fix(tools): re-validate redirects and pin peer IP to close SSRF bypass

validate_url checked the URL string but ScrapeWebsiteTool and
ScrapeElementFromWebsiteTool then fetched with requests' default
allow_redirects=True, so a public host that 302-redirected to an
internal address reached it without re-validation. The resolved IPs
were also discarded, leaving a DNS time-of-check/time-of-use gap.

Add crewai_tools.security.safe_requests:
- SSRFProtectedAdapter re-runs validate_url on every send, including
  each redirect hop (Session.send calls the adapter per hop).
- Connections validate the actual connected peer IP at connect time,
  so the IP that was authorised is the IP that is used (closes the
  DNS-rebinding gap).

Route the two direct-fetch scrape tools through safe_get and add tests.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

.github/workflows/vulnerability-scan.yml

@@ -71,7 +71,8 @@ jobs:
             --ignore-vuln PYSEC-2025-215 \
             --ignore-vuln PYSEC-2025-216 \
             --ignore-vuln PYSEC-2025-217 \
-            --ignore-vuln PYSEC-2025-218
+            --ignore-vuln PYSEC-2025-218 \
+            --ignore-vuln GHSA-f4j7-r4q5-qw2c
         # Ignored CVEs:
         #   PYSEC-2024-277      - joblib 1.5.3: disputed; NumpyArrayWrapper only used with trusted caches
         #   PYSEC-2026-89       - markdown 3.10.2: DoS via malformed HTML; fix 3.8.1 — already past, advisory range is stale
@@ -81,6 +82,9 @@ jobs:
         #   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
         #   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)
+        #                         and chromadb.utils.embedding_functions; the chromadb HTTP server is never started, so the vulnerable route is not exposed.
         continue-on-error: true
 
       - name: Display results

.pre-commit-config.yaml

@@ -28,7 +28,34 @@ repos:
     hooks:
       - id: pip-audit
         name: pip-audit
-        entry: bash -c 'source .venv/bin/activate && uv run pip-audit --skip-editable --ignore-vuln CVE-2026-3219' --
+        # Keep this ignore list in sync with .github/workflows/vulnerability-scan.yml.
+        entry: >-
+          bash -c 'source .venv/bin/activate && uv run pip-audit --skip-editable
+          --ignore-vuln PYSEC-2024-277
+          --ignore-vuln PYSEC-2026-89
+          --ignore-vuln PYSEC-2026-97
+          --ignore-vuln PYSEC-2025-148
+          --ignore-vuln PYSEC-2025-183
+          --ignore-vuln PYSEC-2025-189
+          --ignore-vuln PYSEC-2025-190
+          --ignore-vuln PYSEC-2025-191
+          --ignore-vuln PYSEC-2025-192
+          --ignore-vuln PYSEC-2025-193
+          --ignore-vuln PYSEC-2025-194
+          --ignore-vuln PYSEC-2025-195
+          --ignore-vuln PYSEC-2025-196
+          --ignore-vuln PYSEC-2025-197
+          --ignore-vuln PYSEC-2025-210
+          --ignore-vuln PYSEC-2026-139
+          --ignore-vuln PYSEC-2025-211
+          --ignore-vuln PYSEC-2025-212
+          --ignore-vuln PYSEC-2025-213
+          --ignore-vuln PYSEC-2025-214
+          --ignore-vuln PYSEC-2025-215
+          --ignore-vuln PYSEC-2025-216
+          --ignore-vuln PYSEC-2025-217
+          --ignore-vuln PYSEC-2025-218
+          --ignore-vuln GHSA-f4j7-r4q5-qw2c' --
         language: system
         pass_filenames: false
         stages: [pre-push, manual]

docs/ar/changelog.mdx

@@ -4,6 +4,44 @@ description: "تحديثات المنتج والتحسينات وإصلاحات
 icon: "clock"
 mode: "wide"
 ---
+<Update label="28 مايو 2026">
+  ## v1.14.6
+
+  [عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.6)
+
+  ## ما الذي تغير
+
+  ### الميزات
+  - تحسين StdioTransport لمنع تسرب متغيرات البيئة
+  - تعزيز تكوين التخطيط ومعالجة الملاحظات
+  - إعلان env_vars على DatabricksQueryTool
+  - إضافة وثائق خطة التحكم في الوكيل
+
+  ### إصلاحات الأخطاء
+  - إصلاح تسرب المخرجات المنظمة في حلقات استدعاء الأدوات
+  - حذف ردود الاستدعاء غير القابلة للعودة وحالة المحول في نقطة التحقق
+  - تسلسل الحقول من النوع [BaseModel] كـ JSON schema في نقطة التحقق
+  - تجنب مهمة orphan task_started عند استعادة نطاق الاستئناف
+  - السماح لـ AgentExecutor بالاستعادة من نقطة التحقق
+  - تصحيح خطأ الكتابة من mongodb إلى pymongo في package_dependencies
+
+  ### الوثائق
+  - إضافة كتلة تنقل وثائق ACP (بيتا) إلى صفحات خطة التحكم في الوكيل
+  - إزالة المراجع إلى العمليات التوافقية من صفحة العمليات
+  - إعادة هيكلة صفحة نقاط التحقق
+  - توثيق خطوة تثبيت حزمة الإدارة لمرة واحدة
+  - نقل Secrets Manager / Workload Identity من replicated-config
+  - إزالة تعبيرات `{" "}` JSX التي تكسر عرض `<Steps>`
+
+  ### إعادة الهيكلة
+  - نقل مستودع المهارات إلى experimental + CREWAI_EXPERIMENTAL gate
+
+  ## المساهمون
+
+  @akaKuruma, @alex-clawd, @github-actions[bot], @greysonlalonde, @heitorado, @iris-clawd, @lorenzejay, @lucasgomide, @mattatcha, @thiagomoretto, @vinibrsl
+
+</Update>
+
 <Update label="27 مايو 2026">
   ## v1.14.6a2
 

docs/ar/concepts/llms.mdx

@@ -107,7 +107,7 @@ mode: "wide"
 </Tabs>
 
 <Info>
-  يوفر CrewAI تكاملات SDK أصلية لـ OpenAI و Anthropic و Google (Gemini API) و Azure و AWS Bedrock -- لا حاجة لتثبيت إضافي بخلاف الملحقات الخاصة بالمزود (مثل `uv add "crewai[openai]"`).
+  يوفر CrewAI تكاملات SDK أصلية لـ OpenAI و Anthropic و Google (Gemini API) و Azure و AWS Bedrock و Snowflake Cortex -- لا حاجة لتثبيت إضافي بخلاف الملحقات الخاصة بالمزود (مثل `uv add "crewai[openai]"`).
 
   جميع المزودين الآخرين مدعومون بواسطة **LiteLLM**. إذا كنت تخطط لاستخدام أي منهم، أضفه كتبعية لمشروعك:
   ```bash
@@ -291,6 +291,55 @@ mode: "wide"
     ```
   </Accordion>
 
+  <Accordion title="Snowflake Cortex">
+    يوفر CrewAI تكاملًا أصليًا مع Snowflake Cortex REST API عبر endpoint Chat Completions المتوافق مع OpenAI. تستخدم نماذج `snowflake/...` هذا المسار بدون fallback إلى LiteLLM. يدعم Snowflake Cortex في CrewAI حاليًا Chat Completions فقط، لذلك استخدم وضع `api` الافتراضي ولا تضبط `api="responses"`.
+
+    ```toml Code
+    # Required
+    SNOWFLAKE_PAT=<your-programmatic-access-token>
+    SNOWFLAKE_ACCOUNT_URL=https://<account-identifier>.snowflakecomputing.com
+
+    # Alternative account configuration
+    SNOWFLAKE_ACCOUNT=<account-identifier>
+    ```
+
+    **الاستخدام الأساسي:**
+    ```python Code
+    from crewai import LLM
+
+    llm = LLM(
+        model="snowflake/openai-gpt-4.1",
+        temperature=0.7,
+        max_completion_tokens=1024,
+    )
+    ```
+
+    **نماذج Claude على Cortex:**
+    ```python Code
+    from crewai import LLM
+
+    llm = LLM(
+        model="snowflake/claude-sonnet-4-5",
+        max_completion_tokens=1024,
+        stream=True,
+    )
+    ```
+
+    **متغيرات البيئة المدعومة:**
+    - `SNOWFLAKE_PAT` أو `SNOWFLAKE_TOKEN` أو `SNOWFLAKE_JWT`: الرمز المستخدم كاعتماد Bearer
+    - `SNOWFLAKE_ACCOUNT_URL`: عنوان URL الكامل لحساب Snowflake
+    - `SNOWFLAKE_ACCOUNT` أو `SNOWFLAKE_ACCOUNT_ID` أو `SNOWFLAKE_ACCOUNT_IDENTIFIER`: معرف الحساب المستخدم لبناء URL
+
+    تستخدم طلبات Snowflake REST الدور الافتراضي للمستخدم. تأكد من أن هذا الدور لديه `SNOWFLAKE.CORTEX_USER` أو `SNOWFLAKE.CORTEX_REST_API_USER`. لا يتطلب endpoint Cortex REST Chat Completions معاملات database أو schema أو warehouse أو role صريح.
+
+    **الميزات:**
+    - اختيار provider أصلي باستخدام `model="snowflake/<model-name>"`
+    - Chat Completions مع streaming وبدونه فقط؛ `api="responses"` غير مدعوم
+    - تتبع استخدام الرموز
+    - استدعاء الدوال لنماذج OpenAI و Claude المستضافة في Snowflake
+    - إزالة assistant prefill النهائي غير الصالح تلقائيًا لنماذج Claude في Snowflake
+  </Accordion>
+
   <Accordion title="Anthropic">
     يوفر CrewAI تكاملًا أصليًا مع Anthropic من خلال Anthropic Python SDK.
 

docs/ar/concepts/processes.mdx

@@ -16,7 +16,6 @@ mode: "wide"
 
 - **تسلسلي**: ينفذ المهام بالتتابع، مما يضمن إكمال المهام بتقدم منظم.
 - **هرمي**: ينظم المهام في تسلسل إداري هرمي، حيث يتم تفويض المهام وتنفيذها بناءً على سلسلة أوامر منظمة. يجب تحديد نموذج لغة المدير (`manager_llm`) أو وكيل مدير مخصص (`manager_agent`) في الطاقم لتفعيل العملية الهرمية، مما يسهّل إنشاء وإدارة المهام من قبل المدير.
-- **العملية التوافقية (مخطط لها)**: تهدف إلى اتخاذ القرارات بشكل تعاوني بين الوكلاء حول تنفيذ المهام، وتقدم هذه العملية نهجًا ديمقراطيًا لإدارة المهام داخل CrewAI. وهي مخطط لها للتطوير المستقبلي وغير مطبقة حاليًا في قاعدة الكود.
 
 ## دور العمليات في العمل الجماعي
 تُمكّن العمليات الوكلاء الأفراد من العمل كوحدة متماسكة، مما يبسّط جهودهم لتحقيق أهداف مشتركة بكفاءة وتناسق.
@@ -59,9 +58,9 @@ crew = Crew(
 
 ## فئة Process: نظرة عامة مفصلة
 
-تم تنفيذ فئة `Process` كتعداد (`Enum`)، مما يضمن أمان الأنواع ويقيّد قيم العملية على الأنواع المحددة (`sequential`، `hierarchical`). العملية التوافقية مخطط لإدراجها مستقبلاً، مما يؤكد التزامنا بالتطوير والابتكار المستمر.
+تم تنفيذ فئة `Process` كتعداد (`Enum`)، مما يضمن أمان الأنواع ويقيّد قيم العملية على الأنواع المحددة (`sequential`، `hierarchical`).
 
 ## الخلاصة
 
 التعاون المنظم الذي تسهّله العمليات داخل CrewAI ضروري لتمكين العمل الجماعي المنهجي بين الوكلاء.
-تم تحديث هذه الوثائق لتعكس أحدث الميزات والتحسينات والتكامل المخطط للعملية التوافقية، مما يضمن وصول المستخدمين إلى أحدث المعلومات وأكثرها شمولاً.
+تم تحديث هذه الوثائق لتعكس أحدث الميزات والتحسينات، مما يضمن وصول المستخدمين إلى أحدث المعلومات وأكثرها شمولاً.

docs/ar/enterprise/features/agent-control-plane/monitoring.mdx

@@ -6,6 +6,14 @@ icon: "gauge"
 mode: "wide"
 ---
 
+<Info>
+  **تنقل وثائق ACP (إصدار تجريبي)**
+
+  - [نظرة عامة](/ar/enterprise/features/agent-control-plane/overview)
+  - **المراقبة** *(أنت هنا)*
+  - [القواعد](/ar/enterprise/features/agent-control-plane/rules)
+</Info>
+
 ## نظرة عامة
 
 تبويب **Automations** هو عرض العمليات للقراءة فقط في [Agent Control Plane](/ar/enterprise/features/agent-control-plane/overview). يجمع بين بطاقتَي مقاييس و sankey تفاعلي وجدولين فرعيين — **Automations** و **Consumption** — يمكنك البحث والتصفية والفرز فيهما.

docs/ar/enterprise/features/agent-control-plane/overview.mdx

@@ -5,6 +5,14 @@ sidebarTitle: نظرة عامة
 icon: "book-open"
 ---
 
+<Info>
+  **تنقل وثائق ACP (إصدار تجريبي)**
+
+  - **نظرة عامة** *(أنت هنا)*
+  - [المراقبة](/ar/enterprise/features/agent-control-plane/monitoring)
+  - [القواعد](/ar/enterprise/features/agent-control-plane/rules)
+</Info>
+
 ## نظرة عامة
 
 **Agent Control Plane** (ACP) هو مركز العمليات لكل ما يعمل لديك على CrewAI AMP. إنها شاشة واحدة — مقسّمة إلى تبويبَي **Automations** و **Rules** — تمنح فريقك القدرة على:

docs/ar/enterprise/features/agent-control-plane/rules.mdx

@@ -6,6 +6,14 @@ icon: "shield-check"
 mode: "wide"
 ---
 
+<Info>
+  **تنقل وثائق ACP (إصدار تجريبي)**
+
+  - [نظرة عامة](/ar/enterprise/features/agent-control-plane/overview)
+  - [المراقبة](/ar/enterprise/features/agent-control-plane/monitoring)
+  - **القواعد** *(أنت هنا)*
+</Info>
+
 ## نظرة عامة
 
 تتيح لك القواعد تطبيق سياسات — اليوم: **PII Redaction** — عبر العديد من الأتمتات دفعة واحدة، بدلاً من ضبط كل deployment على حدة. افتح تبويب **Rules** في [Agent Control Plane](/ar/enterprise/features/agent-control-plane/overview) لإدارتها.

docs/ar/enterprise/integrations/databricks.mdx

@@ -0,0 +1,123 @@
+---
+title: تكامل Databricks
+description: "اربط وكلاء CrewAI بـ Databricks Genie وSQL وUnity Catalog Functions وVector Search عبر خوادم MCP المُدارة من Databricks."
+icon: "layer-group"
+mode: "wide"
+---
+
+## نظرة عامة
+
+اربط وكلاء CrewAI مباشرةً بمساحة عمل Databricks الخاصة بك عبر [خوادم MCP المُدارة من Databricks](https://docs.databricks.com/aws/en/generative-ai/mcp/managed-mcp). يتيح تكامل Databricks لوكلائك طرح أسئلة بلغة طبيعية باستخدام **Genie**، وتنفيذ **SQL** خاضع للحوكمة، واستدعاء **Unity Catalog Functions**، واسترجاع المستندات باستخدام **Vector Search** — كل ذلك دون كتابة أو استضافة أي كود موصِّل، مع تطبيق أذونات Unity Catalog في كل استدعاء.
+
+في الخلفية، يُعدّ تكامل Databricks غلافًا مُدارًا حول دعم [خوادم MCP المخصصة](/ar/enterprise/guides/custom-mcp-server) في CrewAI. تكشف Databricks عن كل قدرة كنقطة نهاية [Model Context Protocol](https://modelcontextprotocol.io/) خاصة بها، ويتصل بها CrewAI بأمان نيابةً عنك. ولأن كل خادم يُضاف بشكل منفصل، يمكنك تفعيل القدرات التي تحتاجها فرقك (crews) بالضبط.
+
+## القدرات الرئيسية
+
+<CardGroup cols={2}>
+  <Card title="Genie" icon="comments">
+    اطرح أسئلة بلغة طبيعية واحصل على إجابات مستندة إلى بياناتك باستخدام [Genie](https://docs.databricks.com/aws/en/genie/)، الذي يستعلم من Genie Spaces وUnity Catalog ويوفّر روابط تعود إلى واجهة Databricks.
+  </Card>
+  <Card title="Databricks SQL" icon="database">
+    نفّذ SQL خاضعًا للحوكمة على مستودعات Databricks لديك للاستعلام عن البيانات وتحويلها وإنشاء خطوط أنابيب البيانات مباشرةً من وكلائك.
+  </Card>
+  <Card title="Unity Catalog Functions" icon="function">
+    استدعِ [دوال Unity Catalog](https://docs.databricks.com/aws/en/udf/unity-catalog) لتنفيذ SQL مُعرّف مسبقًا ومنطق أعمال مخصّص كأدوات قابلة لإعادة الاستخدام وخاضعة للحوكمة.
+  </Card>
+  <Card title="Vector Search" icon="magnifying-glass">
+    استرجع المستندات ذات الصلة لسير عمل RAG والمعرفة من فهارس [Mosaic AI Vector Search](https://docs.databricks.com/aws/en/generative-ai/vector-search) باستخدام التشابه الدلالي.
+  </Card>
+</CardGroup>
+
+تعمل جميع الخوادم خلف Unity AI Gateway وتطبّق ضوابط الوصول في Unity Catalog، بحيث لا يرى وكلاؤك سوى البيانات والأدوات المصرَّح لهم باستخدامها.
+
+## المتطلبات المسبقة
+
+قبل استخدام تكامل Databricks، تأكّد من توفّر ما يلي:
+
+- حساب [CrewAI AMP](https://app.crewai.com) باشتراك نشط
+- مساحة عمل Databricks تحتوي على القدرات التي تريد كشفها (Genie Spaces، مستودعات SQL، دوال Unity Catalog، أو فهارس Vector Search)
+- [امتيازات Unity Catalog](https://docs.databricks.com/aws/en/data-governance/unity-catalog) المناسبة على الكائنات الأساسية
+- اسم مضيف مساحة عمل Databricks الخاص بك (مثال: `your-workspace.cloud.databricks.com`)
+
+## خوادم MCP المُدارة من Databricks
+
+تنشر Databricks خادم MCP مُدارًا منفصلًا لكل قدرة. يكشف CrewAI عنها كاتصالات فردية، يُهيَّأ كل منها باستخدام مضيف مساحة العمل ومعرّفات Unity Catalog ذات الصلة. تتبع نقاط النهاية الأنماط التالية:
+
+| الخادم | الوظيفة | نمط عنوان MCP |
+|--------|---------|---------------|
+| **Genie** | أسئلة وأجوبة بلغة طبيعية على Genie Space | `https://<workspace-hostname>/api/2.0/mcp/genie/{genie_space_id}` |
+| **Databricks SQL** | تنفيذ SQL على مستودعاتك | `https://<workspace-hostname>/api/2.0/mcp/sql` |
+| **Unity Catalog Functions** | تشغيل دوال UC المسجّلة | `https://<workspace-hostname>/api/2.0/mcp/functions/{catalog}/{schema}` |
+| **Vector Search** | الاستعلام من فهرس Vector Search | `https://<workspace-hostname>/api/2.0/mcp/vector-search/{catalog}/{schema}` |
+
+<Note>
+لا حاجة لإنشاء عناوين URL هذه يدويًا — يُنشئ CrewAI كل نقطة نهاية من مضيف مساحة العمل والمعرّفات (Genie Space ID، أو catalog/schema) التي تقدّمها عند تهيئة الاتصال. للاطّلاع على المواصفات الكاملة وأحدث تفاصيل نقاط النهاية، راجع [وثائق MCP المُدارة من Databricks](https://docs.databricks.com/aws/en/generative-ai/mcp/managed-mcp).
+</Note>
+
+## ربط Databricks في CrewAI AMP
+
+<Frame>
+    <img src="/images/enterprise/databricks-configure.png" alt="تهيئة خادم MCP مُدار من Databricks في CrewAI AMP" />
+</Frame>
+
+تظهر كل قدرة من قدرات Databricks — **Databricks Genie** و**Databricks SQL** و**Databricks Unity Catalog Functions** و**Databricks Vector Search** — كخادم MCP خاص بها ضمن مجموعة Databricks في صفحة **Tools & Integrations**. هيّئ ما تحتاجه:
+
+<Steps>
+    <Step title="افتح Tools & Integrations">
+        انتقل إلى **Tools & Integrations** في الشريط الجانبي الأيسر في CrewAI AMP وحدِّد مجموعة **Databricks** في قائمة Connections. سترى خوادم Genie وSQL وUnity Catalog Functions وVector Search مُدرجة أسفلها.
+    </Step>
+
+    <Step title="هيّئ خادمًا">
+        انقر على **Configure** بجوار القدرة التي تريد تفعيلها وقدّم تفاصيل الاتصال الخاصة بها:
+
+        - **Workspace Host** — اسم مضيف مساحة عمل Databricks الخاص بك (مثال: `my-workspace.cloud.databricks.com`).
+        - **Genie** — **Genie Space ID** المراد الاستعلام عنه.
+        - **Unity Catalog Functions** — الـ **catalog** والـ **schema** اللذان يحتويان على دوالك.
+        - **Vector Search** — الـ **catalog** والـ **schema** اللذان يحتويان على الفهرس.
+        - **Databricks SQL** — لا توجد معرّفات إضافية؛ تُنفَّذ الاستعلامات على مستودعات SQL في مساحة عملك.
+    </Step>
+
+    <Step title="اختر طريقة المصادقة">
+        اختر كيف يصادق CrewAI على Databricks. يُوصى باستخدام **OAuth**.
+
+        - **Use OAuth** — اتصل بأمان باستخدام OAuth 2.0. يصادق كل مستخدم على حدة، وتُصدر Databricks رموزًا (tokens) محدّدة النطاق للقدرة (`genie` أو `sql` أو `unity-catalog` أو `vector-search`). يتولّى CrewAI تدفّق التفويض ويُجدّد الرموز تلقائيًا.
+        - **Use personal access token** — صادِق باستخدام [رمز وصول شخصي من Databricks](https://docs.databricks.com/aws/en/dev-tools/auth/pat). استخدم هوية بأقل الامتيازات للحدّ من التعرّض.
+    </Step>
+
+    <Step title="صادِق">
+        أكمل المصادقة. بمجرد الاتصال، تصبح أدوات الخادم متاحة لفرقك. كرّر العملية لأي قدرات Databricks أخرى تريد تفعيلها.
+    </Step>
+</Steps>
+
+<Tip>
+لأن كل قدرة هي اتصال منفصل، يمكنك المزج والمطابقة — على سبيل المثال، فعّل Genie وVector Search لفريق بحث، مع حجز SQL وUnity Catalog Functions لفريق هندسة البيانات. تتيح لك إعدادات الرؤية (Visibility) التحكّم في أعضاء الفريق الذين يمكنهم استخدام كل منها.
+</Tip>
+
+## استخدام أدوات Databricks في فرقك
+
+بمجرد الاتصال، تظهر الأدوات التي يكشفها كل خادم MCP جنبًا إلى جنب مع الاتصالات المدمجة في صفحة **Tools & Integrations**. يمكنك:
+
+- **إسناد الأدوات إلى الوكلاء** في فرقك تمامًا مثل أي أداة أخرى في CrewAI.
+- **إدارة الرؤية** للتحكّم في أعضاء الفريق الذين يمكنهم استخدام كل اتصال.
+- **تعديل أو إزالة** أي اتصال في أي وقت من قائمة Connections.
+
+يمكن لوكلائك الآن طلب إجابات مستندة من Genie، وتنفيذ SQL على مستودعاتك، واستدعاء دوال Unity Catalog، والبحث في فهارس Vector Search — مع تدفّق النتائج تلقائيًا إلى استدلالهم.
+
+<Warning>
+تطبّق Databricks الحوكمة عبر Unity Catalog وUnity AI Gateway: لا يمكن للمستخدم اكتشاف الأدوات واستدعاؤها إلا تلك المصرَّح بها لهوية مساحة عمله. إذا فشل استدعاء أداة، فتأكّد من أن المستخدم المتصل (أو هوية الرمز) يمتلك امتيازات Unity Catalog المطلوبة على Genie Space أو المستودع أو الدالة أو الفهرس. تُنفَّذ بعض استعلامات Genie وSQL بشكل غير متزامن وقد تستغرق لحظة لإرجاع النتائج.
+</Warning>
+
+## مزيد من المعلومات
+
+<CardGroup cols={2}>
+  <Card title="خوادم MCP المُدارة من Databricks" icon="layer-group" href="https://docs.databricks.com/aws/en/generative-ai/mcp/managed-mcp">
+    وثائق Databricks الرسمية لخوادم MCP المُدارة Genie وSQL وUnity Catalog Functions وVector Search.
+  </Card>
+  <Card title="خوادم MCP المخصصة في CrewAI" icon="plug" href="/ar/enterprise/guides/custom-mcp-server">
+    تعرّف على كيفية اتصال CrewAI بأي خادم MCP، وهو الأساس الذي يُبنى عليه تكامل Databricks.
+  </Card>
+</CardGroup>
+
+<Card title="بحاجة إلى مساعدة؟" icon="headset" href="mailto:support@crewai.com">
+  تواصل مع فريق الدعم للحصول على المساعدة في تهيئة تكامل Databricks أو في حل المشكلات.
+</Card>

docs/ar/enterprise/integrations/snowflake.mdx

@@ -0,0 +1,134 @@
+---
+title: تكامل Snowflake
+description: "ربط وكلاء CrewAI بـ Snowflake Cortex Analyst و Cortex Search وتنفيذ SQL من خلال خادم MCP المُدار من Snowflake."
+icon: "snowflake"
+mode: "wide"
+---
+
+## نظرة عامة
+
+اربط وكلاء CrewAI مباشرة ببيانات Snowflake الخاصة بك من خلال [خادم MCP المُدار من Snowflake](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp). يتيح تكامل Snowflake لوكلائك الاستعلام عن البيانات المنظمة باستخدام **Cortex Analyst**، والبحث في البيانات غير المنظمة باستخدام **Cortex Search**، وتنفيذ SQL مُدار على مستودعات البيانات الخاصة بك — كل ذلك دون كتابة أو استضافة أي كود للموصّل.
+
+داخلياً، تكامل Snowflake هو غلاف مُدار حول دعم [Custom MCP Server](/ar/enterprise/guides/custom-mcp-server) في CrewAI. يكشف Snowflake عن قدرات Cortex AI الخاصة به من خلال نقطة نهاية [Model Context Protocol](https://modelcontextprotocol.io/)، ويتصل CrewAI بها بشكل آمن نيابةً عنك. أي أداة تكشفها على جانب Snowflake — Cortex Analyst أو Cortex Search أو تنفيذ SQL أو Cortex Agents أو أدواتك المخصصة — تصبح متاحة لطواقمك.
+
+## القدرات الرئيسية
+
+<CardGroup cols={3}>
+  <Card title="Cortex Analyst" icon="chart-bar">
+    اطرح أسئلة بلغة طبيعية ودع [Cortex Analyst](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-analyst) يولّد وينفذ SQL على بياناتك **المنظمة** باستخدام نماذج دلالية غنية.
+  </Card>
+  <Card title="Cortex Search" icon="magnifying-glass">
+    استرجع البيانات **غير المنظمة** ذات الصلة لسير عمل RAG والمعرفة باستخدام [Cortex Search](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-search/cortex-search-overview)، خدمة البحث المُدارة بالكامل من Snowflake.
+  </Card>
+  <Card title="تنفيذ SQL" icon="database">
+    نفّذ استعلامات SQL مُدارة مباشرة على مستودعات Snowflake الخاصة بك، مع وضع القراءة فقط القابل للتكوين، والمهلات الزمنية، واختيار المستودع.
+  </Card>
+</CardGroup>
+
+نظراً لأن التكامل يكشف عن أي أدوات ينشرها خادم MCP الخاص بك، يمكنك أيضاً كشف **Cortex Agents** و**الأدوات المخصصة** (الدوال المعرّفة من المستخدم والإجراءات المخزّنة) لوكلاء CrewAI.
+
+## المتطلبات الأساسية
+
+قبل استخدام تكامل Snowflake، تأكد من توفر ما يلي:
+
+- حساب [CrewAI AMP](https://app.crewai.com) مع اشتراك فعّال
+- حساب Snowflake مع إمكانية الوصول إلى ميزات Cortex AI
+- [خادم MCP مُدار من Snowflake](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp) مُكوّن بالأدوات التي تريد كشفها
+- صلاحيات Snowflake المناسبة (USAGE/SELECT) على خادم MCP والكائنات الأساسية
+
+## إعداد خادم Snowflake MCP
+
+يعمل خادم MCP المُدار من Snowflake داخل حساب Snowflake الخاص بك ويحدد الأدوات المتاحة للعملاء الخارجيين مثل CrewAI. أنشئ واحداً باستخدام أمر [`CREATE MCP SERVER`](https://docs.snowflake.com/en/sql-reference/sql/create-mcp-server)، مع سرد خدمات Cortex Search وعروض Cortex Analyst الدلالية وأدوات SQL التي تريد كشفها.
+
+```sql
+CREATE MCP SERVER my_mcp_server
+  FROM SPECIFICATION $$
+    tools:
+      - name: "sales_analyst"
+        type: "CORTEX_ANALYST"
+        identifier: "MY_DATABASE.MY_SCHEMA.sales_semantic_view"
+        description: "Answer questions about sales metrics"
+      - name: "docs_search"
+        type: "CORTEX_SEARCH_SERVICE_QUERY"
+        identifier: "MY_DATABASE.MY_SCHEMA.support_docs_search"
+        description: "Search internal support documentation"
+      - name: "run_sql"
+        type: "SQL_EXECUTION"
+        description: "Execute read-only SQL queries"
+  $$;
+```
+
+<Note>
+تتبع نقطة نهاية MCP التنسيق `https://<account_URL>/api/v2/databases/{database}/schemas/{schema}/mcp-servers/{name}`. يبني CrewAI هذا العنوان تلقائياً من **عنوان URL للحساب** و**قاعدة البيانات** و**المخطط** و**اسم خادم MCP** الذي تقدمه عند تكوين التكامل.
+</Note>
+
+للمواصفات الكاملة — بما في ذلك Cortex Agents والأدوات المخصصة وحدود حجم الاستجابة وخيارات الحوكمة — راجع [وثائق خادم MCP المُدار من Snowflake](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp).
+
+## ربط Snowflake في CrewAI AMP
+
+<Frame>
+    <img src="/images/enterprise/snowflake-configure.png" alt="تكوين تكامل Snowflake في CrewAI AMP" />
+</Frame>
+
+<Steps>
+    <Step title="فتح الأدوات والتكاملات">
+        انتقل إلى **الأدوات والتكاملات** في الشريط الجانبي الأيسر لـ CrewAI AMP، وابحث عن **Snowflake** في قائمة التطبيقات، وافتح لوحة التكوين الخاصة به.
+    </Step>
+
+    <Step title="تقديم تفاصيل الاتصال">
+        املأ حقول الاتصال التي يستخدمها CrewAI للوصول إلى خادم Snowflake MCP الخاص بك:
+
+        | الحقل | مطلوب | الوصف |
+        |-------|-------|-------|
+        | **الاسم** | نعم | اسم وصفي لهذا الاتصال (القيمة الافتراضية `Snowflake`). |
+        | **الوصف** | لا | ملخص اختياري لما يوفره هذا الاتصال. |
+        | **عنوان URL للحساب** | نعم | عنوان URL لحساب Snowflake الخاص بك، مثل `xy12345.us-east-1.snowflakecomputing.com`. |
+        | **قاعدة البيانات** | نعم | قاعدة البيانات التي تحتوي على خادم MCP الخاص بك (مثل `MY_DATABASE`). |
+        | **المخطط** | نعم | المخطط الذي يحتوي على خادم MCP الخاص بك (مثل `MY_SCHEMA`). |
+        | **اسم خادم MCP** | نعم | اسم كائن خادم MCP الذي أنشأته في Snowflake (مثل `MY_MCP_SERVER`). |
+    </Step>
+
+    <Step title="اختيار طريقة المصادقة">
+        اختر كيفية مصادقة CrewAI مع Snowflake. يُوصى باستخدام **OAuth**.
+
+        - **استخدام OAuth** — اتصل بشكل آمن باستخدام OAuth 2.0 للمصادقة القائمة على الرموز دون مشاركة بيانات الاعتماد الخاصة بك. يتعامل CrewAI مع تدفق التفويض الكامل ويجدد الرموز تلقائياً. انسخ **عنوان URI لإعادة التوجيه** المعروض في النموذج (`https://oauth.crewai.com/oauth/add`) وسجّله كعنوان URI لإعادة التوجيه المعتمد في [تكامل أمان OAuth](https://docs.snowflake.com/en/user-guide/oauth-custom) في Snowflake.
+        - **استخدام رمز وصول شخصي** — المصادقة باستخدام [رمز وصول برمجي](https://docs.snowflake.com/en/user-guide/programmatic-access-tokens) مُنشأ من إعدادات حساب Snowflake الخاص بك. قم بتعيين دور بأقل صلاحيات للرمز للحد من التعرض.
+    </Step>
+
+    <Step title="المصادقة">
+        انقر على **المصادقة**. بالنسبة لـ OAuth، ستتم إعادة توجيهك إلى Snowflake لتفويض الوصول. بمجرد المصادقة، يظهر خادم Snowflake في قائمة الاتصالات وتصبح أدواته متاحة لطواقمك.
+    </Step>
+</Steps>
+
+<Tip>
+مع OAuth، يتم مصادقة كل مستخدم بشكل فردي وتُنفّذ الاستعلامات بدور `DEFAULT_ROLE` الخاص به في Snowflake. تأكد من أن المستخدمين المتصلين لديهم دور ومستودع افتراضي محدد (`ALTER USER <username> SET DEFAULT_ROLE = '<role>' DEFAULT_WAREHOUSE = '<warehouse>'`) حتى تتوفر موارد الحوسبة لأدوات Cortex Analyst و SQL.
+</Tip>
+
+## استخدام أدوات Snowflake في طواقمك
+
+بمجرد الاتصال، تظهر الأدوات التي يكشفها خادم MCP الخاص بك إلى جانب الاتصالات المدمجة في صفحة **الأدوات والتكاملات**. يمكنك:
+
+- **تعيين الأدوات للوكلاء** في طواقمك تماماً مثل أي أداة CrewAI أخرى.
+- **إدارة الرؤية** للتحكم في أعضاء الفريق الذين يمكنهم استخدام الاتصال.
+- **تعديل أو إزالة** الاتصال في أي وقت من قائمة الاتصالات.
+
+يمكن لوكلائك الآن سؤال Cortex Analyst عن المقاييس، وتشغيل Cortex Search على مستنداتك، وتنفيذ SQL — مع تدفق النتائج تلقائياً إلى استدلالهم.
+
+<Warning>
+يفرض Snowflake الحوكمة على خادم MCP: يحدد التحكم في الوصول القائم على الأدوار الأدوات التي يمكن للمستخدم اكتشافها واستدعاؤها، وتنطبق حدود على حجم الاستجابة وعدد الأدوات (بحد أقصى 50 لكل خادم) وعمق التكرار. إذا فشل استدعاء أداة، تأكد من أن دور المستخدم المتصل لديه الصلاحيات المطلوبة على خادم MCP والكائنات الأساسية.
+</Warning>
+
+## معرفة المزيد
+
+<CardGroup cols={2}>
+  <Card title="خادم MCP المُدار من Snowflake" icon="snowflake" href="https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp">
+    الوثائق الرسمية من Snowflake لإنشاء وإدارة خادم MCP.
+  </Card>
+  <Card title="خوادم Custom MCP في CrewAI" icon="plug" href="/ar/enterprise/guides/custom-mcp-server">
+    تعرّف على كيفية اتصال CrewAI بأي خادم MCP، الأساس الذي يبني عليه تكامل Snowflake.
+  </Card>
+</CardGroup>
+
+<Card title="تحتاج مساعدة؟" icon="headset" href="mailto:support@crewai.com">
+  تواصل مع فريق الدعم للحصول على المساعدة في تكامل Snowflake أو استكشاف الأخطاء وإصلاحها.
+</Card>

docs/en/changelog.mdx

@@ -4,6 +4,44 @@ description: "Product updates, improvements, and bug fixes for CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="May 28, 2026">
+  ## v1.14.6
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.6)
+
+  ## What's Changed
+
+  ### Features
+  - Enhance StdioTransport to prevent environment variable leakage
+  - Enhance planning configuration and observation handling
+  - Declare env_vars on DatabricksQueryTool
+  - Add Agent Control Plane docs
+
+  ### Bug Fixes
+  - Fix structured output leaks in tool-calling loops
+  - Drop unroundtrippable callbacks and adapter state in checkpoint
+  - Serialize type[BaseModel] fields as JSON schema in checkpoint
+  - Avoid orphan task_started on resume scope restore
+  - Allow AgentExecutor to restore from checkpoint
+  - Correct mongodb typo to pymongo in package_dependencies
+
+  ### Documentation
+  - Add ACP (Beta) docs navigation block to Agent Control Plane pages
+  - Remove consensual process references from processes page
+  - Restructure checkpointing page
+  - Document one-time admin package install step
+  - Migrate Secrets Manager / Workload Identity from replicated-config
+  - Remove `{" "}` JSX expressions breaking `<Steps>` render
+
+  ### Refactoring
+  - Move Skills Repository to experimental + CREWAI_EXPERIMENTAL gate
+
+  ## Contributors
+
+  @akaKuruma, @alex-clawd, @github-actions[bot], @greysonlalonde, @heitorado, @iris-clawd, @lorenzejay, @lucasgomide, @mattatcha, @thiagomoretto, @vinibrsl
+
+</Update>
+
 <Update label="May 27, 2026">
   ## v1.14.6a2
 

docs/en/concepts/llms.mdx

@@ -107,7 +107,7 @@ There are different places in CrewAI code where you can specify the model to use
 </Tabs>
 
 <Info>
-  CrewAI provides native SDK integrations for OpenAI, Anthropic, Google (Gemini API), Azure, and AWS Bedrock — no extra install needed beyond the provider-specific extras (e.g. `uv add "crewai[openai]"`).
+  CrewAI provides native SDK integrations for OpenAI, Anthropic, Google (Gemini API), Azure, AWS Bedrock, and Snowflake Cortex — no extra install needed beyond the provider-specific extras (e.g. `uv add "crewai[openai]"`).
 
   All other providers are powered by **LiteLLM**. If you plan to use any of them, add it as a dependency to your project:
   ```bash
@@ -291,6 +291,55 @@ In this section, you'll find detailed examples that help you select, configure,
     ```
   </Accordion>
 
+  <Accordion title="Snowflake Cortex">
+    CrewAI provides native integration with the Snowflake Cortex REST API through its OpenAI-compatible Chat Completions endpoint. This avoids LiteLLM fallback for `snowflake/...` models. Snowflake Cortex currently supports Chat Completions only in CrewAI, so use the default `api` mode and do not set `api="responses"`.
+
+    ```toml Code
+    # Required
+    SNOWFLAKE_PAT=<your-programmatic-access-token>
+    SNOWFLAKE_ACCOUNT_URL=https://<account-identifier>.snowflakecomputing.com
+
+    # Alternative account configuration
+    SNOWFLAKE_ACCOUNT=<account-identifier>
+    ```
+
+    **Basic Usage:**
+    ```python Code
+    from crewai import LLM
+
+    llm = LLM(
+        model="snowflake/openai-gpt-4.1",
+        temperature=0.7,
+        max_completion_tokens=1024,
+    )
+    ```
+
+    **Claude Models on Cortex:**
+    ```python Code
+    from crewai import LLM
+
+    llm = LLM(
+        model="snowflake/claude-sonnet-4-5",
+        max_completion_tokens=1024,
+        stream=True,
+    )
+    ```
+
+    **Supported Environment Variables:**
+    - `SNOWFLAKE_PAT`, `SNOWFLAKE_TOKEN`, or `SNOWFLAKE_JWT`: token used as the Bearer credential
+    - `SNOWFLAKE_ACCOUNT_URL`: full Snowflake account URL
+    - `SNOWFLAKE_ACCOUNT`, `SNOWFLAKE_ACCOUNT_ID`, or `SNOWFLAKE_ACCOUNT_IDENTIFIER`: account identifier used to build the account URL
+
+    Snowflake REST requests use the user's default Snowflake role. Make sure that role has `SNOWFLAKE.CORTEX_USER` or `SNOWFLAKE.CORTEX_REST_API_USER`. Database, schema, warehouse, and explicit role parameters are not required by the Cortex REST Chat Completions endpoint.
+
+    **Features:**
+    - Native provider selection with `model="snowflake/<model-name>"`
+    - Streaming and non-streaming Chat Completions only; `api="responses"` is not supported
+    - Token usage tracking
+    - Function calling for Snowflake-hosted OpenAI and Claude models
+    - Automatic removal of invalid trailing assistant prefill for Snowflake Claude models
+  </Accordion>
+
   <Accordion title="Anthropic">
     CrewAI provides native integration with Anthropic through the Anthropic Python SDK.
 

docs/en/concepts/processes.mdx

@@ -16,7 +16,6 @@ mode: "wide"
 
 - **Sequential**: Executes tasks sequentially, ensuring tasks are completed in an orderly progression.
 - **Hierarchical**: Organizes tasks in a managerial hierarchy, where tasks are delegated and executed based on a structured chain of command. A manager language model (`manager_llm`) or a custom manager agent (`manager_agent`) must be specified in the crew to enable the hierarchical process, facilitating the creation and management of tasks by the manager.
-- **Consensual Process (Planned)**: Aiming for collaborative decision-making among agents on task execution, this process type introduces a democratic approach to task management within CrewAI. It is planned for future development and is not currently implemented in the codebase.
 
 ## The Role of Processes in Teamwork
 Processes enable individual agents to operate as a cohesive unit, streamlining their efforts to achieve common objectives with efficiency and coherence.
@@ -59,9 +58,9 @@ Emulates a corporate hierarchy, CrewAI allows specifying a custom manager agent
 
 ## Process Class: Detailed Overview
 
-The `Process` class is implemented as an enumeration (`Enum`), ensuring type safety and restricting process values to the defined types (`sequential`, `hierarchical`). The consensual process is planned for future inclusion, emphasizing our commitment to continuous development and innovation.
+The `Process` class is implemented as an enumeration (`Enum`), ensuring type safety and restricting process values to the defined types (`sequential`, `hierarchical`).
 
 ## Conclusion
 
 The structured collaboration facilitated by processes within CrewAI is crucial for enabling systematic teamwork among agents. 
-This documentation has been updated to reflect the latest features, enhancements, and the planned integration of the Consensual Process, ensuring users have access to the most current and comprehensive information.
+This documentation has been updated to reflect the latest features and enhancements, ensuring users have access to the most current and comprehensive information.

docs/en/concepts/training.mdx

@@ -187,7 +187,7 @@ flowchart TD
 - **Filename Requirement:** Ensure that the filename ends with `.pkl`. The code will raise a `ValueError` if this condition is not met.
 - **Error Handling:** The code handles subprocess errors and unexpected exceptions, providing error messages to the user.
 - Trained guidance is applied at prompt time; it does not modify your Python/YAML agent configuration.
-- Agents automatically load trained suggestions from a file named `trained_agents_data.pkl` located in the current working directory. If you trained to a different filename, either rename it to `trained_agents_data.pkl` before running, or adjust the loader in code.
+- Agents automatically load trained suggestions from a file named `trained_agents_data.pkl` located in the current working directory. If you trained to a different filename, pass that path with `Crew(trained_agents_file="my_custom_trained.pkl")`, set `CREWAI_TRAINED_AGENTS_FILE`, or use `crewai run -f my_custom_trained.pkl`.
 - You can change the output filename when calling `crewai train` with `-f/--filename`. Absolute paths are supported if you want to save outside the CWD.
 
 It is important to note that the training process may take some time, depending on the complexity of your agents and will also require your feedback on each iteration.

docs/en/enterprise/features/agent-control-plane/monitoring.mdx

@@ -6,6 +6,14 @@ icon: "gauge"
 mode: "wide"
 ---
 
+<Info>
+  **ACP (Beta) Docs Navigation**
+
+  - [Overview](/en/enterprise/features/agent-control-plane/overview)
+  - **Monitoring** *(you are here)*
+  - [Rules](/en/enterprise/features/agent-control-plane/rules)
+</Info>
+
 ## Overview
 
 The **Automations** tab is the read-only operations view of the [Agent Control Plane](/en/enterprise/features/agent-control-plane/overview). It combines two metric cards, an interactive sankey, and two sub-tables — **Automations** and **Consumption** — that you can search, filter, and sort.

docs/en/enterprise/features/agent-control-plane/overview.mdx

@@ -5,6 +5,14 @@ sidebarTitle: Overview
 icon: "book-open"
 ---
 
+<Info>
+  **ACP (Beta) Docs Navigation**
+
+  - **Overview** *(you are here)*
+  - [Monitoring](/en/enterprise/features/agent-control-plane/monitoring)
+  - [Rules](/en/enterprise/features/agent-control-plane/rules)
+</Info>
+
 ## Overview
 
 The **Agent Control Plane** (ACP) is the operations hub for everything you have running on CrewAI AMP. It is a single screen — split into **Automations** and **Rules** tabs — that lets your team:

docs/en/enterprise/features/agent-control-plane/rules.mdx

@@ -6,6 +6,14 @@ icon: "shield-check"
 mode: "wide"
 ---
 
+<Info>
+  **ACP (Beta) Docs Navigation**
+
+  - [Overview](/en/enterprise/features/agent-control-plane/overview)
+  - [Monitoring](/en/enterprise/features/agent-control-plane/monitoring)
+  - **Rules** *(you are here)*
+</Info>
+
 ## Overview
 
 Rules let you apply policies — today: **PII Redaction** — across many automations at once, instead of configuring each deployment individually. Open the **Rules** tab in the [Agent Control Plane](/en/enterprise/features/agent-control-plane/overview) to manage them.

docs/en/enterprise/integrations/databricks.mdx

@@ -0,0 +1,123 @@
+---
+title: Databricks Integration
+description: "Connect CrewAI agents to Databricks Genie, SQL, Unity Catalog Functions, and Vector Search through Databricks managed MCP servers."
+icon: "layer-group"
+mode: "wide"
+---
+
+## Overview
+
+Connect your CrewAI agents directly to your Databricks workspace through [Databricks managed MCP servers](https://docs.databricks.com/aws/en/generative-ai/mcp/managed-mcp). The Databricks integration lets your agents ask natural-language questions with **Genie**, run governed **SQL**, call **Unity Catalog Functions**, and retrieve documents with **Vector Search** — all without writing or hosting any connector code, and with Unity Catalog permissions enforced on every call.
+
+Under the hood, the Databricks integration is a managed wrapper around CrewAI's [Custom MCP Server](/en/enterprise/guides/custom-mcp-server) support. Databricks exposes each capability as its own [Model Context Protocol](https://modelcontextprotocol.io/) endpoint, and CrewAI connects to them securely on your behalf. Because each server is added separately, you can enable exactly the capabilities your crews need.
+
+## Key Capabilities
+
+<CardGroup cols={2}>
+  <Card title="Genie" icon="comments">
+    Ask questions in plain language and get grounded answers from your data with [Genie](https://docs.databricks.com/aws/en/genie/), which queries Genie Spaces and Unity Catalog and links back to the Databricks UI.
+  </Card>
+  <Card title="Databricks SQL" icon="database">
+    Run governed SQL against your Databricks warehouses to query, transform, and author data pipelines directly from your agents.
+  </Card>
+  <Card title="Unity Catalog Functions" icon="function">
+    Invoke [Unity Catalog functions](https://docs.databricks.com/aws/en/udf/unity-catalog) to run predefined SQL and custom business logic as governed, reusable tools.
+  </Card>
+  <Card title="Vector Search" icon="magnifying-glass">
+    Retrieve relevant documents for RAG and knowledge workflows from [Mosaic AI Vector Search](https://docs.databricks.com/aws/en/generative-ai/vector-search) indexes using semantic similarity.
+  </Card>
+</CardGroup>
+
+Every server runs behind the Unity AI Gateway and enforces Unity Catalog access controls, so your agents only ever see the data and tools they're permitted to use.
+
+## Prerequisites
+
+Before using the Databricks integration, ensure you have:
+
+- A [CrewAI AMP](https://app.crewai.com) account with an active subscription
+- A Databricks workspace with the capabilities you want to expose (Genie Spaces, SQL warehouses, Unity Catalog functions, or Vector Search indexes)
+- Appropriate [Unity Catalog privileges](https://docs.databricks.com/aws/en/data-governance/unity-catalog) on the underlying objects
+- Your Databricks workspace hostname (e.g. `your-workspace.cloud.databricks.com`)
+
+## Databricks Managed MCP Servers
+
+Databricks publishes a separate managed MCP server for each capability. CrewAI exposes these as individual connections, each configured with your workspace host and the relevant Unity Catalog identifiers. The endpoints follow these patterns:
+
+| Server | What it does | MCP URL pattern |
+|--------|--------------|-----------------|
+| **Genie** | Natural-language Q&A over a Genie Space | `https://<workspace-hostname>/api/2.0/mcp/genie/{genie_space_id}` |
+| **Databricks SQL** | Execute SQL against your warehouses | `https://<workspace-hostname>/api/2.0/mcp/sql` |
+| **Unity Catalog Functions** | Run registered UC functions | `https://<workspace-hostname>/api/2.0/mcp/functions/{catalog}/{schema}` |
+| **Vector Search** | Query a Vector Search index | `https://<workspace-hostname>/api/2.0/mcp/vector-search/{catalog}/{schema}` |
+
+<Note>
+You don't construct these URLs by hand — CrewAI builds each endpoint from the workspace host and identifiers (Genie Space ID, or catalog/schema) you provide when configuring the connection. For the full specification and the latest endpoint details, see the [Databricks managed MCP documentation](https://docs.databricks.com/aws/en/generative-ai/mcp/managed-mcp).
+</Note>
+
+## Connecting Databricks in CrewAI AMP
+
+<Frame>
+    <img src="/images/enterprise/databricks-configure.png" alt="Configure a Databricks managed MCP server in CrewAI AMP" />
+</Frame>
+
+Each Databricks capability — **Databricks Genie**, **Databricks SQL**, **Databricks Unity Catalog Functions**, and **Databricks Vector Search** — appears as its own MCP server under the Databricks group on the **Tools & Integrations** page. Configure the ones you need:
+
+<Steps>
+    <Step title="Open Tools & Integrations">
+        Navigate to **Tools & Integrations** in the left sidebar of CrewAI AMP and locate the **Databricks** group in the Connections list. You'll see the Genie, SQL, Unity Catalog Functions, and Vector Search servers listed beneath it.
+    </Step>
+
+    <Step title="Configure a server">
+        Click **Configure** next to the capability you want to enable and provide its connection details:
+
+        - **Workspace Host** — your Databricks workspace hostname (e.g. `my-workspace.cloud.databricks.com`).
+        - **Genie** — the **Genie Space ID** to query.
+        - **Unity Catalog Functions** — the **catalog** and **schema** that contain your functions.
+        - **Vector Search** — the **catalog** and **schema** that contain your index.
+        - **Databricks SQL** — no additional identifiers; queries run against your workspace's SQL warehouses.
+    </Step>
+
+    <Step title="Choose an authentication method">
+        Select how CrewAI authenticates to Databricks. **OAuth** is recommended.
+
+        - **Use OAuth** — Connect securely using OAuth 2.0. Each user authenticates individually, and Databricks issues tokens scoped to the capability (`genie`, `sql`, `unity-catalog`, or `vector-search`). CrewAI handles the authorization flow and refreshes tokens automatically.
+        - **Use personal access token** — Authenticate with a [Databricks personal access token](https://docs.databricks.com/aws/en/dev-tools/auth/pat). Use a least-privileged identity to limit exposure.
+    </Step>
+
+    <Step title="Authenticate">
+        Complete authentication. Once connected, the server's tools become available to your crews. Repeat for any other Databricks capabilities you want to enable.
+    </Step>
+</Steps>
+
+<Tip>
+Because each capability is a separate connection, you can mix and match — for example, enable Genie and Vector Search for a research crew while reserving SQL and Unity Catalog Functions for a data-engineering crew. Visibility settings let you control which team members can use each one.
+</Tip>
+
+## Using Databricks Tools in Your Crews
+
+Once connected, the tools each MCP server exposes appear alongside built-in connections on the **Tools & Integrations** page. You can:
+
+- **Assign tools to agents** in your crews just like any other CrewAI tool.
+- **Manage visibility** to control which team members can use each connection.
+- **Edit or remove** any connection at any time from the Connections list.
+
+Your agents can now ask Genie for grounded answers, run SQL against your warehouses, call Unity Catalog functions, and search Vector Search indexes — with results flowing back into their reasoning automatically.
+
+<Warning>
+Databricks enforces governance through Unity Catalog and the Unity AI Gateway: a user can only discover and invoke tools their workspace identity is permitted to use. If a tool call fails, confirm the connecting user (or token identity) has the required Unity Catalog privileges on the Genie Space, warehouse, function, or index. Some Genie and SQL queries run asynchronously and may take a moment to return results.
+</Warning>
+
+## Learn More
+
+<CardGroup cols={2}>
+  <Card title="Databricks Managed MCP Servers" icon="layer-group" href="https://docs.databricks.com/aws/en/generative-ai/mcp/managed-mcp">
+    Official Databricks documentation for the managed Genie, SQL, Unity Catalog Functions, and Vector Search MCP servers.
+  </Card>
+  <Card title="Custom MCP Servers in CrewAI" icon="plug" href="/en/enterprise/guides/custom-mcp-server">
+    Learn how CrewAI connects to any MCP server, the foundation the Databricks integration builds on.
+  </Card>
+</CardGroup>
+
+<Card title="Need Help?" icon="headset" href="mailto:support@crewai.com">
+  Contact our support team for assistance with the Databricks integration or troubleshooting.
+</Card>

docs/en/enterprise/integrations/snowflake.mdx

@@ -0,0 +1,134 @@
+---
+title: Snowflake Integration
+description: "Connect CrewAI agents to Snowflake Cortex Analyst, Cortex Search, and SQL execution through the Snowflake-managed MCP server."
+icon: "snowflake"
+mode: "wide"
+---
+
+## Overview
+
+Connect your CrewAI agents directly to your Snowflake data through the [Snowflake-managed MCP server](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp). The Snowflake integration lets your agents query structured data with **Cortex Analyst**, search unstructured data with **Cortex Search**, and run governed SQL against your warehouses — all without writing or hosting any connector code.
+
+Under the hood, the Snowflake integration is a managed wrapper around CrewAI's [Custom MCP Server](/en/enterprise/guides/custom-mcp-server) support. Snowflake exposes its Cortex AI capabilities through a [Model Context Protocol](https://modelcontextprotocol.io/) endpoint, and CrewAI connects to it securely on your behalf. Any tool you expose on the Snowflake side — Cortex Analyst, Cortex Search, SQL execution, Cortex Agents, or your own custom tools — becomes available to your crews.
+
+## Key Capabilities
+
+<CardGroup cols={3}>
+  <Card title="Cortex Analyst" icon="chart-bar">
+    Ask questions in natural language and let [Cortex Analyst](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-analyst) generate and run SQL against your **structured** data using rich semantic models.
+  </Card>
+  <Card title="Cortex Search" icon="magnifying-glass">
+    Retrieve relevant **unstructured** data for RAG and knowledge workflows with [Cortex Search](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-search/cortex-search-overview), Snowflake's fully managed search service.
+  </Card>
+  <Card title="SQL Execution" icon="database">
+    Run governed SQL queries directly against your Snowflake warehouses, with configurable read-only mode, timeouts, and warehouse selection.
+  </Card>
+</CardGroup>
+
+Because the integration surfaces whatever tools your MCP server publishes, you can also expose **Cortex Agents** and **custom tools** (user-defined functions and stored procedures) to your CrewAI agents.
+
+## Prerequisites
+
+Before using the Snowflake integration, ensure you have:
+
+- A [CrewAI AMP](https://app.crewai.com) account with an active subscription
+- A Snowflake account with access to Cortex AI features
+- A [Snowflake-managed MCP server](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp) configured with the tools you want to expose
+- Appropriate Snowflake privileges (USAGE/SELECT) on the MCP server and its underlying objects
+
+## Setting Up the Snowflake MCP Server
+
+The Snowflake-managed MCP server runs inside your Snowflake account and defines which tools are available to external clients like CrewAI. Create one with the [`CREATE MCP SERVER`](https://docs.snowflake.com/en/sql-reference/sql/create-mcp-server) command, listing the Cortex Search services, Cortex Analyst semantic views, and SQL tools you want to expose.
+
+```sql
+CREATE MCP SERVER my_mcp_server
+  FROM SPECIFICATION $$
+    tools:
+      - name: "sales_analyst"
+        type: "CORTEX_ANALYST"
+        identifier: "MY_DATABASE.MY_SCHEMA.sales_semantic_view"
+        description: "Answer questions about sales metrics"
+      - name: "docs_search"
+        type: "CORTEX_SEARCH_SERVICE_QUERY"
+        identifier: "MY_DATABASE.MY_SCHEMA.support_docs_search"
+        description: "Search internal support documentation"
+      - name: "run_sql"
+        type: "SQL_EXECUTION"
+        description: "Execute read-only SQL queries"
+  $$;
+```
+
+<Note>
+The MCP endpoint follows the format `https://<account_URL>/api/v2/databases/{database}/schemas/{schema}/mcp-servers/{name}`. CrewAI builds this URL automatically from the **Account URL**, **Database**, **Schema**, and **MCP Server Name** you provide when configuring the integration.
+</Note>
+
+For the complete specification — including Cortex Agents, custom tools, response-size limits, and governance options — see the [Snowflake-managed MCP server documentation](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp).
+
+## Connecting Snowflake in CrewAI AMP
+
+<Frame>
+    <img src="/images/enterprise/snowflake-configure.png" alt="Configure Snowflake integration in CrewAI AMP" />
+</Frame>
+
+<Steps>
+    <Step title="Open Tools & Integrations">
+        Navigate to **Tools & Integrations** in the left sidebar of CrewAI AMP, find **Snowflake** in the list of applications, and open its configuration panel.
+    </Step>
+
+    <Step title="Provide connection details">
+        Fill in the connection fields that CrewAI uses to reach your Snowflake MCP server:
+
+        | Field | Required | Description |
+        |-------|----------|-------------|
+        | **Name** | Yes | A descriptive name for this connection (defaults to `Snowflake`). |
+        | **Description** | No | An optional summary of what this connection provides. |
+        | **Account URL** | Yes | Your Snowflake account URL, e.g. `xy12345.us-east-1.snowflakecomputing.com`. |
+        | **Database** | Yes | The database that contains your MCP server (e.g. `MY_DATABASE`). |
+        | **Schema** | Yes | The schema that contains your MCP server (e.g. `MY_SCHEMA`). |
+        | **MCP Server Name** | Yes | The name of the MCP server object you created in Snowflake (e.g. `MY_MCP_SERVER`). |
+    </Step>
+
+    <Step title="Choose an authentication method">
+        Select how CrewAI authenticates to Snowflake. **OAuth** is recommended.
+
+        - **Use OAuth** — Connect securely using OAuth 2.0 for token-based authentication without sharing your credentials. CrewAI handles the full authorization flow and refreshes tokens automatically. Copy the **Redirect URI** shown in the form (`https://oauth.crewai.com/oauth/add`) and register it as an authorized redirect URI in your Snowflake [OAuth security integration](https://docs.snowflake.com/en/user-guide/oauth-custom).
+        - **Use personal access token** — Authenticate using a [programmatic access token](https://docs.snowflake.com/en/user-guide/programmatic-access-tokens) generated from your Snowflake account settings. Assign a least-privileged role to the token to limit exposure.
+    </Step>
+
+    <Step title="Authenticate">
+        Click **Authenticate**. For OAuth, you'll be redirected to Snowflake to authorize access. Once authenticated, the Snowflake server appears in your Connections and its tools become available to your crews.
+    </Step>
+</Steps>
+
+<Tip>
+With OAuth, each user authenticates individually and queries run with their Snowflake `DEFAULT_ROLE`. Make sure connecting users have a default role and warehouse set (`ALTER USER <username> SET DEFAULT_ROLE = '<role>' DEFAULT_WAREHOUSE = '<warehouse>'`) so Cortex Analyst and SQL tools have compute to run on.
+</Tip>
+
+## Using Snowflake Tools in Your Crews
+
+Once connected, the tools your MCP server exposes appear alongside built-in connections on the **Tools & Integrations** page. You can:
+
+- **Assign tools to agents** in your crews just like any other CrewAI tool.
+- **Manage visibility** to control which team members can use the connection.
+- **Edit or remove** the connection at any time from the Connections list.
+
+Your agents can now ask Cortex Analyst for metrics, run Cortex Search over your documents, and execute SQL — with results flowing back into their reasoning automatically.
+
+<Warning>
+Snowflake enforces governance on the MCP server: role-based access control determines which tools a user can discover and invoke, and limits apply to response size, tool count (max 50 per server), and recursion depth. If a tool call fails, confirm the connecting user's role has the required privileges on the MCP server and its underlying objects.
+</Warning>
+
+## Learn More
+
+<CardGroup cols={2}>
+  <Card title="Snowflake-managed MCP Server" icon="snowflake" href="https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp">
+    Official Snowflake documentation for creating and governing the MCP server.
+  </Card>
+  <Card title="Custom MCP Servers in CrewAI" icon="plug" href="/en/enterprise/guides/custom-mcp-server">
+    Learn how CrewAI connects to any MCP server, the foundation the Snowflake integration builds on.
+  </Card>
+</CardGroup>
+
+<Card title="Need Help?" icon="headset" href="mailto:support@crewai.com">
+  Contact our support team for assistance with the Snowflake integration or troubleshooting.
+</Card>

docs/ko/changelog.mdx

@@ -4,6 +4,44 @@ description: "CrewAI의 제품 업데이트, 개선 사항 및 버그 수정"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="2026년 5월 28일">
+  ## v1.14.6
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.6)
+
+  ## 변경 사항
+
+  ### 기능
+  - 환경 변수 유출을 방지하기 위해 StdioTransport 강화
+  - 계획 구성 및 관찰 처리 개선
+  - DatabricksQueryTool에서 env_vars 선언
+  - 에이전트 제어 평면 문서 추가
+
+  ### 버그 수정
+  - 도구 호출 루프에서 구조화된 출력 유출 수정
+  - 체크포인트에서 원형으로 돌아갈 수 없는 콜백 및 어댑터 상태 제거
+  - 체크포인트에서 type[BaseModel] 필드를 JSON 스키마로 직렬화
+  - 복원 범위 복원 시 고아 task_started 방지
+  - AgentExecutor가 체크포인트에서 복원할 수 있도록 허용
+  - package_dependencies에서 mongodb 오타를 pymongo로 수정
+
+  ### 문서
+  - 에이전트 제어 평면 페이지에 ACP (Beta) 문서 탐색 블록 추가
+  - 프로세스 페이지에서 합의 프로세스 참조 제거
+  - 체크포인트 페이지 구조 재편성
+  - 일회성 관리자 패키지 설치 단계 문서화
+  - Secrets Manager / Workload Identity를 replicated-config에서 마이그레이션
+  - `<Steps>` 렌더링을 방해하는 `{" "}` JSX 표현 제거
+
+  ### 리팩토링
+  - Skills Repository를 실험적 + CREWAI_EXPERIMENTAL 게이트로 이동
+
+  ## 기여자
+
+  @akaKuruma, @alex-clawd, @github-actions[bot], @greysonlalonde, @heitorado, @iris-clawd, @lorenzejay, @lucasgomide, @mattatcha, @thiagomoretto, @vinibrsl
+
+</Update>
+
 <Update label="2026년 5월 27일">
   ## v1.14.6a2
 

docs/ko/concepts/llms.mdx

@@ -106,7 +106,7 @@ CrewAI 코드 내에는 사용할 모델을 지정할 수 있는 여러 위치
 </Tabs>
 
 <Info>
-  CrewAI는 OpenAI, Anthropic, Google (Gemini API), Azure, AWS Bedrock에 대해 네이티브 SDK 통합을 제공합니다 — 제공자별 extras(예: `uv add "crewai[openai]"`) 외에 추가 설치가 필요하지 않습니다.
+  CrewAI는 OpenAI, Anthropic, Google (Gemini API), Azure, AWS Bedrock, Snowflake Cortex에 대해 네이티브 SDK 통합을 제공합니다 — 제공자별 extras(예: `uv add "crewai[openai]"`) 외에 추가 설치가 필요하지 않습니다.
 
   그 외 모든 제공자는 **LiteLLM**을 통해 지원됩니다. 이를 사용하려면 프로젝트에 의존성으로 추가하세요:
   ```bash
@@ -230,6 +230,55 @@ CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양
     ```
   </Accordion>
 
+  <Accordion title="Snowflake Cortex">
+    CrewAI는 OpenAI 호환 Chat Completions 엔드포인트를 통해 Snowflake Cortex REST API와 네이티브로 통합됩니다. `snowflake/...` 모델은 LiteLLM fallback 없이 사용됩니다. CrewAI에서 Snowflake Cortex는 현재 Chat Completions만 지원하므로 기본 `api` 모드를 사용하고 `api="responses"`를 설정하지 마세요.
+
+    ```toml Code
+    # Required
+    SNOWFLAKE_PAT=<your-programmatic-access-token>
+    SNOWFLAKE_ACCOUNT_URL=https://<account-identifier>.snowflakecomputing.com
+
+    # Alternative account configuration
+    SNOWFLAKE_ACCOUNT=<account-identifier>
+    ```
+
+    **기본 사용법:**
+    ```python Code
+    from crewai import LLM
+
+    llm = LLM(
+        model="snowflake/openai-gpt-4.1",
+        temperature=0.7,
+        max_completion_tokens=1024,
+    )
+    ```
+
+    **Cortex의 Claude 모델:**
+    ```python Code
+    from crewai import LLM
+
+    llm = LLM(
+        model="snowflake/claude-sonnet-4-5",
+        max_completion_tokens=1024,
+        stream=True,
+    )
+    ```
+
+    **지원 환경 변수:**
+    - `SNOWFLAKE_PAT`, `SNOWFLAKE_TOKEN`, 또는 `SNOWFLAKE_JWT`: Bearer 자격 증명으로 사용할 토큰
+    - `SNOWFLAKE_ACCOUNT_URL`: 전체 Snowflake 계정 URL
+    - `SNOWFLAKE_ACCOUNT`, `SNOWFLAKE_ACCOUNT_ID`, 또는 `SNOWFLAKE_ACCOUNT_IDENTIFIER`: 계정 URL을 만들 계정 식별자
+
+    Snowflake REST 요청은 사용자의 기본 Snowflake role을 사용합니다. 해당 role에 `SNOWFLAKE.CORTEX_USER` 또는 `SNOWFLAKE.CORTEX_REST_API_USER`가 있는지 확인하세요. Cortex REST Chat Completions 엔드포인트에는 database, schema, warehouse, 명시적 role 파라미터가 필요하지 않습니다.
+
+    **기능:**
+    - `model="snowflake/<model-name>"`을 통한 네이티브 provider 선택
+    - Streaming 및 non-streaming Chat Completions만 지원; `api="responses"`는 지원되지 않음
+    - 토큰 사용량 추적
+    - Snowflake 호스팅 OpenAI 및 Claude 모델의 함수 호출
+    - Snowflake Claude 모델에서 유효하지 않은 마지막 assistant prefill 자동 제거
+  </Accordion>
+
   <Accordion title="Anthropic">
     ```toml Code
     # Required

docs/ko/concepts/processes.mdx

@@ -16,7 +16,6 @@ mode: "wide"
 
 - **순차적(Sequential)**: 작업을 순차적으로 실행하여 작업이 질서 있게 진행되도록 보장합니다.
 - **계층적(Hierarchical)**: 작업을 관리 계층 구조로 조직하며, 작업은 체계적인 명령 체계를 기반으로 위임 및 실행됩니다. 계층적 프로세스를 활성화하려면 매니저 언어 모델(`manager_llm`) 또는 커스텀 매니저 에이전트(`manager_agent`)를 crew에서 지정해야 하며, 이를 통해 매니저가 작업을 생성하고 관리할 수 있도록 지원합니다.
-- **합의 프로세스(Consensual Process, 계획됨)**: 에이전트들 간에 작업 실행에 대한 협력적 의사결정을 목표로 하며, 이 프로세스 유형은 CrewAI 내에서 작업 관리를 민주적으로 접근하도록 도입됩니다. 앞으로 개발될 예정이며, 현재 코드베이스에는 구현되어 있지 않습니다.
 
 ## 팀워크에서 프로세스의 역할
 프로세스는 개별 에이전트가 통합된 단위로 작동할 수 있도록 하여, 공통된 목표를 효율적이고 일관성 있게 달성하도록 노력하는 과정을 간소화합니다.
@@ -59,9 +58,9 @@ crew = Crew(
 
 ## Process 클래스: 상세 개요
 
-`Process` 클래스는 열거형(`Enum`)으로 구현되어 타입 안전성을 보장하며, 프로세스 값을 정의된 타입(`sequential`, `hierarchical`)으로 제한합니다. 합의 기반(consensual) 프로세스는 향후 추가될 예정이며, 이는 지속적인 개발과 혁신에 대한 우리의 의지를 강조합니다.
+`Process` 클래스는 열거형(`Enum`)으로 구현되어 타입 안전성을 보장하며, 프로세스 값을 정의된 타입(`sequential`, `hierarchical`)으로 제한합니다.
 
 ## 결론
 
 CrewAI 내의 프로세스를 통해 촉진되는 구조화된 협업은 에이전트 간 체계적인 팀워크를 가능하게 하는 데 매우 중요합니다.  
-이 문서는 최신 기능, 향상 사항, 그리고 예정된 Consensual Process 통합을 반영하도록 업데이트되었으며, 사용자가 가장 최신이고 포괄적인 정보를 이용할 수 있도록 보장합니다.
+이 문서는 최신 기능과 향상 사항을 반영하도록 업데이트되었으며, 사용자가 가장 최신이고 포괄적인 정보를 이용할 수 있도록 보장합니다.

docs/ko/enterprise/features/agent-control-plane/monitoring.mdx

@@ -6,6 +6,14 @@ icon: "gauge"
 mode: "wide"
 ---
 
+<Info>
+  **ACP (베타) 문서 내비게이션**
+
+  - [개요](/ko/enterprise/features/agent-control-plane/overview)
+  - **모니터링** *(현재 페이지)*
+  - [규칙](/ko/enterprise/features/agent-control-plane/rules)
+</Info>
+
 ## 개요
 
 **Automations** 탭은 [Agent Control Plane](/ko/enterprise/features/agent-control-plane/overview)의 읽기 전용 운영 뷰입니다. 두 개의 메트릭 카드, 인터랙티브 sankey, 그리고 **Automations**와 **Consumption** 두 개의 서브 테이블을 결합해 검색·필터·정렬을 지원합니다.

docs/ko/enterprise/features/agent-control-plane/overview.mdx

@@ -5,6 +5,14 @@ sidebarTitle: 개요
 icon: "book-open"
 ---
 
+<Info>
+  **ACP (베타) 문서 내비게이션**
+
+  - **개요** *(현재 페이지)*
+  - [모니터링](/ko/enterprise/features/agent-control-plane/monitoring)
+  - [규칙](/ko/enterprise/features/agent-control-plane/rules)
+</Info>
+
 ## 개요
 
 **Agent Control Plane**(ACP)은 CrewAI AMP에서 실행 중인 모든 워크로드를 위한 운영 허브입니다. **Automations**와 **Rules** 두 개의 탭으로 구성된 단일 화면에서 다음 작업을 할 수 있습니다:

docs/ko/enterprise/features/agent-control-plane/rules.mdx

@@ -6,6 +6,14 @@ icon: "shield-check"
 mode: "wide"
 ---
 
+<Info>
+  **ACP (베타) 문서 내비게이션**
+
+  - [개요](/ko/enterprise/features/agent-control-plane/overview)
+  - [모니터링](/ko/enterprise/features/agent-control-plane/monitoring)
+  - **규칙** *(현재 페이지)*
+</Info>
+
 ## 개요
 
 규칙(Rules)은 각 deployment를 개별 설정하는 대신, 정책 — 현재: **PII Redaction** — 을 한 번에 여러 자동화에 적용할 수 있게 해줍니다. 관리하려면 [Agent Control Plane](/ko/enterprise/features/agent-control-plane/overview)에서 **Rules** 탭을 엽니다.

docs/ko/enterprise/integrations/databricks.mdx

@@ -0,0 +1,123 @@
+---
+title: Databricks 연동
+description: "Databricks 관리형 MCP 서버를 통해 CrewAI 에이전트를 Databricks Genie, SQL, Unity Catalog Functions, Vector Search에 연결하세요."
+icon: "layer-group"
+mode: "wide"
+---
+
+## 개요
+
+[Databricks 관리형 MCP 서버](https://docs.databricks.com/aws/en/generative-ai/mcp/managed-mcp)를 통해 CrewAI 에이전트를 Databricks 워크스페이스에 직접 연결하세요. Databricks 연동을 사용하면 에이전트가 **Genie**로 자연어 질문을 하고, 거버넌스가 적용된 **SQL**을 실행하며, **Unity Catalog Functions**를 호출하고, **Vector Search**로 문서를 검색할 수 있습니다. 커넥터 코드를 작성하거나 호스팅할 필요가 없으며, 모든 호출에 Unity Catalog 권한이 적용됩니다.
+
+내부적으로 Databricks 연동은 CrewAI의 [커스텀 MCP 서버](/ko/enterprise/guides/custom-mcp-server) 지원을 감싼 관리형 래퍼입니다. Databricks는 각 기능을 개별 [Model Context Protocol](https://modelcontextprotocol.io/) 엔드포인트로 노출하며, CrewAI가 사용자를 대신해 안전하게 연결합니다. 각 서버를 개별적으로 추가하므로 크루에 필요한 기능만 정확히 활성화할 수 있습니다.
+
+## 주요 기능
+
+<CardGroup cols={2}>
+  <Card title="Genie" icon="comments">
+    [Genie](https://docs.databricks.com/aws/en/genie/)로 자연어 질문을 하고 데이터 기반의 근거 있는 답변을 받으세요. Genie는 Genie Spaces와 Unity Catalog를 조회하고 Databricks UI로 연결되는 링크를 제공합니다.
+  </Card>
+  <Card title="Databricks SQL" icon="database">
+    에이전트에서 직접 Databricks 웨어하우스에 거버넌스가 적용된 SQL을 실행하여 데이터를 조회, 변환하고 데이터 파이프라인을 작성하세요.
+  </Card>
+  <Card title="Unity Catalog Functions" icon="function">
+    [Unity Catalog 함수](https://docs.databricks.com/aws/en/udf/unity-catalog)를 호출하여 사전 정의된 SQL과 맞춤형 비즈니스 로직을 거버넌스가 적용된 재사용 가능한 도구로 실행하세요.
+  </Card>
+  <Card title="Vector Search" icon="magnifying-glass">
+    [Mosaic AI Vector Search](https://docs.databricks.com/aws/en/generative-ai/vector-search) 인덱스에서 의미 유사도를 사용해 RAG 및 지식 워크플로우에 필요한 관련 문서를 검색하세요.
+  </Card>
+</CardGroup>
+
+모든 서버는 Unity AI Gateway 뒤에서 실행되며 Unity Catalog 접근 제어를 적용하므로, 에이전트는 허용된 데이터와 도구만 볼 수 있습니다.
+
+## 사전 준비사항
+
+Databricks 연동을 사용하기 전에 다음을 준비해야 합니다:
+
+- 활성 구독이 있는 [CrewAI AMP](https://app.crewai.com) 계정
+- 노출하려는 기능이 있는 Databricks 워크스페이스(Genie Spaces, SQL 웨어하우스, Unity Catalog 함수 또는 Vector Search 인덱스)
+- 기본 객체에 대한 적절한 [Unity Catalog 권한](https://docs.databricks.com/aws/en/data-governance/unity-catalog)
+- Databricks 워크스페이스 호스트명(예: `your-workspace.cloud.databricks.com`)
+
+## Databricks 관리형 MCP 서버
+
+Databricks는 각 기능마다 별도의 관리형 MCP 서버를 게시합니다. CrewAI는 이를 개별 연결로 노출하며, 각 연결은 워크스페이스 호스트와 관련 Unity Catalog 식별자로 구성됩니다. 엔드포인트는 다음 패턴을 따릅니다:
+
+| 서버 | 기능 | MCP URL 패턴 |
+|------|------|--------------|
+| **Genie** | Genie Space에 대한 자연어 Q&A | `https://<workspace-hostname>/api/2.0/mcp/genie/{genie_space_id}` |
+| **Databricks SQL** | 웨어하우스에 SQL 실행 | `https://<workspace-hostname>/api/2.0/mcp/sql` |
+| **Unity Catalog Functions** | 등록된 UC 함수 실행 | `https://<workspace-hostname>/api/2.0/mcp/functions/{catalog}/{schema}` |
+| **Vector Search** | Vector Search 인덱스 조회 | `https://<workspace-hostname>/api/2.0/mcp/vector-search/{catalog}/{schema}` |
+
+<Note>
+이러한 URL을 직접 만들 필요는 없습니다. CrewAI는 연결을 구성할 때 입력한 워크스페이스 호스트와 식별자(Genie Space ID 또는 catalog/schema)로 각 엔드포인트를 생성합니다. 전체 사양과 최신 엔드포인트 세부 정보는 [Databricks 관리형 MCP 문서](https://docs.databricks.com/aws/en/generative-ai/mcp/managed-mcp)를 참고하세요.
+</Note>
+
+## CrewAI AMP에서 Databricks 연결하기
+
+<Frame>
+    <img src="/images/enterprise/databricks-configure.png" alt="CrewAI AMP에서 Databricks 관리형 MCP 서버 구성" />
+</Frame>
+
+각 Databricks 기능(**Databricks Genie**, **Databricks SQL**, **Databricks Unity Catalog Functions**, **Databricks Vector Search**)은 **Tools & Integrations** 페이지의 Databricks 그룹 아래에 별도의 MCP 서버로 표시됩니다. 필요한 것을 구성하세요:
+
+<Steps>
+    <Step title="Tools & Integrations 열기">
+        CrewAI AMP 왼쪽 사이드바에서 **Tools & Integrations**로 이동하여 Connections 목록에서 **Databricks** 그룹을 찾습니다. 그 아래에 Genie, SQL, Unity Catalog Functions, Vector Search 서버가 나열됩니다.
+    </Step>
+
+    <Step title="서버 구성하기">
+        활성화하려는 기능 옆의 **Configure**를 클릭하고 연결 세부 정보를 입력합니다:
+
+        - **Workspace Host** — Databricks 워크스페이스 호스트명(예: `my-workspace.cloud.databricks.com`).
+        - **Genie** — 조회할 **Genie Space ID**.
+        - **Unity Catalog Functions** — 함수가 포함된 **catalog**와 **schema**.
+        - **Vector Search** — 인덱스가 포함된 **catalog**와 **schema**.
+        - **Databricks SQL** — 추가 식별자가 필요 없으며, 쿼리는 워크스페이스의 SQL 웨어하우스에서 실행됩니다.
+    </Step>
+
+    <Step title="인증 방법 선택하기">
+        CrewAI가 Databricks에 인증하는 방법을 선택합니다. **OAuth**를 권장합니다.
+
+        - **Use OAuth** — OAuth 2.0으로 안전하게 연결합니다. 각 사용자가 개별적으로 인증하며, Databricks는 해당 기능(`genie`, `sql`, `unity-catalog` 또는 `vector-search`)으로 범위가 지정된 토큰을 발급합니다. CrewAI가 인증 흐름을 처리하고 토큰을 자동으로 갱신합니다.
+        - **Use personal access token** — [Databricks 개인 액세스 토큰](https://docs.databricks.com/aws/en/dev-tools/auth/pat)으로 인증합니다. 노출을 제한하려면 최소 권한 ID를 사용하세요.
+    </Step>
+
+    <Step title="인증하기">
+        인증을 완료합니다. 연결되면 해당 서버의 도구를 크루에서 사용할 수 있습니다. 활성화하려는 다른 Databricks 기능에 대해서도 반복합니다.
+    </Step>
+</Steps>
+
+<Tip>
+각 기능이 별도의 연결이므로 자유롭게 조합할 수 있습니다. 예를 들어 리서치 크루에는 Genie와 Vector Search를 활성화하고, 데이터 엔지니어링 크루에는 SQL과 Unity Catalog Functions를 사용하도록 할 수 있습니다. 가시성(Visibility) 설정으로 각 기능을 사용할 수 있는 팀원을 제어할 수 있습니다.
+</Tip>
+
+## 크루에서 Databricks 도구 사용하기
+
+연결되면 각 MCP 서버가 노출하는 도구가 **Tools & Integrations** 페이지의 기본 제공 연결과 함께 표시됩니다. 다음을 할 수 있습니다:
+
+- 다른 CrewAI 도구와 마찬가지로 크루의 에이전트에 **도구 할당**.
+- 각 연결을 사용할 수 있는 팀원을 제어하는 **가시성 관리**.
+- Connections 목록에서 언제든지 연결 **편집 또는 제거**.
+
+이제 에이전트는 Genie에 근거 있는 답변을 요청하고, 웨어하우스에 SQL을 실행하며, Unity Catalog 함수를 호출하고, Vector Search 인덱스를 검색할 수 있으며, 그 결과가 자동으로 추론에 반영됩니다.
+
+<Warning>
+Databricks는 Unity Catalog와 Unity AI Gateway를 통해 거버넌스를 적용합니다. 사용자는 워크스페이스 ID에 허용된 도구만 검색하고 호출할 수 있습니다. 도구 호출이 실패하면 연결하는 사용자(또는 토큰 ID)가 Genie Space, 웨어하우스, 함수 또는 인덱스에 필요한 Unity Catalog 권한을 가지고 있는지 확인하세요. 일부 Genie 및 SQL 쿼리는 비동기로 실행되어 결과를 반환하는 데 시간이 걸릴 수 있습니다.
+</Warning>
+
+## 더 알아보기
+
+<CardGroup cols={2}>
+  <Card title="Databricks 관리형 MCP 서버" icon="layer-group" href="https://docs.databricks.com/aws/en/generative-ai/mcp/managed-mcp">
+    관리형 Genie, SQL, Unity Catalog Functions, Vector Search MCP 서버에 대한 공식 Databricks 문서입니다.
+  </Card>
+  <Card title="CrewAI의 커스텀 MCP 서버" icon="plug" href="/ko/enterprise/guides/custom-mcp-server">
+    Databricks 연동의 기반이 되는, CrewAI가 모든 MCP 서버에 연결하는 방법을 알아보세요.
+  </Card>
+</CardGroup>
+
+<Card title="도움이 필요하신가요?" icon="headset" href="mailto:support@crewai.com">
+  Databricks 연동 구성 또는 문제 해결에 대한 지원이 필요하면 지원팀에 문의하세요.
+</Card>

docs/ko/enterprise/integrations/snowflake.mdx

@@ -0,0 +1,134 @@
+---
+title: Snowflake 연동
+description: "Snowflake 관리형 MCP 서버를 통해 CrewAI 에이전트를 Snowflake Cortex Analyst, Cortex Search 및 SQL 실행에 연결합니다."
+icon: "snowflake"
+mode: "wide"
+---
+
+## 개요
+
+[Snowflake 관리형 MCP 서버](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp)를 통해 CrewAI 에이전트를 Snowflake 데이터에 직접 연결하세요. Snowflake 연동을 사용하면 에이전트가 **Cortex Analyst**로 구조화된 데이터를 쿼리하고, **Cortex Search**로 비구조화된 데이터를 검색하며, 커넥터 코드를 작성하거나 호스팅할 필요 없이 웨어하우스에 대해 관리되는 SQL을 실행할 수 있습니다.
+
+내부적으로 Snowflake 연동은 CrewAI의 [Custom MCP Server](/ko/enterprise/guides/custom-mcp-server) 지원을 기반으로 하는 관리형 래퍼입니다. Snowflake는 [Model Context Protocol](https://modelcontextprotocol.io/) 엔드포인트를 통해 Cortex AI 기능을 노출하며, CrewAI가 이를 안전하게 연결합니다. Snowflake 측에서 노출하는 모든 도구 — Cortex Analyst, Cortex Search, SQL 실행, Cortex Agents 또는 사용자 정의 도구 — 가 크루에서 사용할 수 있게 됩니다.
+
+## 주요 기능
+
+<CardGroup cols={3}>
+  <Card title="Cortex Analyst" icon="chart-bar">
+    자연어로 질문하고 [Cortex Analyst](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-analyst)가 풍부한 시맨틱 모델을 사용하여 **구조화된** 데이터에 대해 SQL을 생성하고 실행하도록 합니다.
+  </Card>
+  <Card title="Cortex Search" icon="magnifying-glass">
+    Snowflake의 완전 관리형 검색 서비스인 [Cortex Search](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-search/cortex-search-overview)를 사용하여 RAG 및 지식 워크플로우를 위한 관련 **비구조화된** 데이터를 검색합니다.
+  </Card>
+  <Card title="SQL 실행" icon="database">
+    구성 가능한 읽기 전용 모드, 타임아웃 및 웨어하우스 선택을 통해 Snowflake 웨어하우스에 대해 관리되는 SQL 쿼리를 직접 실행합니다.
+  </Card>
+</CardGroup>
+
+연동이 MCP 서버가 게시하는 도구를 노출하므로, **Cortex Agents** 및 **사용자 정의 도구**(사용자 정의 함수 및 저장 프로시저)도 CrewAI 에이전트에 노출할 수 있습니다.
+
+## 사전 준비 사항
+
+Snowflake 연동을 사용하기 전에 다음을 확인하십시오:
+
+- 활성 구독이 있는 [CrewAI AMP](https://app.crewai.com) 계정
+- Cortex AI 기능에 액세스할 수 있는 Snowflake 계정
+- 노출하려는 도구가 구성된 [Snowflake 관리형 MCP 서버](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp)
+- MCP 서버 및 기본 객체에 대한 적절한 Snowflake 권한(USAGE/SELECT)
+
+## Snowflake MCP 서버 설정
+
+Snowflake 관리형 MCP 서버는 Snowflake 계정 내에서 실행되며 CrewAI와 같은 외부 클라이언트에서 사용할 수 있는 도구를 정의합니다. [`CREATE MCP SERVER`](https://docs.snowflake.com/en/sql-reference/sql/create-mcp-server) 명령을 사용하여 노출하려는 Cortex Search 서비스, Cortex Analyst 시맨틱 뷰 및 SQL 도구를 나열하여 생성합니다.
+
+```sql
+CREATE MCP SERVER my_mcp_server
+  FROM SPECIFICATION $$
+    tools:
+      - name: "sales_analyst"
+        type: "CORTEX_ANALYST"
+        identifier: "MY_DATABASE.MY_SCHEMA.sales_semantic_view"
+        description: "Answer questions about sales metrics"
+      - name: "docs_search"
+        type: "CORTEX_SEARCH_SERVICE_QUERY"
+        identifier: "MY_DATABASE.MY_SCHEMA.support_docs_search"
+        description: "Search internal support documentation"
+      - name: "run_sql"
+        type: "SQL_EXECUTION"
+        description: "Execute read-only SQL queries"
+  $$;
+```
+
+<Note>
+MCP 엔드포인트는 `https://<account_URL>/api/v2/databases/{database}/schemas/{schema}/mcp-servers/{name}` 형식을 따릅니다. CrewAI는 연동 구성 시 제공하는 **계정 URL**, **데이터베이스**, **스키마** 및 **MCP 서버 이름**을 사용하여 이 URL을 자동으로 구성합니다.
+</Note>
+
+Cortex Agents, 사용자 정의 도구, 응답 크기 제한 및 거버넌스 옵션을 포함한 전체 사양은 [Snowflake 관리형 MCP 서버 문서](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp)를 참조하세요.
+
+## CrewAI AMP에서 Snowflake 연결
+
+<Frame>
+    <img src="/images/enterprise/snowflake-configure.png" alt="CrewAI AMP에서 Snowflake 연동 구성" />
+</Frame>
+
+<Steps>
+    <Step title="도구 및 연동 열기">
+        CrewAI AMP 왼쪽 사이드바에서 **도구 및 연동**으로 이동하고, 애플리케이션 목록에서 **Snowflake**를 찾아 구성 패널을 엽니다.
+    </Step>
+
+    <Step title="연결 세부 정보 제공">
+        CrewAI가 Snowflake MCP 서버에 연결하는 데 사용하는 연결 필드를 채웁니다:
+
+        | 필드 | 필수 | 설명 |
+        |------|------|------|
+        | **이름** | 예 | 이 연결의 설명적 이름(기본값: `Snowflake`). |
+        | **설명** | 아니오 | 이 연결이 제공하는 내용에 대한 선택적 요약. |
+        | **계정 URL** | 예 | Snowflake 계정 URL, 예: `xy12345.us-east-1.snowflakecomputing.com`. |
+        | **데이터베이스** | 예 | MCP 서버가 포함된 데이터베이스(예: `MY_DATABASE`). |
+        | **스키마** | 예 | MCP 서버가 포함된 스키마(예: `MY_SCHEMA`). |
+        | **MCP 서버 이름** | 예 | Snowflake에서 생성한 MCP 서버 객체의 이름(예: `MY_MCP_SERVER`). |
+    </Step>
+
+    <Step title="인증 방법 선택">
+        CrewAI가 Snowflake에 인증하는 방법을 선택합니다. **OAuth**가 권장됩니다.
+
+        - **OAuth 사용** — 자격 증명을 공유하지 않고 토큰 기반 인증을 위해 OAuth 2.0을 사용하여 안전하게 연결합니다. CrewAI가 전체 인증 흐름을 처리하고 자동으로 토큰을 갱신합니다. 양식에 표시된 **리디렉트 URI**(`https://oauth.crewai.com/oauth/add`)를 복사하여 Snowflake [OAuth 보안 연동](https://docs.snowflake.com/en/user-guide/oauth-custom)에 인증된 리디렉트 URI로 등록하세요.
+        - **개인 액세스 토큰 사용** — Snowflake 계정 설정에서 생성한 [프로그래밍 방식 액세스 토큰](https://docs.snowflake.com/en/user-guide/programmatic-access-tokens)을 사용하여 인증합니다. 노출을 제한하기 위해 토큰에 최소 권한 역할을 할당하세요.
+    </Step>
+
+    <Step title="인증">
+        **인증**을 클릭합니다. OAuth의 경우 Snowflake로 리디렉션되어 액세스를 승인합니다. 인증되면 Snowflake 서버가 연결 목록에 나타나고 해당 도구를 크루에서 사용할 수 있게 됩니다.
+    </Step>
+</Steps>
+
+<Tip>
+OAuth를 사용하면 각 사용자가 개별적으로 인증하며 쿼리는 해당 Snowflake `DEFAULT_ROLE`로 실행됩니다. 연결하는 사용자에게 기본 역할과 웨어하우스가 설정되어 있는지 확인하세요(`ALTER USER <username> SET DEFAULT_ROLE = '<role>' DEFAULT_WAREHOUSE = '<warehouse>'`). 그래야 Cortex Analyst 및 SQL 도구에 실행할 컴퓨팅이 있습니다.
+</Tip>
+
+## 크루에서 Snowflake 도구 사용
+
+연결되면 MCP 서버가 노출하는 도구가 **도구 및 연동** 페이지에서 기본 연결과 함께 표시됩니다. 다음을 수행할 수 있습니다:
+
+- 다른 CrewAI 도구처럼 크루의 **에이전트에 도구를 할당**합니다.
+- **가시성을 관리**하여 어떤 팀원이 연결을 사용할 수 있는지 제어합니다.
+- 연결 목록에서 언제든지 연결을 **편집하거나 제거**합니다.
+
+이제 에이전트가 Cortex Analyst에 메트릭을 요청하고, 문서에 대해 Cortex Search를 실행하고, SQL을 실행할 수 있으며 — 결과가 자동으로 추론에 반영됩니다.
+
+<Warning>
+Snowflake는 MCP 서버에 거버넌스를 적용합니다: 역할 기반 액세스 제어가 사용자가 발견하고 호출할 수 있는 도구를 결정하며, 응답 크기, 도구 수(서버당 최대 50개) 및 재귀 깊이에 제한이 적용됩니다. 도구 호출이 실패하면 연결하는 사용자의 역할에 MCP 서버 및 기본 객체에 대한 필수 권한이 있는지 확인하세요.
+</Warning>
+
+## 자세히 알아보기
+
+<CardGroup cols={2}>
+  <Card title="Snowflake 관리형 MCP 서버" icon="snowflake" href="https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp">
+    MCP 서버를 생성하고 관리하기 위한 공식 Snowflake 문서.
+  </Card>
+  <Card title="CrewAI의 Custom MCP 서버" icon="plug" href="/ko/enterprise/guides/custom-mcp-server">
+    CrewAI가 모든 MCP 서버에 연결하는 방법을 알아보세요. Snowflake 연동이 기반으로 하는 기초입니다.
+  </Card>
+</CardGroup>
+
+<Card title="도움이 필요하신가요?" icon="headset" href="mailto:support@crewai.com">
+  Snowflake 연동 또는 문제 해결에 대해 지원팀에 문의하세요.
+</Card>

docs/pt-BR/changelog.mdx

@@ -4,6 +4,44 @@ description: "Atualizações de produto, melhorias e correções do CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="28 mai 2026">
+  ## v1.14.6
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.6)
+
+  ## O que Mudou
+
+  ### Recursos
+  - Aprimorar StdioTransport para evitar vazamento de variáveis de ambiente
+  - Aprimorar a configuração de planejamento e o manuseio de observações
+  - Declarar env_vars no DatabricksQueryTool
+  - Adicionar documentação do Agente Control Plane
+
+  ### Correções de Bugs
+  - Corrigir vazamentos de saída estruturada em loops de chamada de ferramenta
+  - Remover callbacks e estado de adaptador que não podem ser retornados em checkpoint
+  - Serializar campos type[BaseModel] como esquema JSON em checkpoint
+  - Evitar tarefa órfã task_started na restauração de escopo de retomar
+  - Permitir que AgentExecutor restaure a partir de checkpoint
+  - Corrigir erro de digitação de mongodb para pymongo em package_dependencies
+
+  ### Documentação
+  - Adicionar bloco de navegação de documentação ACP (Beta) às páginas do Agente Control Plane
+  - Remover referências a processos consensuais da página de processos
+  - Reestruturar a página de checkpointing
+  - Documentar passo de instalação do pacote administrativo único
+  - Migrar Secrets Manager / Workload Identity de replicated-config
+  - Remover expressões JSX `{" "}` que quebram a renderização de `<Steps>`
+
+  ### Refatoração
+  - Mover Skills Repository para experimental + CREWAI_EXPERIMENTAL gate
+
+  ## Contribuidores
+
+  @akaKuruma, @alex-clawd, @github-actions[bot], @greysonlalonde, @heitorado, @iris-clawd, @lorenzejay, @lucasgomide, @mattatcha, @thiagomoretto, @vinibrsl
+
+</Update>
+
 <Update label="27 mai 2026">
   ## v1.14.6a2
 

docs/pt-BR/concepts/llms.mdx

@@ -106,7 +106,7 @@ Existem diferentes locais no código do CrewAI onde você pode especificar o mod
 </Tabs>
 
 <Info>
-  O CrewAI oferece integrações nativas via SDK para OpenAI, Anthropic, Google (Gemini API), Azure e AWS Bedrock — sem necessidade de instalação extra além dos extras específicos do provedor (ex.: `uv add "crewai[openai]"`).
+  O CrewAI oferece integrações nativas via SDK para OpenAI, Anthropic, Google (Gemini API), Azure, AWS Bedrock e Snowflake Cortex — sem necessidade de instalação extra além dos extras específicos do provedor (ex.: `uv add "crewai[openai]"`).
 
   Todos os outros provedores são alimentados pelo **LiteLLM**. Se você planeja usar algum deles, adicione-o como dependência ao seu projeto:
   ```bash
@@ -230,6 +230,55 @@ Nesta seção, você encontrará exemplos detalhados que ajudam a selecionar, co
     ```
   </Accordion>
 
+  <Accordion title="Snowflake Cortex">
+    O CrewAI oferece integração nativa com a API REST do Snowflake Cortex pelo endpoint Chat Completions compatível com OpenAI. Isso evita fallback para LiteLLM em modelos `snowflake/...`. Atualmente, o Snowflake Cortex no CrewAI oferece suporte apenas a Chat Completions, então use o modo `api` padrão e não defina `api="responses"`.
+
+    ```toml Code
+    # Obrigatório
+    SNOWFLAKE_PAT=<your-programmatic-access-token>
+    SNOWFLAKE_ACCOUNT_URL=https://<account-identifier>.snowflakecomputing.com
+
+    # Configuração alternativa da conta
+    SNOWFLAKE_ACCOUNT=<account-identifier>
+    ```
+
+    **Uso básico:**
+    ```python Code
+    from crewai import LLM
+
+    llm = LLM(
+        model="snowflake/openai-gpt-4.1",
+        temperature=0.7,
+        max_completion_tokens=1024,
+    )
+    ```
+
+    **Modelos Claude no Cortex:**
+    ```python Code
+    from crewai import LLM
+
+    llm = LLM(
+        model="snowflake/claude-sonnet-4-5",
+        max_completion_tokens=1024,
+        stream=True,
+    )
+    ```
+
+    **Variáveis de ambiente suportadas:**
+    - `SNOWFLAKE_PAT`, `SNOWFLAKE_TOKEN` ou `SNOWFLAKE_JWT`: token usado como credencial Bearer
+    - `SNOWFLAKE_ACCOUNT_URL`: URL completa da conta Snowflake
+    - `SNOWFLAKE_ACCOUNT`, `SNOWFLAKE_ACCOUNT_ID` ou `SNOWFLAKE_ACCOUNT_IDENTIFIER`: identificador da conta usado para montar a URL
+
+    As requisições REST do Snowflake usam a role padrão do usuário. Garanta que essa role tenha `SNOWFLAKE.CORTEX_USER` ou `SNOWFLAKE.CORTEX_REST_API_USER`. Parâmetros de banco de dados, schema, warehouse e role explícita não são exigidos pelo endpoint Cortex REST Chat Completions.
+
+    **Recursos:**
+    - Seleção nativa com `model="snowflake/<model-name>"`
+    - Chat Completions com e sem streaming apenas; `api="responses"` não é compatível
+    - Rastreamento de uso de tokens
+    - Chamadas de função para modelos OpenAI e Claude hospedados no Snowflake
+    - Remoção automática de prefill final de assistant inválido para modelos Claude no Snowflake
+  </Accordion>
+
   <Accordion title="Anthropic">
     ```toml Code
     # Obrigatório

docs/pt-BR/concepts/processes.mdx

@@ -16,7 +16,6 @@ mode: "wide"
 
 - **Sequencial**: Executa tarefas de forma sequencial, garantindo que as tarefas sejam concluídas em uma progressão ordenada.
 - **Hierárquico**: Organiza tarefas em uma hierarquia gerencial, onde as tarefas são delegadas e executadas com base numa cadeia de comando estruturada. Um modelo de linguagem de gerente (`manager_llm`) ou um agente gerente personalizado (`manager_agent`) deve ser especificado na crew para habilitar o processo hierárquico, facilitando a criação e o gerenciamento de tarefas pelo gerente.
-- **Processo Consensual (Planejado)**: Visando a tomada de decisão colaborativa entre agentes para execução de tarefas, esse tipo de processo introduz uma abordagem democrática ao gerenciamento de tarefas dentro do CrewAI. Está planejado para desenvolvimento futuro e ainda não está implementado no código-fonte.
 
 ## O Papel dos Processos no Trabalho em Equipe
 Os processos permitem que agentes individuais atuem como uma unidade coesa, otimizando seus esforços para atingir objetivos comuns com eficiência e coerência.
@@ -59,9 +58,9 @@ Emulando uma hierarquia corporativa, o CrewAI permite especificar um agente gere
 
 ## Classe Process: Visão Detalhada
 
-A classe `Process` é implementada como uma enumeração (`Enum`), garantindo segurança de tipo e restringindo os valores de processos aos tipos definidos (`sequential`, `hierarchical`). O processo consensual está planejado para inclusão futura, reforçando nosso compromisso com o desenvolvimento contínuo e a inovação.
+A classe `Process` é implementada como uma enumeração (`Enum`), garantindo segurança de tipo e restringindo os valores de processos aos tipos definidos (`sequential`, `hierarchical`).
 
 ## Conclusão
 
 A colaboração estruturada possibilitada pelos processos dentro do CrewAI é fundamental para permitir o trabalho em equipe sistemático entre agentes.
-Esta documentação foi atualizada para refletir os mais recentes recursos, melhorias e a planejada integração do Processo Consensual, garantindo que os usuários tenham acesso às informações mais atuais e abrangentes.
+Esta documentação foi atualizada para refletir os mais recentes recursos e melhorias, garantindo que os usuários tenham acesso às informações mais atuais e abrangentes.

docs/pt-BR/enterprise/features/agent-control-plane/monitoring.mdx

@@ -6,6 +6,14 @@ icon: "gauge"
 mode: "wide"
 ---
 
+<Info>
+  **Navegação da Documentação do ACP (Beta)**
+
+  - [Visão Geral](/pt-BR/enterprise/features/agent-control-plane/overview)
+  - **Monitoramento** *(você está aqui)*
+  - [Regras](/pt-BR/enterprise/features/agent-control-plane/rules)
+</Info>
+
 ## Visão Geral
 
 A aba **Automações** é a visão de operações somente leitura do [Agent Control Plane](/pt-BR/enterprise/features/agent-control-plane/overview). Ela combina dois cards de métricas, um sankey interativo e duas sub-tabelas — **Automações** e **Consumo** — nas quais você pode buscar, filtrar e ordenar.

docs/pt-BR/enterprise/features/agent-control-plane/overview.mdx

@@ -5,6 +5,14 @@ sidebarTitle: Visão Geral
 icon: "book-open"
 ---
 
+<Info>
+  **Navegação da Documentação do ACP (Beta)**
+
+  - **Visão Geral** *(você está aqui)*
+  - [Monitoramento](/pt-BR/enterprise/features/agent-control-plane/monitoring)
+  - [Regras](/pt-BR/enterprise/features/agent-control-plane/rules)
+</Info>
+
 ## Visão Geral
 
 O **Agent Control Plane** (ACP) é o hub de operações para tudo que você tem rodando no CrewAI AMP. É uma tela única — dividida nas abas **Automações** e **Regras** — que permite à sua equipe:

docs/pt-BR/enterprise/features/agent-control-plane/rules.mdx

@@ -6,6 +6,14 @@ icon: "shield-check"
 mode: "wide"
 ---
 
+<Info>
+  **Navegação da Documentação do ACP (Beta)**
+
+  - [Visão Geral](/pt-BR/enterprise/features/agent-control-plane/overview)
+  - [Monitoramento](/pt-BR/enterprise/features/agent-control-plane/monitoring)
+  - **Regras** *(você está aqui)*
+</Info>
+
 ## Visão Geral
 
 As Regras permitem aplicar políticas — hoje: **PII Redaction** — em muitas automações de uma só vez, em vez de configurar cada deployment individualmente. Abra a aba **Regras** no [Agent Control Plane](/pt-BR/enterprise/features/agent-control-plane/overview) para gerenciá-las.

docs/pt-BR/enterprise/integrations/databricks.mdx

@@ -0,0 +1,123 @@
+---
+title: Integração com Databricks
+description: "Conecte agentes CrewAI ao Databricks Genie, SQL, Unity Catalog Functions e Vector Search por meio dos servidores MCP gerenciados do Databricks."
+icon: "layer-group"
+mode: "wide"
+---
+
+## Visão geral
+
+Conecte seus agentes CrewAI diretamente ao seu workspace do Databricks por meio dos [servidores MCP gerenciados do Databricks](https://docs.databricks.com/aws/en/generative-ai/mcp/managed-mcp). A integração com o Databricks permite que seus agentes façam perguntas em linguagem natural com o **Genie**, executem **SQL** governado, chamem **Unity Catalog Functions** e recuperem documentos com o **Vector Search** — tudo sem escrever ou hospedar qualquer código de conector, e com as permissões do Unity Catalog aplicadas em cada chamada.
+
+Nos bastidores, a integração com o Databricks é um wrapper gerenciado sobre o suporte a [Servidores MCP personalizados](/pt-BR/enterprise/guides/custom-mcp-server) do CrewAI. O Databricks expõe cada recurso como seu próprio endpoint do [Model Context Protocol](https://modelcontextprotocol.io/), e o CrewAI se conecta a eles com segurança em seu nome. Como cada servidor é adicionado separadamente, você pode habilitar exatamente os recursos de que suas crews precisam.
+
+## Principais recursos
+
+<CardGroup cols={2}>
+  <Card title="Genie" icon="comments">
+    Faça perguntas em linguagem natural e obtenha respostas fundamentadas em seus dados com o [Genie](https://docs.databricks.com/aws/en/genie/), que consulta Genie Spaces e o Unity Catalog e fornece links de volta para a interface do Databricks.
+  </Card>
+  <Card title="Databricks SQL" icon="database">
+    Execute SQL governado nos seus warehouses do Databricks para consultar, transformar e criar pipelines de dados diretamente a partir dos seus agentes.
+  </Card>
+  <Card title="Unity Catalog Functions" icon="function">
+    Invoque [funções do Unity Catalog](https://docs.databricks.com/aws/en/udf/unity-catalog) para executar SQL predefinido e lógica de negócio personalizada como ferramentas governadas e reutilizáveis.
+  </Card>
+  <Card title="Vector Search" icon="magnifying-glass">
+    Recupere documentos relevantes para fluxos de RAG e de conhecimento a partir de índices do [Mosaic AI Vector Search](https://docs.databricks.com/aws/en/generative-ai/vector-search) usando similaridade semântica.
+  </Card>
+</CardGroup>
+
+Todos os servidores são executados por trás do Unity AI Gateway e aplicam os controles de acesso do Unity Catalog, de modo que seus agentes só enxergam os dados e as ferramentas que têm permissão para usar.
+
+## Pré-requisitos
+
+Antes de usar a integração com o Databricks, certifique-se de ter:
+
+- Uma conta [CrewAI AMP](https://app.crewai.com) com assinatura ativa
+- Um workspace do Databricks com os recursos que você deseja expor (Genie Spaces, warehouses SQL, funções do Unity Catalog ou índices do Vector Search)
+- [Privilégios apropriados do Unity Catalog](https://docs.databricks.com/aws/en/data-governance/unity-catalog) nos objetos subjacentes
+- O hostname do seu workspace do Databricks (ex.: `your-workspace.cloud.databricks.com`)
+
+## Servidores MCP gerenciados do Databricks
+
+O Databricks publica um servidor MCP gerenciado separado para cada recurso. O CrewAI os expõe como conexões individuais, cada uma configurada com o host do seu workspace e os identificadores relevantes do Unity Catalog. Os endpoints seguem estes padrões:
+
+| Servidor | O que faz | Padrão de URL MCP |
+|----------|-----------|-------------------|
+| **Genie** | Perguntas e respostas em linguagem natural sobre um Genie Space | `https://<workspace-hostname>/api/2.0/mcp/genie/{genie_space_id}` |
+| **Databricks SQL** | Executa SQL nos seus warehouses | `https://<workspace-hostname>/api/2.0/mcp/sql` |
+| **Unity Catalog Functions** | Executa funções UC registradas | `https://<workspace-hostname>/api/2.0/mcp/functions/{catalog}/{schema}` |
+| **Vector Search** | Consulta um índice do Vector Search | `https://<workspace-hostname>/api/2.0/mcp/vector-search/{catalog}/{schema}` |
+
+<Note>
+Você não precisa construir essas URLs manualmente — o CrewAI cria cada endpoint a partir do host do workspace e dos identificadores (Genie Space ID, ou catalog/schema) que você fornece ao configurar a conexão. Para a especificação completa e os detalhes mais recentes dos endpoints, consulte a [documentação de MCP gerenciado do Databricks](https://docs.databricks.com/aws/en/generative-ai/mcp/managed-mcp).
+</Note>
+
+## Conectando o Databricks no CrewAI AMP
+
+<Frame>
+    <img src="/images/enterprise/databricks-configure.png" alt="Configurar um servidor MCP gerenciado do Databricks no CrewAI AMP" />
+</Frame>
+
+Cada recurso do Databricks — **Databricks Genie**, **Databricks SQL**, **Databricks Unity Catalog Functions** e **Databricks Vector Search** — aparece como seu próprio servidor MCP no grupo Databricks da página **Tools & Integrations**. Configure os que você precisar:
+
+<Steps>
+    <Step title="Abra Tools & Integrations">
+        Navegue até **Tools & Integrations** na barra lateral esquerda do CrewAI AMP e localize o grupo **Databricks** na lista de Connections. Você verá os servidores Genie, SQL, Unity Catalog Functions e Vector Search listados abaixo dele.
+    </Step>
+
+    <Step title="Configure um servidor">
+        Clique em **Configure** ao lado do recurso que deseja habilitar e forneça os detalhes da conexão:
+
+        - **Workspace Host** — o hostname do seu workspace do Databricks (ex.: `my-workspace.cloud.databricks.com`).
+        - **Genie** — o **Genie Space ID** a ser consultado.
+        - **Unity Catalog Functions** — o **catalog** e o **schema** que contêm suas funções.
+        - **Vector Search** — o **catalog** e o **schema** que contêm seu índice.
+        - **Databricks SQL** — sem identificadores adicionais; as consultas são executadas nos warehouses SQL do seu workspace.
+    </Step>
+
+    <Step title="Escolha um método de autenticação">
+        Selecione como o CrewAI se autentica no Databricks. **OAuth** é recomendado.
+
+        - **Use OAuth** — Conecte-se com segurança usando OAuth 2.0. Cada usuário se autentica individualmente, e o Databricks emite tokens com escopo para o recurso (`genie`, `sql`, `unity-catalog` ou `vector-search`). O CrewAI gerencia o fluxo de autorização e renova os tokens automaticamente.
+        - **Use personal access token** — Autentique-se com um [token de acesso pessoal do Databricks](https://docs.databricks.com/aws/en/dev-tools/auth/pat). Use uma identidade com privilégios mínimos para limitar a exposição.
+    </Step>
+
+    <Step title="Autentique">
+        Conclua a autenticação. Uma vez conectado, as ferramentas do servidor ficam disponíveis para suas crews. Repita para qualquer outro recurso do Databricks que você queira habilitar.
+    </Step>
+</Steps>
+
+<Tip>
+Como cada recurso é uma conexão separada, você pode combiná-los livremente — por exemplo, habilitar Genie e Vector Search para uma crew de pesquisa e reservar SQL e Unity Catalog Functions para uma crew de engenharia de dados. As configurações de visibilidade permitem controlar quais membros da equipe podem usar cada um.
+</Tip>
+
+## Usando as ferramentas do Databricks nas suas crews
+
+Uma vez conectado, as ferramentas que cada servidor MCP expõe aparecem junto às conexões integradas na página **Tools & Integrations**. Você pode:
+
+- **Atribuir ferramentas aos agentes** nas suas crews, como qualquer outra ferramenta do CrewAI.
+- **Gerenciar a visibilidade** para controlar quais membros da equipe podem usar cada conexão.
+- **Editar ou remover** qualquer conexão a qualquer momento na lista de Connections.
+
+Seus agentes agora podem pedir respostas fundamentadas ao Genie, executar SQL nos seus warehouses, chamar funções do Unity Catalog e pesquisar índices do Vector Search — com os resultados retornando automaticamente ao raciocínio deles.
+
+<Warning>
+O Databricks aplica governança por meio do Unity Catalog e do Unity AI Gateway: um usuário só pode descobrir e invocar ferramentas que a identidade do seu workspace tem permissão para usar. Se uma chamada de ferramenta falhar, confirme se o usuário (ou a identidade do token) que está conectando tem os privilégios necessários do Unity Catalog no Genie Space, warehouse, função ou índice. Algumas consultas do Genie e do SQL são executadas de forma assíncrona e podem levar um momento para retornar resultados.
+</Warning>
+
+## Saiba mais
+
+<CardGroup cols={2}>
+  <Card title="Servidores MCP gerenciados do Databricks" icon="layer-group" href="https://docs.databricks.com/aws/en/generative-ai/mcp/managed-mcp">
+    Documentação oficial do Databricks para os servidores MCP gerenciados Genie, SQL, Unity Catalog Functions e Vector Search.
+  </Card>
+  <Card title="Servidores MCP personalizados no CrewAI" icon="plug" href="/pt-BR/enterprise/guides/custom-mcp-server">
+    Saiba como o CrewAI se conecta a qualquer servidor MCP, a base sobre a qual a integração com o Databricks é construída.
+  </Card>
+</CardGroup>
+
+<Card title="Precisa de ajuda?" icon="headset" href="mailto:support@crewai.com">
+  Entre em contato com nossa equipe de suporte para obter ajuda com a configuração da integração com o Databricks ou com a solução de problemas.
+</Card>

docs/pt-BR/enterprise/integrations/snowflake.mdx

@@ -0,0 +1,134 @@
+---
+title: Integração com Snowflake
+description: "Conecte agentes CrewAI ao Snowflake Cortex Analyst, Cortex Search e execução SQL através do servidor MCP gerenciado pelo Snowflake."
+icon: "snowflake"
+mode: "wide"
+---
+
+## Visão Geral
+
+Conecte seus agentes CrewAI diretamente aos seus dados no Snowflake através do [servidor MCP gerenciado pelo Snowflake](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp). A integração com o Snowflake permite que seus agentes consultem dados estruturados com **Cortex Analyst**, pesquisem dados não estruturados com **Cortex Search** e executem SQL governado nos seus warehouses — tudo sem escrever ou hospedar nenhum código de conector.
+
+Internamente, a integração com o Snowflake é um wrapper gerenciado em torno do suporte a [Custom MCP Server](/pt-BR/enterprise/guides/custom-mcp-server) do CrewAI. O Snowflake expõe suas capacidades de Cortex AI através de um endpoint [Model Context Protocol](https://modelcontextprotocol.io/), e o CrewAI se conecta a ele de forma segura em seu nome. Qualquer ferramenta que você exponha no lado do Snowflake — Cortex Analyst, Cortex Search, execução SQL, Cortex Agents ou suas próprias ferramentas personalizadas — fica disponível para suas crews.
+
+## Capacidades Principais
+
+<CardGroup cols={3}>
+  <Card title="Cortex Analyst" icon="chart-bar">
+    Faça perguntas em linguagem natural e deixe o [Cortex Analyst](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-analyst) gerar e executar SQL nos seus dados **estruturados** usando modelos semânticos ricos.
+  </Card>
+  <Card title="Cortex Search" icon="magnifying-glass">
+    Recupere dados **não estruturados** relevantes para fluxos de trabalho de RAG e conhecimento com o [Cortex Search](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-search/cortex-search-overview), o serviço de busca totalmente gerenciado do Snowflake.
+  </Card>
+  <Card title="Execução SQL" icon="database">
+    Execute consultas SQL governadas diretamente nos seus warehouses Snowflake, com modo somente leitura configurável, timeouts e seleção de warehouse.
+  </Card>
+</CardGroup>
+
+Como a integração expõe quaisquer ferramentas que seu servidor MCP publica, você também pode expor **Cortex Agents** e **ferramentas personalizadas** (funções definidas pelo usuário e stored procedures) para seus agentes CrewAI.
+
+## Pré-requisitos
+
+Antes de usar a integração com o Snowflake, certifique-se de que você tenha:
+
+- Uma conta [CrewAI AMP](https://app.crewai.com) com assinatura ativa
+- Uma conta Snowflake com acesso aos recursos de Cortex AI
+- Um [servidor MCP gerenciado pelo Snowflake](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp) configurado com as ferramentas que você deseja expor
+- Privilégios Snowflake apropriados (USAGE/SELECT) no servidor MCP e seus objetos subjacentes
+
+## Configurando o Servidor Snowflake MCP
+
+O servidor MCP gerenciado pelo Snowflake é executado dentro da sua conta Snowflake e define quais ferramentas estão disponíveis para clientes externos como o CrewAI. Crie um com o comando [`CREATE MCP SERVER`](https://docs.snowflake.com/en/sql-reference/sql/create-mcp-server), listando os serviços Cortex Search, visualizações semânticas do Cortex Analyst e ferramentas SQL que você deseja expor.
+
+```sql
+CREATE MCP SERVER my_mcp_server
+  FROM SPECIFICATION $$
+    tools:
+      - name: "sales_analyst"
+        type: "CORTEX_ANALYST"
+        identifier: "MY_DATABASE.MY_SCHEMA.sales_semantic_view"
+        description: "Answer questions about sales metrics"
+      - name: "docs_search"
+        type: "CORTEX_SEARCH_SERVICE_QUERY"
+        identifier: "MY_DATABASE.MY_SCHEMA.support_docs_search"
+        description: "Search internal support documentation"
+      - name: "run_sql"
+        type: "SQL_EXECUTION"
+        description: "Execute read-only SQL queries"
+  $$;
+```
+
+<Note>
+O endpoint MCP segue o formato `https://<account_URL>/api/v2/databases/{database}/schemas/{schema}/mcp-servers/{name}`. O CrewAI constrói esta URL automaticamente a partir do **URL da Conta**, **Banco de Dados**, **Schema** e **Nome do Servidor MCP** que você fornece ao configurar a integração.
+</Note>
+
+Para a especificação completa — incluindo Cortex Agents, ferramentas personalizadas, limites de tamanho de resposta e opções de governança — consulte a [documentação do servidor MCP gerenciado pelo Snowflake](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp).
+
+## Conectando o Snowflake no CrewAI AMP
+
+<Frame>
+    <img src="/images/enterprise/snowflake-configure.png" alt="Configurar integração Snowflake no CrewAI AMP" />
+</Frame>
+
+<Steps>
+    <Step title="Abrir Ferramentas e Integrações">
+        Navegue até **Ferramentas e Integrações** na barra lateral esquerda do CrewAI AMP, encontre **Snowflake** na lista de aplicações e abra seu painel de configuração.
+    </Step>
+
+    <Step title="Fornecer detalhes da conexão">
+        Preencha os campos de conexão que o CrewAI usa para acessar seu servidor Snowflake MCP:
+
+        | Campo | Obrigatório | Descrição |
+        |-------|-------------|-----------|
+        | **Nome** | Sim | Um nome descritivo para esta conexão (padrão: `Snowflake`). |
+        | **Descrição** | Não | Um resumo opcional do que esta conexão fornece. |
+        | **URL da Conta** | Sim | A URL da sua conta Snowflake, ex.: `xy12345.us-east-1.snowflakecomputing.com`. |
+        | **Banco de Dados** | Sim | O banco de dados que contém seu servidor MCP (ex.: `MY_DATABASE`). |
+        | **Schema** | Sim | O schema que contém seu servidor MCP (ex.: `MY_SCHEMA`). |
+        | **Nome do Servidor MCP** | Sim | O nome do objeto de servidor MCP que você criou no Snowflake (ex.: `MY_MCP_SERVER`). |
+    </Step>
+
+    <Step title="Escolher um método de autenticação">
+        Selecione como o CrewAI se autentica no Snowflake. **OAuth** é recomendado.
+
+        - **Usar OAuth** — Conecte-se de forma segura usando OAuth 2.0 para autenticação baseada em tokens sem compartilhar suas credenciais. O CrewAI gerencia todo o fluxo de autorização e renova os tokens automaticamente. Copie o **URI de Redirecionamento** mostrado no formulário (`https://oauth.crewai.com/oauth/add`) e registre-o como um URI de redirecionamento autorizado na sua [integração de segurança OAuth](https://docs.snowflake.com/en/user-guide/oauth-custom) do Snowflake.
+        - **Usar token de acesso pessoal** — Autentique usando um [token de acesso programático](https://docs.snowflake.com/en/user-guide/programmatic-access-tokens) gerado nas configurações da sua conta Snowflake. Atribua uma role com privilégios mínimos ao token para limitar a exposição.
+    </Step>
+
+    <Step title="Autenticar">
+        Clique em **Autenticar**. Para OAuth, você será redirecionado ao Snowflake para autorizar o acesso. Após autenticado, o servidor Snowflake aparece na sua lista de Conexões e suas ferramentas ficam disponíveis para suas crews.
+    </Step>
+</Steps>
+
+<Tip>
+Com OAuth, cada usuário se autentica individualmente e as consultas são executadas com seu `DEFAULT_ROLE` do Snowflake. Certifique-se de que os usuários que se conectam tenham uma role e warehouse padrão definidos (`ALTER USER <username> SET DEFAULT_ROLE = '<role>' DEFAULT_WAREHOUSE = '<warehouse>'`) para que as ferramentas Cortex Analyst e SQL tenham capacidade de computação para execução.
+</Tip>
+
+## Usando Ferramentas Snowflake nas Suas Crews
+
+Uma vez conectado, as ferramentas que seu servidor MCP expõe aparecem junto com as conexões integradas na página **Ferramentas e Integrações**. Você pode:
+
+- **Atribuir ferramentas a agentes** nas suas crews como qualquer outra ferramenta CrewAI.
+- **Gerenciar visibilidade** para controlar quais membros do time podem usar a conexão.
+- **Editar ou remover** a conexão a qualquer momento na lista de Conexões.
+
+Seus agentes agora podem solicitar métricas ao Cortex Analyst, executar Cortex Search nos seus documentos e executar SQL — com os resultados fluindo automaticamente para o raciocínio deles.
+
+<Warning>
+O Snowflake impõe governança no servidor MCP: o controle de acesso baseado em roles determina quais ferramentas um usuário pode descobrir e invocar, e limites se aplicam ao tamanho da resposta, contagem de ferramentas (máximo de 50 por servidor) e profundidade de recursão. Se uma chamada de ferramenta falhar, confirme que a role do usuário conectado possui os privilégios necessários no servidor MCP e seus objetos subjacentes.
+</Warning>
+
+## Saiba Mais
+
+<CardGroup cols={2}>
+  <Card title="Servidor MCP Gerenciado pelo Snowflake" icon="snowflake" href="https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp">
+    Documentação oficial do Snowflake para criar e governar o servidor MCP.
+  </Card>
+  <Card title="Servidores Custom MCP no CrewAI" icon="plug" href="/pt-BR/enterprise/guides/custom-mcp-server">
+    Saiba como o CrewAI se conecta a qualquer servidor MCP, a base sobre a qual a integração Snowflake é construída.
+  </Card>
+</CardGroup>
+
+<Card title="Precisa de Ajuda?" icon="headset" href="mailto:support@crewai.com">
+  Entre em contato com nossa equipe de suporte para obter ajuda com a integração Snowflake ou solução de problemas.
+</Card>

lib/cli/pyproject.toml

@@ -8,14 +8,14 @@ authors = [
 ]
 requires-python = ">=3.10, <3.14"
 dependencies = [
-    "crewai-core==1.14.6a2",
-    "click~=8.1.7",
+    "crewai-core==1.14.6",
+    "click>=8.1.7,<9",
     "pydantic>=2.11.9,<2.13",
     "pydantic-settings~=2.10.1",
     "appdirs~=1.4.4",
     "cryptography>=42.0",
     "httpx~=0.28.1",
-    "pyjwt>=2.9.0,<3",
+    "pyjwt>=2.13.0,<3",
     "rich>=13.7.1",
     "tomli~=2.0.2",
     "tomli-w~=1.1.0",

lib/cli/src/crewai_cli/__init__.py

@@ -1 +1 @@
-__version__ = "1.14.6a2"
+__version__ = "1.14.6"

lib/cli/src/crewai_cli/cli.py

@@ -17,6 +17,7 @@ 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
@@ -26,7 +27,6 @@ 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.skills.main import SkillCommand
 from crewai_cli.task_outputs import load_task_outputs
 from crewai_cli.tools.main import ToolCommand
 from crewai_cli.train_crew import train_crew
@@ -544,8 +544,19 @@ def tool_publish(is_public: bool, force: bool) -> None:
 
 
 @crewai.group()
+def experimental() -> None:
+    """Experimental, unstable commands. Subject to change without notice."""
+    import os
+
+    if os.environ.get("CREWAI_EXPERIMENTAL") != "1":
+        raise click.UsageError(
+            "Experimental commands are gated. Set CREWAI_EXPERIMENTAL=1 to enable."
+        )
+
+
+@experimental.group(name="skill")
 def skill() -> None:
-    """Skill Repository related commands."""
+    """Skill Repository related commands (experimental)."""
 
 
 @skill.command(name="create")

lib/cli/src/crewai_cli/experimental/skills/main.py

@@ -23,9 +23,10 @@ console = Console()
 _SKILL_MD_TEMPLATE = """\
 ---
 name: {name}
-version: 0.1.0
 description: |
   A short description of what this skill does.
+metadata:
+  version: 0.1.0
 ---
 
 ## Instructions
@@ -147,7 +148,7 @@ class SkillCommand(BaseCommand, PlusAPIMixin):
             )
         else:
             try:
-                from crewai.skills.cache import SkillCacheManager
+                from crewai.experimental.skills.cache import SkillCacheManager
 
                 cache = SkillCacheManager()
                 cache.store(org, name, version, archive_bytes)
@@ -191,7 +192,10 @@ class SkillCommand(BaseCommand, PlusAPIMixin):
             raise SystemExit(1) from exc
 
         name = frontmatter.get("name")
-        version = frontmatter.get("version")
+        raw_metadata = frontmatter.get("metadata")
+        version = (
+            raw_metadata.get("version") if isinstance(raw_metadata, dict) else None
+        )
         description = frontmatter.get("description")
 
         if not name:
@@ -362,10 +366,13 @@ class SkillCommand(BaseCommand, PlusAPIMixin):
             return result
 
     def _read_version(self, skill_md: Path) -> str | None:
-        """Read the version field from a SKILL.md file, or None."""
+        """Read the version from a SKILL.md file's metadata, or None."""
         try:
             fm = self._parse_frontmatter(skill_md.read_text())
-            return fm.get("version")
+            raw_metadata = fm.get("metadata")
+            if isinstance(raw_metadata, dict):
+                return raw_metadata.get("version")
+            return None
         except Exception:
             return None
 

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]==1.14.5a2"
+    "crewai[tools]==1.14.6"
 ]
 
 [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]==1.14.5a2"
+    "crewai[tools]==1.14.6"
 ]
 
 [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]==1.14.5a2"
+    "crewai[tools]==1.14.6"
 ]
 
 [tool.crewai]

lib/cli/tests/experimental/skills/test_main.py

@@ -36,7 +36,7 @@ def skill_command():
             TokenManager().save_tokens(
                 "test-token", (datetime.now() + timedelta(seconds=36000)).timestamp()
             )
-            from crewai_cli.skills.main import SkillCommand
+            from crewai_cli.experimental.skills.main import SkillCommand
             cmd = SkillCommand()
             yield cmd
 
@@ -142,7 +142,7 @@ class TestSkillPublish:
                 mock_resp.status_code = 200
                 mock_resp.json.return_value = {}
                 mock_client.publish_skill.return_value = mock_resp
-                with patch("crewai_cli.skills.main.Settings") as mock_settings_cls:
+                with patch("crewai_cli.experimental.skills.main.Settings") as mock_settings_cls:
                     mock_settings_cls.return_value.org_name = None
                     mock_settings_cls.return_value.enterprise_base_url = None
                     with pytest.raises(SystemExit):
@@ -151,14 +151,14 @@ class TestSkillPublish:
     def test_publish_calls_api(self, skill_command):
         with in_temp_dir():
             Path("SKILL.md").write_text(
-                "---\nname: my-skill\nversion: 1.0.0\ndescription: A test skill.\n---\nInstructions."
+                "---\nname: my-skill\ndescription: A test skill.\nmetadata:\n  version: 1.0.0\n---\nInstructions."
             )
             mock_resp = MagicMock()
             mock_resp.is_success = True
             mock_resp.status_code = 200
             mock_resp.json.return_value = {}
             skill_command.plus_api_client.publish_skill = MagicMock(return_value=mock_resp)
-            with patch("crewai_cli.skills.main.Settings") as mock_settings_cls:
+            with patch("crewai_cli.experimental.skills.main.Settings") as mock_settings_cls:
                 mock_settings_cls.return_value.org_name = "acme"
                 mock_settings_cls.return_value.enterprise_base_url = None
 

lib/cli/tests/test_click_compatibility.py

@@ -0,0 +1,131 @@
+"""Tests for click dependency compatibility.
+
+Regression tests for https://github.com/crewAIInc/crewAI/issues/6002
+The click dependency was previously pinned to ~=8.1.7 (i.e. >=8.1.7,<8.2.0)
+which prevented users from upgrading to click 8.2+ as required by their
+security policies. The constraint has been widened to >=8.1.7,<9 to allow
+newer click 8.x releases while still guarding against a future major version
+break.
+"""
+
+from importlib.metadata import requires
+from pathlib import Path
+
+import click
+import pytest
+from click.testing import CliRunner
+from packaging.requirements import Requirement
+
+
+# ---------------------------------------------------------------------------
+# Verify the runtime click version satisfies the declared constraint
+# ---------------------------------------------------------------------------
+
+def _get_click_requirement_from_pyproject(package_dir: str) -> Requirement:
+    """Parse the click requirement directly from a pyproject.toml file."""
+    import tomli
+
+    pyproject_path = Path(__file__).resolve().parents[3] / package_dir / "pyproject.toml"
+    with open(pyproject_path, "rb") as f:
+        data = tomli.load(f)
+    deps = data["project"]["dependencies"]
+    for dep in deps:
+        req = Requirement(dep)
+        if req.name == "click":
+            return req
+    raise ValueError(f"click not found in {pyproject_path}")
+
+
+@pytest.mark.parametrize(
+    "package_dir",
+    [
+        "lib/crewai",
+        "lib/cli",
+        "lib/devtools",
+    ],
+)
+def test_click_constraint_allows_8_3_3(package_dir: str):
+    """The declared click constraint must accept click 8.3.3 (issue #6002)."""
+    req = _get_click_requirement_from_pyproject(package_dir)
+    # packaging's Requirement.specifier supports `__contains__` for version checks
+    assert "8.3.3" in req.specifier, (
+        f"{package_dir}: click constraint {req.specifier} does not allow 8.3.3"
+    )
+
+
+@pytest.mark.parametrize(
+    "package_dir",
+    [
+        "lib/crewai",
+        "lib/cli",
+        "lib/devtools",
+    ],
+)
+def test_click_constraint_allows_8_1_7(package_dir: str):
+    """The declared click constraint must still accept the original minimum (8.1.7)."""
+    req = _get_click_requirement_from_pyproject(package_dir)
+    assert "8.1.7" in req.specifier, (
+        f"{package_dir}: click constraint {req.specifier} does not allow 8.1.7"
+    )
+
+
+@pytest.mark.parametrize(
+    "package_dir",
+    [
+        "lib/crewai",
+        "lib/cli",
+        "lib/devtools",
+    ],
+)
+def test_click_constraint_rejects_next_major(package_dir: str):
+    """The declared click constraint must reject click 9.0.0."""
+    req = _get_click_requirement_from_pyproject(package_dir)
+    assert "9.0.0" not in req.specifier, (
+        f"{package_dir}: click constraint {req.specifier} should not allow 9.0.0"
+    )
+
+
+# ---------------------------------------------------------------------------
+# Verify the installed click version works with the CLI
+# ---------------------------------------------------------------------------
+
+def test_click_version_is_compatible():
+    """The installed click version must be within the 8.x range."""
+    major = int(click.__version__.split(".")[0])
+    assert major == 8, f"Expected click 8.x, got {click.__version__}"
+
+
+def test_cli_runner_works_with_installed_click():
+    """Smoke-test: CliRunner from the installed click can invoke a trivial command."""
+
+    @click.command()
+    @click.option("--name", default="world")
+    def hello(name: str) -> None:
+        click.echo(f"Hello {name}!")
+
+    runner = CliRunner()
+    result = runner.invoke(hello, ["--name", "crewai"])
+    assert result.exit_code == 0
+    assert "Hello crewai!" in result.output
+
+
+def test_cli_group_works_with_installed_click():
+    """Smoke-test: click.group, click.option, click.argument all work."""
+
+    @click.group()
+    def grp() -> None:
+        pass
+
+    @grp.command()
+    @click.argument("task")
+    @click.option("--verbose", is_flag=True)
+    def run(task: str, verbose: bool) -> None:
+        if verbose:
+            click.echo(f"Running {task} (verbose)")
+        else:
+            click.echo(f"Running {task}")
+
+    runner = CliRunner()
+    result = runner.invoke(grp, ["run", "test-task", "--verbose"])
+    assert result.exit_code == 0
+    assert "Running test-task (verbose)" in result.output

lib/crewai-core/pyproject.toml

@@ -13,7 +13,7 @@ dependencies = [
     "httpx~=0.28.1",
     "packaging>=23.0",
     "portalocker~=2.7.0",
-    "pyjwt>=2.9.0,<3",
+    "pyjwt>=2.13.0,<3",
     "pydantic>=2.11.9,<2.13",
     "rich>=13.7.1",
     "opentelemetry-api~=1.34.0",

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

@@ -1 +1 @@
-__version__ = "1.14.6a2"
+__version__ = "1.14.6"

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

@@ -152,4 +152,4 @@ __all__ = [
     "wrap_file_source",
 ]
 
-__version__ = "1.14.6a2"
+__version__ = "1.14.6"

lib/crewai-files/src/crewai_files/formatting/api.py

@@ -11,7 +11,10 @@ from crewai_files.formatting.anthropic import AnthropicFormatter
 from crewai_files.formatting.bedrock import BedrockFormatter
 from crewai_files.formatting.gemini import GeminiFormatter
 from crewai_files.formatting.openai import OpenAIFormatter, OpenAIResponsesFormatter
-from crewai_files.processing.constraints import get_constraints_for_provider
+from crewai_files.processing.constraints import (
+    get_constraints_for_provider,
+    uses_openai_responses_api,
+)
 from crewai_files.processing.processor import FileProcessor
 from crewai_files.resolution.resolver import FileResolver, FileResolverConfig
 from crewai_files.uploaders.factory import ProviderType
@@ -120,9 +123,11 @@ def format_multimodal_content(
     if not files:
         return content_blocks
 
-    constraints_key: str = provider_type
-    if api == "responses" and "openai" in provider_type.lower():
-        constraints_key = "openai_responses"
+    constraints_key = (
+        "openai_responses"
+        if uses_openai_responses_api(provider_type, api)
+        else provider_type
+    )
 
     processor = FileProcessor(constraints=constraints_key)
     processed_files = processor.process_files(files)
@@ -184,9 +189,11 @@ async def aformat_multimodal_content(
     if not files:
         return content_blocks
 
-    constraints_key: str = provider_type
-    if api == "responses" and "openai" in provider_type.lower():
-        constraints_key = "openai_responses"
+    constraints_key = (
+        "openai_responses"
+        if uses_openai_responses_api(provider_type, api)
+        else provider_type
+    )
 
     processor = FileProcessor(constraints=constraints_key)
     processed_files = await processor.aprocess_files(files)

lib/crewai-files/src/crewai_files/processing/constraints.py

@@ -346,6 +346,20 @@ def get_constraints_for_provider(
     return None
 
 
+def uses_openai_responses_api(provider: str, api: str | None = None) -> bool:
+    """Return whether provider/API should use OpenAI Responses file support."""
+    if api != "responses":
+        return False
+
+    provider_lower = provider.lower()
+    return (
+        "openai" in provider_lower
+        or provider_lower == "gpt"
+        or provider_lower.startswith("gpt-")
+        or "/gpt-" in provider_lower
+    )
+
+
 def get_supported_content_types(provider: str, api: str | None = None) -> list[str]:
     """Get supported MIME type prefixes for a provider.
 
@@ -356,9 +370,9 @@ def get_supported_content_types(provider: str, api: str | None = None) -> list[s
     Returns:
         List of supported MIME type prefixes (e.g., ["image/", "application/pdf"]).
     """
-    lookup_key = provider
-    if api == "responses" and "openai" in provider.lower():
-        lookup_key = "openai_responses"
+    lookup_key = (
+        "openai_responses" if uses_openai_responses_api(provider, api) else provider
+    )
 
     constraints = get_constraints_for_provider(lookup_key)
     if not constraints:

lib/crewai-files/tests/processing/test_constraints.py

@@ -11,6 +11,7 @@ from crewai_files.processing.constraints import (
     ProviderConstraints,
     VideoConstraints,
     get_constraints_for_provider,
+    get_supported_content_types,
 )
 import pytest
 
@@ -70,6 +71,13 @@ class TestPDFConstraints:
         assert constraints.max_size_bytes == 1000
         assert constraints.max_pages is None
 
+    @pytest.mark.parametrize("provider", ["openai", "gpt", "gpt-4o-mini"])
+    def test_openai_responses_supports_pdf_for_gpt_aliases(self, provider):
+        """OpenAI Responses PDF support applies to concrete GPT model names."""
+        supported_types = get_supported_content_types(provider, api="responses")
+
+        assert "application/pdf" in supported_types
+
 
 class TestAudioConstraints:
     """Tests for AudioConstraints dataclass."""

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==1.14.6a2",
+    "crewai==1.14.6",
     "tiktoken>=0.8.0,<0.13",
     "beautifulsoup4~=4.13.4",
     "python-docx~=1.2.0",

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

@@ -330,4 +330,4 @@ __all__ = [
     "ZapierActionTools",
 ]
 
-__version__ = "1.14.6a2"
+__version__ = "1.14.6"

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

@@ -0,0 +1,158 @@
+"""SSRF-safe HTTP fetching for crewai-tools.
+
+:func:`validate_url` checks the URL it is handed, but it cannot protect a
+fetch on its own: ``requests`` re-resolves DNS at connect time and follows
+redirects automatically, so a public-looking host that 302-redirects to an
+internal address (or that rebinds DNS between validation and connect) reaches
+the internal target without ever being re-checked.
+
+This module closes both gaps at the connection layer:
+
+* :class:`SSRFProtectedAdapter` re-runs :func:`validate_url` for every request
+  it sends. ``requests.Session.send`` invokes the adapter once per redirect
+  hop, so each ``Location`` target is validated before it is followed.
+* The adapter's connections validate the *actual* peer IP immediately after
+  the socket connects. The IP that was authorised is therefore the IP the
+  connection uses, removing the DNS time-of-check/time-of-use gap that
+  :func:`validate_url`'s own ``getaddrinfo`` call leaves open.
+
+Use :func:`safe_get` (or :func:`create_safe_session`) instead of calling
+``requests.get`` directly from any tool that fetches a user- or
+LLM-controlled URL.
+"""
+
+from __future__ import annotations
+
+from typing import Any
+
+import requests
+from requests.adapters import DEFAULT_POOLBLOCK, HTTPAdapter
+from urllib3.connection import HTTPConnection, HTTPSConnection
+from urllib3.connectionpool import HTTPConnectionPool, HTTPSConnectionPool
+from urllib3.poolmanager import PoolManager
+
+from crewai_tools.security.safe_path import (
+    _is_escape_hatch_enabled,
+    _is_private_or_reserved,
+    validate_url,
+)
+
+
+def _assert_safe_peer(sock: Any) -> None:
+    """Raise if a connected socket's peer is a private/reserved address.
+
+    Validating the real peer (rather than a separately resolved IP) is what
+    defeats DNS rebinding: the address we connected to is the address we check.
+    """
+    if _is_escape_hatch_enabled():
+        return
+    try:
+        peer = sock.getpeername()
+    except OSError:
+        return
+    ip_str = str(peer[0])
+    if _is_private_or_reserved(ip_str):
+        raise ValueError(
+            f"Connection resolved to private/reserved IP {ip_str}. "
+            f"Access to internal networks is not allowed (possible SSRF via "
+            f"redirect or DNS rebinding)."
+        )
+
+
+class _SafeHTTPConnection(HTTPConnection):
+    def connect(self) -> None:
+        super().connect()
+        _assert_safe_peer(self.sock)
+
+
+class _SafeHTTPSConnection(HTTPSConnection):
+    def connect(self) -> None:
+        super().connect()
+        _assert_safe_peer(self.sock)
+
+
+class _SafeHTTPConnectionPool(HTTPConnectionPool):
+    ConnectionCls = _SafeHTTPConnection
+
+
+class _SafeHTTPSConnectionPool(HTTPSConnectionPool):
+    ConnectionCls = _SafeHTTPSConnection
+
+
+_SAFE_POOL_CLASSES = {
+    "http": _SafeHTTPConnectionPool,
+    "https": _SafeHTTPSConnectionPool,
+}
+
+
+class _SafePoolManager(PoolManager):
+    def __init__(self, *args: Any, **kwargs: Any) -> None:
+        super().__init__(*args, **kwargs)
+        self.pool_classes_by_scheme = _SAFE_POOL_CLASSES
+
+
+class SSRFProtectedAdapter(HTTPAdapter):
+    """Transport adapter that re-validates every hop and pins the peer IP.
+
+    ``validate_url`` runs on each ``send`` — including every redirect hop
+    ``requests`` follows — and the underlying connections reject any socket
+    that ends up connected to a private/reserved address.
+    """
+
+    def init_poolmanager(
+        self,
+        connections: int,
+        maxsize: int,
+        block: bool = DEFAULT_POOLBLOCK,
+        **pool_kwargs: Any,
+    ) -> None:
+        self.poolmanager = _SafePoolManager(
+            num_pools=connections,
+            maxsize=maxsize,
+            block=block,
+            **pool_kwargs,
+        )
+
+    def send(self, request: Any, *args: Any, **kwargs: Any) -> Any:
+        # Re-validate the target of every request the session sends. Because
+        # Session.send calls this once per redirect hop, each Location is
+        # checked before it is followed.
+        validate_url(request.url)
+        return super().send(request, *args, **kwargs)
+
+
+def create_safe_session() -> requests.Session:
+    """Return a ``requests.Session`` that is hardened against SSRF.
+
+    The session validates every request (and redirect hop) and pins
+    connections to the validated peer IP.
+    """
+    session = requests.Session()
+    adapter = SSRFProtectedAdapter()
+    session.mount("http://", adapter)
+    session.mount("https://", adapter)
+    return session
+
+
+def safe_get(url: str, **kwargs: Any) -> requests.Response:
+    """Perform an SSRF-safe ``GET``.
+
+    Drop-in replacement for ``requests.get`` for tools that fetch a
+    user- or LLM-controlled URL. Validates the initial URL and every redirect
+    hop, and rejects connections that land on private/reserved addresses.
+
+    Args:
+        url: The URL to fetch.
+        **kwargs: Forwarded to ``Session.get`` (``headers``, ``cookies``,
+            ``timeout``, ...).
+
+    Returns:
+        The ``requests.Response``.
+
+    Raises:
+        ValueError: If the URL, a redirect target, or the connected peer is
+            not allowed.
+    """
+    validate_url(url)
+    with create_safe_session() as session:
+        return session.get(url, **kwargs)

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

@@ -3,9 +3,8 @@ from typing import Any
 
 from crewai.tools import BaseTool
 from pydantic import BaseModel, Field
-import requests
 
-from crewai_tools.security.safe_path import validate_url
+from crewai_tools.security.safe_requests import safe_get
 
 
 try:
@@ -83,8 +82,7 @@ class ScrapeElementFromWebsiteTool(BaseTool):
         if website_url is None or css_element is None:
             raise ValueError("Both website_url and css_element must be provided.")
 
-        website_url = validate_url(website_url)
-        page = requests.get(
+        page = safe_get(
             website_url,
             headers=self.headers,
             cookies=self.cookies if self.cookies else {},

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

@@ -3,9 +3,8 @@ import re
 from typing import Any
 
 from pydantic import Field
-import requests
 
-from crewai_tools.security.safe_path import validate_url
+from crewai_tools.security.safe_requests import safe_get
 
 
 try:
@@ -75,8 +74,7 @@ class ScrapeWebsiteTool(BaseTool):
         if website_url is None:
             raise ValueError("Website URL must be provided.")
 
-        website_url = validate_url(website_url)
-        page = requests.get(
+        page = safe_get(
             website_url,
             timeout=15,
             headers=self.headers,

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

@@ -0,0 +1,124 @@
+"""Tests for SSRF-safe HTTP fetching (redirect + DNS-rebinding protection)."""
+
+from __future__ import annotations
+
+import http.server
+import socketserver
+import threading
+
+import pytest
+import requests
+
+from crewai_tools.security import safe_requests
+from crewai_tools.security.safe_requests import (
+    SSRFProtectedAdapter,
+    create_safe_session,
+    safe_get,
+)
+
+
+INTERNAL_BODY = b"INTERNAL-ONLY-SECRET"
+
+
+class _InternalHandler(http.server.BaseHTTPRequestHandler):
+    def do_GET(self):
+        self.send_response(200)
+        self.send_header("Content-Type", "text/plain")
+        self.end_headers()
+        self.wfile.write(INTERNAL_BODY)
+
+    def log_message(self, *args):  # silence
+        pass
+
+
+def _serve(handler):
+    """Start a localhost server on an ephemeral port; return (server, port)."""
+    server = socketserver.TCPServer(("127.0.0.1", 0), handler)
+    port = server.server_address[1]
+    threading.Thread(target=server.serve_forever, daemon=True).start()
+    return server, port
+
+
+class TestRedirectRevalidation:
+    """Layer 1: validate_url runs on every send, including each redirect hop.
+
+    ``requests.Session.send`` calls ``adapter.send`` once per redirect hop, so
+    re-validating in ``send`` is what blocks a 302 to an internal target.
+    """
+
+    def test_adapter_revalidates_before_any_network_call(self, monkeypatch):
+        calls: list[str] = []
+
+        def spy(url: str) -> str:
+            calls.append(url)
+            if "internal.target" in url:
+                raise ValueError("URL resolves to private/reserved IP")
+            return url
+
+        monkeypatch.setattr(safe_requests, "validate_url", spy)
+
+        adapter = SSRFProtectedAdapter()
+        # Internal redirect target: send() must reject it before ever calling
+        # the real transport (super().send is never reached).
+        req = requests.Request("GET", "http://internal.target/").prepare()
+        with pytest.raises(ValueError, match="private/reserved"):
+            adapter.send(req)
+        assert calls == ["http://internal.target/"]
+
+    def test_session_mounts_protected_adapter(self):
+        session = create_safe_session()
+        assert isinstance(session.get_adapter("http://x"), SSRFProtectedAdapter)
+        assert isinstance(session.get_adapter("https://x"), SSRFProtectedAdapter)
+
+
+class _FakeSock:
+    def __init__(self, peer):
+        self._peer = peer
+
+    def getpeername(self):
+        return self._peer
+
+
+class TestConnectionPeerGuard:
+    """Layer 2: the connection rejects an internal peer IP at connect time.
+
+    This is what closes the validate-then-connect DNS-rebinding gap — the IP
+    the socket actually connected to is the IP that gets checked, so a host
+    that resolved public at validation time but connects internal is blocked.
+    """
+
+    def test_safe_get_blocks_direct_internal(self):
+        # No network: validate_url rejects 127.0.0.1 at the URL layer first.
+        with pytest.raises(ValueError, match="private/reserved"):
+            safe_get("http://127.0.0.1:9/", timeout=10)
+
+    def test_assert_safe_peer_blocks_private(self):
+        with pytest.raises(ValueError, match="private/reserved"):
+            safe_requests._assert_safe_peer(_FakeSock(("127.0.0.1", 80)))
+
+    def test_assert_safe_peer_blocks_metadata(self):
+        with pytest.raises(ValueError, match="private/reserved"):
+            safe_requests._assert_safe_peer(_FakeSock(("169.254.169.254", 80)))
+
+    def test_assert_safe_peer_allows_public(self):
+        # A public IP must not raise.
+        safe_requests._assert_safe_peer(_FakeSock(("93.184.216.34", 80)))
+
+    def test_assert_safe_peer_respects_escape_hatch(self, monkeypatch):
+        monkeypatch.setenv("CREWAI_TOOLS_ALLOW_UNSAFE_PATHS", "true")
+        # No raise even for a private peer when the escape hatch is on.
+        safe_requests._assert_safe_peer(_FakeSock(("127.0.0.1", 80)))
+
+    def test_connection_validates_peer_after_connect(self, monkeypatch):
+        """_SafeHTTPConnection.connect runs the peer guard after connecting."""
+        conn = safe_requests._SafeHTTPConnection("example.com")
+
+        def fake_super_connect(self):
+            # Simulate a rebind: we connected to an internal address.
+            self.sock = _FakeSock(("127.0.0.1", 80))
+
+        monkeypatch.setattr(
+            safe_requests.HTTPConnection, "connect", fake_super_connect
+        )
+        with pytest.raises(ValueError, match="private/reserved"):
+            conn.connect()

lib/crewai/pyproject.toml

@@ -8,8 +8,8 @@ authors = [
 ]
 requires-python = ">=3.10, <3.14"
 dependencies = [
-    "crewai-core==1.14.6a2",
-    "crewai-cli==1.14.6a2",
+    "crewai-core==1.14.6",
+    "crewai-cli==1.14.6",
     # Core Dependencies
     "pydantic>=2.11.9,<2.13",
     "openai>=2.30.0,<3",
@@ -27,9 +27,9 @@ dependencies = [
     "openpyxl~=3.1.5",
     # Authentication and Security
     "python-dotenv>=1.2.2,<2",
-    "pyjwt>=2.9.0,<3",
+    "pyjwt>=2.13.0,<3",
     # Configuration and Utils
-    "click~=8.1.7",
+    "click>=8.1.7,<9",
     "appdirs~=1.4.4",
     "jsonref~=1.1.0",
     "json-repair~=0.25.2",
@@ -54,7 +54,7 @@ Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
 tools = [
-    "crewai-tools==1.14.6a2",
+    "crewai-tools==1.14.6",
 ]
 embeddings = [
     "tiktoken>=0.8.0,<0.13"

lib/crewai/src/crewai/__init__.py

@@ -48,7 +48,7 @@ def _suppress_pydantic_deprecation_warnings() -> None:
 
 _suppress_pydantic_deprecation_warnings()
 
-__version__ = "1.14.6a2"
+__version__ = "1.14.6"
 
 _LAZY_IMPORTS: dict[str, tuple[str, str]] = {
     "Memory": ("crewai.memory.unified_memory", "Memory"),

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

@@ -472,7 +472,7 @@ class Agent(BaseAgent):
 
         for item in items:
             if isinstance(item, str):
-                from crewai.skills.registry import (
+                from crewai.experimental.skills.registry import (
                     is_registry_ref,
                     parse_registry_ref,
                     resolve_registry_ref,
@@ -1219,9 +1219,17 @@ class Agent(BaseAgent):
 
     def _use_trained_data(self, task_prompt: str) -> str:
         """Use trained data for the agent task prompt to improve output."""
-        trained_file = os.getenv(
-            CREWAI_TRAINED_AGENTS_FILE_ENV, TRAINED_AGENTS_DATA_FILE
+        crew_trained_agents_file = (
+            getattr(self.crew, "trained_agents_file", None)
+            if self.crew and not isinstance(self.crew, str)
+            else None
         )
+        trained_file = (
+            os.fspath(crew_trained_agents_file)
+            if crew_trained_agents_file
+            else os.getenv(CREWAI_TRAINED_AGENTS_FILE_ENV, TRAINED_AGENTS_DATA_FILE)
+        )
+
         if data := CrewTrainingHandler(trained_file).load():
             if trained_data_output := data.get(self.role):
                 task_prompt += (

lib/crewai/src/crewai/crew.py

@@ -179,6 +179,7 @@ class Crew(FlowTrackable, BaseModel):
         max_rpm: Maximum number of requests per minute for the crew execution to
             be respected.
         prompt_file: Path to the prompt json file to be used for the crew.
+        trained_agents_file: Path to trained agent suggestions loaded during inference.
         id: A unique identifier for the crew instance.
         task_callback: Callback to be executed after each task for every agents
             execution.
@@ -303,6 +304,13 @@ class Crew(FlowTrackable, BaseModel):
         default=None,
         description="Path to the prompt json file to be used for the crew.",
     )
+    trained_agents_file: str | Path | None = Field(
+        default=None,
+        description=(
+            "Path to a trained-agents pickle produced by train(). "
+            "When set, agents load suggestions from this file during inference."
+        ),
+    )
     output_log_file: bool | str | None = Field(
         default=None,
         description="Path to the log file to be saved",

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

@@ -60,20 +60,3 @@ class SkillLoadFailedEvent(SkillEvent):
 
     type: Literal["skill_load_failed"] = "skill_load_failed"
     error: str
-
-
-class SkillDownloadStartedEvent(SkillEvent):
-    """Event emitted when a registry skill download begins."""
-
-    type: Literal["skill_download_started"] = "skill_download_started"
-    registry_ref: str
-    version: str | None = None
-
-
-class SkillDownloadCompletedEvent(SkillEvent):
-    """Event emitted when a registry skill download completes."""
-
-    type: Literal["skill_download_completed"] = "skill_download_completed"
-    registry_ref: str
-    version: str | None = None
-    cache_path: Path | None = None

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

@@ -93,6 +93,7 @@ from crewai.utilities.agent_utils import (
     track_delegation_if_needed,
 )
 from crewai.utilities.constants import TRAINING_DATA_FILE
+from crewai.utilities.file_store import aget_all_files, get_all_files
 from crewai.utilities.i18n import I18N_DEFAULT
 from crewai.utilities.planning_types import (
     PlanStep,
@@ -2771,7 +2772,7 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
                     mark_cache_breakpoint(format_message_for_llm(user_prompt))
                 )
 
-            self._inject_files_from_inputs(inputs)
+            await self._ainject_files_from_inputs(inputs)
 
             self.state.ask_for_human_input = bool(
                 inputs.get("ask_for_human_input", False)
@@ -2982,12 +2983,42 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
         training_handler.save(training_data)
 
     def _inject_files_from_inputs(self, inputs: dict[str, Any]) -> None:
-        """Inject files from inputs into the last user message.
+        """Inject files into the last user message.
 
         Args:
             inputs: Input dictionary that may contain a 'files' key.
         """
-        files = inputs.get("files")
+        files: dict[str, Any] = {}
+
+        if self.crew and self.task:
+            stored_files = get_all_files(self.crew.id, self.task.id)
+            if stored_files:
+                files.update(stored_files)
+
+        if inputs.get("files"):
+            files.update(inputs["files"])
+
+        if not files:
+            return
+
+        for i in range(len(self.state.messages) - 1, -1, -1):
+            msg = self.state.messages[i]
+            if msg.get("role") == "user":
+                msg["files"] = files
+                break
+
+    async def _ainject_files_from_inputs(self, inputs: dict[str, Any]) -> None:
+        """Async inject files into the last user message."""
+        files: dict[str, Any] = {}
+
+        if self.crew and self.task:
+            stored_files = await aget_all_files(self.crew.id, self.task.id)
+            if stored_files:
+                files.update(stored_files)
+
+        if inputs.get("files"):
+            files.update(inputs["files"])
+
         if not files:
             return
 

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

@@ -0,0 +1,23 @@
+"""Experimental Skills Repository — registry refs, global cache, downloads.
+
+This package contains the registry-backed pieces of the skills feature
+(`@org/name` refs, `~/.crewai/skills/` cache, download events). The stable
+filesystem-based skill loader still lives in `crewai.skills`.
+"""
+
+from crewai.experimental.skills.cache import SkillCacheManager
+from crewai.experimental.skills.registry import (
+    SkillNotCachedError,
+    is_registry_ref,
+    parse_registry_ref,
+    resolve_registry_ref,
+)
+
+
+__all__ = [
+    "SkillCacheManager",
+    "SkillNotCachedError",
+    "is_registry_ref",
+    "parse_registry_ref",
+    "resolve_registry_ref",
+]

lib/crewai/src/crewai/experimental/skills/_flag.py

@@ -0,0 +1,24 @@
+"""Experimental feature gate for the Skills Repository."""
+
+from __future__ import annotations
+
+import os
+
+
+ENV_VAR = "CREWAI_EXPERIMENTAL"
+
+
+class ExperimentalFeatureDisabledError(RuntimeError):
+    """Raised when an experimental feature is used without the flag set."""
+
+
+def is_enabled() -> bool:
+    return os.environ.get(ENV_VAR) == "1"
+
+
+def require_experimental_skills() -> None:
+    if not is_enabled():
+        raise ExperimentalFeatureDisabledError(
+            "The Skills Repository (registry refs, cache, downloads) is "
+            f"experimental. Set {ENV_VAR}=1 to enable it."
+        )

lib/crewai/src/crewai/experimental/skills/events.py

@@ -0,0 +1,30 @@
+"""Download lifecycle events for registry-backed skills.
+
+These events are emitted only by the experimental Skills Repository
+(`@org/name` resolution + global cache). Local-file skill events still
+live in `crewai.events.types.skill_events`.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Literal
+
+from crewai.events.types.skill_events import SkillEvent
+
+
+class SkillDownloadStartedEvent(SkillEvent):
+    """Event emitted when a registry skill download begins."""
+
+    type: Literal["skill_download_started"] = "skill_download_started"
+    registry_ref: str
+    version: str | None = None
+
+
+class SkillDownloadCompletedEvent(SkillEvent):
+    """Event emitted when a registry skill download completes."""
+
+    type: Literal["skill_download_completed"] = "skill_download_completed"
+    registry_ref: str
+    version: str | None = None
+    cache_path: Path | None = None

lib/crewai/src/crewai/experimental/skills/registry.py

@@ -11,7 +11,7 @@ from pathlib import Path
 import sys
 from typing import Any
 
-from crewai.skills.cache import SkillCacheManager
+from crewai.experimental.skills.cache import SkillCacheManager
 
 
 _logger = logging.getLogger(__name__)
@@ -100,9 +100,11 @@ def resolve_registry_ref(
     Raises:
         SkillNotCachedError: When not cached and running in non-interactive mode.
     """
+    from crewai.experimental.skills._flag import require_experimental_skills
     from crewai.skills.loader import activate_skill
     from crewai.skills.parser import load_skill_metadata
 
+    require_experimental_skills()
     org, name = parse_registry_ref(ref)
 
     local_path = Path.cwd() / "skills" / name
@@ -152,7 +154,7 @@ def download_skill(
 
     try:
         from crewai.events.event_bus import crewai_event_bus
-        from crewai.events.types.skill_events import (
+        from crewai.experimental.skills.events import (
             SkillDownloadCompletedEvent,
             SkillDownloadStartedEvent,
         )

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

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

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

@@ -1,32 +1,84 @@
 from __future__ import annotations
 
 from collections.abc import Iterator
+from functools import cache
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, Literal
+from typing import TYPE_CHECKING, Any, Literal, NamedTuple, cast
 from urllib.parse import urlparse
 
-
-try:
-    from docling.datamodel.base_models import InputFormat
-    from docling.document_converter import DocumentConverter
-    from docling.exceptions import ConversionError
-    from docling_core.transforms.chunker.hierarchical_chunker import HierarchicalChunker
-    from docling_core.types.doc.document import DoclingDocument
-
-    DOCLING_AVAILABLE = True
-except ImportError:
-    DOCLING_AVAILABLE = False
-    if TYPE_CHECKING:
-        from docling.document_converter import DocumentConverter
-        from docling_core.types.doc.document import DoclingDocument
-
-from pydantic import Field
+from pydantic import Field, model_validator
+from typing_extensions import Self
 
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.utilities.constants import KNOWLEDGE_DIRECTORY
 from crewai.utilities.logger import Logger
 
 
+if TYPE_CHECKING:
+    from docling.document_converter import DocumentConverter
+    from docling_core.types.doc.document import DoclingDocument
+
+
+_DOCLING_IMPORT_ERROR = (
+    "The docling package is required to use CrewDoclingSource. "
+    "Please install it using: uv add docling"
+)
+
+
+class _DoclingModules(NamedTuple):
+    """Lazily-imported docling symbols used by ``CrewDoclingSource``."""
+
+    input_format: Any
+    document_converter: Any
+    conversion_error: type[BaseException]
+    hierarchical_chunker: Any
+
+
+@cache
+def _import_docling() -> _DoclingModules:
+    """Import docling submodules lazily and cache the result.
+
+    Raises:
+        ImportError: If the docling package is not installed.
+    """
+    try:
+        from docling.datamodel.base_models import InputFormat
+        from docling.document_converter import DocumentConverter
+        from docling.exceptions import ConversionError
+        from docling_core.transforms.chunker.hierarchical_chunker import (
+            HierarchicalChunker,
+        )
+    except ImportError as e:
+        raise ImportError(_DOCLING_IMPORT_ERROR) from e
+    return _DoclingModules(
+        input_format=InputFormat,
+        document_converter=DocumentConverter,
+        conversion_error=ConversionError,
+        hierarchical_chunker=HierarchicalChunker,
+    )
+
+
+def _build_default_document_converter() -> DocumentConverter:
+    """Construct the default ``DocumentConverter`` with crewAI's allowed formats."""
+    docling = _import_docling()
+    input_format = docling.input_format
+    return cast(
+        "DocumentConverter",
+        docling.document_converter(
+            allowed_formats=[
+                input_format.MD,
+                input_format.ASCIIDOC,
+                input_format.PDF,
+                input_format.DOCX,
+                input_format.HTML,
+                input_format.IMAGE,
+                input_format.XLSX,
+                input_format.PPTX,
+            ]
+        ),
+    )
+
+
 class CrewDoclingSource(BaseKnowledgeSource):
     """Default Source class for converting documents to markdown or json.
 
@@ -34,13 +86,11 @@ class CrewDoclingSource(BaseKnowledgeSource):
     any additional dependencies and follows the docling package as the source of truth.
     """
 
-    def __init__(self, *args: Any, **kwargs: Any) -> None:
-        if not DOCLING_AVAILABLE:
-            raise ImportError(
-                "The docling package is required to use CrewDoclingSource. "
-                "Please install it using: uv add docling"
-            )
-        super().__init__(*args, **kwargs)
+    @model_validator(mode="before")
+    @classmethod
+    def _ensure_docling_available(cls, data: Any) -> Any:
+        _import_docling()
+        return data
 
     _logger: Logger = Logger(verbose=True)
 
@@ -49,23 +99,11 @@ class CrewDoclingSource(BaseKnowledgeSource):
     file_paths: list[Path | str] = Field(default_factory=list)
     chunks: list[str] = Field(default_factory=list)
     safe_file_paths: list[Path | str] = Field(default_factory=list)
-    content: list[DoclingDocument] = Field(default_factory=list)
-    document_converter: DocumentConverter = Field(
-        default_factory=lambda: DocumentConverter(
-            allowed_formats=[
-                InputFormat.MD,
-                InputFormat.ASCIIDOC,
-                InputFormat.PDF,
-                InputFormat.DOCX,
-                InputFormat.HTML,
-                InputFormat.IMAGE,
-                InputFormat.XLSX,
-                InputFormat.PPTX,
-            ]
-        )
-    )
+    content: list[Any] = Field(default_factory=list)
+    document_converter: Any = Field(default_factory=_build_default_document_converter)
 
-    def model_post_init(self, _: Any) -> None:
+    @model_validator(mode="after")
+    def _load_sources(self) -> Self:
         if self.file_path:
             self._logger.log(
                 "warning",
@@ -75,11 +113,13 @@ class CrewDoclingSource(BaseKnowledgeSource):
             self.file_paths = self.file_path
         self.safe_file_paths = self.validate_content()
         self.content = self._load_content()
+        return self
 
     def _load_content(self) -> list[DoclingDocument]:
+        conversion_error = _import_docling().conversion_error
         try:
             return self._convert_source_to_docling_documents()
-        except ConversionError as e:
+        except conversion_error as e:
             self._logger.log(
                 "error",
                 f"Error loading content: {e}. Supported formats: {self.document_converter.allowed_formats}",
@@ -112,7 +152,7 @@ class CrewDoclingSource(BaseKnowledgeSource):
         return [result.document for result in conv_results_iter]
 
     def _chunk_doc(self, doc: DoclingDocument) -> Iterator[str]:
-        chunker = HierarchicalChunker()
+        chunker = _import_docling().hierarchical_chunker()
         for chunk in chunker.chunk(doc):
             yield chunk.text
 

lib/crewai/src/crewai/llm.py

@@ -288,6 +288,7 @@ SUPPORTED_NATIVE_PROVIDERS: Final[list[str]] = [
     "hosted_vllm",
     "cerebras",
     "dashscope",
+    "snowflake",
 ]
 
 
@@ -376,6 +377,7 @@ class LLM(BaseLLM):
                 "hosted_vllm": "hosted_vllm",
                 "cerebras": "cerebras",
                 "dashscope": "dashscope",
+                "snowflake": "snowflake",
             }
 
             canonical_provider = provider_mapping.get(prefix.lower())
@@ -494,6 +496,9 @@ class LLM(BaseLLM):
             # OpenRouter uses org/model format but accepts anything
             return True
 
+        if provider == "snowflake":
+            return True
+
         return False
 
     @classmethod
@@ -592,6 +597,11 @@ class LLM(BaseLLM):
 
             return BedrockCompletion
 
+        if provider == "snowflake":
+            from crewai.llms.providers.snowflake.completion import SnowflakeCompletion
+
+            return SnowflakeCompletion
+
         openai_compatible_providers = {
             "openrouter",
             "deepseek",

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

@@ -0,0 +1,358 @@
+from __future__ import annotations
+
+import ast
+import os
+from typing import Any, Literal
+
+from pydantic import model_validator
+
+from crewai.llms.providers.openai.completion import OpenAICompletion
+from crewai.utilities.types import LLMMessage
+
+
+SNOWFLAKE_CORTEX_PATH = "/api/v2/cortex/v1"
+SNOWFLAKE_TOKEN_ENV_VARS = (
+    "SNOWFLAKE_PAT",
+    "SNOWFLAKE_TOKEN",
+    "SNOWFLAKE_JWT",
+)
+
+
+def _normalize_snowflake_base_url(value: str) -> str:
+    """Return a Snowflake Cortex REST OpenAI-compatible base URL."""
+    base_url = value.strip().rstrip("/")
+    if not base_url:
+        raise ValueError("Snowflake account URL cannot be empty")
+
+    if "://" not in base_url:
+        base_url = f"https://{base_url}"
+
+    if base_url.endswith(SNOWFLAKE_CORTEX_PATH):
+        return base_url
+
+    if "/api/v2/cortex" in base_url:
+        raise ValueError(
+            "Snowflake base URL must be the account URL or Cortex API root "
+            f"ending in {SNOWFLAKE_CORTEX_PATH}; do not include endpoint paths."
+        )
+
+    return f"{base_url}{SNOWFLAKE_CORTEX_PATH}"
+
+
+def _base_url_from_account_identifier(account_identifier: str) -> str:
+    account = account_identifier.strip()
+    if not account:
+        raise ValueError("Snowflake account identifier cannot be empty")
+    return _normalize_snowflake_base_url(f"{account}.snowflakecomputing.com")
+
+
+class SnowflakeCompletion(OpenAICompletion):
+    """Snowflake Cortex REST API native completion implementation.
+
+    Snowflake exposes an OpenAI-compatible Chat Completions endpoint at
+    ``/api/v2/cortex/v1/chat/completions``. This provider reuses CrewAI's
+    native OpenAI transport while applying Snowflake-specific authentication,
+    endpoint normalization, and Claude-family message constraints.
+    """
+
+    provider: str = "snowflake"
+    api: Literal["completions"] = "completions"
+    account_url: str | None = None
+    account_identifier: str | None = None
+    database: str | None = None
+    schema_name: str | None = None
+    warehouse: str | None = None
+    role: str | None = None
+
+    @model_validator(mode="before")
+    @classmethod
+    def _normalize_snowflake_fields(cls, data: Any) -> Any:
+        if not isinstance(data, dict):
+            return data
+
+        data["provider"] = "snowflake"
+        api = data.get("api")
+        if api and api != "completions":
+            raise ValueError(
+                "Snowflake Cortex native provider supports only the Chat Completions API"
+            )
+        data["api"] = "completions"
+
+        data["api_key"] = cls._resolve_token(data.get("api_key"))
+        resolved_base_url = cls._resolve_base_url(data)
+        data["base_url"] = resolved_base_url
+        data["account_url"] = resolved_base_url
+
+        return data
+
+    @staticmethod
+    def _resolve_token(api_key: str | None) -> str:
+        token = api_key
+        if not token:
+            for env_var in SNOWFLAKE_TOKEN_ENV_VARS:
+                token = os.getenv(env_var)
+                if token:
+                    break
+
+        if not token:
+            raise ValueError(
+                "Snowflake token is required. Set SNOWFLAKE_PAT, SNOWFLAKE_TOKEN, "
+                "or SNOWFLAKE_JWT, or pass api_key."
+            )
+
+        if token.startswith("pat/"):
+            token = token.removeprefix("pat/")
+
+        return token
+
+    @classmethod
+    def _resolve_base_url(cls, data: dict[str, Any]) -> str:
+        explicit_base_url = data.get("base_url") or data.get("api_base")
+        if explicit_base_url:
+            return _normalize_snowflake_base_url(explicit_base_url)
+
+        account_url = data.get("account_url") or os.getenv("SNOWFLAKE_ACCOUNT_URL")
+        if account_url:
+            return _normalize_snowflake_base_url(account_url)
+
+        account_identifier = (
+            data.get("account_identifier")
+            or data.get("account")
+            or data.get("snowflake_account")
+            or os.getenv("SNOWFLAKE_ACCOUNT")
+            or os.getenv("SNOWFLAKE_ACCOUNT_ID")
+            or os.getenv("SNOWFLAKE_ACCOUNT_IDENTIFIER")
+        )
+        if account_identifier:
+            return _base_url_from_account_identifier(account_identifier)
+
+        raise ValueError(
+            "Snowflake account URL is required. Set SNOWFLAKE_ACCOUNT_URL or "
+            "SNOWFLAKE_ACCOUNT, or pass account_url/base_url/account_identifier."
+        )
+
+    def _format_messages(self, messages: str | list[LLMMessage]) -> list[LLMMessage]:
+        formatted_messages = super()._format_messages(messages)
+        if self._is_claude_model():
+            formatted_messages = self._normalize_stringified_tool_calls(
+                formatted_messages
+            )
+            formatted_messages = self._remove_incomplete_claude_tool_uses(
+                formatted_messages
+            )
+            return self._ensure_claude_conversation_ends_with_user(formatted_messages)
+        return formatted_messages
+
+    def _is_claude_model(self) -> bool:
+        model = self.model.lower()
+        return model.startswith(("claude-", "anthropic."))
+
+    @staticmethod
+    def _normalize_stringified_tool_calls(
+        messages: list[LLMMessage],
+    ) -> list[LLMMessage]:
+        normalized_messages: list[LLMMessage] = []
+        for message in messages:
+            tool_calls = message.get("tool_calls")
+            if not isinstance(tool_calls, list) or not tool_calls:
+                normalized_messages.append(message)
+                continue
+
+            normalized_tool_calls: list[Any] = []
+            changed = False
+            for tool_call in tool_calls:
+                if isinstance(tool_call, str):
+                    try:
+                        parsed_tool_call = ast.literal_eval(tool_call)
+                    except (ValueError, SyntaxError):
+                        normalized_tool_calls.append(tool_call)
+                        continue
+                    if isinstance(parsed_tool_call, dict):
+                        normalized_tool_calls.append(parsed_tool_call)
+                        changed = True
+                        continue
+                normalized_tool_calls.append(tool_call)
+
+            if changed:
+                normalized_message = dict(message)
+                normalized_message["tool_calls"] = normalized_tool_calls
+                normalized_messages.append(normalized_message)  # type: ignore[arg-type]
+            else:
+                normalized_messages.append(message)
+
+        return normalized_messages
+
+    @staticmethod
+    def _remove_incomplete_claude_tool_uses(
+        messages: list[LLMMessage],
+    ) -> list[LLMMessage]:
+        """Drop dangling Claude tool-use turns before sending to Snowflake.
+
+        Snowflake-hosted Claude models reject histories where an assistant tool
+        use is not accompanied by matching tool results. CrewAI may retry or
+        summarize after an interrupted tool cycle, leaving an assistant
+        ``tool_calls`` message in history without every corresponding
+        ``role='tool'`` result. OpenAI-family models tolerate that more often,
+        but Claude through Snowflake returns:
+        "Each 'toolUse' block must be accompanied with a matching 'toolResult' block."
+        """
+        sanitized: list[LLMMessage] = []
+        index = 0
+
+        while index < len(messages):
+            message = messages[index]
+            expected_ids = SnowflakeCompletion._extract_claude_tool_use_ids(message)
+            if message.get("role") != "assistant" or not expected_ids:
+                sanitized.append(message)
+                index += 1
+                continue
+
+            tool_result_ids: set[str] = set()
+            lookahead = index + 1
+            while lookahead < len(
+                messages
+            ) and SnowflakeCompletion._is_tool_result_message(messages[lookahead]):
+                tool_result_ids.update(
+                    SnowflakeCompletion._extract_claude_tool_result_ids(
+                        messages[lookahead]
+                    )
+                )
+                lookahead += 1
+
+            if expected_ids.issubset(tool_result_ids):
+                summary = SnowflakeCompletion._summarize_tool_results(
+                    messages[index + 1 : lookahead], expected_ids
+                )
+                if summary:
+                    sanitized.append({"role": "user", "content": summary})
+
+            index = lookahead
+
+        return sanitized
+
+    @staticmethod
+    def _summarize_tool_results(
+        messages: list[LLMMessage], expected_ids: set[str]
+    ) -> str:
+        summaries: list[str] = []
+        for message in messages:
+            result_ids = SnowflakeCompletion._extract_claude_tool_result_ids(message)
+            if not result_ids & expected_ids:
+                continue
+
+            name = message.get("name") or "tool"
+            content = message.get("content")
+            if isinstance(content, str):
+                summaries.append(f"{name}: {content}")
+            elif isinstance(content, list):
+                extracted_text = SnowflakeCompletion._extract_tool_result_text(content)
+                summaries.append(f"{name}: {extracted_text or content}")
+
+        if not summaries:
+            return ""
+
+        return "Tool results from previous tool calls:\n" + "\n".join(
+            f"- {summary}" for summary in summaries
+        )
+
+    @staticmethod
+    def _extract_tool_result_text(content: list[Any]) -> str:
+        texts: list[str] = []
+        for item in content:
+            if not isinstance(item, dict) or not isinstance(
+                item.get("toolResult"), dict
+            ):
+                continue
+            result_content = item["toolResult"].get("content", [])
+            texts.extend(
+                str(inner["text"])
+                for inner in result_content
+                if isinstance(inner, dict) and "text" in inner
+            )
+        return " ".join(texts)
+
+    @staticmethod
+    def _extract_claude_tool_use_ids(message: LLMMessage) -> set[str]:
+        tool_calls = message.get("tool_calls") or []
+        ids: set[str] = set()
+        for tool_call in tool_calls:
+            if not isinstance(tool_call, dict):
+                continue
+            tool_call_id = tool_call.get("id")
+            if isinstance(tool_call_id, str):
+                ids.add(tool_call_id)
+
+        content = message.get("content")
+        if isinstance(content, list):
+            for block in content:
+                if isinstance(block, dict) and isinstance(block.get("toolUse"), dict):
+                    tool_use_id = block["toolUse"].get("toolUseId")
+                    if isinstance(tool_use_id, str):
+                        ids.add(tool_use_id)
+        return ids
+
+    @staticmethod
+    def _extract_claude_tool_result_ids(message: LLMMessage) -> set[str]:
+        ids: set[str] = set()
+        tool_call_id = message.get("tool_call_id")
+        if isinstance(tool_call_id, str):
+            ids.add(tool_call_id)
+
+        content = message.get("content")
+        if isinstance(content, list):
+            for block in content:
+                if isinstance(block, dict) and isinstance(
+                    block.get("toolResult"), dict
+                ):
+                    tool_use_id = block["toolResult"].get("toolUseId")
+                    if isinstance(tool_use_id, str):
+                        ids.add(tool_use_id)
+        return ids
+
+    @staticmethod
+    def _is_tool_result_message(message: LLMMessage) -> bool:
+        return message.get("role") == "tool" or bool(
+            SnowflakeCompletion._extract_claude_tool_result_ids(message)
+        )
+
+    @staticmethod
+    def _ensure_claude_conversation_ends_with_user(
+        messages: list[LLMMessage],
+    ) -> list[LLMMessage]:
+        if not messages:
+            return [{"role": "user", "content": "Hello"}]
+
+        if messages[-1].get("role") == "assistant" and not messages[-1].get(
+            "tool_calls"
+        ):
+            messages = messages[:-1]
+
+        if not messages:
+            return [{"role": "user", "content": "Hello"}]
+
+        if messages[-1].get("role") == "user":
+            return messages
+
+        return [
+            *messages,
+            {
+                "role": "user",
+                "content": "Please continue and provide your final answer.",
+            },
+        ]
+
+    def _prepare_completion_params(
+        self, messages: list[LLMMessage], tools: list[dict[str, Any]] | None = None
+    ) -> dict[str, Any]:
+        params = super()._prepare_completion_params(messages=messages, tools=tools)
+        if self._is_claude_model() and "max_tokens" in params:
+            params["max_completion_tokens"] = params.pop("max_tokens")
+        return params
+
+    def supports_function_calling(self) -> bool:
+        model = self.model.lower()
+        return model.startswith(("openai-", "claude-", "anthropic."))
+
+    def supports_multimodal(self) -> bool:
+        model = self.model.lower()
+        return model.startswith(("openai-", "claude-", "anthropic."))

lib/crewai/src/crewai/skills/__init__.py

@@ -3,20 +3,15 @@
 Provides filesystem-based skill packaging with progressive disclosure.
 """
 
-from crewai.skills.cache import SkillCacheManager
 from crewai.skills.loader import activate_skill, discover_skills
 from crewai.skills.models import Skill, SkillFrontmatter
 from crewai.skills.parser import SkillParseError
-from crewai.skills.registry import is_registry_ref, resolve_registry_ref
 
 
 __all__ = [
     "Skill",
-    "SkillCacheManager",
     "SkillFrontmatter",
     "SkillParseError",
     "activate_skill",
     "discover_skills",
-    "is_registry_ref",
-    "resolve_registry_ref",
 ]

lib/crewai/src/crewai/skills/models.py

@@ -49,6 +49,7 @@ class SkillFrontmatter(BaseModel):
         license: Optional license name or reference.
         compatibility: Optional compatibility information (max 500 chars).
         metadata: Optional additional metadata as string key-value pairs.
+            Conventional keys include 'version' (skill semantic version).
         allowed_tools: Optional space-delimited list of pre-approved tools.
     """
 
@@ -71,17 +72,14 @@ class SkillFrontmatter(BaseModel):
     )
     metadata: dict[str, str] | None = Field(
         default=None,
-        description="Arbitrary string key-value pairs for custom skill metadata.",
+        description="Arbitrary string key-value pairs for custom skill metadata. "
+        "Conventional keys include 'version' for the skill's semantic version.",
     )
     allowed_tools: list[str] | None = Field(
         default=None,
         alias="allowed-tools",
         description="Pre-approved tool names the skill may use, parsed from a space-delimited string in frontmatter.",
     )
-    version: str | None = Field(
-        default=None,
-        description="Semantic version of the skill, e.g. '1.0.0'. Optional for local skills.",
-    )
 
     @model_validator(mode="before")
     @classmethod

lib/crewai/src/crewai/tools/agent_tools/read_file_tool.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import base64
+from io import BytesIO
 from typing import TYPE_CHECKING
 
 from pydantic import BaseModel, Field, PrivateAttr
@@ -64,6 +65,9 @@ class ReadFileTool(BaseTool):
         content_type = file_input.content_type
         filename = file_input.filename or file_name
 
+        if content_type == "application/pdf":
+            return self._read_pdf_text(content, filename)
+
         text_types = (
             "text/",
             "application/json",
@@ -76,3 +80,22 @@ class ReadFileTool(BaseTool):
 
         encoded = base64.b64encode(content).decode("ascii")
         return f"[Binary file: {filename} ({content_type})]\nBase64: {encoded}"
+
+    def _read_pdf_text(self, content: bytes, filename: str) -> str:
+        """Extract text from a PDF instead of returning base64."""
+        try:
+            from pypdf import PdfReader
+        except ImportError:
+            encoded = base64.b64encode(content).decode("ascii")
+            return f"[Binary file: {filename} (application/pdf)]\nBase64: {encoded}"
+
+        try:
+            reader = PdfReader(BytesIO(content))
+            page_text = [text for page in reader.pages if (text := page.extract_text())]
+        except Exception as exc:
+            return f"Unable to extract text from PDF '{filename}': {exc}"
+
+        if not page_text:
+            return f"[PDF file with no extractable text: {filename}]"
+
+        return "\n\n".join(page_text)

lib/crewai/tests/agents/test_agent.py

@@ -1067,6 +1067,62 @@ def test_agent_use_trained_data_honors_env_var(crew_training_handler, monkeypatc
     )
 
 
+@patch("crewai.agent.core.CrewTrainingHandler")
+def test_agent_use_trained_data_prefers_crew_trained_agents_file(
+    crew_training_handler, monkeypatch
+):
+    monkeypatch.setenv("CREWAI_TRAINED_AGENTS_FILE", "env_trained.pkl")
+    agent = Agent(
+        role="researcher",
+        goal="test goal",
+        backstory="test backstory",
+    )
+    task = Task(
+        description="Research the topic",
+        expected_output="A short report",
+        agent=agent,
+    )
+    crew = Crew(agents=[agent], tasks=[task], trained_agents_file="crew_trained.pkl")
+    agent.crew = crew
+    crew_training_handler.return_value.load.return_value = {}
+
+    agent._use_trained_data(task_prompt="What is 1 + 1?")
+
+    crew_training_handler.assert_has_calls(
+        [mock.call("crew_trained.pkl"), mock.call().load()]
+    )
+
+
+@patch("crewai.agent.core.CrewTrainingHandler")
+def test_agent_use_trained_data_accepts_crew_trained_agents_file_path(
+    crew_training_handler, tmp_path
+):
+    agent = Agent(
+        role="researcher",
+        goal="test goal",
+        backstory="test backstory",
+    )
+    task = Task(
+        description="Research the topic",
+        expected_output="A short report",
+        agent=agent,
+    )
+    trained_agents_file = tmp_path / "crew_trained.pkl"
+    crew = Crew(
+        agents=[agent],
+        tasks=[task],
+        trained_agents_file=trained_agents_file,
+    )
+    agent.crew = crew
+    crew_training_handler.return_value.load.return_value = {}
+
+    agent._use_trained_data(task_prompt="What is 1 + 1?")
+
+    crew_training_handler.assert_has_calls(
+        [mock.call(str(trained_agents_file)), mock.call().load()]
+    )
+
+
 def test_agent_use_trained_data_skips_load_when_file_missing(tmp_path, monkeypatch):
     monkeypatch.setenv(
         "CREWAI_TRAINED_AGENTS_FILE", str(tmp_path / "does_not_exist.pkl")

lib/crewai/tests/agents/test_agent_executor.py

@@ -7,9 +7,11 @@ flow methods, routing logic, and error handling.
 from __future__ import annotations
 
 import asyncio
+from types import SimpleNamespace
 import time
 from typing import Any
 from unittest.mock import AsyncMock, Mock, patch
+from uuid import uuid4
 
 import pytest
 from pydantic import BaseModel
@@ -64,6 +66,8 @@ from crewai.events.types.tool_usage_events import (
 from crewai.tools.tool_types import ToolResult
 from crewai.utilities.step_execution_context import StepExecutionContext
 from crewai.utilities.planning_types import TodoItem
+from crewai.utilities.file_store import clear_files, clear_task_files, store_files
+from crewai_files import TextFile
 
 class TestAgentExecutorState:
     """Test AgentExecutorState Pydantic model."""
@@ -112,6 +116,58 @@ class TestAgentExecutor:
     class StructuredResult(BaseModel):
         value: str
 
+    def test_inject_files_from_crew_task_store(self):
+        """Crew-level input_files should attach to the LLM user message."""
+        crew_id = uuid4()
+        task_id = uuid4()
+        stored_file = TextFile(source=b"stored content")
+        executor = _build_executor(
+            crew=SimpleNamespace(id=crew_id),
+            task=SimpleNamespace(id=task_id),
+        )
+        executor.state.messages = [{"role": "user", "content": "Analyze this file"}]
+
+        try:
+            store_files(crew_id, {"document": stored_file})
+            executor._inject_files_from_inputs({})
+        finally:
+            clear_files(crew_id)
+            clear_task_files(task_id)
+
+        assert executor.state.messages[0]["files"] == {"document": stored_file}
+
+    @pytest.mark.asyncio
+    async def test_ainject_files_from_crew_task_store_uses_async_store(self):
+        """Async file injection should not call the sync file store helper."""
+        crew_id = uuid4()
+        task_id = uuid4()
+        stored_file = TextFile(source=b"stored content")
+        local_file = TextFile(source=b"local content")
+        inputs = {"files": {"local": local_file}}
+        executor = _build_executor(
+            crew=SimpleNamespace(id=crew_id),
+            task=SimpleNamespace(id=task_id),
+        )
+        executor.state.messages = [{"role": "user", "content": "Analyze this file"}]
+
+        with (
+            patch(
+                "crewai.experimental.agent_executor.aget_all_files",
+                new=AsyncMock(return_value={"document": stored_file}),
+            ) as async_get_files,
+            patch(
+                "crewai.experimental.agent_executor.get_all_files",
+                side_effect=AssertionError("sync file store should not be called"),
+            ),
+        ):
+            await executor._ainject_files_from_inputs(inputs)
+
+        async_get_files.assert_awaited_once_with(crew_id, task_id)
+        assert executor.state.messages[0]["files"] == {
+            "document": stored_file,
+            "local": local_file,
+        }
+
     @pytest.fixture
     def mock_dependencies(self):
         """Create mock dependencies for executor."""

lib/crewai/tests/experimental/skills/conftest.py

@@ -0,0 +1,6 @@
+import pytest
+
+
+@pytest.fixture(autouse=True)
+def _enable_experimental_skills(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setenv("CREWAI_EXPERIMENTAL", "1")

lib/crewai/tests/experimental/skills/test_cache.py

@@ -8,7 +8,7 @@ import json
 import tarfile
 from pathlib import Path
 
-from crewai.skills.cache import SkillCacheManager
+from crewai.experimental.skills.cache import SkillCacheManager
 
 
 def _make_tar_gz(files: dict[str, str]) -> bytes:

lib/crewai/tests/experimental/skills/test_flag.py

@@ -0,0 +1,30 @@
+"""Tests for the CREWAI_EXPERIMENTAL gate on Skills Repository."""
+
+from __future__ import annotations
+
+import pytest
+
+from crewai.experimental.skills._flag import (
+    ExperimentalFeatureDisabledError,
+    require_experimental_skills,
+)
+from crewai.experimental.skills.registry import resolve_registry_ref
+
+
+def test_require_raises_without_flag(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.delenv("CREWAI_EXPERIMENTAL", raising=False)
+    with pytest.raises(ExperimentalFeatureDisabledError):
+        require_experimental_skills()
+
+
+def test_resolve_registry_ref_raises_without_flag(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    monkeypatch.delenv("CREWAI_EXPERIMENTAL", raising=False)
+    with pytest.raises(ExperimentalFeatureDisabledError):
+        resolve_registry_ref("@acme/my-skill")
+
+
+def test_require_passes_with_flag(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setenv("CREWAI_EXPERIMENTAL", "1")
+    require_experimental_skills()

lib/crewai/tests/experimental/skills/test_models_version.py

@@ -0,0 +1,32 @@
+"""Tests for the 'version' metadata key on SkillFrontmatter.
+
+Per the agentskills.io spec, `version` lives under `metadata`, not as a
+top-level frontmatter field.
+"""
+
+from __future__ import annotations
+
+from crewai.skills.models import SkillFrontmatter
+
+
+class TestSkillFrontmatterVersion:
+    def test_no_metadata_by_default(self) -> None:
+        fm = SkillFrontmatter(name="my-skill", description="A skill.")
+        assert fm.metadata is None
+
+    def test_version_via_metadata(self) -> None:
+        fm = SkillFrontmatter(
+            name="my-skill",
+            description="A skill.",
+            metadata={"version": "1.2.3"},
+        )
+        assert fm.metadata is not None
+        assert fm.metadata["version"] == "1.2.3"
+
+    def test_metadata_accepts_other_keys(self) -> None:
+        fm = SkillFrontmatter(
+            name="my-skill",
+            description="A skill.",
+            metadata={"version": "1.0.0", "author": "acme"},
+        )
+        assert fm.metadata == {"version": "1.0.0", "author": "acme"}

lib/crewai/tests/experimental/skills/test_registry.py

@@ -5,7 +5,7 @@ from __future__ import annotations
 from pathlib import Path
 from unittest.mock import MagicMock, patch
 
-from crewai.skills.registry import (
+from crewai.experimental.skills.registry import (
     SkillNotCachedError,
     is_registry_ref,
     parse_registry_ref,
@@ -75,11 +75,11 @@ class TestResolveRegistryRef:
         mock_cache.get_cached_path.return_value = None
 
         with (
-            patch("crewai.skills.registry._is_noninteractive", return_value=False),
+            patch("crewai.experimental.skills.registry._is_noninteractive", return_value=False),
             patch.object(Path, "cwd", return_value=tmp_path),
-            patch("crewai.skills.registry.SkillCacheManager", return_value=mock_cache),
+            patch("crewai.experimental.skills.registry.SkillCacheManager", return_value=mock_cache),
         ):
-            from crewai.skills.registry import resolve_registry_ref
+            from crewai.experimental.skills.registry import resolve_registry_ref
             skill = resolve_registry_ref("@acme/my-skill")
 
         assert skill.name == "my-skill"
@@ -90,11 +90,11 @@ class TestResolveRegistryRef:
         mock_cache.get_cached_path.return_value = None
 
         with (
-            patch("crewai.skills.registry._is_noninteractive", return_value=True),
+            patch("crewai.experimental.skills.registry._is_noninteractive", return_value=True),
             patch.object(Path, "cwd", return_value=tmp_path),
-            patch("crewai.skills.registry.SkillCacheManager", return_value=mock_cache),
+            patch("crewai.experimental.skills.registry.SkillCacheManager", return_value=mock_cache),
         ):
-            from crewai.skills.registry import resolve_registry_ref
+            from crewai.experimental.skills.registry import resolve_registry_ref
             with pytest.raises(SkillNotCachedError) as exc_info:
                 resolve_registry_ref("@acme/ghost-skill")
             assert "@acme/ghost-skill" in str(exc_info.value)
@@ -112,11 +112,11 @@ class TestResolveRegistryRef:
 
         # tmp_path has no ./skills/ directory
         with (
-            patch("crewai.skills.registry._is_noninteractive", return_value=False),
+            patch("crewai.experimental.skills.registry._is_noninteractive", return_value=False),
             patch.object(Path, "cwd", return_value=tmp_path),
-            patch("crewai.skills.registry.SkillCacheManager", return_value=mock_cache),
+            patch("crewai.experimental.skills.registry.SkillCacheManager", return_value=mock_cache),
         ):
-            from crewai.skills.registry import resolve_registry_ref
+            from crewai.experimental.skills.registry import resolve_registry_ref
             skill = resolve_registry_ref("@acme/cached-skill")
 
         assert skill.name == "cached-skill"

lib/crewai/tests/llms/snowflake/test_snowflake.py

@@ -0,0 +1,427 @@
+from __future__ import annotations
+
+from types import SimpleNamespace
+from unittest.mock import Mock, patch
+
+import pytest
+
+from crewai.llm import LLM
+from crewai.llms.providers.snowflake.completion import (
+    SNOWFLAKE_CORTEX_PATH,
+    SnowflakeCompletion,
+    _normalize_snowflake_base_url,
+)
+
+
+def _snowflake_env(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setenv("SNOWFLAKE_PAT", "test-pat")
+    monkeypatch.setenv("SNOWFLAKE_ACCOUNT_URL", "https://org-account.snowflakecomputing.com")
+    monkeypatch.delenv("SNOWFLAKE_TOKEN", raising=False)
+    monkeypatch.delenv("SNOWFLAKE_JWT", raising=False)
+    monkeypatch.delenv("SNOWFLAKE_ACCOUNT", raising=False)
+    monkeypatch.delenv("SNOWFLAKE_ACCOUNT_ID", raising=False)
+    monkeypatch.delenv("SNOWFLAKE_ACCOUNT_IDENTIFIER", raising=False)
+
+
+class TestSnowflakeConfig:
+    def test_normalizes_account_url_to_cortex_base_url(self):
+        assert (
+            _normalize_snowflake_base_url("https://org-account.snowflakecomputing.com")
+            == f"https://org-account.snowflakecomputing.com{SNOWFLAKE_CORTEX_PATH}"
+        )
+
+    def test_preserves_existing_cortex_base_url(self):
+        base_url = f"https://org-account.snowflakecomputing.com{SNOWFLAKE_CORTEX_PATH}"
+        assert _normalize_snowflake_base_url(base_url) == base_url
+
+    def test_rejects_endpoint_path_in_base_url(self):
+        with pytest.raises(ValueError, match="do not include endpoint paths"):
+            _normalize_snowflake_base_url(
+                "https://org-account.snowflakecomputing.com"
+                f"{SNOWFLAKE_CORTEX_PATH}/chat/completions"
+            )
+
+    def test_empty_api_key_falls_back_to_env_token(
+        self, monkeypatch: pytest.MonkeyPatch
+    ):
+        _snowflake_env(monkeypatch)
+
+        llm = SnowflakeCompletion(model="openai-gpt-4.1", api_key="")
+
+        assert llm.api_key == "test-pat"
+
+    def test_uses_env_token_and_account_url(self, monkeypatch: pytest.MonkeyPatch):
+        _snowflake_env(monkeypatch)
+
+        llm = SnowflakeCompletion(model="openai-gpt-4.1")
+
+        assert llm.api_key == "test-pat"
+        assert llm.base_url == (
+            f"https://org-account.snowflakecomputing.com{SNOWFLAKE_CORTEX_PATH}"
+        )
+        assert llm.account_url == llm.base_url
+
+    def test_strips_litellm_pat_prefix_for_compatibility(
+        self, monkeypatch: pytest.MonkeyPatch
+    ):
+        monkeypatch.setenv("SNOWFLAKE_PAT", "pat/test-pat")
+        monkeypatch.setenv("SNOWFLAKE_ACCOUNT", "org-account")
+
+        llm = SnowflakeCompletion(model="openai-gpt-4.1")
+
+        assert llm.api_key == "test-pat"
+
+    def test_missing_token_raises_clear_error(self, monkeypatch: pytest.MonkeyPatch):
+        monkeypatch.delenv("SNOWFLAKE_PAT", raising=False)
+        monkeypatch.delenv("SNOWFLAKE_TOKEN", raising=False)
+        monkeypatch.delenv("SNOWFLAKE_JWT", raising=False)
+        monkeypatch.setenv("SNOWFLAKE_ACCOUNT_URL", "https://org-account.snowflakecomputing.com")
+
+        with pytest.raises(ValueError, match="Snowflake token is required"):
+            SnowflakeCompletion(model="openai-gpt-4.1")
+
+    def test_missing_account_raises_clear_error(self, monkeypatch: pytest.MonkeyPatch):
+        monkeypatch.setenv("SNOWFLAKE_PAT", "test-pat")
+        monkeypatch.delenv("SNOWFLAKE_ACCOUNT_URL", raising=False)
+        monkeypatch.delenv("SNOWFLAKE_ACCOUNT", raising=False)
+        monkeypatch.delenv("SNOWFLAKE_ACCOUNT_ID", raising=False)
+        monkeypatch.delenv("SNOWFLAKE_ACCOUNT_IDENTIFIER", raising=False)
+
+        with pytest.raises(ValueError, match="Snowflake account URL is required"):
+            SnowflakeCompletion(model="openai-gpt-4.1")
+
+    def test_responses_api_is_rejected(self, monkeypatch: pytest.MonkeyPatch):
+        _snowflake_env(monkeypatch)
+
+        with pytest.raises(ValueError, match="supports only the Chat Completions API"):
+            SnowflakeCompletion(model="openai-gpt-4.1", api="responses")
+
+
+class TestSnowflakeFactory:
+    def test_llm_creates_native_snowflake_provider(
+        self, monkeypatch: pytest.MonkeyPatch
+    ):
+        _snowflake_env(monkeypatch)
+
+        llm = LLM(model="snowflake/openai-gpt-4.1")
+
+        assert isinstance(llm, SnowflakeCompletion)
+        assert llm.provider == "snowflake"
+        assert llm.model == "openai-gpt-4.1"
+        assert llm.is_litellm is False
+
+    def test_explicit_provider_creates_native_snowflake_provider(
+        self, monkeypatch: pytest.MonkeyPatch
+    ):
+        _snowflake_env(monkeypatch)
+
+        llm = LLM(model="claude-sonnet-4-5", provider="snowflake")
+
+        assert isinstance(llm, SnowflakeCompletion)
+        assert llm.model == "claude-sonnet-4-5"
+
+
+class TestSnowflakeRequests:
+    def test_prepare_completion_params_uses_snowflake_model_name(
+        self, monkeypatch: pytest.MonkeyPatch
+    ):
+        _snowflake_env(monkeypatch)
+        llm = SnowflakeCompletion(
+            model="openai-gpt-4.1",
+            temperature=0.2,
+            max_completion_tokens=128,
+        )
+
+        params = llm._prepare_completion_params(
+            [{"role": "user", "content": "Hello"}]
+        )
+
+        assert params["model"] == "openai-gpt-4.1"
+        assert params["temperature"] == 0.2
+        assert params["max_completion_tokens"] == 128
+        assert params["messages"] == [{"role": "user", "content": "Hello"}]
+
+    def test_claude_model_removes_trailing_assistant_prefill(
+        self, monkeypatch: pytest.MonkeyPatch
+    ):
+        _snowflake_env(monkeypatch)
+        llm = SnowflakeCompletion(model="claude-sonnet-4-5")
+
+        messages = llm._format_messages(
+            [
+                {"role": "user", "content": "Write a summary."},
+                {"role": "assistant", "content": "Here is"},
+            ]
+        )
+
+        assert messages == [{"role": "user", "content": "Write a summary."}]
+
+    def test_claude_model_normalizes_stringified_tool_calls_with_results(
+        self, monkeypatch: pytest.MonkeyPatch
+    ):
+        _snowflake_env(monkeypatch)
+        llm = SnowflakeCompletion(model="claude-sonnet-4-5")
+
+        messages = llm._format_messages(
+            [
+                {"role": "user", "content": "Use the tools."},
+                {
+                    "role": "assistant",
+                    "content": None,
+                    "tool_calls": [
+                        "{'id': 'toolu_1', 'type': 'function', 'function': {'name': \"'search_the_internet_with_serper'\", 'arguments': '\\\'{\"search_query\":\"CrewAI tools\"}\\\''}}",
+                        "{'id': 'toolu_2', 'type': 'function', 'function': {'name': \"'search_the_internet_with_serper'\", 'arguments': '\\\'{\"search_query\":\"CrewAI demos\"}\\\''}}",
+                    ],
+                },
+                {
+                    "role": "tool",
+                    "tool_call_id": "toolu_1",
+                    "name": "search_the_internet_with_serper",
+                    "content": "result 1",
+                },
+                {
+                    "role": "tool",
+                    "tool_call_id": "toolu_2",
+                    "name": "search_the_internet_with_serper",
+                    "content": "result 2",
+                },
+            ]
+        )
+
+        assert messages[-2] == {"role": "user", "content": "Use the tools."}
+        assert messages[-1]["role"] == "user"
+        assert "result 1" in messages[-1]["content"]
+        assert "result 2" in messages[-1]["content"]
+        assert all("tool_calls" not in message for message in messages)
+
+    def test_claude_model_removes_dangling_tool_call_without_result(
+        self, monkeypatch: pytest.MonkeyPatch
+    ):
+        _snowflake_env(monkeypatch)
+        llm = SnowflakeCompletion(model="claude-sonnet-4-5")
+
+        messages = llm._format_messages(
+            [
+                {"role": "user", "content": "Use the tool."},
+                {
+                    "role": "assistant",
+                    "content": None,
+                    "tool_calls": [
+                        {
+                            "id": "call_1",
+                            "type": "function",
+                            "function": {"name": "lookup", "arguments": "{}"},
+                        }
+                    ],
+                },
+            ]
+        )
+
+        assert messages == [{"role": "user", "content": "Use the tool."}]
+
+    def test_claude_model_preserves_complete_tool_call_result_pair(
+        self, monkeypatch: pytest.MonkeyPatch
+    ):
+        _snowflake_env(monkeypatch)
+        llm = SnowflakeCompletion(model="claude-sonnet-4-5")
+
+        messages = llm._format_messages(
+            [
+                {"role": "user", "content": "Use the tool."},
+                {
+                    "role": "assistant",
+                    "content": None,
+                    "tool_calls": [
+                        {
+                            "id": "call_1",
+                            "type": "function",
+                            "function": {"name": "lookup", "arguments": "{}"},
+                        }
+                    ],
+                },
+                {
+                    "role": "tool",
+                    "tool_call_id": "call_1",
+                    "content": "result",
+                },
+            ]
+        )
+
+        assert messages[-2] == {"role": "user", "content": "Use the tool."}
+        assert messages[-1]["role"] == "user"
+        assert "result" in messages[-1]["content"]
+        assert all("tool_calls" not in message for message in messages)
+
+    def test_claude_model_drops_unrelated_tool_results_from_preserved_pair(
+        self, monkeypatch: pytest.MonkeyPatch
+    ):
+        _snowflake_env(monkeypatch)
+        llm = SnowflakeCompletion(model="claude-sonnet-4-5")
+
+        messages = llm._format_messages(
+            [
+                {"role": "user", "content": "Use the tool."},
+                {
+                    "role": "assistant",
+                    "content": None,
+                    "tool_calls": [
+                        {
+                            "id": "call_1",
+                            "type": "function",
+                            "function": {"name": "lookup", "arguments": "{}"},
+                        }
+                    ],
+                },
+                {
+                    "role": "tool",
+                    "tool_call_id": "call_1",
+                    "content": "valid result",
+                },
+                {
+                    "role": "tool",
+                    "tool_call_id": "unrelated_call",
+                    "content": "unrelated result",
+                },
+            ]
+        )
+
+        assert messages[-2] == {"role": "user", "content": "Use the tool."}
+        assert messages[-1]["role"] == "user"
+        assert "valid result" in messages[-1]["content"]
+        assert "unrelated result" not in messages[-1]["content"]
+        assert all("tool_call_id" not in message for message in messages)
+
+    def test_claude_model_removes_dangling_tool_use_content_block(
+        self, monkeypatch: pytest.MonkeyPatch
+    ):
+        _snowflake_env(monkeypatch)
+        llm = SnowflakeCompletion(model="claude-sonnet-4-5")
+
+        messages = llm._format_messages(
+            [
+                {"role": "user", "content": "Use the tool."},
+                {
+                    "role": "assistant",
+                    "content": [
+                        {
+                            "toolUse": {
+                                "toolUseId": "tooluse_1",
+                                "name": "lookup",
+                                "input": {},
+                            }
+                        }
+                    ],
+                },
+                {"role": "user", "content": "Continue."},
+            ]
+        )
+
+        assert messages == [
+            {"role": "user", "content": "Use the tool."},
+            {"role": "user", "content": "Continue."},
+        ]
+
+    def test_claude_model_preserves_complete_tool_use_content_block_pair(
+        self, monkeypatch: pytest.MonkeyPatch
+    ):
+        _snowflake_env(monkeypatch)
+        llm = SnowflakeCompletion(model="claude-sonnet-4-5")
+
+        messages = llm._format_messages(
+            [
+                {"role": "user", "content": "Use the tool."},
+                {
+                    "role": "assistant",
+                    "content": [
+                        {
+                            "toolUse": {
+                                "toolUseId": "tooluse_1",
+                                "name": "lookup",
+                                "input": {},
+                            }
+                        }
+                    ],
+                },
+                {
+                    "role": "user",
+                    "content": [
+                        {
+                            "toolResult": {
+                                "toolUseId": "tooluse_1",
+                                "content": [{"text": "result"}],
+                            }
+                        }
+                    ],
+                },
+            ]
+        )
+
+        assert messages[-2] == {"role": "user", "content": "Use the tool."}
+        assert messages[-1]["role"] == "user"
+        assert "result" in messages[-1]["content"]
+        assert "toolResult" not in messages[-1]["content"]
+        assert all(
+            not (
+                message.get("role") == "assistant"
+                and isinstance(message.get("content"), list)
+            )
+            for message in messages
+        )
+
+    def test_claude_model_maps_max_tokens_to_max_completion_tokens(
+        self, monkeypatch: pytest.MonkeyPatch
+    ):
+        _snowflake_env(monkeypatch)
+        llm = SnowflakeCompletion(model="claude-sonnet-4-5", max_tokens=256)
+
+        params = llm._prepare_completion_params(
+            [{"role": "user", "content": "Hello"}]
+        )
+
+        assert "max_tokens" not in params
+        assert params["max_completion_tokens"] == 256
+
+    def test_streaming_params_include_usage(self, monkeypatch: pytest.MonkeyPatch):
+        _snowflake_env(monkeypatch)
+        llm = SnowflakeCompletion(model="openai-gpt-4.1", stream=True)
+
+        params = llm._prepare_completion_params(
+            [{"role": "user", "content": "Hello"}]
+        )
+
+        assert params["stream"] is True
+        assert params["stream_options"] == {"include_usage": True}
+
+    def test_non_streaming_call_uses_native_openai_client(
+        self, monkeypatch: pytest.MonkeyPatch
+    ):
+        _snowflake_env(monkeypatch)
+        llm = SnowflakeCompletion(model="openai-gpt-4.1")
+        fake_response = SimpleNamespace(
+            usage=SimpleNamespace(
+                prompt_tokens=3,
+                completion_tokens=2,
+                total_tokens=5,
+                prompt_tokens_details=None,
+                completion_tokens_details=None,
+            ),
+            choices=[
+                SimpleNamespace(
+                    message=SimpleNamespace(content="Snowflake response", tool_calls=None)
+                )
+            ],
+        )
+        create = Mock(return_value=fake_response)
+        fake_client = SimpleNamespace(
+            chat=SimpleNamespace(completions=SimpleNamespace(create=create))
+        )
+
+        with patch.object(llm, "_get_sync_client", return_value=fake_client):
+            response = llm.call([{"role": "user", "content": "Hello"}])
+
+        assert response == "Snowflake response"
+        create.assert_called_once()
+        assert create.call_args.kwargs["model"] == "openai-gpt-4.1"
+        assert create.call_args.kwargs["messages"] == [
+            {"role": "user", "content": "Hello"}
+        ]

lib/crewai/tests/llms/test_multimodal.py

@@ -108,6 +108,16 @@ class TestLiteLLMMultimodal:
 
         assert result == []
 
+    def test_format_responses_pdf_with_concrete_gpt_model(self) -> None:
+        """Test OpenAI Responses PDF support with an inferred GPT provider."""
+        files = {"doc": PDFFile(source=MINIMAL_PDF)}
+
+        result = format_multimodal_content(files, "gpt-4o-mini", api="responses")
+
+        assert len(result) == 1
+        assert result[0]["type"] == "input_file"
+        assert result[0]["file_data"].startswith("data:application/pdf;base64,")
+
 
 @pytest.mark.skipif(not HAS_ANTHROPIC, reason="Anthropic SDK not installed")
 class TestAnthropicMultimodal:
@@ -370,4 +380,4 @@ class TestMultipleFilesFormatting:
 
         result = format_multimodal_content({}, llm.model)
 
-        assert result == []
+        assert result == []

lib/crewai/tests/skills/test_models_version.py

@@ -1,32 +0,0 @@
-"""Tests for the version field added to SkillFrontmatter."""
-
-from __future__ import annotations
-
-import pytest
-from pydantic import ValidationError
-
-from crewai.skills.models import SkillFrontmatter
-
-
-class TestSkillFrontmatterVersion:
-    def test_version_defaults_to_none(self) -> None:
-        fm = SkillFrontmatter(name="my-skill", description="A skill.")
-        assert fm.version is None
-
-    def test_version_can_be_set(self) -> None:
-        fm = SkillFrontmatter(name="my-skill", description="A skill.", version="1.2.3")
-        assert fm.version == "1.2.3"
-
-    def test_existing_frontmatter_without_version_still_valid(self) -> None:
-        """Backward compat: existing SKILL.md files without version must still parse."""
-        fm = SkillFrontmatter(name="old-skill", description="Old skill without version.")
-        assert fm.version is None
-
-    def test_version_is_optional_string(self) -> None:
-        fm = SkillFrontmatter(name="my-skill", description="Desc.", version=None)
-        assert fm.version is None
-
-    def test_frontmatter_is_frozen(self) -> None:
-        fm = SkillFrontmatter(name="my-skill", description="A skill.", version="1.0.0")
-        with pytest.raises(ValidationError):
-            fm.version = "2.0.0"  # type: ignore[misc]

lib/crewai/tests/test_async_human_feedback.py

@@ -569,13 +569,13 @@ class TestFlowResumeWithFeedback:
 
             flow = TestFlow.from_pending("async-direct-test", persistence)
 
-            with patch("crewai.flow.flow.crewai_event_bus.emit"):
+            with patch("crewai.flow.runtime.crewai_event_bus.emit"):
                 result = await flow.resume_async("async feedback")
 
             assert flow.last_human_feedback is not None
             assert flow.last_human_feedback.feedback == "async feedback"
 
-    @patch("crewai.flow.flow.crewai_event_bus.emit")
+    @patch("crewai.flow.runtime.crewai_event_bus.emit")
     def test_resume_basic(self, mock_emit: MagicMock) -> None:
         """Test basic resume functionality."""
         with tempfile.TemporaryDirectory() as tmpdir:
@@ -615,7 +615,7 @@ class TestFlowResumeWithFeedback:
 
             assert persistence.load_pending_feedback("resume-test-123") is None
 
-    @patch("crewai.flow.flow.crewai_event_bus.emit")
+    @patch("crewai.flow.runtime.crewai_event_bus.emit")
     def test_resume_routing(self, mock_emit: MagicMock) -> None:
         """Test resume with routing."""
         with tempfile.TemporaryDirectory() as tmpdir:
@@ -697,7 +697,7 @@ class TestAsyncHumanFeedbackIntegration:
         assert hasattr(method, "__human_feedback_config__")
         assert method.__human_feedback_config__.provider is not None
 
-    @patch("crewai.flow.flow.crewai_event_bus.emit")
+    @patch("crewai.flow.runtime.crewai_event_bus.emit")
     def test_async_provider_pauses_flow(self, mock_emit: MagicMock) -> None:
         """Test that async provider pauses flow execution."""
         with tempfile.TemporaryDirectory() as tmpdir:
@@ -743,7 +743,7 @@ class TestAsyncHumanFeedbackIntegration:
             persisted = persistence.load_pending_feedback(flow_id)
             assert persisted is not None
 
-    @patch("crewai.flow.flow.crewai_event_bus.emit")
+    @patch("crewai.flow.runtime.crewai_event_bus.emit")
     def test_full_async_flow_cycle(self, mock_emit: MagicMock) -> None:
         """Test complete async flow: start -> pause -> resume."""
         with tempfile.TemporaryDirectory() as tmpdir:
@@ -804,7 +804,7 @@ class TestAsyncHumanFeedbackIntegration:
 class TestAutoPersistence:
     """Tests for automatic persistence when no persistence is provided."""
 
-    @patch("crewai.flow.flow.crewai_event_bus.emit")
+    @patch("crewai.flow.runtime.crewai_event_bus.emit")
     def test_auto_persistence_when_none_provided(self, mock_emit: MagicMock) -> None:
         """Test that persistence is auto-created when HumanFeedbackPending is raised."""
 
@@ -925,7 +925,7 @@ class TestCollapseToOutcomeJsonParsing:
 class TestLLMObjectPreservedInContext:
     """Tests that BaseLLM objects have their model string preserved in PendingFeedbackContext."""
 
-    @patch("crewai.flow.flow.crewai_event_bus.emit")
+    @patch("crewai.flow.runtime.crewai_event_bus.emit")
     def test_basellm_object_model_string_survives_roundtrip(self, mock_emit: MagicMock) -> None:
         """Test that when llm is a BaseLLM object, its model string is stored in context
         so that outcome collapsing works after async pause/resume.
@@ -1125,7 +1125,7 @@ class TestAsyncHumanFeedbackEdgeCases:
 
             flow = TestFlow.from_pending("default-test", persistence)
 
-            with patch("crewai.flow.flow.crewai_event_bus.emit"):
+            with patch("crewai.flow.runtime.crewai_event_bus.emit"):
                 result = flow.resume("")
 
             assert flow.last_human_feedback.outcome == "approved"
@@ -1159,7 +1159,7 @@ class TestAsyncHumanFeedbackEdgeCases:
 
             flow = TestFlow.from_pending("no-feedback-test", persistence)
 
-            with patch("crewai.flow.flow.crewai_event_bus.emit"):
+            with patch("crewai.flow.runtime.crewai_event_bus.emit"):
                 result = flow.resume()
 
             assert flow.last_human_feedback.outcome == "approved"
@@ -1213,7 +1213,7 @@ class TestLiveLLMPreservationOnResume:
         assert hasattr(method, "_hf_llm")
         assert method._hf_llm == "gpt-4o-mini"
 
-    @patch("crewai.flow.flow.crewai_event_bus.emit")
+    @patch("crewai.flow.runtime.crewai_event_bus.emit")
     def test_resume_async_uses_live_basellm_over_serialized_string(
         self, mock_emit: MagicMock
     ) -> None:
@@ -1286,7 +1286,7 @@ class TestLiveLLMPreservationOnResume:
             # And verify it's a BaseLLM instance, not a string
             assert isinstance(captured_llm[0], BaseLLM)
 
-    @patch("crewai.flow.flow.crewai_event_bus.emit")
+    @patch("crewai.flow.runtime.crewai_event_bus.emit")
     def test_resume_async_falls_back_to_serialized_string_when_no_hf_llm(
         self, mock_emit: MagicMock
     ) -> None:
@@ -1344,7 +1344,7 @@ class TestLiveLLMPreservationOnResume:
             assert isinstance(captured_llm[0], BaseLLMClass)
             assert captured_llm[0].model == "gpt-4o-mini"
 
-    @patch("crewai.flow.flow.crewai_event_bus.emit")
+    @patch("crewai.flow.runtime.crewai_event_bus.emit")
     def test_resume_async_uses_string_from_context_when_hf_llm_is_string(
         self, mock_emit: MagicMock
     ) -> None:

lib/crewai/tests/test_crew.py

@@ -3010,6 +3010,23 @@ def test__setup_for_training(researcher, writer):
         assert agent.allow_delegation is False
 
 
+def test_crew_trained_agents_file_is_preserved_on_copy(researcher):
+    task = Task(
+        description="Come up with a list of 5 interesting ideas to explore for an article",
+        expected_output="5 bullet points with a paragraph for each idea.",
+        agent=researcher,
+    )
+    crew = Crew(
+        agents=[researcher],
+        tasks=[task],
+        trained_agents_file="custom_trained_agents.pkl",
+    )
+
+    cloned_crew = crew.copy()
+
+    assert cloned_crew.trained_agents_file == "custom_trained_agents.pkl"
+
+
 @pytest.mark.vcr()
 def test_replay_feature(researcher, writer):
     list_ideas = Task(

lib/crewai/tests/test_flow.py

@@ -161,6 +161,87 @@ def test_flow_with_or_condition():
     )
 
 
+def test_or_listener_fires_once_across_parallel_starts():
+    """Parallel ``@start`` paths feeding ``or_`` must not double-fire the listener."""
+    fire_count = 0
+
+    class ParallelOrFlow(Flow):
+        @start()
+        async def fast_start(self):
+            return "fast"
+
+        @start()
+        async def slow_start(self):
+            await asyncio.sleep(0.2)
+            return "slow"
+
+        @listen(or_(fast_start, slow_start))
+        def handler(self):
+            nonlocal fire_count
+            fire_count += 1
+
+    asyncio.run(ParallelOrFlow().kickoff_async())
+
+    assert fire_count == 1
+
+
+def test_or_listener_re_arms_across_router_loop():
+    """Regression for #5972: multi-source ``or_`` re-fires on each router emission."""
+    fire_count = 0
+
+    class CyclicOrFlow(Flow):
+        iteration = 0
+
+        @start()
+        def kick(self):
+            return "kick"
+
+        @router(kick)
+        def initial_router(self):
+            return "SignalA"
+
+        @listen(or_("SignalA", "SignalB"))
+        def handler(self):
+            nonlocal fire_count
+            fire_count += 1
+
+        @router(handler)
+        def loop_router(self):
+            self.iteration += 1
+            return "stop" if self.iteration >= 3 else "SignalB"
+
+    CyclicOrFlow().kickoff()
+
+    assert fire_count == 3
+
+
+def test_or_listener_does_not_double_fire_across_chained_routers():
+    """Chained routers within one dispatch wave must not re-fire the same ``or_`` listener."""
+    fire_count = 0
+
+    class ChainedRouterOrFlow(Flow):
+        @start()
+        def kick(self):
+            return "kick"
+
+        @router(kick)
+        def router_a(self):
+            return "SignalA"
+
+        @router("SignalA")
+        def router_b(self):
+            return "SignalB"
+
+        @listen(or_("SignalA", "SignalB"))
+        def handler(self):
+            nonlocal fire_count
+            fire_count += 1
+
+    ChainedRouterOrFlow().kickoff()
+
+    assert fire_count == 1
+
+
 def test_flow_with_router():
     """Test a flow that uses a router method to determine the next step."""
     execution_order = []