feat: Add Azure AD token authentication support for Azure provider

This commit adds support for Azure AD token authentication (Microsoft Entra ID)
to the Azure AI Inference native provider, addressing issue #4069.

Changes:
- Add credential parameter for passing TokenCredential directly
- Add azure_ad_token parameter and AZURE_AD_TOKEN env var support
- Add use_default_credential flag for DefaultAzureCredential
- Add _StaticTokenCredential class for wrapping static tokens
- Add _select_credential method with clear priority order
- Update error messages to reflect all authentication options
- Add comprehensive tests for all new authentication methods

Authentication Priority:
1. credential parameter (explicit TokenCredential)
2. azure_ad_token parameter or AZURE_AD_TOKEN env var
3. api_key parameter or AZURE_API_KEY env var
4. use_default_credential=True (DefaultAzureCredential)

Fixes #4069

Co-Authored-By: João <joao@crewai.com>

.github/workflows/publish.yml

@@ -1,14 +1,9 @@
 name: Publish to PyPI
 
 on:
-  repository_dispatch:
-    types: [deployment-tests-passed]
+  release:
+    types: [ published ]
   workflow_dispatch:
-    inputs:
-      release_tag:
-        description: 'Release tag to publish'
-        required: false
-        type: string
 
 jobs:
   build:
@@ -17,21 +12,7 @@ jobs:
     permissions:
         contents: read
     steps:
-      - name: Determine release tag
-        id: release
-        run: |
-          # Priority: workflow_dispatch input > repository_dispatch payload > default branch
-          if [ -n "${{ inputs.release_tag }}" ]; then
-            echo "tag=${{ inputs.release_tag }}" >> $GITHUB_OUTPUT
-          elif [ -n "${{ github.event.client_payload.release_tag }}" ]; then
-            echo "tag=${{ github.event.client_payload.release_tag }}" >> $GITHUB_OUTPUT
-          else
-            echo "tag=" >> $GITHUB_OUTPUT
-          fi
-
       - uses: actions/checkout@v4
-        with:
-          ref: ${{ steps.release.outputs.tag || github.ref }}
 
       - name: Set up Python
         uses: actions/setup-python@v5

.github/workflows/trigger-deployment-tests.yml

@@ -1,18 +0,0 @@
-name: Trigger Deployment Tests
-
-on:
-  release:
-    types: [published]
-
-jobs:
-  trigger:
-    name: Trigger deployment tests
-    runs-on: ubuntu-latest
-    steps:
-      - name: Trigger deployment tests
-        uses: peter-evans/repository-dispatch@v3
-        with:
-          token: ${{ secrets.CREWAI_DEPLOYMENTS_PAT }}
-          repository: ${{ secrets.CREWAI_DEPLOYMENTS_REPOSITORY }}
-          event-type: crewai-release
-          client-payload: '{"release_tag": "${{ github.event.release.tag_name }}", "release_name": "${{ github.event.release.name }}"}'

docs/en/api-reference/introduction.mdx

@@ -16,17 +16,16 @@ Welcome to the CrewAI AOP API reference. This API allows you to programmatically
     Navigate to your crew's detail page in the CrewAI AOP dashboard and copy your Bearer Token from the Status tab.
   </Step>
 
-<Step title="Discover Required Inputs">
-  Use the `GET /inputs` endpoint to see what parameters your crew expects.
-</Step>
+  <Step title="Discover Required Inputs">
+    Use the `GET /inputs` endpoint to see what parameters your crew expects.
+  </Step>
 
-<Step title="Start a Crew Execution">
-  Call `POST /kickoff` with your inputs to start the crew execution and receive
-  a `kickoff_id`.
-</Step>
+  <Step title="Start a Crew Execution">
+    Call `POST /kickoff` with your inputs to start the crew execution and receive a `kickoff_id`.
+  </Step>
 
   <Step title="Monitor Progress">
-    Use `GET /{kickoff_id}/status` to check execution status and retrieve results.
+    Use `GET /status/{kickoff_id}` to check execution status and retrieve results.
   </Step>
 </Steps>
 
@@ -41,14 +40,13 @@ curl -H "Authorization: Bearer YOUR_CREW_TOKEN" \
 
 ### Token Types
 
-| Token Type            | Scope                     | Use Case                                                     |
-| :-------------------- | :------------------------ | :----------------------------------------------------------- |
-| **Bearer Token**      | Organization-level access | Full crew operations, ideal for server-to-server integration |
-| **User Bearer Token** | User-scoped access        | Limited permissions, suitable for user-specific operations   |
+| Token Type | Scope | Use Case |
+|:-----------|:--------|:----------|
+| **Bearer Token** | Organization-level access | Full crew operations, ideal for server-to-server integration |
+| **User Bearer Token** | User-scoped access | Limited permissions, suitable for user-specific operations |
 
 <Tip>
-  You can find both token types in the Status tab of your crew's detail page in
-  the CrewAI AOP dashboard.
+You can find both token types in the Status tab of your crew's detail page in the CrewAI AOP dashboard.
 </Tip>
 
 ## Base URL
@@ -65,33 +63,29 @@ Replace `your-crew-name` with your actual crew's URL from the dashboard.
 
 1. **Discovery**: Call `GET /inputs` to understand what your crew needs
 2. **Execution**: Submit inputs via `POST /kickoff` to start processing
-3. **Monitoring**: Poll `GET /{kickoff_id}/status` until completion
+3. **Monitoring**: Poll `GET /status/{kickoff_id}` until completion
 4. **Results**: Extract the final output from the completed response
 
 ## Error Handling
 
 The API uses standard HTTP status codes:
 
-| Code  | Meaning                                    |
-| ----- | :----------------------------------------- |
-| `200` | Success                                    |
-| `400` | Bad Request - Invalid input format         |
-| `401` | Unauthorized - Invalid bearer token        |
-| `404` | Not Found - Resource doesn't exist         |
+| Code | Meaning |
+|------|:--------|
+| `200` | Success |
+| `400` | Bad Request - Invalid input format |
+| `401` | Unauthorized - Invalid bearer token |
+| `404` | Not Found - Resource doesn't exist |
 | `422` | Validation Error - Missing required inputs |
-| `500` | Server Error - Contact support             |
+| `500` | Server Error - Contact support |
 
 ## Interactive Testing
 
 <Info>
-  **Why no "Send" button?** Since each CrewAI AOP user has their own unique crew
-  URL, we use **reference mode** instead of an interactive playground to avoid
-  confusion. This shows you exactly what the requests should look like without
-  non-functional send buttons.
+**Why no "Send" button?** Since each CrewAI AOP user has their own unique crew URL, we use **reference mode** instead of an interactive playground to avoid confusion. This shows you exactly what the requests should look like without non-functional send buttons.
 </Info>
 
 Each endpoint page shows you:
-
 - ✅ **Exact request format** with all parameters
 - ✅ **Response examples** for success and error cases
 - ✅ **Code samples** in multiple languages (cURL, Python, JavaScript, etc.)
@@ -109,7 +103,6 @@ Each endpoint page shows you:
 </CardGroup>
 
 **Example workflow:**
-
 1. **Copy this cURL example** from any endpoint page
 2. **Replace `your-actual-crew-name.crewai.com`** with your real crew URL
 3. **Replace the Bearer token** with your real token from the dashboard
@@ -118,18 +111,10 @@ Each endpoint page shows you:
 ## Need Help?
 
 <CardGroup cols={2}>
-  <Card
-    title="Enterprise Support"
-    icon="headset"
-    href="mailto:support@crewai.com"
-  >
+  <Card title="Enterprise Support" icon="headset" href="mailto:support@crewai.com">
     Get help with API integration and troubleshooting
   </Card>
-  <Card
-    title="Enterprise Dashboard"
-    icon="chart-line"
-    href="https://app.crewai.com"
-  >
+  <Card title="Enterprise Dashboard" icon="chart-line" href="https://app.crewai.com">
     Manage your crews and view execution logs
   </Card>
 </CardGroup>

docs/en/api-reference/status.mdx

@@ -1,6 +1,8 @@
 ---
-title: "GET /{kickoff_id}/status"
+title: "GET /status/{kickoff_id}"
 description: "Get execution status"
-openapi: "/enterprise-api.en.yaml GET /{kickoff_id}/status"
+openapi: "/enterprise-api.en.yaml GET /status/{kickoff_id}"
 mode: "wide"
 ---
+
+

docs/en/enterprise/guides/deploy-crew.mdx

@@ -187,97 +187,6 @@ You can also deploy your crews directly through the CrewAI AOP web interface by
 
 </Steps>
 
-## Option 3: Redeploy Using API (CI/CD Integration)
-
-For automated deployments in CI/CD pipelines, you can use the CrewAI API to trigger redeployments of existing crews. This is particularly useful for GitHub Actions, Jenkins, or other automation workflows.
-
-<Steps>
-  <Step title="Get Your Personal Access Token">
-
-    Navigate to your CrewAI AOP account settings to generate an API token:
-
-    1. Go to [app.crewai.com](https://app.crewai.com)
-    2. Click on **Settings** → **Account** → **Personal Access Token**
-    3. Generate a new token and copy it securely
-    4. Store this token as a secret in your CI/CD system
-
-  </Step>
-
-  <Step title="Find Your Automation UUID">
-
-    Locate the unique identifier for your deployed crew:
-
-    1. Go to **Automations** in your CrewAI AOP dashboard
-    2. Select your existing automation/crew
-    3. Click on **Additional Details**
-    4. Copy the **UUID** - this identifies your specific crew deployment
-
-  </Step>
-
-  <Step title="Trigger Redeployment via API">
-
-    Use the Deploy API endpoint to trigger a redeployment:
-
-    ```bash
-    curl -i -X POST \
-         -H "Authorization: Bearer YOUR_PERSONAL_ACCESS_TOKEN" \
-         https://app.crewai.com/crewai_plus/api/v1/crews/YOUR-AUTOMATION-UUID/deploy
-
-    # HTTP/2 200
-    # content-type: application/json
-    #
-    # {
-    #   "uuid": "your-automation-uuid",
-    #   "status": "Deploy Enqueued",
-    #   "public_url": "https://your-crew-deployment.crewai.com",
-    #   "token": "your-bearer-token"
-    # }
-    ```
-
-    <Info>
-    If your automation was first created connected to Git, the API will automatically pull the latest changes from your repository before redeploying.
-    </Info>
-
-
-  </Step>
-
-  <Step title="GitHub Actions Integration Example">
-
-    Here's a GitHub Actions workflow with more complex deployment triggers:
-
-    ```yaml
-    name: Deploy CrewAI Automation
-
-    on:
-      push:
-        branches: [ main ]
-      pull_request:
-        types: [ labeled ]
-      release:
-        types: [ published ]
-
-    jobs:
-      deploy:
-        runs-on: ubuntu-latest
-        if: |
-          (github.event_name == 'push' && github.ref == 'refs/heads/main') ||
-          (github.event_name == 'pull_request' && contains(github.event.pull_request.labels.*.name, 'deploy')) ||
-          (github.event_name == 'release')
-        steps:
-          - name: Trigger CrewAI Redeployment
-            run: |
-              curl -X POST \
-                   -H "Authorization: Bearer ${{ secrets.CREWAI_PAT }}" \
-                   https://app.crewai.com/crewai_plus/api/v1/crews/${{ secrets.CREWAI_AUTOMATION_UUID }}/deploy
-    ```
-
-    <Tip>
-    Add `CREWAI_PAT` and `CREWAI_AUTOMATION_UUID` as repository secrets. For PR deployments, add a "deploy" label to trigger the workflow.
-    </Tip>
-
-    </Step>
-  </Steps>
-
 ## ⚠️ Environment Variable Security Requirements
 
 <Warning>

docs/enterprise-api.base.yaml

@@ -35,7 +35,7 @@ info:
 
     1. **Discover inputs** using `GET /inputs`
     2. **Start execution** using `POST /kickoff`
-    3. **Monitor progress** using `GET /{kickoff_id}/status`
+    3. **Monitor progress** using `GET /status/{kickoff_id}`
   version: 1.0.0
   contact:
     name: CrewAI Support
@@ -63,7 +63,7 @@ paths:
         Use this endpoint to discover what inputs you need to provide when starting a crew execution.
       operationId: getRequiredInputs
       responses:
-        "200":
+        '200':
           description: Successfully retrieved required inputs
           content:
             application/json:
@@ -84,21 +84,13 @@ paths:
                 outreach_crew:
                   summary: Outreach crew inputs
                   value:
-                    inputs:
-                      [
-                        "name",
-                        "title",
-                        "company",
-                        "industry",
-                        "our_product",
-                        "linkedin_url",
-                      ]
-        "401":
-          $ref: "#/components/responses/UnauthorizedError"
-        "404":
-          $ref: "#/components/responses/NotFoundError"
-        "500":
-          $ref: "#/components/responses/ServerError"
+                    inputs: ["name", "title", "company", "industry", "our_product", "linkedin_url"]
+        '401':
+          $ref: '#/components/responses/UnauthorizedError'
+        '404':
+          $ref: '#/components/responses/NotFoundError'
+        '500':
+          $ref: '#/components/responses/ServerError'
 
   /kickoff:
     post:
@@ -178,7 +170,7 @@ paths:
                   taskWebhookUrl: "https://api.example.com/webhooks/task"
                   crewWebhookUrl: "https://api.example.com/webhooks/crew"
       responses:
-        "200":
+        '200':
           description: Crew execution started successfully
           content:
             application/json:
@@ -190,24 +182,24 @@ paths:
                     format: uuid
                     description: Unique identifier for tracking this execution
                     example: "abcd1234-5678-90ef-ghij-klmnopqrstuv"
-        "400":
+        '400':
           description: Invalid request body or missing required inputs
           content:
             application/json:
               schema:
-                $ref: "#/components/schemas/Error"
-        "401":
-          $ref: "#/components/responses/UnauthorizedError"
-        "422":
+                $ref: '#/components/schemas/Error'
+        '401':
+          $ref: '#/components/responses/UnauthorizedError'
+        '422':
           description: Validation error - ensure all required inputs are provided
           content:
             application/json:
               schema:
-                $ref: "#/components/schemas/ValidationError"
-        "500":
-          $ref: "#/components/responses/ServerError"
+                $ref: '#/components/schemas/ValidationError'
+        '500':
+          $ref: '#/components/responses/ServerError'
 
-  /{kickoff_id}/status:
+  /status/{kickoff_id}:
     get:
       summary: Get Execution Status
       description: |
@@ -230,15 +222,15 @@ paths:
             format: uuid
             example: "abcd1234-5678-90ef-ghij-klmnopqrstuv"
       responses:
-        "200":
+        '200':
           description: Successfully retrieved execution status
           content:
             application/json:
               schema:
                 oneOf:
-                  - $ref: "#/components/schemas/ExecutionRunning"
-                  - $ref: "#/components/schemas/ExecutionCompleted"
-                  - $ref: "#/components/schemas/ExecutionError"
+                  - $ref: '#/components/schemas/ExecutionRunning'
+                  - $ref: '#/components/schemas/ExecutionCompleted'
+                  - $ref: '#/components/schemas/ExecutionError'
               examples:
                 running:
                   summary: Execution in progress
@@ -270,19 +262,19 @@ paths:
                     status: "error"
                     error: "Task execution failed: Invalid API key for external service"
                     execution_time: 23.1
-        "401":
-          $ref: "#/components/responses/UnauthorizedError"
-        "404":
+        '401':
+          $ref: '#/components/responses/UnauthorizedError'
+        '404':
           description: Kickoff ID not found
           content:
             application/json:
               schema:
-                $ref: "#/components/schemas/Error"
+                $ref: '#/components/schemas/Error'
               example:
                 error: "Execution not found"
                 message: "No execution found with ID: abcd1234-5678-90ef-ghij-klmnopqrstuv"
-        "500":
-          $ref: "#/components/responses/ServerError"
+        '500':
+          $ref: '#/components/responses/ServerError'
 
   /resume:
     post:
@@ -362,7 +354,7 @@ paths:
                   taskWebhookUrl: "https://api.example.com/webhooks/task"
                   crewWebhookUrl: "https://api.example.com/webhooks/crew"
       responses:
-        "200":
+        '200':
           description: Execution resumed successfully
           content:
             application/json:
@@ -389,28 +381,28 @@ paths:
                   value:
                     status: "retrying"
                     message: "Task will be retried with your feedback"
-        "400":
+        '400':
           description: Invalid request body or execution not in pending state
           content:
             application/json:
               schema:
-                $ref: "#/components/schemas/Error"
+                $ref: '#/components/schemas/Error'
               example:
                 error: "Invalid Request"
                 message: "Execution is not in pending human input state"
-        "401":
-          $ref: "#/components/responses/UnauthorizedError"
-        "404":
+        '401':
+          $ref: '#/components/responses/UnauthorizedError'
+        '404':
           description: Execution ID or Task ID not found
           content:
             application/json:
               schema:
-                $ref: "#/components/schemas/Error"
+                $ref: '#/components/schemas/Error'
               example:
                 error: "Not Found"
                 message: "Execution ID not found"
-        "500":
-          $ref: "#/components/responses/ServerError"
+        '500':
+          $ref: '#/components/responses/ServerError'
 
 components:
   securitySchemes:
@@ -466,7 +458,7 @@ components:
             tasks:
               type: array
               items:
-                $ref: "#/components/schemas/TaskResult"
+                $ref: '#/components/schemas/TaskResult'
         execution_time:
           type: number
           description: Total execution time in seconds
@@ -544,7 +536,7 @@ components:
       content:
         application/json:
           schema:
-            $ref: "#/components/schemas/Error"
+            $ref: '#/components/schemas/Error'
           example:
             error: "Unauthorized"
             message: "Invalid or missing bearer token"
@@ -554,7 +546,7 @@ components:
       content:
         application/json:
           schema:
-            $ref: "#/components/schemas/Error"
+            $ref: '#/components/schemas/Error'
           example:
             error: "Not Found"
             message: "The requested resource was not found"
@@ -564,7 +556,7 @@ components:
       content:
         application/json:
           schema:
-            $ref: "#/components/schemas/Error"
+            $ref: '#/components/schemas/Error'
           example:
             error: "Internal Server Error"
             message: "An unexpected error occurred"

docs/enterprise-api.en.yaml

@@ -35,7 +35,7 @@ info:
 
     1. **Discover inputs** using `GET /inputs`
     2. **Start execution** using `POST /kickoff`
-    3. **Monitor progress** using `GET /{kickoff_id}/status`
+    3. **Monitor progress** using `GET /status/{kickoff_id}`
   version: 1.0.0
   contact:
     name: CrewAI Support
@@ -63,7 +63,7 @@ paths:
         Use this endpoint to discover what inputs you need to provide when starting a crew execution.
       operationId: getRequiredInputs
       responses:
-        "200":
+        '200':
           description: Successfully retrieved required inputs
           content:
             application/json:
@@ -84,21 +84,13 @@ paths:
                 outreach_crew:
                   summary: Outreach crew inputs
                   value:
-                    inputs:
-                      [
-                        "name",
-                        "title",
-                        "company",
-                        "industry",
-                        "our_product",
-                        "linkedin_url",
-                      ]
-        "401":
-          $ref: "#/components/responses/UnauthorizedError"
-        "404":
-          $ref: "#/components/responses/NotFoundError"
-        "500":
-          $ref: "#/components/responses/ServerError"
+                    inputs: ["name", "title", "company", "industry", "our_product", "linkedin_url"]
+        '401':
+          $ref: '#/components/responses/UnauthorizedError'
+        '404':
+          $ref: '#/components/responses/NotFoundError'
+        '500':
+          $ref: '#/components/responses/ServerError'
 
   /kickoff:
     post:
@@ -178,7 +170,7 @@ paths:
                   taskWebhookUrl: "https://api.example.com/webhooks/task"
                   crewWebhookUrl: "https://api.example.com/webhooks/crew"
       responses:
-        "200":
+        '200':
           description: Crew execution started successfully
           content:
             application/json:
@@ -190,24 +182,24 @@ paths:
                     format: uuid
                     description: Unique identifier for tracking this execution
                     example: "abcd1234-5678-90ef-ghij-klmnopqrstuv"
-        "400":
+        '400':
           description: Invalid request body or missing required inputs
           content:
             application/json:
               schema:
-                $ref: "#/components/schemas/Error"
-        "401":
-          $ref: "#/components/responses/UnauthorizedError"
-        "422":
+                $ref: '#/components/schemas/Error'
+        '401':
+          $ref: '#/components/responses/UnauthorizedError'
+        '422':
           description: Validation error - ensure all required inputs are provided
           content:
             application/json:
               schema:
-                $ref: "#/components/schemas/ValidationError"
-        "500":
-          $ref: "#/components/responses/ServerError"
+                $ref: '#/components/schemas/ValidationError'
+        '500':
+          $ref: '#/components/responses/ServerError'
 
-  /{kickoff_id}/status:
+  /status/{kickoff_id}:
     get:
       summary: Get Execution Status
       description: |
@@ -230,15 +222,15 @@ paths:
             format: uuid
             example: "abcd1234-5678-90ef-ghij-klmnopqrstuv"
       responses:
-        "200":
+        '200':
           description: Successfully retrieved execution status
           content:
             application/json:
               schema:
                 oneOf:
-                  - $ref: "#/components/schemas/ExecutionRunning"
-                  - $ref: "#/components/schemas/ExecutionCompleted"
-                  - $ref: "#/components/schemas/ExecutionError"
+                  - $ref: '#/components/schemas/ExecutionRunning'
+                  - $ref: '#/components/schemas/ExecutionCompleted'
+                  - $ref: '#/components/schemas/ExecutionError'
               examples:
                 running:
                   summary: Execution in progress
@@ -270,19 +262,19 @@ paths:
                     status: "error"
                     error: "Task execution failed: Invalid API key for external service"
                     execution_time: 23.1
-        "401":
-          $ref: "#/components/responses/UnauthorizedError"
-        "404":
+        '401':
+          $ref: '#/components/responses/UnauthorizedError'
+        '404':
           description: Kickoff ID not found
           content:
             application/json:
               schema:
-                $ref: "#/components/schemas/Error"
+                $ref: '#/components/schemas/Error'
               example:
                 error: "Execution not found"
                 message: "No execution found with ID: abcd1234-5678-90ef-ghij-klmnopqrstuv"
-        "500":
-          $ref: "#/components/responses/ServerError"
+        '500':
+          $ref: '#/components/responses/ServerError'
 
   /resume:
     post:
@@ -362,7 +354,7 @@ paths:
                   taskWebhookUrl: "https://api.example.com/webhooks/task"
                   crewWebhookUrl: "https://api.example.com/webhooks/crew"
       responses:
-        "200":
+        '200':
           description: Execution resumed successfully
           content:
             application/json:
@@ -389,28 +381,28 @@ paths:
                   value:
                     status: "retrying"
                     message: "Task will be retried with your feedback"
-        "400":
+        '400':
           description: Invalid request body or execution not in pending state
           content:
             application/json:
               schema:
-                $ref: "#/components/schemas/Error"
+                $ref: '#/components/schemas/Error'
               example:
                 error: "Invalid Request"
                 message: "Execution is not in pending human input state"
-        "401":
-          $ref: "#/components/responses/UnauthorizedError"
-        "404":
+        '401':
+          $ref: '#/components/responses/UnauthorizedError'
+        '404':
           description: Execution ID or Task ID not found
           content:
             application/json:
               schema:
-                $ref: "#/components/schemas/Error"
+                $ref: '#/components/schemas/Error'
               example:
                 error: "Not Found"
                 message: "Execution ID not found"
-        "500":
-          $ref: "#/components/responses/ServerError"
+        '500':
+          $ref: '#/components/responses/ServerError'
 
 components:
   securitySchemes:
@@ -466,7 +458,7 @@ components:
             tasks:
               type: array
               items:
-                $ref: "#/components/schemas/TaskResult"
+                $ref: '#/components/schemas/TaskResult'
         execution_time:
           type: number
           description: Total execution time in seconds
@@ -544,7 +536,7 @@ components:
       content:
         application/json:
           schema:
-            $ref: "#/components/schemas/Error"
+            $ref: '#/components/schemas/Error'
           example:
             error: "Unauthorized"
             message: "Invalid or missing bearer token"
@@ -554,7 +546,7 @@ components:
       content:
         application/json:
           schema:
-            $ref: "#/components/schemas/Error"
+            $ref: '#/components/schemas/Error'
           example:
             error: "Not Found"
             message: "The requested resource was not found"
@@ -564,7 +556,7 @@ components:
       content:
         application/json:
           schema:
-            $ref: "#/components/schemas/Error"
+            $ref: '#/components/schemas/Error'
           example:
             error: "Internal Server Error"
             message: "An unexpected error occurred"

docs/enterprise-api.ko.yaml

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

docs/enterprise-api.pt-BR.yaml

@@ -35,7 +35,7 @@ info:
 
     1. **Descubra os inputs** usando `GET /inputs`
     2. **Inicie a execução** usando `POST /kickoff`
-    3. **Monitore o progresso** usando `GET /{kickoff_id}/status`
+    3. **Monitore o progresso** usando `GET /status/{kickoff_id}`
   version: 1.0.0
   contact:
     name: CrewAI Suporte
@@ -56,7 +56,7 @@ paths:
         Retorna a lista de parâmetros de entrada que sua crew espera.
       operationId: getRequiredInputs
       responses:
-        "200":
+        '200':
           description: Inputs requeridos obtidos com sucesso
           content:
             application/json:
@@ -69,12 +69,12 @@ paths:
                       type: string
                     description: Nomes dos parâmetros de entrada
                     example: ["budget", "interests", "duration", "age"]
-        "401":
-          $ref: "#/components/responses/UnauthorizedError"
-        "404":
-          $ref: "#/components/responses/NotFoundError"
-        "500":
-          $ref: "#/components/responses/ServerError"
+        '401':
+          $ref: '#/components/responses/UnauthorizedError'
+        '404':
+          $ref: '#/components/responses/NotFoundError'
+        '500':
+          $ref: '#/components/responses/ServerError'
 
   /kickoff:
     post:
@@ -104,7 +104,7 @@ paths:
                     age: "35"
 
       responses:
-        "200":
+        '200':
           description: Execução iniciada com sucesso
           content:
             application/json:
@@ -115,12 +115,12 @@ paths:
                     type: string
                     format: uuid
                     example: "abcd1234-5678-90ef-ghij-klmnopqrstuv"
-        "401":
-          $ref: "#/components/responses/UnauthorizedError"
-        "500":
-          $ref: "#/components/responses/ServerError"
+        '401':
+          $ref: '#/components/responses/UnauthorizedError'
+        '500':
+          $ref: '#/components/responses/ServerError'
 
-  /{kickoff_id}/status:
+  /status/{kickoff_id}:
     get:
       summary: Obter Status da Execução
       description: |
@@ -136,25 +136,25 @@ paths:
             type: string
             format: uuid
       responses:
-        "200":
+        '200':
           description: Status recuperado com sucesso
           content:
             application/json:
               schema:
                 oneOf:
-                  - $ref: "#/components/schemas/ExecutionRunning"
-                  - $ref: "#/components/schemas/ExecutionCompleted"
-                  - $ref: "#/components/schemas/ExecutionError"
-        "401":
-          $ref: "#/components/responses/UnauthorizedError"
-        "404":
+                  - $ref: '#/components/schemas/ExecutionRunning'
+                  - $ref: '#/components/schemas/ExecutionCompleted'
+                  - $ref: '#/components/schemas/ExecutionError'
+        '401':
+          $ref: '#/components/responses/UnauthorizedError'
+        '404':
           description: Kickoff ID não encontrado
           content:
             application/json:
               schema:
-                $ref: "#/components/schemas/Error"
-        "500":
-          $ref: "#/components/responses/ServerError"
+                $ref: '#/components/schemas/Error'
+        '500':
+          $ref: '#/components/responses/ServerError'
 
   /resume:
     post:
@@ -234,7 +234,7 @@ paths:
                   taskWebhookUrl: "https://api.example.com/webhooks/task"
                   crewWebhookUrl: "https://api.example.com/webhooks/crew"
       responses:
-        "200":
+        '200':
           description: Execution resumed successfully
           content:
             application/json:
@@ -261,28 +261,28 @@ paths:
                   value:
                     status: "retrying"
                     message: "Task will be retried with your feedback"
-        "400":
+        '400':
           description: Invalid request body or execution not in pending state
           content:
             application/json:
               schema:
-                $ref: "#/components/schemas/Error"
+                $ref: '#/components/schemas/Error'
               example:
                 error: "Invalid Request"
                 message: "Execution is not in pending human input state"
-        "401":
-          $ref: "#/components/responses/UnauthorizedError"
-        "404":
+        '401':
+          $ref: '#/components/responses/UnauthorizedError'
+        '404':
           description: Execution ID or Task ID not found
           content:
             application/json:
               schema:
-                $ref: "#/components/schemas/Error"
+                $ref: '#/components/schemas/Error'
               example:
                 error: "Not Found"
                 message: "Execution ID not found"
-        "500":
-          $ref: "#/components/responses/ServerError"
+        '500':
+          $ref: '#/components/responses/ServerError'
 
 components:
   securitySchemes:
@@ -324,7 +324,7 @@ components:
             tasks:
               type: array
               items:
-                $ref: "#/components/schemas/TaskResult"
+                $ref: '#/components/schemas/TaskResult'
         execution_time:
           type: number
 
@@ -380,16 +380,16 @@ components:
       content:
         application/json:
           schema:
-            $ref: "#/components/schemas/Error"
+            $ref: '#/components/schemas/Error'
     NotFoundError:
       description: Recurso não encontrado
       content:
         application/json:
           schema:
-            $ref: "#/components/schemas/Error"
+            $ref: '#/components/schemas/Error'
     ServerError:
       description: Erro interno do servidor
       content:
         application/json:
           schema:
-            $ref: "#/components/schemas/Error"
+            $ref: '#/components/schemas/Error'

docs/ko/api-reference/introduction.mdx

@@ -16,17 +16,16 @@ CrewAI 엔터프라이즈 API 참고 자료에 오신 것을 환영합니다.
     CrewAI AOP 대시보드에서 자신의 crew 상세 페이지로 이동하여 Status 탭에서 Bearer Token을 복사하세요.
   </Step>
 
-<Step title="필수 입력값 확인하기">
-  `GET /inputs` 엔드포인트를 사용하여 crew가 기대하는 파라미터를 확인하세요.
-</Step>
+  <Step title="필수 입력값 확인하기">
+    `GET /inputs` 엔드포인트를 사용하여 crew가 기대하는 파라미터를 확인하세요.
+  </Step>
 
-<Step title="Crew 실행 시작하기">
-  입력값과 함께 `POST /kickoff`를 호출하여 crew 실행을 시작하고 `kickoff_id`를
-  받으세요.
-</Step>
+  <Step title="Crew 실행 시작하기">
+    입력값과 함께 `POST /kickoff`를 호출하여 crew 실행을 시작하고 `kickoff_id`를 받으세요.
+  </Step>
 
   <Step title="진행 상황 모니터링">
-    `GET /{kickoff_id}/status`를 사용하여 실행 상태를 확인하고 결과를 조회하세요.
+    `GET /status/{kickoff_id}`를 사용하여 실행 상태를 확인하고 결과를 조회하세요.
   </Step>
 </Steps>
 
@@ -41,14 +40,13 @@ curl -H "Authorization: Bearer YOUR_CREW_TOKEN" \
 
 ### 토큰 유형
 
-| 토큰 유형             | 범위             | 사용 사례                             |
-| :-------------------- | :--------------- | :------------------------------------ |
-| **Bearer Token**      | 조직 단위 접근   | 전체 crew 운영, 서버 간 통합에 이상적 |
-| **User Bearer Token** | 사용자 범위 접근 | 제한된 권한, 사용자별 작업에 적합     |
+| 토큰 유형 | 범위 | 사용 사례 |
+|:-----------|:--------|:----------|
+| **Bearer Token** | 조직 단위 접근 | 전체 crew 운영, 서버 간 통합에 이상적 |
+| **User Bearer Token** | 사용자 범위 접근 | 제한된 권한, 사용자별 작업에 적합 |
 
 <Tip>
-  두 토큰 유형 모두 CrewAI AOP 대시보드의 crew 상세 페이지 Status 탭에서 확인할
-  수 있습니다.
+두 토큰 유형 모두 CrewAI AOP 대시보드의 crew 상세 페이지 Status 탭에서 확인할 수 있습니다.
 </Tip>
 
 ## 기본 URL
@@ -65,33 +63,29 @@ https://your-crew-name.crewai.com
 
 1. **탐색**: `GET /inputs`를 호출하여 crew가 필요한 것을 파악합니다.
 2. **실행**: `POST /kickoff`를 통해 입력값을 제출하여 처리를 시작합니다.
-3. **모니터링**: 완료될 때까지 `GET /{kickoff_id}/status`를 주기적으로 조회합니다.
+3. **모니터링**: 완료될 때까지 `GET /status/{kickoff_id}`를 주기적으로 조회합니다.
 4. **결과**: 완료된 응답에서 최종 출력을 추출합니다.
 
 ## 오류 처리
 
 API는 표준 HTTP 상태 코드를 사용합니다:
 
-| 코드  | 의미                                  |
-| ----- | :------------------------------------ |
-| `200` | 성공                                  |
-| `400` | 잘못된 요청 - 잘못된 입력 형식        |
-| `401` | 인증 실패 - 잘못된 베어러 토큰        |
+| 코드 | 의미 |
+|------|:--------|
+| `200` | 성공 |
+| `400` | 잘못된 요청 - 잘못된 입력 형식 |
+| `401` | 인증 실패 - 잘못된 베어러 토큰 |
 | `404` | 찾을 수 없음 - 리소스가 존재하지 않음 |
-| `422` | 유효성 검사 오류 - 필수 입력 누락     |
-| `500` | 서버 오류 - 지원팀에 문의하십시오     |
+| `422` | 유효성 검사 오류 - 필수 입력 누락 |
+| `500` | 서버 오류 - 지원팀에 문의하십시오 |
 
 ## 인터랙티브 테스트
 
 <Info>
-  **왜 "전송" 버튼이 없나요?** 각 CrewAI AOP 사용자는 고유한 crew URL을
-  가지므로, 혼동을 피하기 위해 인터랙티브 플레이그라운드 대신 **참조 모드**를
-  사용합니다. 이를 통해 비작동 전송 버튼 없이 요청이 어떻게 생겼는지 정확히
-  보여줍니다.
+**왜 "전송" 버튼이 없나요?** 각 CrewAI AOP 사용자는 고유한 crew URL을 가지므로, 혼동을 피하기 위해 인터랙티브 플레이그라운드 대신 **참조 모드**를 사용합니다. 이를 통해 비작동 전송 버튼 없이 요청이 어떻게 생겼는지 정확히 보여줍니다.
 </Info>
 
 각 엔드포인트 페이지에서는 다음을 확인할 수 있습니다:
-
 - ✅ 모든 파라미터가 포함된 **정확한 요청 형식**
 - ✅ 성공 및 오류 사례에 대한 **응답 예시**
 - ✅ 여러 언어(cURL, Python, JavaScript 등)로 제공되는 **코드 샘플**
@@ -109,7 +103,6 @@ API는 표준 HTTP 상태 코드를 사용합니다:
 </CardGroup>
 
 **예시 작업 흐름:**
-
 1. **cURL 예제를 복사**합니다 (엔드포인트 페이지에서)
 2. **`your-actual-crew-name.crewai.com`**을(를) 실제 crew URL로 교체합니다
 3. **Bearer 토큰을** 대시보드에서 복사한 실제 토큰으로 교체합니다
@@ -118,18 +111,10 @@ API는 표준 HTTP 상태 코드를 사용합니다:
 ## 도움이 필요하신가요?
 
 <CardGroup cols={2}>
-  <Card
-    title="Enterprise Support"
-    icon="headset"
-    href="mailto:support@crewai.com"
-  >
+  <Card title="Enterprise Support" icon="headset" href="mailto:support@crewai.com">
     API 통합 및 문제 해결에 대한 지원을 받으세요
   </Card>
-  <Card
-    title="Enterprise Dashboard"
-    icon="chart-line"
-    href="https://app.crewai.com"
-  >
+  <Card title="Enterprise Dashboard" icon="chart-line" href="https://app.crewai.com">
     crew를 관리하고 실행 로그를 확인하세요
   </Card>
 </CardGroup>

docs/ko/api-reference/status.mdx

@@ -1,6 +1,8 @@
 ---
-title: "GET /{kickoff_id}/status"
+title: "GET /status/{kickoff_id}"
 description: "실행 상태 조회"
-openapi: "/enterprise-api.ko.yaml GET /{kickoff_id}/status"
+openapi: "/enterprise-api.ko.yaml GET /status/{kickoff_id}"
 mode: "wide"
 ---
+
+

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

@@ -16,17 +16,16 @@ Bem-vindo à referência da API do CrewAI AOP. Esta API permite que você intera
     Navegue até a página de detalhes do seu crew no painel do CrewAI AOP e copie seu Bearer Token na aba Status.
   </Step>
 
-<Step title="Descubra os Inputs Necessários">
-  Use o endpoint `GET /inputs` para ver quais parâmetros seu crew espera.
-</Step>
+  <Step title="Descubra os Inputs Necessários">
+    Use o endpoint `GET /inputs` para ver quais parâmetros seu crew espera.
+  </Step>
 
-<Step title="Inicie uma Execução de Crew">
-  Chame `POST /kickoff` com seus inputs para iniciar a execução do crew e
-  receber um `kickoff_id`.
-</Step>
+  <Step title="Inicie uma Execução de Crew">
+    Chame `POST /kickoff` com seus inputs para iniciar a execução do crew e receber um `kickoff_id`.
+  </Step>
 
   <Step title="Monitore o Progresso">
-    Use `GET /{kickoff_id}/status` para checar o status da execução e recuperar os resultados.
+    Use `GET /status/{kickoff_id}` para checar o status da execução e recuperar os resultados.
   </Step>
 </Steps>
 
@@ -41,14 +40,13 @@ curl -H "Authorization: Bearer YOUR_CREW_TOKEN" \
 
 ### Tipos de Token
 
-| Tipo de Token         | Escopo                         | Caso de Uso                                                          |
-| :-------------------- | :----------------------------- | :------------------------------------------------------------------- |
-| **Bearer Token**      | Acesso em nível de organização | Operações completas de crew, ideal para integração server-to-server  |
-| **User Bearer Token** | Acesso com escopo de usuário   | Permissões limitadas, adequado para operações específicas de usuário |
+| Tipo de Token       | Escopo                   | Caso de Uso                                              |
+|:--------------------|:------------------------|:---------------------------------------------------------|
+| **Bearer Token**    | Acesso em nível de organização | Operações completas de crew, ideal para integração server-to-server |
+| **User Bearer Token** | Acesso com escopo de usuário         | Permissões limitadas, adequado para operações específicas de usuário   |
 
 <Tip>
-  Você pode encontrar ambos os tipos de token na aba Status da página de
-  detalhes do seu crew no painel do CrewAI AOP.
+Você pode encontrar ambos os tipos de token na aba Status da página de detalhes do seu crew no painel do CrewAI AOP.
 </Tip>
 
 ## URL Base
@@ -65,33 +63,29 @@ Substitua `your-crew-name` pela URL real do seu crew no painel.
 
 1. **Descoberta**: Chame `GET /inputs` para entender o que seu crew precisa
 2. **Execução**: Envie os inputs via `POST /kickoff` para iniciar o processamento
-3. **Monitoramento**: Faça polling em `GET /{kickoff_id}/status` até a conclusão
+3. **Monitoramento**: Faça polling em `GET /status/{kickoff_id}` até a conclusão
 4. **Resultados**: Extraia o output final da resposta concluída
 
 ## Tratamento de Erros
 
 A API utiliza códigos de status HTTP padrão:
 
-| Código | Significado                                      |
-| ------ | :----------------------------------------------- |
-| `200`  | Sucesso                                          |
-| `400`  | Requisição Inválida - Formato de input inválido  |
-| `401`  | Não Autorizado - Bearer token inválido           |
-| `404`  | Não Encontrado - Recurso não existe              |
+| Código | Significado                           |
+|--------|:--------------------------------------|
+| `200`  | Sucesso                               |
+| `400`  | Requisição Inválida - Formato de input inválido |
+| `401`  | Não Autorizado - Bearer token inválido |
+| `404`  | Não Encontrado - Recurso não existe     |
 | `422`  | Erro de Validação - Inputs obrigatórios ausentes |
-| `500`  | Erro no Servidor - Contate o suporte             |
+| `500`  | Erro no Servidor - Contate o suporte    |
 
 ## Testes Interativos
 
 <Info>
-  **Por que não há botão "Enviar"?** Como cada usuário do CrewAI AOP possui sua
-  própria URL de crew, utilizamos o **modo referência** em vez de um playground
-  interativo para evitar confusão. Isso mostra exatamente como as requisições
-  devem ser feitas, sem botões de envio não funcionais.
+**Por que não há botão "Enviar"?** Como cada usuário do CrewAI AOP possui sua própria URL de crew, utilizamos o **modo referência** em vez de um playground interativo para evitar confusão. Isso mostra exatamente como as requisições devem ser feitas, sem botões de envio não funcionais.
 </Info>
 
 Cada página de endpoint mostra para você:
-
 - ✅ **Formato exato da requisição** com todos os parâmetros
 - ✅ **Exemplos de resposta** para casos de sucesso e erro
 - ✅ **Exemplos de código** em várias linguagens (cURL, Python, JavaScript, etc.)
@@ -109,7 +103,6 @@ Cada página de endpoint mostra para você:
 </CardGroup>
 
 **Exemplo de fluxo:**
-
 1. **Copie este exemplo cURL** de qualquer página de endpoint
 2. **Substitua `your-actual-crew-name.crewai.com`** pela URL real do seu crew
 3. **Substitua o Bearer token** pelo seu token real do painel
@@ -118,18 +111,10 @@ Cada página de endpoint mostra para você:
 ## Precisa de Ajuda?
 
 <CardGroup cols={2}>
-  <Card
-    title="Suporte Enterprise"
-    icon="headset"
-    href="mailto:support@crewai.com"
-  >
+  <Card title="Suporte Enterprise" icon="headset" href="mailto:support@crewai.com">
     Obtenha ajuda com integração da API e resolução de problemas
   </Card>
-  <Card
-    title="Painel Enterprise"
-    icon="chart-line"
-    href="https://app.crewai.com"
-  >
+  <Card title="Painel Enterprise" icon="chart-line" href="https://app.crewai.com">
     Gerencie seus crews e visualize logs de execução
   </Card>
 </CardGroup>

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

@@ -1,6 +1,8 @@
 ---
-title: "GET /{kickoff_id}/status"
+title: "GET /status/{kickoff_id}"
 description: "Obter o status da execução"
-openapi: "/enterprise-api.pt-BR.yaml GET /{kickoff_id}/status"
+openapi: "/enterprise-api.pt-BR.yaml GET /status/{kickoff_id}"
 mode: "wide"
 ---
+
+

lib/crewai-tools/pyproject.toml

@@ -12,7 +12,7 @@ dependencies = [
     "pytube~=15.0.0",
     "requests~=2.32.5",
     "docker~=7.1.0",
-    "crewai==1.7.1",
+    "crewai==1.7.0",
     "lancedb~=0.5.4",
     "tiktoken~=0.8.0",
     "beautifulsoup4~=4.13.4",

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

@@ -291,4 +291,4 @@ __all__ = [
     "ZapierActionTools",
 ]
 
-__version__ = "1.7.1"
+__version__ = "1.7.0"

lib/crewai/pyproject.toml

@@ -49,7 +49,7 @@ Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
 tools = [
-    "crewai-tools==1.7.1",
+    "crewai-tools==1.7.0",
 ]
 embeddings = [
     "tiktoken~=0.8.0"

lib/crewai/src/crewai/__init__.py

@@ -40,7 +40,7 @@ def _suppress_pydantic_deprecation_warnings() -> None:
 
 _suppress_pydantic_deprecation_warnings()
 
-__version__ = "1.7.1"
+__version__ = "1.7.0"
 _telemetry_submitted = False
 
 

lib/crewai/src/crewai/agent/utils.py

@@ -16,7 +16,7 @@ from crewai.events.types.knowledge_events import (
     KnowledgeSearchQueryFailedEvent,
 )
 from crewai.knowledge.utils.knowledge_utils import extract_knowledge_context
-from crewai.utilities.pydantic_schema_utils import generate_model_description
+from crewai.utilities.converter import generate_model_description
 
 
 if TYPE_CHECKING:

lib/crewai/src/crewai/agents/agent_adapters/base_converter_adapter.py

@@ -5,9 +5,10 @@ from __future__ import annotations
 from abc import ABC, abstractmethod
 import json
 import re
-from typing import TYPE_CHECKING, Any, Final, Literal
+from typing import TYPE_CHECKING, Final, Literal
+
+from crewai.utilities.converter import generate_model_description
 
-from crewai.utilities.pydantic_schema_utils import generate_model_description
 
 
 if TYPE_CHECKING:
@@ -41,7 +42,7 @@ class BaseConverterAdapter(ABC):
         """
         self.agent_adapter = agent_adapter
         self._output_format: Literal["json", "pydantic"] | None = None
-        self._schema: dict[str, Any] | None = None
+        self._schema: str | None = None
 
     @abstractmethod
     def configure_structured_output(self, task: Task) -> None:
@@ -128,7 +129,7 @@ class BaseConverterAdapter(ABC):
     @staticmethod
     def _configure_format_from_task(
         task: Task,
-    ) -> tuple[Literal["json", "pydantic"] | None, dict[str, Any] | None]:
+    ) -> tuple[Literal["json", "pydantic"] | None, str | None]:
         """Determine output format and schema from task requirements.
 
         This is a helper method that examines the task's output requirements

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

@@ -4,7 +4,6 @@ This module contains the OpenAIConverterAdapter class that handles structured
 output conversion for OpenAI agents, supporting JSON and Pydantic model formats.
 """
 
-import json
 from typing import Any
 
 from crewai.agents.agent_adapters.base_converter_adapter import BaseConverterAdapter
@@ -62,7 +61,7 @@ class OpenAIConverterAdapter(BaseConverterAdapter):
         output_schema: str = (
             get_i18n()
             .slice("formatted_task_instructions")
-            .format(output_format=json.dumps(self._schema, indent=2))
+            .format(output_format=self._schema)
         )
 
         return f"{base_prompt}\n\n{output_schema}"

lib/crewai/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]==1.7.1"
+    "crewai[tools]==1.7.0"
 ]
 
 [project.scripts]

lib/crewai/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]==1.7.1"
+    "crewai[tools]==1.7.0"
 ]
 
 [project.scripts]

lib/crewai/src/crewai/cli/tools/main.py

@@ -1,5 +1,4 @@
 import base64
-from json import JSONDecodeError
 import os
 from pathlib import Path
 import subprocess
@@ -163,19 +162,9 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
 
         if login_response.status_code != 200:
             console.print(
-                "Authentication failed. Verify if the currently active organization can access the tool repository, and run 'crewai login' again.",
+                "Authentication failed. Verify if the currently active organization access to the tool repository, and run 'crewai login' again. ",
                 style="bold red",
             )
-            try:
-                console.print(
-                    f"[{login_response.status_code} error - {login_response.json().get('message', 'Unknown error')}]",
-                    style="bold red italic",
-                )
-            except JSONDecodeError:
-                console.print(
-                    f"[{login_response.status_code} error - Unknown error - Invalid JSON response]",
-                    style="bold red italic",
-                )
             raise SystemExit
 
         login_response_json = login_response.json()

lib/crewai/src/crewai/crew.py

@@ -1017,26 +1017,10 @@ class Crew(FlowTrackable, BaseModel):
             tasks=self.tasks, planning_agent_llm=self.planning_llm
         )._handle_crew_planning()
 
-        plan_map: dict[int, str] = {}
-        for step_plan in result.list_of_plans_per_task:
-            if step_plan.task_number in plan_map:
-                self._logger.log(
-                    "warning",
-                    f"Duplicate plan for Task Number {step_plan.task_number}, "
-                    "using the first plan",
-                )
-            else:
-                plan_map[step_plan.task_number] = step_plan.plan
-
-        for idx, task in enumerate(self.tasks):
-            task_number = idx + 1
-            if task_number in plan_map:
-                task.description += plan_map[task_number]
-            else:
-                self._logger.log(
-                    "warning",
-                    f"No plan found for Task Number {task_number}",
-                )
+        for task, step_plan in zip(
+            self.tasks, result.list_of_plans_per_task, strict=False
+        ):
+            task.description += step_plan.plan
 
     def _store_execution_log(
         self,

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

@@ -19,9 +19,9 @@ class SignalType(IntEnum):
 
     SIGTERM = signal.SIGTERM
     SIGINT = signal.SIGINT
-    SIGHUP = getattr(signal, "SIGHUP", 1)
-    SIGTSTP = getattr(signal, "SIGTSTP", 20)
-    SIGCONT = getattr(signal, "SIGCONT", 18)
+    SIGHUP = signal.SIGHUP
+    SIGTSTP = signal.SIGTSTP
+    SIGCONT = signal.SIGCONT
 
 
 class SigTermEvent(BaseEvent):

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

@@ -3,20 +3,23 @@ from __future__ import annotations
 import json
 import logging
 import os
+import time
 from typing import TYPE_CHECKING, Any, TypedDict
 
 from pydantic import BaseModel
 from typing_extensions import Self
 
 from crewai.utilities.agent_utils import is_context_length_exceeded
+from crewai.utilities.converter import generate_model_description
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededError,
 )
-from crewai.utilities.pydantic_schema_utils import generate_model_description
 from crewai.utilities.types import LLMMessage
 
 
 if TYPE_CHECKING:
+    from azure.core.credentials import AccessToken, TokenCredential
+
     from crewai.llms.hooks.base import BaseInterceptor
 
 
@@ -51,6 +54,39 @@ except ImportError:
     ) from None
 
 
+class _StaticTokenCredential:
+    """A simple TokenCredential implementation for static Azure AD tokens.
+
+    This class wraps a static token string and provides it as a TokenCredential
+    that can be used with Azure SDK clients. The token is assumed to be valid
+    and the user is responsible for token rotation.
+    """
+
+    def __init__(self, token: str) -> None:
+        """Initialize with a static token.
+
+        Args:
+            token: The Azure AD bearer token string.
+        """
+        self._token = token
+
+    def get_token(
+        self, *scopes: str, **kwargs: Any
+    ) -> AccessToken:
+        """Get the static token as an AccessToken.
+
+        Args:
+            *scopes: Token scopes (ignored for static tokens).
+            **kwargs: Additional arguments (ignored).
+
+        Returns:
+            AccessToken with the static token and a far-future expiry.
+        """
+        from azure.core.credentials import AccessToken
+
+        return AccessToken(self._token, int(time.time()) + 3600)
+
+
 class AzureCompletionParams(TypedDict, total=False):
     """Type definition for Azure chat completion parameters."""
 
@@ -92,6 +128,9 @@ class AzureCompletion(BaseLLM):
         stop: list[str] | None = None,
         stream: bool = False,
         interceptor: BaseInterceptor[Any, Any] | None = None,
+        credential: TokenCredential | None = None,
+        azure_ad_token: str | None = None,
+        use_default_credential: bool = False,
         **kwargs: Any,
     ):
         """Initialize Azure AI Inference chat completion client.
@@ -111,7 +150,36 @@ class AzureCompletion(BaseLLM):
             stop: Stop sequences
             stream: Enable streaming responses
             interceptor: HTTP interceptor (not yet supported for Azure).
+            credential: Azure TokenCredential for Azure AD authentication (e.g.,
+                DefaultAzureCredential, ManagedIdentityCredential). Takes precedence
+                over other authentication methods.
+            azure_ad_token: Static Azure AD token string (defaults to AZURE_AD_TOKEN
+                env var). Use this for scenarios where you have a pre-fetched token.
+            use_default_credential: If True, automatically use DefaultAzureCredential
+                for Azure AD authentication. Requires azure-identity package.
             **kwargs: Additional parameters
+
+        Authentication Priority:
+            1. credential parameter (explicit TokenCredential)
+            2. azure_ad_token parameter or AZURE_AD_TOKEN env var
+            3. api_key parameter or AZURE_API_KEY env var
+            4. use_default_credential=True (DefaultAzureCredential)
+
+        Example:
+            # Using API key (existing behavior)
+            llm = LLM(model="azure/gpt-4", api_key="...", endpoint="...")
+
+            # Using Azure AD token from environment
+            os.environ["AZURE_AD_TOKEN"] = token_provider()
+            llm = LLM(model="azure/gpt-4", endpoint="...")
+
+            # Using DefaultAzureCredential (Managed Identity, Azure CLI, etc.)
+            llm = LLM(model="azure/gpt-4", endpoint="...", use_default_credential=True)
+
+            # Using explicit TokenCredential
+            from azure.identity import ManagedIdentityCredential
+            llm = LLM(model="azure/gpt-4", endpoint="...",
+                      credential=ManagedIdentityCredential())
         """
         if interceptor is not None:
             raise NotImplementedError(
@@ -124,6 +192,9 @@ class AzureCompletion(BaseLLM):
         )
 
         self.api_key = api_key or os.getenv("AZURE_API_KEY")
+        self.azure_ad_token = azure_ad_token or os.getenv("AZURE_AD_TOKEN")
+        self._explicit_credential = credential
+        self.use_default_credential = use_default_credential
         self.endpoint = (
             endpoint
             or os.getenv("AZURE_ENDPOINT")
@@ -134,10 +205,6 @@ class AzureCompletion(BaseLLM):
         self.timeout = timeout
         self.max_retries = max_retries
 
-        if not self.api_key:
-            raise ValueError(
-                "Azure API key is required. Set AZURE_API_KEY environment variable or pass api_key parameter."
-            )
         if not self.endpoint:
             raise ValueError(
                 "Azure endpoint is required. Set AZURE_ENDPOINT environment variable or pass endpoint parameter."
@@ -146,19 +213,22 @@ class AzureCompletion(BaseLLM):
         # Validate and potentially fix Azure OpenAI endpoint URL
         self.endpoint = self._validate_and_fix_endpoint(self.endpoint, model)
 
+        # Select credential based on priority
+        selected_credential = self._select_credential()
+
         # Build client kwargs
-        client_kwargs = {
+        client_kwargs: dict[str, Any] = {
             "endpoint": self.endpoint,
-            "credential": AzureKeyCredential(self.api_key),
+            "credential": selected_credential,
         }
 
         # Add api_version if specified (primarily for Azure OpenAI endpoints)
         if self.api_version:
             client_kwargs["api_version"] = self.api_version
 
-        self.client = ChatCompletionsClient(**client_kwargs)  # type: ignore[arg-type]
+        self.client = ChatCompletionsClient(**client_kwargs)
 
-        self.async_client = AsyncChatCompletionsClient(**client_kwargs)  # type: ignore[arg-type]
+        self.async_client = AsyncChatCompletionsClient(**client_kwargs)
 
         self.top_p = top_p
         self.frequency_penalty = frequency_penalty
@@ -175,6 +245,47 @@ class AzureCompletion(BaseLLM):
             and "/openai/deployments/" in self.endpoint
         )
 
+    def _select_credential(self) -> AzureKeyCredential | TokenCredential:
+        """Select the appropriate credential based on configuration priority.
+
+        Priority order:
+            1. Explicit credential parameter (TokenCredential)
+            2. azure_ad_token parameter or AZURE_AD_TOKEN env var
+            3. api_key parameter or AZURE_API_KEY env var
+            4. use_default_credential=True (DefaultAzureCredential)
+
+        Returns:
+            The selected credential for Azure authentication.
+
+        Raises:
+            ValueError: If no valid credentials are configured.
+        """
+        if self._explicit_credential is not None:
+            return self._explicit_credential
+
+        if self.azure_ad_token:
+            return _StaticTokenCredential(self.azure_ad_token)
+
+        if self.api_key:
+            return AzureKeyCredential(self.api_key)
+
+        if self.use_default_credential:
+            try:
+                from azure.identity import DefaultAzureCredential
+
+                return DefaultAzureCredential()
+            except ImportError:
+                raise ImportError(
+                    "azure-identity package is required for use_default_credential=True. "
+                    'Install it with: uv add "azure-identity"'
+                ) from None
+
+        raise ValueError(
+            "Azure credentials are required. Provide one of: "
+            "api_key / AZURE_API_KEY, azure_ad_token / AZURE_AD_TOKEN, "
+            "a TokenCredential via 'credential', or set use_default_credential=True."
+        )
+
     @staticmethod
     def _validate_and_fix_endpoint(endpoint: str, model: str) -> str:
         """Validate and fix Azure endpoint URL format.

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

@@ -18,10 +18,10 @@ from crewai.events.types.llm_events import LLMCallType
 from crewai.llms.base_llm import BaseLLM
 from crewai.llms.hooks.transport import AsyncHTTPTransport, HTTPTransport
 from crewai.utilities.agent_utils import is_context_length_exceeded
+from crewai.utilities.converter import generate_model_description
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededError,
 )
-from crewai.utilities.pydantic_schema_utils import generate_model_description
 from crewai.utilities.types import LLMMessage
 
 

lib/crewai/src/crewai/task.py

@@ -494,11 +494,8 @@ class Task(BaseModel):
         future: Future[TaskOutput],
     ) -> None:
         """Execute the task asynchronously with context handling."""
-        try:
-          result = self._execute_core(agent, context, tools)
-          future.set_result(result)
-        except Exception as e:
-          future.set_exception(e)
+        result = self._execute_core(agent, context, tools)
+        future.set_result(result)
 
     async def aexecute_sync(
         self,

lib/crewai/src/crewai/telemetry/telemetry.py

@@ -174,12 +174,9 @@ class Telemetry:
 
         self._register_signal_handler(signal.SIGTERM, SigTermEvent, shutdown=True)
         self._register_signal_handler(signal.SIGINT, SigIntEvent, shutdown=True)
-        if hasattr(signal, "SIGHUP"):
-            self._register_signal_handler(signal.SIGHUP, SigHupEvent, shutdown=False)
-        if hasattr(signal, "SIGTSTP"):
-            self._register_signal_handler(signal.SIGTSTP, SigTStpEvent, shutdown=False)
-        if hasattr(signal, "SIGCONT"):
-            self._register_signal_handler(signal.SIGCONT, SigContEvent, shutdown=False)
+        self._register_signal_handler(signal.SIGHUP, SigHupEvent, shutdown=False)
+        self._register_signal_handler(signal.SIGTSTP, SigTStpEvent, shutdown=False)
+        self._register_signal_handler(signal.SIGCONT, SigContEvent, shutdown=False)
 
     def _register_signal_handler(
         self,

lib/crewai/src/crewai/tools/base_tool.py

@@ -3,13 +3,15 @@ from __future__ import annotations
 from abc import ABC, abstractmethod
 import asyncio
 from collections.abc import Awaitable, Callable
-from inspect import Parameter, signature
-import json
+from inspect import signature
 from typing import (
     Any,
     Generic,
     ParamSpec,
     TypeVar,
+    cast,
+    get_args,
+    get_origin,
     overload,
 )
 
@@ -25,7 +27,6 @@ from typing_extensions import TypeIs
 
 from crewai.tools.structured_tool import CrewStructuredTool
 from crewai.utilities.printer import Printer
-from crewai.utilities.pydantic_schema_utils import generate_model_description
 
 
 _printer = Printer()
@@ -102,40 +103,20 @@ class BaseTool(BaseModel, ABC):
         if v != cls._ArgsSchemaPlaceholder:
             return v
 
-        run_sig = signature(cls._run)
-        fields: dict[str, Any] = {}
-
-        for param_name, param in run_sig.parameters.items():
-            if param_name in ("self", "return"):
-                continue
-            if param.kind in (Parameter.VAR_POSITIONAL, Parameter.VAR_KEYWORD):
-                continue
-
-            annotation = param.annotation if param.annotation != param.empty else Any
-
-            if param.default is param.empty:
-                fields[param_name] = (annotation, ...)
-            else:
-                fields[param_name] = (annotation, param.default)
-
-        if not fields:
-            arun_sig = signature(cls._arun)
-            for param_name, param in arun_sig.parameters.items():
-                if param_name in ("self", "return"):
-                    continue
-                if param.kind in (Parameter.VAR_POSITIONAL, Parameter.VAR_KEYWORD):
-                    continue
-
-                annotation = (
-                    param.annotation if param.annotation != param.empty else Any
-                )
-
-                if param.default is param.empty:
-                    fields[param_name] = (annotation, ...)
-                else:
-                    fields[param_name] = (annotation, param.default)
-
-        return create_model(f"{cls.__name__}Schema", **fields)
+        return cast(
+            type[PydanticBaseModel],
+            type(
+                f"{cls.__name__}Schema",
+                (PydanticBaseModel,),
+                {
+                    "__annotations__": {
+                        k: v
+                        for k, v in cls._run.__annotations__.items()
+                        if k != "return"
+                    },
+                },
+            ),
+        )
 
     @field_validator("max_usage_count", mode="before")
     @classmethod
@@ -245,23 +226,24 @@ class BaseTool(BaseModel, ABC):
         args_schema = getattr(tool, "args_schema", None)
 
         if args_schema is None:
+            # Infer args_schema from the function signature if not provided
             func_signature = signature(tool.func)
-            fields: dict[str, Any] = {}
-            for name, param in func_signature.parameters.items():
-                if name == "self":
-                    continue
-                if param.kind in (Parameter.VAR_POSITIONAL, Parameter.VAR_KEYWORD):
-                    continue
-                param_annotation = (
-                    param.annotation if param.annotation != param.empty else Any
-                )
-                if param.default is param.empty:
-                    fields[name] = (param_annotation, ...)
-                else:
-                    fields[name] = (param_annotation, param.default)
-            if fields:
-                args_schema = create_model(f"{tool.name}Input", **fields)
+            annotations = func_signature.parameters
+            args_fields: dict[str, Any] = {}
+            for name, param in annotations.items():
+                if name != "self":
+                    param_annotation = (
+                        param.annotation if param.annotation != param.empty else Any
+                    )
+                    field_info = Field(
+                        default=...,
+                        description="",
+                    )
+                    args_fields[name] = (param_annotation, field_info)
+            if args_fields:
+                args_schema = create_model(f"{tool.name}Input", **args_fields)
             else:
+                # Create a default schema with no fields if no parameters are found
                 args_schema = create_model(
                     f"{tool.name}Input", __base__=PydanticBaseModel
                 )
@@ -275,37 +257,53 @@ class BaseTool(BaseModel, ABC):
 
     def _set_args_schema(self) -> None:
         if self.args_schema is None:
-            run_sig = signature(self._run)
-            fields: dict[str, Any] = {}
-
-            for param_name, param in run_sig.parameters.items():
-                if param_name in ("self", "return"):
-                    continue
-                if param.kind in (Parameter.VAR_POSITIONAL, Parameter.VAR_KEYWORD):
-                    continue
-
-                annotation = (
-                    param.annotation if param.annotation != param.empty else Any
-                )
-
-                if param.default is param.empty:
-                    fields[param_name] = (annotation, ...)
-                else:
-                    fields[param_name] = (annotation, param.default)
-
-            self.args_schema = create_model(
-                f"{self.__class__.__name__}Schema", **fields
+            class_name = f"{self.__class__.__name__}Schema"
+            self.args_schema = cast(
+                type[PydanticBaseModel],
+                type(
+                    class_name,
+                    (PydanticBaseModel,),
+                    {
+                        "__annotations__": {
+                            k: v
+                            for k, v in self._run.__annotations__.items()
+                            if k != "return"
+                        },
+                    },
+                ),
             )
 
     def _generate_description(self) -> None:
-        """Generate the tool description with a JSON schema for arguments."""
-        schema = generate_model_description(self.args_schema)
-        args_json = json.dumps(schema["json_schema"]["schema"], indent=2)
-        self.description = (
-            f"Tool Name: {self.name}\n"
-            f"Tool Arguments: {args_json}\n"
-            f"Tool Description: {self.description}"
-        )
+        args_schema = {
+            name: {
+                "description": field.description,
+                "type": BaseTool._get_arg_annotations(field.annotation),
+            }
+            for name, field in self.args_schema.model_fields.items()
+        }
+
+        self.description = f"Tool Name: {self.name}\nTool Arguments: {args_schema}\nTool Description: {self.description}"
+
+    @staticmethod
+    def _get_arg_annotations(annotation: type[Any] | None) -> str:
+        if annotation is None:
+            return "None"
+
+        origin = get_origin(annotation)
+        args = get_args(annotation)
+
+        if origin is None:
+            return (
+                annotation.__name__
+                if hasattr(annotation, "__name__")
+                else str(annotation)
+            )
+
+        if args:
+            args_str = ", ".join(BaseTool._get_arg_annotations(arg) for arg in args)
+            return str(f"{origin.__name__}[{args_str}]")
+
+        return str(origin.__name__)
 
 
 class Tool(BaseTool, Generic[P, R]):
@@ -408,23 +406,24 @@ class Tool(BaseTool, Generic[P, R]):
         args_schema = getattr(tool, "args_schema", None)
 
         if args_schema is None:
+            # Infer args_schema from the function signature if not provided
             func_signature = signature(tool.func)
-            fields: dict[str, Any] = {}
-            for name, param in func_signature.parameters.items():
-                if name == "self":
-                    continue
-                if param.kind in (Parameter.VAR_POSITIONAL, Parameter.VAR_KEYWORD):
-                    continue
-                param_annotation = (
-                    param.annotation if param.annotation != param.empty else Any
-                )
-                if param.default is param.empty:
-                    fields[name] = (param_annotation, ...)
-                else:
-                    fields[name] = (param_annotation, param.default)
-            if fields:
-                args_schema = create_model(f"{tool.name}Input", **fields)
+            annotations = func_signature.parameters
+            args_fields: dict[str, Any] = {}
+            for name, param in annotations.items():
+                if name != "self":
+                    param_annotation = (
+                        param.annotation if param.annotation != param.empty else Any
+                    )
+                    field_info = Field(
+                        default=...,
+                        description="",
+                    )
+                    args_fields[name] = (param_annotation, field_info)
+            if args_fields:
+                args_schema = create_model(f"{tool.name}Input", **args_fields)
             else:
+                # Create a default schema with no fields if no parameters are found
                 args_schema = create_model(
                     f"{tool.name}Input", __base__=PydanticBaseModel
                 )
@@ -503,38 +502,32 @@ def tool(
         def _make_tool(f: Callable[P2, R2]) -> Tool[P2, R2]:
             if f.__doc__ is None:
                 raise ValueError("Function must have a docstring")
-            if f.__annotations__ is None:
+
+            func_annotations = getattr(f, "__annotations__", None)
+            if func_annotations is None:
                 raise ValueError("Function must have type annotations")
 
-            func_sig = signature(f)
-            fields: dict[str, Any] = {}
-
-            for param_name, param in func_sig.parameters.items():
-                if param_name == "return":
-                    continue
-                if param.kind in (Parameter.VAR_POSITIONAL, Parameter.VAR_KEYWORD):
-                    continue
-
-                annotation = (
-                    param.annotation if param.annotation != param.empty else Any
-                )
-
-                if param.default is param.empty:
-                    fields[param_name] = (annotation, ...)
-                else:
-                    fields[param_name] = (annotation, param.default)
-
             class_name = "".join(tool_name.split()).title()
-            args_schema = create_model(class_name, **fields)
+            tool_args_schema = cast(
+                type[PydanticBaseModel],
+                type(
+                    class_name,
+                    (PydanticBaseModel,),
+                    {
+                        "__annotations__": {
+                            k: v for k, v in func_annotations.items() if k != "return"
+                        },
+                    },
+                ),
+            )
 
             return Tool(
                 name=tool_name,
                 description=f.__doc__,
                 func=f,
-                args_schema=args_schema,
+                args_schema=tool_args_schema,
                 result_as_answer=result_as_answer,
                 max_usage_count=max_usage_count,
-                current_usage_count=0,
             )
 
         return _make_tool

lib/crewai/src/crewai/utilities/agent_utils.py

@@ -169,18 +169,7 @@ def handle_max_iterations_exceeded(
         )
         raise ValueError("Invalid response from LLM call - None or empty.")
 
-    try:
-        formatted = format_answer(answer=answer)
-    except OutputParserError:
-        printer.print(
-            content="Failed to parse forced final answer. Returning raw response.",
-            color="yellow",
-        )
-        return AgentFinish(
-            thought="Failed to parse LLM response during max iterations",
-            output=answer,
-            text=answer,
-        )
+    formatted = format_answer(answer=answer)
 
     # If format_answer returned an AgentAction, convert it to AgentFinish
     if isinstance(formatted, AgentFinish):
@@ -217,15 +206,9 @@ def format_answer(answer: str) -> AgentAction | AgentFinish:
 
     Returns:
         Either an AgentAction or AgentFinish
-
-    Raises:
-        OutputParserError: If parsing fails due to malformed LLM output format.
-            This allows the retry logic in _invoke_loop() to handle the error.
     """
     try:
         return parse(answer)
-    except OutputParserError:
-        raise
     except Exception:
         return AgentFinish(
             thought="Failed to parse LLM response",

lib/crewai/src/crewai/utilities/converter.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from collections.abc import Callable
+from copy import deepcopy
 import json
 import re
 from typing import TYPE_CHECKING, Any, Final, TypedDict
@@ -11,7 +13,6 @@ from crewai.agents.agent_builder.utilities.base_output_converter import OutputCo
 from crewai.utilities.i18n import get_i18n
 from crewai.utilities.internal_instructor import InternalInstructor
 from crewai.utilities.printer import Printer
-from crewai.utilities.pydantic_schema_utils import generate_model_description
 
 
 if TYPE_CHECKING:
@@ -420,3 +421,221 @@ def create_converter(
         raise Exception("No output converter found or set.")
 
     return converter  # type: ignore[no-any-return]
+
+
+def resolve_refs(schema: dict[str, Any]) -> dict[str, Any]:
+    """Recursively resolve all local $refs in the given JSON Schema using $defs as the source.
+
+    This is needed because Pydantic generates $ref-based schemas that
+    some consumers (e.g. LLMs, tool frameworks) don't handle well.
+
+    Args:
+        schema: JSON Schema dict that may contain "$refs" and "$defs".
+
+    Returns:
+        A new schema dictionary with all local $refs replaced by their definitions.
+    """
+    defs = schema.get("$defs", {})
+    schema_copy = deepcopy(schema)
+
+    def _resolve(node: Any) -> Any:
+        if isinstance(node, dict):
+            ref = node.get("$ref")
+            if isinstance(ref, str) and ref.startswith("#/$defs/"):
+                def_name = ref.replace("#/$defs/", "")
+                if def_name in defs:
+                    return _resolve(deepcopy(defs[def_name]))
+                raise KeyError(f"Definition '{def_name}' not found in $defs.")
+            return {k: _resolve(v) for k, v in node.items()}
+
+        if isinstance(node, list):
+            return [_resolve(i) for i in node]
+
+        return node
+
+    return _resolve(schema_copy)  # type: ignore[no-any-return]
+
+
+def add_key_in_dict_recursively(
+    d: dict[str, Any], key: str, value: Any, criteria: Callable[[dict[str, Any]], bool]
+) -> dict[str, Any]:
+    """Recursively adds a key/value pair to all nested dicts matching `criteria`."""
+    if isinstance(d, dict):
+        if criteria(d) and key not in d:
+            d[key] = value
+        for v in d.values():
+            add_key_in_dict_recursively(v, key, value, criteria)
+    elif isinstance(d, list):
+        for i in d:
+            add_key_in_dict_recursively(i, key, value, criteria)
+    return d
+
+
+def fix_discriminator_mappings(schema: dict[str, Any]) -> dict[str, Any]:
+    """Replace '#/$defs/...' references in discriminator.mapping with just the model name."""
+    output = schema.get("properties", {}).get("output")
+    if not output:
+        return schema
+
+    disc = output.get("discriminator")
+    if not disc or "mapping" not in disc:
+        return schema
+
+    disc["mapping"] = {k: v.split("/")[-1] for k, v in disc["mapping"].items()}
+    return schema
+
+
+def add_const_to_oneof_variants(schema: dict[str, Any]) -> dict[str, Any]:
+    """Add const fields to oneOf variants for discriminated unions.
+
+    The json_schema_to_pydantic library requires each oneOf variant to have
+    a const field for the discriminator property. This function adds those
+    const fields based on the discriminator mapping.
+
+    Args:
+        schema: JSON Schema dict that may contain discriminated unions
+
+    Returns:
+        Modified schema with const fields added to oneOf variants
+    """
+
+    def _process_oneof(node: dict[str, Any]) -> dict[str, Any]:
+        """Process a single node that might contain a oneOf with discriminator."""
+        if not isinstance(node, dict):
+            return node
+
+        if "oneOf" in node and "discriminator" in node:
+            discriminator = node["discriminator"]
+            property_name = discriminator.get("propertyName")
+            mapping = discriminator.get("mapping", {})
+
+            if property_name and mapping:
+                one_of_variants = node.get("oneOf", [])
+
+                for variant in one_of_variants:
+                    if isinstance(variant, dict) and "properties" in variant:
+                        variant_title = variant.get("title", "")
+
+                        matched_disc_value = None
+                        for disc_value, schema_name in mapping.items():
+                            if variant_title == schema_name or variant_title.endswith(
+                                schema_name
+                            ):
+                                matched_disc_value = disc_value
+                                break
+
+                        if matched_disc_value is not None:
+                            props = variant["properties"]
+                            if property_name in props:
+                                props[property_name]["const"] = matched_disc_value
+
+        for key, value in node.items():
+            if isinstance(value, dict):
+                node[key] = _process_oneof(value)
+            elif isinstance(value, list):
+                node[key] = [
+                    _process_oneof(item) if isinstance(item, dict) else item
+                    for item in value
+                ]
+
+        return node
+
+    return _process_oneof(deepcopy(schema))
+
+
+def convert_oneof_to_anyof(schema: dict[str, Any]) -> dict[str, Any]:
+    """Convert oneOf to anyOf for OpenAI compatibility.
+
+    OpenAI's Structured Outputs support anyOf better than oneOf.
+    This recursively converts all oneOf occurrences to anyOf.
+
+    Args:
+        schema: JSON schema dictionary.
+
+    Returns:
+        Modified schema with anyOf instead of oneOf.
+    """
+    if isinstance(schema, dict):
+        if "oneOf" in schema:
+            schema["anyOf"] = schema.pop("oneOf")
+
+        for value in schema.values():
+            if isinstance(value, dict):
+                convert_oneof_to_anyof(value)
+            elif isinstance(value, list):
+                for item in value:
+                    if isinstance(item, dict):
+                        convert_oneof_to_anyof(item)
+
+    return schema
+
+
+def ensure_all_properties_required(schema: dict[str, Any]) -> dict[str, Any]:
+    """Ensure all properties are in the required array for OpenAI strict mode.
+
+    OpenAI's strict structured outputs require all properties to be listed
+    in the required array. This recursively updates all objects to include
+    all their properties in required.
+
+    Args:
+        schema: JSON schema dictionary.
+
+    Returns:
+        Modified schema with all properties marked as required.
+    """
+    if isinstance(schema, dict):
+        if schema.get("type") == "object" and "properties" in schema:
+            properties = schema["properties"]
+            if properties:
+                schema["required"] = list(properties.keys())
+
+        for value in schema.values():
+            if isinstance(value, dict):
+                ensure_all_properties_required(value)
+            elif isinstance(value, list):
+                for item in value:
+                    if isinstance(item, dict):
+                        ensure_all_properties_required(item)
+
+    return schema
+
+
+def generate_model_description(model: type[BaseModel]) -> dict[str, Any]:
+    """Generate JSON schema description of a Pydantic model.
+
+    This function takes a Pydantic model class and returns its JSON schema,
+    which includes full type information, discriminators, and all metadata.
+    The schema is dereferenced to inline all $ref references for better LLM understanding.
+
+    Args:
+        model: A Pydantic model class.
+
+    Returns:
+        A JSON schema dictionary representation of the model.
+    """
+
+    json_schema = model.model_json_schema(ref_template="#/$defs/{model}")
+
+    json_schema = add_key_in_dict_recursively(
+        json_schema,
+        key="additionalProperties",
+        value=False,
+        criteria=lambda d: d.get("type") == "object"
+        and "additionalProperties" not in d,
+    )
+
+    json_schema = resolve_refs(json_schema)
+
+    json_schema.pop("$defs", None)
+    json_schema = fix_discriminator_mappings(json_schema)
+    json_schema = convert_oneof_to_anyof(json_schema)
+    json_schema = ensure_all_properties_required(json_schema)
+
+    return {
+        "type": "json_schema",
+        "json_schema": {
+            "name": model.__name__,
+            "strict": True,
+            "schema": json_schema,
+        },
+    }

lib/crewai/src/crewai/utilities/evaluators/task_evaluator.py

@@ -1,15 +1,14 @@
 from __future__ import annotations
 
-import json
-from typing import TYPE_CHECKING, Any, cast
+from typing import TYPE_CHECKING, cast
 
 from pydantic import BaseModel, Field
 
 from crewai.events.event_bus import crewai_event_bus
 from crewai.events.types.task_events import TaskEvaluationEvent
+from crewai.llm import LLM
 from crewai.utilities.converter import Converter
-from crewai.utilities.i18n import get_i18n
-from crewai.utilities.pydantic_schema_utils import generate_model_description
+from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
 from crewai.utilities.training_converter import TrainingConverter
 
 
@@ -63,7 +62,7 @@ class TaskEvaluator:
         Args:
             original_agent: The agent to evaluate.
         """
-        self.llm = original_agent.llm
+        self.llm = cast(LLM, original_agent.llm)
         self.original_agent = original_agent
 
     def evaluate(self, task: Task, output: str) -> TaskEvaluation:
@@ -80,8 +79,7 @@ class TaskEvaluator:
             - Investigate the Converter.to_pydantic signature, returns BaseModel strictly?
         """
         crewai_event_bus.emit(
-            self,
-            TaskEvaluationEvent(evaluation_type="task_evaluation", task=task),  # type: ignore[no-untyped-call]
+            self, TaskEvaluationEvent(evaluation_type="task_evaluation", task=task)
         )
         evaluation_query = (
             f"Assess the quality of the task completed based on the description, expected output, and actual results.\n\n"
@@ -96,14 +94,9 @@ class TaskEvaluator:
 
         instructions = "Convert all responses into valid JSON output."
 
-        if not self.llm.supports_function_calling():  # type: ignore[union-attr]
-            schema_dict = generate_model_description(TaskEvaluation)
-            output_schema: str = (
-                get_i18n()
-                .slice("formatted_task_instructions")
-                .format(output_format=json.dumps(schema_dict, indent=2))
-            )
-            instructions = f"{instructions}\n\n{output_schema}"
+        if not self.llm.supports_function_calling():
+            model_schema = PydanticSchemaParser(model=TaskEvaluation).get_schema()
+            instructions = f"{instructions}\n\nReturn only valid JSON with the following schema:\n```json\n{model_schema}\n```"
 
         converter = Converter(
             llm=self.llm,
@@ -115,7 +108,7 @@ class TaskEvaluator:
         return cast(TaskEvaluation, converter.to_pydantic())
 
     def evaluate_training_data(
-        self, training_data: dict[str, Any], agent_id: str
+        self, training_data: dict, agent_id: str
     ) -> TrainingTaskEvaluation:
         """
         Evaluate the training data based on the llm output, human feedback, and improved output.
@@ -128,8 +121,7 @@ class TaskEvaluator:
             - Investigate the Converter.to_pydantic signature, returns BaseModel strictly?
         """
         crewai_event_bus.emit(
-            self,
-            TaskEvaluationEvent(evaluation_type="training_data_evaluation"),  # type: ignore[no-untyped-call]
+            self, TaskEvaluationEvent(evaluation_type="training_data_evaluation")
         )
 
         output_training_data = training_data[agent_id]
@@ -172,14 +164,11 @@ class TaskEvaluator:
         )
         instructions = "I'm gonna convert this raw text into valid JSON."
 
-        if not self.llm.supports_function_calling():  # type: ignore[union-attr]
-            schema_dict = generate_model_description(TrainingTaskEvaluation)
-            output_schema: str = (
-                get_i18n()
-                .slice("formatted_task_instructions")
-                .format(output_format=json.dumps(schema_dict, indent=2))
-            )
-            instructions = f"{instructions}\n\n{output_schema}"
+        if not self.llm.supports_function_calling():
+            model_schema = PydanticSchemaParser(
+                model=TrainingTaskEvaluation
+            ).get_schema()
+            instructions = f"{instructions}\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
 
         converter = TrainingConverter(
             llm=self.llm,

lib/crewai/src/crewai/utilities/planning_handler.py

@@ -15,12 +15,9 @@ logger = logging.getLogger(__name__)
 class PlanPerTask(BaseModel):
     """Represents a plan for a specific task."""
 
-    task_number: int = Field(
-        description="The 1-indexed task number this plan corresponds to",
-        ge=1,
-    )
-    task: str = Field(description="The task for which the plan is created")
+    task: str = Field(..., description="The task for which the plan is created")
     plan: str = Field(
+        ...,
         description="The step by step plan on how the agents can execute their tasks using the available tools with mastery",
     )
 

lib/crewai/src/crewai/utilities/pydantic_schema_parser.py

@@ -0,0 +1,103 @@
+from typing import Any, Union, get_args, get_origin
+
+from pydantic import BaseModel, Field
+
+
+class PydanticSchemaParser(BaseModel):
+    model: type[BaseModel] = Field(..., description="The Pydantic model to parse.")
+
+    def get_schema(self) -> str:
+        """Public method to get the schema of a Pydantic model.
+
+        Returns:
+            String representation of the model schema.
+        """
+        return "{\n" + self._get_model_schema(self.model) + "\n}"
+
+    def _get_model_schema(self, model: type[BaseModel], depth: int = 0) -> str:
+        """Recursively get the schema of a Pydantic model, handling nested models and lists.
+
+        Args:
+            model: The Pydantic model to process.
+            depth: The current depth of recursion for indentation purposes.
+
+        Returns:
+            A string representation of the model schema.
+        """
+        indent: str = " " * 4 * depth
+        lines: list[str] = [
+            f"{indent}    {field_name}: {self._get_field_type_for_annotation(field.annotation, depth + 1)}"
+            for field_name, field in model.model_fields.items()
+        ]
+        return ",\n".join(lines)
+
+    def _format_list_type(self, list_item_type: Any, depth: int) -> str:
+        """Format a List type, handling nested models if necessary.
+
+        Args:
+            list_item_type: The type of items in the list.
+            depth: The current depth of recursion for indentation purposes.
+
+        Returns:
+            A string representation of the List type.
+        """
+        if isinstance(list_item_type, type) and issubclass(list_item_type, BaseModel):
+            nested_schema = self._get_model_schema(list_item_type, depth + 1)
+            nested_indent = " " * 4 * depth
+            return f"List[\n{nested_indent}{{\n{nested_schema}\n{nested_indent}}}\n{nested_indent}]"
+        return f"List[{list_item_type.__name__}]"
+
+    def _format_union_type(self, field_type: Any, depth: int) -> str:
+        """Format a Union type, handling Optional and nested types.
+
+        Args:
+            field_type: The Union type to format.
+            depth: The current depth of recursion for indentation purposes.
+
+        Returns:
+            A string representation of the Union type.
+        """
+        args = get_args(field_type)
+        if type(None) in args:
+            # It's an Optional type
+            non_none_args = [arg for arg in args if arg is not type(None)]
+            if len(non_none_args) == 1:
+                inner_type = self._get_field_type_for_annotation(
+                    non_none_args[0], depth
+                )
+                return f"Optional[{inner_type}]"
+            # Union with None and multiple other types
+            inner_types = ", ".join(
+                self._get_field_type_for_annotation(arg, depth) for arg in non_none_args
+            )
+            return f"Optional[Union[{inner_types}]]"
+        # General Union type
+        inner_types = ", ".join(
+            self._get_field_type_for_annotation(arg, depth) for arg in args
+        )
+        return f"Union[{inner_types}]"
+
+    def _get_field_type_for_annotation(self, annotation: Any, depth: int) -> str:
+        """Recursively get the string representation of a field's type annotation.
+
+        Args:
+            annotation: The type annotation to process.
+            depth: The current depth of recursion for indentation purposes.
+
+        Returns:
+            A string representation of the type annotation.
+        """
+        origin: Any = get_origin(annotation)
+        if origin is list:
+            list_item_type = get_args(annotation)[0]
+            return self._format_list_type(list_item_type, depth)
+        if origin is dict:
+            key_type, value_type = get_args(annotation)
+            return f"Dict[{key_type.__name__}, {value_type.__name__}]"
+        if origin is Union:
+            return self._format_union_type(annotation, depth)
+        if isinstance(annotation, type) and issubclass(annotation, BaseModel):
+            nested_schema = self._get_model_schema(annotation, depth)
+            nested_indent = " " * 4 * depth
+            return f"{annotation.__name__}\n{nested_indent}{{\n{nested_schema}\n{nested_indent}}}"
+        return annotation.__name__

lib/crewai/src/crewai/utilities/pydantic_schema_utils.py

@@ -1,245 +0,0 @@
-"""Utilities for generating JSON schemas from Pydantic models.
-
-This module provides functions for converting Pydantic models to JSON schemas
-suitable for use with LLMs and tool definitions.
-"""
-
-from collections.abc import Callable
-from copy import deepcopy
-from typing import Any
-
-from pydantic import BaseModel
-
-
-def resolve_refs(schema: dict[str, Any]) -> dict[str, Any]:
-    """Recursively resolve all local $refs in the given JSON Schema using $defs as the source.
-
-    This is needed because Pydantic generates $ref-based schemas that
-    some consumers (e.g. LLMs, tool frameworks) don't handle well.
-
-    Args:
-        schema: JSON Schema dict that may contain "$refs" and "$defs".
-
-    Returns:
-        A new schema dictionary with all local $refs replaced by their definitions.
-    """
-    defs = schema.get("$defs", {})
-    schema_copy = deepcopy(schema)
-
-    def _resolve(node: Any) -> Any:
-        if isinstance(node, dict):
-            ref = node.get("$ref")
-            if isinstance(ref, str) and ref.startswith("#/$defs/"):
-                def_name = ref.replace("#/$defs/", "")
-                if def_name in defs:
-                    return _resolve(deepcopy(defs[def_name]))
-                raise KeyError(f"Definition '{def_name}' not found in $defs.")
-            return {k: _resolve(v) for k, v in node.items()}
-
-        if isinstance(node, list):
-            return [_resolve(i) for i in node]
-
-        return node
-
-    return _resolve(schema_copy)  # type: ignore[no-any-return]
-
-
-def add_key_in_dict_recursively(
-    d: dict[str, Any], key: str, value: Any, criteria: Callable[[dict[str, Any]], bool]
-) -> dict[str, Any]:
-    """Recursively adds a key/value pair to all nested dicts matching `criteria`.
-
-    Args:
-        d: The dictionary to modify.
-        key: The key to add.
-        value: The value to add.
-        criteria: A function that returns True for dicts that should receive the key.
-
-    Returns:
-        The modified dictionary.
-    """
-    if isinstance(d, dict):
-        if criteria(d) and key not in d:
-            d[key] = value
-        for v in d.values():
-            add_key_in_dict_recursively(v, key, value, criteria)
-    elif isinstance(d, list):
-        for i in d:
-            add_key_in_dict_recursively(i, key, value, criteria)
-    return d
-
-
-def fix_discriminator_mappings(schema: dict[str, Any]) -> dict[str, Any]:
-    """Replace '#/$defs/...' references in discriminator.mapping with just the model name.
-
-    Args:
-        schema: JSON schema dictionary.
-
-    Returns:
-        Modified schema with fixed discriminator mappings.
-    """
-    output = schema.get("properties", {}).get("output")
-    if not output:
-        return schema
-
-    disc = output.get("discriminator")
-    if not disc or "mapping" not in disc:
-        return schema
-
-    disc["mapping"] = {k: v.split("/")[-1] for k, v in disc["mapping"].items()}
-    return schema
-
-
-def add_const_to_oneof_variants(schema: dict[str, Any]) -> dict[str, Any]:
-    """Add const fields to oneOf variants for discriminated unions.
-
-    The json_schema_to_pydantic library requires each oneOf variant to have
-    a const field for the discriminator property. This function adds those
-    const fields based on the discriminator mapping.
-
-    Args:
-        schema: JSON Schema dict that may contain discriminated unions
-
-    Returns:
-        Modified schema with const fields added to oneOf variants
-    """
-
-    def _process_oneof(node: dict[str, Any]) -> dict[str, Any]:
-        """Process a single node that might contain a oneOf with discriminator."""
-        if not isinstance(node, dict):
-            return node
-
-        if "oneOf" in node and "discriminator" in node:
-            discriminator = node["discriminator"]
-            property_name = discriminator.get("propertyName")
-            mapping = discriminator.get("mapping", {})
-
-            if property_name and mapping:
-                one_of_variants = node.get("oneOf", [])
-
-                for variant in one_of_variants:
-                    if isinstance(variant, dict) and "properties" in variant:
-                        variant_title = variant.get("title", "")
-
-                        matched_disc_value = None
-                        for disc_value, schema_name in mapping.items():
-                            if variant_title == schema_name or variant_title.endswith(
-                                schema_name
-                            ):
-                                matched_disc_value = disc_value
-                                break
-
-                        if matched_disc_value is not None:
-                            props = variant["properties"]
-                            if property_name in props:
-                                props[property_name]["const"] = matched_disc_value
-
-        for key, value in node.items():
-            if isinstance(value, dict):
-                node[key] = _process_oneof(value)
-            elif isinstance(value, list):
-                node[key] = [
-                    _process_oneof(item) if isinstance(item, dict) else item
-                    for item in value
-                ]
-
-        return node
-
-    return _process_oneof(deepcopy(schema))
-
-
-def convert_oneof_to_anyof(schema: dict[str, Any]) -> dict[str, Any]:
-    """Convert oneOf to anyOf for OpenAI compatibility.
-
-    OpenAI's Structured Outputs support anyOf better than oneOf.
-    This recursively converts all oneOf occurrences to anyOf.
-
-    Args:
-        schema: JSON schema dictionary.
-
-    Returns:
-        Modified schema with anyOf instead of oneOf.
-    """
-    if isinstance(schema, dict):
-        if "oneOf" in schema:
-            schema["anyOf"] = schema.pop("oneOf")
-
-        for value in schema.values():
-            if isinstance(value, dict):
-                convert_oneof_to_anyof(value)
-            elif isinstance(value, list):
-                for item in value:
-                    if isinstance(item, dict):
-                        convert_oneof_to_anyof(item)
-
-    return schema
-
-
-def ensure_all_properties_required(schema: dict[str, Any]) -> dict[str, Any]:
-    """Ensure all properties are in the required array for OpenAI strict mode.
-
-    OpenAI's strict structured outputs require all properties to be listed
-    in the required array. This recursively updates all objects to include
-    all their properties in required.
-
-    Args:
-        schema: JSON schema dictionary.
-
-    Returns:
-        Modified schema with all properties marked as required.
-    """
-    if isinstance(schema, dict):
-        if schema.get("type") == "object" and "properties" in schema:
-            properties = schema["properties"]
-            if properties:
-                schema["required"] = list(properties.keys())
-
-        for value in schema.values():
-            if isinstance(value, dict):
-                ensure_all_properties_required(value)
-            elif isinstance(value, list):
-                for item in value:
-                    if isinstance(item, dict):
-                        ensure_all_properties_required(item)
-
-    return schema
-
-
-def generate_model_description(model: type[BaseModel]) -> dict[str, Any]:
-    """Generate JSON schema description of a Pydantic model.
-
-    This function takes a Pydantic model class and returns its JSON schema,
-    which includes full type information, discriminators, and all metadata.
-    The schema is dereferenced to inline all $ref references for better LLM understanding.
-
-    Args:
-        model: A Pydantic model class.
-
-    Returns:
-        A JSON schema dictionary representation of the model.
-    """
-    json_schema = model.model_json_schema(ref_template="#/$defs/{model}")
-
-    json_schema = add_key_in_dict_recursively(
-        json_schema,
-        key="additionalProperties",
-        value=False,
-        criteria=lambda d: d.get("type") == "object"
-        and "additionalProperties" not in d,
-    )
-
-    json_schema = resolve_refs(json_schema)
-
-    json_schema.pop("$defs", None)
-    json_schema = fix_discriminator_mappings(json_schema)
-    json_schema = convert_oneof_to_anyof(json_schema)
-    json_schema = ensure_all_properties_required(json_schema)
-
-    return {
-        "type": "json_schema",
-        "json_schema": {
-            "name": model.__name__,
-            "strict": True,
-            "schema": json_schema,
-        },
-    }

lib/crewai/tests/events/types/test_system_events.py

@@ -27,9 +27,9 @@ class TestSignalType:
         """Verify SignalType maps to correct signal numbers."""
         assert SignalType.SIGTERM == signal.SIGTERM
         assert SignalType.SIGINT == signal.SIGINT
-        assert SignalType.SIGHUP == getattr(signal, "SIGHUP", 1)
-        assert SignalType.SIGTSTP == getattr(signal, "SIGTSTP", 20)
-        assert SignalType.SIGCONT == getattr(signal, "SIGCONT", 18)
+        assert SignalType.SIGHUP == signal.SIGHUP
+        assert SignalType.SIGTSTP == signal.SIGTSTP
+        assert SignalType.SIGCONT == signal.SIGCONT
 
 
 class TestSignalEvents:

lib/crewai/tests/llms/azure/test_azure.py

@@ -389,12 +389,12 @@ def test_azure_raises_error_when_endpoint_missing():
 
 
 def test_azure_raises_error_when_api_key_missing():
-    """Test that AzureCompletion raises ValueError when API key is missing"""
+    """Test that AzureCompletion raises ValueError when no credentials are provided"""
     from crewai.llms.providers.azure.completion import AzureCompletion
 
     # Clear environment variables
     with patch.dict(os.environ, {}, clear=True):
-        with pytest.raises(ValueError, match="Azure API key is required"):
+        with pytest.raises(ValueError, match="Azure credentials are required"):
             AzureCompletion(model="gpt-4", endpoint="https://test.openai.azure.com")
 
 
@@ -1127,3 +1127,288 @@ def test_azure_streaming_returns_usage_metrics():
     assert result.token_usage.prompt_tokens > 0
     assert result.token_usage.completion_tokens > 0
     assert result.token_usage.successful_requests >= 1
+
+
+def test_azure_ad_token_authentication():
+    """
+    Test that Azure AD token authentication works via AZURE_AD_TOKEN env var.
+    """
+    from crewai.llms.providers.azure.completion import AzureCompletion, _StaticTokenCredential
+
+    with patch.dict(os.environ, {
+        "AZURE_AD_TOKEN": "test-ad-token",
+        "AZURE_ENDPOINT": "https://test.openai.azure.com"
+    }, clear=True):
+        llm = LLM(model="azure/gpt-4")
+
+        assert isinstance(llm, AzureCompletion)
+        assert llm.azure_ad_token == "test-ad-token"
+        assert llm.api_key is None
+
+
+def test_azure_ad_token_parameter():
+    """
+    Test that azure_ad_token parameter works for Azure AD authentication.
+    """
+    from crewai.llms.providers.azure.completion import AzureCompletion
+
+    llm = LLM(
+        model="azure/gpt-4",
+        azure_ad_token="my-ad-token",
+        endpoint="https://test.openai.azure.com"
+    )
+
+    assert isinstance(llm, AzureCompletion)
+    assert llm.azure_ad_token == "my-ad-token"
+
+
+def test_azure_credential_parameter():
+    """
+    Test that credential parameter works for passing TokenCredential directly.
+    """
+    from crewai.llms.providers.azure.completion import AzureCompletion
+
+    class MockTokenCredential:
+        def get_token(self, *scopes, **kwargs):
+            from azure.core.credentials import AccessToken
+            return AccessToken("mock-token", 9999999999)
+
+    mock_credential = MockTokenCredential()
+
+    llm = LLM(
+        model="azure/gpt-4",
+        credential=mock_credential,
+        endpoint="https://test.openai.azure.com"
+    )
+
+    assert isinstance(llm, AzureCompletion)
+    assert llm._explicit_credential is mock_credential
+
+
+def test_azure_use_default_credential():
+    """
+    Test that use_default_credential=True uses DefaultAzureCredential.
+    """
+    from crewai.llms.providers.azure.completion import AzureCompletion
+
+    try:
+        from azure.identity import DefaultAzureCredential
+        azure_identity_available = True
+    except ImportError:
+        azure_identity_available = False
+
+    if azure_identity_available:
+        with patch('azure.identity.DefaultAzureCredential') as mock_default_cred:
+            mock_default_cred.return_value = MagicMock()
+
+            with patch.dict(os.environ, {
+                "AZURE_ENDPOINT": "https://test.openai.azure.com"
+            }, clear=True):
+                llm = LLM(
+                    model="azure/gpt-4",
+                    use_default_credential=True
+                )
+
+                assert isinstance(llm, AzureCompletion)
+                assert llm.use_default_credential is True
+                mock_default_cred.assert_called_once()
+    else:
+        with patch.dict(os.environ, {
+            "AZURE_ENDPOINT": "https://test.openai.azure.com"
+        }, clear=True):
+            with pytest.raises(ImportError, match="azure-identity package is required"):
+                LLM(
+                    model="azure/gpt-4",
+                    use_default_credential=True
+                )
+
+
+def test_azure_credential_priority_explicit_credential_first():
+    """
+    Test that explicit credential takes priority over other auth methods.
+    """
+    from crewai.llms.providers.azure.completion import AzureCompletion
+
+    class MockTokenCredential:
+        def get_token(self, *scopes, **kwargs):
+            from azure.core.credentials import AccessToken
+            return AccessToken("mock-token", 9999999999)
+
+    mock_credential = MockTokenCredential()
+
+    with patch.dict(os.environ, {
+        "AZURE_API_KEY": "test-key",
+        "AZURE_AD_TOKEN": "test-ad-token",
+        "AZURE_ENDPOINT": "https://test.openai.azure.com"
+    }):
+        llm = LLM(
+            model="azure/gpt-4",
+            credential=mock_credential,
+            api_key="another-key",
+            azure_ad_token="another-token"
+        )
+
+        assert isinstance(llm, AzureCompletion)
+        assert llm._explicit_credential is mock_credential
+
+
+def test_azure_credential_priority_ad_token_over_api_key():
+    """
+    Test that azure_ad_token takes priority over api_key.
+    """
+    from crewai.llms.providers.azure.completion import AzureCompletion, _StaticTokenCredential
+
+    with patch.dict(os.environ, {
+        "AZURE_ENDPOINT": "https://test.openai.azure.com"
+    }, clear=True):
+        llm = LLM(
+            model="azure/gpt-4",
+            azure_ad_token="my-ad-token",
+            api_key="my-api-key"
+        )
+
+        assert isinstance(llm, AzureCompletion)
+        assert llm.azure_ad_token == "my-ad-token"
+        assert llm.api_key == "my-api-key"
+
+
+def test_azure_raises_error_when_no_credentials():
+    """
+    Test that AzureCompletion raises ValueError when no credentials are provided.
+    """
+    from crewai.llms.providers.azure.completion import AzureCompletion
+
+    with patch.dict(os.environ, {
+        "AZURE_ENDPOINT": "https://test.openai.azure.com"
+    }, clear=True):
+        with pytest.raises(ValueError, match="Azure credentials are required"):
+            AzureCompletion(model="gpt-4", endpoint="https://test.openai.azure.com")
+
+
+def test_azure_static_token_credential():
+    """
+    Test that _StaticTokenCredential properly wraps a static token.
+    """
+    from crewai.llms.providers.azure.completion import _StaticTokenCredential
+    from azure.core.credentials import AccessToken
+
+    token = "my-static-token"
+    credential = _StaticTokenCredential(token)
+
+    access_token = credential.get_token("https://cognitiveservices.azure.com/.default")
+
+    assert isinstance(access_token, AccessToken)
+    assert access_token.token == token
+    assert access_token.expires_on > 0
+
+
+def test_azure_ad_token_env_var_used_when_no_api_key():
+    """
+    Test that AZURE_AD_TOKEN env var is used when AZURE_API_KEY is not set.
+    This reproduces the scenario from GitHub issue #4069.
+    """
+    from crewai.llms.providers.azure.completion import AzureCompletion
+
+    with patch.dict(os.environ, {
+        "AZURE_AD_TOKEN": "token-from-provider",
+        "AZURE_ENDPOINT": "https://my-endpoint.openai.azure.com"
+    }, clear=True):
+        llm = LLM(
+            model="azure/gpt-4o-mini",
+            api_version="2024-02-01"
+        )
+
+        assert isinstance(llm, AzureCompletion)
+        assert llm.azure_ad_token == "token-from-provider"
+        assert llm.api_key is None
+
+
+def test_azure_backward_compatibility_api_key():
+    """
+    Test that existing API key authentication still works (backward compatibility).
+    """
+    from crewai.llms.providers.azure.completion import AzureCompletion
+    from azure.core.credentials import AzureKeyCredential
+
+    with patch.dict(os.environ, {
+        "AZURE_API_KEY": "test-api-key",
+        "AZURE_ENDPOINT": "https://test.openai.azure.com"
+    }, clear=True):
+        llm = LLM(model="azure/gpt-4")
+
+        assert isinstance(llm, AzureCompletion)
+        assert llm.api_key == "test-api-key"
+        assert llm.azure_ad_token is None
+
+
+def test_azure_select_credential_returns_correct_type():
+    """
+    Test that _select_credential returns the correct credential type based on config.
+    """
+    from crewai.llms.providers.azure.completion import AzureCompletion, _StaticTokenCredential
+    from azure.core.credentials import AzureKeyCredential
+
+    with patch.dict(os.environ, {
+        "AZURE_ENDPOINT": "https://test.openai.azure.com"
+    }, clear=True):
+        llm_api_key = AzureCompletion(
+            model="gpt-4",
+            api_key="test-key",
+            endpoint="https://test.openai.azure.com"
+        )
+        credential = llm_api_key._select_credential()
+        assert isinstance(credential, AzureKeyCredential)
+
+        llm_ad_token = AzureCompletion(
+            model="gpt-4",
+            azure_ad_token="test-ad-token",
+            endpoint="https://test.openai.azure.com"
+        )
+        credential = llm_ad_token._select_credential()
+        assert isinstance(credential, _StaticTokenCredential)
+
+
+def test_azure_use_default_credential_import_error():
+    """
+    Test that use_default_credential raises ImportError when azure-identity is not available.
+    """
+    from crewai.llms.providers.azure.completion import AzureCompletion
+    import builtins
+
+    original_import = builtins.__import__
+
+    def mock_import(name, *args, **kwargs):
+        if name == 'azure.identity':
+            raise ImportError("No module named 'azure.identity'")
+        return original_import(name, *args, **kwargs)
+
+    with patch.dict(os.environ, {
+        "AZURE_ENDPOINT": "https://test.openai.azure.com"
+    }, clear=True):
+        with patch.object(builtins, '__import__', side_effect=mock_import):
+            with pytest.raises(ImportError, match="azure-identity package is required"):
+                AzureCompletion(
+                    model="gpt-4",
+                    endpoint="https://test.openai.azure.com",
+                    use_default_credential=True
+                )
+
+
+def test_azure_improved_error_message_no_credentials():
+    """
+    Test that the error message when no credentials are provided is helpful.
+    """
+    from crewai.llms.providers.azure.completion import AzureCompletion
+
+    with patch.dict(os.environ, {}, clear=True):
+        with pytest.raises(ValueError) as excinfo:
+            AzureCompletion(model="gpt-4", endpoint="https://test.openai.azure.com")
+
+        error_message = str(excinfo.value)
+        assert "Azure credentials are required" in error_message
+        assert "api_key" in error_message
+        assert "AZURE_API_KEY" in error_message
+        assert "azure_ad_token" in error_message
+        assert "AZURE_AD_TOKEN" in error_message
+        assert "credential" in error_message
+        assert "use_default_credential" in error_message

lib/crewai/tests/test_task.py

@@ -1727,24 +1727,3 @@ def test_task_output_includes_messages():
     assert hasattr(task2_output, "messages")
     assert isinstance(task2_output.messages, list)
     assert len(task2_output.messages) > 0
-
-
-def test_async_execution_fails():
-    researcher = Agent(
-      role="Researcher",
-      goal="Make the best research and analysis on content about AI and AI agents",
-      backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
-      allow_delegation=False,
-    )
-
-    task = Task(
-      description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
-      expected_output="Bullet point list of 5 interesting ideas.",
-      async_execution=True,
-      agent=researcher,
-    )
-
-    with patch.object(Task, "_execute_core", side_effect=RuntimeError("boom!")):
-      with pytest.raises(RuntimeError, match="boom!"):
-        execution = task.execute_async(agent=researcher)
-        execution.result()

lib/crewai/tests/tools/test_base_tool.py

@@ -17,11 +17,10 @@ def test_creating_a_tool_using_annotation():
 
     # Assert all the right attributes were defined
     assert my_tool.name == "Name of my tool"
-    assert "Tool Name: Name of my tool" in my_tool.description
-    assert "Tool Arguments:" in my_tool.description
-    assert '"question"' in my_tool.description
-    assert '"type": "string"' in my_tool.description
-    assert "Tool Description: Clear description for what this tool is useful for" in my_tool.description
+    assert (
+        my_tool.description
+        == "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, your agent will need this information to use it."
+    )
     assert my_tool.args_schema.model_json_schema()["properties"] == {
         "question": {"title": "Question", "type": "string"}
     }
@@ -32,9 +31,10 @@ def test_creating_a_tool_using_annotation():
     converted_tool = my_tool.to_structured_tool()
     assert converted_tool.name == "Name of my tool"
 
-    assert "Tool Name: Name of my tool" in converted_tool.description
-    assert "Tool Arguments:" in converted_tool.description
-    assert '"question"' in converted_tool.description
+    assert (
+        converted_tool.description
+        == "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, your agent will need this information to use it."
+    )
     assert converted_tool.args_schema.model_json_schema()["properties"] == {
         "question": {"title": "Question", "type": "string"}
     }
@@ -56,11 +56,10 @@ def test_creating_a_tool_using_baseclass():
     # Assert all the right attributes were defined
     assert my_tool.name == "Name of my tool"
 
-    assert "Tool Name: Name of my tool" in my_tool.description
-    assert "Tool Arguments:" in my_tool.description
-    assert '"question"' in my_tool.description
-    assert '"type": "string"' in my_tool.description
-    assert "Tool Description: Clear description for what this tool is useful for" in my_tool.description
+    assert (
+        my_tool.description
+        == "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, your agent will need this information to use it."
+    )
     assert my_tool.args_schema.model_json_schema()["properties"] == {
         "question": {"title": "Question", "type": "string"}
     }
@@ -69,9 +68,10 @@ def test_creating_a_tool_using_baseclass():
     converted_tool = my_tool.to_structured_tool()
     assert converted_tool.name == "Name of my tool"
 
-    assert "Tool Name: Name of my tool" in converted_tool.description
-    assert "Tool Arguments:" in converted_tool.description
-    assert '"question"' in converted_tool.description
+    assert (
+        converted_tool.description
+        == "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, your agent will need this information to use it."
+    )
     assert converted_tool.args_schema.model_json_schema()["properties"] == {
         "question": {"title": "Question", "type": "string"}
     }

lib/crewai/tests/tools/test_tool_usage.py

@@ -107,20 +107,25 @@ def test_tool_usage_render():
 
     rendered = tool_usage._render()
 
-    # Check that the rendered output contains the expected tool information
+    # Updated checks to match the actual output
     assert "Tool Name: Random Number Generator" in rendered
     assert "Tool Arguments:" in rendered
+    assert (
+        "'min_value': {'description': 'The minimum value of the range (inclusive)', 'type': 'int'}"
+        in rendered
+    )
+    assert (
+        "'max_value': {'description': 'The maximum value of the range (inclusive)', 'type': 'int'}"
+        in rendered
+    )
     assert (
         "Tool Description: Generates a random number within a specified range"
         in rendered
     )
-
-    # Check that the JSON schema format is used (proper JSON schema types)
-    assert '"min_value"' in rendered
-    assert '"max_value"' in rendered
-    assert '"type": "integer"' in rendered
-    assert '"description": "The minimum value of the range (inclusive)"' in rendered
-    assert '"description": "The maximum value of the range (inclusive)"' in rendered
+    assert (
+        "Tool Name: Random Number Generator\nTool Arguments: {'min_value': {'description': 'The minimum value of the range (inclusive)', 'type': 'int'}, 'max_value': {'description': 'The maximum value of the range (inclusive)', 'type': 'int'}}\nTool Description: Generates a random number within a specified range"
+        in rendered
+    )
 
 
 def test_validate_tool_input_booleans_and_none():

lib/crewai/tests/utilities/evaluators/test_task_evaluator.py

@@ -1,3 +1,4 @@
+from unittest import mock
 from unittest.mock import MagicMock, patch
 
 from crewai.utilities.converter import ConverterError
@@ -43,26 +44,26 @@ def test_evaluate_training_data(converter_mock):
     )
 
     assert result == function_return_value
-
-    # Verify the converter was called with correct arguments
-    converter_mock.assert_called_once()
-    call_kwargs = converter_mock.call_args.kwargs
-
-    assert call_kwargs["llm"] == original_agent.llm
-    assert call_kwargs["model"] == TrainingTaskEvaluation
-    assert "Iteration: data1" in call_kwargs["text"]
-    assert "Iteration: data2" in call_kwargs["text"]
-
-    instructions = call_kwargs["instructions"]
-    assert "I'm gonna convert this raw text into valid JSON." in instructions
-    assert "OpenAPI schema" in instructions
-    assert '"type": "json_schema"' in instructions
-    assert '"name": "TrainingTaskEvaluation"' in instructions
-    assert '"suggestions"' in instructions
-    assert '"quality"' in instructions
-    assert '"final_summary"' in instructions
-
-    converter_mock.return_value.to_pydantic.assert_called_once()
+    converter_mock.assert_has_calls(
+        [
+            mock.call(
+                llm=original_agent.llm,
+                text="Assess the quality of the training data based on the llm output, human feedback , and llm "
+                "output improved result.\n\nIteration: data1\nInitial Output:\nInitial output 1\n\nHuman Feedback:\nHuman feedback "
+                "1\n\nImproved Output:\nImproved output 1\n\n------------------------------------------------\n\nIteration: data2\nInitial Output:\nInitial output 2\n\nHuman "
+                "Feedback:\nHuman feedback 2\n\nImproved Output:\nImproved output 2\n\n------------------------------------------------\n\nPlease provide:\n- Provide "
+                "a list of clear, actionable instructions derived from the Human Feedbacks to enhance the Agent's "
+                "performance. Analyze the differences between Initial Outputs and Improved Outputs to generate specific "
+                "action items for future tasks. Ensure all key and specificpoints from the human feedback are "
+                "incorporated into these instructions.\n- A score from 0 to 10 evaluating on completion, quality, and "
+                "overall performance from the improved output to the initial output based on the human feedback\n",
+                model=TrainingTaskEvaluation,
+                instructions="I'm gonna convert this raw text into valid JSON.\n\nThe json should have the "
+                "following structure, with the following keys:\n{\n    suggestions: List[str],\n    quality: float,\n    final_summary: str\n}",
+            ),
+            mock.call().to_pydantic(),
+        ]
+    )
 
 
 @patch("crewai.utilities.converter.Converter.to_pydantic")

lib/crewai/tests/utilities/test_agent_utils.py

@@ -1,272 +0,0 @@
-"""Tests for agent_utils module.
-
-These tests cover the format_answer() and handle_max_iterations_exceeded() functions,
-specifically testing the fix for issue #4113 where OutputParserError was being
-swallowed instead of being re-raised for retry logic.
-"""
-
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-from crewai.agents.parser import (
-    AgentAction,
-    AgentFinish,
-    OutputParserError,
-)
-from crewai.utilities.agent_utils import (
-    format_answer,
-    handle_max_iterations_exceeded,
-    process_llm_response,
-)
-
-
-class TestFormatAnswer:
-    """Tests for the format_answer function."""
-
-    def test_format_answer_with_valid_action(self) -> None:
-        """Test that format_answer correctly parses a valid action."""
-        answer = "Thought: Let's search\nAction: search\nAction Input: query"
-        result = format_answer(answer)
-        assert isinstance(result, AgentAction)
-        assert result.tool == "search"
-        assert result.tool_input == "query"
-
-    def test_format_answer_with_valid_final_answer(self) -> None:
-        """Test that format_answer correctly parses a valid final answer."""
-        answer = "Thought: I found the answer\nFinal Answer: The result is 42"
-        result = format_answer(answer)
-        assert isinstance(result, AgentFinish)
-        assert result.output == "The result is 42"
-
-    def test_format_answer_raises_output_parser_error_for_malformed_output(
-        self,
-    ) -> None:
-        """Test that format_answer re-raises OutputParserError for malformed output.
-
-        This is the core fix for issue #4113. Previously, format_answer would catch
-        all exceptions and return AgentFinish, which broke the retry logic.
-        """
-        malformed_answer = """Thought
-The user wants to verify something.
-Action
-Video Analysis Tool
-Action Input:
-{"query": "Is there something?"}"""
-
-        with pytest.raises(OutputParserError):
-            format_answer(malformed_answer)
-
-    def test_format_answer_raises_output_parser_error_missing_action(self) -> None:
-        """Test that format_answer re-raises OutputParserError when Action is missing."""
-        answer = "Thought: Let's search\nAction Input: query"
-        with pytest.raises(OutputParserError) as exc_info:
-            format_answer(answer)
-        assert "Action:" in str(exc_info.value)
-
-    def test_format_answer_raises_output_parser_error_missing_action_input(
-        self,
-    ) -> None:
-        """Test that format_answer re-raises OutputParserError when Action Input is missing."""
-        answer = "Thought: Let's search\nAction: search"
-        with pytest.raises(OutputParserError) as exc_info:
-            format_answer(answer)
-        assert "Action Input:" in str(exc_info.value)
-
-    def test_format_answer_returns_agent_finish_for_generic_exception(self) -> None:
-        """Test that format_answer returns AgentFinish for non-OutputParserError exceptions."""
-        with patch(
-            "crewai.utilities.agent_utils.parse",
-            side_effect=ValueError("Unexpected error"),
-        ):
-            result = format_answer("some answer")
-            assert isinstance(result, AgentFinish)
-            assert result.thought == "Failed to parse LLM response"
-            assert result.output == "some answer"
-
-
-class TestProcessLlmResponse:
-    """Tests for the process_llm_response function."""
-
-    def test_process_llm_response_raises_output_parser_error(self) -> None:
-        """Test that process_llm_response propagates OutputParserError."""
-        malformed_answer = "Thought\nMissing colons\nAction\nSome Tool"
-        with pytest.raises(OutputParserError):
-            process_llm_response(malformed_answer, use_stop_words=True)
-
-    def test_process_llm_response_with_valid_action(self) -> None:
-        """Test that process_llm_response correctly processes a valid action."""
-        answer = "Thought: Let's search\nAction: search\nAction Input: query"
-        result = process_llm_response(answer, use_stop_words=True)
-        assert isinstance(result, AgentAction)
-        assert result.tool == "search"
-
-    def test_process_llm_response_with_valid_final_answer(self) -> None:
-        """Test that process_llm_response correctly processes a valid final answer."""
-        answer = "Thought: Done\nFinal Answer: The result"
-        result = process_llm_response(answer, use_stop_words=True)
-        assert isinstance(result, AgentFinish)
-        assert result.output == "The result"
-
-
-class TestHandleMaxIterationsExceeded:
-    """Tests for the handle_max_iterations_exceeded function."""
-
-    def test_handle_max_iterations_exceeded_with_valid_final_answer(self) -> None:
-        """Test that handle_max_iterations_exceeded returns AgentFinish for valid output."""
-        mock_llm = MagicMock()
-        mock_llm.call.return_value = "Thought: Done\nFinal Answer: The final result"
-        mock_printer = MagicMock()
-        mock_i18n = MagicMock()
-        mock_i18n.errors.return_value = "Please provide final answer"
-
-        result = handle_max_iterations_exceeded(
-            formatted_answer=None,
-            printer=mock_printer,
-            i18n=mock_i18n,
-            messages=[],
-            llm=mock_llm,
-            callbacks=[],
-        )
-
-        assert isinstance(result, AgentFinish)
-        assert result.output == "The final result"
-
-    def test_handle_max_iterations_exceeded_with_valid_action_converts_to_finish(
-        self,
-    ) -> None:
-        """Test that handle_max_iterations_exceeded converts AgentAction to AgentFinish."""
-        mock_llm = MagicMock()
-        mock_llm.call.return_value = (
-            "Thought: Using tool\nAction: search\nAction Input: query"
-        )
-        mock_printer = MagicMock()
-        mock_i18n = MagicMock()
-        mock_i18n.errors.return_value = "Please provide final answer"
-
-        result = handle_max_iterations_exceeded(
-            formatted_answer=None,
-            printer=mock_printer,
-            i18n=mock_i18n,
-            messages=[],
-            llm=mock_llm,
-            callbacks=[],
-        )
-
-        assert isinstance(result, AgentFinish)
-
-    def test_handle_max_iterations_exceeded_catches_output_parser_error(self) -> None:
-        """Test that handle_max_iterations_exceeded catches OutputParserError and returns AgentFinish.
-
-        This prevents infinite loops when the forced final answer is malformed.
-        Without this safeguard, the OutputParserError would bubble up to _invoke_loop(),
-        which would retry, hit max iterations again, and loop forever.
-        """
-        malformed_response = """Thought
-Missing colons everywhere
-Action
-Some Tool
-Action Input:
-{"query": "test"}"""
-
-        mock_llm = MagicMock()
-        mock_llm.call.return_value = malformed_response
-        mock_printer = MagicMock()
-        mock_i18n = MagicMock()
-        mock_i18n.errors.return_value = "Please provide final answer"
-
-        result = handle_max_iterations_exceeded(
-            formatted_answer=None,
-            printer=mock_printer,
-            i18n=mock_i18n,
-            messages=[],
-            llm=mock_llm,
-            callbacks=[],
-        )
-
-        assert isinstance(result, AgentFinish)
-        assert result.output == malformed_response
-        assert "Failed to parse LLM response during max iterations" in result.thought
-        mock_printer.print.assert_any_call(
-            content="Failed to parse forced final answer. Returning raw response.",
-            color="yellow",
-        )
-
-    def test_handle_max_iterations_exceeded_with_previous_formatted_answer(
-        self,
-    ) -> None:
-        """Test that handle_max_iterations_exceeded uses previous answer text."""
-        mock_llm = MagicMock()
-        mock_llm.call.return_value = "Thought: Done\nFinal Answer: New result"
-        mock_printer = MagicMock()
-        mock_i18n = MagicMock()
-        mock_i18n.errors.return_value = "Please provide final answer"
-
-        previous_answer = AgentAction(
-            thought="Previous thought",
-            tool="search",
-            tool_input="query",
-            text="Previous text",
-        )
-
-        result = handle_max_iterations_exceeded(
-            formatted_answer=previous_answer,
-            printer=mock_printer,
-            i18n=mock_i18n,
-            messages=[],
-            llm=mock_llm,
-            callbacks=[],
-        )
-
-        assert isinstance(result, AgentFinish)
-        assert result.output == "New result"
-
-    def test_handle_max_iterations_exceeded_raises_on_empty_response(self) -> None:
-        """Test that handle_max_iterations_exceeded raises ValueError for empty response."""
-        mock_llm = MagicMock()
-        mock_llm.call.return_value = ""
-        mock_printer = MagicMock()
-        mock_i18n = MagicMock()
-        mock_i18n.errors.return_value = "Please provide final answer"
-
-        with pytest.raises(ValueError, match="Invalid response from LLM call"):
-            handle_max_iterations_exceeded(
-                formatted_answer=None,
-                printer=mock_printer,
-                i18n=mock_i18n,
-                messages=[],
-                llm=mock_llm,
-                callbacks=[],
-            )
-
-
-class TestRetryLogicIntegration:
-    """Integration tests to verify the retry logic works correctly with the fix."""
-
-    def test_malformed_output_allows_retry_in_format_answer(self) -> None:
-        """Test that malformed output raises OutputParserError which can be caught for retry.
-
-        This simulates what happens in _invoke_loop() when the LLM returns malformed output.
-        The OutputParserError should be raised so the loop can catch it and retry.
-        """
-        malformed_outputs = [
-            "Thought\nMissing colon after Thought",
-            "Thought: OK\nAction\nMissing colon after Action",
-            "Thought: OK\nAction: tool\nAction Input\nMissing colon",
-            "Random text without any structure",
-        ]
-
-        for malformed in malformed_outputs:
-            with pytest.raises(OutputParserError):
-                format_answer(malformed)
-
-    def test_valid_output_does_not_raise(self) -> None:
-        """Test that valid outputs are parsed correctly without raising."""
-        valid_outputs = [
-            ("Thought: Let's search\nAction: search\nAction Input: query", AgentAction),
-            ("Thought: Done\nFinal Answer: The result", AgentFinish),
-        ]
-
-        for output, expected_type in valid_outputs:
-            result = format_answer(output)
-            assert isinstance(result, expected_type)

lib/crewai/tests/utilities/test_converter.py

@@ -16,6 +16,7 @@ from crewai.utilities.converter import (
     handle_partial_json,
     validate_model,
 )
+from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
 from pydantic import BaseModel
 import pytest
 

lib/crewai/tests/utilities/test_planning_handler.py

@@ -1,11 +1,7 @@
-"""Tests for the planning handler module."""
-
-from unittest.mock import MagicMock, patch
+from unittest.mock import patch
 
 import pytest
-
 from crewai.agent import Agent
-from crewai.crew import Crew
 from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 from crewai.task import Task
 from crewai.tasks.task_output import TaskOutput
@@ -17,7 +13,7 @@ from crewai.utilities.planning_handler import (
 )
 
 
-class TestInternalCrewPlanner:
+class InternalCrewPlanner:
     @pytest.fixture
     def crew_planner(self):
         tasks = [
@@ -53,9 +49,9 @@ class TestInternalCrewPlanner:
 
     def test_handle_crew_planning(self, crew_planner):
         list_of_plans_per_task = [
-            PlanPerTask(task_number=1, task="Task1", plan="Plan 1"),
-            PlanPerTask(task_number=2, task="Task2", plan="Plan 2"),
-            PlanPerTask(task_number=3, task="Task3", plan="Plan 3"),
+            PlanPerTask(task="Task1", plan="Plan 1"),
+            PlanPerTask(task="Task2", plan="Plan 2"),
+            PlanPerTask(task="Task3", plan="Plan 3"),
         ]
         with patch.object(Task, "execute_sync") as execute:
             execute.return_value = TaskOutput(
@@ -101,12 +97,12 @@ class TestInternalCrewPlanner:
         # Knowledge field should not be present when empty
         assert '"agent_knowledge"' not in tasks_summary
 
-    @patch("crewai.knowledge.knowledge.Knowledge.add_sources")
-    @patch("crewai.knowledge.storage.knowledge_storage.KnowledgeStorage")
-    def test_create_tasks_summary_with_knowledge_and_tools(
-        self, mock_storage, mock_add_sources
-    ):
+    @patch("crewai.knowledge.storage.knowledge_storage.chromadb")
+    def test_create_tasks_summary_with_knowledge_and_tools(self, mock_chroma):
         """Test task summary generation with both knowledge and tools present."""
+        # Mock ChromaDB collection
+        mock_collection = mock_chroma.return_value.get_or_create_collection.return_value
+        mock_collection.add.return_value = None
 
         # Create mock tools with proper string descriptions and structured tool support
         class MockTool(BaseTool):
@@ -170,9 +166,7 @@ class TestInternalCrewPlanner:
                 description="Description",
                 agent="agent",
                 pydantic=PlannerTaskPydanticOutput(
-                    list_of_plans_per_task=[
-                        PlanPerTask(task_number=1, task="Task1", plan="Plan 1")
-                    ]
+                    list_of_plans_per_task=[PlanPerTask(task="Task1", plan="Plan 1")]
                 ),
             )
             result = crew_planner_different_llm._handle_crew_planning()
@@ -183,181 +177,3 @@ class TestInternalCrewPlanner:
                 crew_planner_different_llm.tasks
             )
             execute.assert_called_once()
-
-    def test_plan_per_task_requires_task_number(self):
-        """Test that PlanPerTask model requires task_number field."""
-        with pytest.raises(ValueError):
-            PlanPerTask(task="Task1", plan="Plan 1")
-
-    def test_plan_per_task_with_task_number(self):
-        """Test PlanPerTask model with task_number field."""
-        plan = PlanPerTask(task_number=5, task="Task5", plan="Plan for task 5")
-        assert plan.task_number == 5
-        assert plan.task == "Task5"
-        assert plan.plan == "Plan for task 5"
-
-
-class TestCrewPlanningIntegration:
-    """Tests for Crew._handle_crew_planning integration with task_number matching."""
-
-    def test_crew_planning_with_out_of_order_plans(self):
-        """Test that plans are correctly matched to tasks even when returned out of order.
-
-        This test verifies the fix for issue #3953 where plans returned by the LLM
-        in a different order than the tasks would be incorrectly assigned.
-        """
-        agent1 = Agent(role="Agent 1", goal="Goal 1", backstory="Backstory 1")
-        agent2 = Agent(role="Agent 2", goal="Goal 2", backstory="Backstory 2")
-        agent3 = Agent(role="Agent 3", goal="Goal 3", backstory="Backstory 3")
-
-        task1 = Task(
-            description="First task description",
-            expected_output="Output 1",
-            agent=agent1,
-        )
-        task2 = Task(
-            description="Second task description",
-            expected_output="Output 2",
-            agent=agent2,
-        )
-        task3 = Task(
-            description="Third task description",
-            expected_output="Output 3",
-            agent=agent3,
-        )
-
-        crew = Crew(
-            agents=[agent1, agent2, agent3],
-            tasks=[task1, task2, task3],
-            planning=True,
-        )
-
-        out_of_order_plans = [
-            PlanPerTask(task_number=3, task="Task 3", plan=" [PLAN FOR TASK 3]"),
-            PlanPerTask(task_number=1, task="Task 1", plan=" [PLAN FOR TASK 1]"),
-            PlanPerTask(task_number=2, task="Task 2", plan=" [PLAN FOR TASK 2]"),
-        ]
-
-        mock_planner_result = PlannerTaskPydanticOutput(
-            list_of_plans_per_task=out_of_order_plans
-        )
-
-        with patch.object(
-            CrewPlanner, "_handle_crew_planning", return_value=mock_planner_result
-        ):
-            crew._handle_crew_planning()
-
-        assert "[PLAN FOR TASK 1]" in task1.description
-        assert "[PLAN FOR TASK 2]" in task2.description
-        assert "[PLAN FOR TASK 3]" in task3.description
-
-        assert "[PLAN FOR TASK 3]" not in task1.description
-        assert "[PLAN FOR TASK 1]" not in task2.description
-        assert "[PLAN FOR TASK 2]" not in task3.description
-
-    def test_crew_planning_with_missing_plan(self):
-        """Test that missing plans are handled gracefully with a warning."""
-        agent1 = Agent(role="Agent 1", goal="Goal 1", backstory="Backstory 1")
-        agent2 = Agent(role="Agent 2", goal="Goal 2", backstory="Backstory 2")
-
-        task1 = Task(
-            description="First task description",
-            expected_output="Output 1",
-            agent=agent1,
-        )
-        task2 = Task(
-            description="Second task description",
-            expected_output="Output 2",
-            agent=agent2,
-        )
-
-        crew = Crew(
-            agents=[agent1, agent2],
-            tasks=[task1, task2],
-            planning=True,
-        )
-
-        original_task1_desc = task1.description
-        original_task2_desc = task2.description
-
-        incomplete_plans = [
-            PlanPerTask(task_number=1, task="Task 1", plan=" [PLAN FOR TASK 1]"),
-        ]
-
-        mock_planner_result = PlannerTaskPydanticOutput(
-            list_of_plans_per_task=incomplete_plans
-        )
-
-        with patch.object(
-            CrewPlanner, "_handle_crew_planning", return_value=mock_planner_result
-        ):
-            crew._handle_crew_planning()
-
-        assert "[PLAN FOR TASK 1]" in task1.description
-
-        assert task2.description == original_task2_desc
-
-    def test_crew_planning_preserves_original_description(self):
-        """Test that planning appends to the original task description."""
-        agent = Agent(role="Agent 1", goal="Goal 1", backstory="Backstory 1")
-
-        task = Task(
-            description="Original task description",
-            expected_output="Output 1",
-            agent=agent,
-        )
-
-        crew = Crew(
-            agents=[agent],
-            tasks=[task],
-            planning=True,
-        )
-
-        plans = [
-            PlanPerTask(task_number=1, task="Task 1", plan=" - Additional plan steps"),
-        ]
-
-        mock_planner_result = PlannerTaskPydanticOutput(list_of_plans_per_task=plans)
-
-        with patch.object(
-            CrewPlanner, "_handle_crew_planning", return_value=mock_planner_result
-        ):
-            crew._handle_crew_planning()
-
-        assert "Original task description" in task.description
-        assert "Additional plan steps" in task.description
-
-    def test_crew_planning_with_duplicate_task_numbers(self):
-        """Test that duplicate task numbers use the first plan and log a warning."""
-        agent = Agent(role="Agent 1", goal="Goal 1", backstory="Backstory 1")
-
-        task = Task(
-            description="Task description",
-            expected_output="Output 1",
-            agent=agent,
-        )
-
-        crew = Crew(
-            agents=[agent],
-            tasks=[task],
-            planning=True,
-        )
-
-        # Two plans with the same task_number - should use the first one
-        duplicate_plans = [
-            PlanPerTask(task_number=1, task="Task 1", plan=" [FIRST PLAN]"),
-            PlanPerTask(task_number=1, task="Task 1", plan=" [SECOND PLAN]"),
-        ]
-
-        mock_planner_result = PlannerTaskPydanticOutput(
-            list_of_plans_per_task=duplicate_plans
-        )
-
-        with patch.object(
-            CrewPlanner, "_handle_crew_planning", return_value=mock_planner_result
-        ):
-            crew._handle_crew_planning()
-
-        # Should use the first plan, not the second
-        assert "[FIRST PLAN]" in task.description
-        assert "[SECOND PLAN]" not in task.description

lib/crewai/tests/utilities/test_pydantic_schema_parser.py

@@ -0,0 +1,94 @@
+from typing import Any, Dict, List, Optional, Set, Tuple, Union
+
+import pytest
+from pydantic import BaseModel, Field
+
+from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
+
+
+def test_simple_model():
+    class SimpleModel(BaseModel):
+        field1: int
+        field2: str
+
+    parser = PydanticSchemaParser(model=SimpleModel)
+    schema = parser.get_schema()
+
+    expected_schema = """{
+    field1: int,
+    field2: str
+}"""
+    assert schema.strip() == expected_schema.strip()
+
+
+def test_nested_model():
+    class NestedModel(BaseModel):
+        nested_field: int
+
+    class ParentModel(BaseModel):
+        parent_field: str
+        nested: NestedModel
+
+    parser = PydanticSchemaParser(model=ParentModel)
+    schema = parser.get_schema()
+
+    expected_schema = """{
+    parent_field: str,
+    nested: NestedModel
+    {
+        nested_field: int
+    }
+}"""
+    assert schema.strip() == expected_schema.strip()
+
+
+def test_model_with_list():
+    class ListModel(BaseModel):
+        list_field: List[int]
+
+    parser = PydanticSchemaParser(model=ListModel)
+    schema = parser.get_schema()
+
+    expected_schema = """{
+    list_field: List[int]
+}"""
+    assert schema.strip() == expected_schema.strip()
+
+
+def test_model_with_optional_field():
+    class OptionalModel(BaseModel):
+        optional_field: Optional[str]
+
+    parser = PydanticSchemaParser(model=OptionalModel)
+    schema = parser.get_schema()
+
+    expected_schema = """{
+    optional_field: Optional[str]
+}"""
+    assert schema.strip() == expected_schema.strip()
+
+
+def test_model_with_union():
+    class UnionModel(BaseModel):
+        union_field: Union[int, str]
+
+    parser = PydanticSchemaParser(model=UnionModel)
+    schema = parser.get_schema()
+
+    expected_schema = """{
+    union_field: Union[int, str]
+}"""
+    assert schema.strip() == expected_schema.strip()
+
+
+def test_model_with_dict():
+    class DictModel(BaseModel):
+        dict_field: Dict[str, int]
+
+    parser = PydanticSchemaParser(model=DictModel)
+    schema = parser.get_schema()
+
+    expected_schema = """{
+    dict_field: Dict[str, int]
+}"""
+    assert schema.strip() == expected_schema.strip()

lib/devtools/src/crewai_devtools/__init__.py

@@ -1,3 +1,3 @@
 """CrewAI development tools."""
 
-__version__ = "1.7.1"
+__version__ = "1.7.0"

lib/devtools/src/crewai_devtools/cli.py

@@ -323,17 +323,13 @@ def cli() -> None:
     "--dry-run", is_flag=True, help="Show what would be done without making changes"
 )
 @click.option("--no-push", is_flag=True, help="Don't push changes to remote")
-@click.option(
-    "--no-commit", is_flag=True, help="Don't commit changes (just update files)"
-)
-def bump(version: str, dry_run: bool, no_push: bool, no_commit: bool) -> None:
+def bump(version: str, dry_run: bool, no_push: bool) -> None:
     """Bump version across all packages in lib/.
 
     Args:
         version: New version to set (e.g., 1.0.0, 1.0.0a1).
         dry_run: Show what would be done without making changes.
         no_push: Don't push changes to remote.
-        no_commit: Don't commit changes (just update files).
     """
     try:
         # Check prerequisites
@@ -401,60 +397,51 @@ def bump(version: str, dry_run: bool, no_push: bool, no_commit: bool) -> None:
         else:
             console.print("[dim][DRY RUN][/dim] Would run: uv sync")
 
-        if no_commit:
-            console.print("\nSkipping git operations (--no-commit flag set)")
+        branch_name = f"feat/bump-version-{version}"
+        if not dry_run:
+            console.print(f"\nCreating branch {branch_name}...")
+            run_command(["git", "checkout", "-b", branch_name])
+            console.print("[green]✓[/green] Branch created")
+
+            console.print("\nCommitting changes...")
+            run_command(["git", "add", "."])
+            run_command(["git", "commit", "-m", f"feat: bump versions to {version}"])
+            console.print("[green]✓[/green] Changes committed")
+
+            if not no_push:
+                console.print("\nPushing branch...")
+                run_command(["git", "push", "-u", "origin", branch_name])
+                console.print("[green]✓[/green] Branch pushed")
         else:
-            branch_name = f"feat/bump-version-{version}"
-            if not dry_run:
-                console.print(f"\nCreating branch {branch_name}...")
-                run_command(["git", "checkout", "-b", branch_name])
-                console.print("[green]✓[/green] Branch created")
+            console.print(f"[dim][DRY RUN][/dim] Would create branch: {branch_name}")
+            console.print(
+                f"[dim][DRY RUN][/dim] Would commit: feat: bump versions to {version}"
+            )
+            if not no_push:
+                console.print(f"[dim][DRY RUN][/dim] Would push branch: {branch_name}")
 
-                console.print("\nCommitting changes...")
-                run_command(["git", "add", "."])
-                run_command(
-                    ["git", "commit", "-m", f"feat: bump versions to {version}"]
-                )
-                console.print("[green]✓[/green] Changes committed")
-
-                if not no_push:
-                    console.print("\nPushing branch...")
-                    run_command(["git", "push", "-u", "origin", branch_name])
-                    console.print("[green]✓[/green] Branch pushed")
-            else:
-                console.print(
-                    f"[dim][DRY RUN][/dim] Would create branch: {branch_name}"
-                )
-                console.print(
-                    f"[dim][DRY RUN][/dim] Would commit: feat: bump versions to {version}"
-                )
-                if not no_push:
-                    console.print(
-                        f"[dim][DRY RUN][/dim] Would push branch: {branch_name}"
-                    )
-
-            if not dry_run and not no_push:
-                console.print("\nCreating pull request...")
-                run_command(
-                    [
-                        "gh",
-                        "pr",
-                        "create",
-                        "--base",
-                        "main",
-                        "--title",
-                        f"feat: bump versions to {version}",
-                        "--body",
-                        "",
-                    ]
-                )
-                console.print("[green]✓[/green] Pull request created")
-            elif dry_run:
-                console.print(
-                    f"[dim][DRY RUN][/dim] Would create PR: feat: bump versions to {version}"
-                )
-            else:
-                console.print("\nSkipping PR creation (--no-push flag set)")
+        if not dry_run and not no_push:
+            console.print("\nCreating pull request...")
+            run_command(
+                [
+                    "gh",
+                    "pr",
+                    "create",
+                    "--base",
+                    "main",
+                    "--title",
+                    f"feat: bump versions to {version}",
+                    "--body",
+                    "",
+                ]
+            )
+            console.print("[green]✓[/green] Pull request created")
+        elif dry_run:
+            console.print(
+                f"[dim][DRY RUN][/dim] Would create PR: feat: bump versions to {version}"
+            )
+        else:
+            console.print("\nSkipping PR creation (--no-push flag set)")
 
         console.print(f"\n[green]✓[/green] Version bump to {version} complete!")