Fix test isolation: reset TraceCollectionListener singleton in cleanup_event_handlers fixture

Prevents singleton state pollution (trace_batch_id="debug-trace-batch") from
test_flow_conversation.py leaking into test_trace_enable_disable.py when both
files run in the same pytest-xdist worker under --dist=loadfile. The polluted
singleton caused a background HTTP request to fake.crewai.com that corrupted
VCR cassette state, preventing the OpenAI LLM entry from matching.

.github/workflows/vulnerability-scan.yml

@@ -64,6 +64,7 @@ jobs:
             --ignore-vuln PYSEC-2025-197 \
             --ignore-vuln PYSEC-2025-210 \
             --ignore-vuln PYSEC-2026-139 \
+            --ignore-vuln GHSA-rrmf-rvhw-rf47 \
             --ignore-vuln PYSEC-2025-211 \
             --ignore-vuln PYSEC-2025-212 \
             --ignore-vuln PYSEC-2025-213 \
@@ -81,6 +82,7 @@ jobs:
         #   PYSEC-2025-183      - pyjwt 2.12.1: disputed weak-encryption claim; key length is application-chosen
         #   PYSEC-2025-189..197 - torch 2.11.0: memory-corruption/DoS in functions only reachable via untrusted models; no fix available
         #   PYSEC-2025-210, PYSEC-2026-139 - torch 2.11.0: profiler/deserialization issues; no fix available
+        #   GHSA-rrmf-rvhw-rf47 - torch 2.11.0 (CVE-2025-3000, alias of PYSEC-2025-194): memory corruption in torch.jit.script, CVSS 1.9, local-only; affected <=2.12.0, no fix available. pip-audit reports it under the GHSA id so the PYSEC ignore above does not catch it.
         #   PYSEC-2025-211..218 - transformers 5.5.4: deserialization/code injection via malicious model checkpoints; no fix available
         #   GHSA-f4j7-r4q5-qw2c - chromadb 1.1.1 (CVE-2026-45829): pre-auth RCE via /api/v2/tenants/{tenant}/databases/{db}/collections when trust_remote_code=true.
         #                         Advisory: vulnerable >=1.0.0,<=1.5.9, firstPatchedVersion=none. We only use chromadb.PersistentClient (lib/crewai/src/crewai/rag/chromadb/factory.py)

.gitignore

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

.pre-commit-config.yaml

@@ -47,6 +47,7 @@ repos:
           --ignore-vuln PYSEC-2025-197
           --ignore-vuln PYSEC-2025-210
           --ignore-vuln PYSEC-2026-139
+          --ignore-vuln GHSA-rrmf-rvhw-rf47
           --ignore-vuln PYSEC-2025-211
           --ignore-vuln PYSEC-2025-212
           --ignore-vuln PYSEC-2025-213

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:
@@ -105,6 +197,21 @@ def cleanup_event_handlers() -> Generator[None, Any, None]:
     except Exception:  # noqa: S110
         pass
 
+    try:
+        from crewai.events.listeners.tracing.trace_listener import (
+            TraceCollectionListener,
+        )
+
+        if TraceCollectionListener._instance is not None:
+            instance_dict = TraceCollectionListener._instance.__dict__
+            if "_initialized" in instance_dict:
+                del TraceCollectionListener._instance._initialized
+            if "_listeners_setup" in instance_dict:
+                del TraceCollectionListener._instance._listeners_setup
+        TraceCollectionListener._instance = None
+    except Exception:  # noqa: S110
+        pass
+
 
 @pytest.fixture(autouse=True, scope="function")
 def reset_event_state() -> None:

docs/ar/changelog.mdx

@@ -4,6 +4,178 @@ description: "تحديثات المنتج والتحسينات وإصلاحات
 icon: "clock"
 mode: "wide"
 ---
+<Update label="11 يونيو 2026">
+  ## v1.14.7
+
+  [عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7)
+
+  ## ما الذي تغير
+
+  ### الميزات
+  - إضافة واجهات خلفية افتراضية قابلة للتوصيل للذاكرة، والمعرفة، وrag، وflow.
+  - عرض السبب الحقيقي للإنهاء، ومعلمات العينة، وresponse.id في أحداث LLM.
+  - تصنيف مشغلات DSL كزخارف واعية للمسار.
+  - إضافة واجهة برمجة تطبيقات الدردشة لتدفقات المحادثة.
+  - جعل واجهة القفل قابلة للتجاوز.
+  - بناء FlowDefinition من بيانات التعريف الخاصة بـ Flow DSL.
+  - إضافة مزود LLM من Snowflake Cortex الأصلي.
+  - إضافة دعم لملفات الوكلاء المدربين من crew.
+
+  ### إصلاحات الأخطاء
+  - إصلاح نقطة التحقق لإعادة بناء BaseLLM مخصص كـ LLM ملموس عند الاستعادة.
+  - تقييد الاستعادة على علامة لمنع اللقطات الحية من إعادة التشغيل كاستئناف.
+  - تحديد حالة وقت التشغيل لكل تشغيل للحد من النمو وعزل التشغيل المتزامن.
+  - إصلاح إعدادات التتبع على crewai-login.
+  - احترام suppress_flow_events لأحداث تنفيذ الطريقة.
+  - استعادة [project.scripts] في حزمة crewai لتثبيت أداة uv.
+  - حل مشكلات CVE الخاصة بـ pip-audit لـ aiohttp وdocling وdocling-core.
+  - إصلاح إدخال الملفات الذي لا يعمل بشكل موثوق.
+  - إصلاح تاريخ نتائج أدوات Snowflake Claude غير المكتملة.
+
+  ### الوثائق
+  - تحديث سجل التغييرات والإصدار لـ v1.14.7.
+  - تحديث وثائق جامع OpenTelemetry.
+  - تحديث دليل NVIDIA Nemotron LLM.
+  - إضافة دليل تكامل Databricks.
+  - إضافة دليل تكامل Snowflake.
+
+  ### الأداء
+  - تحسين سرعة استيراد crewai من خلال تحميل مستندات docling بشكل كسول.
+
+  ### إعادة الهيكلة
+  - تبسيط تقييم شروط التدفق ليكون بلا حالة لكل حدث.
+  - فصل منطق المحادثة عن وقت التشغيل وإضافة تعريف المحادثة.
+  - تقسيم `flow.py` إلى DSL، وتعريف، ووقت تشغيل.
+
+  ## المساهمون
+
+  @Luzk, @alex-clawd, @devin-ai-integration[bot], @greysonlalonde, @gvieira, @jessemiller, @lorenzejay, @lucasgomide, @mattatcha, @vinibrsl
+
+</Update>
+
+<Update label="10 يونيو 2026">
+  ## v1.14.7rc2
+
+  [عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7rc2)
+
+  ## ما الذي تغير
+
+  ### إصلاحات الأخطاء
+  - استعادة البوابة على علامة لمنع اللقطات الحية من إعادة التشغيل كاستئناف
+
+  ### الوثائق
+  - تحديث سجل التغييرات والإصدار لـ v1.14.7rc1
+
+  ## المساهمون
+
+  @greysonlalonde
+
+</Update>
+
+<Update label="10 يونيو 2026">
+  ## v1.14.7rc1
+
+  [عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7rc1)
+
+  ## ما الذي تغير
+
+  ### الميزات
+  - إضافة `reset_runtime_state` لإطلاق حالة الحافلة المتراكمة
+  - التعامل مع دعم كل من الموجهات المخصصة
+  - فصل منطق المحادثة عن وقت التشغيل وإضافة `conversational_definition`
+
+  ### إصلاحات الأخطاء
+  - إصلاح نطاق حالة وقت التشغيل لكل تشغيل للحد من النمو وعزل التشغيلات المتزامنة
+  - إصلاح إعدادات القياس عن بُعد على `crewai-login`
+  - إصلاح احترام `suppress_flow_events` لفعاليات تنفيذ الأساليب
+
+  ### الوثائق
+  - تحديث صور OpenTelemetry
+  - تحديث الوثائق لتعكس الحالة الجديدة لجمع بيانات OpenTelemetry
+  - تحديث سجل التغييرات والإصدار لـ v1.14.7a4
+
+  ### إعادة الهيكلة
+  - تبسيط تقييم شرط التدفق ليكون بلا حالة لكل حدث
+  - تحسين دورة توجيه المحادثة مع تقليل مسار واحد
+
+  ## المساهمون
+
+  @greysonlalonde, @lorenzejay, @lucasgomide, @vinibrsl
+
+</Update>
+
+<Update label="9 يونيو 2026">
+  ## v1.14.7a4
+
+  [عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7a4)
+
+  ## ما الذي تغير
+
+  ### الميزات
+  - نقل وقت التشغيل @listen/@router لقراءة من FlowDefinition
+  - إضافة واجهات خلفية افتراضية قابلة للتوصيل للذاكرة، والمعرفة، وrag، وflow
+
+  ### الوثائق
+  - تحديث سجل التغييرات والإصدار لـ v1.14.7a3
+
+  ## المساهمون
+
+  @greysonlalonde, @mattatcha, @vinibrsl
+
+</Update>
+
+<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/concepts/flows.mdx

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

docs/ar/enterprise/guides/capture_telemetry_logs.mdx

@@ -24,15 +24,39 @@ mode: "wide"
 
 1. في CrewAI AMP، انتقل إلى **Settings** > **OpenTelemetry Collectors**.
 2. انقر على **Add Collector**.
-3. اختر نوع التكامل — **OpenTelemetry Traces** أو **OpenTelemetry Logs**.
-4. هيّئ الاتصال:
-   - **Endpoint** — نقطة نهاية OTLP لمجمّعك (مثل `https://otel-collector.example.com:4317`).
-   - **Service Name** — اسم لتعريف هذه الخدمة في منصة المراقبة.
-   - **Custom Headers** *(اختياري)* — أضف رؤوس المصادقة أو التوجيه كأزواج مفتاح-قيمة.
-   - **Certificate** *(اختياري)* — قدم شهادة TLS إذا كان مجمّعك يتطلبها.
-5. انقر على **Save**.
+3. اختر تكاملاً:
+   - **OpenTelemetry Traces** و**OpenTelemetry Logs** — صدّر إلى أي مجمّع أو واجهة خلفية متوافقة مع OTLP.
+   - **Datadog** — أرسل التتبعات مباشرة إلى استقبال OTLP الخاص بـ Datadog، دون الحاجة إلى مجمّع منفصل أو Datadog Agent.
+4. هيّئ الاتصال. تعتمد الحقول على التكامل الذي اخترته:
 
-<Frame>![تهيئة مجمّع OpenTelemetry](/images/crewai-otel-collector-config.png)</Frame>
+<Tabs>
+  <Tab title="OpenTelemetry Traces / Logs">
+    إن **OpenTelemetry Traces** و**OpenTelemetry Logs** تكاملان منفصلان يتشاركان نفس الحقول — اختر التكامل المطابق للإشارة التي تريد تصديرها.
+
+    - **Endpoint** — نقطة نهاية OTLP لمجمّعك (مثل `https://otel-collector.example.com:4317`).
+    - **Service Name** — اسم لتعريف هذه الخدمة في منصة المراقبة.
+    - **Custom Headers** *(اختياري)* — أضف رؤوس المصادقة أو التوجيه كأزواج مفتاح-قيمة.
+    - **Certificate** *(اختياري)* — قدم شهادة TLS إذا كان مجمّعك يتطلبها.
+
+    <Frame>![تهيئة مجمّع OpenTelemetry](/images/crewai-otel-collector-opentelemetry.png)</Frame>
+  </Tab>
+  <Tab title="Datadog">
+    - **Datadog Site Domain** — مضيف OTLP لموقع Datadog الخاص بك فقط، دون بروتوكول أو مسار. يقوم CrewAI ببناء نقطة نهاية HTTPS OTLP الكاملة نيابةً عنك. استخدم المضيف المطابق لـ [موقع Datadog](https://docs.datadoghq.com/getting_started/site/) الخاص بك:
+      - `otlp.datadoghq.com` (US1)
+      - `otlp.us3.datadoghq.com` (US3)
+      - `otlp.us5.datadoghq.com` (US5)
+      - `otlp.datadoghq.eu` (EU1)
+      - `otlp.ap1.datadoghq.com` (AP1)
+    - **API Key** — مفتاح واجهة برمجة تطبيقات Datadog الخاص بك. راجع [كيفية إنشاء واحد](https://docs.datadoghq.com/account_management/api-app-keys/#api-keys).
+
+    يصدّر تكامل Datadog **التتبعات**.
+
+    <Frame>![تهيئة مجمّع Datadog](/images/crewai-otel-collector-datadog.png)</Frame>
+  </Tab>
+</Tabs>
+
+5. *(اختياري)* انقر على **Test Connection** للتحقق من قدرة CrewAI على الوصول إلى نقطة النهاية باستخدام بيانات الاعتماد التي قدمتها.
+6. انقر على **Save**.
 
 <Tip>
   يمكنك إضافة مجمّعات متعددة — على سبيل المثال، واحد للتتبعات وآخر للسجلات، أو الإرسال إلى واجهات خلفية مختلفة لأغراض مختلفة.

docs/ar/guides/advanced/customizing-prompts.mdx

@@ -161,6 +161,18 @@ crew = Crew(
 )
 ```
 
+<Note>
+يُحتفظ بـ `agent.i18n` للتوافق مع الإصدارات السابقة فقط، وقد تم إهماله. لتخصيص المطالبات أثناء التشغيل، مرّر `prompt_file` إلى `Crew`. وللوصول البرمجي المباشر إلى شرائح المطالبات، استخدم أداة i18n مباشرة:
+</Note>
+
+```python
+from crewai.utilities.i18n import get_i18n
+
+i18n = get_i18n("custom_prompts.json")
+format_slice = i18n.slice("format")
+tool_prompt = i18n.tools("ask_question")
+```
+
 #### الخيار 3: تعطيل مطالبات النظام لنماذج o1
 ```python
 agent = Agent(
@@ -208,6 +220,8 @@ agent = Agent(
 
 يدمج CrewAI بعد ذلك تخصيصاتك مع الإعدادات الافتراضية، فلا تحتاج لإعادة تعريف كل مطالبة. إليك الطريقة:
 
+بالنسبة للكود الذي يحتاج إلى قراءة شرائح المطالبات مباشرة، استخدم `crewai.utilities.i18n.get_i18n()` مع ملف المطالبات نفسه بدلًا من قراءة `agent.i18n`.
+
 ### مثال: تخصيص أساسي للمطالبات
 
 أنشئ ملف `custom_prompts.json` بالمطالبات التي تريد تعديلها. تأكد من إدراج جميع المطالبات عالية المستوى التي يجب أن يحتويها، وليس فقط تغييراتك:

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

@@ -7,97 +7,87 @@ 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 — دون API منفصل `chat()` على `Flow`.
+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 | `kickoff(session_id=...)` → `inputs["id"]` → `state.id` |
-| سطر المستخدم | `kickoff(user_message=...)` يُضاف إلى `state.messages` قبل تشغيل الرسم |
-| اكتمال الجولة | `FlowFinished` لهذا **التشغيل** فقط؛ تستمر المحادثة في `kickoff` التالي |
-| تتبع الجلسة | `ConversationalConfig(defer_trace_finalization=True)` + `finalize_session_traces()` |
+| 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()` |
 
-## نقطة دخول واحدة: `kickoff`
+## واجهات الجولات
 
-استخدم **`flow.kickoff(user_message=..., session_id=...)`** لكل رسالة مستخدم (REST أو WebSocket أو CLI). لا تنشئ غلاف `chat()` مخصصاً على `Flow`.
+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 |
 |-----|-----------|
-| `kickoff(user_message=..., session_id=...)` | كل رسالة مستخدم |
-| `kickoff_async(...)` | نفس المعاملات؛ دخول async أصلي |
+| `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 `kickoff` |
+| `ChatSession.handle_turn(...)` | طبقة نقل فوق `handle_turn` |
 
 ## بداية سريعة
 
 ```python
 from uuid import uuid4
 
-from crewai.flow import (
-    ChatState,
-    ConversationalConfig,
-    Flow,
-    listen,
-    or_,
-    persist,
-    router,
-    start,
+from crewai import Flow
+from crewai.flow import listen
+from crewai.experimental.conversational import (
+    ConversationConfig,
+    ConversationState,
 )
-from crewai.flow.persistence import SQLiteFlowPersistence
 
 
-class SupportFlow(Flow[ChatState]):
-    conversational_config = ConversationalConfig(
-        default_intents=["order", "help", "goodbye"],
-        intent_llm="gpt-4o-mini",
-        defer_trace_finalization=True,
-    )
+@ConversationConfig(defer_trace_finalization=True)
+class SupportFlow(Flow[ConversationState]):
+    conversational = True
 
-    @start()
-    def bootstrap(self):
-        if not self.state.session_ready:
-            self.state.session_ready = True
-        return "ready"
-
-    @router(bootstrap)
-    def route(self):
-        return self.state.last_intent or "help"
+    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_message("assistant", reply)
+        self.append_assistant_message(reply)
         return reply
 
     @listen("help")
     def handle_help(self):
         reply = "كيف يمكنني المساعدة؟"
-        self.append_message("assistant", reply)
+        self.append_assistant_message(reply)
         return reply
 
     @listen("goodbye")
     def handle_goodbye(self):
         reply = "وداعاً!"
-        self.append_message("assistant", reply)
+        self.append_assistant_message(reply)
         return reply
 
-    @persist(SQLiteFlowPersistence("support.db"))
-    @listen(or_(handle_order, handle_help, handle_goodbye))
-    def finalize(self):
-        return self.state.model_dump()
-
 
 session_id = str(uuid4())
 flow = SupportFlow()
 
-flow.kickoff(user_message="أين طلبي؟", session_id=session_id)
-flow.kickoff(user_message="وماذا عن الإرجاع؟", session_id=session_id)
-flow.finalize_session_traces()
+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 `kickoff` مع `user_message` يشغّل:
+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`.
@@ -106,7 +96,7 @@ flow.finalize_session_traces()
 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_message("assistant", reply)`** في المعالجات. سطر المستخدم محفوظ عند kickoff — لا تُضفه مرة أخرى.
+استدعِ **`append_assistant_message(reply)`** في المعالجات. سطر المستخدم محفوظ عبر `handle_turn` — لا تُضفه مرة أخرى.
 
 ## `ConversationalConfig` (افتراضيات على مستوى الصنف)
 
@@ -290,6 +280,15 @@ 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.
@@ -371,7 +370,37 @@ Routes:
 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.
 
-يمكنك أيضاً استدعاء `flow.kickoff(user_message=..., session_id=...)` مباشرةً — نفس منطق الإعادة والتشغيل يعمل. `handle_turn` هو الغلاف المريح.
+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
 
@@ -407,17 +436,10 @@ class SupportFlow(Flow[ConversationState]):
 - **العمل المتداخل** (`Agent.kickoff()`, crews, Exa) يُلحق بدفعة **الأب**؛ flow داخلي من `AgentExecutor` لا يغلق دفعة الجلسة مبكراً.
 
 ```python
-try:
-    while True:
-        line = input("You: ").strip()
-        if not line:
-            break
-        flow.kickoff(user_message=line, session_id=session_id)
-finally:
-    flow.finalize_session_traces()
+flow.chat(session_id=session_id)
 ```
 
-`ChatSession.close()` يستدعي `finalize_session_traces()` عند التأجيل.
+`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.
 

docs/en/changelog.mdx

@@ -4,6 +4,178 @@ description: "Product updates, improvements, and bug fixes for CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="Jun 11, 2026">
+  ## v1.14.7
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7)
+
+  ## What's Changed
+
+  ### Features
+  - Add pluggable default backends for memory, knowledge, rag, and flow.
+  - Surface real finish_reason, sampling params, and response.id on LLM events.
+  - Type DSL triggers as route-aware decorators.
+  - Add chat API for conversational flows.
+  - Make locking backend overridable.
+  - Build FlowDefinition from Flow DSL metadata.
+  - Add native Snowflake Cortex LLM provider.
+  - Add crew trained agents file support.
+
+  ### Bug Fixes
+  - Fix checkpoint to rebuild custom BaseLLM as concrete LLM on restore.
+  - Gate restore on a flag to prevent live snapshots from replaying as resume.
+  - Scope runtime state per run to bound growth and isolate concurrent runs.
+  - Fix telemetry setup on crewai-login.
+  - Respect suppress_flow_events for method-execution events.
+  - Restore [project.scripts] in crewai package for uv tool install.
+  - Resolve pip-audit CVEs for aiohttp, docling, and docling-core.
+  - Fix file input not working reliably.
+  - Fix Snowflake Claude incomplete tool result histories.
+
+  ### Documentation
+  - Update changelog and version for v1.14.7.
+  - Update OpenTelemetry collector documentation.
+  - Update NVIDIA Nemotron LLM guide.
+  - Add Databricks integration guide.
+  - Add Snowflake integration guide.
+
+  ### Performance
+  - Improve crewai import speed by lazy-loading docling imports.
+
+  ### Refactoring
+  - Simplify flow condition evaluation to be stateless per event.
+  - Decouple convo logic from runtime and add a conversational_definition.
+  - Split `flow.py` into DSL, definition, and runtime.
+
+  ## Contributors
+
+  @Luzk, @alex-clawd, @devin-ai-integration[bot], @greysonlalonde, @gvieira, @jessemiller, @lorenzejay, @lucasgomide, @mattatcha, @vinibrsl
+
+</Update>
+
+<Update label="Jun 10, 2026">
+  ## v1.14.7rc2
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7rc2)
+
+  ## What's Changed
+
+  ### Bug Fixes
+  - Gate restore on a flag to prevent live snapshots from replaying as resume
+
+  ### Documentation
+  - Update changelog and version for v1.14.7rc1
+
+  ## Contributors
+
+  @greysonlalonde
+
+</Update>
+
+<Update label="Jun 10, 2026">
+  ## v1.14.7rc1
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7rc1)
+
+  ## What's Changed
+
+  ### Features
+  - Add `reset_runtime_state` to release accumulated bus state
+  - Handle supporting both custom prompts
+  - Decouple conversation logic from runtime and add a `conversational_definition`
+
+  ### Bug Fixes
+  - Fix scope of runtime state per run to bound growth and isolate concurrent runs
+  - Fix telemetry setup on `crewai-login`
+  - Fix respect for `suppress_flow_events` for method-execution events
+
+  ### Documentation
+  - Update OpenTelemetry images
+  - Update documentation to reflect new state of OpenTelemetry collector
+  - Update changelog and version for v1.14.7a4
+
+  ### Refactoring
+  - Simplify flow condition evaluation to be stateless per event
+  - Improve conversation routing cycle with one less route
+
+  ## Contributors
+
+  @greysonlalonde, @lorenzejay, @lucasgomide, @vinibrsl
+
+</Update>
+
+<Update label="Jun 09, 2026">
+  ## v1.14.7a4
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7a4)
+
+  ## What's Changed
+
+  ### Features
+  - Migrate @listen/@router runtime to read from FlowDefinition
+  - Add pluggable default backends for memory, knowledge, rag, and flow
+
+  ### Documentation
+  - Update changelog and version for v1.14.7a3
+
+  ## Contributors
+
+  @greysonlalonde, @mattatcha, @vinibrsl
+
+</Update>
+
+<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/flows.mdx

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

docs/en/concepts/memory.mdx

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

docs/en/enterprise/guides/capture_telemetry_logs.mdx

@@ -24,15 +24,39 @@ Telemetry data follows the [OpenTelemetry GenAI semantic conventions](https://op
 
 1. In CrewAI AMP, go to **Settings** > **OpenTelemetry Collectors**.
 2. Click **Add Collector**.
-3. Select an integration type — **OpenTelemetry Traces** or **OpenTelemetry Logs**.
-4. Configure the connection:
-   - **Endpoint** — Your collector's OTLP endpoint (e.g., `https://otel-collector.example.com:4317`).
-   - **Service Name** — A name to identify this service in your observability platform.
-   - **Custom Headers** *(optional)* — Add authentication or routing headers as key-value pairs.
-   - **Certificate** *(optional)* — Provide a TLS certificate if your collector requires one.
-5. Click **Save**.
+3. Select an integration:
+   - **OpenTelemetry Traces** and **OpenTelemetry Logs** — export to any OTLP-compatible collector or backend.
+   - **Datadog** — send traces straight to Datadog's OTLP intake, no separate collector or Datadog Agent required.
+4. Configure the connection. The fields depend on the integration you selected:
 
-<Frame>![OpenTelemetry Collector Configuration](/images/crewai-otel-collector-config.png)</Frame>
+<Tabs>
+  <Tab title="OpenTelemetry Traces / Logs">
+    **OpenTelemetry Traces** and **OpenTelemetry Logs** are separate integrations that share the same fields — pick the one matching the signal you want to export.
+
+    - **Endpoint** — Your collector's OTLP endpoint (e.g., `https://otel-collector.example.com:4317`).
+    - **Service Name** — A name to identify this service in your observability platform.
+    - **Custom Headers** *(optional)* — Add authentication or routing headers as key-value pairs.
+    - **Certificate** *(optional)* — Provide a TLS certificate if your collector requires one.
+
+    <Frame>![OpenTelemetry collector configuration](/images/crewai-otel-collector-opentelemetry.png)</Frame>
+  </Tab>
+  <Tab title="Datadog">
+    - **Datadog Site Domain** — Your Datadog site's OTLP host only, with no protocol or path. CrewAI builds the full HTTPS OTLP endpoint for you. Use the host that matches your [Datadog site](https://docs.datadoghq.com/getting_started/site/):
+      - `otlp.datadoghq.com` (US1)
+      - `otlp.us3.datadoghq.com` (US3)
+      - `otlp.us5.datadoghq.com` (US5)
+      - `otlp.datadoghq.eu` (EU1)
+      - `otlp.ap1.datadoghq.com` (AP1)
+    - **API Key** — Your Datadog API key. See [how to create one](https://docs.datadoghq.com/account_management/api-app-keys/#api-keys).
+
+    The Datadog integration exports **traces**.
+
+    <Frame>![Datadog collector configuration](/images/crewai-otel-collector-datadog.png)</Frame>
+  </Tab>
+</Tabs>
+
+5. *(optional)* Click **Test Connection** to verify CrewAI can reach the endpoint with the credentials you provided.
+6. Click **Save**.
 
 <Tip>
   You can add multiple collectors — for example, one for traces and another for logs, or send to different backends for different purposes.

docs/en/guides/advanced/customizing-prompts.mdx

@@ -161,6 +161,18 @@ crew = Crew(
 )
 ```
 
+<Note>
+`agent.i18n` is maintained only for backward compatibility and is deprecated. For runtime prompt customization, pass `prompt_file` to `Crew`. For programmatic access to prompt slices, use the i18n utility directly:
+</Note>
+
+```python
+from crewai.utilities.i18n import get_i18n
+
+i18n = get_i18n("custom_prompts.json")
+format_slice = i18n.slice("format")
+tool_prompt = i18n.tools("ask_question")
+```
+
 #### Option 3: Disable System Prompts for o1 Models
 ```python
 agent = Agent(
@@ -208,6 +220,8 @@ One straightforward approach is to create a JSON file for the prompts you want t
 
 CrewAI then merges your customizations with the defaults, so you don't have to redefine every prompt. Here's how:
 
+For code that needs to read prompt slices directly, use `crewai.utilities.i18n.get_i18n()` with the same prompt file instead of reading `agent.i18n`.
+
 ### Example: Basic Prompt Customization
 
 Create a `custom_prompts.json` file with the prompts you want to modify. Ensure you list all top-level prompts it should contain, not just your changes:

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

@@ -1,130 +1,121 @@
 ---
 title: Conversational Flows
-description: Build multi-turn chat apps with kickoff per turn, message history, intent routing, tracing, and WebSocket bridges.
+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 classification, deferred tracing, and UI bridges — without a separate `chat()` API on `Flow`.
+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 | `kickoff(session_id=...)` → `inputs["id"]` → `state.id` |
-| User line | `kickoff(user_message=...)` appends to `state.messages` before the graph runs |
-| Turn complete | `FlowFinished` for **this run** only; chat continues on the next `kickoff` |
-| Full-session trace | `ConversationalConfig(defer_trace_finalization=True)` + `finalize_session_traces()` |
+| 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()` |
 
-## One entry point: `kickoff`
+## Turn APIs
 
-Use **`flow.kickoff(user_message=..., session_id=...)`** for every user message (REST, WebSocket, CLI). Do not add a custom `chat()` wrapper on `Flow`.
+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 |
 |-----|---------|
-| `kickoff(user_message=..., session_id=...)` | Each user message |
-| `kickoff_async(...)` | Same parameters; native async entry |
+| `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 `kickoff` (SSE / WebSocket) |
+| `ChatSession.handle_turn(...)` | Transport layer over `handle_turn` (SSE / WebSocket) |
 
 ## Quick start
 
 ```python
 from uuid import uuid4
 
-from crewai.flow import (
-    ChatState,
-    ConversationalConfig,
-    Flow,
-    listen,
-    or_,
-    persist,
-    router,
-    start,
+from crewai import Flow
+from crewai.flow import listen
+from crewai.experimental.conversational import (
+    ConversationConfig,
+    ConversationState,
 )
-from crewai.flow.persistence import SQLiteFlowPersistence
 
 
-class SupportFlow(Flow[ChatState]):
-    conversational_config = ConversationalConfig(
-        default_intents=["order", "help", "goodbye"],
-        intent_llm="gpt-4o-mini",
-        defer_trace_finalization=True,
-    )
+@ConversationConfig(defer_trace_finalization=True)
+class SupportFlow(Flow[ConversationState]):
+    conversational = True
 
-    @start()
-    def bootstrap(self):
-        if not self.state.session_ready:
-            self.state.session_ready = True
-        return "ready"
-
-    @router(bootstrap)
-    def route(self):
-        # last_intent set in prepare_conversational_turn when default_intents is set
-        return self.state.last_intent or "help"
+    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_message("assistant", reply)
+        self.append_assistant_message(reply)
         return reply
 
     @listen("help")
     def handle_help(self):
         reply = "How can I help?"
-        self.append_message("assistant", reply)
+        self.append_assistant_message(reply)
         return reply
 
     @listen("goodbye")
     def handle_goodbye(self):
         reply = "Goodbye!"
-        self.append_message("assistant", reply)
+        self.append_assistant_message(reply)
         return reply
 
-    @persist(SQLiteFlowPersistence("support.db"))
-    @listen(or_(handle_order, handle_help, handle_goodbye))
-    def finalize(self):
-        return self.state.model_dump()
-
 
 session_id = str(uuid4())
 flow = SupportFlow()
 
-flow.kickoff(user_message="Where is my order?", session_id=session_id)
-flow.kickoff(user_message="What about returns?", session_id=session_id)
-flow.finalize_session_traces()  # one trace link for the whole chat
+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 `kickoff` with `user_message` runs this pipeline:
+Each `handle_turn` runs this pipeline:
 
-1. **`_configure_conversational_kickoff`** — merges `session_id` / `user_message` into `inputs`, applies `ConversationalConfig`, enables deferred tracing when configured.
+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. **`prepare_conversational_turn`** — appends the user message to `state.messages`, sets `last_user_message`, clears `last_intent`, optionally classifies when `intents` / `default_intents` + `intent_llm` are set.
-5. **Graph execution** — `@start` → `@router` → `@listen` handlers.
+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_message("assistant", reply)`** so the next turn’s `conversation_messages` includes assistant text. The user line is already stored at kickoff — do not append it again in handlers.
+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.
 
-## `ConversationalConfig` (class-level defaults)
+## `ConversationConfig` (class-level defaults)
 
-Set on your `Flow` subclass as `conversational_config: ClassVar[ConversationalConfig | None]`.
+Decorate your conversational `Flow` subclass with `ConversationConfig`.
 
 | Field | Default | Purpose |
 |-------|---------|---------|
-| `default_intents` | `None` | Outcome labels for automatic pre-kickoff classification |
-| `intent_llm` | `None` | Model for classification (required when intents are used) |
-| `interactive_prompt` | `"You: "` | Prompt for `kickoff(interactive=True)` |
-| `interactive_timeout` | `None` | Per-line timeout in interactive mode |
-| `exit_commands` | `exit`, `quit` | Words that end interactive mode |
-| `defer_trace_finalization` | `True` | Keep one trace batch open across turns |
+| `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 per kickoff with `intents=` and `intent_llm=` keyword arguments.
+Override pre-classification per turn with `handle_turn(..., intents=..., intent_llm=...)`.
 
-## `ChatState` (recommended persisted shape)
+## 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
@@ -138,7 +129,7 @@ class MyChatState(ChatState):
 
 | Field | Role |
 |-------|------|
-| `id` | Session UUID (same as `session_id` / `inputs["id"]`) |
+| `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) |
@@ -148,27 +139,26 @@ class MyChatState(ChatState):
 
 ## `Flow` conversational API
 
-### `kickoff` / `kickoff_async` parameters
+### `handle_turn` parameters
 
 | Parameter | Purpose |
 |-----------|---------|
-| `user_message` | This turn’s text (or `{"role": "user", "content": "..."}`) |
+| `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`) |
-| `interactive` | CLI loop via `ask()` (local demos only) |
-| `interactive_prompt` | Override prompt in interactive mode |
-| `interactive_timeout` | Per-line `ask()` timeout |
-| `exit_commands` | Words that end interactive mode |
-| `inputs` | Additional state fields (merged with conversational keys) |
-| `restore_from_state_id` | Fork hydration from another persisted flow |
+| `**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_config` | Class-level `ConversationalConfig` defaults |
-| `defer_trace_finalization` | Instance flag; set automatically from config on kickoff |
+| `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)` |
 
@@ -176,7 +166,8 @@ class MyChatState(ChatState):
 
 | Name | Description |
 |------|-------------|
-| `append_message(role, content, **extra)` | Append to `state.messages` (roles: `user`, `assistant`, `system`, `tool`) |
+| `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` |
@@ -193,7 +184,7 @@ Importable for tests or custom orchestration:
 | `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=...)` | Turn hydration (usually called by kickoff) |
+| `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` |
@@ -201,21 +192,20 @@ Importable for tests or custom orchestration:
 
 ## Intent routing patterns
 
-### A. Pre-classify via `ConversationalConfig` (simplest)
+### A. Pre-classify via `ConversationConfig` (simplest)
 
-Set `default_intents` and `intent_llm`. Each kickoff runs classification before your `@router`; read `self.state.last_intent` in `route()`.
+Set `default_intents` and `intent_llm`. Each `handle_turn()` runs classification before routing; read `self.state.last_intent` in `route_turn()`.
 
-### B. Classify inside `@router` (richer prompts)
+### B. Classify inside `route_turn` (richer prompts)
 
-Set `default_intents=None` so kickoff only appends the user message. In `route()`, call `classify_intent` with a custom prompt or descriptions:
+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
-@router(bootstrap)
-def route(self):
+def route_turn(self, context):
     intent = self.classify_intent(
-        self._routing_prompt(self.state.last_user_message),
+        self._routing_prompt(self.state.current_user_message),
         ("GREETING", "ORDER", "RESEARCH", "GOODBYE"),
-        llm=self.conversational_config.intent_llm or "gpt-4o-mini",
+        llm="gpt-4o-mini",
     )
     self.state.last_intent = intent
     return intent
@@ -225,7 +215,7 @@ Use **`@listen("RESEARCH")`** (or similar) for steps that run `Agent.kickoff()`
 
 ## When the flow finishes but the user keeps chatting
 
-`FlowFinished` means **this graph run** completed. The conversation continues with another `kickoff` and the same `session_id`. `@persist` restores `messages`, flags, and context.
+`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.
 
@@ -242,57 +232,66 @@ Do **not** use `@human_feedback` for follow-up chat lines unless a human must ap
   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`, drives the router LLM, and keeps the trace batch open across turns. You write the **custom routes**; the framework owns the rest.
+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 an LLM-driven router and per-route handlers without wiring the lifecycle yourself. Use `Flow[ChatState]` (the lower-level pattern above) when you need full control.
+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 LLM, Flow
+from crewai import 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(),  # routes + descriptions auto-discovered from @listen handlers
-)
+@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 (built-in)
+    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("Summarize the first result.")   # routes back to converse
+    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.
@@ -312,7 +311,21 @@ Class decorator that attaches per-class chat defaults.
 ### `RouterConfig` and the auto-built route catalog
 
 ```python
-RouterConfig(
+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
@@ -336,6 +349,9 @@ The router prompt that gets sent to the LLM is built automatically. For each rou
 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."""
@@ -374,13 +390,49 @@ You can override any of these by defining a same-named handler in your subclass.
 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.
 
-You can also call `flow.kickoff(user_message=..., session_id=...)` directly — the same reset/run logic fires. `handle_turn` is the ergonomic wrapper.
+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
 
@@ -402,7 +454,7 @@ Inside a `@listen(label)` handler, choose:
 
 ## Tracing across turns
 
-With `defer_trace_finalization=True` (default in `ConversationalConfig`):
+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()`.
@@ -410,17 +462,12 @@ With `defer_trace_finalization=True` (default in `ConversationalConfig`):
 - **Nested work** (`Agent.kickoff()`, crews, Exa tools) appends to the **parent** batch; inner `AgentExecutor` flows do not close the session batch early.
 
 ```python
-try:
-    while True:
-        line = input("You: ").strip()
-        if not line:
-            break
-        flow.kickoff(user_message=line, session_id=session_id)
-finally:
-    flow.finalize_session_traces()
+flow.chat(session_id=session_id)
 ```
 
-`ChatSession.close()` calls `finalize_session_traces()` when deferral is enabled.
+`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.
 

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

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

docs/ko/changelog.mdx

@@ -4,6 +4,178 @@ description: "CrewAI의 제품 업데이트, 개선 사항 및 버그 수정"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="2026년 6월 11일">
+  ## v1.14.7
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7)
+
+  ## 변경 사항
+
+  ### 기능
+  - 메모리, 지식, RAG 및 흐름에 대한 플러그 가능한 기본 백엔드를 추가했습니다.
+  - LLM 이벤트에서 실제 finish_reason, 샘플링 매개변수 및 response.id를 표시합니다.
+  - 경로 인식 장식자로서의 타입 DSL 트리거를 설정합니다.
+  - 대화 흐름을 위한 채팅 API를 추가했습니다.
+  - 잠금 백엔드를 재정의 가능하도록 만듭니다.
+  - Flow DSL 메타데이터에서 FlowDefinition을 빌드합니다.
+  - 네이티브 Snowflake Cortex LLM 공급자를 추가했습니다.
+  - 훈련된 에이전트 파일 지원을 추가했습니다.
+
+  ### 버그 수정
+  - 복원 시 사용자 정의 BaseLLM을 구체적인 LLM으로 재구성하도록 체크포인트를 수정했습니다.
+  - 라이브 스냅샷이 재개로 재생되지 않도록 플래그를 사용하여 복원을 제한합니다.
+  - 실행마다 런타임 상태의 범위를 설정하여 성장을 제한하고 동시 실행을 격리합니다.
+  - crewai-login에서 텔레메트리 설정을 수정했습니다.
+  - 메서드 실행 이벤트에 대해 suppress_flow_events를 존중합니다.
+  - uv 도구 설치를 위해 crewai 패키지에서 [project.scripts]를 복원합니다.
+  - aiohttp, docling 및 docling-core에 대한 pip-audit CVE를 해결합니다.
+  - 파일 입력이 신뢰할 수 없게 작동하는 문제를 수정했습니다.
+  - Snowflake Claude의 불완전한 도구 결과 기록을 수정했습니다.
+
+  ### 문서
+  - v1.14.7에 대한 변경 로그 및 버전을 업데이트했습니다.
+  - OpenTelemetry 수집기 문서를 업데이트했습니다.
+  - NVIDIA Nemotron LLM 가이드를 업데이트했습니다.
+  - Databricks 통합 가이드를 추가했습니다.
+  - Snowflake 통합 가이드를 추가했습니다.
+
+  ### 성능
+  - docling 가져오기를 지연 로딩하여 crewai 가져오기 속도를 개선했습니다.
+
+  ### 리팩토링
+  - 흐름 조건 평가를 이벤트별로 상태 비저장으로 단순화했습니다.
+  - 대화 논리를 런타임에서 분리하고 conversational_definition을 추가했습니다.
+  - `flow.py`를 DSL, 정의 및 런타임으로 분리했습니다.
+
+  ## 기여자
+
+  @Luzk, @alex-clawd, @devin-ai-integration[bot], @greysonlalonde, @gvieira, @jessemiller, @lorenzejay, @lucasgomide, @mattatcha, @vinibrsl
+
+</Update>
+
+<Update label="2026년 6월 10일">
+  ## v1.14.7rc2
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7rc2)
+
+  ## 변경 사항
+
+  ### 버그 수정
+  - 라이브 스냅샷이 재개로 재생되는 것을 방지하기 위한 플래그에서 게이트 복원
+
+  ### 문서
+  - v1.14.7rc1에 대한 변경 로그 및 버전 업데이트
+
+  ## 기여자
+
+  @greysonlalonde
+
+</Update>
+
+<Update label="2026년 6월 10일">
+  ## v1.14.7rc1
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7rc1)
+
+  ## 변경 사항
+
+  ### 기능
+  - 누적된 버스 상태를 해제하기 위해 `reset_runtime_state` 추가
+  - 사용자 정의 프롬프트를 모두 지원하도록 처리
+  - 대화 논리를 런타임과 분리하고 `conversational_definition` 추가
+
+  ### 버그 수정
+  - 실행당 런타임 상태의 범위를 수정하여 성장 제한 및 동시 실행 격리
+  - `crewai-login`에서 원격 측정 설정 수정
+  - 메서드 실행 이벤트에 대한 `suppress_flow_events` 존중 수정
+
+  ### 문서
+  - OpenTelemetry 이미지 업데이트
+  - OpenTelemetry 수집기의 새로운 상태를 반영하도록 문서 업데이트
+  - v1.14.7a4에 대한 변경 로그 및 버전 업데이트
+
+  ### 리팩토링
+  - 이벤트당 상태 비저장 방식으로 흐름 조건 평가 단순화
+  - 경로를 하나 줄여 대화 라우팅 사이클 개선
+
+  ## 기여자
+
+  @greysonlalonde, @lorenzejay, @lucasgomide, @vinibrsl
+
+</Update>
+
+<Update label="2026년 6월 9일">
+  ## v1.14.7a4
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7a4)
+
+  ## 변경 사항
+
+  ### 기능
+  - @listen/@router 런타임을 FlowDefinition에서 읽도록 마이그레이션
+  - 메모리, 지식, rag 및 flow에 대한 플러그형 기본 백엔드 추가
+
+  ### 문서
+  - v1.14.7a3에 대한 변경 로그 및 버전 업데이트
+
+  ## 기여자
+
+  @greysonlalonde, @mattatcha, @vinibrsl
+
+</Update>
+
+<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/concepts/flows.mdx

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

docs/ko/enterprise/guides/capture_telemetry_logs.mdx

@@ -24,15 +24,39 @@ CrewAI AMP는 배포에서 OpenTelemetry **트레이스**와 **로그**를 자
 
 1. CrewAI AMP에서 **Settings** > **OpenTelemetry Collectors**로 이동합니다.
 2. **Add Collector**를 클릭합니다.
-3. 통합 유형을 선택합니다 — **OpenTelemetry Traces** 또는 **OpenTelemetry Logs**.
-4. 연결을 구성합니다:
-   - **Endpoint** — 수집기의 OTLP 엔드포인트 (예: `https://otel-collector.example.com:4317`).
-   - **Service Name** — 관측 가능성 플랫폼에서 이 서비스를 식별하기 위한 이름.
-   - **Custom Headers** *(선택 사항)* — 인증 또는 라우팅 헤더를 키-값 쌍으로 추가합니다.
-   - **Certificate** *(선택 사항)* — 수집기에서 TLS 인증서가 필요한 경우 제공합니다.
-5. **Save**를 클릭합니다.
+3. 통합을 선택합니다:
+   - **OpenTelemetry Traces** 및 **OpenTelemetry Logs** — OTLP 호환 수집기 또는 백엔드로 내보냅니다.
+   - **Datadog** — 별도의 수집기나 Datadog Agent 없이 트레이스를 Datadog의 OTLP 인테이크로 직접 전송합니다.
+4. 연결을 구성합니다. 필드는 선택한 통합에 따라 달라집니다:
 
-<Frame>![OpenTelemetry 수집기 구성](/images/crewai-otel-collector-config.png)</Frame>
+<Tabs>
+  <Tab title="OpenTelemetry Traces / Logs">
+    **OpenTelemetry Traces**와 **OpenTelemetry Logs**는 동일한 필드를 공유하는 별개의 통합입니다 — 내보내려는 신호에 맞는 것을 선택하세요.
+
+    - **Endpoint** — 수집기의 OTLP 엔드포인트 (예: `https://otel-collector.example.com:4317`).
+    - **Service Name** — 관측 가능성 플랫폼에서 이 서비스를 식별하기 위한 이름.
+    - **Custom Headers** *(선택 사항)* — 인증 또는 라우팅 헤더를 키-값 쌍으로 추가합니다.
+    - **Certificate** *(선택 사항)* — 수집기에서 TLS 인증서가 필요한 경우 제공합니다.
+
+    <Frame>![OpenTelemetry 수집기 구성](/images/crewai-otel-collector-opentelemetry.png)</Frame>
+  </Tab>
+  <Tab title="Datadog">
+    - **Datadog Site Domain** — Datadog 사이트의 OTLP 호스트만 입력합니다 (프로토콜이나 경로 제외). CrewAI가 전체 HTTPS OTLP 엔드포인트를 자동으로 구성합니다. [Datadog 사이트](https://docs.datadoghq.com/getting_started/site/)에 맞는 호스트를 사용하세요:
+      - `otlp.datadoghq.com` (US1)
+      - `otlp.us3.datadoghq.com` (US3)
+      - `otlp.us5.datadoghq.com` (US5)
+      - `otlp.datadoghq.eu` (EU1)
+      - `otlp.ap1.datadoghq.com` (AP1)
+    - **API Key** — Datadog API 키입니다. [키 생성 방법](https://docs.datadoghq.com/account_management/api-app-keys/#api-keys)을 참고하세요.
+
+    Datadog 통합은 **트레이스**를 내보냅니다.
+
+    <Frame>![Datadog 수집기 구성](/images/crewai-otel-collector-datadog.png)</Frame>
+  </Tab>
+</Tabs>
+
+5. *(선택 사항)* **Test Connection**을 클릭하여 제공한 자격 증명으로 CrewAI가 엔드포인트에 연결할 수 있는지 확인합니다.
+6. **Save**를 클릭합니다.
 
 <Tip>
   여러 수집기를 추가할 수 있습니다 — 예를 들어, 트레이스용 하나와 로그용 하나를 추가하거나, 다른 목적을 위해 다른 백엔드로 전송할 수 있습니다.

docs/ko/guides/advanced/customizing-prompts.mdx

@@ -161,6 +161,18 @@ crew = Crew(
 )
 ```
 
+<Note>
+`agent.i18n`은 이전 버전과의 호환성을 위해서만 유지되며 사용이 중단될 예정입니다. 런타임 프롬프트 커스터마이징에는 `Crew`에 `prompt_file`을 전달하세요. 프롬프트 슬라이스를 코드에서 직접 읽어야 한다면 i18n 유틸리티를 직접 사용하세요:
+</Note>
+
+```python
+from crewai.utilities.i18n import get_i18n
+
+i18n = get_i18n("custom_prompts.json")
+format_slice = i18n.slice("format")
+tool_prompt = i18n.tools("ask_question")
+```
+
 #### 옵션 3: o1 모델에 대한 시스템 프롬프트 비활성화
 ```python
 agent = Agent(
@@ -208,6 +220,8 @@ agent = Agent(
 
 그러면 CrewAI가 기본값과 사용자가 지정한 내용을 병합하므로, 모든 프롬프트를 다시 정의할 필요가 없습니다. 방법은 다음과 같습니다:
 
+프롬프트 슬라이스를 코드에서 직접 읽어야 하는 경우에는 `agent.i18n`을 읽는 대신 동일한 프롬프트 파일로 `crewai.utilities.i18n.get_i18n()`을 사용하세요.
+
 ### 예시: 기본 프롬프트 커스터마이징
 
 수정하고 싶은 프롬프트를 포함하는 `custom_prompts.json` 파일을 생성하세요. 변경 사항만이 아니라 포함해야 하는 모든 최상위 프롬프트를 반드시 나열해야 합니다:
@@ -314,4 +328,4 @@ CrewAI에서의 저수준 prompt 커스터마이제이션은 매우 맞춤화되
 
 <Check>
 이제 CrewAI에서 고급 prompt 커스터마이징을 위한 기초를 갖추었습니다. 모델별 구조나 도메인별 제약에 맞춰 적용하든, 이러한 저수준 접근 방식은 agent 상호작용을 매우 전문적으로 조정할 수 있게 해줍니다.
-</Check>
+</Check>

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

@@ -7,98 +7,87 @@ 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 브리지를 제공하며, `Flow`에 별도 `chat()` API는 없습니다.
+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 | `kickoff(session_id=...)` → `inputs["id"]` → `state.id` |
-| 사용자 입력 | `kickoff(user_message=...)`가 그래프 실행 전 `state.messages`에 추가 |
-| 턴 완료 | `FlowFinished`는 **이번 실행**만 의미; 다음 `kickoff`로 대화 계속 |
-| 세션 전체 트레이스 | `ConversationalConfig(defer_trace_finalization=True)` + `finalize_session_traces()` |
+| 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()` |
 
-## 단일 진입점: `kickoff`
+## 턴 API
 
-모든 사용자 메시지에 **`flow.kickoff(user_message=..., session_id=...)`**를 사용하세요 (REST, WebSocket, CLI). `Flow`에 커스텀 `chat()` 래퍼를 만들지 마세요.
+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 |
 |-----|------|
-| `kickoff(user_message=..., session_id=...)` | 각 사용자 메시지 |
-| `kickoff_async(...)` | 동일 파라미터; 네이티브 async 진입 |
+| `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(...)` | `kickoff` 위의 전송 계층 (SSE / WebSocket) |
+| `ChatSession.handle_turn(...)` | `handle_turn` 위의 전송 계층 (SSE / WebSocket) |
 
 ## 빠른 시작
 
 ```python
 from uuid import uuid4
 
-from crewai.flow import (
-    ChatState,
-    ConversationalConfig,
-    Flow,
-    listen,
-    or_,
-    persist,
-    router,
-    start,
+from crewai import Flow
+from crewai.flow import listen
+from crewai.experimental.conversational import (
+    ConversationConfig,
+    ConversationState,
 )
-from crewai.flow.persistence import SQLiteFlowPersistence
 
 
-class SupportFlow(Flow[ChatState]):
-    conversational_config = ConversationalConfig(
-        default_intents=["order", "help", "goodbye"],
-        intent_llm="gpt-4o-mini",
-        defer_trace_finalization=True,
-    )
+@ConversationConfig(defer_trace_finalization=True)
+class SupportFlow(Flow[ConversationState]):
+    conversational = True
 
-    @start()
-    def bootstrap(self):
-        if not self.state.session_ready:
-            self.state.session_ready = True
-        return "ready"
-
-    @router(bootstrap)
-    def route(self):
-        # default_intents 설정 시 prepare_conversational_turn에서 last_intent 설정
-        return self.state.last_intent or "help"
+    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_message("assistant", reply)
+        self.append_assistant_message(reply)
         return reply
 
     @listen("help")
     def handle_help(self):
         reply = "무엇을 도와드릴까요?"
-        self.append_message("assistant", reply)
+        self.append_assistant_message(reply)
         return reply
 
     @listen("goodbye")
     def handle_goodbye(self):
         reply = "안녕히 가세요!"
-        self.append_message("assistant", reply)
+        self.append_assistant_message(reply)
         return reply
 
-    @persist(SQLiteFlowPersistence("support.db"))
-    @listen(or_(handle_order, handle_help, handle_goodbye))
-    def finalize(self):
-        return self.state.model_dump()
-
 
 session_id = str(uuid4())
 flow = SupportFlow()
 
-flow.kickoff(user_message="주문 어디까지 왔나요?", session_id=session_id)
-flow.kickoff(user_message="반품은 어떻게 하나요?", session_id=session_id)
-flow.finalize_session_traces()  # 전체 대화에 대한 단일 trace 링크
+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
 
-`user_message`가 있는 각 `kickoff`는 다음 파이프라인을 실행합니다:
+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.
@@ -107,7 +96,7 @@ flow.finalize_session_traces()  # 전체 대화에 대한 단일 trace 링크
 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_message("assistant", reply)`**를 호출해 다음 턴의 `conversation_messages`에 어시스턴트 응답이 포함되게 하세요. 사용자 입력은 kickoff 시 이미 저장됩니다 — 핸들러에서 다시 추가하지 마세요.
+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)
 
@@ -292,6 +281,15 @@ 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.
@@ -373,7 +371,37 @@ Routes:
 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.
 
-`flow.kickoff(user_message=..., session_id=...)`를 직접 호출해도 동일한 reset/run 로직이 동작합니다. `handle_turn`은 그 위에 얹은 편의 래퍼입니다.
+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
 
@@ -409,17 +437,10 @@ LLM router를 우회해 프로그램적으로 라우트를 선택하려면 `rout
 - **중첩 작업** (`Agent.kickoff()`, crew, Exa tool)은 **부모** batch에 추가; 내부 `AgentExecutor` flow가 세션 batch를 조기 종료하지 않음.
 
 ```python
-try:
-    while True:
-        line = input("You: ").strip()
-        if not line:
-            break
-        flow.kickoff(user_message=line, session_id=session_id)
-finally:
-    flow.finalize_session_traces()
+flow.chat(session_id=session_id)
 ```
 
-지연 활성화 시 `ChatSession.close()`가 `finalize_session_traces()`를 호출합니다.
+`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.
 

docs/pt-BR/changelog.mdx

@@ -4,6 +4,178 @@ description: "Atualizações de produto, melhorias e correções do CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="11 jun 2026">
+  ## v1.14.7
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7)
+
+  ## O que Mudou
+
+  ### Recursos
+  - Adicionar backends padrão plugáveis para memória, conhecimento, rag e fluxo.
+  - Exibir o verdadeiro finish_reason, parâmetros de amostragem e response.id em eventos LLM.
+  - Tipar os gatilhos DSL como decoradores cientes de rotas.
+  - Adicionar API de chat para fluxos de conversa.
+  - Tornar o backend de bloqueio substituível.
+  - Construir FlowDefinition a partir de metadados Flow DSL.
+  - Adicionar provedor nativo Snowflake Cortex LLM.
+  - Adicionar suporte a arquivos de agentes treinados pela equipe.
+
+  ### Correções de Bugs
+  - Corrigir checkpoint para reconstruir BaseLLM personalizado como LLM concreto na restauração.
+  - Controlar a restauração com uma flag para evitar que snapshots ao vivo sejam reproduzidos como retomar.
+  - Escopar o estado de execução por execução para limitar o crescimento e isolar execuções concorrentes.
+  - Corrigir configuração de telemetria no crewai-login.
+  - Respeitar suppress_flow_events para eventos de execução de método.
+  - Restaurar [project.scripts] no pacote crewai para instalação da ferramenta uv.
+  - Resolver CVEs de pip-audit para aiohttp, docling e docling-core.
+  - Corrigir entrada de arquivo que não estava funcionando de forma confiável.
+  - Corrigir histórias de resultados de ferramentas incompletas do Snowflake Claude.
+
+  ### Documentação
+  - Atualizar changelog e versão para v1.14.7.
+  - Atualizar documentação do coletor OpenTelemetry.
+  - Atualizar guia do LLM NVIDIA Nemotron.
+  - Adicionar guia de integração do Databricks.
+  - Adicionar guia de integração do Snowflake.
+
+  ### Desempenho
+  - Melhorar a velocidade de importação do crewai através do carregamento preguiçoso de imports do docling.
+
+  ### Refatoração
+  - Simplificar a avaliação de condições de fluxo para ser sem estado por evento.
+  - Desacoplar a lógica de conversa da execução e adicionar uma conversational_definition.
+  - Dividir `flow.py` em DSL, definição e execução.
+
+  ## Contribuidores
+
+  @Luzk, @alex-clawd, @devin-ai-integration[bot], @greysonlalonde, @gvieira, @jessemiller, @lorenzejay, @lucasgomide, @mattatcha, @vinibrsl
+
+</Update>
+
+<Update label="10 jun 2026">
+  ## v1.14.7rc2
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7rc2)
+
+  ## O que Mudou
+
+  ### Correções de Bugs
+  - Restauração de portão em uma flag para evitar que snapshots ao vivo sejam reproduzidos como retomar
+
+  ### Documentação
+  - Atualizar changelog e versão para v1.14.7rc1
+
+  ## Contributors
+
+  @greysonlalonde
+
+</Update>
+
+<Update label="10 jun 2026">
+  ## v1.14.7rc1
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7rc1)
+
+  ## O que Mudou
+
+  ### Recursos
+  - Adicionar `reset_runtime_state` para liberar o estado acumulado do barramento
+  - Lidar com suporte a ambos os prompts personalizados
+  - Desacoplar a lógica de conversa do tempo de execução e adicionar uma `conversational_definition`
+
+  ### Correções de Bugs
+  - Corrigir o escopo do estado de tempo de execução por execução para limitar o crescimento e isolar execuções concorrentes
+  - Corrigir a configuração de telemetria em `crewai-login`
+  - Corrigir o respeito a `suppress_flow_events` para eventos de execução de método
+
+  ### Documentação
+  - Atualizar imagens do OpenTelemetry
+  - Atualizar a documentação para refletir o novo estado do coletor OpenTelemetry
+  - Atualizar o changelog e a versão para v1.14.7a4
+
+  ### Refatoração
+  - Simplificar a avaliação da condição de fluxo para ser sem estado por evento
+  - Melhorar o ciclo de roteamento de conversas com uma rota a menos
+
+  ## Contribuidores
+
+  @greysonlalonde, @lorenzejay, @lucasgomide, @vinibrsl
+
+</Update>
+
+<Update label="09 jun 2026">
+  ## v1.14.7a4
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.7a4)
+
+  ## O Que Mudou
+
+  ### Funcionalidades
+  - Migrar a execução @listen/@router para ler a partir de FlowDefinition
+  - Adicionar backends padrão plugáveis para memória, conhecimento, rag e flow
+
+  ### Documentação
+  - Atualizar changelog e versão para v1.14.7a3
+
+  ## Contributors
+
+  @greysonlalonde, @mattatcha, @vinibrsl
+
+</Update>
+
+<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/concepts/flows.mdx

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

docs/pt-BR/enterprise/guides/capture_telemetry_logs.mdx

@@ -24,15 +24,39 @@ Os dados de telemetria seguem as [convenções semânticas GenAI do OpenTelemetr
 
 1. No CrewAI AMP, vá para **Settings** > **OpenTelemetry Collectors**.
 2. Clique em **Add Collector**.
-3. Selecione um tipo de integração — **OpenTelemetry Traces** ou **OpenTelemetry Logs**.
-4. Configure a conexão:
-   - **Endpoint** — O endpoint OTLP do seu coletor (por exemplo, `https://otel-collector.example.com:4317`).
-   - **Service Name** — Um nome para identificar este serviço na sua plataforma de observabilidade.
-   - **Custom Headers** *(opcional)* — Adicione headers de autenticação ou roteamento como pares chave-valor.
-   - **Certificate** *(opcional)* — Forneça um certificado TLS se o seu coletor exigir um.
-5. Clique em **Save**.
+3. Selecione uma integração:
+   - **OpenTelemetry Traces** e **OpenTelemetry Logs** — exporte para qualquer coletor ou backend compatível com OTLP.
+   - **Datadog** — envie traces diretamente para a ingestão OTLP do Datadog, sem precisar de um coletor separado ou do Datadog Agent.
+4. Configure a conexão. Os campos dependem da integração selecionada:
 
-<Frame>![Configuração do Coletor OpenTelemetry](/images/crewai-otel-collector-config.png)</Frame>
+<Tabs>
+  <Tab title="OpenTelemetry Traces / Logs">
+    **OpenTelemetry Traces** e **OpenTelemetry Logs** são integrações separadas que compartilham os mesmos campos — escolha a que corresponde ao sinal que você quer exportar.
+
+    - **Endpoint** — O endpoint OTLP do seu coletor (por exemplo, `https://otel-collector.example.com:4317`).
+    - **Service Name** — Um nome para identificar este serviço na sua plataforma de observabilidade.
+    - **Custom Headers** *(opcional)* — Adicione headers de autenticação ou roteamento como pares chave-valor.
+    - **Certificate** *(opcional)* — Forneça um certificado TLS se o seu coletor exigir um.
+
+    <Frame>![Configuração do coletor OpenTelemetry](/images/crewai-otel-collector-opentelemetry.png)</Frame>
+  </Tab>
+  <Tab title="Datadog">
+    - **Datadog Site Domain** — Apenas o host OTLP do seu site Datadog, sem protocolo ou caminho. O CrewAI monta o endpoint HTTPS OTLP completo para você. Use o host correspondente ao seu [site Datadog](https://docs.datadoghq.com/getting_started/site/):
+      - `otlp.datadoghq.com` (US1)
+      - `otlp.us3.datadoghq.com` (US3)
+      - `otlp.us5.datadoghq.com` (US5)
+      - `otlp.datadoghq.eu` (EU1)
+      - `otlp.ap1.datadoghq.com` (AP1)
+    - **API Key** — Sua chave de API do Datadog. Veja [como criar uma](https://docs.datadoghq.com/account_management/api-app-keys/#api-keys).
+
+    A integração com o Datadog exporta **traces**.
+
+    <Frame>![Configuração do coletor Datadog](/images/crewai-otel-collector-datadog.png)</Frame>
+  </Tab>
+</Tabs>
+
+5. *(opcional)* Clique em **Test Connection** para verificar se o CrewAI consegue acessar o endpoint com as credenciais fornecidas.
+6. Clique em **Save**.
 
 <Tip>
   Você pode adicionar múltiplos coletores — por exemplo, um para traces e outro para logs, ou enviar para diferentes backends para diferentes propósitos.

docs/pt-BR/guides/advanced/customizing-prompts.mdx

@@ -161,6 +161,18 @@ crew = Crew(
 )
 ```
 
+<Note>
+`agent.i18n` é mantido apenas para compatibilidade retroativa e está obsoleto. Para customização de prompts em tempo de execução, passe `prompt_file` para `Crew`. Para acesso programático aos slices de prompt, use diretamente o utilitário de i18n:
+</Note>
+
+```python
+from crewai.utilities.i18n import get_i18n
+
+i18n = get_i18n("custom_prompts.json")
+format_slice = i18n.slice("format")
+tool_prompt = i18n.tools("ask_question")
+```
+
 #### Opção 3: Desativar Prompts de Sistema para Modelos o1
 ```python
 agent = Agent(
@@ -208,6 +220,8 @@ Uma abordagem direta é criar um arquivo JSON para os prompts que deseja sobresc
 
 O CrewAI então mescla suas customizações com os padrões, assim você não precisa redefinir todos os prompts. Veja como:
 
+Para código que precisa ler slices de prompt diretamente, use `crewai.utilities.i18n.get_i18n()` com o mesmo arquivo de prompts em vez de ler `agent.i18n`.
+
 ### Exemplo: Customização Básica de Prompt
 
 Crie um arquivo `custom_prompts.json` com os prompts que deseja modificar. Certifique-se de listar todos os prompts de nível superior que ele deve conter, não apenas suas alterações:

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

@@ -7,98 +7,87 @@ 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 e pontes para UI — sem uma API `chat()` separada em `Flow`.
+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 | `kickoff(session_id=...)` → `inputs["id"]` → `state.id` |
-| Linha do usuário | `kickoff(user_message=...)` acrescenta em `state.messages` antes do grafo rodar |
-| Fim do turno | `FlowFinished` só para **esta execução**; o chat segue no próximo `kickoff` |
-| Trace da sessão | `ConversationalConfig(defer_trace_finalization=True)` + `finalize_session_traces()` |
+| 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()` |
 
-## Um ponto de entrada: `kickoff`
+## APIs de turno
 
-Use **`flow.kickoff(user_message=..., session_id=...)`** para cada mensagem (REST, WebSocket, CLI). Não crie um wrapper `chat()` customizado em `Flow`.
+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 |
 |-----|-----|
-| `kickoff(user_message=..., session_id=...)` | Cada mensagem do usuário |
-| `kickoff_async(...)` | Mesmos parâmetros; entrada async nativa |
+| `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 `kickoff` (SSE / WebSocket) |
+| `ChatSession.handle_turn(...)` | Camada de transporte sobre `handle_turn` (SSE / WebSocket) |
 
 ## Início rápido
 
 ```python
 from uuid import uuid4
 
-from crewai.flow import (
-    ChatState,
-    ConversationalConfig,
-    Flow,
-    listen,
-    or_,
-    persist,
-    router,
-    start,
+from crewai import Flow
+from crewai.flow import listen
+from crewai.experimental.conversational import (
+    ConversationConfig,
+    ConversationState,
 )
-from crewai.flow.persistence import SQLiteFlowPersistence
 
 
-class SupportFlow(Flow[ChatState]):
-    conversational_config = ConversationalConfig(
-        default_intents=["order", "help", "goodbye"],
-        intent_llm="gpt-4o-mini",
-        defer_trace_finalization=True,
-    )
+@ConversationConfig(defer_trace_finalization=True)
+class SupportFlow(Flow[ConversationState]):
+    conversational = True
 
-    @start()
-    def bootstrap(self):
-        if not self.state.session_ready:
-            self.state.session_ready = True
-        return "ready"
-
-    @router(bootstrap)
-    def route(self):
-        # last_intent definido em prepare_conversational_turn quando default_intents está setado
-        return self.state.last_intent or "help"
+    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_message("assistant", reply)
+        self.append_assistant_message(reply)
         return reply
 
     @listen("help")
     def handle_help(self):
         reply = "Como posso ajudar?"
-        self.append_message("assistant", reply)
+        self.append_assistant_message(reply)
         return reply
 
     @listen("goodbye")
     def handle_goodbye(self):
         reply = "Até logo!"
-        self.append_message("assistant", reply)
+        self.append_assistant_message(reply)
         return reply
 
-    @persist(SQLiteFlowPersistence("support.db"))
-    @listen(or_(handle_order, handle_help, handle_goodbye))
-    def finalize(self):
-        return self.state.model_dump()
-
 
 session_id = str(uuid4())
 flow = SupportFlow()
 
-flow.kickoff(user_message="Onde está meu pedido?", session_id=session_id)
-flow.kickoff(user_message="E as devoluções?", session_id=session_id)
-flow.finalize_session_traces()  # um link de trace para o chat inteiro
+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 `kickoff` com `user_message` executa este pipeline:
+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.
@@ -107,7 +96,7 @@ Cada `kickoff` com `user_message` executa este pipeline:
 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_message("assistant", reply)`** para que o próximo turno inclua a resposta do assistente. A linha do usuário já é salva no kickoff — não acrescente de novo nos handlers.
+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)
 
@@ -293,6 +282,15 @@ 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.
@@ -374,7 +372,37 @@ Você pode sobrescrever qualquer uma definindo um handler com o mesmo nome na su
 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.
 
-Você também pode chamar `flow.kickoff(user_message=..., session_id=...)` diretamente — a mesma lógica de reset/run é acionada. `handle_turn` é o wrapper ergonômico.
+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
 
@@ -410,17 +438,10 @@ Com `defer_trace_finalization=True` (padrão em `ConversationalConfig`):
 - **Trabalho aninhado** (`Agent.kickoff()`, crews, tools Exa) acrescenta ao batch **pai**; flows internos de `AgentExecutor` não fecham o batch da sessão cedo.
 
 ```python
-try:
-    while True:
-        line = input("You: ").strip()
-        if not line:
-            break
-        flow.kickoff(user_message=line, session_id=session_id)
-finally:
-    flow.finalize_session_traces()
+flow.chat(session_id=session_id)
 ```
 
-`ChatSession.close()` chama `finalize_session_traces()` quando o adiamento está habilitado.
+`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.
 

lib/cli/pyproject.toml

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

lib/cli/src/crewai_cli/__init__.py

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

lib/cli/src/crewai_cli/cli.py

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

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

@@ -34,6 +34,39 @@ def _run_predeploy_validation(skip_validate: bool) -> bool:
     return True
 
 
+def _display_git_repository_help() -> None:
+    """Explain how to prepare a new project for deployment."""
+    console.print(
+        "Deployment requires a Git repository with an origin remote.",
+        style="bold red",
+    )
+    console.print(
+        "CrewAI AMP deploys from the remote repository URL, so commit and push "
+        "this project first, then run deploy again.",
+        style="yellow",
+    )
+    console.print("\nSuggested setup:")
+    console.print("  git init")
+    console.print("  git add .")
+    console.print('  git commit -m "Initial crew"')
+    console.print("  git branch -M main")
+    console.print("  git remote add origin <your-repo-url>")
+    console.print("  git push -u origin main")
+
+
+def _display_git_remote_help() -> None:
+    """Explain how to add a remote to an existing Git repository."""
+    console.print("No remote repository URL found.", style="bold red")
+    console.print(
+        "CrewAI AMP deploys from the origin remote. Add a remote, push your "
+        "latest commit, then run deploy again.",
+        style="yellow",
+    )
+    console.print("\nSuggested setup:")
+    console.print("  git remote add origin <your-repo-url>")
+    console.print("  git push -u origin HEAD")
+
+
 class DeployCommand(BaseCommand, PlusAPIMixin):
     """
     A class to handle deployment-related operations for CrewAI projects.
@@ -124,14 +157,11 @@ class DeployCommand(BaseCommand, PlusAPIMixin):
         try:
             remote_repo_url = git.Repository().origin_url()
         except ValueError:
-            remote_repo_url = None
+            _display_git_repository_help()
+            return
 
         if remote_repo_url is None:
-            console.print("No remote repository URL found.", style="bold red")
-            console.print(
-                "Please ensure your project has a valid remote repository.",
-                style="yellow",
-            )
+            _display_git_remote_help()
             return
 
         self._confirm_input(env_vars, remote_repo_url, confirm)

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

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

lib/cli/src/crewai_cli/git.py

@@ -48,6 +48,7 @@ class Repository:
                 ["git", "rev-parse", "--is-inside-work-tree"],  # noqa: S607
                 cwd=self.path,
                 encoding="utf-8",
+                stderr=subprocess.DEVNULL,
             )
             return True
         except subprocess.CalledProcessError:

lib/cli/src/crewai_cli/run_crew.py

@@ -1,25 +1,311 @@
+from __future__ import annotations
+
+from contextlib import AbstractContextManager, nullcontext
 from enum import Enum
+import os
+from pathlib import Path
+import re
 import subprocess
+import sys
+from typing import TYPE_CHECKING, Any
 
 import click
+from crewai.project.json_loader import find_crew_json_file
 from crewai_core.constants import CREWAI_TRAINED_AGENTS_FILE_ENV
 from packaging import version
 
-from crewai_cli.utils import build_env_with_all_tool_credentials, read_toml
+from crewai_cli.utils import (
+    build_env_with_all_tool_credentials,
+    enable_prompt_line_editing,
+    read_toml,
+)
 from crewai_cli.version import get_crewai_version
 
 
+if TYPE_CHECKING:
+    from crewai_cli.crew_run_tui import CrewRunApp
+
+
 class CrewType(Enum):
     STANDARD = "standard"
     FLOW = "flow"
 
 
-def run_crew(trained_agents_file: str | None = None) -> None:
-    """Run the crew or flow by running a command in the UV environment.
+# Must accept the same names as the kickoff interpolation pattern in
+# crewai.utilities.string_utils (_VARIABLE_PATTERN), including hyphens —
+# otherwise placeholders are interpolated at runtime but never prompted for.
+_INPUT_PLACEHOLDER_RE = re.compile(r"(?<!{){([A-Za-z_][A-Za-z0-9_\-]*)}(?!})")
 
-    Starting from version 0.103.0, this command can be used to run both
-    standard crews and flows. For flows, it detects the type from pyproject.toml
-    and automatically runs the appropriate command.
+
+def _has_json_crew() -> bool:
+    """Check if this is a JSON-defined crew project.
+
+    The project type declared in pyproject.toml wins: a flow project that
+    happens to contain a crew.json(c) file still runs as a flow. A missing
+    or unreadable pyproject means a bare JSON crew project.
+    """
+    if find_crew_json_file() is None:
+        return False
+    try:
+        pyproject_data = read_toml()
+    except Exception:
+        return True
+    declared_type: str | None = (
+        pyproject_data.get("tool", {}).get("crewai", {}).get("type")
+    )
+    return declared_type != "flow"
+
+
+def _extract_input_placeholders(text: str | None) -> set[str]:
+    if not text:
+        return set()
+    return set(_INPUT_PLACEHOLDER_RE.findall(text))
+
+
+def _missing_input_names(crew: Any, inputs: dict[str, Any]) -> list[str]:
+    """Return input placeholders used by a crew but not provided as defaults."""
+    placeholders: set[str] = set()
+
+    for agent in getattr(crew, "agents", []) or []:
+        placeholders.update(_extract_input_placeholders(getattr(agent, "role", None)))
+        placeholders.update(_extract_input_placeholders(getattr(agent, "goal", None)))
+        placeholders.update(
+            _extract_input_placeholders(getattr(agent, "backstory", None))
+        )
+
+    for task in getattr(crew, "tasks", []) or []:
+        placeholders.update(
+            _extract_input_placeholders(getattr(task, "description", None))
+        )
+        placeholders.update(
+            _extract_input_placeholders(getattr(task, "expected_output", None))
+        )
+        placeholders.update(
+            _extract_input_placeholders(getattr(task, "output_file", None))
+        )
+
+    return sorted(name for name in placeholders if name not in inputs)
+
+
+def _prompt_for_missing_inputs(
+    crew: Any, default_inputs: dict[str, Any]
+) -> dict[str, Any]:
+    """Ask for runtime values for placeholders that lack default inputs."""
+    inputs = dict(default_inputs or {})
+    missing = _missing_input_names(crew, inputs)
+    if not missing:
+        return inputs
+
+    enable_prompt_line_editing()
+
+    click.echo()
+    click.secho("  Runtime inputs", fg="cyan", bold=True)
+    click.secho(
+        "  Values for {placeholder} references in your agents and tasks.",
+        dim=True,
+    )
+
+    for name in missing:
+        inputs[name] = click.prompt(
+            click.style(f"  {name}", fg="cyan"),
+            prompt_suffix=click.style(" > ", fg="bright_white"),
+        )
+
+    return inputs
+
+
+def _json_loading_status(message: str) -> AbstractContextManager[Any]:
+    from rich.console import Console
+    from rich.text import Text
+
+    console = Console()
+    if not console.is_terminal:
+        return nullcontext()
+    return console.status(
+        Text(f"  {message}", style="bold #1F7982"),
+        spinner="dots",
+    )
+
+
+def _load_json_crew(crew_path: Path) -> tuple[Any, dict[str, Any]]:
+    from crewai.project.crew_loader import load_crew
+
+    return load_crew(crew_path)
+
+
+def _load_json_crew_for_tui(
+    crew_path: Path,
+) -> tuple[type[Any], Any, dict[str, Any], list[str], list[str]]:
+    with _json_loading_status("Preparing crew..."):
+        from crewai_cli.crew_run_tui import CrewRunApp
+
+        crew, default_inputs = _load_json_crew(crew_path)
+        _prepare_json_crew_for_tui(crew)
+        task_names = [
+            getattr(task, "name", "") or getattr(task, "description", "")[:40] or "Task"
+            for task in crew.tasks
+        ]
+        agent_names = [
+            getattr(agent, "role", "") or getattr(agent, "name", "") or "Agent"
+            for agent in crew.agents
+        ]
+
+    return CrewRunApp, crew, default_inputs, task_names, agent_names
+
+
+def _prepare_json_crew_for_tui(crew: Any) -> None:
+    """Apply the same quiet/streaming setup used by the TUI JSON loader."""
+    crew.verbose = False
+    for agent in crew.agents:
+        agent.verbose = False
+        if hasattr(agent, "llm") and hasattr(agent.llm, "stream"):
+            agent.llm.stream = True
+
+
+def _run_json_crew(trained_agents_file: str | None = None) -> Any:
+    """Load and run a JSON-defined crew."""
+    from dotenv import load_dotenv
+
+    env_file = Path.cwd() / ".env"
+    if env_file.exists():
+        load_dotenv(env_file, override=True)
+
+    # JSON crews run in-process, so export the trained-agents file directly
+    # instead of forwarding it to a subprocess like classic crews do.
+    if trained_agents_file:
+        os.environ[CREWAI_TRAINED_AGENTS_FILE_ENV] = trained_agents_file
+
+    crew_path = find_crew_json_file()
+    if crew_path is None:
+        raise FileNotFoundError("No crew.jsonc or crew.json found")
+
+    crew_run_app_cls, crew, default_inputs, task_names, agent_names = (
+        _load_json_crew_for_tui(crew_path)
+    )
+    runtime_inputs = _prompt_for_missing_inputs(crew, default_inputs)
+
+    app = crew_run_app_cls(
+        crew_name=crew.name or "Crew",
+        total_tasks=len(crew.tasks),
+        agent_names=agent_names,
+        task_names=task_names,
+    )
+    app._crew = crew
+    app._default_inputs = runtime_inputs
+
+    app.run()
+
+    _print_post_tui_summary(app)
+
+    if app._status == "failed":
+        # Mirror the classic subprocess path: a failed crew must produce a
+        # non-zero exit code so scripts and CI don't treat it as success.
+        raise SystemExit(1)
+
+    if app._status not in ("completed", "failed"):
+        # User quit mid-run. kickoff runs in a thread worker that cannot be
+        # force-cancelled, so end the process to stop in-flight LLM and tool
+        # work instead of letting it burn tokens in the background.
+        click.secho("\n  Run cancelled.", fg="yellow")
+        sys.stdout.flush()
+        os._exit(130)
+
+    if getattr(app, "_want_deploy", False):
+        _chain_deploy()
+
+    return app._crew_result
+
+
+def _chain_deploy() -> None:
+    from rich.console import Console
+
+    console = Console()
+    try:
+        from crewai_cli.deploy.main import DeployCommand
+
+        console.print("\nStarting deployment…\n", style="bold #FF5A50")
+        DeployCommand().create_crew(confirm=False, skip_validate=True)
+    except SystemExit:
+        from crewai_cli.authentication.main import AuthenticationCommand
+
+        console.print()
+        AuthenticationCommand().login()
+        try:
+            DeployCommand().create_crew(confirm=False, skip_validate=True)
+        except Exception as e:
+            console.print(f"\nDeploy failed: {e}\n", style="bold red")
+    except Exception as e:
+        console.print(f"\nDeploy failed: {e}\n", style="bold red")
+
+
+def _print_post_tui_summary(app: CrewRunApp) -> None:
+    """Print a summary to the terminal after the Textual TUI exits."""
+    import time
+
+    from rich.console import Console
+    from rich.markdown import Markdown
+    from rich.padding import Padding
+    from rich.panel import Panel
+    from rich.text import Text
+
+    console = Console()
+    elapsed = time.time() - app._start_time
+
+    out_tokens = app._output_tokens + app._live_out_tokens
+    token_parts = []
+    if app._input_tokens:
+        token_parts.append(f"↑{app._input_tokens:,}")
+    if out_tokens:
+        token_parts.append(f"↓{out_tokens:,}")
+    token_str = "  ".join(token_parts)
+    if token_str:
+        token_str += " tokens"
+
+    crewai_red = "#FF5A50"
+    crewai_teal = "#1F7982"
+
+    if app._status == "completed":
+        summary = Text()
+        summary.append(
+            f"  ✔ Completed {app._total_tasks} tasks",
+            style=f"bold {crewai_teal}",
+        )
+        summary.append(f" in {elapsed:.1f}s", style="dim")
+        if token_str:
+            summary.append(f"  {token_str}", style="dim")
+        console.print(
+            Panel(
+                summary,
+                title=f" {app._crew_name} ",
+                title_align="left",
+                border_style=crewai_teal,
+                padding=(0, 1),
+            )
+        )
+        if app._final_output:
+            console.print()
+            console.print(Text("  Final Result", style=f"bold {crewai_teal}"))
+            console.print()
+            console.print(Padding(Markdown(app._final_output), (0, 2)))
+    elif app._status == "failed":
+        content = Text()
+        content.append("  ✘ Failed", style=f"bold {crewai_red}")
+        content.append(f" after {elapsed:.1f}s\n", style="dim")
+        if app._error:
+            content.append(f"\n  {app._error}\n", style=crewai_red)
+        console.print(
+            Panel(
+                content,
+                title=f" {app._crew_name} ",
+                title_align="left",
+                border_style=crewai_red,
+                padding=(0, 1),
+            )
+        )
+
+
+def run_crew(trained_agents_file: str | None = None) -> None:
+    """Run the crew or flow.
 
     Args:
         trained_agents_file: Optional path to a trained-agents pickle produced
@@ -27,6 +313,11 @@ def run_crew(trained_agents_file: str | None = None) -> None:
             ``CREWAI_TRAINED_AGENTS_FILE`` so agents load suggestions from this
             file instead of the default ``trained_agents_data.pkl``.
     """
+    # JSON crew projects take precedence
+    if _has_json_crew():
+        _run_json_crew(trained_agents_file=trained_agents_file)
+        return
+
     crewai_version = get_crewai_version()
     min_required_version = "0.71.0"
     pyproject_data = read_toml()

lib/cli/src/crewai_cli/run_flow_definition.py

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

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

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

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

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

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

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

lib/cli/src/crewai_cli/tui_picker.py

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

lib/cli/src/crewai_cli/utils.py

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

lib/cli/tests/deploy/test_deploy_main.py

@@ -150,6 +150,7 @@ class TestDeployCommand(unittest.TestCase):
     @patch("crewai_cli.deploy.main.fetch_and_json_env_file")
     @patch("crewai_cli.deploy.main.git.Repository.origin_url")
     @patch("builtins.input")
+    @pytest.mark.timeout(180)
     def test_create_crew(self, mock_input, mock_git_origin_url, mock_fetch_env):
         mock_fetch_env.return_value = {"ENV_VAR": "value"}
         mock_git_origin_url.return_value = "https://github.com/test/repo.git"
@@ -165,6 +166,40 @@ class TestDeployCommand(unittest.TestCase):
             self.assertIn("Deployment created successfully!", fake_out.getvalue())
             self.assertIn("new-uuid", fake_out.getvalue())
 
+    @patch("crewai_cli.deploy.main.fetch_and_json_env_file")
+    @patch("crewai_cli.deploy.main.git.Repository")
+    def test_create_crew_without_git_repo_shows_setup_help(
+        self, mock_repository, mock_fetch_env
+    ):
+        mock_fetch_env.return_value = {"ENV_VAR": "value"}
+        mock_repository.side_effect = ValueError("not a Git repository")
+
+        with patch("sys.stdout", new=StringIO()) as fake_out:
+            self.deploy_command.create_crew(skip_validate=True)
+            output = fake_out.getvalue()
+
+        self.assertIn("Deployment requires a Git repository", output)
+        self.assertIn("git init", output)
+        self.assertIn("git remote add origin <your-repo-url>", output)
+        self.mock_client.create_crew.assert_not_called()
+
+    @patch("crewai_cli.deploy.main.fetch_and_json_env_file")
+    @patch("crewai_cli.deploy.main.git.Repository")
+    def test_create_crew_without_remote_shows_remote_help(
+        self, mock_repository, mock_fetch_env
+    ):
+        mock_fetch_env.return_value = {"ENV_VAR": "value"}
+        mock_repository.return_value.origin_url.return_value = None
+
+        with patch("sys.stdout", new=StringIO()) as fake_out:
+            self.deploy_command.create_crew(skip_validate=True)
+            output = fake_out.getvalue()
+
+        self.assertIn("No remote repository URL found.", output)
+        self.assertIn("git remote add origin <your-repo-url>", output)
+        self.assertIn("git push -u origin HEAD", output)
+        self.mock_client.create_crew.assert_not_called()
+
     def test_list_crews(self):
         mock_response = MagicMock()
         mock_response.status_code = 200

lib/cli/tests/deploy/test_validate.py

@@ -110,6 +110,45 @@ def _run_without_import_check(root: Path) -> DeployValidator:
     return v
 
 
+def _scaffold_json_crew(root: Path, *, task_agent: str = "researcher") -> None:
+    (root / "pyproject.toml").write_text(_make_pyproject(name="json_crew"))
+    (root / "uv.lock").write_text("# dummy uv lockfile\n")
+    agents_dir = root / "agents"
+    agents_dir.mkdir()
+    (agents_dir / "researcher.jsonc").write_text(
+        dedent(
+            """
+            {
+              "role": "Researcher",
+              "goal": "Research things",
+              "backstory": "Experienced researcher",
+              "llm": "openai/gpt-4o-mini"
+            }
+            """
+        ).strip()
+        + "\n"
+    )
+    (root / "crew.jsonc").write_text(
+        dedent(
+            f"""
+            {{
+              "name": "json_crew",
+              "agents": ["researcher"],
+              "tasks": [
+                {{
+                  "name": "research",
+                  "description": "Research https://example.com/a//b",
+                  "expected_output": "Findings",
+                  "agent": "{task_agent}"
+                }}
+              ]
+            }}
+            """
+        ).strip()
+        + "\n"
+    )
+
+
 @pytest.mark.parametrize(
     "project_name, expected",
     [
@@ -129,6 +168,38 @@ def test_valid_standard_crew_project_passes(tmp_path: Path) -> None:
     assert v.ok, f"expected clean run, got {v.results}"
 
 
+def test_valid_json_crew_project_passes(tmp_path: Path) -> None:
+    _scaffold_json_crew(tmp_path)
+    v = DeployValidator(project_root=tmp_path)
+    v.run()
+    assert "invalid_crew_json" not in _codes(v)
+
+
+def test_json_task_agent_mismatch_is_error(tmp_path: Path) -> None:
+    _scaffold_json_crew(tmp_path, task_agent="missing_agent")
+    v = DeployValidator(project_root=tmp_path)
+    v.run()
+    finding = next(r for r in v.results if r.code == "invalid_crew_json")
+    assert finding.severity is Severity.ERROR
+    assert "missing_agent" in finding.detail
+
+
+def test_json_runtime_fields_are_deploy_errors(tmp_path: Path) -> None:
+    _scaffold_json_crew(tmp_path)
+    crew_path = tmp_path / "crew.jsonc"
+    crew_path.write_text(
+        crew_path.read_text().replace(
+            '"name": "json_crew",',
+            '"name": "json_crew",\n  "id": "00000000-0000-4000-8000-000000000000",',
+        )
+    )
+    v = DeployValidator(project_root=tmp_path)
+    v.run()
+    finding = next(r for r in v.results if r.code == "invalid_crew_json")
+    assert finding.severity is Severity.ERROR
+    assert "runtime-only" in finding.detail
+
+
 def test_missing_pyproject_errors(tmp_path: Path) -> None:
     v = _run_without_import_check(tmp_path)
     assert "missing_pyproject" in _codes(v)
@@ -426,4 +497,31 @@ def test_create_crew_aborts_on_validation_error(tmp_path: Path) -> None:
         cmd = DeployCommand()
         cmd.create_crew()
         assert not cmd.plus_api_client.create_crew.called
-        del mock_api  # silence unused-var lint
+        del mock_api  # silence unused-var lint
+
+
+def test_is_json_crew_defers_to_declared_flow_type(tmp_path):
+    """A flow project with a stray crew.jsonc must validate as a flow."""
+    (tmp_path / "crew.jsonc").write_text("{}")
+    (tmp_path / "pyproject.toml").write_text(
+        '[project]\nname = "demo"\nversion = "0.1.0"\n\n'
+        '[tool.crewai]\ntype = "flow"\n'
+    )
+
+    assert DeployValidator(project_root=tmp_path)._is_json_crew is False
+
+
+def test_is_json_crew_true_for_declared_crew_type(tmp_path):
+    (tmp_path / "crew.jsonc").write_text("{}")
+    (tmp_path / "pyproject.toml").write_text(
+        '[project]\nname = "demo"\nversion = "0.1.0"\n\n'
+        '[tool.crewai]\ntype = "crew"\n'
+    )
+
+    assert DeployValidator(project_root=tmp_path)._is_json_crew is True
+
+
+def test_is_json_crew_true_without_pyproject(tmp_path):
+    (tmp_path / "crew.jsonc").write_text("{}")
+
+    assert DeployValidator(project_root=tmp_path)._is_json_crew is True

lib/cli/tests/test_cli.py

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

lib/cli/tests/test_create_crew.py

@@ -6,6 +6,8 @@ from unittest import mock
 
 import pytest
 from click.testing import CliRunner
+import crewai_cli.create_json_crew as json_crew
+import crewai_cli.tui_picker as tui_picker
 from crewai_cli.create_crew import create_crew, create_folder_structure
 
 
@@ -345,3 +347,441 @@ def test_env_vars_are_uppercased_in_env_file(
     env_file_path = crew_path / ".env"
     content = env_file_path.read_text()
     assert "MODEL=" in content
+
+
+def test_json_wizard_defaults_to_sequential_and_memory_enabled(monkeypatch):
+    monkeypatch.setattr(
+        json_crew,
+        "_wizard_agent",
+        lambda **_: {
+            "name": "researcher",
+            "role": "Researcher",
+            "goal": "Research",
+            "backstory": "Researcher",
+            "llm": "openai/gpt-5.5",
+            "tools": [],
+            "planning": False,
+            "allow_delegation": False,
+        },
+    )
+    monkeypatch.setattr(
+        json_crew,
+        "_wizard_task",
+        lambda **_: {
+            "name": "research_task",
+            "description": "Research",
+            "expected_output": "Findings",
+            "agent": "researcher",
+            "context": [],
+        },
+    )
+
+    def confirm(label: str, default: bool = False) -> bool:
+        if label == "Enable crew memory?":
+            return default
+        return False
+
+    monkeypatch.setattr(json_crew, "_confirm", confirm)
+    monkeypatch.setattr(json_crew.click, "prompt", lambda *_, **__: "")
+    monkeypatch.setattr(
+        json_crew,
+        "pick_one",
+        lambda *_args, **_kwargs: pytest.fail("process should not be prompted"),
+    )
+
+    _agents, _tasks, settings = json_crew._wizard_agents_and_tasks(
+        skip_provider=True,
+        default_llm="openai/gpt-5.5",
+    )
+
+    assert settings == {"process": "sequential", "memory": True, "inputs": {}}
+
+
+def test_json_wizard_shows_interpolation_hint(capsys):
+    json_crew._show_interpolation_hint("tasks")
+
+    output = capsys.readouterr().out
+    assert "{placeholder}" in output
+    assert "dynamic values" in output
+    assert "{topic}" not in output
+    assert "Description >" not in output
+    assert '"description"' not in output
+
+
+def test_json_wizard_text_prompt_uses_full_prompt_for_readline(monkeypatch):
+    prompts: list[str] = []
+
+    monkeypatch.setattr(
+        json_crew, "_readline_safe_prompt", lambda prompt: f"safe:{prompt}"
+    )
+    monkeypatch.setattr(
+        "builtins.input", lambda prompt: prompts.append(prompt) or "Draft content"
+    )
+
+    assert json_crew._prompt_text("Goal", spacing_before=False) == "Draft content"
+    assert len(prompts) == 1
+    assert prompts[0].startswith("safe:")
+    assert "Goal" in prompts[0]
+    assert " > " in prompts[0]
+
+
+def test_json_wizard_tool_picker_prioritizes_common_tools(monkeypatch):
+    picker_calls: list[tuple[str, list[str], dict[str, object]]] = []
+
+    def pick_many(title: str, labels: list[str], **kwargs):
+        picker_calls.append((title, labels, kwargs))
+        return [1, 3], None
+
+    monkeypatch.setattr(json_crew, "pick_many", pick_many)
+
+    tools = json_crew._select_tools()
+
+    assert tools == ["SerperDevTool", "DirectoryReadTool"]
+    assert len(picker_calls) == 1
+    labels = picker_calls[0][1]
+    assert 0 in picker_calls[0][2]["separator_indices"]
+    assert labels[0] == "── Common tools ──"
+    assert labels[1].strip().endswith("SerperDevTool")
+    assert labels[2].strip().endswith("ScrapeWebsiteTool")
+    assert labels[3].strip().endswith("DirectoryReadTool")
+    assert labels[4].strip().endswith("FileReadTool")
+    assert labels[5].strip().endswith("FileWriterTool")
+    assert labels[1].index("Google search") < labels[1].index("SerperDevTool")
+    assert "More tools" not in labels
+
+
+def test_json_wizard_tool_picker_collapses_categories_by_default(monkeypatch):
+    picker_calls: list[tuple[str, list[str], dict[str, object]]] = []
+
+    def pick_many(title: str, labels: list[str], **kwargs):
+        picker_calls.append((title, labels, kwargs))
+        return [], None
+
+    monkeypatch.setattr(json_crew, "pick_many", pick_many)
+
+    json_crew._select_tools()
+
+    labels = picker_calls[0][1]
+    action_indices = picker_calls[0][2]["action_indices"]
+    # Categories show as collapsed action rows, not separators with tools
+    assert any(label.startswith("▸ Search & Research") for label in labels)
+    assert any(label.startswith("▸ Web Scraping") for label in labels)
+    assert not any(label.strip().endswith("BraveSearchTool") for label in labels)
+    assert len(action_indices) >= 4
+    # Only the common tools section is visible beyond the category rows
+    assert len(labels) == 1 + 5 + len(action_indices)
+
+
+def test_json_wizard_tool_picker_expands_one_category_at_a_time(monkeypatch):
+    picker_calls: list[tuple[str, list[str], dict[str, object]]] = []
+
+    def find_category_row(labels: list[str], category: str) -> int:
+        return next(
+            idx for idx, label in enumerate(labels) if category in label
+        )
+
+    def pick_many(title: str, labels: list[str], **kwargs):
+        picker_calls.append((title, labels, kwargs))
+        call_num = len(picker_calls)
+        if call_num == 1:
+            return [], find_category_row(labels, "Search & Research")
+        if call_num == 2:
+            # Search & Research is expanded; select BraveSearchTool and
+            # expand Web Scraping instead
+            brave = next(
+                idx
+                for idx, label in enumerate(labels)
+                if label.strip().endswith("BraveSearchTool")
+            )
+            return [brave], find_category_row(labels, "Web Scraping")
+        return [], None
+
+    monkeypatch.setattr(json_crew, "pick_many", pick_many)
+
+    tools = json_crew._select_tools()
+
+    assert tools == ["BraveSearchTool"]
+    assert len(picker_calls) == 3
+    # Second render: Search & Research expanded, others collapsed
+    labels2 = picker_calls[1][1]
+    assert any(label.startswith("▾ Search & Research") for label in labels2)
+    assert any(label.strip().endswith("BraveSearchTool") for label in labels2)
+    assert any(label.startswith("▸ Web Scraping") for label in labels2)
+    # Third render: Web Scraping expanded, Search & Research collapsed again
+    labels3 = picker_calls[2][1]
+    assert any(label.startswith("▸ Search & Research") for label in labels3)
+    assert any(label.startswith("▾ Web Scraping") for label in labels3)
+    assert not any(label.strip().endswith("BraveSearchTool") for label in labels3)
+    # The collapsed Search & Research row reports its selection count
+    assert any(
+        "Search & Research" in label and "1 selected" in label for label in labels3
+    )
+    # Cursor returns to the toggled category row
+    assert picker_calls[2][2]["initial_cursor"] == next(
+        idx for idx, label in enumerate(labels3) if "Web Scraping" in label
+    )
+
+
+def test_json_wizard_tool_picker_preserves_selection_across_renders(monkeypatch):
+    picker_calls: list[tuple[str, list[str], dict[str, object]]] = []
+
+    def pick_many(title: str, labels: list[str], **kwargs):
+        picker_calls.append((title, labels, kwargs))
+        call_num = len(picker_calls)
+        if call_num == 1:
+            # Select a common tool, then expand a category
+            category_row = next(
+                idx for idx, label in enumerate(labels) if "Web Scraping" in label
+            )
+            return [1], category_row
+        # Confirm without touching anything else
+        return sorted(kwargs["preselected"]), None
+
+    monkeypatch.setattr(json_crew, "pick_many", pick_many)
+
+    tools = json_crew._select_tools()
+
+    # The common-tool selection survived the expand re-render via preselected
+    assert tools == ["SerperDevTool"]
+    assert 1 in picker_calls[1][2]["preselected"]
+
+
+def test_json_wizard_tool_picker_lists_builtin_tools_across_categories(monkeypatch):
+    picker_calls: list[tuple[str, list[str], dict[str, object]]] = []
+    expanded_labels: list[str] = []
+
+    def pick_many(title: str, labels: list[str], **kwargs):
+        picker_calls.append((title, labels, kwargs))
+        expanded_labels.extend(labels)
+        action_indices = sorted(kwargs["action_indices"])
+        call_num = len(picker_calls)
+        if call_num <= len(action_indices):
+            # Expand the n-th category (indices shift between renders, so
+            # recompute from this render's action rows)
+            return [], action_indices[call_num - 1]
+        return [], None
+
+    monkeypatch.setattr(json_crew, "pick_many", pick_many)
+
+    json_crew._select_tools()
+
+    tool_names = {
+        label.rsplit(maxsplit=1)[-1]
+        for label in expanded_labels
+        if not label.startswith(("▸", "▾", "──"))
+    }
+
+    assert {
+        "DirectorySearchTool",
+        "MDXSearchTool",
+        "XMLSearchTool",
+        "YoutubeVideoSearchTool",
+        "S3ReaderTool",
+        "E2BExecTool",
+        "TavilyResearchTool",
+        "SerplyNewsSearchTool",
+        "BrowserbaseLoadTool",
+        "PatronusEvalTool",
+    }.issubset(tool_names)
+    assert {
+        "MCPServerAdapter",
+        "MongoDBVectorSearchConfig",
+        "ScrapegraphScrapeToolSchema",
+        "SnowflakeConfig",
+    }.isdisjoint(tool_names)
+
+
+def test_multi_picker_skips_separator_on_initial_cursor(monkeypatch):
+    cursors: list[int] = []
+
+    monkeypatch.setattr(tui_picker, "_read_key", lambda: "enter")
+    monkeypatch.setattr(
+        tui_picker,
+        "_draw_multi",
+        lambda _labels, cursor, *_args, **_kwargs: cursors.append(cursor),
+    )
+    monkeypatch.setattr(tui_picker, "_clear_lines", lambda *_args, **_kwargs: None)
+
+    assert tui_picker._arrow_select_multi(
+        ["── Common tools ──", "Google search via Serper API SerperDevTool"],
+        separator_indices={0},
+    ) == ([], None)
+    assert cursors == [1]
+
+
+def test_json_wizard_agent_attribute_prompts_are_compact(monkeypatch):
+    prompt_calls: list[tuple[str, bool]] = []
+    prompt_values = {
+        "Role": "Senior Dev Rel",
+        "Goal": "Draft content",
+        "Backstory": "Knows developer communities",
+    }
+
+    def prompt_text(
+        label: str,
+        default: str = "",
+        *,
+        spacing_before: bool = True,
+    ) -> str:
+        prompt_calls.append((label, spacing_before))
+        return prompt_values[label]
+
+    monkeypatch.setattr(json_crew, "_prompt_text", prompt_text)
+    monkeypatch.setattr(json_crew, "_select_model", lambda: "openai/gpt-5.5")
+    monkeypatch.setattr(json_crew, "pick_many", lambda *_args, **_kwargs: ([], None))
+    monkeypatch.setattr(json_crew, "_confirm", lambda *_args, **_kwargs: False)
+
+    agent = json_crew._wizard_agent(agent_num=1, existing_names=[])
+
+    assert agent is not None
+    assert prompt_calls == [
+        ("Role", False),
+        ("Goal", False),
+        ("Backstory", False),
+    ]
+
+
+def test_json_wizard_task_attribute_prompts_are_compact(monkeypatch):
+    prompt_calls: list[tuple[str, bool]] = []
+    prompt_values = {
+        "Description": "Research latest release",
+        "Expected output": "Release summary",
+    }
+
+    def prompt_text(
+        label: str,
+        default: str = "",
+        *,
+        spacing_before: bool = True,
+    ) -> str:
+        prompt_calls.append((label, spacing_before))
+        return prompt_values[label]
+
+    monkeypatch.setattr(json_crew, "_prompt_text", prompt_text)
+
+    task = json_crew._wizard_task(
+        task_num=1,
+        agent_names=["senior_dev_rel"],
+        prior_task_names=[],
+    )
+
+    assert task is not None
+    assert prompt_calls == [
+        ("Description", False),
+        ("Expected output", False),
+    ]
+
+
+def test_json_create_provider_preselects_default_model(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with mock.patch(
+        "crewai_cli.create_json_crew._wizard_agents_and_tasks"
+    ) as mock_wizard:
+        mock_wizard.return_value = (
+            [
+                {
+                    "name": "researcher",
+                    "role": "Researcher",
+                    "goal": "Research",
+                    "backstory": "Researcher",
+                    "llm": "openai/gpt-5.5",
+                    "tools": [],
+                    "planning": False,
+                    "allow_delegation": False,
+                }
+            ],
+            [
+                {
+                    "name": "research_task",
+                    "description": "Research",
+                    "expected_output": "Findings",
+                    "agent": "researcher",
+                    "context": [],
+                }
+            ],
+            {"process": "sequential", "memory": False, "inputs": {}},
+        )
+
+        json_crew.create_json_crew("JSON Crew", provider="openai", skip_provider=True)
+
+    mock_wizard.assert_called_once_with(
+        skip_provider=True,
+        default_llm="openai/gpt-5.5",
+    )
+    assert (tmp_path / "json_crew" / "crew.jsonc").exists()
+    assert not (tmp_path / "json_crew" / "tests").exists()
+    assert not (tmp_path / "json_crew" / "config.jsonc").exists()
+
+    crew_template = (tmp_path / "json_crew" / "crew.jsonc").read_text()
+    assert (
+        '"guardrail": "Every factual claim needs context support."'
+        in crew_template
+    )
+    assert '"guardrails": [' in crew_template
+    assert '"guardrail_max_retries": 2' in crew_template
+    assert "Docs: https://docs.crewai.com/concepts/tasks" in crew_template
+    assert '"output_pydantic": null' in crew_template
+    assert '"markdown": false' in crew_template
+    assert "Docs: https://docs.crewai.com/concepts/crews" in crew_template
+    assert '"manager_agent": "researcher"' in crew_template
+    assert '"output_log_file": "crew.log"' in crew_template
+    assert "Crew-level LLM fields also accept object form" in crew_template
+    assert '"chat_llm": {"model": "llama3", "provider": "ollama"' in (
+        crew_template
+    )
+    assert "Use {placeholder} in agent or task text" in crew_template
+    assert "`crewai run` prompts for any placeholders" in crew_template
+    assert "Use {placeholder} inputs here" in crew_template
+
+    agent_template = (
+        tmp_path / "json_crew" / "agents" / "researcher.jsonc"
+    ).read_text()
+    assert "You can use {placeholder} inputs in role, goal, or backstory" in (
+        agent_template
+    )
+    assert '"role": "Senior {industry} Researcher"' in agent_template
+    assert "Optional agent-level guardrail" in agent_template
+    assert '"guardrail_max_retries": 2' in agent_template
+    assert "Docs: https://docs.crewai.com/concepts/agents" in agent_template
+    assert '"reasoning": true' in agent_template
+    assert "For custom endpoints or deployment-based providers" in agent_template
+    assert '"deployment_name": "my-deployment", "provider": "azure"' in (
+        agent_template
+    )
+    assert '"planning_config": {' in agent_template
+    assert '"llm": {"model": "deepseek-chat", "provider": "deepseek"}' in (
+        agent_template
+    )
+    assert '"knowledge_sources": []' in agent_template
+
+
+def test_json_provider_default_model_helper():
+    assert json_crew._default_model_for_provider("openai") == "openai/gpt-5.5"
+    assert json_crew._default_model_for_provider("anthropic/claude-custom") == (
+        "anthropic/claude-custom"
+    )
+    assert json_crew._default_model_for_provider("unknown") is None
+
+
+def test_json_wizard_task_reprompts_on_cancelled_agent_pick(monkeypatch):
+    """Esc on the agent picker must reprompt, not silently assign agent 0."""
+    prompts = iter(["Do the research", "A report"])
+    monkeypatch.setattr(json_crew, "_prompt_text", lambda *a, **k: next(prompts))
+
+    pick_calls: list[str] = []
+    picks = iter([-1, 1])
+
+    def fake_pick_one(title: str, labels: list[str]) -> int:
+        pick_calls.append(title)
+        return next(picks)
+
+    monkeypatch.setattr(json_crew, "pick_one", fake_pick_one)
+
+    task = json_crew._wizard_task(
+        task_num=1,
+        agent_names=["first_agent", "second_agent"],
+        prior_task_names=[],
+    )
+
+    assert len(pick_calls) == 2
+    assert task["agent"] == "second_agent"

lib/cli/tests/test_crew_run_tui.py

@@ -0,0 +1,796 @@
+from datetime import datetime
+import time
+
+import pytest
+
+from crewai.events.event_bus import crewai_event_bus
+from crewai.events.types.observation_events import (
+    GoalAchievedEarlyEvent,
+    PlanRefinementEvent,
+    PlanReplanTriggeredEvent,
+    PlanStepCompletedEvent,
+    PlanStepStartedEvent,
+    StepObservationCompletedEvent,
+    StepObservationFailedEvent,
+    StepObservationStartedEvent,
+)
+from crewai.events.types.tool_usage_events import (
+    ToolUsageErrorEvent,
+    ToolUsageFinishedEvent,
+    ToolUsageStartedEvent,
+)
+from crewai_cli import run_crew
+from crewai_cli.crew_run_tui import CrewRunApp
+
+
+def _app_with_plan() -> CrewRunApp:
+    app = CrewRunApp()
+    app._plan = {
+        "plan": "Demo plan",
+        "steps": [
+            {"step_number": 1, "description": "First"},
+            {"step_number": 2, "description": "Second"},
+            {"step_number": 3, "description": "Third"},
+        ],
+    }
+    app._plan_step_status = {1: "pending", 2: "pending", 3: "pending"}
+    return app
+
+
+def _log_entry(name: str) -> dict:
+    now = time.time()
+    return {
+        "tool_name": name,
+        "status": "success",
+        "args": None,
+        "result": f"{name} result",
+        "error": None,
+        "start_time": now,
+        "duration": 1.0,
+        "task_idx": 1,
+    }
+
+
+def _emit_event(event: object) -> None:
+    future = crewai_event_bus.emit(None, event)
+    if future:
+        future.result(timeout=5)
+
+
+def test_chain_deploy_skips_validation_after_auth_retry(monkeypatch) -> None:
+    create_calls: list[dict[str, object]] = []
+    login_calls: list[bool] = []
+
+    class FakeDeployCommand:
+        attempts = 0
+
+        def create_crew(self, **kwargs) -> None:
+            create_calls.append(kwargs)
+            FakeDeployCommand.attempts += 1
+            if FakeDeployCommand.attempts == 1:
+                raise SystemExit(1)
+
+    class FakeAuthenticationCommand:
+        def login(self) -> None:
+            login_calls.append(True)
+
+    monkeypatch.setattr("crewai_cli.deploy.main.DeployCommand", FakeDeployCommand)
+    monkeypatch.setattr(
+        "crewai_cli.authentication.main.AuthenticationCommand",
+        FakeAuthenticationCommand,
+    )
+
+    run_crew._chain_deploy()
+
+    assert create_calls == [
+        {"confirm": False, "skip_validate": True},
+        {"confirm": False, "skip_validate": True},
+    ]
+    assert login_calls == [True]
+
+
+def test_plan_step_status_updates_only_the_explicit_step() -> None:
+    app = _app_with_plan()
+
+    app._set_plan_step_status(2, "done")
+
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "done",
+        3: "pending",
+    }
+
+
+def test_step_observation_events_update_the_explicit_step() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        future = crewai_event_bus.emit(
+            None,
+            StepObservationStartedEvent(
+                agent_role="Agent",
+                step_number=2,
+                step_description="Second",
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+
+        assert app._plan_step_status == {
+            1: "pending",
+            2: "active",
+            3: "pending",
+        }
+
+        future = crewai_event_bus.emit(
+            None,
+            StepObservationCompletedEvent(
+                agent_role="Agent",
+                step_number=2,
+                step_description="Second",
+                step_completed_successfully=True,
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+    finally:
+        app._unsubscribe()
+
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "done",
+        3: "pending",
+    }
+
+
+def test_plan_step_lifecycle_events_update_the_explicit_step() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        _emit_event(
+            PlanStepStartedEvent(
+                agent_role="Agent",
+                step_number=2,
+                step_description="Second",
+            )
+        )
+
+        assert app._plan_step_status == {
+            1: "pending",
+            2: "active",
+            3: "pending",
+        }
+
+        _emit_event(
+            PlanStepCompletedEvent(
+                agent_role="Agent",
+                step_number=2,
+                step_description="Second",
+                success=True,
+                result="done",
+            )
+        )
+    finally:
+        app._unsubscribe()
+
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "done",
+        3: "pending",
+    }
+
+
+def test_failed_plan_step_lifecycle_event_marks_exact_step_failed() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        _emit_event(
+            PlanStepCompletedEvent(
+                agent_role="Agent",
+                step_number=2,
+                step_description="Second",
+                success=False,
+                error="Step failed",
+            )
+        )
+    finally:
+        app._unsubscribe()
+
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "failed",
+        3: "pending",
+    }
+
+
+def test_tool_usage_events_do_not_advance_plan_steps() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        future = crewai_event_bus.emit(
+            None,
+            ToolUsageStartedEvent(tool_name="search", tool_args={"query": "CrewAI"}),
+        )
+        if future:
+            future.result(timeout=5)
+
+        now = datetime.now()
+        future = crewai_event_bus.emit(
+            None,
+            ToolUsageFinishedEvent(
+                tool_name="search",
+                tool_args={"query": "CrewAI"},
+                started_at=now,
+                finished_at=now,
+                output="result",
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+    finally:
+        app._unsubscribe()
+
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "pending",
+        3: "pending",
+    }
+
+
+def test_next_tool_does_not_mark_unfinished_tool_successful() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        _emit_event(
+            ToolUsageStartedEvent(tool_name="search", tool_args={"query": "CrewAI"}),
+        )
+        _emit_event(
+            ToolUsageStartedEvent(tool_name="scrape", tool_args={"url": "https://x"}),
+        )
+    finally:
+        app._unsubscribe()
+
+    assert app._log_entries[0]["status"] == "timeout"
+    assert app._log_entries[0]["result"] is None
+    assert app._log_entries[0]["error"] == (
+        "No result received before the next tool started"
+    )
+    assert app._log_entries[1]["status"] == "running"
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "pending",
+        3: "pending",
+    }
+
+
+def test_internal_reasoning_function_call_is_hidden_from_activity_log() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        future = crewai_event_bus.emit(
+            None,
+            ToolUsageStartedEvent(
+                tool_name="create_reasoning_plan",
+                tool_args={"plan": "Plan", "steps": [], "ready": True},
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+
+        now = datetime.now()
+        future = crewai_event_bus.emit(
+            None,
+            ToolUsageFinishedEvent(
+                tool_name="create_reasoning_plan",
+                tool_args={"plan": "Plan", "steps": [], "ready": True},
+                started_at=now,
+                finished_at=now,
+                output='{"plan":"Plan","steps":[],"ready":true}',
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+
+        future = crewai_event_bus.emit(
+            None,
+            ToolUsageErrorEvent(
+                tool_name="create_reasoning_plan",
+                tool_args={"plan": "Plan", "steps": [], "ready": True},
+                error="internal planning fallback",
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+    finally:
+        app._unsubscribe()
+
+    assert app._log_entries == []
+    assert app._current_task_steps == []
+
+
+def test_tool_failure_does_not_override_successful_plan_step_completion() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        _emit_event(
+            PlanStepStartedEvent(
+                agent_role="Agent",
+                step_number=1,
+                step_description="First",
+            )
+        )
+        _emit_event(
+            ToolUsageStartedEvent(
+                tool_name="search_the_internet_with_serper",
+                tool_args={"search_query": "CrewAI release"},
+                plan_step_number=1,
+                plan_step_description="First",
+            )
+        )
+        _emit_event(
+            ToolUsageErrorEvent(
+                tool_name="search_the_internet_with_serper",
+                tool_args={"search_query": "CrewAI release"},
+                plan_step_number=1,
+                plan_step_description="First",
+                error="No results",
+            )
+        )
+        _emit_event(
+            PlanStepCompletedEvent(
+                agent_role="Agent",
+                step_number=1,
+                step_description="First",
+                success=True,
+                result="Recovered with another source",
+            )
+        )
+    finally:
+        app._unsubscribe()
+
+    assert app._plan_step_status == {
+        1: "done",
+        2: "pending",
+        3: "pending",
+    }
+
+
+def test_tool_event_step_metadata_is_stored_in_activity_log() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        _emit_event(
+            ToolUsageStartedEvent(
+                tool_name="search_the_internet_with_serper",
+                tool_args={"search_query": "CrewAI release"},
+                plan_step_number=2,
+                plan_step_description="Second",
+            )
+        )
+        now = datetime.now()
+        _emit_event(
+            ToolUsageFinishedEvent(
+                tool_name="search_the_internet_with_serper",
+                tool_args={"search_query": "CrewAI release"},
+                plan_step_number=2,
+                plan_step_description="Second",
+                started_at=now,
+                finished_at=now,
+                output="Found official source",
+            )
+        )
+    finally:
+        app._unsubscribe()
+
+    assert app._log_entries[0]["plan_step_number"] == 2
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "pending",
+        3: "pending",
+    }
+
+
+def test_starting_next_tool_does_not_infer_plan_step_progress() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        _emit_event(
+            ToolUsageStartedEvent(
+                tool_name="search_the_internet_with_serper",
+                tool_args={"search_query": "CrewAI release"},
+            )
+        )
+        _emit_event(
+            ToolUsageErrorEvent(
+                tool_name="search_the_internet_with_serper",
+                tool_args={"search_query": "CrewAI release"},
+                error="No results",
+            )
+        )
+        _emit_event(
+            ToolUsageStartedEvent(
+                tool_name="read_website_content",
+                tool_args={"url": "https://example.com"},
+            )
+        )
+    finally:
+        app._unsubscribe()
+
+    assert app._log_entries[0]["status"] == "error"
+    assert app._log_entries[1]["status"] == "running"
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "pending",
+        3: "pending",
+    }
+
+
+@pytest.mark.asyncio
+async def test_crew_done_does_not_mark_unfinished_tool_successful() -> None:
+    app = _app_with_plan()
+
+    async with app.run_test(size=(100, 40)) as pilot:
+        app._plan_step_status = {1: "failed", 2: "done", 3: "pending"}
+        app._log_entries = [
+            {
+                "tool_name": "search",
+                "status": "running",
+                "args": '{"query": "CrewAI"}',
+                "result": None,
+                "error": None,
+                "start_time": time.time() - 2,
+                "duration": None,
+                "task_idx": 1,
+            }
+        ]
+
+        app._on_crew_done("final output")
+        await pilot.pause()
+
+    assert app._log_entries[0]["status"] == "timeout"
+    assert app._log_entries[0]["result"] is None
+    assert app._log_entries[0]["error"] == "No result received before crew completed"
+    assert app._plan_step_status == {1: "failed", 2: "done", 3: "done"}
+
+
+def test_streamed_step_observation_updates_named_step_only() -> None:
+    app = _app_with_plan()
+
+    updated = app._try_parse_step_observation(
+        '{"step_completed_successfully":true,'
+        '"key_information_learned":"Step 2 succeeded with the official source."}'
+    )
+
+    assert updated is True
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "done",
+        3: "pending",
+    }
+
+
+def test_failed_streamed_step_observation_marks_named_step_failed() -> None:
+    app = _app_with_plan()
+
+    updated = app._try_parse_step_observation(
+        '{"step_completed_successfully":false,'
+        '"key_information_learned":"Step 2 failed because the tool failed."}'
+    )
+
+    assert updated is True
+    assert app._plan_step_status == {
+        1: "pending",
+        2: "failed",
+        3: "pending",
+    }
+
+
+def test_streamed_goal_achieved_observation_collapses_remaining_steps_done() -> None:
+    app = _app_with_plan()
+
+    updated = app._try_parse_step_observation(
+        '{"step_number":2,'
+        '"step_completed_successfully":true,'
+        '"key_information_learned":"Goal is already satisfied.",'
+        '"goal_already_achieved":true}'
+    )
+
+    assert updated is True
+    assert app._plan_step_status == {
+        1: "done",
+        2: "done",
+        3: "done",
+    }
+
+
+def test_task_completion_collapses_pending_plan_steps_but_preserves_failed() -> None:
+    app = _app_with_plan()
+    app._plan_step_status = {1: "failed", 2: "done", 3: "pending"}
+
+    app._collapse_plan_on_task_done()
+
+    assert app._plan_step_status == {1: "failed", 2: "done", 3: "done"}
+
+
+def test_observation_failure_collapses_to_done_because_executor_continues() -> None:
+    app = _app_with_plan()
+    app._plan_step_status = {1: "done", 2: "active", 3: "pending"}
+    app._subscribe()
+    try:
+        future = crewai_event_bus.emit(
+            None,
+            StepObservationFailedEvent(
+                agent_role="Agent",
+                step_number=2,
+                step_description="Second",
+                error="observer timeout",
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+    finally:
+        app._unsubscribe()
+
+    assert app._plan_step_status == {
+        1: "done",
+        2: "done",
+        3: "pending",
+    }
+
+
+def test_goal_achieved_event_collapses_remaining_steps_done() -> None:
+    app = _app_with_plan()
+    app._plan_step_status = {1: "done", 2: "active", 3: "pending"}
+    app._subscribe()
+    try:
+        future = crewai_event_bus.emit(
+            None,
+            GoalAchievedEarlyEvent(
+                agent_role="Agent",
+                step_number=2,
+                steps_completed=2,
+                steps_remaining=1,
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+    finally:
+        app._unsubscribe()
+
+    assert app._plan_step_status == {
+        1: "done",
+        2: "done",
+        3: "done",
+    }
+
+
+def test_replan_event_keeps_old_plan_until_next_streamed_plan_replaces_it() -> None:
+    app = _app_with_plan()
+    app._subscribe()
+    try:
+        future = crewai_event_bus.emit(
+            None,
+            PlanReplanTriggeredEvent(
+                agent_role="Agent",
+                step_number=2,
+                replan_reason="Need updated sources",
+                replan_count=1,
+                completed_steps_preserved=1,
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+    finally:
+        app._unsubscribe()
+
+    assert app._plan is not None
+    assert app._plan_step_status == {1: "pending", 2: "pending", 3: "pending"}
+    assert app._awaiting_replan is True
+
+    app._try_parse_plan(
+        '{"plan":"Updated plan","steps":['
+        '{"step_number":1,"description":"Updated first"},'
+        '{"step_number":2,"description":"Updated second"}]}'
+    )
+
+    assert app._plan == {
+        "plan": "Updated plan",
+        "steps": [
+            {"step_number": 1, "description": "Updated first"},
+            {"step_number": 2, "description": "Updated second"},
+        ],
+    }
+    assert app._plan_step_status == {1: "pending", 2: "pending"}
+    assert app._awaiting_replan is False
+
+
+def test_plan_refinement_updates_descriptions_without_new_statuses() -> None:
+    app = _app_with_plan()
+    app._plan_step_status = {1: "done", 2: "active", 3: "pending"}
+    app._subscribe()
+    try:
+        future = crewai_event_bus.emit(
+            None,
+            PlanRefinementEvent(
+                agent_role="Agent",
+                step_number=2,
+                refined_step_count=1,
+                refinements=["Step 3: Write the final answer from verified facts"],
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+    finally:
+        app._unsubscribe()
+
+    assert app._plan_step_status == {
+        1: "done",
+        2: "done",
+        3: "pending",
+    }
+    assert app._plan["steps"][2]["description"] == (
+        "Write the final answer from verified facts"
+    )
+
+
+def test_step_observation_json_is_hidden_from_streaming_text() -> None:
+    app = _app_with_plan()
+
+    assert (
+        app._strip_step_observation_json(
+            'Visible before {"step_completed_successfully":true,'
+            '"key_information_learned":"Step 2 succeeded."} visible after'
+        )
+        == "Visible before  visible after"
+    )
+
+
+@pytest.mark.asyncio
+async def test_completed_run_keeps_activity_log_keyboard_navigation_active() -> None:
+    app = CrewRunApp()
+
+    async with app.run_test(size=(100, 40)) as pilot:
+        app._log_entries = [_log_entry("search"), _log_entry("scrape")]
+
+        app._on_crew_done("final output")
+        await pilot.pause()
+
+        assert app.focused is app.query_one("#log-panel")
+
+        await pilot.press("down", "enter")
+        await pilot.pause()
+
+        assert app._log_cursor == 1
+        assert app._log_expanded == {1}
+
+        await pilot.press("up")
+        await pilot.pause()
+
+        assert app._log_cursor == 0
+
+
+class _FakeTask:
+    fingerprint = None
+
+    def __init__(self, task_id: str, name: str) -> None:
+        self.id = task_id
+        self.name = name
+        self.description = name
+
+
+def test_async_task_completion_marks_the_right_sidebar_row() -> None:
+    """Overlapping tasks: completing task 1 while task 2 runs must not
+    mark task 2 done, and starting task 2 must not mark task 1 done."""
+    from crewai.events.types.task_events import TaskCompletedEvent, TaskStartedEvent
+    from crewai.tasks.task_output import TaskOutput
+
+    app = CrewRunApp(total_tasks=2, task_names=["first", "second"])
+    app._subscribe()
+    try:
+        task1 = _FakeTask("id-1", "first")
+        task2 = _FakeTask("id-2", "second")
+
+        for task in (task1, task2):
+            future = crewai_event_bus.emit(
+                None, TaskStartedEvent(context=None, task=task)
+            )
+            if future:
+                future.result(timeout=5)
+
+        # Both started: neither prematurely done
+        assert app._task_statuses == {1: "active", 2: "active"}
+
+        future = crewai_event_bus.emit(
+            None,
+            TaskCompletedEvent(
+                output=TaskOutput(description="first", raw="done", agent="a"),
+                task=task1,
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+
+        assert app._task_statuses == {1: "done", 2: "active"}
+    finally:
+        app._unsubscribe()
+
+
+def test_pop_task_state_falls_back_to_current_task() -> None:
+    app = CrewRunApp(total_tasks=2, task_names=["first", "second"])
+    app._current_task_idx = 2
+    app._current_task_desc = "second"
+
+    class _Evt:
+        task = None
+        task_name = "unknown"
+
+    state = app._pop_task_state(_Evt())
+    assert state["idx"] == 2
+    assert state["desc"] == "second"
+
+
+def test_overlapping_task_logs_keep_their_own_state() -> None:
+    """Task 1 completing after task 2 started must log its own description,
+    agent, and output — and must not steal or reset task 2's stream state."""
+    from crewai.events.types.task_events import TaskCompletedEvent, TaskStartedEvent
+    from crewai.tasks.task_output import TaskOutput
+
+    app = CrewRunApp(total_tasks=2, task_names=["first", "second"])
+    app._subscribe()
+    try:
+        task1 = _FakeTask("id-1", "first")
+        task2 = _FakeTask("id-2", "second")
+
+        for task in (task1, task2):
+            future = crewai_event_bus.emit(
+                None, TaskStartedEvent(context=None, task=task)
+            )
+            if future:
+                future.result(timeout=5)
+
+        # Task 2 is current and has streamed state in flight
+        app._task_full_output = "task two streaming output"
+        app._current_task_steps = [{"type": "llm", "summary": "thinking"}]
+
+        future = crewai_event_bus.emit(
+            None,
+            TaskCompletedEvent(
+                output=TaskOutput(
+                    description="first", raw="task one result", agent="a1"
+                ),
+                task=task1,
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+
+        # Task 1's entry carries its own identity and output
+        entry1 = app._task_logs[-1]
+        assert entry1["idx"] == 1
+        assert entry1["desc"] == "first"
+        assert entry1["output"] == "task one result"
+        assert entry1["steps"] == []
+
+        # Task 2's in-flight stream state was not consumed or reset
+        assert app._task_full_output == "task two streaming output"
+        assert app._current_task_steps == [{"type": "llm", "summary": "thinking"}]
+
+        future = crewai_event_bus.emit(
+            None,
+            TaskCompletedEvent(
+                output=TaskOutput(
+                    description="second", raw="task two result", agent="a2"
+                ),
+                task=task2,
+            ),
+        )
+        if future:
+            future.result(timeout=5)
+
+        entry2 = app._task_logs[-1]
+        assert entry2["idx"] == 2
+        assert entry2["desc"] == "second"
+        assert entry2["output"] == "task two streaming output"
+        assert any(step.get("summary") == "thinking" for step in entry2["steps"])
+    finally:
+        app._unsubscribe()

lib/cli/tests/test_run_crew.py

@@ -0,0 +1,144 @@
+"""Tests for crewai_cli.run_crew JSON crew handling."""
+
+import os
+from pathlib import Path
+
+import pytest
+from crewai_core.constants import CREWAI_TRAINED_AGENTS_FILE_ENV
+
+import crewai_cli.run_crew as run_crew_module
+
+
+def test_run_crew_forwards_trained_agents_file_to_json_crews(monkeypatch):
+    """crewai run -f must reach JSON crews, not only classic subprocess crews."""
+    monkeypatch.setattr(run_crew_module, "_has_json_crew", lambda: True)
+    called: dict = {}
+
+    def fake_run_json_crew(trained_agents_file=None):
+        called["trained_agents_file"] = trained_agents_file
+
+    monkeypatch.setattr(run_crew_module, "_run_json_crew", fake_run_json_crew)
+
+    run_crew_module.run_crew(trained_agents_file="some.pkl")
+
+    assert called == {"trained_agents_file": "some.pkl"}
+
+
+def test_run_json_crew_exports_trained_agents_env(monkeypatch, tmp_path: Path):
+    """JSON crews run in-process, so the pickle path must land in the env var."""
+    monkeypatch.chdir(tmp_path)
+    monkeypatch.delenv(CREWAI_TRAINED_AGENTS_FILE_ENV, raising=False)
+
+    try:
+        # No crew.json(c) in tmp_path: the loader fails *after* the env var
+        # export, which is the part under test.
+        with pytest.raises(FileNotFoundError):
+            run_crew_module._run_json_crew(trained_agents_file="some.pkl")
+        assert os.environ[CREWAI_TRAINED_AGENTS_FILE_ENV] == "some.pkl"
+    finally:
+        os.environ.pop(CREWAI_TRAINED_AGENTS_FILE_ENV, None)
+
+
+def test_run_json_crew_leaves_env_untouched_without_flag(monkeypatch, tmp_path: Path):
+    monkeypatch.chdir(tmp_path)
+    monkeypatch.delenv(CREWAI_TRAINED_AGENTS_FILE_ENV, raising=False)
+
+    with pytest.raises(FileNotFoundError):
+        run_crew_module._run_json_crew()
+
+    assert CREWAI_TRAINED_AGENTS_FILE_ENV not in os.environ
+
+
+def test_missing_input_names_accepts_hyphenated_placeholders():
+    """The prompt regex must accept the same names kickoff interpolation does."""
+    from types import SimpleNamespace
+
+    crew = SimpleNamespace(
+        agents=[
+            SimpleNamespace(
+                role="Researcher", goal="Cover {my-topic}", backstory=""
+            )
+        ],
+        tasks=[
+            SimpleNamespace(
+                description="Write about {my-topic} for {target-audience}",
+                expected_output="Post",
+                output_file=None,
+            )
+        ],
+    )
+
+    assert run_crew_module._missing_input_names(crew, {}) == [
+        "my-topic",
+        "target-audience",
+    ]
+
+
+def _patch_tui_run(monkeypatch, status: str):
+    """Stub the TUI pieces of _run_json_crew so only exit handling runs."""
+
+    class FakeApp:
+        def __init__(self, **kwargs):
+            self._status = status
+            self._crew_result = "result" if status == "completed" else None
+            self._want_deploy = False
+
+        def run(self):
+            pass
+
+    from types import SimpleNamespace
+
+    crew = SimpleNamespace(name="Demo", tasks=[], agents=[])
+    monkeypatch.setattr(
+        run_crew_module, "find_crew_json_file", lambda: Path("crew.jsonc")
+    )
+    monkeypatch.setattr(
+        run_crew_module,
+        "_load_json_crew_for_tui",
+        lambda _path: (FakeApp, crew, {}, [], []),
+    )
+    monkeypatch.setattr(
+        run_crew_module, "_prompt_for_missing_inputs", lambda _crew, inputs: inputs
+    )
+    monkeypatch.setattr(run_crew_module, "_print_post_tui_summary", lambda _app: None)
+
+
+def test_run_json_crew_failed_status_exits_nonzero(monkeypatch, tmp_path: Path):
+    monkeypatch.chdir(tmp_path)
+    _patch_tui_run(monkeypatch, status="failed")
+
+    with pytest.raises(SystemExit) as exc_info:
+        run_crew_module._run_json_crew()
+
+    assert exc_info.value.code == 1
+
+
+def test_run_json_crew_completed_status_returns_result(monkeypatch, tmp_path: Path):
+    monkeypatch.chdir(tmp_path)
+    _patch_tui_run(monkeypatch, status="completed")
+
+    assert run_crew_module._run_json_crew() == "result"
+
+
+def test_has_json_crew_defers_to_declared_flow_type(monkeypatch, tmp_path: Path):
+    """A flow project containing a stray crew.jsonc must still run as a flow."""
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "crew.jsonc").write_text("{}")
+    (tmp_path / "pyproject.toml").write_text('[tool.crewai]\ntype = "flow"\n')
+
+    assert run_crew_module._has_json_crew() is False
+
+
+def test_has_json_crew_true_for_declared_crew_type(monkeypatch, tmp_path: Path):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "crew.jsonc").write_text("{}")
+    (tmp_path / "pyproject.toml").write_text('[tool.crewai]\ntype = "crew"\n')
+
+    assert run_crew_module._has_json_crew() is True
+
+
+def test_has_json_crew_true_without_pyproject(monkeypatch, tmp_path: Path):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "crew.jsonc").write_text("{}")
+
+    assert run_crew_module._has_json_crew() is True

lib/cli/tests/test_run_flow_definition.py

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

lib/cli/tests/tools/test_main.py

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

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

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

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-core/src/crewai_core/telemetry.py

@@ -17,7 +17,7 @@ import contextlib
 import logging
 import os
 import threading
-from typing import Any, Final
+from typing import Any, ClassVar, Final
 
 from opentelemetry import trace
 from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
@@ -27,7 +27,7 @@ from opentelemetry.sdk.trace.export import (
     BatchSpanProcessor,
     SpanExportResult,
 )
-from opentelemetry.trace import Span, Status, StatusCode
+from opentelemetry.trace import ProxyTracerProvider, Span, Status, StatusCode
 from typing_extensions import Self
 
 
@@ -72,8 +72,8 @@ class Telemetry:
     and event-bus signal handlers (see ``crewai.telemetry.telemetry``).
     """
 
-    _instance = None
-    _lock = threading.Lock()
+    _instance: ClassVar[Self | None] = None
+    _lock: ClassVar[threading.Lock] = threading.Lock()
 
     def __new__(cls) -> Self:
         if cls._instance is None:
@@ -149,6 +149,10 @@ class Telemetry:
         if self.ready and not self.trace_set:
             try:
                 with suppress_warnings():
+                    existing_provider = trace.get_tracer_provider()
+                    if not isinstance(existing_provider, ProxyTracerProvider):
+                        self.trace_set = True
+                        return
                     trace.set_tracer_provider(self.provider)
                     self.trace_set = True
             except Exception as e:

lib/crewai-core/tests/test_smoke.py

@@ -13,6 +13,7 @@ from crewai_core import (
     user_data,
     version,
 )
+from opentelemetry.sdk.trace import TracerProvider
 import pytest
 
 
@@ -94,3 +95,36 @@ def test_user_data_decline_blocks(
 def test_unused_var_warning_silenced() -> None:
     # Touch os to keep the import (used by env-var fixtures above)
     assert os.environ is not None
+
+
+def test_core_telemetry_skips_duplicate_tracer_provider(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    from crewai_core.telemetry import Telemetry
+
+    Telemetry._instance = None
+    monkeypatch.delenv("OTEL_SDK_DISABLED", raising=False)
+    monkeypatch.delenv("CREWAI_DISABLE_TELEMETRY", raising=False)
+    monkeypatch.delenv("CREWAI_DISABLE_TRACKING", raising=False)
+
+    monkeypatch.setattr(
+        "crewai_core.telemetry.trace.get_tracer_provider",
+        lambda: TracerProvider(),
+    )
+
+    called = False
+
+    def fail_if_called(provider: object) -> None:
+        nonlocal called
+        called = True
+
+    monkeypatch.setattr(
+        "crewai_core.telemetry.trace.set_tracer_provider",
+        fail_if_called,
+    )
+
+    telemetry = Telemetry()
+    telemetry.set_tracer()
+
+    assert called is False
+    assert telemetry.trace_set is True

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

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

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

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

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

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

lib/crewai-tools/pyproject.toml

@@ -10,7 +10,7 @@ requires-python = ">=3.10, <3.14"
 dependencies = [
     "pytube~=15.0.0",
     "requests>=2.33.0,<3",
-    "crewai==1.14.7a1",
+    "crewai==1.14.7",
     "tiktoken>=0.8.0,<0.13",
     "beautifulsoup4~=4.13.4",
     "python-docx~=1.2.0",
@@ -63,7 +63,7 @@ spider-client = [
     "spider-client>=0.1.25",
 ]
 scrapegraph-py = [
-    "scrapegraph-py>=1.9.0",
+    "scrapegraph-py>=1.9.0,<2",
 ]
 linkup-sdk = [
     "linkup-sdk>=0.2.2",

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

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

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

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

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

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

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

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

lib/crewai-tools/tests/file_read_tool_test.py

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

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

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

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

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

lib/crewai/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==1.14.7",
+    "crewai-cli==1.14.7",
     # Core Dependencies
     "pydantic>=2.11.9,<2.13",
     "openai>=2.30.0,<3",
@@ -33,11 +33,12 @@ dependencies = [
     "appdirs~=1.4.4",
     "jsonref~=1.1.0",
     "json-repair~=0.25.2",
+    "cel-python>=0.5.0,<0.6",
     "tomli-w~=1.1.0",
     "tomli~=2.0.2",
     "json5~=0.10.0",
     "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 +55,7 @@ Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
 tools = [
-    "crewai-tools==1.14.7a1",
+    "crewai-tools==1.14.7",
 ]
 embeddings = [
     "tiktoken>=0.8.0,<0.13"
@@ -67,7 +68,11 @@ 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__ = "1.14.7"
 
 _LAZY_IMPORTS: dict[str, tuple[str, str]] = {
     "Memory": ("crewai.memory.unified_memory", "Memory"),

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

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

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

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

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

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

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

@@ -46,6 +46,7 @@ from crewai.state.checkpoint_config import CheckpointConfig, _coerce_checkpoint
 from crewai.tools.base_tool import BaseTool, Tool
 from crewai.types.callback import SerializableCallable
 from crewai.utilities.config import process_config
+from crewai.utilities.i18n import I18N, get_i18n
 from crewai.utilities.logger import Logger
 from crewai.utilities.rpm_controller import RPMController
 from crewai.utilities.string_utils import interpolate_only
@@ -81,16 +82,42 @@ _LLM_TYPE_REGISTRY: dict[str, str] = {
 def _validate_llm_ref(value: Any) -> Any:
     if isinstance(value, dict):
         import importlib
+        import inspect
 
         llm_type = value.get("llm_type")
-        if not llm_type or llm_type not in _LLM_TYPE_REGISTRY:
+        if not llm_type:
+            model = (
+                value.get("model")
+                or value.get("model_name")
+                or value.get("deployment_name")
+            )
+            if not model:
+                raise ValueError(
+                    "LLM config objects must include 'model', 'model_name', "
+                    "or 'deployment_name', or a serialized 'llm_type'. "
+                    f"Got keys: {list(value)}"
+                )
+            from crewai.llm import LLM
+
+            llm_kwargs = {**value, "model": model}
+            llm_kwargs.pop("model_name", None)
+            llm_kwargs.pop("deployment_name", None)
+            return LLM(**llm_kwargs)
+
+        if llm_type not in _LLM_TYPE_REGISTRY:
             raise ValueError(
-                f"Unknown or missing llm_type: {llm_type!r}. "
+                f"Unknown llm_type: {llm_type!r}. "
                 f"Expected one of {list(_LLM_TYPE_REGISTRY)}"
             )
         dotted = _LLM_TYPE_REGISTRY[llm_type]
         mod_path, cls_name = dotted.rsplit(".", 1)
         cls = getattr(importlib.import_module(mod_path), cls_name)
+        if inspect.isabstract(cls):
+            from crewai.llm import LLM
+
+            return LLM(
+                **{k: v for k, v in value.items() if v is not None and k != "llm_type"}
+            )
         return cls(**value)
     return value
 
@@ -186,6 +213,7 @@ class BaseAgent(BaseModel, ABC, metaclass=AgentMeta):
         tools (list[Any] | None): Tools at the agent's disposal.
         max_iter (int): Maximum iterations for an agent to execute a task.
         agent_executor: An instance of the CrewAgentExecutor class.
+        i18n (I18N): Internationalization settings.
         llm (Any): Language model that will run the agent.
         crew (Any): Crew to which the agent belongs.
 
@@ -265,6 +293,14 @@ class BaseAgent(BaseModel, ABC, metaclass=AgentMeta):
             _serialize_executor_ref, return_type=dict | None, when_used="json"
         ),
     ] = Field(default=None, description="An instance of the CrewAgentExecutor class.")
+    i18n: I18N = Field(
+        default_factory=get_i18n,
+        description="Internationalization settings.",
+        deprecated=(
+            "Agent.i18n is deprecated and will be removed in a future release. "
+            "Use crewai.utilities.i18n.get_i18n() or Crew(prompt_file=...) instead."
+        ),
+    )
 
     llm: Annotated[
         str | BaseLLM | None,
@@ -601,7 +637,10 @@ class BaseAgent(BaseModel, ABC, metaclass=AgentMeta):
         if self.memory is True:
             from crewai.memory.unified_memory import Memory
 
-            self.memory = Memory()
+            memory_kwargs: dict[str, Any] = {}
+            if self.llm is not None:
+                memory_kwargs["llm"] = self.llm
+            self.memory = Memory(**memory_kwargs)
         elif self.memory is False:
             self.memory = None
         return self

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

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

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

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

lib/crewai/src/crewai/context.py

@@ -117,8 +117,10 @@ def capture_execution_context(
     )
 
 
-def apply_execution_context(ctx: ExecutionContext) -> None:
+def apply_execution_context(ctx: ExecutionContext | dict[str, Any]) -> None:
     """Write an ExecutionContext back into the ContextVars."""
+    if isinstance(ctx, dict):
+        ctx = ExecutionContext.model_validate(ctx)
     _current_task_id.set(ctx.current_task_id)
     current_flow_request_id.set(ctx.flow_request_id)
     current_flow_id.set(ctx.flow_id)

lib/crewai/src/crewai/crew.py

@@ -658,7 +658,14 @@ class Crew(FlowTrackable, BaseModel):
                 from crewai.rag.embeddings.factory import build_embedder
 
                 embedder = build_embedder(cast(dict[str, Any], self.embedder))
-            self._memory = Memory(embedder=embedder, root_scope=crew_root_scope)
+            memory_kwargs: dict[str, Any] = {
+                "embedder": embedder,
+                "root_scope": crew_root_scope,
+            }
+            memory_llm = self._memory_llm()
+            if memory_llm is not None:
+                memory_kwargs["llm"] = memory_llm
+            self._memory = Memory(**memory_kwargs)
         elif self.memory:
             # User passed a Memory / MemoryScope / MemorySlice instance
             # Respect user's configuration — don't auto-set root_scope
@@ -668,6 +675,16 @@ class Crew(FlowTrackable, BaseModel):
 
         return self
 
+    def _memory_llm(self) -> str | BaseLLM | None:
+        """Return the LLM auto-created memory should use for analysis."""
+        if self.chat_llm is not None:
+            return self.chat_llm
+        for agent in self.agents:
+            agent_llm: str | BaseLLM | None = getattr(agent, "llm", None)
+            if agent_llm is not None:
+                return agent_llm
+        return None
+
     @model_validator(mode="after")
     def create_crew_knowledge(self) -> Crew:
         """Create the knowledge for the crew."""
@@ -1013,6 +1030,7 @@ class Crew(FlowTrackable, BaseModel):
         )
         token = attach(baggage_ctx)
 
+        runtime_scope = crewai_event_bus._enter_runtime_scope()
         try:
             inputs = prepare_kickoff(self, inputs, input_files)
 
@@ -1048,6 +1066,7 @@ class Crew(FlowTrackable, BaseModel):
                 self._memory.drain_writes()
             clear_files(self.id)
             detach(token)
+            crewai_event_bus._exit_runtime_scope(runtime_scope)
 
     def _post_kickoff(self, result: CrewOutput) -> CrewOutput:
         return result
@@ -1223,6 +1242,7 @@ class Crew(FlowTrackable, BaseModel):
         )
         token = attach(baggage_ctx)
 
+        runtime_scope = crewai_event_bus._enter_runtime_scope()
         try:
             inputs = prepare_kickoff(self, inputs, input_files)
 
@@ -1256,6 +1276,7 @@ class Crew(FlowTrackable, BaseModel):
         finally:
             clear_files(self.id)
             detach(token)
+            crewai_event_bus._exit_runtime_scope(runtime_scope)
 
     async def akickoff_for_each(
         self,

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,
@@ -114,6 +116,11 @@ if TYPE_CHECKING:
         MemorySaveFailedEvent,
         MemorySaveStartedEvent,
     )
+    from crewai.events.types.observation_events import (
+        PlanStepCompletedEvent,
+        PlanStepEvent,
+        PlanStepStartedEvent,
+    )
     from crewai.events.types.reasoning_events import (
         AgentReasoningCompletedEvent,
         AgentReasoningFailedEvent,
@@ -176,6 +183,8 @@ _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",
@@ -216,6 +225,9 @@ _LAZY_EVENT_MAPPING: dict[str, str] = {
     "MemorySaveCompletedEvent": "crewai.events.types.memory_events",
     "MemorySaveFailedEvent": "crewai.events.types.memory_events",
     "MemorySaveStartedEvent": "crewai.events.types.memory_events",
+    "PlanStepCompletedEvent": "crewai.events.types.observation_events",
+    "PlanStepEvent": "crewai.events.types.observation_events",
+    "PlanStepStartedEvent": "crewai.events.types.observation_events",
     "AgentReasoningCompletedEvent": "crewai.events.types.reasoning_events",
     "AgentReasoningFailedEvent": "crewai.events.types.reasoning_events",
     "AgentReasoningStartedEvent": "crewai.events.types.reasoning_events",
@@ -291,6 +303,8 @@ __all__ = [
     "CheckpointRestoreStartedEvent",
     "CheckpointStartedEvent",
     "CircularDependencyError",
+    "ConversationMessageAddedEvent",
+    "ConversationRouteSelectedEvent",
     "CrewKickoffCompletedEvent",
     "CrewKickoffFailedEvent",
     "CrewKickoffStartedEvent",
@@ -343,6 +357,9 @@ __all__ = [
     "MethodExecutionFailedEvent",
     "MethodExecutionFinishedEvent",
     "MethodExecutionStartedEvent",
+    "PlanStepCompletedEvent",
+    "PlanStepEvent",
+    "PlanStepStartedEvent",
     "ReasoningEvent",
     "SkillActivatedEvent",
     "SkillDiscoveryCompletedEvent",

lib/crewai/src/crewai/events/event_bus.py

@@ -80,6 +80,17 @@ def is_replaying() -> bool:
     return _replaying.get()
 
 
+_runtime_state_var: contextvars.ContextVar[RuntimeState | None] = (
+    contextvars.ContextVar("crewai_runtime_state", default=None)
+)
+_registered_entity_ids_var: contextvars.ContextVar[set[int] | None] = (
+    contextvars.ContextVar("crewai_registered_entity_ids", default=None)
+)
+_runtime_scope_depth: contextvars.ContextVar[int] = contextvars.ContextVar(
+    "crewai_runtime_scope_depth", default=0
+)
+
+
 class CrewAIEventsBus:
     """Singleton event bus for handling events in CrewAI.
 
@@ -116,7 +127,6 @@ class CrewAIEventsBus:
     _futures_lock: threading.Lock
     _executor_initialized: bool
     _has_pending_events: bool
-    _runtime_state: RuntimeState | None
 
     def __new__(cls) -> Self:
         """Create or return the singleton instance.
@@ -151,8 +161,6 @@ class CrewAIEventsBus:
         self._console = ConsoleFormatter()
         self._executor_initialized = False
         self._has_pending_events = False
-        self._runtime_state: RuntimeState | None = None
-        self._registered_entity_ids: set[int] = set()
 
     def _ensure_executor_initialized(self) -> None:
         """Lazily initialize the thread pool executor and event loop.
@@ -281,6 +289,51 @@ class CrewAIEventsBus:
         """The RuntimeState currently attached to the bus, if any."""
         return self._runtime_state
 
+    @property
+    def _runtime_state(self) -> RuntimeState | None:
+        return _runtime_state_var.get()
+
+    @_runtime_state.setter
+    def _runtime_state(self, value: RuntimeState | None) -> None:
+        _runtime_state_var.set(value)
+
+    @property
+    def _registered_entity_ids(self) -> set[int]:
+        ids = _registered_entity_ids_var.get()
+        if ids is None:
+            ids = set()
+            _registered_entity_ids_var.set(ids)
+        return ids
+
+    @_registered_entity_ids.setter
+    def _registered_entity_ids(self, value: set[int]) -> None:
+        _registered_entity_ids_var.set(value)
+
+    def reset_runtime_state(self) -> None:
+        """Detach the RuntimeState and clear the entity registry."""
+        self._runtime_state = None
+        self._registered_entity_ids = set()
+
+    def _enter_runtime_scope(self) -> bool:
+        depth = _runtime_scope_depth.get()
+        _runtime_scope_depth.set(depth + 1)
+        if depth != 0:
+            return False
+        if _runtime_state_var.get() is None:
+            from crewai import RuntimeState
+
+            if RuntimeState is not None:
+                _runtime_state_var.set(RuntimeState(root=[]))
+            _registered_entity_ids_var.set(set())
+        return True
+
+    def _exit_runtime_scope(self, outermost: bool) -> None:
+        depth = _runtime_scope_depth.get()
+        _runtime_scope_depth.set(depth - 1 if depth > 0 else 0)
+        if outermost:
+            _runtime_state_var.set(None)
+            _registered_entity_ids_var.set(None)
+
     def register_entity(self, entity: Any) -> None:
         """Add an entity to the RuntimeState, creating it if needed.
 
@@ -349,6 +402,7 @@ class CrewAIEventsBus:
         source: Any,
         event: BaseEvent,
         handlers: SyncHandlerSet,
+        state: RuntimeState | None,
     ) -> None:
         """Call provided synchronous handlers.
 
@@ -356,8 +410,8 @@ class CrewAIEventsBus:
             source: The emitting object
             event: The event instance
             handlers: Frozenset of sync handlers to call
+            state: The RuntimeState captured on the emitting context
         """
-        state = self._runtime_state
         errors: list[tuple[SyncHandler, Exception]] = [
             (handler, error)
             for handler in handlers
@@ -376,6 +430,7 @@ class CrewAIEventsBus:
         source: Any,
         event: BaseEvent,
         handlers: AsyncHandlerSet,
+        state: RuntimeState | None,
     ) -> None:
         """Asynchronously call provided async handlers.
 
@@ -383,8 +438,8 @@ class CrewAIEventsBus:
             source: The object that emitted the event
             event: The event instance
             handlers: Frozenset of async handlers to call
+            state: The RuntimeState captured on the emitting context
         """
-        state = self._runtime_state
 
         async def _call(handler: AsyncHandler) -> Any:
             if _get_param_count(handler) >= 3:
@@ -399,7 +454,9 @@ class CrewAIEventsBus:
                     f"[CrewAIEventsBus] Async handler error in {getattr(handler, '__name__', handler)}: {result}"
                 )
 
-    async def _emit_with_dependencies(self, source: Any, event: BaseEvent) -> None:
+    async def _emit_with_dependencies(
+        self, source: Any, event: BaseEvent, state: RuntimeState | None
+    ) -> None:
         """Emit an event with dependency-aware handler execution.
 
         Handlers are grouped into execution levels based on their dependencies.
@@ -450,18 +507,18 @@ class CrewAIEventsBus:
 
             if level_sync:
                 if event_type is LLMStreamChunkEvent:
-                    self._call_handlers(source, event, level_sync)
+                    self._call_handlers(source, event, level_sync, state)
                 else:
                     ctx = contextvars.copy_context()
                     future = self._sync_executor.submit(
-                        ctx.run, self._call_handlers, source, event, level_sync
+                        ctx.run, self._call_handlers, source, event, level_sync, state
                     )
                     await asyncio.get_running_loop().run_in_executor(
                         None, future.result
                     )
 
             if level_async:
-                await self._acall_handlers(source, event, level_async)
+                await self._acall_handlers(source, event, level_async, state)
 
     def _register_source(self, source: Any) -> None:
         """Register the source entity in RuntimeState if applicable."""
@@ -556,21 +613,23 @@ class CrewAIEventsBus:
         self._ensure_executor_initialized()
         self._has_pending_events = True
 
+        state = self._runtime_state
+
         if has_dependencies:
             return self._track_future(
                 asyncio.run_coroutine_threadsafe(
-                    self._emit_with_dependencies(source, event),
+                    self._emit_with_dependencies(source, event, state),
                     self._loop,
                 )
             )
 
         if sync_handlers:
             if event_type is LLMStreamChunkEvent:
-                self._call_handlers(source, event, sync_handlers)
+                self._call_handlers(source, event, sync_handlers, state)
             else:
                 ctx = contextvars.copy_context()
                 sync_future = self._sync_executor.submit(
-                    ctx.run, self._call_handlers, source, event, sync_handlers
+                    ctx.run, self._call_handlers, source, event, sync_handlers, state
                 )
                 if not async_handlers:
                     return self._track_future(sync_future)
@@ -578,7 +637,7 @@ class CrewAIEventsBus:
         if async_handlers:
             return self._track_future(
                 asyncio.run_coroutine_threadsafe(
-                    self._acall_handlers(source, event, async_handlers),
+                    self._acall_handlers(source, event, async_handlers, state),
                     self._loop,
                 )
             )
@@ -590,21 +649,22 @@ class CrewAIEventsBus:
         source: Any,
         event: BaseEvent,
         handlers: AsyncHandlerSet,
+        state: RuntimeState | None,
     ) -> None:
         """Call async handlers with the replaying flag set on the loop thread."""
         token = _replaying.set(True)
         try:
-            await self._acall_handlers(source, event, handlers)
+            await self._acall_handlers(source, event, handlers, state)
         finally:
             _replaying.reset(token)
 
     async def _emit_with_dependencies_replaying(
-        self, source: Any, event: BaseEvent
+        self, source: Any, event: BaseEvent, state: RuntimeState | None
     ) -> None:
         """Dependency-aware dispatch with the replaying flag set."""
         token = _replaying.set(True)
         try:
-            await self._emit_with_dependencies(source, event)
+            await self._emit_with_dependencies(source, event, state)
         finally:
             _replaying.reset(token)
 
@@ -638,12 +698,13 @@ class CrewAIEventsBus:
         self._ensure_executor_initialized()
         self._has_pending_events = True
 
+        state = self._runtime_state
         token = _replaying.set(True)
         try:
             if has_dependencies:
                 return self._track_future(
                     asyncio.run_coroutine_threadsafe(
-                        self._emit_with_dependencies_replaying(source, event),
+                        self._emit_with_dependencies_replaying(source, event, state),
                         self._loop,
                     )
                 )
@@ -651,7 +712,7 @@ class CrewAIEventsBus:
             if sync_handlers:
                 ctx = contextvars.copy_context()
                 sync_future = self._sync_executor.submit(
-                    ctx.run, self._call_handlers, source, event, sync_handlers
+                    ctx.run, self._call_handlers, source, event, sync_handlers, state
                 )
                 self._track_future(sync_future)
                 if not async_handlers:
@@ -659,7 +720,9 @@ class CrewAIEventsBus:
 
             return self._track_future(
                 asyncio.run_coroutine_threadsafe(
-                    self._acall_handlers_replaying(source, event, async_handlers),
+                    self._acall_handlers_replaying(
+                        source, event, async_handlers, state
+                    ),
                     self._loop,
                 )
             )
@@ -727,7 +790,9 @@ class CrewAIEventsBus:
             async_handlers = self._async_handlers.get(event_type, frozenset())
 
         if async_handlers:
-            await self._acall_handlers(source, event, async_handlers)
+            await self._acall_handlers(
+                source, event, async_handlers, self._runtime_state
+            )
 
     def register_handler(
         self,

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

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

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

@@ -53,6 +53,8 @@ from crewai.events.types.crew_events import (
     CrewTrainStartedEvent,
 )
 from crewai.events.types.flow_events import (
+    ConversationMessageAddedEvent,
+    ConversationRouteSelectedEvent,
     FlowFinishedEvent,
     FlowStartedEvent,
     MethodExecutionFailedEvent,
@@ -97,6 +99,10 @@ from crewai.events.types.memory_events import (
     MemorySaveFailedEvent,
     MemorySaveStartedEvent,
 )
+from crewai.events.types.observation_events import (
+    PlanStepCompletedEvent,
+    PlanStepStartedEvent,
+)
 from crewai.events.types.reasoning_events import (
     AgentReasoningCompletedEvent,
     AgentReasoningFailedEvent,
@@ -154,6 +160,8 @@ EventTypes = (
     | TaskStartedEvent
     | TaskCompletedEvent
     | TaskFailedEvent
+    | ConversationMessageAddedEvent
+    | ConversationRouteSelectedEvent
     | FlowStartedEvent
     | FlowFinishedEvent
     | MethodExecutionStartedEvent
@@ -187,6 +195,8 @@ EventTypes = (
     | MemoryRetrievalStartedEvent
     | MemoryRetrievalCompletedEvent
     | MemoryRetrievalFailedEvent
+    | PlanStepStartedEvent
+    | PlanStepCompletedEvent
     | MCPConnectionStartedEvent
     | MCPConnectionCompletedEvent
     | MCPConnectionFailedEvent

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

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

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

@@ -18,6 +18,7 @@ from crewai.events.listeners.tracing.trace_batch_manager import TraceBatchManage
 from crewai.events.listeners.tracing.types import TraceEvent
 from crewai.events.listeners.tracing.utils import (
     is_tracing_enabled_in_context,
+    is_tui_mode,
     safe_serialize_to_dict,
     should_auto_collect_first_time_traces,
     should_enable_tracing,
@@ -62,6 +63,8 @@ from crewai.events.types.crew_events import (
     CrewKickoffStartedEvent,
 )
 from crewai.events.types.flow_events import (
+    ConversationMessageAddedEvent,
+    ConversationRouteSelectedEvent,
     FlowCreatedEvent,
     FlowFinishedEvent,
     FlowPlotEvent,
@@ -210,8 +213,8 @@ class TraceCollectionListener(BaseEventListener):
             not should_enable_tracing()
             and not is_tracing_enabled_in_context()
             and not should_auto_collect_first_time_traces()
+            and not is_tui_mode()
         ):
-            self._listeners_setup = True
             return
 
         self._register_flow_event_handlers(crewai_event_bus)
@@ -255,6 +258,18 @@ 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)
@@ -278,11 +293,17 @@ class TraceCollectionListener(BaseEventListener):
         @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:
+            if self._should_defer_session_finalization():
                 return
             if self._nested_in_flow_execution():
                 return
             if self.batch_manager.batch_owner_type == "crew":
+                if is_tui_mode():
+                    if self.first_time_handler.is_first_time:
+                        self.first_time_handler.mark_events_collected()
+                    elif is_tracing_enabled_in_context() or should_enable_tracing():
+                        self.batch_manager.finalize_batch()
+                    return
                 if self.first_time_handler.is_first_time:
                     self.first_time_handler.mark_events_collected()
                     self.first_time_handler.handle_execution_completion()
@@ -292,10 +313,16 @@ 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:
+            if self._should_defer_session_finalization():
                 return
             if self._nested_in_flow_execution():
                 return
+            if is_tui_mode():
+                if self.first_time_handler.is_first_time:
+                    self.first_time_handler.mark_events_collected()
+                elif is_tracing_enabled_in_context() or should_enable_tracing():
+                    self.batch_manager.finalize_batch()
+                return
             if self.first_time_handler.is_first_time:
                 self.first_time_handler.mark_events_collected()
                 self.first_time_handler.handle_execution_completion()
@@ -720,7 +747,7 @@ class TraceCollectionListener(BaseEventListener):
             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:
+            if self._should_defer_session_finalization():
                 return
             self.batch_manager.finalize_batch()
 
@@ -731,6 +758,15 @@ class TraceCollectionListener(BaseEventListener):
 
         return current_flow_id.get() is not None
 
+    def _should_defer_session_finalization(self) -> bool:
+        """True when the active trace belongs to a deferred flow session."""
+        from crewai.flow.flow_context import current_flow_defer_trace_finalization
+
+        return (
+            self.batch_manager.defer_session_finalization
+            or current_flow_defer_trace_finalization.get()
+        )
+
     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":
@@ -766,12 +802,17 @@ class TraceCollectionListener(BaseEventListener):
     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.
+        When ``suppress_flow_events=True`` (infrastructure flows such as
+        ``AgentExecutor`` and the memory flows), flow and method lifecycle
+        events are not emitted, so the batch is claimed from the flow context
+        (``current_flow_id``) to keep LLM/tool events from falling back to an
+        implicit crew batch.
         """
-        from crewai.flow.flow_context import current_flow_id, current_flow_name
+        from crewai.flow.flow_context import (
+            current_flow_defer_trace_finalization,
+            current_flow_id,
+            current_flow_name,
+        )
 
         flow_id = current_flow_id.get()
         if flow_id is None:
@@ -787,6 +828,8 @@ class TraceCollectionListener(BaseEventListener):
         }
         self.batch_manager.batch_owner_type = "flow"
         self.batch_manager.batch_owner_id = flow_id
+        if current_flow_defer_trace_finalization.get():
+            self.batch_manager.defer_session_finalization = True
         self._initialize_batch(user_context, execution_metadata)
         return True
 

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

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

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

@@ -1,6 +1,6 @@
 from typing import Any, Literal
 
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel, ConfigDict, field_serializer
 
 from crewai.events.base_events import BaseEvent
 
@@ -57,6 +57,10 @@ class MethodExecutionFailedEvent(FlowEvent):
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
+    @field_serializer("error")
+    def _serialize_error(self, error: Exception) -> str:
+        return str(error)
+
 
 class MethodExecutionPausedEvent(FlowEvent):
     """Event emitted when a flow method is paused waiting for human feedback.
@@ -166,6 +170,31 @@ 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/events/types/observation_events.py

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

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

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

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

@@ -46,6 +46,8 @@ from crewai.events.types.observation_events import (
     GoalAchievedEarlyEvent,
     PlanRefinementEvent,
     PlanReplanTriggeredEvent,
+    PlanStepCompletedEvent,
+    PlanStepStartedEvent,
 )
 from crewai.events.types.tool_usage_events import (
     ToolUsageErrorEvent,
@@ -73,6 +75,7 @@ from crewai.tools.base_tool import BaseTool
 from crewai.tools.structured_tool import CrewStructuredTool
 from crewai.utilities.agent_utils import (
     _llm_stop_words_applied,
+    build_text_tool_calling_fallback_message,
     check_native_tool_support,
     enforce_rpm_limit,
     extract_tool_call_info,
@@ -86,6 +89,7 @@ from crewai.utilities.agent_utils import (
     has_reached_max_iterations,
     is_context_length_exceeded,
     is_inside_event_loop,
+    is_native_tool_calling_unsupported_error,
     is_tool_call_list,
     parse_tool_call_args,
     process_llm_response,
@@ -241,6 +245,23 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
                 self._tool_name_mapping,
             ) = setup_native_tools(self.original_tools)
 
+    def _downgrade_to_text_tool_calling(self) -> None:
+        """Switch a running execution from native tools to text tool calls."""
+        self.state.use_native_tools = False
+        self.state.pending_tool_calls.clear()
+        self._openai_tools = []
+        self._available_functions = {}
+        if self.tools:
+            self.state.messages.append(
+                format_message_for_llm(
+                    build_text_tool_calling_fallback_message(
+                        self.tools_description,
+                        self.tools_names,
+                    ),
+                    role="user",
+                )
+            )
+
     def _is_tool_call_list(self, response: list[Any]) -> bool:
         """Check if a response is a list of tool calls."""
         return is_tool_call_list(response)
@@ -279,6 +300,16 @@ 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.
@@ -339,6 +370,84 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
 
         self.state.todos = TodoList(items=todos)
 
+    def _emit_plan_step_started(self, todo: TodoItem) -> None:
+        try:
+            crewai_event_bus.emit(
+                self.agent,
+                event=PlanStepStartedEvent(
+                    agent_role=self.agent.role,
+                    step_number=todo.step_number,
+                    step_description=todo.description,
+                    tool_to_use=todo.tool_to_use,
+                    from_task=self.task,
+                    from_agent=self.agent,
+                ),
+            )
+        except Exception:  # noqa: S110
+            pass
+
+    def _emit_plan_step_completed(
+        self,
+        todo: TodoItem,
+        *,
+        success: bool,
+        result: str | None = None,
+        error: str | None = None,
+    ) -> None:
+        try:
+            crewai_event_bus.emit(
+                self.agent,
+                event=PlanStepCompletedEvent(
+                    agent_role=self.agent.role,
+                    step_number=todo.step_number,
+                    step_description=todo.description,
+                    tool_to_use=todo.tool_to_use,
+                    success=success,
+                    result=result,
+                    error=error,
+                    from_task=self.task,
+                    from_agent=self.agent,
+                ),
+            )
+        except Exception:  # noqa: S110
+            pass
+
+    def _mark_todo_running(self, todo: TodoItem) -> None:
+        previous_status = todo.status
+        self.state.todos.mark_running(todo.step_number)
+        if previous_status != "running":
+            self._emit_plan_step_started(todo)
+
+    def _mark_todo_completed(
+        self,
+        step_number: int,
+        result: str | None = None,
+    ) -> None:
+        todo = self.state.todos.get_by_step_number(step_number)
+        previous_status = todo.status if todo else None
+        self.state.todos.mark_completed(step_number, result=result)
+        todo = self.state.todos.get_by_step_number(step_number)
+        if todo and previous_status != "completed":
+            self._emit_plan_step_completed(todo, success=True, result=result)
+
+    def _mark_todo_failed(
+        self,
+        step_number: int,
+        result: str | None = None,
+        error: str | None = None,
+    ) -> None:
+        todo = self.state.todos.get_by_step_number(step_number)
+        previous_status = todo.status if todo else None
+        self.state.todos.mark_failed(step_number, result=result)
+        todo = self.state.todos.get_by_step_number(step_number)
+        if todo and previous_status != "failed":
+            self._emit_plan_step_completed(
+                todo,
+                success=False,
+                result=result,
+                error=error,
+            )
+
     def _ensure_step_executor(self) -> Any:
         """Lazily create the StepExecutor (avoids circular imports)."""
         if self._step_executor is None:
@@ -587,8 +696,10 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
             and not observation.step_completed_successfully
             and observation.needs_full_replan
         ):
-            self.state.todos.mark_failed(
-                current_todo.step_number, result=current_todo.result
+            self._mark_todo_failed(
+                current_todo.step_number,
+                result=current_todo.result,
+                error=observation.replan_reason,
             )
             if self.agent.verbose:
                 PRINTER.print(
@@ -604,8 +715,9 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
             return "replan_now"
 
         if observation and not observation.step_completed_successfully:
-            self.state.todos.mark_failed(
-                current_todo.step_number, result=current_todo.result
+            self._mark_todo_failed(
+                current_todo.step_number,
+                result=current_todo.result,
             )
             if self.agent.verbose:
                 failed = len(self.state.todos.get_failed_todos())
@@ -619,9 +731,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
                 )
             return "continue_plan"
 
-        self.state.todos.mark_completed(
-            current_todo.step_number, result=current_todo.result
-        )
+        self._mark_todo_completed(current_todo.step_number, result=current_todo.result)
 
         if self.agent.verbose:
             completed = self.state.todos.completed_count
@@ -651,7 +761,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
 
         # If observation is missing or step succeeded — continue
         if not observation or observation.step_completed_successfully:
-            self.state.todos.mark_completed(
+            self._mark_todo_completed(
                 current_todo.step_number, result=current_todo.result
             )
             if self.agent.verbose:
@@ -666,8 +776,10 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
         # Step failed — only replan if observer explicitly requires it,
         # otherwise mark done and continue (same gate as low-effort).
         if observation.needs_full_replan:
-            self.state.todos.mark_failed(
-                current_todo.step_number, result=current_todo.result
+            self._mark_todo_failed(
+                current_todo.step_number,
+                result=current_todo.result,
+                error=observation.replan_reason,
             )
             if self.agent.verbose:
                 PRINTER.print(
@@ -684,9 +796,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
 
         # Step failed but observer does not require a full replan — mark as
         # failed (not completed) so get_failed_todos() tracks it correctly.
-        self.state.todos.mark_failed(
-            current_todo.step_number, result=current_todo.result
-        )
+        self._mark_todo_failed(current_todo.step_number, result=current_todo.result)
         if self.agent.verbose:
             failed = len(self.state.todos.get_failed_todos())
             total = len(self.state.todos.items)
@@ -721,12 +831,12 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
         observation = self.state.observations.get(current_todo.step_number)
         if not observation:
             # No observation available — default to continue
-            self.state.todos.mark_completed(current_todo.step_number)
+            self._mark_todo_completed(current_todo.step_number)
             return "continue_plan"
 
         # Goal already achieved — early termination
         if observation.goal_already_achieved:
-            self.state.todos.mark_completed(
+            self._mark_todo_completed(
                 current_todo.step_number, result=current_todo.result
             )
             if self.agent.verbose:
@@ -738,8 +848,10 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
 
         # Full replan needed
         if observation.needs_full_replan:
-            self.state.todos.mark_failed(
-                current_todo.step_number, result=current_todo.result
+            self._mark_todo_failed(
+                current_todo.step_number,
+                result=current_todo.result,
+                error=observation.replan_reason,
             )
             if self.agent.verbose:
                 PRINTER.print(
@@ -751,9 +863,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
 
         # Step failed — also trigger replan
         if not observation.step_completed_successfully:
-            self.state.todos.mark_failed(
-                current_todo.step_number, result=current_todo.result
-            )
+            self._mark_todo_failed(current_todo.step_number, result=current_todo.result)
             if self.agent.verbose:
                 PRINTER.print(
                     content="[Decide] Step failed — triggering replan",
@@ -763,7 +873,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
             return "replan_now"
 
         if observation.remaining_plan_still_valid and observation.suggested_refinements:
-            self.state.todos.mark_completed(
+            self._mark_todo_completed(
                 current_todo.step_number, result=current_todo.result
             )
             if self.agent.verbose:
@@ -773,9 +883,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
                 )
             return "refine_and_continue"
 
-        self.state.todos.mark_completed(
-            current_todo.step_number, result=current_todo.result
-        )
+        self._mark_todo_completed(current_todo.step_number, result=current_todo.result)
         if self.agent.verbose:
             completed = self.state.todos.completed_count
             total = len(self.state.todos.items)
@@ -951,7 +1059,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
             return "needs_replan"
 
         if len(ready) == 1:
-            self.state.todos.mark_running(ready[0].step_number)
+            self._mark_todo_running(ready[0])
             return "single_todo_ready"
 
         return "multiple_todos_ready"
@@ -1089,7 +1197,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
 
         # Mark all ready todos as running
         for todo in ready:
-            self.state.todos.mark_running(todo.step_number)
+            self._mark_todo_running(todo)
 
         # Build context and executor for each todo, then run in parallel
         async def _run_step(todo: TodoItem) -> tuple[TodoItem, object]:
@@ -1117,7 +1225,11 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
             if isinstance(item, BaseException):
                 error_msg = f"Error: {item!s}"
                 todo.result = error_msg
-                self.state.todos.mark_failed(todo.step_number, result=error_msg)
+                self._mark_todo_failed(
+                    todo.step_number,
+                    result=error_msg,
+                    error=error_msg,
+                )
                 if self.agent.verbose:
                     PRINTER.print(
                         content=f"Todo {todo.step_number} failed: {error_msg}",
@@ -1187,9 +1299,9 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
 
             # Mark based on observation result
             if observation.step_completed_successfully:
-                self.state.todos.mark_completed(todo.step_number, result=todo.result)
+                self._mark_todo_completed(todo.step_number, result=todo.result)
             else:
-                self.state.todos.mark_failed(todo.step_number, result=todo.result)
+                self._mark_todo_failed(todo.step_number, result=todo.result)
 
             if self.agent.verbose:
                 PRINTER.print(
@@ -1339,7 +1451,11 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
     def call_llm_native_tools(
         self,
     ) -> Literal[
-        "native_tool_calls", "native_finished", "context_error", "todo_satisfied"
+        "native_tool_calls",
+        "native_finished",
+        "context_error",
+        "todo_satisfied",
+        "continue_reasoning",
     ]:
         """Execute LLM call with native function calling.
 
@@ -1418,6 +1534,9 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
             return self._route_finish_with_todos("native_finished")
 
         except Exception as e:
+            if is_native_tool_calling_unsupported_error(e):
+                self._downgrade_to_text_tool_calling()
+                return "continue_reasoning"
             if is_context_length_exceeded(e):
                 self._last_context_error = e
                 return "context_error"
@@ -2075,7 +2194,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
             step_number: The step number to mark.
             result: The result of the todo.
         """
-        self.state.todos.mark_completed(step_number, result=result)
+        self._mark_todo_completed(step_number, result=result)
 
         if self.agent.verbose:
             completed = self.state.todos.completed_count

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

@@ -1,29 +1,36 @@
-"""Conversational graph + helpers as a mixin for ``Flow`` (experimental).
+"""Conversational graph + helpers as an experimental Flow extension.
 
-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``).
+The conversational chat surface remains experimental and may change before the
+v2 graduation path. It lives here so ``crewai.flow.runtime`` can stay focused
+on the execution engine. ``crewai.flow.flow`` composes this mixin onto the
+public ``Flow`` class for backwards compatibility.
+
+The built-in conversational graph only registers for subclasses that opt in
+with ``conversational = True``. Static conversational metadata is projected
+into ``FlowDefinition.conversational`` via the Python DSL builder.
 
 Import surface:
-    - :class:`_ConversationalMixin` — internal; ``Flow`` mixes it in. Users
-      don't import it directly.
+    - :class:`_ConversationalMixin` — internal; the public ``Flow`` class
+      composes 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 Mapping, Sequence
+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 typing import TYPE_CHECKING, Any, ClassVar, Literal, TypeVar, 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,
@@ -39,26 +46,69 @@ from crewai.flow.conversation import (
     get_conversation_messages,
     receive_user_message as _receive_user_message,
 )
-from crewai.flow.dsl import listen, router, start
+from crewai.flow.dsl import listen, start
+from crewai.flow.dsl._utils import _method_action, _set_flow_method_definition
+from crewai.flow.flow_definition import FlowMethodDefinition
 from crewai.utilities.types import LLMMessage
 
 
 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``).
+def _iter_condition_labels(condition: Any) -> set[str]:
+    if isinstance(condition, str):
+        return {condition}
+    if isinstance(condition, dict):
+        labels: set[str] = set()
+        for value in condition.values():
+            if isinstance(value, list):
+                for item in value:
+                    labels.update(_iter_condition_labels(item))
+            else:
+                labels.update(_iter_condition_labels(value))
+        return labels
+    return set()
 
-    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.
+
+def _conversation_start_router(func: Callable[..., Any]) -> Any:
+    wrapper = start()(func)
+    _set_flow_method_definition(
+        cast(Any, wrapper),
+        FlowMethodDefinition(do=_method_action(func), start=True, router=True),
+    )
+    return wrapper
+
+
+class _ConversationalMixin:
+    """Experimental conversational graph for ``Flow``.
+
+    This mixin owns chat behavior and runtime hooks. Non-chat flows see these
+    methods as inert attributes unless they opt in with ``conversational = True``.
     """
 
+    # === EXPERIMENTAL: conversational mode ===
+    # When ``conversational = True`` on a Flow subclass, this mixin's built-in
+    # graph registers and ``handle_turn`` / ``chat`` become chat entry points.
+    conversational: ClassVar[bool] = False
+    conversational_config: ClassVar[ConversationConfig | None] = None
+    builtin_routes: ClassVar[tuple[str, ...]] = ("converse", "end")
+    internal_routes: ClassVar[tuple[str, ...]] = ("answer_from_history",)
+    builtin_route_descriptions: ClassVar[dict[str, str]] = {
+        "converse": (
+            "Ordinary chat, follow-ups, summaries, clarifications, and "
+            "questions answerable from prior conversation history."
+        ),
+        "end": ("User signals the conversation is finished (goodbye, exit, done)."),
+        "answer_from_history": (
+            "Answer directly from prior conversation history without invoking "
+            "tools, agents, or custom routes."
+        ),
+    }
+
     # 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.
@@ -66,22 +116,15 @@ class _ConversationalMixin:
     # (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]
+        _pending_events: dict[Any, Any]
         _method_call_counts: dict[Any, int]
         _is_execution_resuming: bool
+        _conversation_messages: list[LLMMessage]
         _pending_user_message: str | dict[str, Any] | None
         _pending_intents: Sequence[str] | None
         _pending_intent_llm: str | BaseLLM | None
@@ -92,8 +135,8 @@ class _ConversationalMixin:
         def _collapse_to_outcome(
             self,
             feedback: str,
-            outcomes: tuple[str, ...],
-            llm: str | BaseLLM | Any,
+            outcomes: Sequence[str],
+            llm: str | BaseLLM,
         ) -> str:
             pass
 
@@ -103,38 +146,60 @@ class _ConversationalMixin:
         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.
+        @property
+        def method_outputs(self) -> list[Any]:
+            pass
 
-        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``.
+    def conversation_start(self) -> str | None:
+        """Return the current user message for conversational route selection.
+
+        This remains as a plain overridable helper for compatibility. It is not
+        registered as a Flow method; ``route_conversation`` is the synthetic
+        built-in start/router that begins a conversational turn.
         """
         state = cast(ConversationState, self.state)
         return state.current_user_message
 
-    @router(conversation_start)
+    @_conversation_start_router
     @_conversational_only
     def route_conversation(self) -> str:
         """Route the current turn to a listener label."""
+        if "conversation_start" not in {
+            str(method_name) for method_name in self._completed_methods
+        }:
+            self.conversation_start()
         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")
@@ -216,8 +281,8 @@ class _ConversationalMixin:
         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.
+        # Stash the pending turn so the kickoff extension hook 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
@@ -243,6 +308,59 @@ class _ConversationalMixin:
             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 self._is_conversational_enabled():
+            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)
@@ -353,13 +471,61 @@ class _ConversationalMixin:
         metadata: dict[str, Any] | None = None,
     ) -> None:
         """Append a final user-visible assistant message."""
-        cast(ConversationState, self.state).messages.append(
+        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,
@@ -368,14 +534,14 @@ class _ConversationalMixin:
         **extra: Any,
     ) -> None:
         """Append a message to conversation history (legacy ChatState path)."""
-        _append_conversation_message(cast("Flow[Any]", self), role, content, **extra)
+        _append_conversation_message(cast(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))
+            for message in get_conversation_messages(cast(Any, self))
         ]
 
     def receive_user_message(
@@ -391,9 +557,14 @@ class _ConversationalMixin:
         ``state.messages`` and preserve ``last_intent`` across turns.
         Non-conversational flows fall through to the legacy helper.
         """
-        if self.conversational:
+        if self._is_conversational_enabled():
             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:
@@ -407,9 +578,7 @@ class _ConversationalMixin:
                 return intent
             return text
 
-        return _receive_user_message(
-            cast("Flow[Any]", self), text, outcomes=outcomes, llm=llm
-        )
+        return _receive_user_message(cast(Any, self), text, outcomes=outcomes, llm=llm)
 
     def classify_intent(
         self,
@@ -433,27 +602,104 @@ class _ConversationalMixin:
     def _conversation_config(self) -> ConversationConfig | None:
         return getattr(type(self), "conversational_config", None)
 
+    @property
+    def _conversation_definition(self) -> Any | None:
+        return self._conversation_flow_definition().conversational
+
+    def _conversation_flow_definition(self) -> Any:
+        flow_definition = getattr(type(self), "flow_definition", None)
+        if not callable(flow_definition):
+            raise AttributeError(
+                f"{type(self).__name__} does not expose flow_definition()"
+            )
+        return flow_definition()
+
+    @classmethod
+    def _conversational_definition(cls) -> Any | None:
+        flow_definition = getattr(cls, "flow_definition", None)
+        if not callable(flow_definition):
+            return None
+        return flow_definition().conversational
+
+    @classmethod
+    def _is_conversational(cls) -> bool:
+        definition = cls._conversational_definition()
+        return bool(definition and definition.enabled)
+
+    def _is_conversational_enabled(self) -> bool:
+        definition = self._conversation_definition
+        return bool(definition and definition.enabled)
+
+    def _initialize_runtime_extension_attrs(self) -> None:
+        if not isinstance(getattr(self, "_conversation_messages", None), list):
+            object.__setattr__(self, "_conversation_messages", [])
+        if not hasattr(self, "_pending_user_message"):
+            object.__setattr__(self, "_pending_user_message", None)
+        if not hasattr(self, "_pending_intents"):
+            object.__setattr__(self, "_pending_intents", None)
+        if not hasattr(self, "_pending_intent_llm"):
+            object.__setattr__(self, "_pending_intent_llm", None)
+
+    def _create_default_extension_state(self) -> ConversationState | None:
+        initial_state_t = getattr(self, "_initial_state_t", None)
+        if type(self)._is_conversational() and (
+            not hasattr(self, "_initial_state_t")
+            or isinstance(initial_state_t, TypeVar)
+        ):
+            return ConversationState()
+        return None
+
+    def _should_apply_pending_kickoff_context(self) -> bool:
+        return (
+            type(self)._is_conversational() and self._pending_user_message is not None
+        )
+
+    def _apply_pending_kickoff_context(self) -> None:
+        self._apply_pending_conversational_turn()
+
+    def _order_start_methods_for_kickoff(
+        self,
+        start_methods: list[Any],
+    ) -> tuple[list[Any], bool]:
+        if not type(self)._is_conversational():
+            return start_methods, False
+
+        route_conversation = "route_conversation"
+        if route_conversation not in {str(method) for method in start_methods}:
+            return start_methods, False
+
+        ordered_starts = [
+            method for method in start_methods if str(method) != route_conversation
+        ]
+        ordered_starts.append(
+            next(
+                method for method in start_methods if str(method) == route_conversation
+            )
+        )
+        return ordered_starts, True
+
     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.
+          - the static conversational definition enables deferred finalization.
 
         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)
+        definition = self._conversation_definition
+        return bool(
+            definition and definition.enabled and definition.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._pending_events.clear()
         self._method_call_counts.clear()
         self._clear_or_listeners()
         self._is_execution_resuming = False
@@ -605,11 +851,12 @@ class _ConversationalMixin:
         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))
+        flow_definition = self._conversation_flow_definition()
+        for listener_name, method_definition in flow_definition.methods.items():
+            if method_definition.listen is None or method_definition.router:
+                continue
+            for trigger_label in _iter_condition_labels(method_definition.listen):
+                label_to_method.setdefault(trigger_label, listener_name)
 
         routes = self._effective_routes(router_config)
         overrides = (
@@ -660,21 +907,31 @@ class _ConversationalMixin:
 
     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)
+        flow_definition = self._conversation_flow_definition()
+        for method_definition in flow_definition.methods.values():
+            if method_definition.listen is None or method_definition.router:
+                continue
+            labels.update(_iter_condition_labels(method_definition.listen))
         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()
+        definition = self._conversation_definition
+        builtin_routes = (
+            tuple(definition.builtin_routes)
+            if definition is not None
+            else self.builtin_routes
+        )
+        internal_routes = (
+            tuple(definition.internal_routes)
+            if definition is not None
+            else self.internal_routes
+        )
         if not custom_routes:
             custom_routes = (
-                self._valid_route_labels()
-                - set(self.builtin_routes)
-                - set(self.internal_routes)
+                self._valid_route_labels() - set(builtin_routes) - set(internal_routes)
             )
-        return custom_routes | set(self.builtin_routes)
+        return custom_routes | set(builtin_routes)
 
     def _default_conversation_llm(self) -> Any | None:
         config = self._conversation_config
@@ -780,7 +1037,8 @@ class _ConversationalMixin:
         # of warning about an empty scope stack.
         started_id = getattr(self, "_deferred_flow_started_event_id", None)
         if started_id:
-            last_output = self._method_outputs[-1] if self._method_outputs else None
+            method_outputs = self.method_outputs
+            last_output = method_outputs[-1] if method_outputs else None
             restore_event_scope(((started_id, "flow_started"),))
             try:
                 crewai_event_bus.emit(
@@ -803,12 +1061,15 @@ class _ConversationalMixin:
 
         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()
+        try:
+            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()
+        finally:
+            batch_manager.defer_session_finalization = False
 
 
 __all__ = ["_ConversationalMixin"]

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

@@ -9,9 +9,9 @@ from crewai.flow.conversation import (
     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.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 (

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

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

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

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

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

@@ -0,0 +1,48 @@
+"""Static conversational Flow definition models.
+
+This module is part of the serializable Flow Definition contract. It should
+only contain static data shapes. Experimental conversational runtime behavior
+continues to live in ``crewai.experimental.conversational_mixin``.
+"""
+
+from __future__ import annotations
+
+from typing import Any, Literal
+
+from pydantic import BaseModel, Field
+
+
+class FlowConversationalRouterDefinition(BaseModel):
+    """Static conversational router configuration."""
+
+    prompt: str | None = None
+    response_format: Any = None
+    llm: Any = None
+    routes: list[str] | None = None
+    route_descriptions: dict[str, str] | None = None
+    default_intent: str | None = "converse"
+    fallback_intent: str | None = "converse"
+    intent_field: str = "intent"
+
+
+class FlowConversationalDefinition(BaseModel):
+    """Static conversational Flow configuration."""
+
+    enabled: bool = False
+    system_prompt: str | None = None
+    llm: Any = None
+    router: FlowConversationalRouterDefinition | None = None
+    answer_from_history_prompt: str | None = None
+    default_intents: list[str] | None = None
+    intent_llm: Any = None
+    answer_from_history_llm: Any = None
+    visible_agent_outputs: list[str] | Literal["all"] | None = None
+    defer_trace_finalization: bool = True
+    builtin_routes: list[str] = Field(default_factory=lambda: ["converse", "end"])
+    internal_routes: list[str] = Field(default_factory=lambda: ["answer_from_history"])
+
+
+__all__ = [
+    "FlowConversationalDefinition",
+    "FlowConversationalRouterDefinition",
+]

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 +1,59 @@
+from __future__ import annotations
+
+from collections.abc import Callable, Sequence
+from typing import TYPE_CHECKING, Any, TypeVar
+
+from crewai.flow.human_feedback import (
+    HumanFeedbackConfig,
+    HumanFeedbackResult,
+    _validate_human_feedback_options,
+)
+
+
+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 human_feedback(
+    message: str,
+    emit: Sequence[str] | None = None,
+    llm: str | BaseLLM | None = "gpt-5.4-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.
+
+    The decorator is a pure metadata stamper: it records the feedback
+    configuration on the method, and the Flow engine collects and routes
+    feedback after the method completes, driven by the flow's definition.
+    """
+    _validate_human_feedback_options(
+        emit=emit, llm=llm, default_outcome=default_outcome
+    )
+    config = HumanFeedbackConfig(
+        message=message,
+        emit=list(emit) if emit is not None else None,
+        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:
+        func.__human_feedback_config__ = config  # type: ignore[attr-defined]
+        return func
+
+    return decorator

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

@@ -0,0 +1,57 @@
+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,
+    _method_action,
+    _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(
+                do=_method_action(func),
+                listen=_to_definition_condition(condition),
+            ),
+        )
+        return wrapper
+
+    return cast(FlowMethodDecorator, decorator)