralised lock factory.
 
-If ``REDIS_URL`` is set and the ``redis`` package is installed, locks are
-distributed via ``portalocker.RedisLock``. Otherwise, falls back to the
-standard file-based ``portalocker.Lock`` in the system temp dir.
+By default, if ``REDIS_URL`` is set and the ``redis`` package is installed,
+locks are distributed via ``portalocker.RedisLock``. Otherwise, falls back to
+the standard file-based ``portalocker.Lock`` in the system temp dir.
+
+The backend can be replaced via :func:`set_lock_backend` to plug in a custom
+locking strategy (e.g. a different distributed lock service, or an in-process
+lock for tests).
 """
 
 from __future__ import annotations
 
-from collections.abc import Iterator
-from contextlib import contextmanager
+from collections.abc import Callable, Iterator
+from contextlib import AbstractContextManager, contextmanager
 from functools import lru_cache
 from hashlib import md5
 import logging
@@ -30,6 +34,25 @@ _REDIS_URL: str | None = os.environ.get("REDIS_URL")
 
 _DEFAULT_TIMEOUT: Final[int] = 120
 
+# A backend is called as ``backend(name, timeout=...)`` and returns a context
+# manager that holds the lock while the ``with`` block runs.
+LockBackend = Callable[..., AbstractContextManager[None]]
+
+# ``None`` means use the built-in Redis/file selection.
+_backend: LockBackend | None = None
+
+
+def set_lock_backend(backend: LockBackend | None) -> None:
+    """Replace the process-wide locking backend used by :func:`lock`.
+
+    Intended for one-time setup at startup. Pass ``None`` to restore the
+    built-in Redis/file default. In-flight :func:`lock` calls keep the backend
+    they started with, but swapping backends while other threads acquire locks
+    is otherwise unsynchronised.
+    """
+    global _backend
+    _backend = backend
+
 
 def _redis_available() -> bool:
     """Return True if redis is installed and REDIS_URL is set."""
@@ -58,10 +81,19 @@ def lock(name: str, *, timeout: float = _DEFAULT_TIMEOUT) -> Iterator[None]:
     """Acquire a named lock, yielding while it is held.
 
     Args:
-        name: A human-readable lock name (e.g. ``"chromadb_init"``).
-              Automatically namespaced to avoid collisions.
+        name: A human-readable lock name (e.g. ``"chromadb_init"``). The
+              built-in default namespaces it to avoid collisions; a custom
+              backend receives it verbatim.
         timeout: Maximum seconds to wait for the lock before raising.
     """
+    # Snapshot the global once: a concurrent set_lock_backend() must not turn
+    # the check-then-call into calling ``None``.
+    backend = _backend
+    if backend is not None:
+        with backend(name, timeout=timeout):
+            yield
+        return
+
     channel = f"crewai:{md5(name.encode(), usedforsecurity=False).hexdigest()}"
 
     if _redis_available():

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

@@ -152,4 +152,4 @@ __all__ = [
     "wrap_file_source",
 ]
 
-__version__ = "1.14.7a1"
+__version__ = "1.14.7a3"

lib/crewai-tools/pyproject.toml

@@ -10,7 +10,7 @@ requires-python = ">=3.10, <3.14"
 dependencies = [
     "pytube~=15.0.0",
     "requests>=2.33.0,<3",
-    "crewai==1.14.7a1",
+    "crewai==1.14.7a3",
     "tiktoken>=0.8.0,<0.13",
     "beautifulsoup4~=4.13.4",
     "python-docx~=1.2.0",

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

@@ -330,4 +330,4 @@ __all__ = [
     "ZapierActionTools",
 ]
 
-__version__ = "1.14.7a1"
+__version__ = "1.14.7a3"

lib/crewai/pyproject.toml

@@ -8,8 +8,8 @@ authors = [
 ]
 requires-python = ">=3.10, <3.14"
 dependencies = [
-    "crewai-core==1.14.7a1",
-    "crewai-cli==1.14.7a1",
+    "crewai-core==1.14.7a3",
+    "crewai-cli==1.14.7a3",
     # Core Dependencies
     "pydantic>=2.11.9,<2.13",
     "openai>=2.30.0,<3",
@@ -37,7 +37,7 @@ dependencies = [
     "tomli~=2.0.2",
     "json5~=0.10.0",
     "portalocker~=2.7.0",
-    "pydantic-settings~=2.10.1",
+    "pydantic-settings>=2.10.1,<3",
     "httpx~=0.28.1",
     "mcp~=1.26.0",
     "aiosqlite~=0.21.0",
@@ -54,7 +54,7 @@ Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
 tools = [
-    "crewai-tools==1.14.7a1",
+    "crewai-tools==1.14.7a3",
 ]
 embeddings = [
     "tiktoken>=0.8.0,<0.13"
@@ -67,7 +67,11 @@ openpyxl = [
 ]
 mem0 = ["mem0ai>=2.0.0,<3"]
 docling = [
-    "docling~=2.84.0",
+    "docling~=2.97.0",
+    # docling 2.97 split into docling-slim; the chunker package (HierarchicalChunker)
+    # now eagerly imports code-chunking submodules that need tree-sitter/semchunk,
+    # which only the docling-core[chunking] extra provides.
+    "docling-core[chunking]>=2.74.1",
 ]
 qdrant = [
     "qdrant-client[fastembed]~=1.14.3",

lib/crewai/src/crewai/__init__.py

@@ -48,7 +48,7 @@ def _suppress_pydantic_deprecation_warnings() -> None:
 
 _suppress_pydantic_deprecation_warnings()
 
-__version__ = "1.14.7a1"
+__version__ = "1.14.7a3"
 
 _LAZY_IMPORTS: dict[str, tuple[str, str]] = {
     "Memory": ("crewai.memory.unified_memory", "Memory"),

lib/crewai/src/crewai/crew.py

@@ -7,7 +7,6 @@ from copy import copy as shallow_copy
 from hashlib import md5
 import json
 from pathlib import Path
-import re
 from typing import (
     TYPE_CHECKING,
     Annotated,
@@ -142,7 +141,10 @@ from crewai.utilities.streaming import (
     signal_end,
     signal_error,
 )
-from crewai.utilities.string_utils import sanitize_tool_name
+from crewai.utilities.string_utils import (
+    extract_template_variables,
+    sanitize_tool_name,
+)
 from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
 from crewai.utilities.training_handler import CrewTrainingHandler
 
@@ -1960,20 +1962,24 @@ class Crew(FlowTrackable, BaseModel):
         Scans each task's 'description' + 'expected_output', and each agent's
         'role', 'goal', and 'backstory'.
 
+        Only placeholders that interpolation can actually fill are returned;
+        non-identifier expressions such as ``{x if x else "y"}`` are ignored so
+        they are not surfaced as required inputs (matching interpolation
+        behavior, see :func:`extract_template_variables`).
+
         Returns a set of all discovered placeholder names.
         """
-        placeholder_pattern = re.compile(r"\{(.+?)}")
         required_inputs: set[str] = set()
 
         for task in self.tasks:
             # description and expected_output might contain e.g. {topic}, {user_name}
             text = f"{task.description or ''} {task.expected_output or ''}"
-            required_inputs.update(placeholder_pattern.findall(text))
+            required_inputs.update(extract_template_variables(text))
 
         for agent in self.agents:
             # role, goal, backstory might have placeholders like {role_detail}, etc.
             text = f"{agent.role or ''} {agent.goal or ''} {agent.backstory or ''}"
-            required_inputs.update(placeholder_pattern.findall(text))
+            required_inputs.update(extract_template_variables(text))
 
         return required_inputs
 

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

@@ -61,6 +61,8 @@ if TYPE_CHECKING:
         CrewTrainStartedEvent,
     )
     from crewai.events.types.flow_events import (
+        ConversationMessageAddedEvent,
+        ConversationRouteSelectedEvent,
         FlowCreatedEvent,
         FlowEvent,
         FlowFinishedEvent,
@@ -176,6 +178,8 @@ _LAZY_EVENT_MAPPING: dict[str, str] = {
     "CrewTrainCompletedEvent": "crewai.events.types.crew_events",
     "CrewTrainFailedEvent": "crewai.events.types.crew_events",
     "CrewTrainStartedEvent": "crewai.events.types.crew_events",
+    "ConversationMessageAddedEvent": "crewai.events.types.flow_events",
+    "ConversationRouteSelectedEvent": "crewai.events.types.flow_events",
     "FlowCreatedEvent": "crewai.events.types.flow_events",
     "FlowEvent": "crewai.events.types.flow_events",
     "FlowFinishedEvent": "crewai.events.types.flow_events",
@@ -291,6 +295,8 @@ __all__ = [
     "CheckpointRestoreStartedEvent",
     "CheckpointStartedEvent",
     "CircularDependencyError",
+    "ConversationMessageAddedEvent",
+    "ConversationRouteSelectedEvent",
     "CrewKickoffCompletedEvent",
     "CrewKickoffFailedEvent",
     "CrewKickoffStartedEvent",

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

@@ -306,20 +306,24 @@ class EventListener(BaseEventListener):
             self._telemetry.flow_execution_span(
                 event.flow_name, list(source._methods.keys())
             )
-            self.formatter.handle_flow_created(event.flow_name, str(source.flow_id))
-            self.formatter.handle_flow_started(event.flow_name, str(source.flow_id))
+            if not getattr(source, "suppress_flow_events", False):
+                self.formatter.handle_flow_created(event.flow_name, str(source.flow_id))
+                self.formatter.handle_flow_started(event.flow_name, str(source.flow_id))
 
         @crewai_event_bus.on(FlowFinishedEvent)
         def on_flow_finished(source: Any, event: FlowFinishedEvent) -> None:
-            self.formatter.handle_flow_status(
-                event.flow_name,
-                source.flow_id,
-            )
+            if not getattr(source, "suppress_flow_events", False):
+                self.formatter.handle_flow_status(
+                    event.flow_name,
+                    source.flow_id,
+                )
 
         @crewai_event_bus.on(MethodExecutionStartedEvent)
         def on_method_execution_started(
-            _: Any, event: MethodExecutionStartedEvent
+            source: Any, event: MethodExecutionStartedEvent
         ) -> None:
+            if getattr(source, "suppress_flow_events", False):
+                return
             self.formatter.handle_method_status(
                 event.method_name,
                 "running",
@@ -327,8 +331,10 @@ class EventListener(BaseEventListener):
 
         @crewai_event_bus.on(MethodExecutionFinishedEvent)
         def on_method_execution_finished(
-            _: Any, event: MethodExecutionFinishedEvent
+            source: Any, event: MethodExecutionFinishedEvent
         ) -> None:
+            if getattr(source, "suppress_flow_events", False):
+                return
             self.formatter.handle_method_status(
                 event.method_name,
                 "completed",

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

@@ -53,6 +53,8 @@ from crewai.events.types.crew_events import (
     CrewTrainStartedEvent,
 )
 from crewai.events.types.flow_events import (
+    ConversationMessageAddedEvent,
+    ConversationRouteSelectedEvent,
     FlowFinishedEvent,
     FlowStartedEvent,
     MethodExecutionFailedEvent,
@@ -154,6 +156,8 @@ EventTypes = (
     | TaskStartedEvent
     | TaskCompletedEvent
     | TaskFailedEvent
+    | ConversationMessageAddedEvent
+    | ConversationRouteSelectedEvent
     | FlowStartedEvent
     | FlowFinishedEvent
     | MethodExecutionStartedEvent

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

@@ -222,6 +222,8 @@ To enable tracing later, do any one of these:
             return
         self.batch_manager.batch_owner_type = None
         self.batch_manager.batch_owner_id = None
+        self.batch_manager.defer_session_finalization = False
+        self.batch_manager._batch_finalized = False
         self.batch_manager.current_batch = None
         self.batch_manager.event_buffer.clear()
         self.batch_manager.trace_batch_id = None

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

@@ -62,6 +62,7 @@ class TraceBatchManager:
         self._pending_events_lock = Lock()
         self._pending_events_cv = Condition(self._pending_events_lock)
         self._pending_events_count = 0
+        self._finalize_lock = Lock()
 
         self.is_current_batch_ephemeral = False
         self.trace_batch_id: str | None = None
@@ -70,6 +71,8 @@ class TraceBatchManager:
         self.execution_start_times: dict[str, datetime] = {}
         self.batch_owner_type: str | None = None
         self.batch_owner_id: str | None = None
+        self.defer_session_finalization: bool = False
+        self._batch_finalized: bool = False
         self.backend_initialized: bool = False
         self.ephemeral_trace_url: str | None = None
         try:
@@ -101,6 +104,7 @@ class TraceBatchManager:
                 user_context=user_context, execution_metadata=execution_metadata
             )
             self.is_current_batch_ephemeral = use_ephemeral
+            self._batch_finalized = False
 
             self.record_start_time("execution")
 
@@ -312,6 +316,9 @@ class TraceBatchManager:
     def finalize_batch(self) -> TraceBatch | None:
         """Finalize batch and return it for sending"""
 
+        if self._batch_finalized:
+            return None
+
         if not self.current_batch or not is_tracing_enabled_in_context():
             return None
 
@@ -340,16 +347,15 @@ class TraceBatchManager:
         self.current_batch.events = sorted_events
         events_sent_count = len(sorted_events)
         if sorted_events:
-            original_buffer = self.event_buffer
             self.event_buffer = sorted_events
             events_sent_to_backend_status = self._send_events_to_backend()
-            self.event_buffer = original_buffer
             if events_sent_to_backend_status == 500 and self.trace_batch_id:
                 self._mark_batch_as_failed(
                     self.trace_batch_id, "Error sending events to backend"
                 )
                 return None
-        self._finalize_backend_batch(events_sent_count)
+        if not self._finalize_backend_batch(events_sent_count):
+            return None
 
         finalized_batch = self.current_batch
 
@@ -360,80 +366,87 @@ class TraceBatchManager:
         self.event_buffer.clear()
         self.trace_batch_id = None
         self.is_current_batch_ephemeral = False
+        self._batch_finalized = True
 
         self._cleanup_batch_data()
 
         return finalized_batch
 
-    def _finalize_backend_batch(self, events_count: int = 0) -> None:
+    def _finalize_backend_batch(self, events_count: int = 0) -> bool:
         """Send batch finalization to backend
 
         Args:
             events_count: Number of events that were successfully sent
         """
-        if not self.plus_api or not self.trace_batch_id:
-            return
+        with self._finalize_lock:
+            batch_id = self.trace_batch_id
+            is_ephemeral = self.is_current_batch_ephemeral
+            if self._batch_finalized or not self.plus_api or not batch_id:
+                return True
 
-        try:
-            payload: TraceFinalizePayload = {
-                "status": "completed",
-                "duration_ms": self.calculate_duration("execution"),
-                "final_event_count": events_count,
-            }
+            try:
+                payload: TraceFinalizePayload = {
+                    "status": "completed",
+                    "duration_ms": self.calculate_duration("execution"),
+                    "final_event_count": events_count,
+                }
 
-            response = (
-                self.plus_api.finalize_ephemeral_trace_batch(
-                    self.trace_batch_id, payload
-                )
-                if self.is_current_batch_ephemeral
-                else self.plus_api.finalize_trace_batch(self.trace_batch_id, payload)
-            )
-
-            if response.status_code == 200:
-                access_code = response.json().get("access_code", None)
-                console = Console()
-                settings = Settings()
-                base_url = settings.enterprise_base_url or DEFAULT_CREWAI_ENTERPRISE_URL
-                return_link = (
-                    f"{base_url}/crewai_plus/trace_batches/{self.trace_batch_id}"
-                    if not self.is_current_batch_ephemeral and access_code is None
-                    else f"{base_url}/crewai_plus/ephemeral_trace_batches/{self.trace_batch_id}?access_code={access_code}"
+                response = (
+                    self.plus_api.finalize_ephemeral_trace_batch(batch_id, payload)
+                    if is_ephemeral
+                    else self.plus_api.finalize_trace_batch(batch_id, payload)
                 )
 
-                if self.is_current_batch_ephemeral:
-                    self.ephemeral_trace_url = return_link
+                if response.status_code == 200:
+                    self._batch_finalized = True
+                    access_code = response.json().get("access_code", None)
+                    console = Console()
+                    settings = Settings()
+                    base_url = (
+                        settings.enterprise_base_url or DEFAULT_CREWAI_ENTERPRISE_URL
+                    )
+                    return_link = (
+                        f"{base_url}/crewai_plus/trace_batches/{batch_id}"
+                        if not is_ephemeral and access_code is None
+                        else f"{base_url}/crewai_plus/ephemeral_trace_batches/{batch_id}?access_code={access_code}"
+                    )
 
-                message_parts = [
-                    f"✅ Trace batch finalized with session ID: {self.trace_batch_id}",
-                    "",
-                    f"🔗 View here: {return_link}",
-                ]
+                    if is_ephemeral:
+                        self.ephemeral_trace_url = return_link
 
-                if access_code:
-                    message_parts.append(f"🔑 Access Code: {access_code}")
+                    message_parts = [
+                        f"✅ Trace batch finalized with session ID: {batch_id}",
+                        "",
+                        f"🔗 View here: {return_link}",
+                    ]
 
-                panel = Panel(
-                    "\n".join(message_parts),
-                    title="Trace Batch Finalization",
-                    border_style="green",
-                )
-                if not should_auto_collect_first_time_traces():
-                    console.print(panel)
+                    if access_code:
+                        message_parts.append(f"🔑 Access Code: {access_code}")
+
+                    panel = Panel(
+                        "\n".join(message_parts),
+                        title="Trace Batch Finalization",
+                        border_style="green",
+                    )
+                    if not should_auto_collect_first_time_traces():
+                        console.print(panel)
+                    return True
 
-            else:
                 logger.error(
                     f"❌ Failed to finalize trace batch: {response.status_code} - {response.text}"
                 )
-                self._mark_batch_as_failed(self.trace_batch_id, response.text)
+                self._mark_batch_as_failed(batch_id, response.text)
+                return False
 
-        except Exception as e:
-            logger.error(f"❌ Error finalizing trace batch: {e}")
-            try:
-                self._mark_batch_as_failed(self.trace_batch_id, str(e))
-            except Exception:
-                logger.debug(
-                    "Could not mark trace batch as failed (network unavailable)"
-                )
+            except Exception as e:
+                logger.error(f"❌ Error finalizing trace batch: {e}")
+                try:
+                    self._mark_batch_as_failed(batch_id, str(e))
+                except Exception:
+                    logger.debug(
+                        "Could not mark trace batch as failed (network unavailable)"
+                    )
+                return False
 
     def _cleanup_batch_data(self) -> None:
         """Clean up batch data after successful finalization to free memory"""

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

@@ -1,5 +1,6 @@
 """Trace collection listener for orchestrating trace collection."""
 
+from datetime import datetime, timezone
 import os
 from typing import Any, ClassVar
 import uuid
@@ -61,6 +62,8 @@ from crewai.events.types.crew_events import (
     CrewKickoffStartedEvent,
 )
 from crewai.events.types.flow_events import (
+    ConversationMessageAddedEvent,
+    ConversationRouteSelectedEvent,
     FlowCreatedEvent,
     FlowFinishedEvent,
     FlowPlotEvent,
@@ -230,11 +233,14 @@ class TraceCollectionListener(BaseEventListener):
 
         @event_bus.on(FlowStartedEvent)
         def on_flow_started(source: Any, event: FlowStartedEvent) -> None:
-            # Always call _initialize_flow_batch to claim ownership.
-            # If batch was already initialized by a concurrent action event
-            # (race condition), initialize_batch() returns early but
-            # batch_owner_type is still correctly set to "flow".
-            self._initialize_flow_batch(source, event)
+            # Only the first execution to open the session batch owns it. A flow
+            # that starts while a batch already exists is nested -- inside a crew
+            # (e.g. an agent's Flow-based executor), a conversational Flow, or a
+            # parent flow -- and must NOT re-claim ownership. Re-claiming would
+            # mark batch_owner_type="flow" and cause the nested flow to finalize
+            # the parent's batch prematurely when it completes.
+            if not self.batch_manager.is_batch_initialized():
+                self._initialize_flow_batch(source, event)
             self._handle_trace_event("flow_started", source, event)
 
         @event_bus.on(MethodExecutionStartedEvent)
@@ -251,6 +257,18 @@ class TraceCollectionListener(BaseEventListener):
         def on_method_failed(source: Any, event: MethodExecutionFailedEvent) -> None:
             self._handle_trace_event("method_execution_failed", source, event)
 
+        @event_bus.on(ConversationMessageAddedEvent)
+        def on_conversation_message_added(
+            source: Any, event: ConversationMessageAddedEvent
+        ) -> None:
+            self._handle_action_event("conversation_message_added", source, event)
+
+        @event_bus.on(ConversationRouteSelectedEvent)
+        def on_conversation_route_selected(
+            source: Any, event: ConversationRouteSelectedEvent
+        ) -> None:
+            self._handle_action_event("conversation_route_selected", source, event)
+
         @event_bus.on(FlowFinishedEvent)
         def on_flow_finished(source: Any, event: FlowFinishedEvent) -> None:
             self._handle_trace_event("flow_finished", source, event)
@@ -264,18 +282,20 @@ class TraceCollectionListener(BaseEventListener):
 
         @event_bus.on(CrewKickoffStartedEvent)
         def on_crew_started(source: Any, event: CrewKickoffStartedEvent) -> None:
-            if self.batch_manager.batch_owner_type != "flow":
-                # Always call _initialize_crew_batch to claim ownership.
-                # If batch was already initialized by a concurrent action event
-                # (e.g. LLM/tool before crew_kickoff_started), initialize_batch()
-                # returns early but batch_owner_type is still correctly set to "crew".
-                # Skip only when a parent flow already owns the batch.
+            # Nested crew inside Flow.kickoff: never claim an existing flow session batch.
+            if not self._nested_in_flow_execution() and (
+                not self.batch_manager.is_batch_initialized()
+            ):
                 self._initialize_crew_batch(source, event)
             self._handle_trace_event("crew_kickoff_started", source, event)
 
         @event_bus.on(CrewKickoffCompletedEvent)
         def on_crew_completed(source: Any, event: CrewKickoffCompletedEvent) -> None:
             self._handle_trace_event("crew_kickoff_completed", source, event)
+            if self.batch_manager.defer_session_finalization:
+                return
+            if self._nested_in_flow_execution():
+                return
             if self.batch_manager.batch_owner_type == "crew":
                 if self.first_time_handler.is_first_time:
                     self.first_time_handler.mark_events_collected()
@@ -286,10 +306,14 @@ class TraceCollectionListener(BaseEventListener):
         @event_bus.on(CrewKickoffFailedEvent)
         def on_crew_failed(source: Any, event: CrewKickoffFailedEvent) -> None:
             self._handle_trace_event("crew_kickoff_failed", source, event)
+            if self.batch_manager.defer_session_finalization:
+                return
+            if self._nested_in_flow_execution():
+                return
             if self.first_time_handler.is_first_time:
                 self.first_time_handler.mark_events_collected()
                 self.first_time_handler.handle_execution_completion()
-            else:
+            elif self.batch_manager.batch_owner_type == "crew":
                 self.batch_manager.finalize_batch()
 
         @event_bus.on(TaskStartedEvent)
@@ -707,8 +731,32 @@ class TraceCollectionListener(BaseEventListener):
         @on_signal
         def handle_signal(source: Any, event: SignalEvent) -> None:
             """Flush trace batch on system signals to prevent data loss."""
-            if self.batch_manager.is_batch_initialized():
-                self.batch_manager.finalize_batch()
+            if not self.batch_manager.is_batch_initialized():
+                return
+            # Multi-turn flows defer batch finalization to finalize_session_traces().
+            if self.batch_manager.defer_session_finalization:
+                return
+            self.batch_manager.finalize_batch()
+
+    @staticmethod
+    def _is_inside_active_flow_context() -> bool:
+        """True when ``kickoff_async`` has set ``current_flow_id`` (nested crew)."""
+        from crewai.flow.flow_context import current_flow_id
+
+        return current_flow_id.get() is not None
+
+    def _flow_owns_trace_batch(self) -> bool:
+        """True when an in-flight conversational flow already owns the trace batch."""
+        if self.batch_manager.batch_owner_type == "flow":
+            return True
+        batch = self.batch_manager.current_batch
+        if batch is not None:
+            return batch.execution_metadata.get("execution_type") == "flow"
+        return False
+
+    def _nested_in_flow_execution(self) -> bool:
+        """True when a crew runs inside a flow session (context or batch ownership)."""
+        return self._is_inside_active_flow_context() or self._flow_owns_trace_batch()
 
     def _initialize_crew_batch(self, source: Any, event: BaseEvent) -> None:
         """Initialize trace batch.
@@ -729,6 +777,33 @@ class TraceCollectionListener(BaseEventListener):
 
         self._initialize_batch(user_context, execution_metadata)
 
+    def _try_initialize_flow_batch_from_context(self, event: Any) -> bool:
+        """Claim a flow trace batch when an action event fires inside kickoff.
+
+        When ``suppress_flow_events=True``, console panels are hidden but
+        ``FlowStartedEvent`` and method lifecycle events still emit; if no
+        batch exists yet, LLM/tool events must not fall back to implicit crew
+        batches.
+        """
+        from crewai.flow.flow_context import current_flow_id, current_flow_name
+
+        flow_id = current_flow_id.get()
+        if flow_id is None:
+            return False
+
+        started_at = getattr(event, "timestamp", None) or datetime.now(timezone.utc)
+        user_context = self._get_user_context()
+        execution_metadata = {
+            "flow_name": current_flow_name.get() or "Unknown Flow",
+            "execution_start": started_at,
+            "crewai_version": get_crewai_version(),
+            "execution_type": "flow",
+        }
+        self.batch_manager.batch_owner_type = "flow"
+        self.batch_manager.batch_owner_id = flow_id
+        self._initialize_batch(user_context, execution_metadata)
+        return True
+
     def _initialize_flow_batch(self, source: Any, event: BaseEvent) -> None:
         """Initialize trace batch for Flow execution.
 
@@ -793,12 +868,19 @@ class TraceCollectionListener(BaseEventListener):
             event: Event object.
         """
         if not self.batch_manager.is_batch_initialized():
-            user_context = self._get_user_context()
-            execution_metadata = {
-                "crew_name": getattr(source, "name", "Unknown Crew"),
-                "crewai_version": get_crewai_version(),
-            }
-            self._initialize_batch(user_context, execution_metadata)
+            if self._try_initialize_flow_batch_from_context(event):
+                pass
+            elif not self._nested_in_flow_execution():
+                user_context = self._get_user_context()
+                execution_metadata = {
+                    "crew_name": getattr(source, "name", "Unknown Crew"),
+                    "crewai_version": get_crewai_version(),
+                }
+                self.batch_manager.batch_owner_type = "crew"
+                self.batch_manager.batch_owner_id = getattr(
+                    source, "id", str(uuid.uuid4())
+                )
+                self._initialize_batch(user_context, execution_metadata)
 
         self.batch_manager.begin_event_processing()
         try:

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

@@ -166,6 +166,31 @@ class FlowInputReceivedEvent(FlowEvent):
     type: Literal["flow_input_received"] = "flow_input_received"
 
 
+class ConversationMessageAddedEvent(FlowEvent):
+    """Event emitted when a conversational Flow records a message.
+
+    This gives trace consumers a first-class transcript signal instead of
+    requiring them to inspect the full method state payload.
+    """
+
+    session_id: str
+    role: Literal["user", "assistant", "system", "tool"]
+    content: Any
+    message_index: int
+    type: Literal["conversation_message_added"] = "conversation_message_added"
+
+
+class ConversationRouteSelectedEvent(FlowEvent):
+    """Event emitted when a conversational Flow selects a route for a turn."""
+
+    session_id: str
+    route: str
+    user_message: str | None = None
+    message_index: int | None = None
+    previous_intent: str | None = None
+    type: Literal["conversation_route_selected"] = "conversation_route_selected"
+
+
 class HumanFeedbackRequestedEvent(FlowEvent):
     """Event emitted when human feedback is requested.
 

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

@@ -1,7 +1,7 @@
 from enum import Enum
 from typing import Any, Literal
 
-from pydantic import BaseModel
+from pydantic import BaseModel, field_validator
 
 from crewai.events.base_events import BaseEvent
 
@@ -48,6 +48,43 @@ class LLMCallStartedEvent(LLMEventBase):
     tools: list[dict[str, Any]] | None = None
     callbacks: list[Any] | None = None
     available_functions: dict[str, Any] | None = None
+    # Sampling/request parameters forwarded for OTel GenAI compliance.
+    # All optional so legacy emitters keep working unchanged.
+    temperature: float | None = None
+    top_p: float | None = None
+    max_tokens: int | float | None = None
+    stream: bool | None = None
+    seed: int | None = None
+    stop_sequences: list[str] | None = None
+    frequency_penalty: float | None = None
+    presence_penalty: float | None = None
+    n: int | None = None
+
+    @field_validator("stop_sequences", mode="before")
+    @classmethod
+    def _coerce_stop_sequences_to_str_list(cls, value: Any) -> list[str] | None:
+        """Normalize stop_sequences to ``list[str] | None``.
+
+        Some providers store stop sequences in non-Python-list containers —
+        e.g. a Vertex AI / Gemini code path can hand back a
+        ``google.protobuf.struct_pb2.ListValue`` or a ``RepeatedScalarContainer``.
+        Without coercion the OTel SDK falls back to ``str(value)`` when
+        ``gen_ai.request.stop_sequences`` is set, producing the protobuf
+        textproto repr (``values { string_value: \"...\" }``) instead of a
+        proper ``Sequence[str]``.
+
+        A bare string is treated as a single stop sequence. Anything that
+        can't be iterated cleanly falls back to ``None`` rather than crashing
+        event construction.
+        """
+        if value is None:
+            return None
+        if isinstance(value, str):
+            return [value]
+        try:
+            return [item if isinstance(item, str) else str(item) for item in value]
+        except TypeError:
+            return None
 
 
 class LLMCallCompletedEvent(LLMEventBase):
@@ -58,6 +95,23 @@ class LLMCallCompletedEvent(LLMEventBase):
     response: Any
     call_type: LLMCallType
     usage: dict[str, Any] | None = None
+    finish_reason: str | None = None
+    response_id: str | None = None
+
+    @field_validator("finish_reason", "response_id", mode="before")
+    @classmethod
+    def _coerce_non_string_to_none(cls, value: Any) -> str | None:
+        """Drop non-string values so test mocks and exotic provider types
+        (MagicMock, protobuf enums, etc.) never crash event construction.
+
+        Provider helpers are best-effort: when extraction returns something
+        non-string (e.g. a ``MagicMock`` in unit tests), we treat it as
+        "no value" rather than raising. Downstream telemetry already
+        handles the missing-attribute case.
+        """
+        if value is None or isinstance(value, str):
+            return value
+        return None
 
 
 class LLMCallFailedEvent(LLMEventBase):

lib/crewai/src/crewai/experimental/__init__.py

@@ -1,31 +1,32 @@
-from crewai.experimental.agent_executor import AgentExecutor, CrewAgentExecutorFlow
-from crewai.experimental.evaluation import (
-    AgentEvaluationResult,
-    AgentEvaluator,
-    BaseEvaluator,
-    EvaluationScore,
-    EvaluationTraceCallback,
-    ExperimentResult,
-    ExperimentResults,
-    ExperimentRunner,
-    GoalAlignmentEvaluator,
-    MetricCategory,
-    ParameterExtractionEvaluator,
-    ReasoningEfficiencyEvaluator,
-    SemanticQualityEvaluator,
-    ToolInvocationEvaluator,
-    ToolSelectionEvaluator,
-    create_default_evaluator,
-    create_evaluation_callbacks,
+"""Experimental CrewAI surface — APIs here may change without major-version bumps."""
+
+from __future__ import annotations
+
+from typing import Any
+
+# ``crewai.experimental.conversational`` is pure data shapes — no Flow or Task
+# imports — so it's safe to eager-import. Everything else is resolved lazily
+# below; otherwise the chain
+#     crewai → Flow → experimental.conversational → experimental.__init__
+#                  → experimental.agent_executor / experimental.evaluation
+#                  → Flow / Task (mid-load)
+# would deadlock with "partially initialized module" ImportErrors.
+from crewai.experimental.conversational import (
+    AgentMessage,
+    ConversationConfig,
+    ConversationEvent,
+    ConversationMessage,
+    ConversationState,
+    RouterConfig,
 )
 
 
-__all__ = [
+_LAZY_FROM_AGENT_EXECUTOR = {"AgentExecutor", "CrewAgentExecutorFlow"}
+
+_LAZY_FROM_EVALUATION = {
     "AgentEvaluationResult",
     "AgentEvaluator",
-    "AgentExecutor",
     "BaseEvaluator",
-    "CrewAgentExecutorFlow",  # Deprecated alias for AgentExecutor
     "EvaluationScore",
     "EvaluationTraceCallback",
     "ExperimentResult",
@@ -40,4 +41,62 @@ __all__ = [
     "ToolSelectionEvaluator",
     "create_default_evaluator",
     "create_evaluation_callbacks",
+}
+
+
+def __getattr__(name: str) -> Any:
+    """Lazily resolve symbols whose modules import ``Flow`` or ``Task``.
+
+    Eager re-exports would deadlock when ``Flow`` itself is the consumer that
+    triggered ``crewai.experimental.__init__`` (``Flow`` imports types from
+    :mod:`crewai.experimental.conversational`). Callers like
+    ``from crewai.experimental import AgentExecutor`` still work — the
+    real import just runs lazily, after the original loader finishes.
+    """
+    if name in _LAZY_FROM_AGENT_EXECUTOR:
+        from crewai.experimental.agent_executor import (
+            AgentExecutor,
+            CrewAgentExecutorFlow,
+        )
+
+        globals()["AgentExecutor"] = AgentExecutor
+        globals()["CrewAgentExecutorFlow"] = CrewAgentExecutorFlow
+        return globals()[name]
+
+    if name in _LAZY_FROM_EVALUATION:
+        from crewai.experimental import evaluation as _evaluation_mod
+
+        for attr in _LAZY_FROM_EVALUATION:
+            globals()[attr] = getattr(_evaluation_mod, attr)
+        return globals()[name]
+
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
+
+
+__all__ = [
+    "AgentEvaluationResult",
+    "AgentEvaluator",
+    "AgentExecutor",
+    "AgentMessage",
+    "BaseEvaluator",
+    "ConversationConfig",
+    "ConversationEvent",
+    "ConversationMessage",
+    "ConversationState",
+    "CrewAgentExecutorFlow",  # Deprecated alias for AgentExecutor
+    "EvaluationScore",
+    "EvaluationTraceCallback",
+    "ExperimentResult",
+    "ExperimentResults",
+    "ExperimentRunner",
+    "GoalAlignmentEvaluator",
+    "MetricCategory",
+    "ParameterExtractionEvaluator",
+    "ReasoningEfficiencyEvaluator",
+    "RouterConfig",
+    "SemanticQualityEvaluator",
+    "ToolInvocationEvaluator",
+    "ToolSelectionEvaluator",
+    "create_default_evaluator",
+    "create_evaluation_callbacks",
 ]

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

@@ -279,6 +279,16 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
         """Set state messages."""
         self._state.messages = value
 
+    @property
+    def ask_for_human_input(self) -> bool:
+        """Compatibility property - returns state ask_for_human_input."""
+        return self._state.ask_for_human_input  # type: ignore[no-any-return]
+
+    @ask_for_human_input.setter
+    def ask_for_human_input(self, value: bool) -> None:
+        """Set state ask_for_human_input."""
+        self._state.ask_for_human_input = value
+
     @start()
     def generate_plan(self) -> None:
         """Generate execution plan if planning is enabled.

lib/crewai/src/crewai/experimental/conversational.py

@@ -0,0 +1,184 @@
+"""Conversational types and helpers shared by ``Flow`` (experimental).
+
+The conversational chat surface (``Flow`` with ``conversational = True``) is
+EXPERIMENTAL. APIs in this module and the conversational methods on ``Flow``
+may change without a major-version bump until the feature graduates.
+
+This module hosts the **data shapes** — ``ConversationConfig``,
+``RouterConfig``, ``ConversationState`` and its message types — plus the
+``_conversational_only`` decorator used to gate built-in conversational
+methods on the base ``Flow`` class. The methods themselves live on ``Flow``
+directly.
+"""
+
+from __future__ import annotations
+
+from collections.abc import Callable, Sequence
+from dataclasses import dataclass
+from typing import Any, Literal, TypeVar, cast
+from uuid import uuid4
+
+from pydantic import BaseModel, ConfigDict, Field
+
+from crewai.utilities.types import LLMMessage
+
+
+ConversationMessageRole = Literal["user", "assistant", "system", "tool"]
+ConversationEventVisibility = Literal["private", "public"]
+
+F = TypeVar("F", bound=Callable[..., Any])
+
+
+def _conversational_only(func: F) -> F:
+    """Mark a method as part of the conversational built-in graph.
+
+    Methods carrying this marker only register on a ``Flow`` subclass when
+    ``conversational = True``. Subclasses that don't opt in see them as
+    inert attributes — they don't fire and don't pollute the listener graph.
+    """
+    func.__conversational_only__ = True  # type: ignore[attr-defined]
+    return func
+
+
+@dataclass
+class RouterConfig:
+    """LLM router configuration for the experimental conversational ``Flow``.
+
+    .. warning::
+
+       **EXPERIMENTAL.** Part of the conversational ``Flow`` surface. Fields
+       and defaults may change before the feature graduates from
+       ``crewai.experimental``. Pin your CrewAI version if you depend on
+       a specific shape.
+
+    ``route_descriptions`` overrides the per-route descriptions used to build
+    the router LLM's "available routes" catalog. Routes without an entry fall
+    back to the handler's docstring first line (or, for built-in routes, the
+    framework's canned description). ``prompt`` is reserved for domain
+    policy/voice, not the route catalog — that's auto-built.
+    """
+
+    prompt: str | None = None
+    response_format: type[BaseModel] | None = None
+    llm: Any | None = None
+    routes: Sequence[str] | None = None
+    route_descriptions: dict[str, str] | None = None
+    default_intent: str | None = "converse"
+    fallback_intent: str | None = "converse"
+    intent_field: str = "intent"
+
+
+@dataclass
+class ConversationConfig:
+    """Class-level configuration for the experimental conversational ``Flow``.
+
+    .. warning::
+
+       **EXPERIMENTAL.** Part of the conversational ``Flow`` surface. Fields
+       and defaults may change before the feature graduates from
+       ``crewai.experimental``. Pin your CrewAI version if you depend on
+       a specific shape.
+
+    ``system_prompt`` defaults to the ``slices.conversational_system_prompt``
+    translation when left as ``None``. Pass an empty string to opt out of any
+    system prompt for ``converse_turn``. ``answer_from_history_prompt`` falls
+    back to ``slices.conversational_answer_from_history_prompt`` when ``None``.
+    """
+
+    system_prompt: str | None = None
+    llm: Any | None = None
+    router: RouterConfig | None = None
+    answer_from_history_prompt: str | None = None
+    default_intents: Sequence[str] | None = None
+    intent_llm: Any | None = None
+    answer_from_history_llm: Any | None = None
+    visible_agent_outputs: Sequence[str] | Literal["all"] | None = None
+    defer_trace_finalization: bool = True
+
+    def __call__(self, flow_cls: type[Any]) -> type[Any]:
+        """Use this config as a class decorator."""
+        flow_cls.conversational_config = self
+        return flow_cls
+
+
+class ConversationMessage(BaseModel):
+    """Canonical user-facing message shared across conversational turns."""
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
+    role: ConversationMessageRole
+    content: str | list[dict[str, Any]] | None
+    name: str | None = None
+    tool_call_id: str | None = None
+    tool_calls: list[dict[str, Any]] | None = None
+    files: dict[str, Any] | None = None
+    metadata: dict[str, Any] = Field(default_factory=dict)
+
+
+class AgentMessage(BaseModel):
+    """Private per-agent message or scratch result."""
+
+    role: ConversationMessageRole | str = "assistant"
+    content: Any
+    metadata: dict[str, Any] = Field(default_factory=dict)
+
+
+class ConversationEvent(BaseModel):
+    """Structured trace/event that is separate from user-visible messages."""
+
+    type: str
+    payload: dict[str, Any] = Field(default_factory=dict)
+    agent_name: str | None = None
+    visibility: ConversationEventVisibility = "private"
+
+
+class ConversationState(BaseModel):
+    """Structured state for the experimental conversational ``Flow``.
+
+    .. warning::
+
+       **EXPERIMENTAL.** Field shape and defaults may change before the
+       conversational ``Flow`` graduates from ``crewai.experimental``.
+
+    ``messages`` is the canonical user-facing history. Agent/tool scratch work
+    belongs in ``events`` or ``agent_threads`` unless explicitly made public.
+    """
+
+    id: str = Field(default_factory=lambda: str(uuid4()))
+    messages: list[ConversationMessage] = Field(default_factory=list)
+    current_user_message: str | None = None
+    last_user_message: str | None = None
+    last_intent: str | None = None
+    ended: bool = False
+    events: list[ConversationEvent] = Field(default_factory=list)
+    agent_threads: dict[str, list[AgentMessage]] = Field(default_factory=dict)
+    session_ready: bool = False
+
+
+def message_to_llm_dict(message: Any) -> LLMMessage:
+    """Coerce a stored ``ConversationMessage`` (or dict) into an ``LLMMessage``."""
+    if isinstance(message, BaseModel):
+        data = message.model_dump(exclude_none=True)
+    elif isinstance(message, dict):
+        data = dict(message)
+    else:
+        data = {"role": "user", "content": str(message)}
+
+    return cast(
+        LLMMessage,
+        {key: value for key, value in data.items() if key != "metadata"},
+    )
+
+
+__all__ = [
+    "AgentMessage",
+    "ConversationConfig",
+    "ConversationEvent",
+    "ConversationEventVisibility",
+    "ConversationMessage",
+    "ConversationMessageRole",
+    "ConversationState",
+    "RouterConfig",
+    "_conversational_only",
+    "message_to_llm_dict",
+]

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

@@ -0,0 +1,942 @@
+"""Conversational graph + helpers as a mixin for ``Flow`` (experimental).
+
+The experimental conversational chat surface lives here as a mixin so that
+``crewai.flow.runtime`` stays focused on the execution engine. ``Flow``
+inherits from ``_ConversationalMixin``; the methods only register on
+subclasses that opt in via ``conversational = True`` (enforced by the
+``_conversational_only`` marker + ``FlowMeta`` gating in
+``crewai.flow.runtime``).
+
+Import surface:
+    - :class:`_ConversationalMixin` — internal; ``Flow`` mixes it in. Users
+      don't import it directly.
+    - The data types this mixin uses live in
+      :mod:`crewai.experimental.conversational`.
+"""
+
+from __future__ import annotations
+
+from collections.abc import Callable, Mapping, Sequence
+from enum import Enum
+import json
+import logging
+from typing import TYPE_CHECKING, Any, ClassVar, Literal, cast
+
+from pydantic import BaseModel, Field, create_model
+
+from crewai.events.event_bus import crewai_event_bus
+from crewai.events.types.flow_events import (
+    ConversationMessageAddedEvent,
+    ConversationRouteSelectedEvent,
+)
+from crewai.experimental.conversational import (
+    AgentMessage,
+    ConversationConfig,
+    ConversationEvent,
+    ConversationMessage,
+    ConversationState,
+    RouterConfig,
+    _conversational_only,
+    message_to_llm_dict,
+)
+from crewai.flow.conversation import (
+    append_message as _append_conversation_message,
+    get_conversation_messages,
+    receive_user_message as _receive_user_message,
+)
+from crewai.flow.dsl import listen, router, start
+from crewai.utilities.types import LLMMessage
+
+
+if TYPE_CHECKING:
+    from crewai.flow.runtime import Flow
+    from crewai.llms.base_llm import BaseLLM
+
+
+logger = logging.getLogger(__name__)
+
+
+class _ConversationalMixin:
+    """Built-in conversational graph for ``Flow`` (gated on ``conversational``).
+
+    Mixed into ``Flow`` so its execution engine (``runtime.py``) stays focused
+    on running graphs. The methods here only register on subclasses that set
+    ``conversational = True``; non-chat flows see them as inert attributes.
+    """
+
+    # The metaclass + state attributes referenced below live on ``Flow`` —
+    # this mixin is never instantiated standalone. These type-only
+    # declarations exist so static analyzers don't flag attribute access.
+    # Class-level slots use ``ClassVar`` to match Flow's actual declarations
+    # (otherwise mypy flags "Cannot override instance variable with class
+    # variable" when Flow declares them as ``ClassVar``).
+    if TYPE_CHECKING:
+        conversational: ClassVar[bool]
+        conversational_config: ClassVar[ConversationConfig | None]
+        builtin_routes: ClassVar[tuple[str, ...]]
+        internal_routes: ClassVar[tuple[str, ...]]
+        builtin_route_descriptions: ClassVar[dict[str, str]]
+        # Registry ClassVars populated by ``FlowMeta`` at class creation.
+        _listeners: ClassVar[dict[Any, Any]]
+
+        # Instance attrs from ``Flow``.
+        state: Any
+        name: str | None
+        _completed_methods: set[Any]
+        _method_outputs: list[Any]
+        _pending_and_listeners: dict[Any, Any]
+        _method_call_counts: dict[Any, int]
+        _is_execution_resuming: bool
+        _pending_user_message: str | dict[str, Any] | None
+        _pending_intents: Sequence[str] | None
+        _pending_intent_llm: str | BaseLLM | None
+
+        def _clear_or_listeners(self) -> None:
+            pass
+
+        def _collapse_to_outcome(
+            self,
+            feedback: str,
+            outcomes: tuple[str, ...],
+            llm: str | BaseLLM | Any,
+        ) -> str:
+            pass
+
+        def _copy_and_serialize_state(self) -> dict[str, Any]:
+            pass
+
+        def kickoff(self, *args: Any, **kwargs: Any) -> Any:
+            pass
+
+    @start()
+    @_conversational_only
+    def conversation_start(self) -> str | None:
+        """Internal Flow entrypoint that hands the user message to the router.
+
+        In conversational mode, ``Flow.kickoff_async`` runs all ``@start``
+        methods sequentially and this one is registered last, so any user
+        ``@start`` methods (e.g. permission loading) have already finished
+        before the returned value triggers ``route_conversation``.
+        """
+        state = cast(ConversationState, self.state)
+        return state.current_user_message
+
+    @router(conversation_start)
+    @_conversational_only
+    def route_conversation(self) -> str:
+        """Route the current turn to a listener label."""
+        state = cast(ConversationState, self.state)
+        context = self.build_router_context()
+        previous_intent = state.last_intent
+        configured_route = self.route_turn(context)
+        if configured_route:
+            state.last_intent = configured_route
+            self._emit_conversation_route_selected(
+                configured_route,
+                previous_intent=previous_intent,
+            )
+            return configured_route
+
+        if state.last_intent:
+            self._emit_conversation_route_selected(
+                state.last_intent,
+                previous_intent=previous_intent,
+            )
+            return state.last_intent
+
+        if self.can_answer_from_history(context):
+            state.last_intent = "answer_from_history"
+            self._emit_conversation_route_selected(
+                "answer_from_history",
+                previous_intent=previous_intent,
+            )
+            return "answer_from_history"
+
+        state.last_intent = "converse"
+        self._emit_conversation_route_selected(
+            "converse",
+            previous_intent=previous_intent,
+        )
+        return "converse"
+
+    @listen("converse")
+    @_conversational_only
+    def converse_turn(self) -> str:
+        """Built-in chat handler over canonical conversation history."""
+        llm = self._default_conversation_llm()
+        if llm is None:
+            content = "I can continue the conversation once an LLM is configured."
+            self.append_assistant_message(content)
+            return content
+
+        messages: list[LLMMessage] = []
+        system_prompt = self._resolve_system_prompt()
+        if system_prompt:
+            messages.append({"role": "system", "content": system_prompt})
+        messages.extend(self.conversation_messages)
+
+        response = self._coerce_llm(llm).call(messages=messages)
+        content = self._stringify_result(response)
+        self.append_assistant_message(content)
+        return content
+
+    @listen("end")
+    @_conversational_only
+    def end_conversation(self) -> str:
+        """Built-in conversation terminator."""
+        cast(ConversationState, self.state).ended = True
+        content = "Conversation ended."
+        self.append_assistant_message(content)
+        return content
+
+    @listen("answer_from_history")
+    @_conversational_only
+    def answer_from_history_turn(self) -> str | None:
+        """Answer directly from canonical conversation history when configured."""
+        config = self._conversation_config
+        if config is None:
+            return None
+        llm = config.answer_from_history_llm
+        if llm is None:
+            return None
+
+        llm_instance = self._coerce_llm(llm)
+        messages: list[LLMMessage] = [
+            {
+                "role": "system",
+                "content": self._resolve_answer_from_history_prompt(),
+            },
+            *self.build_agent_context("answer_from_history"),
+        ]
+        response = llm_instance.call(messages=messages)
+        content = self._stringify_result(response)
+        self.append_assistant_message(content)
+        return content
+
+    def handle_turn(
+        self,
+        message: str,
+        *,
+        session_id: str | None = None,
+        intents: Sequence[str] | None = None,
+        intent_llm: str | BaseLLM | None = None,
+        **kickoff_kwargs: Any,
+    ) -> Any:
+        """Append a user message, run one conversational turn, and return output.
+
+        .. warning::
+
+           **EXPERIMENTAL.** This is the public entry point for the
+           conversational ``Flow``. Signature and semantics may change before
+           the feature graduates from ``crewai.experimental``.
+
+        Available only when ``conversational = True`` is set on the subclass.
+        Stashes the message + session_id as pending turn state, runs kickoff
+        (which restores from persist and then applies the pending turn), and
+        promotes the result to an assistant message when the handler didn't.
+        """
+        state = cast(ConversationState, self.state)
+        sid = session_id or state.id
+
+        # Stash the pending turn so ``_apply_pending_conversational_turn``
+        # picks it up AFTER persist restore.
+        self._pending_user_message = message
+        self._pending_intents = list(intents) if intents else None
+        self._pending_intent_llm = intent_llm
+
+        # Each turn is a fresh execution; clear graph tracking so the second
+        # turn re-runs instead of being treated as a checkpoint restore.
+        if "from_checkpoint" not in kickoff_kwargs:
+            self._reset_turn_execution_state()
+
+        assistant_count = self._assistant_message_count()
+        try:
+            result = self.kickoff(inputs={"id": sid}, **kickoff_kwargs)
+        finally:
+            self._pending_user_message = None
+            self._pending_intents = None
+            self._pending_intent_llm = None
+
+        if (
+            result is not None
+            and self._assistant_message_count() == assistant_count
+            and self._is_public_turn_result(result)
+        ):
+            self.append_assistant_message(self._stringify_result(result))
+        return result
+
+    def chat(
+        self,
+        *,
+        session_id: str | None = None,
+        prompt: str = "\nYou: ",
+        assistant_prefix: str = "\nAssistant: ",
+        exit_commands: Sequence[str] = ("exit", "quit"),
+        input_fn: Callable[[str], str] = input,
+        output_fn: Callable[[str], None] = print,
+        skip_empty: bool = True,
+        defer_trace_finalization: bool = True,
+        **handle_turn_kwargs: Any,
+    ) -> None:
+        """Run an interactive terminal chat loop for a conversational Flow.
+
+        ``chat()`` is a convenience wrapper around ``handle_turn()`` for local
+        REPLs. For web apps, tests, and custom transports, call
+        ``handle_turn()`` directly. The input/output callables are injectable so
+        callers can customize prompts or exercise the loop without patching
+        builtins.
+        """
+        if not getattr(type(self), "conversational", False):
+            raise ValueError("Flow.chat() is only available on conversational flows")
+
+        exit_set = {command.lower() for command in exit_commands}
+        previous_defer = getattr(self, "defer_trace_finalization", False)
+        if defer_trace_finalization:
+            self.defer_trace_finalization = True
+
+        try:
+            while True:
+                try:
+                    message = input_fn(prompt).strip()
+                except (EOFError, KeyboardInterrupt):
+                    output_fn("")
+                    break
+
+                if message.lower() in exit_set:
+                    break
+                if skip_empty and not message:
+                    continue
+
+                result = self.handle_turn(
+                    message,
+                    session_id=session_id,
+                    **handle_turn_kwargs,
+                )
+                output_fn(f"{assistant_prefix}{self._stringify_result(result)}")
+        finally:
+            self.finalize_session_traces()
+            if defer_trace_finalization:
+                self.defer_trace_finalization = previous_defer
+
+    def build_router_context(self) -> dict[str, Any]:
+        """Build context used by the routing policy for the current turn."""
+        state = cast(ConversationState, self.state)
+        return {
+            "system_prompt": self._resolve_system_prompt(),
+            "current_user_message": state.current_user_message,
+            "message_history": self.conversation_messages,
+            "events": [event.model_dump() for event in state.events],
+            "last_intent": state.last_intent,
+        }
+
+    def build_agent_context(self, agent_name: str) -> list[LLMMessage]:
+        """Build canonical message context for an agent or direct LLM call."""
+        state = cast(ConversationState, self.state)
+        messages = list(self.conversation_messages)
+        thread = state.agent_threads.get(agent_name, [])
+        messages.extend(
+            cast(
+                LLMMessage,
+                {
+                    "role": msg.role,
+                    "content": self._stringify_result(msg.content),
+                },
+            )
+            for msg in thread
+        )
+        return messages
+
+    def route_turn(self, context: dict[str, Any]) -> str | None:
+        """Route the current turn via the LLM router.
+
+        When ``ConversationConfig.router`` is omitted, the router is
+        auto-enabled with default settings as long as the flow declares
+        custom ``@listen`` handlers (anything beyond the built-in
+        ``converse`` / ``end`` routes). ``@ConversationConfig(llm=ROUTER_LLM)``
+        is enough to dispatch to your custom handlers — no explicit
+        ``RouterConfig()`` needed.
+
+        Pass an explicit ``RouterConfig`` only to override the routing prompt,
+        supply per-route descriptions, or change the default/fallback intent.
+        Override this method to bypass the LLM router entirely (e.g.,
+        permission gates before the LLM decision).
+        """
+        config = self._conversation_config
+        if config is None:
+            return None
+
+        router_config = config.router
+        if router_config is None:
+            if config.default_intents:
+                return None
+            custom_routes = self._effective_routes(None) - set(self.builtin_routes)
+            if not custom_routes:
+                return None
+            router_config = RouterConfig()
+
+        return self._route_with_config(router_config, context)
+
+    def can_answer_from_history(self, context: dict[str, Any]) -> bool:
+        """Return whether this turn can be answered from message history."""
+        config = self._conversation_config
+        if config is None or config.answer_from_history_llm is None:
+            return False
+        if len(self.conversation_messages) < 2:
+            return False
+
+        feedback = (
+            f"{self._resolve_answer_from_history_prompt()}\n\n"
+            f"Current user message: {context.get('current_user_message')}\n\n"
+            f"Message history:\n{self._format_messages(self.conversation_messages)}"
+        )
+        outcome = self._collapse_to_outcome(
+            feedback,
+            ("answer_from_history", "route_to_flow"),
+            config.answer_from_history_llm,
+        )
+        return outcome == "answer_from_history"
+
+    def append_agent_result(
+        self,
+        agent_name: str,
+        result: Any,
+        *,
+        visibility: Literal["private", "public"] = "private",
+        metadata: dict[str, Any] | None = None,
+    ) -> None:
+        """Record an agent result, optionally making it visible to the user."""
+        content = self._stringify_result(result)
+        event_visibility = self._resolve_visibility(agent_name, visibility)
+        event = ConversationEvent(
+            type="agent_result",
+            agent_name=agent_name,
+            visibility=event_visibility,
+            payload={"content": content, **(metadata or {})},
+        )
+        state = cast(ConversationState, self.state)
+        state.events.append(event)
+        state.agent_threads.setdefault(agent_name, []).append(
+            AgentMessage(content=content, metadata=metadata or {})
+        )
+        if event_visibility == "public":
+            self.append_assistant_message(content)
+
+    def append_assistant_message(
+        self,
+        content: str,
+        *,
+        metadata: dict[str, Any] | None = None,
+    ) -> None:
+        """Append a final user-visible assistant message."""
+        state = cast(ConversationState, self.state)
+        state.messages.append(
+            ConversationMessage(
+                role="assistant",
+                content=content,
+                metadata=metadata or {},
+            )
+        )
+        self._emit_conversation_message_added(
+            role="assistant",
+            content=content,
+            message_index=len(state.messages) - 1,
+        )
+
+    def _emit_conversation_message_added(
+        self,
+        *,
+        role: Literal["user", "assistant", "system", "tool"],
+        content: Any,
+        message_index: int,
+    ) -> None:
+        """Emit a compact transcript event for conversational trace views."""
+        state = cast(ConversationState, self.state)
+        crewai_event_bus.emit(
+            self,
+            ConversationMessageAddedEvent(
+                type="conversation_message_added",
+                flow_name=self.name or self.__class__.__name__,
+                session_id=state.id,
+                role=role,
+                content=content,
+                message_index=message_index,
+            ),
+        )
+
+    def _emit_conversation_route_selected(
+        self,
+        route: str,
+        *,
+        previous_intent: str | None = None,
+    ) -> None:
+        """Emit the conversational routing decision for the current turn."""
+        state = cast(ConversationState, self.state)
+        crewai_event_bus.emit(
+            self,
+            ConversationRouteSelectedEvent(
+                type="conversation_route_selected",
+                flow_name=self.name or self.__class__.__name__,
+                session_id=state.id,
+                route=route,
+                user_message=state.current_user_message,
+                message_index=(len(state.messages) - 1) if state.messages else None,
+                previous_intent=previous_intent,
+            ),
+        )
+
+    def append_message(
+        self,
+        role: Literal["user", "assistant", "system", "tool"],
+        content: str,
+        **extra: Any,
+    ) -> None:
+        """Append a message to conversation history (legacy ChatState path)."""
+        _append_conversation_message(cast("Flow[Any]", self), role, content, **extra)
+
+    @property
+    def conversation_messages(self) -> list[LLMMessage]:
+        """Message history from state, coerced to LLM-shaped dicts."""
+        return [
+            message_to_llm_dict(message)
+            for message in get_conversation_messages(cast("Flow[Any]", self))
+        ]
+
+    def receive_user_message(
+        self,
+        text: str,
+        *,
+        outcomes: Sequence[str] | None = None,
+        llm: str | BaseLLM | None = None,
+    ) -> str:
+        """Append a user message and optionally classify intent.
+
+        Conversational flows push a ``ConversationMessage`` onto
+        ``state.messages`` and preserve ``last_intent`` across turns.
+        Non-conversational flows fall through to the legacy helper.
+        """
+        if self.conversational:
+            state = cast(ConversationState, self.state)
+            state.messages.append(ConversationMessage(role="user", content=text))
+            self._emit_conversation_message_added(
+                role="user",
+                content=text,
+                message_index=len(state.messages) - 1,
+            )
+            state.current_user_message = text
+            state.last_user_message = text
+            if outcomes and llm is not None:
+                intent = self.classify_intent(
+                    text,
+                    outcomes,
+                    llm=llm,
+                    context=self.conversation_messages,
+                )
+                state.last_intent = intent
+                return intent
+            return text
+
+        return _receive_user_message(
+            cast("Flow[Any]", self), text, outcomes=outcomes, llm=llm
+        )
+
+    def classify_intent(
+        self,
+        text: str,
+        outcomes: Sequence[str],
+        *,
+        llm: str | BaseLLM,
+        context: Sequence[Mapping[str, Any]] | None = None,
+    ) -> str:
+        """Map user text to one of the given outcomes using an LLM."""
+        if context:
+            context_blob = "\n".join(
+                f"{m.get('role', 'user')}: {m.get('content', '')}" for m in context
+            )
+            feedback = f"{context_blob}\n\nLatest user message: {text}"
+        else:
+            feedback = text
+        return self._collapse_to_outcome(feedback, tuple(outcomes), llm)
+
+    @property
+    def _conversation_config(self) -> ConversationConfig | None:
+        return getattr(type(self), "conversational_config", None)
+
+    def _should_defer_trace_finalization(self) -> bool:
+        """Whether per-turn ``FlowFinished`` + ``finalize_batch`` should be skipped.
+
+        True when either:
+          - ``flow.defer_trace_finalization`` is set on the instance, OR
+          - the class-level ``ConversationConfig.defer_trace_finalization``
+            on a conversational subclass is True.
+
+        Either source enables the deferred-session pattern. The caller
+        eventually invokes ``finalize_session_traces()`` to close the batch.
+        """
+        if getattr(self, "defer_trace_finalization", False):
+            return True
+        config = self._conversation_config
+        return bool(config and config.defer_trace_finalization)
+
+    def _reset_turn_execution_state(self) -> None:
+        """Clear per-execution tracking so the next turn re-runs the graph."""
+        self._completed_methods.clear()
+        self._method_outputs.clear()
+        self._pending_and_listeners.clear()
+        self._method_call_counts.clear()
+        self._clear_or_listeners()
+        self._is_execution_resuming = False
+
+    def _apply_pending_conversational_turn(self) -> None:
+        """Drain the stashed user message + classify if intents configured.
+
+        Called from ``Flow.kickoff_async`` AFTER persist state restore so
+        the appended message survives ``self.persistence.load_state(...)``.
+        """
+        if self._pending_user_message is None:
+            return
+
+        text = self._coerce_user_message_text(self._pending_user_message)
+        if not text.strip():
+            return
+
+        cfg = self._conversation_config
+        outcomes = self._pending_intents
+        if outcomes is None and cfg is not None:
+            outcomes = cfg.default_intents
+        llm = self._pending_intent_llm
+        if llm is None and cfg is not None:
+            llm = cfg.intent_llm
+
+        if outcomes:
+            if llm is None:
+                raise ValueError("intent_llm is required when intents are provided")
+            self.receive_user_message(text, outcomes=outcomes, llm=llm)
+        else:
+            self.receive_user_message(text)
+
+    def _resolve_system_prompt(self) -> str | None:
+        """Return the effective conversational system prompt."""
+        from crewai.utilities.i18n import I18N_DEFAULT
+
+        config = self._conversation_config
+        if config is None or config.system_prompt is None:
+            return I18N_DEFAULT.slice("conversational_system_prompt")
+        return config.system_prompt or None
+
+    def _resolve_answer_from_history_prompt(self) -> str:
+        """Return the effective ``answer_from_history`` prompt."""
+        from crewai.utilities.i18n import I18N_DEFAULT
+
+        config = self._conversation_config
+        if config is None or not config.answer_from_history_prompt:
+            return I18N_DEFAULT.slice("conversational_answer_from_history_prompt")
+        return config.answer_from_history_prompt
+
+    def _route_with_config(
+        self,
+        router_config: RouterConfig,
+        context: dict[str, Any],
+    ) -> str | None:
+        router_llm = self._default_router_llm(router_config)
+        if router_llm is None:
+            return router_config.default_intent
+
+        try:
+            llm = self._coerce_llm(router_llm)
+            response = self._call_router_llm(
+                llm,
+                messages=self._build_router_messages(router_config, context),
+                response_format=self._router_response_format(router_config),
+            )
+            intent = self._extract_router_intent(response, router_config.intent_field)
+        except Exception:
+            return router_config.fallback_intent or router_config.default_intent
+
+        if intent is None:
+            return router_config.fallback_intent or router_config.default_intent
+
+        valid_labels = self._effective_routes(router_config)
+        if valid_labels and intent not in valid_labels:
+            return router_config.fallback_intent or router_config.default_intent
+
+        return intent
+
+    def _default_router_llm(self, router_config: RouterConfig) -> Any | None:
+        config = self._conversation_config
+        return (
+            router_config.llm
+            or (config.intent_llm if config else None)
+            or (config.llm if config else None)
+        )
+
+    def _router_response_format(
+        self,
+        router_config: RouterConfig,
+    ) -> type[BaseModel]:
+        if router_config.response_format is not None:
+            return router_config.response_format
+
+        routes = sorted(self._effective_routes(router_config))
+        field_definitions: dict[str, Any] = {
+            router_config.intent_field: (
+                str,
+                Field(description=f"One of: {', '.join(routes)}"),
+            )
+        }
+        return cast(
+            type[BaseModel],
+            create_model("ConversationRoute", **field_definitions),
+        )
+
+    def _call_router_llm(
+        self,
+        llm: Any,
+        *,
+        messages: list[LLMMessage],
+        response_format: type[BaseModel],
+    ) -> Any:
+        try:
+            return llm.call(messages=messages, response_format=response_format)
+        except TypeError as exc:
+            if "response_format" not in str(exc):
+                raise
+            return llm.call(messages=messages, response_model=response_format)
+
+    def _build_router_messages(
+        self,
+        router_config: RouterConfig,
+        context: dict[str, Any],
+    ) -> list[LLMMessage]:
+        catalog = self._build_route_catalog(router_config)
+        context = {**context, "available_routes": sorted(catalog.keys())}
+        domain_prompt = f"{router_config.prompt}\n\n" if router_config.prompt else ""
+        routes_section = "Routes:\n" + "\n".join(
+            f"- {label}: {description}" if description else f"- {label}"
+            for label, description in sorted(catalog.items())
+        )
+        routing_prompt = (
+            domain_prompt
+            + routes_section
+            + "\n\nChoose exactly one route from the list above. Prefer "
+            "'converse' for follow-ups, summaries, and clarifications about "
+            "prior turns — even if they touch on a topic the user previously "
+            "invoked a custom route for. Use a custom route only when the user "
+            "is making a fresh request for that tool or workflow."
+        )
+        return [
+            {"role": "system", "content": routing_prompt},
+            {"role": "user", "content": json.dumps(context, default=str)},
+        ]
+
+    def _build_route_catalog(
+        self,
+        router_config: RouterConfig | None,
+    ) -> dict[str, str]:
+        label_to_method: dict[str, str] = {}
+        for listener_name, condition in self._listeners.items():
+            if isinstance(condition, tuple):
+                _, trigger_labels = condition
+                for trigger_label in trigger_labels:
+                    label_to_method.setdefault(str(trigger_label), str(listener_name))
+
+        routes = self._effective_routes(router_config)
+        overrides = (
+            router_config.route_descriptions
+            if router_config and router_config.route_descriptions
+            else {}
+        )
+
+        catalog: dict[str, str] = {}
+        for route_label in routes:
+            if route_label in overrides:
+                catalog[route_label] = overrides[route_label]
+                continue
+            if route_label in self.builtin_route_descriptions:
+                catalog[route_label] = self.builtin_route_descriptions[route_label]
+                continue
+            handler_name = label_to_method.get(route_label)
+            description = ""
+            if handler_name:
+                method = getattr(type(self), handler_name, None)
+                doc = getattr(method, "__doc__", None)
+                if doc:
+                    description = doc.strip().split("\n", 1)[0].strip()
+            catalog[route_label] = description
+
+        return catalog
+
+    def _extract_router_intent(self, response: Any, intent_field: str) -> str | None:
+        if isinstance(response, BaseModel):
+            value = getattr(response, intent_field, None)
+        elif isinstance(response, dict):
+            value = response.get(intent_field)
+        elif isinstance(response, str):
+            try:
+                parsed = json.loads(response)
+            except json.JSONDecodeError:
+                value = response.strip()
+            else:
+                value = parsed.get(intent_field)
+        else:
+            value = getattr(response, intent_field, None)
+
+        if value is None:
+            return None
+        if isinstance(value, Enum):
+            return str(value.value)
+        return str(value)
+
+    def _valid_route_labels(self) -> set[str]:
+        labels: set[str] = set()
+        for condition in self._listeners.values():
+            if isinstance(condition, tuple):
+                _, methods = condition
+                labels.update(str(method) for method in methods)
+        return labels
+
+    def _effective_routes(self, router_config: RouterConfig | None = None) -> set[str]:
+        custom_routes = set(router_config.routes or ()) if router_config else set()
+        if not custom_routes:
+            custom_routes = (
+                self._valid_route_labels()
+                - set(self.builtin_routes)
+                - set(self.internal_routes)
+            )
+        return custom_routes | set(self.builtin_routes)
+
+    def _default_conversation_llm(self) -> Any | None:
+        config = self._conversation_config
+        if config is None:
+            return None
+        if config.llm is not None:
+            return config.llm
+        if config.answer_from_history_llm is not None:
+            return config.answer_from_history_llm
+        if config.router is not None:
+            return config.router.llm
+        return config.intent_llm
+
+    def _resolve_visibility(
+        self,
+        agent_name: str,
+        visibility: Literal["private", "public"],
+    ) -> Literal["private", "public"]:
+        if visibility == "public":
+            return "public"
+        config = self._conversation_config
+        visible = config.visible_agent_outputs if config else None
+        if visible == "all" or (visible is not None and agent_name in visible):
+            return "public"
+        return "private"
+
+    def _assistant_message_count(self) -> int:
+        state = cast(ConversationState, self.state)
+        return sum(1 for message in state.messages if message.role == "assistant")
+
+    def _is_public_turn_result(self, result: Any) -> bool:
+        if not isinstance(result, str):
+            return False
+        if result in {
+            "conversation",
+            "converse",
+            "end",
+            "answer_from_history",
+            "route_to_flow",
+        }:
+            return False
+        return result != cast(ConversationState, self.state).last_intent
+
+    @staticmethod
+    def _coerce_user_message_text(user_message: str | dict[str, Any] | Any) -> str:
+        if isinstance(user_message, str):
+            return user_message
+        if isinstance(user_message, dict) and user_message.get("content") is not None:
+            return str(user_message["content"])
+        return str(user_message)
+
+    @staticmethod
+    def _stringify_result(result: Any) -> str:
+        if hasattr(result, "raw"):
+            return str(result.raw)
+        if isinstance(result, BaseModel):
+            return result.model_dump_json()
+        return str(result)
+
+    @staticmethod
+    def _format_messages(messages: Sequence[Mapping[str, Any]]) -> str:
+        return "\n".join(
+            f"{message.get('role', 'user')}: {message.get('content', '')}"
+            for message in messages
+        )
+
+    @staticmethod
+    def _coerce_llm(llm: str | BaseLLM | Any) -> Any:
+        from crewai.llm import LLM
+        from crewai.llms.base_llm import BaseLLM as BaseLLMClass
+
+        if isinstance(llm, str):
+            return LLM(model=llm)
+        if isinstance(llm, BaseLLMClass) or callable(getattr(llm, "call", None)):
+            return llm
+        raise ValueError(f"Invalid llm type: {type(llm)}. Expected str or BaseLLM.")
+
+    def finalize_session_traces(self) -> None:
+        """Emit a final ``FlowFinishedEvent`` and finalize the trace batch.
+
+        Pairs with ``flow.defer_trace_finalization = True`` (or
+        ``ConversationConfig(defer_trace_finalization=True)``): per-turn
+        ``handle_turn()`` skips the close, then a single call here at
+        session end emits one ``FlowFinishedEvent`` + ``finalize_batch()``
+        so the whole conversation lands as one trace.
+
+        Safe to call when not deferring — it's a no-op if the trace batch
+        was already finalized per-turn or never started.
+        """
+        from crewai.events.event_bus import crewai_event_bus
+        from crewai.events.event_context import restore_event_scope
+        from crewai.events.listeners.tracing.trace_listener import (
+            TraceCollectionListener,
+        )
+        from crewai.events.types.flow_events import FlowFinishedEvent
+
+        # Only emit the session-end event when a deferred flow_started is
+        # actually pending. ``_deferred_flow_started_event_id`` is set only by
+        # deferred kickoffs; when finalization was not deferred, each per-turn
+        # kickoff already emitted its own flow_finished, so emitting here would
+        # duplicate the session-end event and confuse tracing. Restoring the
+        # stashed scope also pairs this flow_finished with its opener instead
+        # of warning about an empty scope stack.
+        started_id = getattr(self, "_deferred_flow_started_event_id", None)
+        if started_id:
+            last_output = self._method_outputs[-1] if self._method_outputs else None
+            restore_event_scope(((started_id, "flow_started"),))
+            try:
+                crewai_event_bus.emit(
+                    self,
+                    FlowFinishedEvent(
+                        type="flow_finished",
+                        flow_name=self.name or self.__class__.__name__,
+                        result=last_output,
+                        state=self._copy_and_serialize_state(),
+                    ),
+                )
+            except Exception:
+                logger.warning(
+                    "FlowFinishedEvent emission failed during finalize_session_traces",
+                    exc_info=True,
+                )
+            finally:
+                restore_event_scope(())
+                object.__setattr__(self, "_deferred_flow_started_event_id", None)
+
+        trace_listener = TraceCollectionListener()
+        batch_manager = trace_listener.batch_manager
+        if batch_manager.batch_owner_type == "flow":
+            if trace_listener.first_time_handler.is_first_time:
+                trace_listener.first_time_handler.mark_events_collected()
+                trace_listener.first_time_handler.handle_execution_completion()
+            else:
+                batch_manager.finalize_batch()
+
+
+__all__ = ["_ConversationalMixin"]

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

@@ -4,10 +4,14 @@ from crewai.flow.async_feedback import (
     HumanFeedbackProvider,
     PendingFeedbackContext,
 )
+from crewai.flow.conversation import (
+    ChatState,
+    ConversationalConfig,
+    ConversationalInputs,
+)
+from crewai.flow.dsl import HumanFeedbackResult, human_feedback
 from crewai.flow.flow import Flow, and_, listen, or_, router, start
 from crewai.flow.flow_config import flow_config
-from crewai.flow.flow_serializer import flow_structure
-from crewai.flow.human_feedback import HumanFeedbackResult, human_feedback
 from crewai.flow.input_provider import InputProvider, InputResponse
 from crewai.flow.persistence import persist
 from crewai.flow.visualization import (
@@ -18,7 +22,10 @@ from crewai.flow.visualization import (
 
 
 __all__ = [
+    "ChatState",
     "ConsoleProvider",
+    "ConversationalConfig",
+    "ConversationalInputs",
     "Flow",
     "FlowStructure",
     "HumanFeedbackPending",
@@ -30,7 +37,6 @@ __all__ = [
     "and_",
     "build_flow_structure",
     "flow_config",
-    "flow_structure",
     "human_feedback",
     "listen",
     "or_",

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

@@ -0,0 +1,246 @@
+"""Conversational turn helpers for CrewAI Flows.
+
+Provides message history utilities, kickoff input normalization, and optional
+class-level defaults via ``ConversationalConfig``. Session identity is ``state.id``
+(``inputs["id"]`` / ``kickoff(session_id=...)``), not a separate Flow field.
+"""
+
+from __future__ import annotations
+
+from collections.abc import Sequence
+from dataclasses import dataclass, field
+from typing import TYPE_CHECKING, Any, Literal, TypedDict, cast
+from uuid import uuid4
+
+from pydantic import BaseModel, Field
+
+from crewai.utilities.types import LLMMessage
+
+
+if TYPE_CHECKING:
+    from crewai.flow.flow import Flow
+    from crewai.llms.base_llm import BaseLLM
+
+
+_EXIT_COMMANDS_DEFAULT: tuple[str, ...] = ("exit", "quit")
+
+
+class ConversationalInputs(TypedDict, total=False):
+    """Conventional ``kickoff(inputs=...)`` keys for chat turns."""
+
+    id: str
+    user_message: str | dict[str, Any]
+    last_intent: str
+
+
+@dataclass
+class ConversationalConfig:
+    """Optional class-level defaults for conversational flows.
+
+    Override per kickoff via ``user_message``, ``session_id``, ``intents``, etc.
+    """
+
+    default_intents: Sequence[str] | None = None
+    intent_llm: str | None = None
+    interactive_prompt: str = "You: "
+    interactive_timeout: float | None = None
+    exit_commands: Sequence[str] = field(default_factory=lambda: _EXIT_COMMANDS_DEFAULT)
+    defer_trace_finalization: bool = True
+
+
+class ChatState(BaseModel):
+    """Recommended persisted state shape for multi-turn flows."""
+
+    id: str = Field(default_factory=lambda: str(uuid4()))
+    messages: list[LLMMessage] = Field(default_factory=list)
+    last_user_message: str | None = None
+    last_intent: str | None = None
+    session_ready: bool = False
+
+
+def _coerce_user_message_text(user_message: str | dict[str, Any] | Any) -> str:
+    if isinstance(user_message, str):
+        return user_message
+    if isinstance(user_message, dict):
+        content = user_message.get("content")
+        if content is not None:
+            return str(content)
+    return str(user_message)
+
+
+def normalize_kickoff_inputs(
+    inputs: dict[str, Any] | None,
+    *,
+    user_message: str | dict[str, Any] | None = None,
+    session_id: str | None = None,
+) -> dict[str, Any] | None:
+    """Merge conversational kickoff kwargs into the inputs dict.
+
+    Returns ``None`` when the caller passed no inputs and no conversational
+    kwargs — so ``FlowStartedEvent.inputs`` stays ``None`` for stateless flows
+    instead of being materialized as an empty dict.
+    """
+    if inputs is None and user_message is None and session_id is None:
+        return None
+
+    merged: dict[str, Any] = dict(inputs or {})
+
+    if session_id is not None:
+        merged["id"] = session_id
+
+    if user_message is not None:
+        merged["user_message"] = user_message
+
+    return merged
+
+
+def get_conversation_messages(flow: Flow[Any]) -> list[LLMMessage]:
+    """Read message history from flow state or the internal fallback buffer."""
+    buffer: list[LLMMessage] = getattr(flow, "_conversation_messages", [])
+    state = getattr(flow, "_state", None)
+    if state is None:
+        return list(buffer)
+
+    if isinstance(state, dict):
+        messages = state.get("messages")
+        if isinstance(messages, list):
+            return cast(list[LLMMessage], messages)
+    elif isinstance(state, BaseModel) and hasattr(state, "messages"):
+        messages = getattr(state, "messages", None)
+        if isinstance(messages, list):
+            return cast(list[LLMMessage], messages)
+
+    return list(buffer)
+
+
+def append_message(
+    flow: Flow[Any],
+    role: Literal["user", "assistant", "system", "tool"],
+    content: str,
+    **extra: Any,
+) -> None:
+    """Append a message to ``state.messages`` or the flow fallback buffer."""
+    message: LLMMessage = {"role": role, "content": content}
+    for key, value in extra.items():
+        if key in ("tool_call_id", "name", "tool_calls", "files"):
+            message[key] = value  # type: ignore[literal-required]
+
+    state = getattr(flow, "_state", None)
+    if state is not None:
+        if isinstance(state, dict):
+            messages = state.get("messages")
+            if isinstance(messages, list):
+                messages.append(message)
+                return
+        elif isinstance(state, BaseModel) and hasattr(state, "messages"):
+            messages = getattr(state, "messages", None)
+            if messages is None:
+                object.__setattr__(state, "messages", [])
+                messages = state.messages
+            if isinstance(messages, list):
+                messages.append(message)
+                return
+
+    if not hasattr(flow, "_conversation_messages"):
+        object.__setattr__(flow, "_conversation_messages", [])
+    flow._conversation_messages.append(message)
+
+
+def set_state_field(flow: Flow[Any], name: str, value: Any) -> None:
+    """Set a field on structured or dict flow state when present."""
+    state = getattr(flow, "_state", None)
+    if state is None:
+        return
+    if isinstance(state, dict):
+        state[name] = value
+    elif isinstance(state, BaseModel) and hasattr(state, name):
+        object.__setattr__(state, name, value)
+
+
+def receive_user_message(
+    flow: Flow[Any],
+    text: str,
+    *,
+    outcomes: Sequence[str] | None = None,
+    llm: str | BaseLLM | None = None,
+) -> str:
+    """Record a user turn: append message and optionally classify intent."""
+    append_message(flow, "user", text)
+    set_state_field(flow, "last_user_message", text)
+
+    if outcomes and llm is not None:
+        intent = flow.classify_intent(
+            text,
+            outcomes,
+            llm=llm,
+            context=get_conversation_messages(flow),
+        )
+        set_state_field(flow, "last_intent", intent)
+        return intent
+
+    return text
+
+
+def prepare_conversational_turn(
+    flow: Flow[Any],
+    *,
+    user_message: str | dict[str, Any] | None = None,
+    intents: Sequence[str] | None = None,
+    intent_llm: str | BaseLLM | None = None,
+    config: ConversationalConfig | None = None,
+) -> None:
+    """Hydrate conversation state after inputs are merged into flow state."""
+    if user_message is None:
+        state = getattr(flow, "_state", None)
+        if isinstance(state, dict) and "user_message" in state:
+            user_message = state["user_message"]
+        elif isinstance(state, BaseModel) and hasattr(state, "user_message"):
+            user_message = getattr(state, "user_message", None)
+
+    if user_message is None:
+        return
+
+    text = _coerce_user_message_text(user_message)
+    if not text.strip():
+        return
+
+    # Fresh classification each turn (do not reuse prior turn's route label).
+    set_state_field(flow, "last_intent", None)
+
+    resolved_intents = intents
+    if resolved_intents is None and config is not None:
+        resolved_intents = config.default_intents
+
+    resolved_llm = intent_llm
+    if resolved_llm is None and config is not None:
+        resolved_llm = config.intent_llm
+
+    if resolved_intents:
+        if resolved_llm is None:
+            raise ValueError("intent_llm is required when intents are provided")
+        receive_user_message(
+            flow,
+            text,
+            outcomes=resolved_intents,
+            llm=resolved_llm,
+        )
+    else:
+        receive_user_message(flow, text)
+
+
+def input_history_to_messages(entries: Sequence[Any]) -> list[LLMMessage]:
+    """Convert ``Flow.input_history`` entries to LLM message format."""
+    messages: list[LLMMessage] = []
+    for entry in entries:
+        prompt = entry.get("message") if isinstance(entry, dict) else None
+        response = entry.get("response") if isinstance(entry, dict) else None
+        if prompt:
+            messages.append({"role": "assistant", "content": str(prompt)})
+        if response:
+            messages.append({"role": "user", "content": str(response)})
+    return messages
+
+
+def get_conversational_config(flow: Flow[Any]) -> ConversationalConfig | None:
+    """Return class-level ``conversational_config`` if defined."""
+    return getattr(type(flow), "conversational_config", None)

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

@@ -1,320 +0,0 @@
-"""Flow authoring DSL: the ``@start`` / ``@listen`` / ``@router`` decorators
-plus the ``or_`` / ``and_`` condition combinators.
-
-These decorators wrap user methods into the typed wrappers defined in
-``flow_wrappers`` and record their trigger conditions. The structural model
-those conditions feed is built in ``flow_definition``; execution happens in
-``runtime``.
-"""
-
-from __future__ import annotations
-
-from collections.abc import Callable
-from typing import Any, ParamSpec, TypeVar
-
-from crewai.flow.constants import AND_CONDITION, OR_CONDITION
-from crewai.flow.flow_definition import (
-    _extract_all_methods,
-    is_flow_condition_dict,
-    is_flow_method_callable,
-    is_flow_method_name,
-)
-from crewai.flow.flow_wrappers import (
-    FlowCondition,
-    FlowConditions,
-    ListenMethod,
-    RouterMethod,
-    StartMethod,
-)
-
-
-P = ParamSpec("P")
-R = TypeVar("R")
-
-
-def start(
-    condition: str | FlowCondition | Callable[..., Any] | None = None,
-) -> Callable[[Callable[P, R]], StartMethod[P, R]]:
-    """Marks a method as a flow's starting point.
-
-    This decorator designates a method as an entry point for the flow execution.
-    It can optionally specify conditions that trigger the start based on other
-    method executions.
-
-    Args:
-        condition: Defines when the start method should execute. Can be:
-            - str: Name of a method that triggers this start
-            - FlowCondition: Result from or_() or and_(), including nested conditions
-            - Callable[..., Any]: A method reference that triggers this start
-            Default is None, meaning unconditional start.
-
-    Returns:
-        A decorator function that wraps the method as a flow start point and preserves its signature.
-
-    Raises:
-        ValueError: If the condition format is invalid.
-
-    Examples:
-        >>> @start()  # Unconditional start
-        >>> def begin_flow(self):
-        ...     pass
-
-        >>> @start("method_name")  # Start after specific method
-        >>> def conditional_start(self):
-        ...     pass
-
-        >>> @start(and_("method1", "method2"))  # Start after multiple methods
-        >>> def complex_start(self):
-        ...     pass
-    """
-
-    def decorator(func: Callable[P, R]) -> StartMethod[P, R]:
-        """Decorator that wraps a function as a start method.
-
-        Args:
-            func: The function to wrap as a start method.
-
-        Returns:
-            A StartMethod wrapper around the function.
-        """
-        wrapper = StartMethod(func)
-
-        if condition is not None:
-            if is_flow_method_name(condition):
-                wrapper.__trigger_methods__ = [condition]
-                wrapper.__condition_type__ = OR_CONDITION
-            elif is_flow_condition_dict(condition):
-                if "conditions" in condition:
-                    wrapper.__trigger_condition__ = condition
-                    wrapper.__trigger_methods__ = _extract_all_methods(condition)
-                    wrapper.__condition_type__ = condition["type"]
-                elif "methods" in condition:
-                    wrapper.__trigger_methods__ = condition["methods"]
-                    wrapper.__condition_type__ = condition["type"]
-                else:
-                    raise ValueError(
-                        "Condition dict must contain 'conditions' or 'methods'"
-                    )
-            elif is_flow_method_callable(condition):
-                wrapper.__trigger_methods__ = [condition.__name__]
-                wrapper.__condition_type__ = OR_CONDITION
-            else:
-                raise ValueError(
-                    "Condition must be a method, string, or a result of or_() or and_()"
-                )
-        return wrapper
-
-    return decorator
-
-
-def listen(
-    condition: str | FlowCondition | Callable[..., Any],
-) -> Callable[[Callable[P, R]], ListenMethod[P, R]]:
-    """Creates a listener that executes when specified conditions are met.
-
-    This decorator sets up a method to execute in response to other method
-    executions in the flow. It supports both simple and complex triggering
-    conditions.
-
-    Args:
-        condition: Specifies when the listener should execute.
-
-    Returns:
-        A decorator function that wraps the method as a flow listener and preserves its signature.
-
-    Raises:
-        ValueError: If the condition format is invalid.
-
-    Examples:
-        >>> @listen("process_data")
-        >>> def handle_processed_data(self):
-        ...     pass
-
-        >>> @listen("method_name")
-        >>> def handle_completion(self):
-        ...     pass
-    """
-
-    def decorator(func: Callable[P, R]) -> ListenMethod[P, R]:
-        """Decorator that wraps a function as a listener method.
-
-        Args:
-            func: The function to wrap as a listener method.
-
-        Returns:
-            A ListenMethod wrapper around the function.
-        """
-        wrapper = ListenMethod(func)
-
-        if is_flow_method_name(condition):
-            wrapper.__trigger_methods__ = [condition]
-            wrapper.__condition_type__ = OR_CONDITION
-        elif is_flow_condition_dict(condition):
-            if "conditions" in condition:
-                wrapper.__trigger_condition__ = condition
-                wrapper.__trigger_methods__ = _extract_all_methods(condition)
-                wrapper.__condition_type__ = condition["type"]
-            elif "methods" in condition:
-                wrapper.__trigger_methods__ = condition["methods"]
-                wrapper.__condition_type__ = condition["type"]
-            else:
-                raise ValueError(
-                    "Condition dict must contain 'conditions' or 'methods'"
-                )
-        elif is_flow_method_callable(condition):
-            wrapper.__trigger_methods__ = [condition.__name__]
-            wrapper.__condition_type__ = OR_CONDITION
-        else:
-            raise ValueError(
-                "Condition must be a method, string, or a result of or_() or and_()"
-            )
-        return wrapper
-
-    return decorator
-
-
-def router(
-    condition: str | FlowCondition | Callable[..., Any],
-) -> Callable[[Callable[P, R]], RouterMethod[P, R]]:
-    """Creates a routing method that directs flow execution based on conditions.
-
-    This decorator marks a method as a router, which can dynamically determine
-    the next steps in the flow based on its return value. Routers are triggered
-    by specified conditions and can return constants that determine which path
-    the flow should take.
-
-    Args:
-        condition: Specifies when the router should execute. Can be:
-            - str: Name of a method that triggers this router
-            - FlowCondition: Result from or_() or and_(), including nested conditions
-            - Callable[..., Any]: A method reference that triggers this router
-
-    Returns:
-        A decorator function that wraps the method as a router and preserves its signature.
-
-    Raises:
-        ValueError: If the condition format is invalid.
-
-    Examples:
-        >>> @router("check_status")
-        >>> def route_based_on_status(self):
-        ...     if self.state.status == "success":
-        ...         return "SUCCESS"
-        ...     return "FAILURE"
-
-        >>> @router(and_("validate", "process"))
-        >>> def complex_routing(self):
-        ...     if all([self.state.valid, self.state.processed]):
-        ...         return "CONTINUE"
-        ...     return "STOP"
-    """
-
-    def decorator(func: Callable[P, R]) -> RouterMethod[P, R]:
-        """Decorator that wraps a function as a router method.
-
-        Args:
-            func: The function to wrap as a router method.
-
-        Returns:
-            A RouterMethod wrapper around the function.
-        """
-        wrapper = RouterMethod(func)
-
-        if is_flow_method_name(condition):
-            wrapper.__trigger_methods__ = [condition]
-            wrapper.__condition_type__ = OR_CONDITION
-        elif is_flow_condition_dict(condition):
-            if "conditions" in condition:
-                wrapper.__trigger_condition__ = condition
-                wrapper.__trigger_methods__ = _extract_all_methods(condition)
-                wrapper.__condition_type__ = condition["type"]
-            elif "methods" in condition:
-                wrapper.__trigger_methods__ = condition["methods"]
-                wrapper.__condition_type__ = condition["type"]
-            else:
-                raise ValueError(
-                    "Condition dict must contain 'conditions' or 'methods'"
-                )
-        elif is_flow_method_callable(condition):
-            wrapper.__trigger_methods__ = [condition.__name__]
-            wrapper.__condition_type__ = OR_CONDITION
-        else:
-            raise ValueError(
-                "Condition must be a method, string, or a result of or_() or and_()"
-            )
-        return wrapper
-
-    return decorator
-
-
-def or_(*conditions: str | FlowCondition | Callable[..., Any]) -> FlowCondition:
-    """Combines multiple conditions with OR logic for flow control.
-
-    Creates a condition that is satisfied when any of the specified conditions
-    are met. This is used with @start, @listen, or @router decorators to create
-    complex triggering conditions.
-
-    Args:
-        conditions: Variable number of conditions that can be method names, existing condition dictionaries, or method references.
-
-    Returns:
-        A condition dictionary with format {"type": "OR", "conditions": list_of_conditions} where each condition can be a string (method name) or a nested dict
-
-    Raises:
-        ValueError: If condition format is invalid.
-
-    Examples:
-        >>> @listen(or_("success", "timeout"))
-        >>> def handle_completion(self):
-        ...     pass
-
-        >>> @listen(or_(and_("step1", "step2"), "step3"))
-        >>> def handle_nested(self):
-        ...     pass
-    """
-    processed_conditions: FlowConditions = []
-    for condition in conditions:
-        if is_flow_condition_dict(condition) or is_flow_method_name(condition):
-            processed_conditions.append(condition)
-        elif is_flow_method_callable(condition):
-            processed_conditions.append(condition.__name__)
-        else:
-            raise ValueError("Invalid condition in or_()")
-    return {"type": OR_CONDITION, "conditions": processed_conditions}
-
-
-def and_(*conditions: str | FlowCondition | Callable[..., Any]) -> FlowCondition:
-    """Combines multiple conditions with AND logic for flow control.
-
-    Creates a condition that is satisfied only when all specified conditions
-    are met. This is used with @start, @listen, or @router decorators to create
-    complex triggering conditions.
-
-    Args:
-        *conditions: Variable number of conditions that can be method names, existing condition dictionaries, or method references.
-
-    Returns:
-        A condition dictionary with format {"type": "AND", "conditions": list_of_conditions}
-        where each condition can be a string (method name) or a nested dict
-
-    Raises:
-        ValueError: If any condition is invalid.
-
-    Examples:
-        >>> @listen(and_("validated", "processed"))
-        >>> def handle_complete_data(self):
-        ...     pass
-
-        >>> @listen(and_(or_("step1", "step2"), "step3"))
-        >>> def handle_nested(self):
-        ...     pass
-    """
-    processed_conditions: FlowConditions = []
-    for condition in conditions:
-        if is_flow_condition_dict(condition) or is_flow_method_name(condition):
-            processed_conditions.append(condition)
-        elif is_flow_method_callable(condition):
-            processed_conditions.append(condition.__name__)
-        else:
-            raise ValueError("Invalid condition in and_()")
-    return {"type": AND_CONDITION, "conditions": processed_conditions}

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

@@ -0,0 +1,29 @@
+"""Flow DSL: the Python authoring layer for Flows.
+
+Provides the ``@start`` / ``@listen`` / ``@router`` decorators and the
+``or_`` / ``and_`` condition combinators used to write Flow classes in
+Python. The DSL is one way to produce a Flow Structure: this package
+extracts a :class:`~crewai.flow.flow_definition.FlowDefinition` from a
+Python Flow class. Execution is handled by ``runtime``.
+"""
+
+from crewai.flow.dsl._conditions import and_, or_
+from crewai.flow.dsl._human_feedback import (
+    HumanFeedbackResult,
+    human_feedback,
+)
+from crewai.flow.dsl._listen import listen
+from crewai.flow.dsl._router import router
+from crewai.flow.dsl._start import start
+from crewai.flow.dsl._utils import build_flow_definition as build_flow_definition
+
+
+__all__ = [
+    "HumanFeedbackResult",
+    "and_",
+    "human_feedback",
+    "listen",
+    "or_",
+    "router",
+    "start",
+]

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

@@ -0,0 +1,86 @@
+"""Flow DSL condition primitives."""
+
+from __future__ import annotations
+
+from collections.abc import Sequence
+from typing import Any
+
+from typing_extensions import TypeIs
+
+from crewai.flow.constants import AND_CONDITION, OR_CONDITION
+from crewai.flow.dsl._types import FlowTrigger
+from crewai.flow.flow_definition import FlowDefinitionCondition
+from crewai.flow.flow_wrappers import (
+    FlowCondition,
+    FlowConditionType,
+)
+
+
+_CONDITION_TYPES = (AND_CONDITION, OR_CONDITION)
+
+
+def or_(*triggers: FlowTrigger) -> FlowCondition:
+    """Return a condition that fires when any trigger fires."""
+    return _condition_tree(OR_CONDITION, triggers)
+
+
+def and_(*triggers: FlowTrigger) -> FlowCondition:
+    """Return a condition that fires after all triggers fire."""
+    return _condition_tree(AND_CONDITION, triggers)
+
+
+def _trigger_name(value: Any) -> str | None:
+    if isinstance(value, str):
+        return value
+
+    name = getattr(value, "__name__", None)
+    if callable(value) and isinstance(name, str):
+        return name
+
+    return None
+
+
+def _is_condition(value: Any) -> TypeIs[FlowCondition]:
+    return (
+        isinstance(value, dict)
+        and set(value) == {"type", "conditions"}
+        and value["type"] in _CONDITION_TYPES
+        and isinstance(value["conditions"], list)
+        and all(
+            _trigger_name(condition) is not None or _is_condition(condition)
+            for condition in value["conditions"]
+        )
+    )
+
+
+def _coerce_trigger(trigger: FlowTrigger) -> str | FlowCondition:
+    name = _trigger_name(trigger)
+    if name is not None:
+        return name
+    if _is_condition(trigger):
+        return trigger
+    raise ValueError("Invalid condition")
+
+
+def _condition_tree(
+    condition_type: FlowConditionType,
+    triggers: Sequence[FlowTrigger],
+) -> FlowCondition:
+    return {
+        "type": condition_type,
+        "conditions": [_coerce_trigger(trigger) for trigger in triggers],
+    }
+
+
+def _to_definition_condition(condition: FlowTrigger) -> FlowDefinitionCondition:
+    trigger = _coerce_trigger(condition)
+    if isinstance(trigger, str):
+        return trigger
+
+    key = trigger["type"].lower()
+    return {
+        key: [
+            _to_definition_condition(sub_condition)
+            for sub_condition in trigger["conditions"]
+        ]
+    }

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

@@ -0,0 +1,90 @@
+from __future__ import annotations
+
+from collections.abc import Callable, Sequence
+from typing import TYPE_CHECKING, Any, TypeVar
+
+from crewai.flow.flow_definition import FlowMethodDefinition
+from crewai.flow.human_feedback import (
+    HumanFeedbackConfig,
+    HumanFeedbackResult,
+    _build_human_feedback_runtime_decorator,
+)
+
+
+if TYPE_CHECKING:
+    from crewai.flow.async_feedback.types import HumanFeedbackProvider
+    from crewai.llms.base_llm import BaseLLM
+
+
+F = TypeVar("F", bound=Callable[..., Any])
+
+__all__ = ["HumanFeedbackResult", "human_feedback"]
+
+
+def _stamp_human_feedback_metadata(
+    wrapper: Any,
+    func: Callable[..., Any],
+    config: HumanFeedbackConfig,
+) -> None:
+    for attr in [
+        "__is_flow_method__",
+        "__flow_persistence_config__",
+        "__flow_method_definition__",
+    ]:
+        if hasattr(func, attr):
+            setattr(wrapper, attr, getattr(func, attr))
+
+    wrapper.__human_feedback_config__ = config
+    wrapper.__is_flow_method__ = True
+
+    if config.emit:
+        fragment = getattr(wrapper, "__flow_method_definition__", None)
+        if isinstance(fragment, FlowMethodDefinition):
+            wrapper.__flow_method_definition__ = fragment.model_copy(
+                update={"router": True, "emit": list(config.emit)}
+            )
+
+    wrapper._human_feedback_llm = config.llm
+
+
+def human_feedback(
+    message: str,
+    emit: Sequence[str] | None = None,
+    llm: str | BaseLLM | None = "gpt-4o-mini",
+    default_outcome: str | None = None,
+    metadata: dict[str, Any] | None = None,
+    provider: HumanFeedbackProvider | None = None,
+    learn: bool = False,
+    learn_source: str = "hitl",
+    learn_strict: bool = False,
+) -> Callable[[F], F]:
+    """Decorator for Flow methods that require human feedback."""
+    runtime_decorator = _build_human_feedback_runtime_decorator(
+        message=message,
+        emit=emit,
+        llm=llm,
+        default_outcome=default_outcome,
+        metadata=metadata,
+        provider=provider,
+        learn=learn,
+        learn_source=learn_source,
+        learn_strict=learn_strict,
+    )
+    config = HumanFeedbackConfig(
+        message=message,
+        emit=emit,
+        llm=llm,
+        default_outcome=default_outcome,
+        metadata=metadata,
+        provider=provider,
+        learn=learn,
+        learn_source=learn_source,
+        learn_strict=learn_strict,
+    )
+
+    def decorator(func: F) -> F:
+        wrapper = runtime_decorator(func)
+        _stamp_human_feedback_metadata(wrapper, func, config)
+        return wrapper
+
+    return decorator

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

@@ -0,0 +1,52 @@
+from __future__ import annotations
+
+from collections.abc import Callable
+from typing import cast
+
+from crewai.flow.dsl._conditions import _to_definition_condition
+from crewai.flow.dsl._types import FlowMethodDecorator, FlowTrigger
+from crewai.flow.dsl._utils import (
+    P,
+    R,
+    _set_flow_method_definition,
+)
+from crewai.flow.flow_definition import FlowMethodDefinition
+from crewai.flow.flow_wrappers import ListenMethod
+
+
+def listen(condition: FlowTrigger) -> FlowMethodDecorator:
+    """Creates a listener that executes when specified conditions are met.
+
+    This decorator sets up a method to execute in response to other method
+    executions in the flow. It supports both simple and complex triggering
+    conditions.
+
+    Args:
+        condition: Route label, method reference, or condition returned by
+            or_() / and_() that triggers the listener.
+
+    Returns:
+        A flow method decorator that preserves the decorated method's static signature.
+
+    Raises:
+        ValueError: If the condition format is invalid.
+
+    Examples:
+        >>> @listen("process_data")
+        >>> def handle_processed_data(self):
+        ...     pass
+
+        >>> @listen("method_name")
+        >>> def handle_completion(self):
+        ...     pass
+    """
+
+    def decorator(func: Callable[P, R]) -> ListenMethod[P, R]:
+        wrapper = ListenMethod(func)
+
+        _set_flow_method_definition(
+            wrapper, FlowMethodDefinition(listen=_to_definition_condition(condition))
+        )
+        return wrapper
+
+    return cast(FlowMethodDecorator, decorator)

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

@@ -0,0 +1,158 @@
+from __future__ import annotations
+
+from collections.abc import Callable, Sequence
+from enum import Enum
+import inspect
+from types import UnionType
+from typing import (
+    Any,
+    Literal,
+    Union,
+    cast,
+    get_args,
+    get_origin,
+    get_type_hints,
+)
+
+from crewai.flow.dsl._conditions import _to_definition_condition
+from crewai.flow.dsl._types import FlowMethodDecorator, FlowTrigger
+from crewai.flow.dsl._utils import (
+    P,
+    R,
+    _set_flow_method_definition,
+)
+from crewai.flow.flow_definition import FlowMethodDefinition
+from crewai.flow.flow_wrappers import RouterMethod
+
+
+def _unwrap_function(function: Any) -> Any:
+    if hasattr(function, "__func__"):
+        function = function.__func__
+
+    if hasattr(function, "__wrapped__"):
+        wrapped = function.__wrapped__
+        if hasattr(wrapped, "unwrap"):
+            return wrapped.unwrap()
+        return wrapped
+
+    if hasattr(function, "unwrap"):
+        return function.unwrap()
+
+    return function
+
+
+def _string_values_from_annotation(annotation: Any) -> list[str]:
+    if annotation is inspect.Signature.empty or isinstance(annotation, str):
+        return []
+    if isinstance(annotation, type) and issubclass(annotation, Enum):
+        return [member.value for member in annotation if isinstance(member.value, str)]
+
+    origin = get_origin(annotation)
+    if origin is None:
+        return []
+
+    args = get_args(annotation)
+    if origin is Literal or getattr(origin, "__name__", "") == "Literal":
+        return [arg for arg in args if isinstance(arg, str)]
+
+    if not (
+        origin is Union
+        or origin is UnionType
+        or getattr(origin, "__name__", "") == "Annotated"
+    ):
+        return []
+
+    values: list[str] = []
+    for arg in args:
+        values.extend(_string_values_from_annotation(arg))
+    return values
+
+
+def _return_annotation(function: Any) -> Any:
+    unwrapped = _unwrap_function(function)
+
+    try:
+        return get_type_hints(unwrapped, include_extras=True).get(
+            "return", inspect.Signature.empty
+        )
+    except (NameError, TypeError, ValueError):
+        try:
+            return inspect.signature(unwrapped).return_annotation
+        except (TypeError, ValueError):
+            return inspect.Signature.empty
+
+
+def _get_router_return_events(function: Any) -> list[str] | None:
+    values = _string_values_from_annotation(_return_annotation(function))
+    return list(dict.fromkeys(values)) if values else None
+
+
+def _normalize_router_emit(value: Sequence[Any] | str) -> list[str]:
+    if isinstance(value, str):
+        return [str(value)]
+    return list(dict.fromkeys(str(item) for item in value))
+
+
+def router(
+    condition: FlowTrigger,
+    *,
+    emit: Sequence[str] | str | None = None,
+) -> FlowMethodDecorator:
+    """Creates a routing method that directs flow execution based on conditions.
+
+    This decorator marks a method as a router, which can dynamically determine
+    the next steps in the flow based on its return value. Routers are triggered
+    by specified conditions and can return constants that emit downstream events.
+
+    Args:
+        condition: Specifies when the router should execute. Can be:
+            - str: Route label or method name that triggers this router
+            - FlowCondition: Result from or_() or and_(), including nested conditions
+            - Flow method reference: A method whose completion triggers this router
+        emit: Optional explicit router output events for static FlowDefinition
+            and visualization. If omitted, Literal/Enum return annotations are
+            used when available.
+
+    Returns:
+        A flow method decorator that preserves the decorated method's static signature.
+
+    Raises:
+        ValueError: If the condition format is invalid.
+
+    Examples:
+        >>> @router("check_status")
+        >>> def route_based_on_status(self):
+        ...     if self.state.status == "success":
+        ...         return "SUCCESS"
+        ...     return "FAILURE"
+
+        >>> @router(and_("validate", "process"))
+        >>> def complex_routing(self):
+        ...     if all([self.state.valid, self.state.processed]):
+        ...         return "CONTINUE"
+        ...     return "STOP"
+
+        >>> @router("check_status", emit=["SUCCESS", "FAILURE"])
+        >>> def explicit_routing(self):
+        ...     return "SUCCESS"
+    """
+
+    def decorator(func: Callable[P, R]) -> RouterMethod[P, R]:
+        wrapper = RouterMethod(func)
+
+        if emit is not None:
+            router_events = _normalize_router_emit(emit)
+        else:
+            router_events = _get_router_return_events(func) or []
+
+        _set_flow_method_definition(
+            wrapper,
+            FlowMethodDefinition(
+                listen=_to_definition_condition(condition),
+                router=True,
+                emit=router_events or None,
+            ),
+        )
+        return wrapper
+
+    return cast(FlowMethodDecorator, decorator)

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

@@ -0,0 +1,65 @@
+from __future__ import annotations
+
+from collections.abc import Callable
+from typing import cast
+
+from crewai.flow.dsl._conditions import _to_definition_condition
+from crewai.flow.dsl._types import FlowMethodDecorator, FlowTrigger
+from crewai.flow.dsl._utils import (
+    P,
+    R,
+    _set_flow_method_definition,
+)
+from crewai.flow.flow_definition import FlowMethodDefinition
+from crewai.flow.flow_wrappers import StartMethod
+
+
+def start(
+    condition: FlowTrigger | None = None,
+) -> FlowMethodDecorator:
+    """Marks a method as a flow's starting point.
+
+    This decorator designates a method as an entry point for the flow execution.
+    It can optionally specify conditions that trigger the start based on other
+    method executions.
+
+    Args:
+        condition: Defines when the start method should execute. Can be:
+            - str: Route label or method name that triggers this start
+            - FlowCondition: Result from or_() or and_(), including nested conditions
+            - Flow method reference: A method whose completion triggers this start
+            Default is None, meaning unconditional start.
+
+    Returns:
+        A flow method decorator that preserves the decorated method's static signature.
+
+    Raises:
+        ValueError: If the condition format is invalid.
+
+    Examples:
+        >>> @start()  # Unconditional start
+        >>> def begin_flow(self):
+        ...     pass
+
+        >>> @start("method_name")  # Start after specific method
+        >>> def conditional_start(self):
+        ...     pass
+
+        >>> @start(and_("method1", "method2"))  # Start after multiple methods
+        >>> def complex_start(self):
+        ...     pass
+    """
+
+    def decorator(func: Callable[P, R]) -> StartMethod[P, R]:
+        wrapper = StartMethod(func)
+
+        if condition is not None:
+            _set_flow_method_definition(
+                wrapper,
+                FlowMethodDefinition(start=_to_definition_condition(condition)),
+            )
+        else:
+            _set_flow_method_definition(wrapper, FlowMethodDefinition(start=True))
+        return wrapper
+
+    return cast(FlowMethodDecorator, decorator)

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

@@ -0,0 +1,27 @@
+"""Private typing helpers for the Python Flow DSL."""
+
+from __future__ import annotations
+
+from collections.abc import Callable
+from typing import Any, Protocol, TypeAlias, TypeVar
+
+from crewai.flow.flow_wrappers import FlowCondition
+from crewai.flow.types import FlowMethodCallable
+
+
+__all__ = ["FlowMethodDecorator", "FlowTrigger"]
+
+F = TypeVar("F", bound=Callable[..., Any])
+
+FlowTrigger: TypeAlias = str | FlowMethodCallable[..., Any] | FlowCondition
+
+
+class FlowMethodDecorator(Protocol):
+    """Decorator returned by Flow DSL authoring helpers.
+
+    The runtime wraps methods in FlowMethod subclasses, but the authoring
+    contract preserves the decorated method's static callable type.
+    """
+
+    def __call__(self, func: F) -> F:
+        raise NotImplementedError

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

@@ -0,0 +1,330 @@
+from __future__ import annotations
+
+import json
+import logging
+from typing import Any, ParamSpec, TypeVar
+
+from pydantic import BaseModel
+from typing_extensions import TypeIs
+
+from crewai.flow.flow_definition import (
+    FlowConfigDefinition,
+    FlowDefinition,
+    FlowDefinitionDiagnostic,
+    FlowHumanFeedbackDefinition,
+    FlowMethodDefinition,
+    FlowPersistenceDefinition,
+    FlowStateDefinition,
+)
+from crewai.flow.flow_wrappers import (
+    FlowMethod,
+)
+
+
+P = ParamSpec("P")
+R = TypeVar("R")
+
+logger = logging.getLogger(__name__)
+
+_FLOW_METHOD_DEFINITION_ATTR = "__flow_method_definition__"
+
+
+def is_flow_method(obj: Any) -> TypeIs[FlowMethod[Any, Any]]:
+    """Check if the object carries Flow method wrapper metadata."""
+    return hasattr(obj, "__is_flow_method__") or hasattr(
+        obj, _FLOW_METHOD_DEFINITION_ATTR
+    )
+
+
+def _should_include_flow_method(flow_class: type, method: Any) -> bool:
+    if getattr(method, "__conversational_only__", False):
+        return bool(getattr(flow_class, "conversational", False))
+    return True
+
+
+def _set_flow_method_definition(
+    wrapper: FlowMethod[P, R],
+    definition: FlowMethodDefinition,
+) -> None:
+    setattr(wrapper, _FLOW_METHOD_DEFINITION_ATTR, definition)
+
+
+def _get_flow_method_definition(method: Any) -> FlowMethodDefinition | None:
+    definition = getattr(method, _FLOW_METHOD_DEFINITION_ATTR, None)
+    if isinstance(definition, FlowMethodDefinition):
+        return definition
+    if definition is not None:
+        return FlowMethodDefinition.model_validate(definition)
+    return None
+
+
+def _object_ref(value: Any) -> str:
+    target = value if isinstance(value, type) else type(value)
+    module = getattr(target, "__module__", "")
+    qualname = getattr(target, "__qualname__", getattr(target, "__name__", ""))
+    return f"{module}:{qualname}" if module and qualname else repr(value)
+
+
+def _is_json_serializable(value: Any) -> bool:
+    try:
+        json.dumps(value)
+    except (TypeError, ValueError):
+        return False
+    return True
+
+
+def _serialize_static_value(
+    value: Any,
+    diagnostics: list[FlowDefinitionDiagnostic],
+    path: str,
+) -> Any:
+    if value is None or _is_json_serializable(value):
+        return value
+
+    to_config = getattr(value, "to_config_dict", None)
+    if callable(to_config):
+        try:
+            config = to_config()
+            if _is_json_serializable(config):
+                return config
+        except Exception:
+            logger.debug(
+                "Failed to serialize %s via to_config_dict().",
+                path,
+                exc_info=True,
+            )
+
+    if isinstance(value, BaseModel):
+        try:
+            data = value.model_dump(mode="json")
+            if _is_json_serializable(data):
+                return data
+        except Exception:
+            logger.debug(
+                "Failed to serialize %s via Pydantic model_dump().",
+                path,
+                exc_info=True,
+            )
+
+    ref = _object_ref(value)
+    diagnostics.append(
+        FlowDefinitionDiagnostic(
+            code="non_serializable_value",
+            path=path,
+            message=f"value is not fully serializable; preserved import reference {ref}",
+        )
+    )
+    return {"ref": ref}
+
+
+def _state_ref(value: Any) -> str | None:
+    if value is None:
+        return None
+    target = value if isinstance(value, type) else type(value)
+    module = getattr(target, "__module__", None)
+    qualname = getattr(target, "__qualname__", None)
+    if module and qualname:
+        return f"{module}:{qualname}"
+    return None
+
+
+def _build_state_definition(
+    flow_class: type,
+    diagnostics: list[FlowDefinitionDiagnostic],
+) -> FlowStateDefinition | None:
+    from pydantic import BaseModel as PydanticBaseModel
+
+    state_value = getattr(flow_class, "_initial_state_t", None)
+    initial_state = getattr(flow_class, "initial_state", None)
+    if initial_state is not None:
+        state_value = initial_state
+
+    if state_value is None:
+        return None
+    if state_value is dict or isinstance(state_value, dict):
+        default = None
+        if isinstance(state_value, dict):
+            default = _serialize_static_value(state_value, diagnostics, "state.default")
+        return FlowStateDefinition(type="dict", default=default)
+    if isinstance(state_value, type) and issubclass(state_value, PydanticBaseModel):
+        return FlowStateDefinition(type="pydantic", ref=_state_ref(state_value))
+    if isinstance(state_value, PydanticBaseModel):
+        return FlowStateDefinition(
+            type="pydantic",
+            ref=_state_ref(state_value),
+            default=_serialize_static_value(state_value, diagnostics, "state.default"),
+        )
+    diagnostics.append(
+        FlowDefinitionDiagnostic(
+            code="unknown_state_type",
+            path="state",
+            message=f"could not serialize state type {_object_ref(state_value)}",
+        )
+    )
+    return FlowStateDefinition(type="unknown", ref=_state_ref(state_value))
+
+
+def _build_config_definition(
+    flow_class: type,
+    diagnostics: list[FlowDefinitionDiagnostic],
+) -> FlowConfigDefinition:
+    config_field_names = set(FlowConfigDefinition.model_fields)
+    field_defaults = {
+        name: field.default
+        for name, field in getattr(flow_class, "model_fields", {}).items()
+        if name in config_field_names
+    }
+    values: dict[str, Any] = {}
+    for field_name, default in field_defaults.items():
+        value = getattr(flow_class, field_name, default)
+        values[field_name] = _serialize_static_value(
+            value, diagnostics, f"config.{field_name}"
+        )
+    return FlowConfigDefinition(**values)
+
+
+def _build_human_feedback_definition(
+    method: Any,
+    diagnostics: list[FlowDefinitionDiagnostic],
+    path: str,
+) -> FlowHumanFeedbackDefinition | None:
+    config = getattr(method, "__human_feedback_config__", None)
+    if config is None:
+        return None
+    emit = getattr(config, "emit", None)
+    return FlowHumanFeedbackDefinition(
+        message=str(config.message),
+        emit=[str(value) for value in emit] if emit is not None else None,
+        llm=_serialize_static_value(
+            getattr(config, "llm", None), diagnostics, f"{path}.llm"
+        ),
+        default_outcome=getattr(config, "default_outcome", None),
+        metadata=_serialize_static_value(
+            getattr(config, "metadata", None), diagnostics, f"{path}.metadata"
+        ),
+        provider=_serialize_static_value(
+            getattr(config, "provider", None), diagnostics, f"{path}.provider"
+        ),
+        learn=bool(getattr(config, "learn", False)),
+        learn_source=str(getattr(config, "learn_source", "hitl")),
+        learn_strict=bool(getattr(config, "learn_strict", False)),
+    )
+
+
+def _build_persistence_definition(
+    value: Any,
+    diagnostics: list[FlowDefinitionDiagnostic],
+    path: str,
+) -> FlowPersistenceDefinition | None:
+    config = getattr(value, "__flow_persistence_config__", None)
+    if config is None:
+        return None
+    persistence = getattr(config, "persistence", None)
+    verbose = bool(getattr(config, "verbose", False))
+    return FlowPersistenceDefinition(
+        enabled=True,
+        verbose=verbose,
+        persistence=_serialize_static_value(
+            persistence, diagnostics, f"{path}.persistence"
+        ),
+    )
+
+
+def _build_method_definition(
+    method: Any,
+    diagnostics: list[FlowDefinitionDiagnostic],
+    path: str,
+) -> FlowMethodDefinition:
+    fragment = _get_flow_method_definition(method)
+    if fragment is None:
+        method_definition = FlowMethodDefinition()
+    else:
+        method_definition = fragment.model_copy(deep=True)
+
+    human_feedback = _build_human_feedback_definition(
+        method, diagnostics, f"{path}.human_feedback"
+    )
+    if human_feedback is not None:
+        method_definition.human_feedback = human_feedback
+        if human_feedback.emit:
+            method_definition.router = True
+            method_definition.emit = None
+
+    method_definition.persist = _build_persistence_definition(
+        method, diagnostics, f"{path}.persist"
+    )
+
+    return method_definition
+
+
+def _iter_flow_methods(flow_class: type) -> dict[str, Any]:
+    methods: dict[str, Any] = {}
+    for attr_name in flow_class.__dict__:
+        if attr_name.startswith("_"):
+            continue
+        try:
+            attr_value = getattr(flow_class, attr_name)
+        except AttributeError:
+            continue
+        if is_flow_method(attr_value) and _should_include_flow_method(
+            flow_class, attr_value
+        ):
+            methods[attr_name] = attr_value
+
+    # A wrapped method whose name collides with a base Flow model field
+    # (e.g. ``checkpoint``) is absorbed by Pydantic as a field; the underlying
+    # function is preserved as the field default. Recover those so the
+    # definition still reflects every method once the class is built.
+    for field_name, field in getattr(flow_class, "model_fields", {}).items():
+        if field_name in methods or field_name.startswith("_"):
+            continue
+        default = getattr(field, "default", None)
+        if is_flow_method(default) and _should_include_flow_method(flow_class, default):
+            methods[field_name] = default
+    return methods
+
+
+def _build_flow_definition_from_class(
+    flow_class: type,
+    namespace: dict[str, Any] | None = None,
+) -> FlowDefinition:
+    diagnostics: list[FlowDefinitionDiagnostic] = []
+    methods: dict[str, FlowMethodDefinition] = {}
+    flow_methods = _iter_flow_methods(flow_class)
+    if namespace is not None:
+        for attr_name, attr_value in namespace.items():
+            if is_flow_method(attr_value) and _should_include_flow_method(
+                flow_class, attr_value
+            ):
+                flow_methods[attr_name] = attr_value
+
+    for method_name, method in flow_methods.items():
+        methods[method_name] = _build_method_definition(
+            method, diagnostics, f"methods.{method_name}"
+        )
+
+    description = None
+    docstring = flow_class.__doc__
+    if docstring:
+        description = docstring.strip()
+
+    definition = FlowDefinition(
+        name=getattr(flow_class, "__name__", "Flow"),
+        description=description,
+        state=_build_state_definition(flow_class, diagnostics),
+        config=_build_config_definition(flow_class, diagnostics),
+        persist=_build_persistence_definition(flow_class, diagnostics, "persist"),
+        methods=methods,
+        diagnostics=diagnostics,
+    )
+    definition.diagnostics.extend(definition.validate_contract())
+    definition.log_diagnostics()
+    return definition
+
+
+def build_flow_definition(
+    flow_class: type,
+    namespace: dict[str, Any] | None = None,
+) -> FlowDefinition:
+    """Build a FlowDefinition from a Python Flow class."""
+    return _build_flow_definition_from_class(flow_class, namespace)

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

@@ -3,8 +3,8 @@
 The implementation now lives in three modules, split by concern:
 
 - ``crewai.flow.dsl`` -- authoring decorators (``@start`` / ``@listen`` /
-  ``@router``, ``or_`` / ``and_``)
-- ``crewai.flow.flow_definition`` -- the structural model extracted from the DSL
+  ``@router``, ``or_`` / ``and_``) and Python Flow class projection
+- ``crewai.flow.flow_definition`` -- the serializable Flow Definition contract
 - ``crewai.flow.runtime`` -- the Flow execution engine and state
 
 Prefer importing from those modules in new code; this module preserves the

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

@@ -18,3 +18,7 @@ current_flow_id: contextvars.ContextVar[str | None] = contextvars.ContextVar(
 current_flow_method_name: contextvars.ContextVar[str] = contextvars.ContextVar(
     "flow_method_name", default="unknown"
 )
+
+current_flow_name: contextvars.ContextVar[str | None] = contextvars.ContextVar(
+    "flow_name", default=None
+)

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

@@ -1,592 +0,0 @@
-"""Flow structure serializer for introspecting Flow classes.
-
-This module provides the flow_structure() function that analyzes a Flow class
-and returns a JSON-serializable dictionary describing its graph structure.
-This is used by Studio UI to render a visual flow graph.
-
-Example:
-    >>> from crewai.flow import Flow, start, listen
-    >>> from crewai.flow.flow_serializer import flow_structure
-    >>>
-    >>> class MyFlow(Flow):
-    ...     @start()
-    ...     def begin(self):
-    ...         return "started"
-    ...
-    ...     @listen(begin)
-    ...     def process(self):
-    ...         return "done"
-    >>>
-    >>> structure = flow_structure(MyFlow)
-    >>> print(structure["name"])
-    'MyFlow'
-"""
-
-from __future__ import annotations
-
-import inspect
-import logging
-import re
-import textwrap
-from typing import Any, TypedDict, get_args, get_origin
-
-from pydantic import BaseModel
-from pydantic_core import PydanticUndefined
-
-from crewai.flow.flow_wrappers import (
-    FlowCondition,
-    FlowMethod,
-    ListenMethod,
-    RouterMethod,
-    StartMethod,
-)
-
-
-logger = logging.getLogger(__name__)
-
-
-class MethodInfo(TypedDict, total=False):
-    """Information about a single flow method.
-
-    Attributes:
-        name: The method name.
-        type: Method type - start, listen, router, or start_router.
-        trigger_methods: List of method names that trigger this method.
-        condition_type: 'AND' or 'OR' for composite conditions, null otherwise.
-        router_paths: For routers, the possible route names returned.
-        has_human_feedback: Whether the method has @human_feedback decorator.
-        has_crew: Whether the method body references a Crew.
-    """
-
-    name: str
-    type: str
-    trigger_methods: list[str]
-    condition_type: str | None
-    router_paths: list[str]
-    has_human_feedback: bool
-    has_crew: bool
-
-
-class EdgeInfo(TypedDict, total=False):
-    """Information about an edge between flow methods.
-
-    Attributes:
-        from_method: Source method name.
-        to_method: Target method name.
-        edge_type: Type of edge - 'listen' or 'route'.
-        condition: Route name for router edges, null for listen edges.
-    """
-
-    from_method: str
-    to_method: str
-    edge_type: str
-    condition: str | None
-
-
-class StateFieldInfo(TypedDict, total=False):
-    """Information about a state field.
-
-    Attributes:
-        name: Field name.
-        type: Field type as string.
-        default: Default value if any.
-    """
-
-    name: str
-    type: str
-    default: Any
-
-
-class StateSchemaInfo(TypedDict, total=False):
-    """Information about the flow's state schema.
-
-    Attributes:
-        fields: List of field information.
-    """
-
-    fields: list[StateFieldInfo]
-
-
-class FlowStructureInfo(TypedDict, total=False):
-    """Complete flow structure information.
-
-    Attributes:
-        name: Flow class name.
-        description: Flow docstring if available.
-        methods: List of method information.
-        edges: List of edge information.
-        state_schema: State schema if typed, null otherwise.
-        inputs: Detected flow inputs if available.
-    """
-
-    name: str
-    description: str | None
-    methods: list[MethodInfo]
-    edges: list[EdgeInfo]
-    state_schema: StateSchemaInfo | None
-    inputs: list[str]
-
-
-def _get_method_type(
-    method_name: str,
-    method: Any,
-    start_methods: list[str],
-    routers: set[str],
-) -> str:
-    """Determine the type of a flow method.
-
-    Args:
-        method_name: Name of the method.
-        method: The method object.
-        start_methods: List of start method names.
-        routers: Set of router method names.
-
-    Returns:
-        One of: 'start', 'listen', 'router', or 'start_router'.
-    """
-    is_start = method_name in start_methods or getattr(
-        method, "__is_start_method__", False
-    )
-    is_router = method_name in routers or getattr(method, "__is_router__", False)
-
-    if is_start and is_router:
-        return "start_router"
-    if is_start:
-        return "start"
-    if is_router:
-        return "router"
-    return "listen"
-
-
-def _has_human_feedback(method: Any) -> bool:
-    """Check if a method has the @human_feedback decorator.
-
-    Args:
-        method: The method object to check.
-
-    Returns:
-        True if the method has __human_feedback_config__ attribute.
-    """
-    return hasattr(method, "__human_feedback_config__")
-
-
-def _detect_crew_reference(method: Any) -> bool:
-    """Detect if a method body references a Crew.
-
-    Checks for patterns like:
-    - .crew() method calls
-    - Crew( instantiation
-    - References to Crew class in type hints
-
-    Note:
-        This is a **best-effort heuristic for UI hints**, not a guarantee.
-        Uses inspect.getsource + regex which can false-positive on comments
-        or string literals, and may fail on dynamically generated methods
-        or lambdas. Do not rely on this for correctness-critical logic.
-
-    Args:
-        method: The method object to inspect.
-
-    Returns:
-        True if crew reference detected, False otherwise.
-    """
-    try:
-        func = method
-        if hasattr(method, "_meth"):
-            func = method._meth
-        elif hasattr(method, "__wrapped__"):
-            func = method.__wrapped__
-
-        source = inspect.getsource(func)
-        source = textwrap.dedent(source)
-
-        crew_patterns = [
-            r"\.crew\(\)",  # .crew() method call
-            r"Crew\s*\(",  # Crew( instantiation
-            r":\s*Crew\b",  # Type hint with Crew
-            r"->.*Crew",  # Return type hint with Crew
-        ]
-
-        for pattern in crew_patterns:
-            if re.search(pattern, source):
-                return True
-
-        return False
-    except (OSError, TypeError):
-        return False
-
-
-def _extract_trigger_methods(method: Any) -> tuple[list[str], str | None]:
-    """Extract trigger methods and condition type from a method.
-
-    Args:
-        method: The method object to inspect.
-
-    Returns:
-        Tuple of (trigger_methods list, condition_type or None).
-    """
-    trigger_methods: list[str] = []
-    condition_type: str | None = None
-
-    if hasattr(method, "__trigger_methods__") and method.__trigger_methods__:
-        trigger_methods = [str(m) for m in method.__trigger_methods__]
-
-    # For complex conditions (or_/and_ combinators), extract from __trigger_condition__
-    if (
-        not trigger_methods
-        and hasattr(method, "__trigger_condition__")
-        and method.__trigger_condition__
-    ):
-        trigger_condition = method.__trigger_condition__
-        trigger_methods = _extract_all_methods_from_condition(trigger_condition)
-
-    if hasattr(method, "__condition_type__") and method.__condition_type__:
-        condition_type = str(method.__condition_type__)
-
-    return trigger_methods, condition_type
-
-
-def _extract_router_paths(
-    method: Any, router_paths_registry: dict[str, list[str]]
-) -> list[str]:
-    """Extract router paths for a router method.
-
-    Args:
-        method: The method object.
-        router_paths_registry: The class-level _router_paths dict.
-
-    Returns:
-        List of possible route names.
-    """
-    method_name = getattr(method, "__name__", "")
-
-    if hasattr(method, "__router_paths__") and method.__router_paths__:
-        return [str(p) for p in method.__router_paths__]
-
-    if method_name in router_paths_registry:
-        return [str(p) for p in router_paths_registry[method_name]]
-
-    return []
-
-
-def _extract_all_methods_from_condition(
-    condition: str | FlowCondition | dict[str, Any] | list[Any],
-) -> list[str]:
-    """Extract all method names from a condition tree recursively.
-
-    Args:
-        condition: Can be a string, FlowCondition tuple, dict, or list.
-
-    Returns:
-        List of all method names found in the condition.
-    """
-    if isinstance(condition, str):
-        return [condition]
-    if isinstance(condition, tuple) and len(condition) == 2:
-        # FlowCondition: (condition_type, methods_list)
-        _, methods = condition
-        if isinstance(methods, list):
-            result: list[str] = []
-            for m in methods:
-                result.extend(_extract_all_methods_from_condition(m))
-            return result
-        return []
-    if isinstance(condition, dict):
-        conditions_list = condition.get("conditions", [])
-        dict_methods: list[str] = []
-        for sub_cond in conditions_list:
-            dict_methods.extend(_extract_all_methods_from_condition(sub_cond))
-        return dict_methods
-    if isinstance(condition, list):
-        list_methods: list[str] = []
-        for item in condition:
-            list_methods.extend(_extract_all_methods_from_condition(item))
-        return list_methods
-    return []
-
-
-def _generate_edges(
-    listeners: dict[str, tuple[str, list[str]] | FlowCondition],
-    routers: set[str],
-    router_paths: dict[str, list[str]],
-    all_methods: set[str],
-) -> list[EdgeInfo]:
-    """Generate edges from listeners and routers.
-
-    Args:
-        listeners: Map of listener_name -> (condition_type, trigger_methods) or FlowCondition.
-        routers: Set of router method names.
-        router_paths: Map of router_name -> possible return values.
-        all_methods: Set of all method names in the flow.
-
-    Returns:
-        List of EdgeInfo dictionaries.
-    """
-    edges: list[EdgeInfo] = []
-
-    for listener_name, condition_data in listeners.items():
-        trigger_methods: list[str] = []
-
-        if isinstance(condition_data, tuple) and len(condition_data) == 2:
-            _condition_type, methods = condition_data
-            trigger_methods = [str(m) for m in methods]
-        elif isinstance(condition_data, dict):
-            trigger_methods = _extract_all_methods_from_condition(condition_data)
-
-        edges.extend(
-            EdgeInfo(
-                from_method=trigger,
-                to_method=listener_name,
-                edge_type="listen",
-                condition=None,
-            )
-            for trigger in trigger_methods
-            if trigger in all_methods
-        )
-
-    for router_name, paths in router_paths.items():
-        for path in paths:
-            for listener_name, condition_data in listeners.items():
-                path_triggers: list[str] = []
-
-                if isinstance(condition_data, tuple) and len(condition_data) == 2:
-                    _, methods = condition_data
-                    path_triggers = [str(m) for m in methods]
-                elif isinstance(condition_data, dict):
-                    path_triggers = _extract_all_methods_from_condition(condition_data)
-
-                if str(path) in path_triggers:
-                    edges.append(
-                        EdgeInfo(
-                            from_method=router_name,
-                            to_method=listener_name,
-                            edge_type="route",
-                            condition=str(path),
-                        )
-                    )
-
-    return edges
-
-
-def _extract_state_schema(flow_class: type) -> StateSchemaInfo | None:
-    """Extract state schema from a Flow class.
-
-    Checks for:
-    - Generic type parameter (Flow[MyState])
-    - initial_state class attribute
-
-    Args:
-        flow_class: The Flow class to inspect.
-
-    Returns:
-        StateSchemaInfo if a Pydantic model state is detected, None otherwise.
-    """
-    state_type: type | None = None
-
-    # _initial_state_t is set by Flow.__class_getitem__
-    if hasattr(flow_class, "_initial_state_t"):
-        state_type = flow_class._initial_state_t
-
-    if state_type is None and hasattr(flow_class, "initial_state"):
-        initial_state = flow_class.initial_state
-        if isinstance(initial_state, type) and issubclass(initial_state, BaseModel):
-            state_type = initial_state
-        elif isinstance(initial_state, BaseModel):
-            state_type = type(initial_state)
-
-    if state_type is None and hasattr(flow_class, "__orig_bases__"):
-        for base in flow_class.__orig_bases__:
-            origin = get_origin(base)
-            if origin is not None:
-                args = get_args(base)
-                if args:
-                    candidate = args[0]
-                    if isinstance(candidate, type) and issubclass(candidate, BaseModel):
-                        state_type = candidate
-                        break
-
-    if state_type is None or not issubclass(state_type, BaseModel):
-        return None
-
-    fields: list[StateFieldInfo] = []
-    try:
-        model_fields = state_type.model_fields
-        for field_name, field_info in model_fields.items():
-            field_type_str = "Any"
-            if field_info.annotation is not None:
-                field_type_str = str(field_info.annotation)
-                field_type_str = field_type_str.replace("typing.", "")
-                field_type_str = field_type_str.replace("<class '", "").replace(
-                    "'>", ""
-                )
-
-            default_value = None
-            if (
-                field_info.default is not PydanticUndefined
-                and field_info.default is not None
-                and not callable(field_info.default)
-            ):
-                try:
-                    default_value = field_info.default
-                except Exception:
-                    default_value = str(field_info.default)
-
-            fields.append(
-                StateFieldInfo(
-                    name=field_name,
-                    type=field_type_str,
-                    default=default_value,
-                )
-            )
-    except Exception:
-        logger.debug(
-            "Failed to extract state schema fields for %s", flow_class.__name__
-        )
-
-    return StateSchemaInfo(fields=fields) if fields else None
-
-
-def _detect_flow_inputs(flow_class: type) -> list[str]:
-    """Detect flow input parameters.
-
-    Inspects the __init__ signature for custom parameters beyond standard Flow params.
-
-    Args:
-        flow_class: The Flow class to inspect.
-
-    Returns:
-        List of detected input names.
-    """
-    inputs: list[str] = []
-
-    try:
-        init_method = flow_class.__init__  # type: ignore[misc]
-        init_sig = inspect.signature(init_method)
-        standard_params = {
-            "self",
-            "persistence",
-            "tracing",
-            "suppress_flow_events",
-            "max_method_calls",
-            "kwargs",
-        }
-        inputs.extend(
-            param_name
-            for param_name in init_sig.parameters
-            if param_name not in standard_params and not param_name.startswith("_")
-        )
-    except Exception:
-        logger.debug(
-            "Failed to detect inputs from __init__ for %s", flow_class.__name__
-        )
-
-    return inputs
-
-
-def flow_structure(flow_class: type) -> FlowStructureInfo:
-    """Introspect a Flow class and return its structure as a JSON-serializable dict.
-
-    This function analyzes a Flow CLASS (not instance) and returns complete
-    information about its graph structure including methods, edges, and state.
-
-    Args:
-        flow_class: A Flow class (not an instance) to introspect.
-
-    Returns:
-        FlowStructureInfo dictionary containing:
-        - name: Flow class name
-        - description: Docstring if available
-        - methods: List of method info dicts
-        - edges: List of edge info dicts
-        - state_schema: State schema if typed, None otherwise
-        - inputs: Detected input names
-
-    Raises:
-        TypeError: If flow_class is not a class.
-
-    Example:
-        >>> structure = flow_structure(MyFlow)
-        >>> print(structure["name"])
-        'MyFlow'
-        >>> for method in structure["methods"]:
-        ...     print(method["name"], method["type"])
-    """
-    if not isinstance(flow_class, type):
-        raise TypeError(
-            f"flow_structure requires a Flow class, not an instance. "
-            f"Got {type(flow_class).__name__}"
-        )
-
-    start_methods: list[str] = getattr(flow_class, "_start_methods", [])
-    listeners: dict[str, Any] = getattr(flow_class, "_listeners", {})
-    routers: set[str] = getattr(flow_class, "_routers", set())
-    router_paths_registry: dict[str, list[str]] = getattr(
-        flow_class, "_router_paths", {}
-    )
-
-    methods: list[MethodInfo] = []
-    all_method_names: set[str] = set()
-
-    for attr_name in dir(flow_class):
-        if attr_name.startswith("_"):
-            continue
-
-        try:
-            attr = getattr(flow_class, attr_name)
-        except AttributeError:
-            continue
-
-        is_flow_method = (
-            isinstance(attr, (FlowMethod, StartMethod, ListenMethod, RouterMethod))
-            or hasattr(attr, "__is_flow_method__")
-            or hasattr(attr, "__is_start_method__")
-            or hasattr(attr, "__trigger_methods__")
-            or hasattr(attr, "__is_router__")
-        )
-
-        if not is_flow_method:
-            continue
-
-        all_method_names.add(attr_name)
-
-        method_type = _get_method_type(attr_name, attr, start_methods, routers)
-
-        trigger_methods, condition_type = _extract_trigger_methods(attr)
-
-        router_paths_list: list[str] = []
-        if method_type in ("router", "start_router"):
-            router_paths_list = _extract_router_paths(attr, router_paths_registry)
-
-        has_hf = _has_human_feedback(attr)
-
-        has_crew = _detect_crew_reference(attr)
-
-        method_info = MethodInfo(
-            name=attr_name,
-            type=method_type,
-            trigger_methods=trigger_methods,
-            condition_type=condition_type,
-            router_paths=router_paths_list,
-            has_human_feedback=has_hf,
-            has_crew=has_crew,
-        )
-        methods.append(method_info)
-
-    edges = _generate_edges(listeners, routers, router_paths_registry, all_method_names)
-
-    state_schema = _extract_state_schema(flow_class)
-
-    inputs = _detect_flow_inputs(flow_class)
-
-    description: str | None = None
-    if flow_class.__doc__:
-        description = flow_class.__doc__.strip()
-
-    return FlowStructureInfo(
-        name=flow_class.__name__,
-        description=description,
-        methods=methods,
-        edges=edges,
-        state_schema=state_schema,
-        inputs=inputs,
-    )

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

@@ -16,7 +16,16 @@ P = ParamSpec("P")
 R = TypeVar("R")
 
 FlowConditionType: TypeAlias = Literal["OR", "AND"]
-SimpleFlowCondition: TypeAlias = tuple[FlowConditionType, list[FlowMethodName]]
+
+__all__ = [
+    "FlowCondition",
+    "FlowConditionType",
+    "FlowConditions",
+    "FlowMethod",
+    "ListenMethod",
+    "RouterMethod",
+    "StartMethod",
+]
 
 
 class FlowCondition(TypedDict, total=False):
@@ -26,16 +35,14 @@ class FlowCondition(TypedDict, total=False):
 
     Attributes:
         type: The type of the condition.
-        conditions: A list of conditions types.
-        methods: A list of methods.
+        conditions: A sequence of route labels, method names, or nested conditions.
     """
 
     type: Required[FlowConditionType]
-    conditions: Sequence[FlowMethodName | FlowCondition]
-    methods: list[FlowMethodName]
+    conditions: Sequence[str | FlowCondition]
 
 
-FlowConditions: TypeAlias = list[FlowMethodName | FlowCondition]
+FlowConditions: TypeAlias = Sequence[str | FlowCondition]
 
 
 class FlowMethod(Generic[P, R]):
@@ -72,10 +79,11 @@ class FlowMethod(Generic[P, R]):
 
         # Preserve flow-related attributes from wrapped method (e.g., from @human_feedback)
         for attr in [
-            "__is_router__",
-            "__router_paths__",
             "__human_feedback_config__",
-            "_hf_llm",  # Live LLM object for HITL resume
+            "__conversational_only__",  # gates registration on Flow.conversational
+            "__flow_persistence_config__",
+            "__flow_method_definition__",
+            "_human_feedback_llm",  # Live LLM object for HITL resume
         ]:
             if hasattr(meth, attr):
                 setattr(self, attr, getattr(meth, attr))
@@ -144,24 +152,10 @@ class FlowMethod(Generic[P, R]):
 class StartMethod(FlowMethod[P, R]):
     """Wrapper for methods marked as flow start points."""
 
-    __is_start_method__: bool = True
-    __trigger_methods__: list[FlowMethodName] | None = None
-    __condition_type__: FlowConditionType | None = None
-    __trigger_condition__: FlowCondition | None = None
-
 
 class ListenMethod(FlowMethod[P, R]):
     """Wrapper for methods marked as flow listeners."""
 
-    __trigger_methods__: list[FlowMethodName] | None = None
-    __condition_type__: FlowConditionType | None = None
-    __trigger_condition__: FlowCondition | None = None
-
 
 class RouterMethod(FlowMethod[P, R]):
     """Wrapper for methods marked as flow routers."""
-
-    __is_router__: bool = True
-    __trigger_methods__: list[FlowMethodName] | None = None
-    __condition_type__: FlowConditionType | None = None
-    __trigger_condition__: FlowCondition | None = None

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

@@ -78,14 +78,10 @@ logger = logging.getLogger(__name__)
 
 F = TypeVar("F", bound=Callable[..., Any])
 
+__all__ = ["HumanFeedbackResult", "human_feedback"]
+
 
 def _serialize_llm_for_context(llm: Any) -> dict[str, Any] | str | None:
-    """Serialize a BaseLLM object to a dict preserving full config.
-
-    Delegates to ``llm.to_config_dict()`` when available (BaseLLM and
-    subclasses). Falls back to extracting the model string with provider
-    prefix for unknown LLM types.
-    """
     to_config: Callable[[], dict[str, Any]] | None = getattr(
         llm, "to_config_dict", None
     )
@@ -103,13 +99,6 @@ def _serialize_llm_for_context(llm: Any) -> dict[str, Any] | str | None:
 def _deserialize_llm_from_context(
     llm_data: dict[str, Any] | str | None,
 ) -> BaseLLM | None:
-    """Reconstruct an LLM instance from serialized context data.
-
-    Handles both the new dict format (with full config) and the legacy
-    string format (model name only) for backward compatibility.
-
-    Returns a BaseLLM instance, or None if llm_data is None.
-    """
     if llm_data is None:
         return None
 
@@ -198,16 +187,12 @@ class HumanFeedbackMethod(FlowMethod[Any, Any]):
     """Wrapper for methods decorated with @human_feedback.
 
     This wrapper extends FlowMethod to add human feedback specific attributes
-    that are used by FlowMeta for routing and by visualization tools.
+    used by the FlowDefinition builder and runtime feedback handling.
 
     Attributes:
-        __is_router__: True when emit is specified, enabling router behavior.
-        __router_paths__: List of possible outcomes when acting as a router.
         __human_feedback_config__: The HumanFeedbackConfig for this method.
     """
 
-    __is_router__: bool = False
-    __router_paths__: list[str] | None = None
     __human_feedback_config__: HumanFeedbackConfig | None = None
 
 
@@ -232,7 +217,7 @@ class DistilledLessons(BaseModel):
     )
 
 
-def human_feedback(
+def _build_human_feedback_runtime_decorator(
     message: str,
     emit: Sequence[str] | None = None,
     llm: str | BaseLLM | None = "gpt-4o-mini",
@@ -243,102 +228,6 @@ def human_feedback(
     learn_source: str = "hitl",
     learn_strict: bool = False,
 ) -> Callable[[F], F]:
-    """Decorator for Flow methods that require human feedback.
-
-    This decorator wraps a Flow method to:
-    1. Execute the method and capture its output
-    2. Display the output to the human with a feedback request
-    3. Collect the human's free-form feedback
-    4. Optionally collapse the feedback to a predefined outcome using an LLM
-    5. Store the result for access by downstream methods
-
-    When `emit` is specified, the decorator acts as a router, and the
-    collapsed outcome triggers the appropriate @listen decorated method.
-
-    Supports both synchronous (blocking) and asynchronous (non-blocking)
-    feedback collection through the `provider` parameter. If no provider
-    is specified, defaults to synchronous console input.
-
-    Args:
-        message: The message shown to the human when requesting feedback.
-            This should clearly explain what kind of feedback is expected.
-        emit: Optional sequence of outcome strings. When provided, the
-            human's feedback will be collapsed to one of these outcomes
-            using the specified LLM. The outcome then triggers @listen
-            methods that match.
-        llm: The LLM model to use for collapsing feedback to outcomes.
-            Required when emit is specified. Can be a model string
-            like "gpt-4o-mini" or a BaseLLM instance.
-        default_outcome: The outcome to use when the human provides no
-            feedback (empty input). Must be one of the emit values
-            if emit is specified.
-        metadata: Optional metadata for enterprise integrations. This is
-            passed through to the HumanFeedbackResult and can be used
-            by enterprise forks for features like Slack/Teams integration.
-        provider: Optional HumanFeedbackProvider for custom feedback
-            collection. Use this for async workflows that integrate with
-            external systems like Slack, Teams, or webhooks. When the
-            provider raises HumanFeedbackPending, the flow pauses and
-            can be resumed later with Flow.resume().
-        learn: Enable HITL learning. Recall past lessons to pre-review
-            output before the human sees it, and distill new lessons
-            from feedback after.
-        learn_source: Memory source tag for stored/recalled lessons.
-        learn_strict: When True, re-raise exceptions from the pre-review
-            and distillation steps instead of falling back to raw output.
-            Default False preserves graceful degradation; failures are
-            always logged via ``logger.warning`` regardless of this flag.
-
-    Returns:
-        A decorator function that wraps the method with human feedback
-        collection logic.
-
-    Raises:
-        ValueError: If emit is specified but llm is not provided.
-        ValueError: If default_outcome is specified but emit is not.
-        ValueError: If default_outcome is not in the emit list.
-        HumanFeedbackPending: When an async provider pauses execution.
-
-    Example:
-        Basic feedback without routing:
-        ```python
-        @start()
-        @human_feedback(message="Please review this output:")
-        def generate_content(self):
-            return "Generated content..."
-        ```
-
-        With routing based on feedback:
-        ```python
-        @start()
-        @human_feedback(
-            message="Review and approve or reject:",
-            emit=["approved", "rejected", "needs_revision"],
-            llm="gpt-4o-mini",
-            default_outcome="needs_revision",
-        )
-        def review_document(self):
-            return document_content
-
-
-        @listen("approved")
-        def publish(self):
-            print(f"Publishing: {self.last_human_feedback.output}")
-        ```
-
-        Async feedback with custom provider:
-        ```python
-        @start()
-        @human_feedback(
-            message="Review this content:",
-            emit=["approved", "rejected"],
-            llm="gpt-4o-mini",
-            provider=SlackProvider(channel="#reviews"),
-        )
-        def generate_content(self):
-            return "Content to review..."
-        ```
-    """
     if emit is not None:
         if not llm:
             raise ValueError(
@@ -356,20 +245,12 @@ def human_feedback(
         raise ValueError("default_outcome requires emit to be specified.")
 
     def decorator(func: F) -> F:
-        """Inner decorator that wraps the function."""
-
         def _get_hitl_prompt(key: str) -> str:
-            """Read a HITL prompt from the i18n translations."""
             from crewai.utilities.i18n import I18N_DEFAULT
 
             return I18N_DEFAULT.slice(key)
 
         def _resolve_llm_instance() -> Any:
-            """Resolve the ``llm`` parameter to a BaseLLM instance.
-
-            Uses the SAME model specified in the decorator so pre-review,
-            distillation, and outcome collapsing all share one model.
-            """
             if llm is None:
                 from crewai.llm import LLM
 
@@ -383,7 +264,6 @@ def human_feedback(
         def _pre_review_with_lessons(
             flow_instance: Flow[Any], method_output: Any
         ) -> Any:
-            """Recall past HITL lessons and use LLM to pre-review the output."""
             try:
                 mem = flow_instance.memory
                 if mem is None:
@@ -431,7 +311,6 @@ def human_feedback(
         def _distill_and_store_lessons(
             flow_instance: Flow[Any], method_output: Any, raw_feedback: str
         ) -> None:
-            """Extract generalizable lessons from output + feedback, store in memory."""
             try:
                 mem = flow_instance.memory
                 if mem is None:
@@ -485,7 +364,6 @@ def human_feedback(
         def _build_feedback_context(
             flow_instance: Flow[Any], method_output: Any
         ) -> tuple[Any, Any]:
-            """Build the PendingFeedbackContext and resolve the effective provider."""
             from crewai.flow.async_feedback.types import PendingFeedbackContext
 
             context = PendingFeedbackContext(
@@ -509,7 +387,6 @@ def human_feedback(
             return context, effective_provider
 
         def _request_feedback(flow_instance: Flow[Any], method_output: Any) -> str:
-            """Request feedback using provider or default console (sync)."""
             context, effective_provider = _build_feedback_context(
                 flow_instance, method_output
             )
@@ -535,7 +412,6 @@ def human_feedback(
         async def _request_feedback_async(
             flow_instance: Flow[Any], method_output: Any
         ) -> str:
-            """Request feedback, awaiting the provider if it returns a coroutine."""
             context, effective_provider = _build_feedback_context(
                 flow_instance, method_output
             )
@@ -559,7 +435,6 @@ def human_feedback(
             method_output: Any,
             raw_feedback: str,
         ) -> HumanFeedbackResult | str:
-            """Process feedback and return result or outcome."""
             collapsed_outcome: str | None = None
 
             if not raw_feedback.strip():
@@ -655,42 +530,33 @@ def human_feedback(
 
             wrapper = sync_wrapper
 
-        for attr in [
-            "__is_start_method__",
-            "__trigger_methods__",
-            "__condition_type__",
-            "__trigger_condition__",
-            "__is_flow_method__",
-        ]:
-            if hasattr(func, attr):
-                setattr(wrapper, attr, getattr(func, attr))
-
-        # Create config inline to avoid race conditions
-        wrapper.__human_feedback_config__ = HumanFeedbackConfig(
-            message=message,
-            emit=emit,
-            llm=llm,
-            default_outcome=default_outcome,
-            metadata=metadata,
-            provider=provider,
-            learn=learn,
-            learn_source=learn_source,
-            learn_strict=learn_strict,
-        )
-        wrapper.__is_flow_method__ = True
-
-        if emit:
-            wrapper.__is_router__ = True
-            wrapper.__router_paths__ = list(emit)
-
-        # Stash the live LLM object for HITL resume to retrieve.
-        # When a flow pauses for human feedback and later resumes (possibly in a
-        # different process), the serialized context only contains a model string.
-        # By storing the original LLM on the wrapper, resume_async can retrieve
-        # the fully-configured LLM (with credentials, project, safety_settings, etc.)
-        # instead of creating a bare LLM from just the model string.
-        wrapper._hf_llm = llm
-
         return wrapper  # type: ignore[no-any-return]
 
     return decorator
+
+
+def human_feedback(
+    message: str,
+    emit: Sequence[str] | None = None,
+    llm: str | BaseLLM | None = "gpt-4o-mini",
+    default_outcome: str | None = None,
+    metadata: dict[str, Any] | None = None,
+    provider: HumanFeedbackProvider | None = None,
+    learn: bool = False,
+    learn_source: str = "hitl",
+    learn_strict: bool = False,
+) -> Callable[[F], F]:
+    """Compatibility import path for the Flow human-feedback DSL decorator."""
+    from crewai.flow.dsl._human_feedback import human_feedback as dsl_human_feedback
+
+    return dsl_human_feedback(
+        message=message,
+        emit=emit,
+        llm=llm,
+        default_outcome=default_outcome,
+        metadata=metadata,
+        provider=provider,
+        learn=learn,
+        learn_source=learn_source,
+        learn_strict=learn_strict,
+    )

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

@@ -4,16 +4,9 @@ CrewAI Flow Persistence.
 This module provides interfaces and implementations for persisting flow states.
 """
 
-from typing import Any, TypeVar
-
-from pydantic import BaseModel
-
 from crewai.flow.persistence.base import FlowPersistence
 from crewai.flow.persistence.decorators import persist
 from crewai.flow.persistence.sqlite import SQLiteFlowPersistence
 
 
 __all__ = ["FlowPersistence", "SQLiteFlowPersistence", "persist"]
-
-StateType = TypeVar("StateType", bound=dict[str, Any] | BaseModel)
-DictStateType = dict[str, Any]

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

@@ -28,13 +28,14 @@ import asyncio
 from collections.abc import Callable
 import functools
 import logging
+from types import SimpleNamespace
 from typing import TYPE_CHECKING, Any, Final, TypeVar, cast
 
 from crewai_core.printer import PRINTER
 from pydantic import BaseModel
 
 from crewai.flow.persistence.base import FlowPersistence
-from crewai.flow.persistence.sqlite import SQLiteFlowPersistence
+from crewai.flow.persistence.factory import default_flow_persistence
 
 
 if TYPE_CHECKING:
@@ -44,6 +45,8 @@ if TYPE_CHECKING:
 logger = logging.getLogger(__name__)
 T = TypeVar("T")
 
+__all__ = ["PersistenceDecorator", "persist"]
+
 LOG_MESSAGES: Final[dict[str, str]] = {
     "save_state": "Saving flow state to memory for ID: {}",
     "save_error": "Failed to persist state for method {}: {}",
@@ -52,6 +55,25 @@ LOG_MESSAGES: Final[dict[str, str]] = {
 }
 
 
+def _stamp_persistence_metadata(
+    target: Any,
+    persistence: FlowPersistence,
+    verbose: bool,
+) -> None:
+    target.__flow_persistence_config__ = SimpleNamespace(
+        persistence=persistence,
+        verbose=verbose,
+    )
+
+
+_PRESERVED_FLOW_ATTRS: Final[tuple[str, ...]] = (
+    "__human_feedback_config__",
+    "__flow_persistence_config__",
+    "__flow_method_definition__",
+    "_human_feedback_llm",
+)
+
+
 class PersistenceDecorator:
     """Class to handle flow state persistence with consistent logging."""
 
@@ -144,7 +166,9 @@ def persist(
 
     Args:
         persistence: Optional FlowPersistence implementation to use.
-                    If not provided, uses SQLiteFlowPersistence.
+                    If not provided, uses ``default_flow_persistence()`` (the
+                    registered factory when present, else the built-in SQLite
+                    fallback).
         verbose: Whether to log persistence operations. Defaults to False.
 
     Returns:
@@ -163,10 +187,12 @@ def persist(
     """
 
     def decorator(target: type | Callable[..., T]) -> type | Callable[..., T]:
-        """Decorator that handles both class and method decoration."""
-        actual_persistence = persistence or SQLiteFlowPersistence()
+        actual_persistence = (
+            persistence if persistence is not None else default_flow_persistence()
+        )
 
         if isinstance(target, type):
+            _stamp_persistence_metadata(target, actual_persistence, verbose)
             original_init = target.__init__  # type: ignore[misc]
 
             @functools.wraps(original_init)
@@ -183,11 +209,8 @@ def persist(
                 for name, method in target.__dict__.items()
                 if callable(method)
                 and (
-                    hasattr(method, "__is_start_method__")
-                    or hasattr(method, "__trigger_methods__")
-                    or hasattr(method, "__condition_type__")
-                    or hasattr(method, "__is_flow_method__")
-                    or hasattr(method, "__is_router__")
+                    hasattr(method, "__is_flow_method__")
+                    or hasattr(method, "__flow_method_definition__")
                 )
             }
 
@@ -211,12 +234,7 @@ def persist(
 
                     wrapped = create_async_wrapper(name, method)
 
-                    for attr in [
-                        "__is_start_method__",
-                        "__trigger_methods__",
-                        "__condition_type__",
-                        "__is_router__",
-                    ]:
+                    for attr in _PRESERVED_FLOW_ATTRS:
                         if hasattr(method, attr):
                             setattr(wrapped, attr, getattr(method, attr))
                     wrapped.__is_flow_method__ = True  # type: ignore[attr-defined]
@@ -239,12 +257,7 @@ def persist(
 
                     wrapped = create_sync_wrapper(name, method)
 
-                    for attr in [
-                        "__is_start_method__",
-                        "__trigger_methods__",
-                        "__condition_type__",
-                        "__is_router__",
-                    ]:
+                    for attr in _PRESERVED_FLOW_ATTRS:
                         if hasattr(method, attr):
                             setattr(wrapped, attr, getattr(method, attr))
                     wrapped.__is_flow_method__ = True  # type: ignore[attr-defined]
@@ -254,6 +267,7 @@ def persist(
             return target
         method = target
         method.__is_flow_method__ = True  # type: ignore[attr-defined]
+        _stamp_persistence_metadata(method, actual_persistence, verbose)
 
         if asyncio.iscoroutinefunction(method):
 
@@ -271,15 +285,13 @@ def persist(
                 )
                 return cast(T, result)
 
-            for attr in [
-                "__is_start_method__",
-                "__trigger_methods__",
-                "__condition_type__",
-                "__is_router__",
-            ]:
+            for attr in _PRESERVED_FLOW_ATTRS:
                 if hasattr(method, attr):
                     setattr(method_async_wrapper, attr, getattr(method, attr))
             method_async_wrapper.__is_flow_method__ = True  # type: ignore[attr-defined]
+            _stamp_persistence_metadata(
+                method_async_wrapper, actual_persistence, verbose
+            )
             return cast(Callable[..., T], method_async_wrapper)
 
         @functools.wraps(method)
@@ -290,15 +302,11 @@ def persist(
             )
             return result
 
-        for attr in [
-            "__is_start_method__",
-            "__trigger_methods__",
-            "__condition_type__",
-            "__is_router__",
-        ]:
+        for attr in _PRESERVED_FLOW_ATTRS:
             if hasattr(method, attr):
                 setattr(method_sync_wrapper, attr, getattr(method, attr))
         method_sync_wrapper.__is_flow_method__ = True  # type: ignore[attr-defined]
+        _stamp_persistence_metadata(method_sync_wrapper, actual_persistence, verbose)
         return cast(Callable[..., T], method_sync_wrapper)
 
     return decorator

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

@@ -0,0 +1,60 @@
+"""Pluggable default persistence backend for flows.
+
+By default, ``@persist`` and the flow runtime persist state with
+:class:`~crewai.flow.persistence.sqlite.SQLiteFlowPersistence` when no explicit
+``persistence=`` is given. Registering a factory via
+:func:`set_flow_persistence_factory` lets an application back flow state with a
+custom :class:`~crewai.flow.persistence.base.FlowPersistence` -- a database, a
+remote service, an in-memory fake for tests -- without passing a
+``persistence=`` instance at every ``@persist`` / kickoff site.
+
+This mirrors :func:`crewai_core.lock_store.set_lock_backend`: a one-time,
+process-wide setter intended for application startup. Pass ``None`` to restore
+the built-in SQLite default. Call :func:`default_flow_persistence` to build the
+default backend (the registered factory if any, else SQLite).
+"""
+
+from __future__ import annotations
+
+from collections.abc import Callable
+from typing import TYPE_CHECKING
+
+
+if TYPE_CHECKING:
+    from crewai.flow.persistence.base import FlowPersistence
+
+FlowPersistenceFactory = Callable[[], "FlowPersistence"]
+
+_factory: FlowPersistenceFactory | None = None
+
+
+def set_flow_persistence_factory(factory: FlowPersistenceFactory | None) -> None:
+    """Replace the process-wide default flow persistence factory.
+
+    Intended for one-time setup at startup. Pass ``None`` to restore the
+    built-in ``SQLiteFlowPersistence``. Only affects flows that fall back to
+    the default; an explicit ``persistence=`` instance always wins.
+
+    The default is resolved at each fall-back site (``@persist`` and the
+    runtime's pause/resume paths), so the factory may be called more than once
+    for a single flow. Return instances backed by shared durable state (or a
+    singleton) so state saved on one call is visible to the next -- the
+    built-in SQLite default satisfies this by sharing one on-disk file.
+    """
+    global _factory
+    _factory = factory
+
+
+def default_flow_persistence() -> FlowPersistence:
+    """Build the default flow persistence backend.
+
+    Returns the result of the registered factory if one is set, otherwise a
+    built-in :class:`~crewai.flow.persistence.sqlite.SQLiteFlowPersistence`.
+    """
+    factory = _factory
+    if factory is not None:
+        return factory()
+
+    from crewai.flow.persistence.sqlite import SQLiteFlowPersistence
+
+    return SQLiteFlowPersistence()

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

@@ -5,15 +5,7 @@ the Flow system.
 """
 
 from datetime import datetime
-from typing import (
-    Annotated,
-    Any,
-    NewType,
-    ParamSpec,
-    Protocol,
-    TypeVar,
-    TypedDict,
-)
+from typing import Annotated, Any, NewType, ParamSpec, Protocol, TypeVar, TypedDict
 
 from typing_extensions import NotRequired, Required
 
@@ -22,7 +14,6 @@ P = ParamSpec("P")
 R = TypeVar("R", covariant=True)
 
 FlowMethodName = NewType("FlowMethodName", str)
-FlowRouteName = NewType("FlowRouteName", str)
 PendingListenerKey = NewType(
     "PendingListenerKey",
     Annotated[str, "nested flow conditions use 'listener_name:object_id'"],
@@ -32,7 +23,7 @@ PendingListenerKey = NewType(
 class FlowMethodCallable(Protocol[P, R]):
     """A callable that can be used as a flow method reference."""
 
-    __name__: FlowMethodName
+    __name__: str
 
     def __call__(self, *args: P.args, **kwargs: P.kwargs) -> R: ...
 

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

@@ -1,53 +0,0 @@
-"""Backwards-compatible shim. The implementation moved to ``crewai.flow.flow_definition``.
-
-Import from ``crewai.flow.flow_definition`` directly in new code.
-"""
-
-from crewai.flow.flow_definition import (
-    _extract_all_methods,
-    _extract_all_methods_recursive,
-    _extract_string_literals_from_type_annotation,
-    _normalize_condition,
-    _unwrap_function,
-    build_ancestor_dict,
-    build_parent_children_dict,
-    calculate_node_levels,
-    count_outgoing_edges,
-    dfs_ancestors,
-    extract_flow_definition,
-    get_child_index,
-    get_possible_return_constants,
-    is_ancestor,
-    is_flow_condition_dict,
-    is_flow_condition_list,
-    is_flow_method,
-    is_flow_method_callable,
-    is_flow_method_name,
-    is_simple_flow_condition,
-    process_router_paths,
-)
-
-
-__all__ = [
-    "_extract_all_methods",
-    "_extract_all_methods_recursive",
-    "_extract_string_literals_from_type_annotation",
-    "_normalize_condition",
-    "_unwrap_function",
-    "build_ancestor_dict",
-    "build_parent_children_dict",
-    "calculate_node_levels",
-    "count_outgoing_edges",
-    "dfs_ancestors",
-    "extract_flow_definition",
-    "get_child_index",
-    "get_possible_return_constants",
-    "is_ancestor",
-    "is_flow_condition_dict",
-    "is_flow_condition_list",
-    "is_flow_method",
-    "is_flow_method_callable",
-    "is_flow_method_name",
-    "is_simple_flow_condition",
-    "process_router_paths",
-]

lib/crewai/src/crewai/flow/visualization/assets/interactive.js

@@ -684,7 +684,7 @@ class TriggeredByHighlighter {
         });
       } else {
         for (const [nodeName, nodeInfo] of Object.entries(nodeData)) {
-          if (nodeInfo.router_paths && nodeInfo.router_paths.includes(triggerNodeId)) {
+          if (nodeInfo.router_events && nodeInfo.router_events.includes(triggerNodeId)) {
             const routerNode = nodeName;
 
             const routerEdges = allEdges.filter(
@@ -768,7 +768,7 @@ class TriggeredByHighlighter {
     this.animateEdgeStyles();
   }
 
-  highlightAllRouterPaths() {
+  highlightAllRouterEvents() {
     this.clear();
 
     if (!this.activeDrawerNodeId) {
@@ -792,10 +792,10 @@ class TriggeredByHighlighter {
       routerEdges.forEach(edge => {
         pathNodes.add(edge.to);
       });
-    } else if (activeMetadata && activeMetadata.router_paths && activeMetadata.router_paths.length > 0) {
-      activeMetadata.router_paths.forEach(pathName => {
+    } else if (activeMetadata && activeMetadata.router_events && activeMetadata.router_events.length > 0) {
+      activeMetadata.router_events.forEach(eventName => {
         for (const [nodeName, nodeInfo] of Object.entries(nodeData)) {
-          if (nodeInfo.router_paths && nodeInfo.router_paths.includes(pathName)) {
+          if (nodeInfo.router_events && nodeInfo.router_events.includes(eventName)) {
             const edgeFromRouter = allEdges.filter(
               (edge) => edge.from === nodeName && edge.to === this.activeDrawerNodeId && edge.dashes
             );
@@ -821,6 +821,42 @@ class TriggeredByHighlighter {
     this.animateEdgeStyles();
   }
 
+  highlightRouterEvent(eventName) {
+    this.clear();
+
+    if (this.activeDrawerEdges && this.activeDrawerEdges.length > 0) {
+      this.resetEdgesToDefault(this.activeDrawerEdges);
+      this.activeDrawerEdges = [];
+    }
+
+    if (!this.activeDrawerNodeId || !eventName) {
+      return;
+    }
+
+    const routerEdges = this.edges.get().filter(
+      (edge) =>
+        edge.from === this.activeDrawerNodeId &&
+        edge.dashes &&
+        edge.label === eventName,
+    );
+
+    if (routerEdges.length === 0) {
+      return;
+    }
+
+    const pathNodes = new Set([this.activeDrawerNodeId]);
+    routerEdges.forEach((edge) => {
+      pathNodes.add(edge.from);
+      pathNodes.add(edge.to);
+    });
+
+    this.highlightedNodes = Array.from(pathNodes);
+    this.highlightedEdges = routerEdges.map((e) => e.id);
+
+    this.animateNodeOpacity();
+    this.animateEdgeStyles();
+  }
+
   highlightTriggeredBy(triggerNodeId) {
     this.clear();
 
@@ -892,8 +928,8 @@ class TriggeredByHighlighter {
       ) {
         for (const [nodeName, nodeInfo] of Object.entries(nodeData)) {
           if (
-            nodeInfo.router_paths &&
-            nodeInfo.router_paths.includes(triggerNodeId)
+            nodeInfo.router_events &&
+            nodeInfo.router_events.includes(triggerNodeId)
           ) {
             const routerNode = nodeName;
 
@@ -1501,7 +1537,7 @@ class DrawerManager {
     const activeMetadata = nodeData[activeNodeId];
     if (activeMetadata && activeMetadata.trigger_methods && activeMetadata.trigger_methods.includes(triggerNodeId)) {
       for (const [nodeName, nodeInfo] of Object.entries(nodeData)) {
-        if (nodeInfo.router_paths && nodeInfo.router_paths.includes(triggerNodeId)) {
+        if (nodeInfo.router_events && nodeInfo.router_events.includes(triggerNodeId)) {
           const routerEdges = allEdges.filter(
             (edge) => edge.from === nodeName && edge.dashes
           );
@@ -1660,16 +1696,16 @@ class DrawerManager {
             `;
     }
 
-    if (metadata.router_paths && metadata.router_paths.length > 0) {
-      const uniqueRouterPaths = [...new Set(metadata.router_paths)];
-      const routerPathsJson = JSON.stringify(uniqueRouterPaths).replace(/"/g, '"');
+    if (metadata.router_events && metadata.router_events.length > 0) {
+      const uniqueRouterEvents = [...new Set(metadata.router_events)];
+      const routerEventsJson = JSON.stringify(uniqueRouterEvents).replace(/"/g, '"');
       metadataContent += `
                 <div class="drawer-section">
-                    <div class="drawer-section-title router-paths-title" data-router-paths="${routerPathsJson}" style="cursor: pointer; display: inline-flex; align-items: center; gap: 4px;">
-                        Router Paths <i data-lucide="chevron-down" style="width: 14px; height: 14px; color: var(--text-primary);"></i>
+                    <div class="drawer-section-title router-events-title" data-router-events="${routerEventsJson}" style="cursor: pointer; display: inline-flex; align-items: center; gap: 4px;">
+                        Router Events <i data-lucide="chevron-down" style="width: 14px; height: 14px; color: var(--text-primary);"></i>
                     </div>
                     <ul class="drawer-list">
-                        ${uniqueRouterPaths.map((p) => `<li><span class="drawer-code-link" data-node-id="${p}" style="color: {{ CREWAI_ORANGE }}; border-color: rgba(255,90,80,0.3);">${p}</span></li>`).join("")}
+                        ${uniqueRouterEvents.map((eventName) => `<li><span class="drawer-code-link" data-router-event="${eventName}" style="color: {{ CREWAI_ORANGE }}; border-color: rgba(255,90,80,0.3);">${eventName}</span></li>`).join("")}
                     </ul>
                 </div>
             `;
@@ -1823,14 +1859,26 @@ class DrawerManager {
       });
     });
 
-    const routerPathsTitle = this.elements.content.querySelector(
-      ".router-paths-title[data-router-paths]",
+    const routerEventLinks = this.elements.content.querySelectorAll(
+      ".drawer-code-link[data-router-event]",
     );
-    if (routerPathsTitle) {
-      routerPathsTitle.addEventListener("click", (e) => {
+    routerEventLinks.forEach((link) => {
+      link.addEventListener("click", (e) => {
         e.preventDefault();
         e.stopPropagation();
-        this.triggeredByHighlighter.highlightAllRouterPaths();
+        const routerEvent = link.getAttribute("data-router-event");
+        this.triggeredByHighlighter.highlightRouterEvent(routerEvent);
+      });
+    });
+
+    const routerEventsTitle = this.elements.content.querySelector(
+      ".router-events-title[data-router-events]",
+    );
+    if (routerEventsTitle) {
+      routerEventsTitle.addEventListener("click", (e) => {
+        e.preventDefault();
+        e.stopPropagation();
+        this.triggeredByHighlighter.highlightAllRouterEvents();
       });
     }
   }

lib/crewai/src/crewai/flow/visualization/builder.py

@@ -1,131 +1,118 @@
-"""Flow structure builder for analyzing Flow execution."""
+"""Flow structure builder for definition-only Flow visualization."""
 
 from __future__ import annotations
 
 from collections import defaultdict
-import inspect
 import logging
-from typing import TYPE_CHECKING, Any
+from typing import TYPE_CHECKING, Any, cast
 
 from crewai.flow.constants import AND_CONDITION, OR_CONDITION
-from crewai.flow.flow_wrappers import FlowCondition
-from crewai.flow.types import FlowMethodName
-from crewai.flow.utils import (
-    is_flow_condition_dict,
-    is_simple_flow_condition,
+from crewai.flow.flow_definition import (
+    FlowDefinition,
+    FlowDefinitionCondition,
+    FlowMethodDefinition,
 )
-from crewai.flow.visualization.schema import extract_method_signature
 from crewai.flow.visualization.types import FlowStructure, NodeMetadata, StructureEdge
 
 
 logger = logging.getLogger(__name__)
 
+__all__ = ["build_flow_structure", "calculate_execution_paths"]
+
 
 if TYPE_CHECKING:
     from crewai.flow.flow import Flow
 
 
+def _definition_condition_items(
+    condition: dict[str, Any],
+    key: str,
+) -> list[FlowDefinitionCondition]:
+    return cast(list[FlowDefinitionCondition], condition.get(key, []))
+
+
+def _definition_condition_parts(
+    condition: dict[str, Any],
+) -> tuple[str, list[FlowDefinitionCondition]]:
+    if "and" in condition:
+        return AND_CONDITION, _definition_condition_items(condition, "and")
+    return OR_CONDITION, _definition_condition_items(condition, "or")
+
+
+def _condition_type_from_definition(
+    condition: FlowDefinitionCondition | None,
+) -> str | None:
+    if isinstance(condition, dict):
+        if "and" in condition:
+            return AND_CONDITION
+        if "or" in condition:
+            return OR_CONDITION
+    if isinstance(condition, str):
+        return OR_CONDITION
+    return None
+
+
+def _runtime_condition_from_definition(
+    condition: FlowDefinitionCondition,
+) -> str | dict[str, Any]:
+    if isinstance(condition, str):
+        return condition
+    condition_type, conditions = _definition_condition_parts(condition)
+    return {
+        "type": condition_type,
+        "conditions": [_runtime_condition_from_definition(item) for item in conditions],
+    }
+
+
+def _method_trigger_condition(
+    method_definition: FlowMethodDefinition,
+) -> FlowDefinitionCondition | None:
+    if method_definition.listen is not None:
+        return method_definition.listen
+    if isinstance(method_definition.start, str | dict):
+        return method_definition.start
+    return None
+
+
+def _method_router_events(method_definition: FlowMethodDefinition) -> list[str]:
+    if method_definition.human_feedback and method_definition.human_feedback.emit:
+        return [str(event) for event in method_definition.human_feedback.emit]
+    if method_definition.emit:
+        return [str(event) for event in method_definition.emit]
+    return []
+
+
 def _extract_direct_or_triggers(
-    condition: str | dict[str, Any] | list[Any] | FlowCondition,
+    condition: FlowDefinitionCondition,
 ) -> list[str]:
-    """Extract direct OR-level trigger strings from a condition.
-
-    This function extracts strings that would directly trigger a listener,
-    meaning they appear at the top level of an OR condition. Strings nested
-    inside AND conditions are NOT considered direct triggers for router paths.
-
-    For example:
-    - or_("a", "b") -> ["a", "b"] (both are direct triggers)
-    - and_("a", "b") -> [] (neither are direct triggers, both required)
-    - or_(and_("a", "b"), "c") -> ["c"] (only "c" is a direct trigger)
-
-    Args:
-        condition: Can be a string, dict, or list.
-
-    Returns:
-        List of direct OR-level trigger strings.
-    """
     if isinstance(condition, str):
         return [condition]
-    if isinstance(condition, dict):
-        cond_type = condition.get("type", OR_CONDITION)
-        conditions_list = condition.get("conditions", [])
-
-        if cond_type == OR_CONDITION:
-            strings = []
-            for sub_cond in conditions_list:
-                strings.extend(_extract_direct_or_triggers(sub_cond))
-            return strings
+    condition_type, conditions = _definition_condition_parts(condition)
+    if condition_type == AND_CONDITION:
         return []
-    if isinstance(condition, list):
-        strings = []
-        for item in condition:
-            strings.extend(_extract_direct_or_triggers(item))
-        return strings
-    if callable(condition) and hasattr(condition, "__name__"):
-        return [condition.__name__]
-    return []
+    strings: list[str] = []
+    for sub_condition in conditions:
+        strings.extend(_extract_direct_or_triggers(sub_condition))
+    return strings
 
 
 def _extract_all_trigger_names(
-    condition: str | dict[str, Any] | list[Any] | FlowCondition,
+    condition: FlowDefinitionCondition,
 ) -> list[str]:
-    """Extract ALL trigger names from a condition for display purposes.
-
-    Unlike _extract_direct_or_triggers, this extracts ALL strings and method
-    names from the entire condition tree, including those nested in AND conditions.
-    This is used for displaying trigger information in the UI.
-
-    For example:
-    - or_("a", "b") -> ["a", "b"]
-    - and_("a", "b") -> ["a", "b"]
-    - or_(and_("a", method_6), method_4) -> ["a", "method_6", "method_4"]
-
-    Args:
-        condition: Can be a string, dict, or list.
-
-    Returns:
-        List of all trigger names found in the condition.
-    """
     if isinstance(condition, str):
         return [condition]
-    if isinstance(condition, dict):
-        conditions_list = condition.get("conditions", [])
-        strings = []
-        for sub_cond in conditions_list:
-            strings.extend(_extract_all_trigger_names(sub_cond))
-        return strings
-    if isinstance(condition, list):
-        strings = []
-        for item in condition:
-            strings.extend(_extract_all_trigger_names(item))
-        return strings
-    if callable(condition) and hasattr(condition, "__name__"):
-        return [condition.__name__]
-    return []
+    _, conditions = _definition_condition_parts(condition)
+    strings: list[str] = []
+    for sub_condition in conditions:
+        strings.extend(_extract_all_trigger_names(sub_condition))
+    return strings
 
 
 def _create_edges_from_condition(
-    condition: str | dict[str, Any] | list[Any] | FlowCondition,
+    condition: FlowDefinitionCondition,
     target: str,
     nodes: dict[str, NodeMetadata],
 ) -> list[StructureEdge]:
-    """Create edges from a condition tree, preserving AND/OR semantics.
-
-    This function recursively processes the condition tree and creates edges
-    with the appropriate condition_type for each trigger.
-
-    For AND conditions, all triggers get edges with condition_type="AND".
-    For OR conditions, triggers get edges with condition_type="OR".
-
-    Args:
-        condition: The condition tree (string, dict, or list).
-        target: The target node name.
-        nodes: Dictionary of all nodes for validation.
-
-    Returns:
-        List of StructureEdge objects representing the condition.
-    """
     edges: list[StructureEdge] = []
 
     if isinstance(condition, str):
@@ -135,24 +122,11 @@ def _create_edges_from_condition(
                     source=condition,
                     target=target,
                     condition_type=OR_CONDITION,
-                    is_router_path=False,
-                )
-            )
-    elif callable(condition) and hasattr(condition, "__name__"):
-        method_name = condition.__name__
-        if method_name in nodes:
-            edges.append(
-                StructureEdge(
-                    source=method_name,
-                    target=target,
-                    condition_type=OR_CONDITION,
-                    is_router_path=False,
+                    is_router_event=False,
                 )
             )
     elif isinstance(condition, dict):
-        cond_type = condition.get("type", OR_CONDITION)
-        conditions_list = condition.get("conditions", [])
-
+        cond_type, conditions = _definition_condition_parts(condition)
         if cond_type == AND_CONDITION:
             triggers = _extract_all_trigger_names(condition)
             edges.extend(
@@ -160,277 +134,144 @@ def _create_edges_from_condition(
                     source=trigger,
                     target=target,
                     condition_type=AND_CONDITION,
-                    is_router_path=False,
+                    is_router_event=False,
                 )
                 for trigger in triggers
                 if trigger in nodes
             )
         else:
-            for sub_cond in conditions_list:
-                edges.extend(_create_edges_from_condition(sub_cond, target, nodes))
-    elif isinstance(condition, list):
-        for item in condition:
-            edges.extend(_create_edges_from_condition(item, target, nodes))
+            for sub_condition in conditions:
+                edges.extend(_create_edges_from_condition(sub_condition, target, nodes))
 
     return edges
 
 
-def build_flow_structure(flow: Flow[Any]) -> FlowStructure:
-    """Build a structure representation of a Flow's execution.
+def _flow_definition_from(
+    flow_or_definition: Flow[Any] | type[Flow[Any]] | FlowDefinition,
+) -> FlowDefinition:
+    if isinstance(flow_or_definition, FlowDefinition):
+        return flow_or_definition
 
-    Args:
-        flow: Flow instance to analyze.
+    flow_class = (
+        flow_or_definition
+        if isinstance(flow_or_definition, type)
+        else type(flow_or_definition)
+    )
+    flow_definition = getattr(flow_class, "flow_definition", None)
+    if callable(flow_definition):
+        return cast(FlowDefinition, flow_definition())
+    raise TypeError(
+        "build_flow_structure requires a FlowDefinition or a Flow class/instance "
+        "with flow_definition()."
+    )
 
-    Returns:
-        Dictionary with nodes, edges, start_methods, and router_methods.
-    """
+
+def build_flow_structure(
+    flow_or_definition: Flow[Any] | type[Flow[Any]] | FlowDefinition,
+) -> FlowStructure:
+    """Build a visualization structure projection from a FlowDefinition."""
+    definition = _flow_definition_from(flow_or_definition)
     nodes: dict[str, NodeMetadata] = {}
     edges: list[StructureEdge] = []
     start_methods: list[str] = []
     router_methods: list[str] = []
 
-    for method_name, method in flow._methods.items():
-        node_metadata: NodeMetadata = {"type": "listen"}
+    for method_name, method_definition in definition.methods.items():
+        node_metadata: NodeMetadata = {"type": "listen", "class_name": definition.name}
 
-        if hasattr(method, "__is_start_method__") and method.__is_start_method__:
+        if method_definition.is_start:
             node_metadata["type"] = "start"
             start_methods.append(method_name)
 
-        if hasattr(method, "__is_router__") and method.__is_router__:
+        if method_definition.router:
             node_metadata["is_router"] = True
             node_metadata["type"] = "router"
             router_methods.append(method_name)
+            router_events = _method_router_events(method_definition)
+            if router_events:
+                node_metadata["router_events"] = router_events
 
-            if method_name in flow._router_paths:
-                node_metadata["router_paths"] = [
-                    str(p) for p in flow._router_paths[method_name]
-                ]
-
-        if hasattr(method, "__trigger_methods__") and method.__trigger_methods__:
-            node_metadata["trigger_methods"] = [
-                str(m) for m in method.__trigger_methods__
-            ]
-
-        if hasattr(method, "__condition_type__") and method.__condition_type__:
-            node_metadata["trigger_condition_type"] = method.__condition_type__
-            if "condition_type" not in node_metadata:
-                node_metadata["condition_type"] = method.__condition_type__
+        trigger_condition = _method_trigger_condition(method_definition)
+        condition_type = _condition_type_from_definition(trigger_condition)
+        if condition_type is not None and trigger_condition is not None:
+            node_metadata["trigger_condition_type"] = condition_type
+            node_metadata["condition_type"] = condition_type
+            extracted = _extract_all_trigger_names(trigger_condition)
+            if extracted:
+                node_metadata["trigger_methods"] = extracted
+            runtime_condition = _runtime_condition_from_definition(trigger_condition)
+            if isinstance(runtime_condition, dict):
+                node_metadata["trigger_condition"] = runtime_condition
 
         if node_metadata.get("is_router") and "condition_type" not in node_metadata:
             node_metadata["condition_type"] = "IF"
 
-        if (
-            hasattr(method, "__trigger_condition__")
-            and method.__trigger_condition__ is not None
-        ):
-            node_metadata["trigger_condition"] = method.__trigger_condition__
-
-            if "trigger_methods" not in node_metadata:
-                extracted = _extract_all_trigger_names(method.__trigger_condition__)
-                if extracted:
-                    node_metadata["trigger_methods"] = extracted
-
-        node_metadata["method_signature"] = extract_method_signature(
-            method, method_name
-        )
-
-        try:
-            source_code = inspect.getsource(method)
-            node_metadata["source_code"] = source_code
-
-            try:
-                source_lines, start_line = inspect.getsourcelines(method)
-                node_metadata["source_lines"] = source_lines
-                node_metadata["source_start_line"] = start_line
-            except (OSError, TypeError):
-                pass
-
-            try:
-                source_file = inspect.getsourcefile(method)
-                if source_file:
-                    node_metadata["source_file"] = source_file
-            except (OSError, TypeError):
-                try:
-                    class_file = inspect.getsourcefile(flow.__class__)
-                    if class_file:
-                        node_metadata["source_file"] = class_file
-                except (OSError, TypeError):
-                    pass
-        except (OSError, TypeError):
-            pass
-
-        try:
-            class_obj = flow.__class__
-
-            if class_obj:
-                class_name = class_obj.__name__
-
-                bases = class_obj.__bases__
-                if bases:
-                    base_strs = []
-                    for base in bases:
-                        if hasattr(base, "__name__"):
-                            if hasattr(base, "__origin__"):
-                                base_strs.append(str(base))
-                            else:
-                                base_strs.append(base.__name__)
-                        else:
-                            base_strs.append(str(base))
-
-                    try:
-                        source_lines = inspect.getsource(class_obj).split("\n")
-                        _, class_start_line = inspect.getsourcelines(class_obj)
-
-                        for idx, line in enumerate(source_lines):
-                            stripped = line.strip()
-                            if stripped.startswith("class ") and class_name in stripped:
-                                class_signature = stripped.rstrip(":")
-                                node_metadata["class_signature"] = class_signature
-                                node_metadata["class_line_number"] = (
-                                    class_start_line + idx
-                                )
-                                break
-                    except (OSError, TypeError):
-                        class_signature = f"class {class_name}({', '.join(base_strs)})"
-                        node_metadata["class_signature"] = class_signature
-                else:
-                    class_signature = f"class {class_name}"
-                    node_metadata["class_signature"] = class_signature
-
-                node_metadata["class_name"] = class_name
-        except (OSError, TypeError, AttributeError):
-            pass
-
         nodes[method_name] = node_metadata
 
-    for listener_name, condition_data in flow._listeners.items():
-        if listener_name in router_methods:
+    for method_name, method_definition in definition.methods.items():
+        trigger_condition = _method_trigger_condition(method_definition)
+        if trigger_condition is None:
             continue
-
-        if is_simple_flow_condition(condition_data):
-            cond_type, methods = condition_data
-            edges.extend(
-                StructureEdge(
-                    source=str(trigger_method),
-                    target=str(listener_name),
-                    condition_type=cond_type,
-                    is_router_path=False,
-                )
-                for trigger_method in methods
-                if str(trigger_method) in nodes
-            )
-        elif is_flow_condition_dict(condition_data):
-            edges.extend(
-                _create_edges_from_condition(condition_data, str(listener_name), nodes)
-            )
-
-    for method_name, node_metadata in nodes.items():  # type: ignore[assignment]
-        if node_metadata.get("is_router") and "trigger_methods" in node_metadata:
-            trigger_methods = node_metadata["trigger_methods"]
-            condition_type = node_metadata.get("trigger_condition_type", OR_CONDITION)
-
-            if "trigger_condition" in node_metadata:
-                edges.extend(
-                    _create_edges_from_condition(
-                        node_metadata["trigger_condition"],  # type: ignore[arg-type]
-                        method_name,
-                        nodes,
-                    )
-                )
-            else:
-                edges.extend(
-                    StructureEdge(
-                        source=trigger_method,
-                        target=method_name,
-                        condition_type=condition_type,
-                        is_router_path=False,
-                    )
-                    for trigger_method in trigger_methods
-                    if trigger_method in nodes
-                )
+        edges.extend(
+            _create_edges_from_condition(trigger_condition, method_name, nodes)
+        )
 
     all_string_triggers: set[str] = set()
-    for condition_data in flow._listeners.values():
-        if is_simple_flow_condition(condition_data):
-            _, methods = condition_data
-            for m in methods:
-                if str(m) not in nodes:  # It's a string trigger, not a method name
-                    all_string_triggers.add(str(m))
-        elif is_flow_condition_dict(condition_data):
-            for trigger in _extract_direct_or_triggers(condition_data):
-                if trigger not in nodes:
-                    all_string_triggers.add(trigger)
+    for method_definition in definition.methods.values():
+        trigger_condition = _method_trigger_condition(method_definition)
+        if trigger_condition is None:
+            continue
+        for trigger in _extract_direct_or_triggers(trigger_condition):
+            if trigger not in nodes:
+                all_string_triggers.add(trigger)
 
-    all_router_outputs: set[str] = set()
+    all_router_events: set[str] = set()
     for router_method_name in router_methods:
-        if router_method_name not in flow._router_paths:
-            flow._router_paths[FlowMethodName(router_method_name)] = []
+        router_events = _method_router_events(definition.methods[router_method_name])
+        if router_events and router_method_name in nodes:
+            nodes[router_method_name]["router_events"] = router_events
+            all_router_events.update(router_events)
 
-        current_paths = flow._router_paths.get(FlowMethodName(router_method_name), [])
-        if current_paths and router_method_name in nodes:
-            nodes[router_method_name]["router_paths"] = [str(p) for p in current_paths]
-            all_router_outputs.update(str(p) for p in current_paths)
-
-        if not current_paths:
+        if not router_events:
             logger.warning(
-                f"Could not determine return paths for router '{router_method_name}'. "
-                f"Add a return type annotation like "
-                f"'-> Literal[\"path1\", \"path2\"]' or '-> YourEnum' "
-                f"to enable proper flow visualization."
+                f"Router events for '{router_method_name}' are dynamic or not "
+                f"statically inferable; static visualization may omit event edges."
             )
 
-    orphaned_triggers = all_string_triggers - all_router_outputs
+    orphaned_triggers = all_string_triggers - all_router_events
     if orphaned_triggers:
-        logger.error(
-            f"Found listeners waiting for triggers {orphaned_triggers} "
-            f"but no router outputs these values explicitly. "
-            f"If your router returns a non-static value, check that your router has proper return type annotations."
+        logger.warning(
+            f"Static visualization could not match listener triggers "
+            f"{orphaned_triggers} to explicit router events. "
+            f"Dynamic router values may still trigger these listeners at runtime."
         )
 
     for router_method_name in router_methods:
-        if router_method_name not in flow._router_paths:
-            continue
+        router_events = _method_router_events(definition.methods[router_method_name])
 
-        router_paths = flow._router_paths[FlowMethodName(router_method_name)]
-
-        for path in router_paths:
-            for listener_name, condition_data in flow._listeners.items():
+        for event in router_events:
+            for listener_name, method_definition in definition.methods.items():
                 if listener_name == router_method_name:
                     continue
 
-                trigger_strings_from_cond: list[str] = []
+                trigger_condition = _method_trigger_condition(method_definition)
+                if trigger_condition is None:
+                    continue
+                trigger_strings_from_cond = _extract_direct_or_triggers(
+                    trigger_condition
+                )
 
-                if is_simple_flow_condition(condition_data):
-                    _, methods = condition_data
-                    trigger_strings_from_cond = [str(m) for m in methods]
-                elif is_flow_condition_dict(condition_data):
-                    trigger_strings_from_cond = _extract_direct_or_triggers(
-                        condition_data
-                    )
-
-                if str(path) in trigger_strings_from_cond:
+                if str(event) in trigger_strings_from_cond:
                     edges.append(
                         StructureEdge(
                             source=router_method_name,
-                            target=str(listener_name),
+                            target=listener_name,
                             condition_type=None,
-                            is_router_path=True,
-                            router_path_label=str(path),
+                            is_router_event=True,
+                            router_event=str(event),
                         )
                     )
 
-    for start_method in flow._start_methods:
-        if start_method not in nodes and start_method in flow._methods:
-            method = flow._methods[start_method]
-            nodes[str(start_method)] = NodeMetadata(type="start")
-
-            if hasattr(method, "__trigger_methods__") and method.__trigger_methods__:
-                nodes[str(start_method)]["trigger_methods"] = [
-                    str(m) for m in method.__trigger_methods__
-                ]
-            if hasattr(method, "__condition_type__") and method.__condition_type__:
-                nodes[str(start_method)]["condition_type"] = method.__condition_type__
-
     return FlowStructure(
         nodes=nodes,
         edges=edges,
@@ -453,7 +294,7 @@ def calculate_execution_paths(structure: FlowStructure) -> int:
         graph[edge["source"]].append(
             {
                 "target": edge["target"],
-                "is_router": edge["is_router_path"],
+                "is_router": edge["is_router_event"],
                 "condition": edge["condition_type"],
             }
         )
@@ -466,15 +307,6 @@ def calculate_execution_paths(structure: FlowStructure) -> int:
         return 0
 
     def count_paths_from(node: str, visited: set[str]) -> int:
-        """Recursively count execution paths from a given node.
-
-        Args:
-            node: Node name to start counting from.
-            visited: Set of already visited nodes to prevent cycles.
-
-        Returns:
-            Number of execution paths from this node to terminal nodes.
-        """
         if node in terminal_nodes:
             return 1
 

lib/crewai/src/crewai/flow/visualization/renderers/interactive.py

@@ -309,18 +309,18 @@ def render_interactive(
                 </div>
             """)
 
-        if metadata.get("router_paths"):
-            paths = metadata["router_paths"]
-            paths_items = "".join(
+        if metadata.get("router_events"):
+            router_events = metadata["router_events"]
+            event_items = "".join(
                 [
                     f'<li style="margin: 3px 0;"><code style="background: rgba(255,90,80,0.08); padding: 2px 6px; border-radius: 3px; font-size: 10px; color: {CREWAI_ORANGE}; border: 1px solid rgba(255,90,80,0.2); font-weight: 600;">{p}</code></li>'
-                    for p in paths
+                    for p in router_events
                 ]
             )
             title_parts.append(f"""
                 <div>
-                    <div style="font-size: 10px; text-transform: uppercase; color: {GRAY}; letter-spacing: 0.5px; margin-bottom: 4px; font-weight: 600;">Router Paths</div>
-                    <ul style="list-style: none; padding: 0; margin: 0;">{paths_items}</ul>
+                    <div style="font-size: 10px; text-transform: uppercase; color: {GRAY}; letter-spacing: 0.5px; margin-bottom: 4px; font-weight: 600;">Router Events</div>
+                    <ul style="list-style: none; padding: 0; margin: 0;">{event_items}</ul>
                 </div>
             """)
 
@@ -364,11 +364,11 @@ def render_interactive(
         edge_color: str = GRAY
         edge_dashes: bool | list[int] = False
 
-        if edge["is_router_path"]:
+        if edge["is_router_event"]:
             edge_color = CREWAI_ORANGE
             edge_dashes = [15, 10]
-            if "router_path_label" in edge:
-                edge_label = edge["router_path_label"]
+            if "router_event" in edge:
+                edge_label = edge["router_event"] or ""
         elif edge["condition_type"] == "AND":
             edge_label = "AND"
             edge_color = CREWAI_ORANGE

lib/crewai/src/crewai/flow/visualization/schema.py

@@ -1,104 +0,0 @@
-"""OpenAPI schema conversion utilities for Flow methods."""
-
-import inspect
-from typing import Any, get_args, get_origin
-
-
-def type_to_openapi_schema(type_hint: Any) -> dict[str, Any]:
-    """Convert Python type hint to OpenAPI schema.
-
-    Args:
-        type_hint: Python type hint to convert.
-
-    Returns:
-        OpenAPI schema dictionary.
-    """
-    if type_hint is inspect.Parameter.empty:
-        return {}
-
-    if type_hint is None or type_hint is type(None):
-        return {"type": "null"}
-
-    if hasattr(type_hint, "__module__") and hasattr(type_hint, "__name__"):
-        if type_hint.__module__ == "typing" and type_hint.__name__ == "Any":
-            return {}
-
-    type_str = str(type_hint)
-    if type_str == "typing.Any" or type_str == "<class 'typing.Any'>":
-        return {}
-
-    if isinstance(type_hint, str):
-        return {"type": type_hint}
-
-    origin = get_origin(type_hint)
-    args = get_args(type_hint)
-
-    if type_hint is str:
-        return {"type": "string"}
-    if type_hint is int:
-        return {"type": "integer"}
-    if type_hint is float:
-        return {"type": "number"}
-    if type_hint is bool:
-        return {"type": "boolean"}
-    if type_hint is dict or origin is dict:
-        if args and len(args) > 1:
-            return {
-                "type": "object",
-                "additionalProperties": type_to_openapi_schema(args[1]),
-            }
-        return {"type": "object"}
-    if type_hint is list or origin is list:
-        if args:
-            return {"type": "array", "items": type_to_openapi_schema(args[0])}
-        return {"type": "array"}
-    if hasattr(type_hint, "__name__"):
-        return {"type": "object", "className": type_hint.__name__}
-
-    return {}
-
-
-def extract_method_signature(method: Any, method_name: str) -> dict[str, Any]:
-    """Extract method signature as OpenAPI schema with documentation.
-
-    Args:
-        method: Method to analyze.
-        method_name: Method name.
-
-    Returns:
-        Dictionary with operationId, parameters, returns, summary, and description.
-    """
-    try:
-        sig = inspect.signature(method)
-
-        parameters = {}
-        for param_name, param in sig.parameters.items():
-            if param_name == "self":
-                continue
-            parameters[param_name] = type_to_openapi_schema(param.annotation)
-
-        return_type = type_to_openapi_schema(sig.return_annotation)
-
-        docstring = inspect.getdoc(method)
-
-        result: dict[str, Any] = {
-            "operationId": method_name,
-            "parameters": parameters,
-            "returns": return_type,
-        }
-
-        if docstring:
-            lines = docstring.strip().split("\n")
-            summary = lines[0].strip()
-
-            if summary:
-                result["summary"] = summary
-
-            if len(lines) > 1:
-                description = "\n".join(line.strip() for line in lines[1:]).strip()
-                if description:
-                    result["description"] = description
-
-        return result
-    except Exception:
-        return {"operationId": method_name, "parameters": {}, "returns": {}}

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

@@ -1,6 +1,11 @@
 """Type definitions for Flow structure visualization."""
 
-from typing import Any, TypedDict
+from typing import Any
+
+from typing_extensions import Required, TypedDict
+
+
+__all__ = ["FlowStructure", "NodeMetadata", "StructureEdge"]
 
 
 class NodeMetadata(TypedDict, total=False):
@@ -8,19 +13,12 @@ class NodeMetadata(TypedDict, total=False):
 
     type: str
     is_router: bool
-    router_paths: list[str]
+    router_events: list[str]
     condition_type: str | None
     trigger_condition_type: str | None
     trigger_methods: list[str]
     trigger_condition: dict[str, Any] | None
-    method_signature: dict[str, Any]
-    source_code: str
-    source_lines: list[str]
-    source_start_line: int
-    source_file: str
-    class_signature: str
     class_name: str
-    class_line_number: int
 
 
 class StructureEdge(TypedDict, total=False):
@@ -29,8 +27,8 @@ class StructureEdge(TypedDict, total=False):
     source: str
     target: str
     condition_type: str | None
-    is_router_path: bool
-    router_path_label: str
+    is_router_event: Required[bool]
+    router_event: str | None
 
 
 class FlowStructure(TypedDict):

lib/crewai/src/crewai/knowledge/knowledge.py

@@ -13,6 +13,7 @@ from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSourc
 from crewai.knowledge.source.text_file_knowledge_source import (
     TextFileKnowledgeSource,
 )
+from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
 from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
 from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
 from crewai.rag.embeddings.types import EmbedderConfig
@@ -89,7 +90,7 @@ class Knowledge(BaseModel):
     Knowledge is a collection of sources and setup for the vector store to save and query relevant context.
     Args:
         sources: list[BaseKnowledgeSource] = Field(default_factory=list)
-        storage: KnowledgeStorage | None = Field(default=None)
+        storage: BaseKnowledgeStorage | None = Field(default=None)
         embedder: EmbedderConfig | None = None
     """
 
@@ -98,7 +99,7 @@ class Knowledge(BaseModel):
         BeforeValidator(_resolve_knowledge_sources),
     ] = Field(default_factory=list)
     model_config = ConfigDict(arbitrary_types_allowed=True)
-    storage: KnowledgeStorage | None = Field(default=None)
+    storage: BaseKnowledgeStorage | None = Field(default=None)
     embedder: Annotated[
         EmbedderConfig | None,
         PlainSerializer(
@@ -112,15 +113,22 @@ class Knowledge(BaseModel):
         collection_name: str,
         sources: list[BaseKnowledgeSource],
         embedder: EmbedderConfig | None = None,
-        storage: KnowledgeStorage | None = None,
+        storage: BaseKnowledgeStorage | None = None,
         **data: object,
     ) -> None:
         super().__init__(**data)
-        if storage:
+        if storage is not None:
             self.storage = storage
         else:
-            self.storage = KnowledgeStorage(
-                embedder=embedder, collection_name=collection_name
+            from crewai.knowledge.storage.factory import resolve_knowledge_storage
+
+            custom = resolve_knowledge_storage(embedder, collection_name)
+            self.storage = (
+                custom
+                if custom is not None
+                else KnowledgeStorage(
+                    embedder=embedder, collection_name=collection_name
+                )
             )
         self.sources = sources
 
@@ -152,10 +160,9 @@ class Knowledge(BaseModel):
             raise e
 
     def reset(self) -> None:
-        if self.storage:
-            self.storage.reset()
-        else:
+        if self.storage is None:
             raise ValueError("Storage is not initialized.")
+        self.storage.reset()
 
     async def aquery(
         self, query: list[str], results_limit: int = 5, score_threshold: float = 0.6
@@ -193,7 +200,6 @@ class Knowledge(BaseModel):
 
     async def areset(self) -> None:
         """Reset the knowledge base asynchronously."""
-        if self.storage:
-            await self.storage.areset()
-        else:
+        if self.storage is None:
             raise ValueError("Storage is not initialized.")
+        await self.storage.areset()

lib/crewai/src/crewai/knowledge/source/base_file_knowledge_source.py

@@ -5,7 +5,7 @@ from typing import Any
 from pydantic import Field, field_validator
 
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
-from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
+from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
 from crewai.utilities.constants import KNOWLEDGE_DIRECTORY
 from crewai.utilities.logger import Logger
 
@@ -22,7 +22,7 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
         default_factory=list, description="The path to the file"
     )
     content: dict[Path, str] = Field(init=False, default_factory=dict)
-    storage: KnowledgeStorage | None = Field(default=None)
+    storage: BaseKnowledgeStorage | None = Field(default=None)
     safe_file_paths: list[Path] = Field(default_factory=list)
 
     @field_validator("file_path", "file_paths", mode="before")
@@ -70,14 +70,14 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
 
     def _save_documents(self) -> None:
         """Save the documents to the storage."""
-        if self.storage:
+        if self.storage is not None:
             self.storage.save(self.chunks)
         else:
             raise ValueError("No storage found to save documents.")
 
     async def _asave_documents(self) -> None:
         """Save the documents to the storage asynchronously."""
-        if self.storage:
+        if self.storage is not None:
             await self.storage.asave(self.chunks)
         else:
             raise ValueError("No storage found to save documents.")

lib/crewai/src/crewai/knowledge/source/base_knowledge_source.py

@@ -4,9 +4,15 @@ from typing import Any
 import numpy as np
 from pydantic import BaseModel, ConfigDict, Field
 
+from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
 from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
 
 
+# ``KnowledgeStorage`` is re-exported for backwards compatibility; the ``storage``
+# field below is typed to the base interface so any backend plugs in.
+__all__ = ["BaseKnowledgeSource", "KnowledgeStorage"]
+
+
 class BaseKnowledgeSource(BaseModel, ABC):
     """Abstract base class for knowledge sources."""
 
@@ -18,7 +24,7 @@ class BaseKnowledgeSource(BaseModel, ABC):
     )
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
-    storage: KnowledgeStorage | None = Field(default=None)
+    storage: BaseKnowledgeStorage | None = Field(default=None)
     metadata: dict[str, Any] = Field(default_factory=dict)  # Currently unused
     collection_name: str | None = Field(default=None)
 
@@ -49,7 +55,7 @@ class BaseKnowledgeSource(BaseModel, ABC):
         Raises:
             ValueError: If no storage is configured.
         """
-        if self.storage:
+        if self.storage is not None:
             self.storage.save(self.chunks)
         else:
             raise ValueError("No storage found to save documents.")
@@ -66,7 +72,7 @@ class BaseKnowledgeSource(BaseModel, ABC):
         Raises:
             ValueError: If no storage is configured.
         """
-        if self.storage:
+        if self.storage is not None:
             await self.storage.asave(self.chunks)
         else:
             raise ValueError("No storage found to save documents.")

lib/crewai/src/crewai/knowledge/storage/factory.py

@@ -0,0 +1,56 @@
+"""Pluggable default storage backend for knowledge collections.
+
+By default, :class:`~crewai.knowledge.knowledge.Knowledge` builds a
+:class:`~crewai.knowledge.storage.knowledge_storage.KnowledgeStorage` when no
+explicit ``storage=`` is given. Registering a factory via
+:func:`set_knowledge_storage_factory` lets an application back knowledge with a
+custom :class:`~crewai.knowledge.storage.base_knowledge_storage.BaseKnowledgeStorage`
+without subclassing ``Knowledge`` or passing a ``storage=`` instance at every
+call site.
+
+This mirrors :func:`crewai_core.lock_store.set_lock_backend`: a one-time,
+process-wide setter intended for application startup. Pass ``None`` to restore
+the built-in default.
+"""
+
+from __future__ import annotations
+
+from collections.abc import Callable
+from typing import TYPE_CHECKING
+
+
+if TYPE_CHECKING:
+    from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
+    from crewai.rag.embeddings.types import EmbedderConfig
+
+# Receives the same inputs as the built-in default -- the embedder config and
+# collection name -- and returns a storage backend, or ``None`` to defer to the
+# built-in ``KnowledgeStorage``.
+KnowledgeStorageFactory = Callable[
+    ["EmbedderConfig | None", "str | None"], "BaseKnowledgeStorage | None"
+]
+
+_factory: KnowledgeStorageFactory | None = None
+
+
+def set_knowledge_storage_factory(factory: KnowledgeStorageFactory | None) -> None:
+    """Replace the process-wide default knowledge storage factory.
+
+    Intended for one-time setup at startup. Pass ``None`` to restore the
+    built-in ``KnowledgeStorage``. Only affects ``Knowledge`` instances
+    constructed afterwards; an explicit ``storage=`` instance always wins.
+    """
+    global _factory
+    _factory = factory
+
+
+def resolve_knowledge_storage(
+    embedder: EmbedderConfig | None, collection_name: str | None
+) -> BaseKnowledgeStorage | None:
+    """Return the registered factory's backend, or ``None`` for the built-in.
+
+    ``None`` means no factory is registered or it declined; the caller then
+    falls back to the built-in ``KnowledgeStorage``.
+    """
+    factory = _factory
+    return factory(embedder, collection_name) if factory is not None else None

lib/crewai/src/crewai/llm.py

@@ -23,7 +23,6 @@ from crewai.events.event_bus import crewai_event_bus
 from crewai.events.types.llm_events import (
     LLMCallCompletedEvent,
     LLMCallFailedEvent,
-    LLMCallStartedEvent,
     LLMCallType,
     LLMStreamChunkEvent,
 )
@@ -32,6 +31,7 @@ from crewai.events.types.tool_usage_events import (
     ToolUsageFinishedEvent,
     ToolUsageStartedEvent,
 )
+from crewai.llms._finish_reason_utils import extract_choices_finish_reason_and_id
 from crewai.llms.base_llm import (
     BaseLLM,
     JsonResponseFormat,
@@ -732,6 +732,11 @@ class LLM(BaseLLM):
         last_chunk = None
         chunk_count = 0
         usage_info = None
+        # Tracked across the loop: LiteLLM with include_usage emits a final
+        # usage-only chunk with empty choices, so the post-loop last_chunk has
+        # no finish_reason. Capture both incrementally instead.
+        stream_finish_reason: str | None = None
+        stream_response_id: str | None = None
 
         accumulated_tool_args: defaultdict[int, AccumulatedToolArgs] = defaultdict(
             AccumulatedToolArgs
@@ -750,6 +755,16 @@ class LLM(BaseLLM):
 
                 if isinstance(chunk, ModelResponseBase):
                     response_id = chunk.id
+                elif isinstance(chunk, dict):
+                    response_id = chunk.get("id")
+
+                chunk_finish, chunk_id = self._extract_finish_reason_and_response_id(
+                    chunk
+                )
+                if chunk_finish:
+                    stream_finish_reason = chunk_finish
+                if chunk_id and not stream_response_id:
+                    stream_response_id = chunk_id
 
                 try:
                     choices = None
@@ -922,6 +937,11 @@ class LLM(BaseLLM):
                 if tool_calls_list:
                     return tool_calls_list
 
+            finish_reason, response_id_last = (
+                stream_finish_reason,
+                stream_response_id,
+            )
+
             if not tool_calls or not available_functions:
                 if response_model and self.is_litellm:
                     instructor_instance = InternalInstructor(
@@ -939,6 +959,8 @@ class LLM(BaseLLM):
                         from_agent=from_agent,
                         messages=params["messages"],
                         usage=usage_dict,
+                        finish_reason=finish_reason,
+                        response_id=response_id_last,
                     )
                     return structured_response
 
@@ -950,6 +972,8 @@ class LLM(BaseLLM):
                     from_agent=from_agent,
                     messages=params["messages"],
                     usage=usage_dict,
+                    finish_reason=finish_reason,
+                    response_id=response_id_last,
                 )
                 return full_response
 
@@ -965,6 +989,8 @@ class LLM(BaseLLM):
                 from_agent=from_agent,
                 messages=params["messages"],
                 usage=usage_dict,
+                finish_reason=finish_reason,
+                response_id=response_id_last,
             )
             return full_response
 
@@ -978,6 +1004,10 @@ class LLM(BaseLLM):
             logging.error(f"Error in streaming response: {e!s}")
             if full_response.strip():
                 logging.warning(f"Returning partial response despite error: {e!s}")
+                finish_reason, response_id_last = (
+                    stream_finish_reason,
+                    stream_response_id,
+                )
                 self._handle_emit_call_events(
                     response=full_response,
                     call_type=LLMCallType.LLM_CALL,
@@ -985,6 +1015,8 @@ class LLM(BaseLLM):
                     from_agent=from_agent,
                     messages=params["messages"],
                     usage=self._usage_to_dict(usage_info),
+                    finish_reason=finish_reason,
+                    response_id=response_id_last,
                 )
                 return full_response
 
@@ -1169,6 +1201,10 @@ class LLM(BaseLLM):
             else None
         )
 
+        finish_reason, response_id = self._extract_finish_reason_and_response_id(
+            response
+        )
+
         if response_model is not None:
             # When using instructor/response_model, litellm returns a Pydantic model instance
             if isinstance(response, BaseModel):
@@ -1180,6 +1216,8 @@ class LLM(BaseLLM):
                     from_agent=from_agent,
                     messages=params["messages"],
                     usage=response_usage,
+                    finish_reason=finish_reason,
+                    response_id=response_id,
                 )
                 return structured_response
 
@@ -1216,6 +1254,8 @@ class LLM(BaseLLM):
                 from_agent=from_agent,
                 messages=params["messages"],
                 usage=response_usage,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
             return text_response
 
@@ -1233,6 +1273,8 @@ class LLM(BaseLLM):
             from_agent=from_agent,
             messages=params["messages"],
             usage=response_usage,
+            finish_reason=finish_reason,
+            response_id=response_id,
         )
         return text_response
 
@@ -1310,6 +1352,10 @@ class LLM(BaseLLM):
             else None
         )
 
+        finish_reason, response_id = self._extract_finish_reason_and_response_id(
+            response
+        )
+
         if response_model is not None:
             if isinstance(response, BaseModel):
                 structured_response = response.model_dump_json()
@@ -1320,6 +1366,8 @@ class LLM(BaseLLM):
                     from_agent=from_agent,
                     messages=params["messages"],
                     usage=response_usage,
+                    finish_reason=finish_reason,
+                    response_id=response_id,
                 )
                 return structured_response
 
@@ -1358,6 +1406,8 @@ class LLM(BaseLLM):
                 from_agent=from_agent,
                 messages=params["messages"],
                 usage=response_usage,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
             return text_response
 
@@ -1375,6 +1425,8 @@ class LLM(BaseLLM):
             from_agent=from_agent,
             messages=params["messages"],
             usage=response_usage,
+            finish_reason=finish_reason,
+            response_id=response_id,
         )
         return text_response
 
@@ -1412,12 +1464,29 @@ class LLM(BaseLLM):
         params["stream"] = True
         params["stream_options"] = {"include_usage": True}
         response_id = None
+        # See sync sibling: incrementally track finish_reason/response_id so the
+        # usage-only final chunk doesn't wipe them.
+        stream_finish_reason: str | None = None
+        stream_response_id: str | None = None
 
         try:
             async for chunk in await litellm.acompletion(**params):
                 chunk_count += 1
                 chunk_content = None
-                response_id = chunk.id if isinstance(chunk, ModelResponseBase) else None
+                if isinstance(chunk, ModelResponseBase):
+                    response_id = chunk.id
+                elif isinstance(chunk, dict):
+                    response_id = chunk.get("id")
+                else:
+                    response_id = None
+
+                chunk_finish, chunk_id = self._extract_finish_reason_and_response_id(
+                    chunk
+                )
+                if chunk_finish:
+                    stream_finish_reason = chunk_finish
+                if chunk_id and not stream_response_id:
+                    stream_response_id = chunk_id
 
                 try:
                     choices = None
@@ -1525,6 +1594,10 @@ class LLM(BaseLLM):
                         return tool_calls_list
 
             usage_dict = self._usage_to_dict(usage_info)
+            finish_reason, response_id_last = (
+                stream_finish_reason,
+                stream_response_id,
+            )
             self._handle_emit_call_events(
                 response=full_response,
                 call_type=LLMCallType.LLM_CALL,
@@ -1532,6 +1605,8 @@ class LLM(BaseLLM):
                 from_agent=from_agent,
                 messages=params.get("messages"),
                 usage=usage_dict,
+                finish_reason=finish_reason,
+                response_id=response_id_last,
             )
             return full_response
 
@@ -1545,6 +1620,10 @@ class LLM(BaseLLM):
             if chunk_count == 0:
                 raise
             if full_response:
+                finish_reason, response_id_last = (
+                    stream_finish_reason,
+                    stream_response_id,
+                )
                 self._handle_emit_call_events(
                     response=full_response,
                     call_type=LLMCallType.LLM_CALL,
@@ -1552,6 +1631,8 @@ class LLM(BaseLLM):
                     from_agent=from_agent,
                     messages=params.get("messages"),
                     usage=self._usage_to_dict(usage_info),
+                    finish_reason=finish_reason,
+                    response_id=response_id_last,
                 )
                 return full_response
             raise
@@ -1678,19 +1759,14 @@ class LLM(BaseLLM):
             ValueError: If response format is not supported
             LLMContextLengthExceededError: If input exceeds model's context limit
         """
-        with llm_call_context() as call_id:
-            crewai_event_bus.emit(
-                self,
-                event=LLMCallStartedEvent(
-                    messages=messages,
-                    tools=tools,
-                    callbacks=callbacks,
-                    available_functions=available_functions,
-                    from_task=from_task,
-                    from_agent=from_agent,
-                    model=self.model,
-                    call_id=call_id,
-                ),
+        with llm_call_context():
+            self._emit_call_started_event(
+                messages=messages,
+                tools=tools,
+                callbacks=callbacks,
+                available_functions=available_functions,
+                from_task=from_task,
+                from_agent=from_agent,
             )
 
             self._validate_call_params()
@@ -1822,19 +1898,14 @@ class LLM(BaseLLM):
             ValueError: If response format is not supported
             LLMContextLengthExceededError: If input exceeds model's context limit
         """
-        with llm_call_context() as call_id:
-            crewai_event_bus.emit(
-                self,
-                event=LLMCallStartedEvent(
-                    messages=messages,
-                    tools=tools,
-                    callbacks=callbacks,
-                    available_functions=available_functions,
-                    from_task=from_task,
-                    from_agent=from_agent,
-                    model=self.model,
-                    call_id=call_id,
-                ),
+        with llm_call_context():
+            self._emit_call_started_event(
+                messages=messages,
+                tools=tools,
+                callbacks=callbacks,
+                available_functions=available_functions,
+                from_task=from_task,
+                from_agent=from_agent,
             )
 
             self._validate_call_params()
@@ -1925,16 +1996,62 @@ class LLM(BaseLLM):
 
     @staticmethod
     def _usage_to_dict(usage: Any) -> dict[str, Any] | None:
+        """Convert a provider usage object to a plain dict and flatten the
+        cache/reasoning sub-counts that LiteLLM nests under provider-specific
+        shapes into the top-level keys the rest of the pipeline expects.
+
+        LiteLLM hands back provider usage as-is, so cache-read, cache-creation
+        and reasoning tokens may live in nested objects (e.g.
+        ``prompt_tokens_details.cached_tokens``) or under Anthropic-style keys
+        (``cache_read_input_tokens``). Downstream span mapping only reads the
+        flat ``cached_prompt_tokens`` / ``reasoning_tokens`` /
+        ``cache_creation_tokens`` keys, so we surface them here.
+
+        Only those derived buckets are populated; ``prompt_tokens`` /
+        ``completion_tokens`` / ``total_tokens`` are left untouched. Extraction
+        precedence mirrors ``BaseLLM._track_token_usage_internal``.
+        """
         if usage is None:
             return None
         if isinstance(usage, dict):
-            return usage
-        if isinstance(usage, BaseModel):
-            result: dict[str, Any] = usage.model_dump()
-            return result
-        if hasattr(usage, "__dict__"):
-            return {k: v for k, v in vars(usage).items() if not k.startswith("_")}
-        return None
+            data: dict[str, Any] = dict(usage)
+        elif isinstance(usage, BaseModel):
+            data = usage.model_dump()
+        elif hasattr(usage, "__dict__"):
+            data = {k: v for k, v in vars(usage).items() if not k.startswith("_")}
+        else:
+            return None
+
+        def _nested(container: Any, key: str) -> Any:
+            if isinstance(container, dict):
+                return container.get(key)
+            return getattr(container, key, None)
+
+        prompt_details = data.get("prompt_tokens_details")
+        completion_details = data.get("completion_tokens_details")
+
+        cached_prompt_tokens = (
+            data.get("cached_tokens")
+            or data.get("cached_prompt_tokens")
+            or data.get("cache_read_input_tokens")
+            or _nested(prompt_details, "cached_tokens")
+        )
+        if cached_prompt_tokens is not None:
+            data["cached_prompt_tokens"] = cached_prompt_tokens
+
+        reasoning_tokens = data.get("reasoning_tokens") or _nested(
+            completion_details, "reasoning_tokens"
+        )
+        if reasoning_tokens is not None:
+            data["reasoning_tokens"] = reasoning_tokens
+
+        cache_creation_tokens = data.get("cache_creation_tokens") or data.get(
+            "cache_creation_input_tokens"
+        )
+        if cache_creation_tokens is not None:
+            data["cache_creation_tokens"] = cache_creation_tokens
+
+        return data
 
     def _handle_emit_call_events(
         self,
@@ -1944,6 +2061,8 @@ class LLM(BaseLLM):
         from_agent: BaseAgent | None = None,
         messages: str | list[LLMMessage] | None = None,
         usage: dict[str, Any] | None = None,
+        finish_reason: str | None = None,
+        response_id: str | None = None,
     ) -> None:
         """Handle the events for the LLM call.
 
@@ -1954,6 +2073,10 @@ class LLM(BaseLLM):
             from_agent: Optional agent object
             messages: Optional messages object
             usage: Optional token usage data
+            finish_reason: Raw provider finish reason (e.g. "stop", "length",
+                "tool_calls"). Optional; downstream telemetry coerces to the
+                OTel GenAI enum.
+            response_id: Raw provider response identifier. Optional.
         """
         crewai_event_bus.emit(
             self,
@@ -1966,9 +2089,24 @@ class LLM(BaseLLM):
                 model=self.model,
                 call_id=get_current_call_id(),
                 usage=usage,
+                finish_reason=finish_reason,
+                response_id=response_id,
             ),
         )
 
+    def _effective_max_tokens(self) -> int | float | None:
+        """LiteLLM sends ``max_tokens or max_completion_tokens`` as the cap."""
+        return self.max_tokens or self.max_completion_tokens
+
+    @staticmethod
+    def _extract_finish_reason_and_response_id(
+        response_or_chunk: Any,
+    ) -> tuple[str | None, str | None]:
+        """LiteLLM responses/chunks share the choices-shape with OpenAI/Azure;
+        delegate to the shared extractor.
+        """
+        return extract_choices_finish_reason_and_id(response_or_chunk)
+
     def _process_message_files(self, messages: list[LLMMessage]) -> list[LLMMessage]:
         """Process files attached to messages and format for provider.
 

lib/crewai/src/crewai/llms/_finish_reason_utils.py

@@ -0,0 +1,55 @@
+"""Shared extractors for ``finish_reason`` + ``response_id`` across LLM providers.
+
+OpenAI Chat Completions, Azure AI Inference, and LiteLLM all expose the same
+choices-based response shape (``response.id`` + ``response.choices[0].finish_reason``),
+both as object attributes and (for LiteLLM stream chunks) as dict keys. This
+module centralises that introspection so every provider doesn't reinvent the
+defensive walk. Providers with genuinely different shapes — Anthropic
+(``stop_reason``), Bedrock (``stopReason``), Gemini (protobuf enum), OpenAI
+Responses (``status``) — keep their own helpers.
+"""
+
+from __future__ import annotations
+
+from typing import Any
+
+
+def _as_str(value: Any) -> str | None:
+    return value if isinstance(value, str) else None
+
+
+def extract_choices_finish_reason_and_id(
+    response_or_chunk: Any,
+) -> tuple[str | None, str | None]:
+    """Extract ``(finish_reason, response_id)`` from a choices-shaped response.
+
+    Handles both object-style (``response.id``, ``response.choices[0].finish_reason``)
+    and dict-style (``response["id"]``, ``response["choices"][0]["finish_reason"]``)
+    inputs. Returns ``(None, None)`` on any failure; never raises. Non-string
+    raw values are coerced to ``None`` so test mocks and exotic provider types
+    (MagicMock, protobuf enums, etc.) don't propagate downstream.
+    """
+    raw_id = getattr(response_or_chunk, "id", None)
+    if raw_id is None and isinstance(response_or_chunk, dict):
+        raw_id = response_or_chunk.get("id")
+    response_id = _as_str(raw_id)
+
+    if isinstance(response_or_chunk, dict):
+        choices = response_or_chunk.get("choices")
+    else:
+        choices = getattr(response_or_chunk, "choices", None)
+
+    finish_reason: str | None = None
+    if choices:
+        try:
+            first = choices[0]
+        except (IndexError, TypeError, KeyError):
+            first = None
+        if first is not None:
+            if isinstance(first, dict):
+                raw_finish = first.get("finish_reason")
+            else:
+                raw_finish = getattr(first, "finish_reason", None)
+            finish_reason = _as_str(raw_finish)
+
+    return finish_reason, response_id

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

@@ -150,6 +150,13 @@ class BaseLLM(BaseModel, ABC):
     llm_type: str = "base"
     model: str
     temperature: float | None = None
+    top_p: float | None = None
+    max_tokens: int | float | None = None
+    stream: bool | None = None
+    seed: int | None = None
+    frequency_penalty: float | None = None
+    presence_penalty: float | None = None
+    n: int | None = None
     api_key: str | None = None
     base_url: str | None = None
     provider: str = Field(default="openai")
@@ -464,6 +471,16 @@ class BaseLLM(BaseModel, ABC):
         """
         return None
 
+    def _effective_max_tokens(self) -> int | float | None:
+        """Token cap actually sent to the provider, for start-event telemetry.
+
+        Defaults to ``self.max_tokens``. Providers that cap generation through a
+        differently named field (e.g. ``max_completion_tokens`` on OpenAI/Azure,
+        ``max_output_tokens`` on Gemini) override this so ``LLMCallStartedEvent``
+        reports the real limit instead of ``None``.
+        """
+        return self.max_tokens
+
     def _emit_call_started_event(
         self,
         messages: str | list[LLMMessage],
@@ -472,10 +489,38 @@ class BaseLLM(BaseModel, ABC):
         available_functions: dict[str, Any] | None = None,
         from_task: Task | None = None,
         from_agent: BaseAgent | None = None,
+        temperature: float | None = None,
+        top_p: float | None = None,
+        max_tokens: int | float | None = None,
+        stream: bool | None = None,
+        seed: int | None = None,
+        stop_sequences: list[str] | None = None,
+        frequency_penalty: float | None = None,
+        presence_penalty: float | None = None,
+        n: int | None = None,
     ) -> None:
         """Emit LLM call started event."""
         from crewai.utilities.serialization import to_serializable
 
+        if temperature is None:
+            temperature = self.temperature
+        if top_p is None:
+            top_p = self.top_p
+        if max_tokens is None:
+            max_tokens = self._effective_max_tokens()
+        if stream is None:
+            stream = self.stream
+        if seed is None:
+            seed = self.seed
+        if stop_sequences is None:
+            stop_sequences = self.stop_sequences or None
+        if frequency_penalty is None:
+            frequency_penalty = self.frequency_penalty
+        if presence_penalty is None:
+            presence_penalty = self.presence_penalty
+        if n is None:
+            n = self.n
+
         crewai_event_bus.emit(
             self,
             event=LLMCallStartedEvent(
@@ -487,6 +532,15 @@ class BaseLLM(BaseModel, ABC):
                 from_agent=from_agent,
                 model=self.model,
                 call_id=get_current_call_id(),
+                temperature=temperature,
+                top_p=top_p,
+                max_tokens=max_tokens,
+                stream=stream,
+                seed=seed,
+                stop_sequences=stop_sequences,
+                frequency_penalty=frequency_penalty,
+                presence_penalty=presence_penalty,
+                n=n,
             ),
         )
 
@@ -498,6 +552,8 @@ class BaseLLM(BaseModel, ABC):
         from_agent: BaseAgent | None = None,
         messages: str | list[LLMMessage] | None = None,
         usage: dict[str, Any] | None = None,
+        finish_reason: str | None = None,
+        response_id: str | None = None,
     ) -> None:
         """Emit LLM call completed event."""
         from crewai.utilities.serialization import to_serializable
@@ -513,6 +569,8 @@ class BaseLLM(BaseModel, ABC):
                 model=self.model,
                 call_id=get_current_call_id(),
                 usage=usage,
+                finish_reason=finish_reason,
+                response_id=response_id,
             ),
         )
 

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

@@ -923,6 +923,8 @@ class AnthropicCompletion(BaseLLM):
         usage = self._extract_anthropic_token_usage(response)
         self._track_token_usage_internal(usage)
 
+        finish_reason, response_id = self._extract_finish_reason_and_id(response)
+
         if _is_pydantic_model_class(response_model) and response.content:
             if use_native_structured_output:
                 for block in response.content:
@@ -935,6 +937,8 @@ class AnthropicCompletion(BaseLLM):
                             from_agent=from_agent,
                             messages=params["messages"],
                             usage=usage,
+                            finish_reason=finish_reason,
+                            response_id=response_id,
                         )
                         return structured_data
             else:
@@ -951,6 +955,8 @@ class AnthropicCompletion(BaseLLM):
                             from_agent=from_agent,
                             messages=params["messages"],
                             usage=usage,
+                            finish_reason=finish_reason,
+                            response_id=response_id,
                         )
                         return structured_data
 
@@ -973,6 +979,8 @@ class AnthropicCompletion(BaseLLM):
                         from_agent=from_agent,
                         messages=params["messages"],
                         usage=usage,
+                        finish_reason=finish_reason,
+                        response_id=response_id,
                     )
                     return list(tool_uses)
 
@@ -1005,6 +1013,8 @@ class AnthropicCompletion(BaseLLM):
             from_agent=from_agent,
             messages=params["messages"],
             usage=usage,
+            finish_reason=finish_reason,
+            response_id=response_id,
         )
 
         if usage.get("total_tokens", 0) > 0:
@@ -1147,6 +1157,10 @@ class AnthropicCompletion(BaseLLM):
         usage = self._extract_anthropic_token_usage(final_message)
         self._track_token_usage_internal(usage)
 
+        finish_reason, final_response_id = self._extract_finish_reason_and_id(
+            final_message
+        )
+
         if _is_pydantic_model_class(response_model):
             if use_native_structured_output:
                 structured_data = response_model.model_validate_json(full_response)
@@ -1157,6 +1171,8 @@ class AnthropicCompletion(BaseLLM):
                     from_agent=from_agent,
                     messages=params["messages"],
                     usage=usage,
+                    finish_reason=finish_reason,
+                    response_id=final_response_id,
                 )
                 return structured_data
             for block in final_message.content:
@@ -1172,6 +1188,8 @@ class AnthropicCompletion(BaseLLM):
                         from_agent=from_agent,
                         messages=params["messages"],
                         usage=usage,
+                        finish_reason=finish_reason,
+                        response_id=final_response_id,
                     )
                     return structured_data
 
@@ -1201,6 +1219,8 @@ class AnthropicCompletion(BaseLLM):
             from_agent=from_agent,
             messages=params["messages"],
             usage=usage,
+            finish_reason=finish_reason,
+            response_id=final_response_id,
         )
 
         return self._invoke_after_llm_call_hooks(
@@ -1361,6 +1381,10 @@ class AnthropicCompletion(BaseLLM):
 
             final_content = self._apply_stop_words(final_content)
 
+            finish_reason, final_response_id = self._extract_finish_reason_and_id(
+                final_response
+            )
+
             self._emit_call_completed_event(
                 response=final_content,
                 call_type=LLMCallType.LLM_CALL,
@@ -1368,6 +1392,8 @@ class AnthropicCompletion(BaseLLM):
                 from_agent=from_agent,
                 messages=follow_up_params["messages"],
                 usage=follow_up_usage,
+                finish_reason=finish_reason,
+                response_id=final_response_id,
             )
 
             total_usage = {
@@ -1447,6 +1473,8 @@ class AnthropicCompletion(BaseLLM):
         usage = self._extract_anthropic_token_usage(response)
         self._track_token_usage_internal(usage)
 
+        finish_reason, response_id = self._extract_finish_reason_and_id(response)
+
         if _is_pydantic_model_class(response_model) and response.content:
             if use_native_structured_output:
                 for block in response.content:
@@ -1459,6 +1487,8 @@ class AnthropicCompletion(BaseLLM):
                             from_agent=from_agent,
                             messages=params["messages"],
                             usage=usage,
+                            finish_reason=finish_reason,
+                            response_id=response_id,
                         )
                         return structured_data
             else:
@@ -1475,6 +1505,8 @@ class AnthropicCompletion(BaseLLM):
                             from_agent=from_agent,
                             messages=params["messages"],
                             usage=usage,
+                            finish_reason=finish_reason,
+                            response_id=response_id,
                         )
                         return structured_data
 
@@ -1495,6 +1527,8 @@ class AnthropicCompletion(BaseLLM):
                         from_agent=from_agent,
                         messages=params["messages"],
                         usage=usage,
+                        finish_reason=finish_reason,
+                        response_id=response_id,
                     )
                     return list(tool_uses)
 
@@ -1519,6 +1553,8 @@ class AnthropicCompletion(BaseLLM):
             from_agent=from_agent,
             messages=params["messages"],
             usage=usage,
+            finish_reason=finish_reason,
+            response_id=response_id,
         )
 
         if usage.get("total_tokens", 0) > 0:
@@ -1647,6 +1683,10 @@ class AnthropicCompletion(BaseLLM):
         usage = self._extract_anthropic_token_usage(final_message)
         self._track_token_usage_internal(usage)
 
+        finish_reason, final_response_id = self._extract_finish_reason_and_id(
+            final_message
+        )
+
         if _is_pydantic_model_class(response_model):
             if use_native_structured_output:
                 structured_data = response_model.model_validate_json(full_response)
@@ -1657,6 +1697,8 @@ class AnthropicCompletion(BaseLLM):
                     from_agent=from_agent,
                     messages=params["messages"],
                     usage=usage,
+                    finish_reason=finish_reason,
+                    response_id=final_response_id,
                 )
                 return structured_data
             for block in final_message.content:
@@ -1672,6 +1714,8 @@ class AnthropicCompletion(BaseLLM):
                         from_agent=from_agent,
                         messages=params["messages"],
                         usage=usage,
+                        finish_reason=finish_reason,
+                        response_id=final_response_id,
                     )
                     return structured_data
 
@@ -1701,6 +1745,8 @@ class AnthropicCompletion(BaseLLM):
             from_agent=from_agent,
             messages=params["messages"],
             usage=usage,
+            finish_reason=finish_reason,
+            response_id=final_response_id,
         )
 
         return full_response
@@ -1753,6 +1799,10 @@ class AnthropicCompletion(BaseLLM):
 
             final_content = self._apply_stop_words(final_content)
 
+            finish_reason, final_response_id = self._extract_finish_reason_and_id(
+                final_response
+            )
+
             self._emit_call_completed_event(
                 response=final_content,
                 call_type=LLMCallType.LLM_CALL,
@@ -1760,6 +1810,8 @@ class AnthropicCompletion(BaseLLM):
                 from_agent=from_agent,
                 messages=follow_up_params["messages"],
                 usage=follow_up_usage,
+                finish_reason=finish_reason,
+                response_id=final_response_id,
             )
 
             total_usage = {
@@ -1813,6 +1865,20 @@ class AnthropicCompletion(BaseLLM):
 
         return int(200000 * CONTEXT_WINDOW_USAGE_RATIO)
 
+    @staticmethod
+    def _extract_finish_reason_and_id(
+        message: Any,
+    ) -> tuple[str | None, str | None]:
+        """Extract raw finish_reason and response_id from an Anthropic
+        ``Message`` / ``BetaMessage``. Anthropic exposes ``stop_reason`` (e.g.
+        ``"end_turn"``, ``"max_tokens"``, ``"tool_use"``); we forward it raw
+        and let downstream telemetry map to the OTel GenAI enum.
+        """
+        return (
+            getattr(message, "stop_reason", None),
+            getattr(message, "id", None),
+        )
+
     @staticmethod
     def _extract_anthropic_token_usage(
         response: Message | BetaMessage,

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

@@ -9,6 +9,7 @@ from urllib.parse import urlparse
 from pydantic import BaseModel, PrivateAttr, model_validator
 from typing_extensions import Self
 
+from crewai.llms._finish_reason_utils import extract_choices_finish_reason_and_id
 from crewai.llms.hooks.base import BaseInterceptor
 from crewai.utilities.agent_utils import is_context_length_exceeded
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
@@ -783,6 +784,8 @@ class AzureCompletion(BaseLLM):
         from_task: Any | None = None,
         from_agent: Any | None = None,
         usage: dict[str, Any] | None = None,
+        finish_reason: str | None = None,
+        response_id: str | None = None,
     ) -> BaseModel:
         """Validate content against response model and emit completion event.
 
@@ -792,6 +795,8 @@ class AzureCompletion(BaseLLM):
             params: Completion parameters containing messages
             from_task: Task that initiated the call
             from_agent: Agent that initiated the call
+            finish_reason: Raw provider finish reason.
+            response_id: Raw provider response id.
 
         Returns:
             Validated Pydantic model instance
@@ -809,6 +814,8 @@ class AzureCompletion(BaseLLM):
                 from_agent=from_agent,
                 messages=params["messages"],
                 usage=usage,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
 
             return structured_data
@@ -848,6 +855,8 @@ class AzureCompletion(BaseLLM):
         usage = self._extract_azure_token_usage(response)
         self._track_token_usage_internal(usage)
 
+        finish_reason, response_id = self._extract_finish_reason_and_id(response)
+
         # Without available_functions, return tool_calls so the caller (executor) handles execution
         if message.tool_calls and not available_functions:
             self._emit_call_completed_event(
@@ -857,6 +866,8 @@ class AzureCompletion(BaseLLM):
                 from_agent=from_agent,
                 messages=params["messages"],
                 usage=usage,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
             return list(message.tool_calls)
 
@@ -892,6 +903,8 @@ class AzureCompletion(BaseLLM):
                 from_task=from_task,
                 from_agent=from_agent,
                 usage=usage,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
 
         content = self._apply_stop_words(content)
@@ -903,6 +916,8 @@ class AzureCompletion(BaseLLM):
             from_agent=from_agent,
             messages=params["messages"],
             usage=usage,
+            finish_reason=finish_reason,
+            response_id=response_id,
         )
 
         return self._invoke_after_llm_call_hooks(
@@ -1011,6 +1026,8 @@ class AzureCompletion(BaseLLM):
         from_task: Any | None = None,
         from_agent: Any | None = None,
         response_model: type[BaseModel] | None = None,
+        finish_reason: str | None = None,
+        response_id: str | None = None,
     ) -> str | Any:
         """Finalize streaming response with usage tracking, tool execution, and events.
 
@@ -1039,6 +1056,8 @@ class AzureCompletion(BaseLLM):
                 from_task=from_task,
                 from_agent=from_agent,
                 usage=usage_data,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
 
         # Without available_functions, return tool calls in OpenAI-compatible format for the executor
@@ -1061,6 +1080,8 @@ class AzureCompletion(BaseLLM):
                 from_agent=from_agent,
                 messages=params["messages"],
                 usage=usage_data,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
             return formatted_tool_calls
 
@@ -1094,6 +1115,8 @@ class AzureCompletion(BaseLLM):
             from_agent=from_agent,
             messages=params["messages"],
             usage=usage_data,
+            finish_reason=finish_reason,
+            response_id=response_id,
         )
 
         return self._invoke_after_llm_call_hooks(
@@ -1113,8 +1136,16 @@ class AzureCompletion(BaseLLM):
         tool_calls: dict[int, dict[str, Any]] = {}
 
         usage_data: dict[str, Any] | None = None
+        stream_finish_reason: str | None = None
+        stream_response_id: str | None = None
         for update in self._get_sync_client().complete(**params):
             if isinstance(update, StreamingChatCompletionsUpdate):
+                chunk_finish, chunk_id = self._extract_finish_reason_and_id(update)
+                if chunk_finish:
+                    stream_finish_reason = chunk_finish
+                if chunk_id:
+                    stream_response_id = chunk_id
+
                 if update.usage:
                     usage = update.usage
                     usage_data = {
@@ -1141,6 +1172,8 @@ class AzureCompletion(BaseLLM):
             from_task=from_task,
             from_agent=from_agent,
             response_model=response_model,
+            finish_reason=stream_finish_reason,
+            response_id=stream_response_id,
         )
 
     async def _ahandle_completion(
@@ -1180,10 +1213,18 @@ class AzureCompletion(BaseLLM):
         tool_calls: dict[int, dict[str, Any]] = {}
 
         usage_data: dict[str, Any] | None = None
+        stream_finish_reason: str | None = None
+        stream_response_id: str | None = None
 
         stream = await self._get_async_client().complete(**params)
         async for update in stream:
             if isinstance(update, StreamingChatCompletionsUpdate):
+                chunk_finish, chunk_id = self._extract_finish_reason_and_id(update)
+                if chunk_finish:
+                    stream_finish_reason = chunk_finish
+                if chunk_id:
+                    stream_response_id = chunk_id
+
                 if hasattr(update, "usage") and update.usage:
                     usage = update.usage
                     usage_data = {
@@ -1210,6 +1251,8 @@ class AzureCompletion(BaseLLM):
             from_task=from_task,
             from_agent=from_agent,
             response_model=response_model,
+            finish_reason=stream_finish_reason,
+            response_id=stream_response_id,
         )
 
     def supports_function_calling(self) -> bool:
@@ -1271,6 +1314,19 @@ class AzureCompletion(BaseLLM):
 
         return int(8192 * CONTEXT_WINDOW_USAGE_RATIO)
 
+    def _effective_max_tokens(self) -> int | float | None:
+        """Azure reasoning/newer chat models cap via ``max_completion_tokens``."""
+        return self.max_tokens or self.max_completion_tokens
+
+    @staticmethod
+    def _extract_finish_reason_and_id(
+        response_or_update: Any,
+    ) -> tuple[str | None, str | None]:
+        """Azure ``ChatCompletions`` / ``StreamingChatCompletionsUpdate``
+        share the choices-shape; delegate to the shared extractor.
+        """
+        return extract_choices_finish_reason_and_id(response_or_update)
+
     @staticmethod
     def _extract_azure_token_usage(response: ChatCompletions) -> dict[str, Any]:
         """Extract token usage and response metadata from Azure response."""

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

@@ -677,7 +677,7 @@ class BedrockCompletion(BaseLLM):
             if usage:
                 self._track_token_usage_internal(usage)
 
-            stop_reason = response.get("stopReason")
+            stop_reason, response_id = self._extract_finish_reason_and_id(response)
             if stop_reason:
                 logging.debug(f"Response stop reason: {stop_reason}")
                 if stop_reason == "max_tokens":
@@ -716,6 +716,8 @@ class BedrockCompletion(BaseLLM):
                                 from_agent=from_agent,
                                 messages=messages,
                                 usage=usage,
+                                finish_reason=stop_reason,
+                                response_id=response_id,
                             )
                             return result
                         except Exception as e:
@@ -738,6 +740,8 @@ class BedrockCompletion(BaseLLM):
                     from_agent=from_agent,
                     messages=messages,
                     usage=usage,
+                    finish_reason=stop_reason,
+                    response_id=response_id,
                 )
                 return non_structured_output_tool_uses
 
@@ -812,6 +816,8 @@ class BedrockCompletion(BaseLLM):
                 from_agent=from_agent,
                 messages=messages,
                 usage=usage,
+                finish_reason=stop_reason,
+                response_id=response_id,
             )
 
             return self._invoke_after_llm_call_hooks(
@@ -951,7 +957,9 @@ class BedrockCompletion(BaseLLM):
             )
 
             stream = response.get("stream")
-            response_id = None
+            _, stream_response_id = self._extract_finish_reason_and_id(response)
+            response_id = stream_response_id
+            stream_finish_reason: str | None = None
             if stream:
                 for event in stream:
                     if "messageStart" in event:
@@ -1042,6 +1050,9 @@ class BedrockCompletion(BaseLLM):
                                     result = response_model.model_validate(
                                         function_args
                                     )
+                                    # contentBlockStop fires before messageStop sets
+                                    # stream_finish_reason; structured output always
+                                    # completes via the tool-call path.
                                     self._emit_call_completed_event(
                                         response=result.model_dump_json(),
                                         call_type=LLMCallType.LLM_CALL,
@@ -1049,6 +1060,9 @@ class BedrockCompletion(BaseLLM):
                                         from_agent=from_agent,
                                         messages=messages,
                                         usage=usage_data,
+                                        finish_reason=stream_finish_reason
+                                        or "tool_use",
+                                        response_id=response_id,
                                     )
                                     return result  # type: ignore[return-value]
                                 except Exception as e:
@@ -1102,6 +1116,7 @@ class BedrockCompletion(BaseLLM):
                             tool_use_id = None
                     elif "messageStop" in event:
                         stop_reason = event["messageStop"].get("stopReason")
+                        stream_finish_reason = stop_reason
                         logging.debug(f"Streaming message stopped: {stop_reason}")
                         if stop_reason == "max_tokens":
                             logging.warning(
@@ -1147,6 +1162,8 @@ class BedrockCompletion(BaseLLM):
             from_agent=from_agent,
             messages=messages,
             usage=usage_data,
+            finish_reason=stream_finish_reason,
+            response_id=response_id,
         )
 
         return full_response
@@ -1262,7 +1279,7 @@ class BedrockCompletion(BaseLLM):
             if usage:
                 self._track_token_usage_internal(usage)
 
-            stop_reason = response.get("stopReason")
+            stop_reason, response_id = self._extract_finish_reason_and_id(response)
             if stop_reason:
                 logging.debug(f"Response stop reason: {stop_reason}")
                 if stop_reason == "max_tokens":
@@ -1300,6 +1317,8 @@ class BedrockCompletion(BaseLLM):
                                 from_agent=from_agent,
                                 messages=messages,
                                 usage=usage,
+                                finish_reason=stop_reason,
+                                response_id=response_id,
                             )
                             return result
                         except Exception as e:
@@ -1322,6 +1341,8 @@ class BedrockCompletion(BaseLLM):
                     from_agent=from_agent,
                     messages=messages,
                     usage=usage,
+                    finish_reason=stop_reason,
+                    response_id=response_id,
                 )
                 return non_structured_output_tool_uses
 
@@ -1397,6 +1418,8 @@ class BedrockCompletion(BaseLLM):
                 from_agent=from_agent,
                 messages=messages,
                 usage=usage,
+                finish_reason=stop_reason,
+                response_id=response_id,
             )
 
             return text_content
@@ -1531,7 +1554,9 @@ class BedrockCompletion(BaseLLM):
             )
 
             stream = response.get("stream")
-            response_id = None
+            _, stream_response_id = self._extract_finish_reason_and_id(response)
+            response_id = stream_response_id
+            stream_finish_reason: str | None = None
             if stream:
                 async for event in stream:
                     if "messageStart" in event:
@@ -1623,6 +1648,9 @@ class BedrockCompletion(BaseLLM):
                                     result = response_model.model_validate(
                                         function_args
                                     )
+                                    # contentBlockStop fires before messageStop sets
+                                    # stream_finish_reason; structured output always
+                                    # completes via the tool-call path.
                                     self._emit_call_completed_event(
                                         response=result.model_dump_json(),
                                         call_type=LLMCallType.LLM_CALL,
@@ -1630,6 +1658,9 @@ class BedrockCompletion(BaseLLM):
                                         from_agent=from_agent,
                                         messages=messages,
                                         usage=usage_data,
+                                        finish_reason=stream_finish_reason
+                                        or "tool_use",
+                                        response_id=response_id,
                                     )
                                     return result  # type: ignore[return-value]
                                 except Exception as e:
@@ -1687,6 +1718,7 @@ class BedrockCompletion(BaseLLM):
 
                     elif "messageStop" in event:
                         stop_reason = event["messageStop"].get("stopReason")
+                        stream_finish_reason = stop_reason
                         logging.debug(f"Streaming message stopped: {stop_reason}")
                         if stop_reason == "max_tokens":
                             logging.warning(
@@ -1733,6 +1765,8 @@ class BedrockCompletion(BaseLLM):
             from_agent=from_agent,
             messages=messages,
             usage=usage_data,
+            finish_reason=stream_finish_reason,
+            response_id=response_id,
         )
 
         return self._invoke_after_llm_call_hooks(
@@ -1988,6 +2022,25 @@ class BedrockCompletion(BaseLLM):
 
         return config
 
+    @staticmethod
+    def _extract_finish_reason_and_id(
+        response: Any,
+    ) -> tuple[str | None, str | None]:
+        """Extract raw finish_reason (``stopReason``) from a Bedrock Converse
+        response dict. Defensive — returns (None, None) on any failure.
+
+        Bedrock Converse has no model-level response id; ResponseMetadata.RequestId
+        is an AWS infra trace id (semantically different from OpenAI's chatcmpl-XXX),
+        so we omit response_id rather than mislead downstream telemetry consumers.
+        """
+        finish_reason: str | None = None
+        try:
+            if isinstance(response, dict):
+                finish_reason = response.get("stopReason")
+        except (AttributeError, KeyError, TypeError, IndexError):
+            finish_reason = None
+        return finish_reason, None
+
     def _handle_client_error(self, e: ClientError) -> str:
         """Handle AWS ClientError with specific error codes and return error message."""
         error_code = e.response.get("Error", {}).get("Code", "Unknown")

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

@@ -682,6 +682,8 @@ class GeminiCompletion(BaseLLM):
         from_task: Any | None = None,
         from_agent: Any | None = None,
         usage: dict[str, Any] | None = None,
+        finish_reason: str | None = None,
+        response_id: str | None = None,
     ) -> BaseModel:
         """Validate content against response model and emit completion event.
 
@@ -691,6 +693,8 @@ class GeminiCompletion(BaseLLM):
             messages_for_event: Messages to include in event
             from_task: Task that initiated the call
             from_agent: Agent that initiated the call
+            finish_reason: Raw provider finish reason.
+            response_id: Raw provider response id.
 
         Returns:
             Validated Pydantic model instance
@@ -708,6 +712,8 @@ class GeminiCompletion(BaseLLM):
                 from_agent=from_agent,
                 messages=messages_for_event,
                 usage=usage,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
 
             return structured_data
@@ -724,6 +730,8 @@ class GeminiCompletion(BaseLLM):
         from_task: Any | None = None,
         from_agent: Any | None = None,
         usage: dict[str, Any] | None = None,
+        finish_reason: str | None = None,
+        response_id: str | None = None,
     ) -> str | BaseModel:
         """Finalize completion response with validation and event emission.
 
@@ -747,6 +755,8 @@ class GeminiCompletion(BaseLLM):
                 from_task=from_task,
                 from_agent=from_agent,
                 usage=usage,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
 
         self._emit_call_completed_event(
@@ -756,6 +766,8 @@ class GeminiCompletion(BaseLLM):
             from_agent=from_agent,
             messages=messages_for_event,
             usage=usage,
+            finish_reason=finish_reason,
+            response_id=response_id,
         )
 
         return self._invoke_after_llm_call_hooks(
@@ -770,6 +782,8 @@ class GeminiCompletion(BaseLLM):
         from_task: Any | None = None,
         from_agent: Any | None = None,
         usage: dict[str, Any] | None = None,
+        finish_reason: str | None = None,
+        response_id: str | None = None,
     ) -> BaseModel:
         """Validate and emit event for structured_output tool call.
 
@@ -795,6 +809,8 @@ class GeminiCompletion(BaseLLM):
                 from_agent=from_agent,
                 messages=self._convert_contents_to_dict(contents),
                 usage=usage,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
             return validated_data
         except Exception as e:
@@ -828,6 +844,8 @@ class GeminiCompletion(BaseLLM):
         Returns:
             Final response content or function call result
         """
+        finish_reason, response_id = self._extract_finish_reason_and_id(response)
+
         if response.candidates and (self.tools or available_functions):
             candidate = response.candidates[0]
             if candidate.content and candidate.content.parts:
@@ -854,6 +872,8 @@ class GeminiCompletion(BaseLLM):
                                 from_task=from_task,
                                 from_agent=from_agent,
                                 usage=usage,
+                                finish_reason=finish_reason,
+                                response_id=response_id,
                             )
 
                 non_structured_output_parts = [
@@ -875,6 +895,8 @@ class GeminiCompletion(BaseLLM):
                         from_agent=from_agent,
                         messages=self._convert_contents_to_dict(contents),
                         usage=usage,
+                        finish_reason=finish_reason,
+                        response_id=response_id,
                     )
                     return non_structured_output_parts
 
@@ -915,6 +937,8 @@ class GeminiCompletion(BaseLLM):
             from_task=from_task,
             from_agent=from_agent,
             usage=usage,
+            finish_reason=finish_reason,
+            response_id=response_id,
         )
 
     def _process_stream_chunk(
@@ -925,7 +949,13 @@ class GeminiCompletion(BaseLLM):
         usage_data: dict[str, int] | None,
         from_task: Any | None = None,
         from_agent: Any | None = None,
-    ) -> tuple[str, dict[int, dict[str, Any]], dict[str, int] | None]:
+    ) -> tuple[
+        str,
+        dict[int, dict[str, Any]],
+        dict[str, int] | None,
+        str | None,
+        str | None,
+    ]:
         """Process a single streaming chunk.
 
         Args:
@@ -937,9 +967,13 @@ class GeminiCompletion(BaseLLM):
             from_agent: Agent that initiated the call
 
         Returns:
-            Tuple of (updated full_response, updated function_calls, updated usage_data)
+            Tuple of (updated full_response, updated function_calls, updated
+            usage_data, chunk finish_reason, chunk response_id).
         """
         response_id = chunk.response_id if hasattr(chunk, "response_id") else None
+        chunk_finish_reason, chunk_response_id = self._extract_finish_reason_and_id(
+            chunk
+        )
         if chunk.usage_metadata:
             usage_data = self._extract_token_usage(chunk)
 
@@ -996,7 +1030,13 @@ class GeminiCompletion(BaseLLM):
                             response_id=response_id,
                         )
 
-        return full_response, function_calls, usage_data
+        return (
+            full_response,
+            function_calls,
+            usage_data,
+            chunk_finish_reason,
+            chunk_response_id,
+        )
 
     def _finalize_streaming_response(
         self,
@@ -1008,6 +1048,8 @@ class GeminiCompletion(BaseLLM):
         from_task: Any | None = None,
         from_agent: Any | None = None,
         response_model: type[BaseModel] | None = None,
+        finish_reason: str | None = None,
+        response_id: str | None = None,
     ) -> str | BaseModel | list[dict[str, Any]]:
         """Finalize streaming response with usage tracking, function execution, and events.
 
@@ -1038,6 +1080,8 @@ class GeminiCompletion(BaseLLM):
                         from_task=from_task,
                         from_agent=from_agent,
                         usage=usage_data,
+                        finish_reason=finish_reason,
+                        response_id=response_id,
                     )
 
         non_structured_output_calls = {
@@ -1058,6 +1102,8 @@ class GeminiCompletion(BaseLLM):
                 from_agent=from_agent,
                 messages=self._convert_contents_to_dict(contents),
                 usage=usage_data,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
             return raw_parts
 
@@ -1095,6 +1141,8 @@ class GeminiCompletion(BaseLLM):
             from_task=from_task,
             from_agent=from_agent,
             usage=usage_data,
+            finish_reason=finish_reason,
+            response_id=response_id,
         )
 
     def _handle_completion(
@@ -1148,6 +1196,8 @@ class GeminiCompletion(BaseLLM):
         full_response = ""
         function_calls: dict[int, dict[str, Any]] = {}
         usage_data: dict[str, int] | None = None
+        stream_finish_reason: str | None = None
+        stream_response_id: str | None = None
 
         # The API accepts list[Content] but mypy is overly strict about variance
         contents_for_api: Any = contents
@@ -1156,7 +1206,13 @@ class GeminiCompletion(BaseLLM):
             contents=contents_for_api,
             config=config,
         ):
-            full_response, function_calls, usage_data = self._process_stream_chunk(
+            (
+                full_response,
+                function_calls,
+                usage_data,
+                chunk_finish_reason,
+                chunk_response_id,
+            ) = self._process_stream_chunk(
                 chunk=chunk,
                 full_response=full_response,
                 function_calls=function_calls,
@@ -1164,6 +1220,10 @@ class GeminiCompletion(BaseLLM):
                 from_task=from_task,
                 from_agent=from_agent,
             )
+            if chunk_finish_reason:
+                stream_finish_reason = chunk_finish_reason
+            if chunk_response_id:
+                stream_response_id = chunk_response_id
 
         return self._finalize_streaming_response(
             full_response=full_response,
@@ -1174,6 +1234,8 @@ class GeminiCompletion(BaseLLM):
             from_task=from_task,
             from_agent=from_agent,
             response_model=response_model,
+            finish_reason=stream_finish_reason,
+            response_id=stream_response_id,
         )
 
     async def _ahandle_completion(
@@ -1227,6 +1289,8 @@ class GeminiCompletion(BaseLLM):
         full_response = ""
         function_calls: dict[int, dict[str, Any]] = {}
         usage_data: dict[str, int] | None = None
+        stream_finish_reason: str | None = None
+        stream_response_id: str | None = None
 
         # The API accepts list[Content] but mypy is overly strict about variance
         contents_for_api: Any = contents
@@ -1236,7 +1300,13 @@ class GeminiCompletion(BaseLLM):
             config=config,
         )
         async for chunk in stream:
-            full_response, function_calls, usage_data = self._process_stream_chunk(
+            (
+                full_response,
+                function_calls,
+                usage_data,
+                chunk_finish_reason,
+                chunk_response_id,
+            ) = self._process_stream_chunk(
                 chunk=chunk,
                 full_response=full_response,
                 function_calls=function_calls,
@@ -1244,6 +1314,10 @@ class GeminiCompletion(BaseLLM):
                 from_task=from_task,
                 from_agent=from_agent,
             )
+            if chunk_finish_reason:
+                stream_finish_reason = chunk_finish_reason
+            if chunk_response_id:
+                stream_response_id = chunk_response_id
 
         return self._finalize_streaming_response(
             full_response=full_response,
@@ -1254,6 +1328,8 @@ class GeminiCompletion(BaseLLM):
             from_task=from_task,
             from_agent=from_agent,
             response_model=response_model,
+            finish_reason=stream_finish_reason,
+            response_id=stream_response_id,
         )
 
     def supports_function_calling(self) -> bool:
@@ -1300,6 +1376,34 @@ class GeminiCompletion(BaseLLM):
 
         return int(1048576 * CONTEXT_WINDOW_USAGE_RATIO)  # 1M tokens default
 
+    def _effective_max_tokens(self) -> int | float | None:
+        """Gemini caps generation via ``max_output_tokens``."""
+        return self.max_output_tokens or self.max_tokens
+
+    @staticmethod
+    def _extract_finish_reason_and_id(
+        response: Any,
+    ) -> tuple[str | None, str | None]:
+        """Extract raw finish_reason and response_id from a Gemini
+        ``GenerateContentResponse``. ``finish_reason`` is the protobuf enum's
+        ``.name`` attribute (e.g. ``"STOP"``, ``"MAX_TOKENS"``); we forward
+        it raw and let downstream telemetry map to the OTel GenAI enum.
+        """
+        raw_response_id = getattr(response, "response_id", None)
+        response_id = raw_response_id if isinstance(raw_response_id, str) else None
+
+        finish_reason: str | None = None
+        candidates = getattr(response, "candidates", None)
+        if candidates:
+            try:
+                candidate_finish = getattr(candidates[0], "finish_reason", None)
+            except (IndexError, TypeError, KeyError):
+                candidate_finish = None
+            if candidate_finish is not None:
+                name = getattr(candidate_finish, "name", None)
+                finish_reason = name if isinstance(name, str) else None
+        return finish_reason, response_id
+
     @staticmethod
     def _extract_token_usage(response: GenerateContentResponse) -> dict[str, Any]:
         """Extract token usage and response metadata from Gemini response."""

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

@@ -29,6 +29,7 @@ from openai.types.responses import (
 from pydantic import BaseModel, PrivateAttr, model_validator
 
 from crewai.events.types.llm_events import LLMCallType
+from crewai.llms._finish_reason_utils import extract_choices_finish_reason_and_id
 from crewai.llms.base_llm import BaseLLM, JsonResponseFormat, llm_call_context
 from crewai.llms.hooks.base import BaseInterceptor
 from crewai.llms.hooks.transport import AsyncHTTPTransport, HTTPTransport
@@ -825,6 +826,10 @@ class OpenAICompletion(BaseLLM):
             usage = self._extract_responses_token_usage(response)
             self._track_token_usage_internal(usage)
 
+            finish_reason, response_id = self._extract_responses_finish_reason_and_id(
+                response
+            )
+
             if self.parse_tool_outputs:
                 parsed_result = self._extract_builtin_tool_outputs(response)
                 parsed_result.text = self._apply_stop_words(parsed_result.text)
@@ -836,6 +841,8 @@ class OpenAICompletion(BaseLLM):
                     from_agent=from_agent,
                     messages=params.get("input", []),
                     usage=usage,
+                    finish_reason=finish_reason,
+                    response_id=response_id,
                 )
 
                 return parsed_result
@@ -849,6 +856,8 @@ class OpenAICompletion(BaseLLM):
                     from_agent=from_agent,
                     messages=params.get("input", []),
                     usage=usage,
+                    finish_reason=finish_reason,
+                    response_id=response_id,
                 )
                 return function_calls
 
@@ -887,6 +896,8 @@ class OpenAICompletion(BaseLLM):
                         from_agent=from_agent,
                         messages=params.get("input", []),
                         usage=usage,
+                        finish_reason=finish_reason,
+                        response_id=response_id,
                     )
                     return structured_result
                 except ValueError as e:
@@ -901,6 +912,8 @@ class OpenAICompletion(BaseLLM):
                 from_agent=from_agent,
                 messages=params.get("input", []),
                 usage=usage,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
 
             content = self._invoke_after_llm_call_hooks(
@@ -960,6 +973,10 @@ class OpenAICompletion(BaseLLM):
             usage = self._extract_responses_token_usage(response)
             self._track_token_usage_internal(usage)
 
+            finish_reason, response_id = self._extract_responses_finish_reason_and_id(
+                response
+            )
+
             if self.parse_tool_outputs:
                 parsed_result = self._extract_builtin_tool_outputs(response)
                 parsed_result.text = self._apply_stop_words(parsed_result.text)
@@ -971,6 +988,8 @@ class OpenAICompletion(BaseLLM):
                     from_agent=from_agent,
                     messages=params.get("input", []),
                     usage=usage,
+                    finish_reason=finish_reason,
+                    response_id=response_id,
                 )
 
                 return parsed_result
@@ -984,6 +1003,8 @@ class OpenAICompletion(BaseLLM):
                     from_agent=from_agent,
                     messages=params.get("input", []),
                     usage=usage,
+                    finish_reason=finish_reason,
+                    response_id=response_id,
                 )
                 return function_calls
 
@@ -1022,6 +1043,8 @@ class OpenAICompletion(BaseLLM):
                         from_agent=from_agent,
                         messages=params.get("input", []),
                         usage=usage,
+                        finish_reason=finish_reason,
+                        response_id=response_id,
                     )
                     return structured_result
                 except ValueError as e:
@@ -1036,6 +1059,8 @@ class OpenAICompletion(BaseLLM):
                 from_agent=from_agent,
                 messages=params.get("input", []),
                 usage=usage,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
 
         except NotFoundError as e:
@@ -1123,6 +1148,12 @@ class OpenAICompletion(BaseLLM):
                     usage = self._extract_responses_token_usage(event.response)
                     self._track_token_usage_internal(usage)
 
+        finish_reason, response_id = (
+            self._extract_responses_finish_reason_and_id(final_response)
+            if final_response is not None
+            else (None, response_id_stream)
+        )
+
         if self.parse_tool_outputs and final_response:
             parsed_result = self._extract_builtin_tool_outputs(final_response)
             parsed_result.text = self._apply_stop_words(parsed_result.text)
@@ -1134,6 +1165,8 @@ class OpenAICompletion(BaseLLM):
                 from_agent=from_agent,
                 messages=params.get("input", []),
                 usage=usage,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
 
             return parsed_result
@@ -1171,6 +1204,8 @@ class OpenAICompletion(BaseLLM):
                     from_agent=from_agent,
                     messages=params.get("input", []),
                     usage=usage,
+                    finish_reason=finish_reason,
+                    response_id=response_id,
                 )
                 return structured_result
             except ValueError as e:
@@ -1185,6 +1220,8 @@ class OpenAICompletion(BaseLLM):
             from_agent=from_agent,
             messages=params.get("input", []),
             usage=usage,
+            finish_reason=finish_reason,
+            response_id=response_id,
         )
 
         return self._invoke_after_llm_call_hooks(
@@ -1248,6 +1285,12 @@ class OpenAICompletion(BaseLLM):
                     usage = self._extract_responses_token_usage(event.response)
                     self._track_token_usage_internal(usage)
 
+        finish_reason, response_id = (
+            self._extract_responses_finish_reason_and_id(final_response)
+            if final_response is not None
+            else (None, response_id_stream)
+        )
+
         if self.parse_tool_outputs and final_response:
             parsed_result = self._extract_builtin_tool_outputs(final_response)
             parsed_result.text = self._apply_stop_words(parsed_result.text)
@@ -1259,6 +1302,8 @@ class OpenAICompletion(BaseLLM):
                 from_agent=from_agent,
                 messages=params.get("input", []),
                 usage=usage,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
 
             return parsed_result
@@ -1296,6 +1341,8 @@ class OpenAICompletion(BaseLLM):
                     from_agent=from_agent,
                     messages=params.get("input", []),
                     usage=usage,
+                    finish_reason=finish_reason,
+                    response_id=response_id,
                 )
                 return structured_result
             except ValueError as e:
@@ -1310,6 +1357,8 @@ class OpenAICompletion(BaseLLM):
             from_agent=from_agent,
             messages=params.get("input", []),
             usage=usage,
+            finish_reason=finish_reason,
+            response_id=response_id,
         )
 
         return full_response
@@ -1603,6 +1652,9 @@ class OpenAICompletion(BaseLLM):
                 usage = self._extract_openai_token_usage(parsed_response)
                 self._track_token_usage_internal(usage)
 
+                parsed_finish_reason, parsed_response_id = (
+                    self._extract_chat_finish_reason_and_id(parsed_response)
+                )
                 parsed_object = parsed_response.choices[0].message.parsed
                 if parsed_object:
                     self._emit_call_completed_event(
@@ -1612,6 +1664,8 @@ class OpenAICompletion(BaseLLM):
                         from_agent=from_agent,
                         messages=params["messages"],
                         usage=usage,
+                        finish_reason=parsed_finish_reason,
+                        response_id=parsed_response_id,
                     )
                     return parsed_object
 
@@ -1625,6 +1679,9 @@ class OpenAICompletion(BaseLLM):
 
             choice: Choice = response.choices[0]
             message = choice.message
+            finish_reason, response_id = self._extract_chat_finish_reason_and_id(
+                response
+            )
 
             # Without available_functions, return tool_calls so the caller (executor) handles execution
             if message.tool_calls and not available_functions:
@@ -1635,6 +1692,8 @@ class OpenAICompletion(BaseLLM):
                     from_agent=from_agent,
                     messages=params["messages"],
                     usage=usage,
+                    finish_reason=finish_reason,
+                    response_id=response_id,
                 )
                 return list(message.tool_calls)
 
@@ -1675,6 +1734,8 @@ class OpenAICompletion(BaseLLM):
                         from_agent=from_agent,
                         messages=params["messages"],
                         usage=usage,
+                        finish_reason=finish_reason,
+                        response_id=response_id,
                     )
                     return structured_result
                 except ValueError as e:
@@ -1689,6 +1750,8 @@ class OpenAICompletion(BaseLLM):
                 from_agent=from_agent,
                 messages=params["messages"],
                 usage=usage,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
 
             if usage.get("total_tokens", 0) > 0:
@@ -1734,6 +1797,8 @@ class OpenAICompletion(BaseLLM):
         available_functions: dict[str, Any] | None = None,
         from_task: Any | None = None,
         from_agent: Any | None = None,
+        finish_reason: str | None = None,
+        response_id: str | None = None,
     ) -> str | list[dict[str, Any]]:
         """Finalize a streaming response with usage tracking, tool call handling, and events.
 
@@ -1745,6 +1810,9 @@ class OpenAICompletion(BaseLLM):
             available_functions: Available functions for tool calling.
             from_task: Task that initiated the call.
             from_agent: Agent that initiated the call.
+            finish_reason: Raw provider finish reason (e.g. "stop", "length",
+                "tool_calls") extracted from the last streaming chunk.
+            response_id: Raw provider response id from any chunk.
 
         Returns:
             Tool calls list when tools were invoked without available_functions,
@@ -1774,6 +1842,8 @@ class OpenAICompletion(BaseLLM):
                 from_agent=from_agent,
                 messages=params["messages"],
                 usage=usage_data,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
             return tool_calls_list
 
@@ -1817,6 +1887,8 @@ class OpenAICompletion(BaseLLM):
             from_agent=from_agent,
             messages=params["messages"],
             usage=usage_data,
+            finish_reason=finish_reason,
+            response_id=response_id,
         )
 
         return full_response
@@ -1861,6 +1933,9 @@ class OpenAICompletion(BaseLLM):
                 if final_completion:
                     usage = self._extract_openai_token_usage(final_completion)
                     self._track_token_usage_internal(usage)
+                    parsed_finish_reason, parsed_response_id = (
+                        self._extract_chat_finish_reason_and_id(final_completion)
+                    )
                     if final_completion.choices:
                         parsed_result = final_completion.choices[0].message.parsed
                         if parsed_result:
@@ -1871,6 +1946,8 @@ class OpenAICompletion(BaseLLM):
                                 from_agent=from_agent,
                                 messages=params["messages"],
                                 usage=usage,
+                                finish_reason=parsed_finish_reason,
+                                response_id=parsed_response_id,
                             )
                             return parsed_result
 
@@ -1882,11 +1959,15 @@ class OpenAICompletion(BaseLLM):
         )
 
         usage_data: dict[str, Any] | None = None
+        stream_finish_reason: str | None = None
+        stream_response_id: str | None = None
 
         for completion_chunk in completion_stream:
             response_id_stream = (
                 completion_chunk.id if hasattr(completion_chunk, "id") else None
             )
+            if response_id_stream:
+                stream_response_id = response_id_stream
 
             if hasattr(completion_chunk, "usage") and completion_chunk.usage:
                 usage_data = self._extract_openai_token_usage(completion_chunk)
@@ -1897,6 +1978,9 @@ class OpenAICompletion(BaseLLM):
 
             choice = completion_chunk.choices[0]
             chunk_delta: ChoiceDelta = choice.delta
+            chunk_finish = getattr(choice, "finish_reason", None)
+            if chunk_finish:
+                stream_finish_reason = chunk_finish
 
             if chunk_delta.content:
                 full_response += chunk_delta.content
@@ -1954,6 +2038,8 @@ class OpenAICompletion(BaseLLM):
             available_functions=available_functions,
             from_task=from_task,
             from_agent=from_agent,
+            finish_reason=stream_finish_reason,
+            response_id=stream_response_id,
         )
         if isinstance(result, str):
             return self._invoke_after_llm_call_hooks(
@@ -1989,6 +2075,9 @@ class OpenAICompletion(BaseLLM):
                 usage = self._extract_openai_token_usage(parsed_response)
                 self._track_token_usage_internal(usage)
 
+                parsed_finish_reason, parsed_response_id = (
+                    self._extract_chat_finish_reason_and_id(parsed_response)
+                )
                 parsed_object = parsed_response.choices[0].message.parsed
                 if parsed_object:
                     self._emit_call_completed_event(
@@ -1998,6 +2087,8 @@ class OpenAICompletion(BaseLLM):
                         from_agent=from_agent,
                         messages=params["messages"],
                         usage=usage,
+                        finish_reason=parsed_finish_reason,
+                        response_id=parsed_response_id,
                     )
                     return parsed_object
 
@@ -2011,6 +2102,9 @@ class OpenAICompletion(BaseLLM):
 
             choice: Choice = response.choices[0]
             message = choice.message
+            finish_reason, response_id = self._extract_chat_finish_reason_and_id(
+                response
+            )
 
             # Without available_functions, return tool_calls so the caller (executor) handles execution
             if message.tool_calls and not available_functions:
@@ -2021,6 +2115,8 @@ class OpenAICompletion(BaseLLM):
                     from_agent=from_agent,
                     messages=params["messages"],
                     usage=usage,
+                    finish_reason=finish_reason,
+                    response_id=response_id,
                 )
                 return list(message.tool_calls)
 
@@ -2065,6 +2161,8 @@ class OpenAICompletion(BaseLLM):
                         from_agent=from_agent,
                         messages=params["messages"],
                         usage=usage,
+                        finish_reason=finish_reason,
+                        response_id=response_id,
                     )
                     return structured_result
                 except ValueError as e:
@@ -2079,6 +2177,8 @@ class OpenAICompletion(BaseLLM):
                 from_agent=from_agent,
                 messages=params["messages"],
                 usage=usage,
+                finish_reason=finish_reason,
+                response_id=response_id,
             )
 
             if usage.get("total_tokens", 0) > 0:
@@ -2130,8 +2230,12 @@ class OpenAICompletion(BaseLLM):
 
             accumulated_content = ""
             usage_data: dict[str, Any] | None = None
+            parsed_stream_finish_reason: str | None = None
+            parsed_stream_response_id: str | None = None
             async for chunk in completion_stream:
                 response_id_stream = chunk.id if hasattr(chunk, "id") else None
+                if response_id_stream:
+                    parsed_stream_response_id = response_id_stream
 
                 if hasattr(chunk, "usage") and chunk.usage:
                     usage_data = self._extract_openai_token_usage(chunk)
@@ -2142,6 +2246,9 @@ class OpenAICompletion(BaseLLM):
 
                 choice = chunk.choices[0]
                 delta: ChoiceDelta = choice.delta
+                chunk_finish = getattr(choice, "finish_reason", None)
+                if chunk_finish:
+                    parsed_stream_finish_reason = chunk_finish
 
                 if delta.content:
                     accumulated_content += delta.content
@@ -2165,6 +2272,8 @@ class OpenAICompletion(BaseLLM):
                     from_agent=from_agent,
                     messages=params["messages"],
                     usage=usage_data,
+                    finish_reason=parsed_stream_finish_reason,
+                    response_id=parsed_stream_response_id,
                 )
 
                 return parsed_object
@@ -2177,6 +2286,8 @@ class OpenAICompletion(BaseLLM):
                     from_agent=from_agent,
                     messages=params["messages"],
                     usage=usage_data,
+                    finish_reason=parsed_stream_finish_reason,
+                    response_id=parsed_stream_response_id,
                 )
                 return accumulated_content
 
@@ -2185,9 +2296,13 @@ class OpenAICompletion(BaseLLM):
         ] = await self._get_async_client().chat.completions.create(**params)
 
         usage_data = None
+        stream_finish_reason: str | None = None
+        stream_response_id: str | None = None
 
         async for chunk in stream:
             response_id_stream = chunk.id if hasattr(chunk, "id") else None
+            if response_id_stream:
+                stream_response_id = response_id_stream
 
             if hasattr(chunk, "usage") and chunk.usage:
                 usage_data = self._extract_openai_token_usage(chunk)
@@ -2198,6 +2313,9 @@ class OpenAICompletion(BaseLLM):
 
             choice = chunk.choices[0]
             chunk_delta: ChoiceDelta = choice.delta
+            chunk_finish = getattr(choice, "finish_reason", None)
+            if chunk_finish:
+                stream_finish_reason = chunk_finish
 
             if chunk_delta.content:
                 full_response += chunk_delta.content
@@ -2255,6 +2373,8 @@ class OpenAICompletion(BaseLLM):
             available_functions=available_functions,
             from_task=from_task,
             from_agent=from_agent,
+            finish_reason=stream_finish_reason,
+            response_id=stream_response_id,
         )
 
     def supports_function_calling(self) -> bool:
@@ -2305,6 +2425,32 @@ class OpenAICompletion(BaseLLM):
 
         return int(8192 * CONTEXT_WINDOW_USAGE_RATIO)
 
+    def _effective_max_tokens(self) -> int | float | None:
+        """Newer OpenAI chat models cap via ``max_completion_tokens``."""
+        return self.max_tokens or self.max_completion_tokens
+
+    @staticmethod
+    def _extract_chat_finish_reason_and_id(
+        response: Any,
+    ) -> tuple[str | None, str | None]:
+        """ChatCompletion / ChatCompletionChunk share the choices-shape;
+        delegate to the shared extractor.
+        """
+        return extract_choices_finish_reason_and_id(response)
+
+    @staticmethod
+    def _extract_responses_finish_reason_and_id(
+        response: Any,
+    ) -> tuple[str | None, str | None]:
+        """Extract finish_reason and response_id from an OpenAI Responses
+        API ``Response`` object. The Responses API exposes ``status`` rather
+        than ``finish_reason``; we forward the raw status value.
+        """
+        return (
+            getattr(response, "status", None),
+            getattr(response, "id", None),
+        )
+
     def _extract_openai_token_usage(
         self, response: ChatCompletion | ChatCompletionChunk
     ) -> dict[str, Any]:

lib/crewai/src/crewai/memory/recall_flow.py

@@ -337,7 +337,7 @@ class RecallFlow(Flow[RecallState]):
     @router(re_search)
     def re_decide_depth(self) -> str:
         """Re-evaluate depth after re-search. Same logic as decide_depth."""
-        return self.decide_depth()  # type: ignore[call-arg]
+        return self.decide_depth()
 
     @listen("synthesize")
     def synthesize_results(self) -> list[MemoryMatch]:

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

@@ -0,0 +1,55 @@
+"""Pluggable default storage backend for the unified memory system.
+
+By default, :class:`~crewai.memory.unified_memory.Memory` builds a built-in
+vector store from its ``storage`` spec string (LanceDB, or Qdrant for the
+``"qdrant-edge"`` spec). Registering a factory via
+:func:`set_memory_storage_factory` lets an application route memory through a
+custom :class:`~crewai.memory.storage.backend.StorageBackend` -- a different
+vector store, a remote service, an in-memory fake for tests -- without
+subclassing ``Memory`` or threading an explicit ``storage=`` instance through
+every construction site.
+
+This mirrors :func:`crewai_core.lock_store.set_lock_backend`: a one-time,
+process-wide setter intended for application startup. Pass ``None`` to restore
+the built-in default.
+"""
+
+from __future__ import annotations
+
+from collections.abc import Callable
+from typing import TYPE_CHECKING
+
+
+if TYPE_CHECKING:
+    from crewai.memory.storage.backend import StorageBackend
+
+# Receives the raw ``storage`` spec string and returns a backend to use, or
+# ``None`` to defer to the built-in selection for that spec.
+MemoryStorageFactory = Callable[[str], "StorageBackend | None"]
+
+_factory: MemoryStorageFactory | None = None
+
+
+def set_memory_storage_factory(factory: MemoryStorageFactory | None) -> None:
+    """Replace the process-wide default memory storage factory.
+
+    Intended for one-time setup at startup. Pass ``None`` to restore the
+    built-in LanceDB/Qdrant selection. Only affects ``Memory`` instances
+    constructed afterwards; an explicit ``storage=`` instance always wins.
+
+    The factory is consulted for every string ``storage`` spec, so it must
+    return ``None`` for specs it does not handle to let the built-in
+    LanceDB/Qdrant/path selection take over.
+    """
+    global _factory
+    _factory = factory
+
+
+def resolve_memory_storage(spec: str) -> StorageBackend | None:
+    """Return the registered factory's backend for ``spec``, or ``None``.
+
+    ``None`` means no factory is registered or it declined this spec; the
+    caller then falls back to the built-in selection.
+    """
+    factory = _factory
+    return factory(spec) if factory is not None else None

lib/crewai/src/crewai/memory/unified_memory.py

@@ -204,7 +204,12 @@ class Memory(BaseModel):
         )
 
         if isinstance(self.storage, str):
-            if self.storage == "qdrant-edge":
+            from crewai.memory.storage.factory import resolve_memory_storage
+
+            custom = resolve_memory_storage(self.storage)
+            if custom is not None:
+                self._storage = custom
+            elif self.storage == "qdrant-edge":
                 from crewai.memory.storage.qdrant_edge_storage import QdrantEdgeStorage
 
                 self._storage = QdrantEdgeStorage()

lib/crewai/src/crewai/rag/factory.py

@@ -1,5 +1,6 @@
 """Factory functions for creating RAG clients from configuration."""
 
+from collections.abc import Callable
 from typing import cast
 
 from crewai.rag.config.optional_imports.protocols import (
@@ -11,6 +12,32 @@ from crewai.rag.core.base_client import BaseClient
 from crewai.utilities.import_utils import require
 
 
+# RAG uses a provider-keyed registry (rather than the single-default setter
+# used by the memory/knowledge/flow seams) because ``create_client`` already
+# dispatches on ``config.provider`` -- the natural seam here is per-provider.
+# A factory receives the RAG config and returns a client; one registered for a
+# built-in provider name overrides the built-in for that provider.
+RagClientFactory = Callable[[RagConfigType], BaseClient]
+
+_factories: dict[str, RagClientFactory] = {}
+
+
+def register_rag_client_factory(provider: str, factory: RagClientFactory) -> None:
+    """Register a client factory for a RAG ``provider`` name.
+
+    Lets an application plug in a client for a new provider, or override a
+    built-in provider (``"chromadb"`` / ``"qdrant"``), without modifying
+    :func:`create_client`. Registered factories take precedence over the
+    built-ins. Intended for one-time setup at startup.
+    """
+    _factories[provider] = factory
+
+
+def unregister_rag_client_factory(provider: str) -> None:
+    """Remove a previously registered factory; a no-op if none is registered."""
+    _factories.pop(provider, None)
+
+
 def create_client(config: RagConfigType) -> BaseClient:
     """Create a client from configuration using the appropriate factory.
 
@@ -24,6 +51,10 @@ def create_client(config: RagConfigType) -> BaseClient:
         ValueError: If the configuration provider is not supported.
     """
 
+    factory = _factories.get(config.provider)
+    if factory is not None:
+        return factory(config)
+
     if config.provider == "chromadb":
         chromadb_mod = cast(
             ChromaFactoryModule,

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

@@ -35,6 +35,8 @@
     "knowledge_search_query": "The original query is: {task_prompt}.",
     "knowledge_search_query_system_prompt": "Your goal is to rewrite the user query so that it is optimized for retrieval from a vector database. Consider how the query will be used to find relevant documents, and aim to make it more specific and context-aware. \n\n Do not include any other text than the rewritten query, especially any preamble or postamble and only add expected output format if its relevant to the rewritten query. \n\n Focus on the key words of the intended task and to retrieve the most relevant information. \n\n There will be some extra context provided that might need to be removed such as expected_output formats structured_outputs and other instructions.",
     "human_feedback_collapse": "Based on the following human feedback, determine which outcome best matches their intent.\n\nFeedback: {feedback}\n\nPossible outcomes: {outcomes}\n\nRespond with ONLY one of the exact outcome values listed above, nothing else.",
+    "conversational_system_prompt": "You are a helpful conversational assistant. Maintain context across turns, answer using the canonical message history when possible, and respond clearly and concisely. Ask for clarification when the user's intent is ambiguous.",
+    "conversational_answer_from_history_prompt": "Given the current user message and the canonical message history, decide whether the assistant can answer from message_history without running additional tools or agents. If so, answer clearly using only that context.",
     "hitl_pre_review_system": "You are reviewing content before a human sees it. Apply the lessons from past human feedback to improve the output. Preserve the original meaning and structure, but incorporate the corrections and preferences indicated by the lessons.",
     "hitl_pre_review_user": "Output to review:\n{output}\n\nLessons from past human feedback:\n{lessons}\n\nApply the lessons to improve the output.",
     "hitl_distill_system": "You extract generalizable lessons from human feedback on system outputs. A lesson should be a reusable rule or preference that applies to future similar outputs -- not a one-time correction specific to this exact content.\n\nExamples of good lessons:\n- Always include source citations when making factual claims\n- Use bullet points instead of long paragraphs for action items\n- Avoid technical jargon when the audience is non-technical\n\nIf the feedback is just approval (e.g. looks good, approved) or contains no generalizable guidance, return an empty list.",

lib/crewai/src/crewai/utilities/string_utils.py

@@ -23,6 +23,26 @@ def _duplicate_separator_pattern(separator: str) -> re.Pattern[str]:
     return re.compile(f"(?:{re.escape(separator)}){{2,}}")
 
 
+def extract_template_variables(input_string: str | None) -> list[str]:
+    """Return the template variable names referenced in a string.
+
+    Only recognizes placeholders that interpolation can actually fill, i.e.
+    ``{name}`` where ``name`` starts with a letter/underscore and contains only
+    letters, numbers, underscores, and hyphens. Expressions such as
+    ``{x if x else "y"}`` or JSON snippets are intentionally ignored so they are
+    never treated as required inputs.
+
+    Args:
+        input_string: The string to scan. May be ``None`` or empty.
+
+    Returns:
+        The matched variable names, in order of appearance (with duplicates).
+    """
+    if not input_string:
+        return []
+    return _VARIABLE_PATTERN.findall(input_string)
+
+
 def sanitize_tool_name(name: str, max_length: int = _MAX_TOOL_NAME_LENGTH) -> str:
     """Sanitize tool name for LLM provider compatibility.
 

lib/crewai/tests/cassettes/tracing/TestTraceListenerSetup.test_trace_listener_collects_crew_events.yaml

@@ -17,251 +17,6 @@ interactions:
     status:
       code: 200
       message: OK
-- request:
-    body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test backstory\nYour
-      personal goal is: Test goal\nTo give my best complete final answer to the task
-      respond using the exact following format:\n\nThought: I now can give a great
-      answer\nFinal Answer: Your final answer must be the great and the most complete
-      as possible, it must be outcome described.\n\nI MUST use these formats, my job
-      depends on it!"}, {"role": "user", "content": "\nCurrent Task: Say hello to
-      the world\n\nThis is the expected criteria for your final answer: hello world\nyou
-      MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
-      This is VERY important to you, use the tools available and give your best Final
-      Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop":
-      ["\nObservation:"]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate, zstd
-      connection:
-      - keep-alive
-      content-length:
-      - '825'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=ePO5hy0kEoADCuKcboFy1iS1qckCE5KCpifQaXnlomM-1754508545-1.0.1.1-ieWfjcdIxQIXGfaMizvmgTvZPRFehqDXliegaOT7EO.kt7KSSFGmNDcC35_D9hOhE.fJ5K302uX0snQF3nLaapds2dqgGbNcsyFPOKNvAdI;
-        _cfuvid=NaXWifUGChHp6Ap1mvfMrNzmO4HdzddrqXkSR9T.hYo-1754508545647-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.93.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.93.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-read-timeout:
-      - '600.0'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.9
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: "{\n  \"id\": \"chatcmpl-C1e6uBsZ3iMw51p03hHTkBgHjA5ym\",\n  \"object\"\
-        : \"chat.completion\",\n  \"created\": 1754508548,\n  \"model\": \"gpt-4o-mini-2024-07-18\"\
-        ,\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n  \
-        \      \"role\": \"assistant\",\n        \"content\": \"I now can give a great\
-        \ answer  \\nFinal Answer: hello world\",\n        \"refusal\": null,\n  \
-        \      \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"\
-        finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\"\
-        : 157,\n    \"completion_tokens\": 13,\n    \"total_tokens\": 170,\n    \"\
-        prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\"\
-        : 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\"\
-        : 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n\
-        \      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\"\
-        : \"default\",\n  \"system_fingerprint\": \"fp_34a54ae93c\"\n}\n"
-    headers:
-      CF-RAY:
-      - 96b0f0fb5c067ad9-SJC
-      Connection:
-      - keep-alive
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 06 Aug 2025 19:29:09 GMT
-      Server:
-      - cloudflare
-      Strict-Transport-Security:
-      - max-age=31536000; includeSubDomains; preload
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '628'
-      openai-project:
-      - proj_xitITlrFeen7zjNSzML82h9x
-      openai-version:
-      - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '657'
-      x-ratelimit-limit-project-tokens:
-      - '150000000'
-      x-ratelimit-limit-requests:
-      - '30000'
-      x-ratelimit-limit-tokens:
-      - '150000000'
-      x-ratelimit-remaining-project-tokens:
-      - '149999827'
-      x-ratelimit-remaining-requests:
-      - '29999'
-      x-ratelimit-remaining-tokens:
-      - '149999827'
-      x-ratelimit-reset-project-tokens:
-      - 0s
-      x-ratelimit-reset-requests:
-      - 2ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_a0daca00035c423daf0e9df208720180
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test backstory\nYour
-      personal goal is: Test goal\nTo give my best complete final answer to the task
-      respond using the exact following format:\n\nThought: I now can give a great
-      answer\nFinal Answer: Your final answer must be the great and the most complete
-      as possible, it must be outcome described.\n\nI MUST use these formats, my job
-      depends on it!"}, {"role": "user", "content": "\nCurrent Task: Say hello to
-      the world\n\nThis is the expected criteria for your final answer: hello world\nyou
-      MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
-      This is VERY important to you, use the tools available and give your best Final
-      Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini"}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate, zstd
-      connection:
-      - keep-alive
-      content-length:
-      - '797'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=f59gEPi_nA3TTxtjbKaSQpvkTwezaAqOvqfxiGzRnVQ-1754508546-1.0.1.1-JrSaytxVIQSVE00I.vyGj7d4HJbbMV6R9fWPJbkDKu0Y8ueMRzTwTUnfz0YzP5nsZX5oxoE6WlmFxOuz0rRuq9YhZZsO_TbaFBOFk1jGK9U;
-        _cfuvid=3D66v3.J_RcVoYy9dlF.jHwq1zTIm842xynZxzSy1Wc-1754508546352-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.93.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.93.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-read-timeout:
-      - '200.0'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.9
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: "{\n  \"id\": \"chatcmpl-C1e6vUMjwrC8Zt9Htraa70hbbt5d7\",\n  \"object\"\
-        : \"chat.completion\",\n  \"created\": 1754508549,\n  \"model\": \"gpt-4o-mini-2024-07-18\"\
-        ,\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n  \
-        \      \"role\": \"assistant\",\n        \"content\": \"I now can give a great\
-        \ answer  \\nFinal Answer: hello world\",\n        \"refusal\": null,\n  \
-        \      \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"\
-        finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\"\
-        : 157,\n    \"completion_tokens\": 13,\n    \"total_tokens\": 170,\n    \"\
-        prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\"\
-        : 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\"\
-        : 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n\
-        \      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\"\
-        : \"default\",\n  \"system_fingerprint\": \"fp_34a54ae93c\"\n}\n"
-    headers:
-      CF-RAY:
-      - 96b0f101793aeb2c-SJC
-      Connection:
-      - keep-alive
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 06 Aug 2025 19:29:09 GMT
-      Server:
-      - cloudflare
-      Strict-Transport-Security:
-      - max-age=31536000; includeSubDomains; preload
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '541'
-      openai-project:
-      - proj_xitITlrFeen7zjNSzML82h9x
-      openai-version:
-      - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '557'
-      x-ratelimit-limit-project-tokens:
-      - '150000000'
-      x-ratelimit-limit-requests:
-      - '30000'
-      x-ratelimit-limit-tokens:
-      - '150000000'
-      x-ratelimit-remaining-project-tokens:
-      - '149999827'
-      x-ratelimit-remaining-requests:
-      - '29999'
-      x-ratelimit-remaining-tokens:
-      - '149999827'
-      x-ratelimit-reset-project-tokens:
-      - 0s
-      x-ratelimit-reset-requests:
-      - 2ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_df70f95325b14817a692f23cf9cca880
-    status:
-      code: 200
-      message: OK
 - request:
     body: '{"trace_id": "2487456d-e03a-4eae-92a1-e9779e8f06a1", "execution_type":
       "crew", "execution_context": {"crew_fingerprint": null, "crew_name": "Unknown
@@ -330,6 +85,117 @@ interactions:
     status:
       code: 404
       message: Not Found
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Test Agent. Test backstory\nYour
+      personal goal is: Test goal"},{"role":"user","content":"\nCurrent Task: Say
+      hello to the world\n\nThis is the expected criteria for your final answer: hello
+      world\nyou MUST return the actual complete content as the final answer, not
+      a summary.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '386'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 2.32.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-DmQBou4covfqbekZpX1DEVm8haN4N\",\n  \"object\"\
+        : \"chat.completion\",\n  \"created\": 1780432788,\n  \"model\": \"gpt-4o-mini-2024-07-18\"\
+        ,\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n  \
+        \      \"role\": \"assistant\",\n        \"content\": \"hello world\",\n \
+        \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"\
+        logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\"\
+        : {\n    \"prompt_tokens\": 71,\n    \"completion_tokens\": 2,\n    \"total_tokens\"\
+        : 73,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n   \
+        \   \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n  \
+        \    \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\"\
+        : 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\"\
+        : \"default\",\n  \"system_fingerprint\": \"fp_df8c8d3b43\"\n}\n"
+    headers:
+      Access-Control-Expose-Headers:
+      - ACCESS-CONTROL-XXX
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-Ray:
+      - a05944f98aa2456e-SJC
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 02 Jun 2026 20:39:48 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '394'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      set-cookie:
+      - SET-COOKIE-XXX
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
 - request:
     body: '{"version": "0.152.0", "batch_id": "2487456d-e03a-4eae-92a1-e9779e8f06a1",
       "user_context": {"user_id": "anonymous", "organization_id": "", "session_id":
@@ -471,4 +337,3 @@ interactions:
     status:
       code: 404
       message: Not Found
-version: 1