feat: bump versions to 1.10.1a1

* refactor: update step callback methods to support asynchronous invocation

- Replaced synchronous step callback invocations with asynchronous counterparts in the CrewAgentExecutor class.
- Introduced a new async method _ainvoke_step_callback to handle step callbacks in an async context, improving responsiveness and performance in asynchronous workflows.

* chore: bump version to 1.10.1b1 across multiple files

- Updated version strings from 1.10.1b to 1.10.1b1 in various project files including pyproject.toml and __init__.py files.
- Adjusted dependency specifications to reflect the new version in relevant templates and modules.

.env.test

@@ -21,7 +21,6 @@ OPENROUTER_API_KEY=fake-openrouter-key
 AWS_ACCESS_KEY_ID=fake-aws-access-key
 AWS_SECRET_ACCESS_KEY=fake-aws-secret-key
 AWS_DEFAULT_REGION=us-east-1
-AWS_REGION_NAME=us-east-1
 
 # -----------------------------------------------------------------------------
 # Azure OpenAI Configuration

.github/workflows/publish.yml

@@ -1,8 +1,6 @@
 name: Publish to PyPI
 
 on:
-  repository_dispatch:
-    types: [deployment-tests-passed]
   workflow_dispatch:
     inputs:
       release_tag:
@@ -20,11 +18,8 @@ jobs:
       - 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

.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/changelog.mdx

@@ -4,6 +4,56 @@ description: "Product updates, improvements, and bug fixes for CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="Feb 26, 2026">
+  ## v1.10.0
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.10.0)
+
+  ## What's Changed
+
+  ### Features
+  - Enhance MCP tool resolution and related events
+  - Update lancedb version and add lance-namespace packages
+  - Enhance JSON argument parsing and validation in CrewAgentExecutor and BaseTool
+  - Migrate CLI HTTP client from requests to httpx
+  - Add versioned documentation
+  - Add yanked detection for version notes
+  - Implement user input handling in Flows
+  - Enhance HITL self-loop functionality in human feedback integration tests
+  - Add started_event_id and set in eventbus
+  - Auto update tools.specs
+
+  ### Bug Fixes
+  - Validate tool kwargs even when empty to prevent cryptic TypeError
+  - Preserve null types in tool parameter schemas for LLM
+  - Map output_pydantic/output_json to native structured output
+  - Ensure callbacks are ran/awaited if promise
+  - Capture method name in exception context
+  - Preserve enum type in router result; improve types
+  - Fix cyclic flows silently breaking when persistence ID is passed in inputs
+  - Correct CLI flag format from --skip-provider to --skip_provider
+  - Ensure OpenAI tool call stream is finalized
+  - Resolve complex schema $ref pointers in MCP tools
+  - Enforce additionalProperties=false in schemas
+  - Reject reserved script names for crew folders
+  - Resolve race condition in guardrail event emission test
+
+  ### Documentation
+  - Add litellm dependency note for non-native LLM providers
+  - Clarify NL2SQL security model and hardening guidance
+  - Add 96 missing actions across 9 integrations
+
+  ### Refactoring
+  - Refactor crew to provider
+  - Extract HITL to provider pattern
+  - Improve hook typing and registration
+
+  ## Contributors
+
+  @dependabot[bot], @github-actions[bot], @github-code-quality[bot], @greysonlalonde, @heitorado, @hobostay, @joaomdmoura, @johnvan7, @jonathansampson, @lorenzejay, @lucasgomide, @mattatcha, @mplachta, @nicoferdi96, @theCyberTech, @thiagomoretto, @vinibrsl
+
+</Update>
+
 <Update label="Jan 26, 2026">
   ## v1.9.0
 

docs/en/concepts/llms.mdx

@@ -106,6 +106,15 @@ There are different places in CrewAI code where you can specify the model to use
   </Tab>
 </Tabs>
 
+<Info>
+  CrewAI provides native SDK integrations for OpenAI, Anthropic, Google (Gemini API), Azure, and AWS Bedrock — no extra install needed beyond the provider-specific extras (e.g. `uv add "crewai[openai]"`).
+
+  All other providers are powered by **LiteLLM**. If you plan to use any of them, add it as a dependency to your project:
+  ```bash
+  uv add 'crewai[litellm]'
+  ```
+</Info>
+
 ## Provider Configuration Examples
 
 CrewAI supports a multitude of LLM providers, each offering unique features, authentication methods, and model capabilities.
@@ -275,6 +284,11 @@ In this section, you'll find detailed examples that help you select, configure,
     | `meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8` | 128k | 4028 | Text, Image | Text |
     | `meta_llama/Llama-3.3-70B-Instruct` | 128k | 4028 | Text | Text |
     | `meta_llama/Llama-3.3-8B-Instruct` | 128k | 4028 | Text | Text |
+
+    **Note:** This provider uses LiteLLM. Add it as a dependency to your project:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Anthropic">
@@ -470,7 +484,7 @@ In this section, you'll find detailed examples that help you select, configure,
       To get an Express mode API key:
       - New Google Cloud users: Get an [express mode API key](https://cloud.google.com/vertex-ai/generative-ai/docs/start/quickstart?usertype=apikey)
       - Existing Google Cloud users: Get a [Google Cloud API key bound to a service account](https://cloud.google.com/docs/authentication/api-keys)
-      
+
       For more details, see the [Vertex AI Express mode documentation](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/start/quickstart?usertype=apikey).
     </Info>
 
@@ -571,6 +585,11 @@ In this section, you'll find detailed examples that help you select, configure,
     | gemini-1.5-flash               | 1M tokens      | Balanced multimodal model, good for most tasks                    |
     | gemini-1.5-flash-8B            | 1M tokens      | Fastest, most cost-efficient, good for high-frequency tasks       |
     | gemini-1.5-pro                 | 2M tokens      | Best performing, wide variety of reasoning tasks including logical reasoning, coding, and creative collaboration |
+
+    **Note:** This provider uses LiteLLM. Add it as a dependency to your project:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Azure">
@@ -652,6 +671,7 @@ In this section, you'll find detailed examples that help you select, configure,
     # Optional
     AWS_SESSION_TOKEN=<your-session-token>  # For temporary credentials
     AWS_DEFAULT_REGION=<your-region>  # Defaults to us-east-1
+    AWS_REGION_NAME=<your-region>  # Alternative configuration for backwards compatibility with LiteLLM. Defaults to us-east-1
     ```
 
     **Basic Usage:**
@@ -695,6 +715,7 @@ In this section, you'll find detailed examples that help you select, configure,
     - `AWS_SECRET_ACCESS_KEY`: AWS secret key (required)
     - `AWS_SESSION_TOKEN`: AWS session token for temporary credentials (optional)
     - `AWS_DEFAULT_REGION`: AWS region (defaults to `us-east-1`)
+    - `AWS_REGION_NAME`: AWS region (defaults to `us-east-1`). Alternative configuration for backwards compatibility with LiteLLM
 
     **Features:**
     - Native tool calling support via Converse API
@@ -764,6 +785,11 @@ In this section, you'll find detailed examples that help you select, configure,
         model="sagemaker/<my-endpoint>"
     )
     ```
+
+    **Note:** This provider uses LiteLLM. Add it as a dependency to your project:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Mistral">
@@ -779,6 +805,11 @@ In this section, you'll find detailed examples that help you select, configure,
         temperature=0.7
     )
     ```
+
+    **Note:** This provider uses LiteLLM. Add it as a dependency to your project:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Nvidia NIM">
@@ -865,6 +896,11 @@ In this section, you'll find detailed examples that help you select, configure,
     | rakuten/rakutenai-7b-instruct                                     | 1,024 tokens   | Advanced state-of-the-art LLM with language understanding, superior reasoning, and text generation. |
     | rakuten/rakutenai-7b-chat                                         | 1,024 tokens   | Advanced state-of-the-art LLM with language understanding, superior reasoning, and text generation. |
     | baichuan-inc/baichuan2-13b-chat                                  | 4,096 tokens   | Support Chinese and English chat, coding, math, instruction following, solving quizzes |
+
+    **Note:** This provider uses LiteLLM. Add it as a dependency to your project:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Local NVIDIA NIM Deployed using WSL2">
@@ -905,6 +941,11 @@ In this section, you'll find detailed examples that help you select, configure,
 
         # ...
     ```
+
+    **Note:** This provider uses LiteLLM. Add it as a dependency to your project:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Groq">
@@ -926,6 +967,11 @@ In this section, you'll find detailed examples that help you select, configure,
     | Llama 3.1 70B/8B  | 131,072 tokens   | High-performance, large context tasks      |
     | Llama 3.2 Series  | 8,192 tokens     | General-purpose tasks                      |
     | Mixtral 8x7B      | 32,768 tokens    | Balanced performance and context           |
+
+    **Note:** This provider uses LiteLLM. Add it as a dependency to your project:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="IBM watsonx.ai">
@@ -948,6 +994,11 @@ In this section, you'll find detailed examples that help you select, configure,
         base_url="https://api.watsonx.ai/v1"
     )
     ```
+
+    **Note:** This provider uses LiteLLM. Add it as a dependency to your project:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Ollama (Local LLMs)">
@@ -961,6 +1012,11 @@ In this section, you'll find detailed examples that help you select, configure,
         base_url="http://localhost:11434"
     )
     ```
+
+    **Note:** This provider uses LiteLLM. Add it as a dependency to your project:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Fireworks AI">
@@ -976,6 +1032,11 @@ In this section, you'll find detailed examples that help you select, configure,
         temperature=0.7
     )
     ```
+
+    **Note:** This provider uses LiteLLM. Add it as a dependency to your project:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Perplexity AI">
@@ -991,6 +1052,11 @@ In this section, you'll find detailed examples that help you select, configure,
         base_url="https://api.perplexity.ai/"
     )
     ```
+
+    **Note:** This provider uses LiteLLM. Add it as a dependency to your project:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Hugging Face">
@@ -1005,6 +1071,11 @@ In this section, you'll find detailed examples that help you select, configure,
         model="huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct"
     )
     ```
+
+    **Note:** This provider uses LiteLLM. Add it as a dependency to your project:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="SambaNova">
@@ -1028,6 +1099,11 @@ In this section, you'll find detailed examples that help you select, configure,
     | Llama 3.2 Series   | 8,192 tokens           | General-purpose, multimodal tasks            |
     | Llama 3.3 70B      | Up to 131,072 tokens   | High-performance and output quality          |
     | Qwen2 familly      | 8,192 tokens           | High-performance and output quality          |
+
+    **Note:** This provider uses LiteLLM. Add it as a dependency to your project:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Cerebras">
@@ -1053,6 +1129,11 @@ In this section, you'll find detailed examples that help you select, configure,
       - Good balance of speed and quality
       - Support for long context windows
     </Info>
+
+    **Note:** This provider uses LiteLLM. Add it as a dependency to your project:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Open Router">
@@ -1075,6 +1156,11 @@ In this section, you'll find detailed examples that help you select, configure,
       - openrouter/deepseek/deepseek-r1
       - openrouter/deepseek/deepseek-chat
     </Info>
+
+    **Note:** This provider uses LiteLLM. Add it as a dependency to your project:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Nebius AI Studio">
@@ -1097,6 +1183,11 @@ In this section, you'll find detailed examples that help you select, configure,
       - Competitive pricing
       - Good balance of speed and quality
     </Info>
+
+    **Note:** This provider uses LiteLLM. Add it as a dependency to your project:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 </AccordionGroup>
 

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

@@ -177,6 +177,11 @@ You need to push your crew to a GitHub repository. If you haven't created a crew
       ![Set Environment Variables](/images/enterprise/set-env-variables.png)
     </Frame>
 
+    <Info>
+      Using private Python packages? You'll need to add your registry credentials here too.
+      See [Private Package Registries](/en/enterprise/guides/private-package-registry) for the required variables.
+    </Info>
+
   </Step>
 
   <Step title="Deploy Your Crew">

docs/en/enterprise/guides/prepare-for-deployment.mdx

@@ -256,6 +256,12 @@ Before deployment, ensure you have:
 1. **LLM API keys** ready (OpenAI, Anthropic, Google, etc.)
 2. **Tool API keys** if using external tools (Serper, etc.)
 
+<Info>
+  If your project depends on packages from a **private PyPI registry**, you'll also need to configure
+  registry authentication credentials as environment variables. See the
+  [Private Package Registries](/en/enterprise/guides/private-package-registry) guide for details.
+</Info>
+
 <Tip>
   Test your project locally with the same environment variables before deploying
   to catch configuration issues early.

docs/en/enterprise/guides/private-package-registry.mdx

@@ -0,0 +1,263 @@
+---
+title: "Private Package Registries"
+description: "Install private Python packages from authenticated PyPI registries in CrewAI AMP"
+icon: "lock"
+mode: "wide"
+---
+
+<Note>
+  This guide covers how to configure your CrewAI project to install Python packages
+  from private PyPI registries (Azure DevOps Artifacts, GitHub Packages, GitLab, AWS CodeArtifact, etc.)
+  when deploying to CrewAI AMP.
+</Note>
+
+## When You Need This
+
+If your project depends on internal or proprietary Python packages hosted on a private registry
+rather than the public PyPI, you'll need to:
+
+1. Tell UV **where** to find the package (an index URL)
+2. Tell UV **which** packages come from that index (a source mapping)
+3. Provide **credentials** so UV can authenticate during install
+
+CrewAI AMP uses [UV](https://docs.astral.sh/uv/) for dependency resolution and installation.
+UV supports authenticated private registries through `pyproject.toml` configuration combined
+with environment variables for credentials.
+
+## Step 1: Configure pyproject.toml
+
+Three pieces work together in your `pyproject.toml`:
+
+### 1a. Declare the dependency
+
+Add the private package to your `[project.dependencies]` like any other dependency:
+
+```toml
+[project]
+dependencies = [
+    "crewai[tools]>=0.100.1,<1.0.0",
+    "my-private-package>=1.2.0",
+]
+```
+
+### 1b. Define the index
+
+Register your private registry as a named index under `[[tool.uv.index]]`:
+
+```toml
+[[tool.uv.index]]
+name = "my-private-registry"
+url = "https://pkgs.dev.azure.com/my-org/_packaging/my-feed/pypi/simple/"
+explicit = true
+```
+
+<Info>
+  The `name` field is important — UV uses it to construct the environment variable names
+  for authentication (see [Step 2](#step-2-set-authentication-credentials) below).
+
+  Setting `explicit = true` means UV won't search this index for every package — only the
+  ones you explicitly map to it in `[tool.uv.sources]`. This avoids unnecessary queries
+  against your private registry and protects against dependency confusion attacks.
+</Info>
+
+### 1c. Map the package to the index
+
+Tell UV which packages should be resolved from your private index using `[tool.uv.sources]`:
+
+```toml
+[tool.uv.sources]
+my-private-package = { index = "my-private-registry" }
+```
+
+### Complete example
+
+```toml
+[project]
+name = "my-crew-project"
+version = "0.1.0"
+requires-python = ">=3.10,<=3.13"
+dependencies = [
+    "crewai[tools]>=0.100.1,<1.0.0",
+    "my-private-package>=1.2.0",
+]
+
+[tool.crewai]
+type = "crew"
+
+[[tool.uv.index]]
+name = "my-private-registry"
+url = "https://pkgs.dev.azure.com/my-org/_packaging/my-feed/pypi/simple/"
+explicit = true
+
+[tool.uv.sources]
+my-private-package = { index = "my-private-registry" }
+```
+
+After updating `pyproject.toml`, regenerate your lock file:
+
+```bash
+uv lock
+```
+
+<Warning>
+  Always commit the updated `uv.lock` along with your `pyproject.toml` changes.
+  The lock file is required for deployment — see [Prepare for Deployment](/en/enterprise/guides/prepare-for-deployment).
+</Warning>
+
+## Step 2: Set Authentication Credentials
+
+UV authenticates against private indexes using environment variables that follow a naming convention
+based on the index name you defined in `pyproject.toml`:
+
+```
+UV_INDEX_{UPPER_NAME}_USERNAME
+UV_INDEX_{UPPER_NAME}_PASSWORD
+```
+
+Where `{UPPER_NAME}` is your index name converted to **uppercase** with **hyphens replaced by underscores**.
+
+For example, an index named `my-private-registry` uses:
+
+| Variable | Value |
+|----------|-------|
+| `UV_INDEX_MY_PRIVATE_REGISTRY_USERNAME` | Your registry username or token name |
+| `UV_INDEX_MY_PRIVATE_REGISTRY_PASSWORD` | Your registry password or token/PAT |
+
+<Warning>
+  These environment variables **must** be added via the CrewAI AMP **Environment Variables** settings —
+  either globally or at the deployment level. They cannot be set in `.env` files or hardcoded in your project.
+
+  See [Setting Environment Variables in AMP](#setting-environment-variables-in-amp) below.
+</Warning>
+
+## Registry Provider Reference
+
+The table below shows the index URL format and credential values for common registry providers.
+Replace placeholder values with your actual organization and feed details.
+
+| Provider | Index URL | Username | Password |
+|----------|-----------|----------|----------|
+| **Azure DevOps Artifacts** | `https://pkgs.dev.azure.com/{org}/_packaging/{feed}/pypi/simple/` | Any non-empty string (e.g. `token`) | Personal Access Token (PAT) with Packaging Read scope |
+| **GitHub Packages** | `https://pypi.pkg.github.com/{owner}/simple/` | GitHub username | Personal Access Token (classic) with `read:packages` scope |
+| **GitLab Package Registry** | `https://gitlab.com/api/v4/projects/{project_id}/packages/pypi/simple/` | `__token__` | Project or Personal Access Token with `read_api` scope |
+| **AWS CodeArtifact** | Use the URL from `aws codeartifact get-repository-endpoint` | `aws` | Token from `aws codeartifact get-authorization-token` |
+| **Google Artifact Registry** | `https://{region}-python.pkg.dev/{project}/{repo}/simple/` | `_json_key_base64` | Base64-encoded service account key |
+| **JFrog Artifactory** | `https://{instance}.jfrog.io/artifactory/api/pypi/{repo}/simple/` | Username or email | API key or identity token |
+| **Self-hosted (devpi, Nexus, etc.)** | Your registry's simple API URL | Registry username | Registry password |
+
+<Tip>
+  For **AWS CodeArtifact**, the authorization token expires periodically.
+  You'll need to refresh the `UV_INDEX_*_PASSWORD` value when it expires.
+  Consider automating this in your CI/CD pipeline.
+</Tip>
+
+## Setting Environment Variables in AMP
+
+Private registry credentials must be configured as environment variables in CrewAI AMP.
+You have two options:
+
+<Tabs>
+  <Tab title="Web Interface">
+    1. Log in to [CrewAI AMP](https://app.crewai.com)
+    2. Navigate to your automation
+    3. Open the **Environment Variables** tab
+    4. Add each variable (`UV_INDEX_*_USERNAME` and `UV_INDEX_*_PASSWORD`) with its value
+
+    See the [Deploy to AMP — Set Environment Variables](/en/enterprise/guides/deploy-to-amp#set-environment-variables) step for details.
+  </Tab>
+  <Tab title="CLI Deployment">
+    Add the variables to your local `.env` file before running `crewai deploy create`.
+    The CLI will securely transfer them to the platform:
+
+    ```bash
+    # .env
+    OPENAI_API_KEY=sk-...
+    UV_INDEX_MY_PRIVATE_REGISTRY_USERNAME=token
+    UV_INDEX_MY_PRIVATE_REGISTRY_PASSWORD=your-pat-here
+    ```
+
+    ```bash
+    crewai deploy create
+    ```
+  </Tab>
+</Tabs>
+
+<Warning>
+  **Never** commit credentials to your repository. Use AMP environment variables for all secrets.
+  The `.env` file should be listed in `.gitignore`.
+</Warning>
+
+To update credentials on an existing deployment, see [Update Your Crew — Environment Variables](/en/enterprise/guides/update-crew).
+
+## How It All Fits Together
+
+When CrewAI AMP builds your automation, the resolution flow works like this:
+
+<Steps>
+  <Step title="Build starts">
+    AMP pulls your repository and reads `pyproject.toml` and `uv.lock`.
+  </Step>
+  <Step title="UV resolves dependencies">
+    UV reads `[tool.uv.sources]` to determine which index each package should come from.
+  </Step>
+  <Step title="UV authenticates">
+    For each private index, UV looks up `UV_INDEX_{NAME}_USERNAME` and `UV_INDEX_{NAME}_PASSWORD`
+    from the environment variables you configured in AMP.
+  </Step>
+  <Step title="Packages install">
+    UV downloads and installs all packages — both public (from PyPI) and private (from your registry).
+  </Step>
+  <Step title="Automation runs">
+    Your crew or flow starts with all dependencies available.
+  </Step>
+</Steps>
+
+## Troubleshooting
+
+### Authentication Errors During Build
+
+**Symptom**: Build fails with `401 Unauthorized` or `403 Forbidden` when resolving a private package.
+
+**Check**:
+- The `UV_INDEX_*` environment variable names match your index name exactly (uppercased, hyphens → underscores)
+- Credentials are set in AMP environment variables, not just in a local `.env`
+- Your token/PAT has the required read permissions for the package feed
+- The token hasn't expired (especially relevant for AWS CodeArtifact)
+
+### Package Not Found
+
+**Symptom**: `No matching distribution found for my-private-package`.
+
+**Check**:
+- The index URL in `pyproject.toml` ends with `/simple/`
+- The `[tool.uv.sources]` entry maps the correct package name to the correct index name
+- The package is actually published to your private registry
+- Run `uv lock` locally with the same credentials to verify resolution works
+
+### Lock File Conflicts
+
+**Symptom**: `uv lock` fails or produces unexpected results after adding a private index.
+
+**Solution**: Set the credentials locally and regenerate:
+
+```bash
+export UV_INDEX_MY_PRIVATE_REGISTRY_USERNAME=token
+export UV_INDEX_MY_PRIVATE_REGISTRY_PASSWORD=your-pat
+uv lock
+```
+
+Then commit the updated `uv.lock`.
+
+## Related Guides
+
+<CardGroup cols={3}>
+  <Card title="Prepare for Deployment" icon="clipboard-check" href="/en/enterprise/guides/prepare-for-deployment">
+    Verify project structure and dependencies before deploying.
+  </Card>
+  <Card title="Deploy to AMP" icon="rocket" href="/en/enterprise/guides/deploy-to-amp">
+    Deploy your crew or flow and configure environment variables.
+  </Card>
+  <Card title="Update Your Crew" icon="arrows-rotate" href="/en/enterprise/guides/update-crew">
+    Update environment variables and push changes to a running deployment.
+  </Card>
+</CardGroup>

docs/en/learn/llm-connections.mdx

@@ -7,7 +7,7 @@ mode: "wide"
 
 ## Connect CrewAI to LLMs
 
-CrewAI uses LiteLLM to connect to a wide variety of Language Models (LLMs). This integration provides extensive versatility, allowing you to use models from numerous providers with a simple, unified interface.
+CrewAI connects to LLMs through native SDK integrations for the most popular providers (OpenAI, Anthropic, Google Gemini, Azure, and AWS Bedrock), and uses LiteLLM as a flexible fallback for all other providers.
 
 <Note>
     By default, CrewAI uses the `gpt-4o-mini` model. This is determined by the `OPENAI_MODEL_NAME` environment variable, which defaults to "gpt-4o-mini" if not set.
@@ -41,6 +41,14 @@ LiteLLM supports a wide range of providers, including but not limited to:
 
 For a complete and up-to-date list of supported providers, please refer to the [LiteLLM Providers documentation](https://docs.litellm.ai/docs/providers).
 
+<Info>
+  To use any provider not covered by a native integration, add LiteLLM as a dependency to your project:
+  ```bash
+  uv add 'crewai[litellm]'
+  ```
+  Native providers (OpenAI, Anthropic, Google Gemini, Azure, AWS Bedrock) use their own SDK extras — see the [Provider Configuration Examples](/en/concepts/llms#provider-configuration-examples).
+</Info>
+
 ## Changing the LLM
 
 To use a different LLM with your CrewAI agents, you have several options:

docs/en/observability/tracing.mdx

@@ -35,7 +35,7 @@ Visit [app.crewai.com](https://app.crewai.com) and create your free account. Thi
 If you haven't already, install CrewAI with the CLI tools:
 
 ```bash
-uv add crewai[tools]
+uv add 'crewai[tools]'
 ```
 
 Then authenticate your CLI with your CrewAI AMP account:

docs/ko/changelog.mdx

@@ -4,6 +4,56 @@ description: "CrewAI의 제품 업데이트, 개선 사항 및 버그 수정"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="2026년 2월 26일">
+  ## v1.10.0
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.10.0)
+
+  ## 변경 사항
+
+  ### 기능
+  - MCP 도구 해상도 및 관련 이벤트 개선
+  - lancedb 버전 업데이트 및 lance-namespace 패키지 추가
+  - CrewAgentExecutor 및 BaseTool에서 JSON 인수 파싱 및 검증 개선
+  - CLI HTTP 클라이언트를 requests에서 httpx로 마이그레이션
+  - 버전화된 문서 추가
+  - 버전 노트에 대한 yanked 감지 추가
+  - Flows에서 사용자 입력 처리 구현
+  - 인간 피드백 통합 테스트에서 HITL 자기 루프 기능 개선
+  - eventbus에 started_event_id 추가 및 설정
+  - tools.specs 자동 업데이트
+
+  ### 버그 수정
+  - 빈 경우에도 도구 kwargs를 검증하여 모호한 TypeError 방지
+  - LLM을 위한 도구 매개변수 스키마에서 null 타입 유지
+  - output_pydantic/output_json을 네이티브 구조화된 출력으로 매핑
+  - 약속이 있는 경우 콜백이 실행/대기되도록 보장
+  - 예외 컨텍스트에서 메서드 이름 캡처
+  - 라우터 결과에서 enum 타입 유지; 타입 개선
+  - 입력으로 지속성 ID가 전달될 때 조용히 깨지는 순환 흐름 수정
+  - CLI 플래그 형식을 --skip-provider에서 --skip_provider로 수정
+  - OpenAI 도구 호출 스트림이 완료되도록 보장
+  - MCP 도구에서 복잡한 스키마 $ref 포인터 해결
+  - 스키마에서 additionalProperties=false 강제 적용
+  - 크루 폴더에 대해 예약된 스크립트 이름 거부
+  - 가드레일 이벤트 방출 테스트에서 경쟁 조건 해결
+
+  ### 문서
+  - 비네이티브 LLM 공급자를 위한 litellm 종속성 노트 추가
+  - NL2SQL 보안 모델 및 강화 지침 명확화
+  - 9개 통합에서 96개의 누락된 작업 추가
+
+  ### 리팩토링
+  - crew를 provider로 리팩토링
+  - HITL을 provider 패턴으로 추출
+  - 훅 타이핑 및 등록 개선
+
+  ## 기여자
+
+  @dependabot[bot], @github-actions[bot], @github-code-quality[bot], @greysonlalonde, @heitorado, @hobostay, @joaomdmoura, @johnvan7, @jonathansampson, @lorenzejay, @lucasgomide, @mattatcha, @mplachta, @nicoferdi96, @theCyberTech, @thiagomoretto, @vinibrsl
+
+</Update>
+
 <Update label="2026년 1월 26일">
   ## v1.9.0
 

docs/ko/concepts/llms.mdx

@@ -105,6 +105,15 @@ CrewAI 코드 내에는 사용할 모델을 지정할 수 있는 여러 위치
   </Tab>
 </Tabs>
 
+<Info>
+  CrewAI는 OpenAI, Anthropic, Google (Gemini API), Azure, AWS Bedrock에 대해 네이티브 SDK 통합을 제공합니다 — 제공자별 extras(예: `uv add "crewai[openai]"`) 외에 추가 설치가 필요하지 않습니다.
+
+  그 외 모든 제공자는 **LiteLLM**을 통해 지원됩니다. 이를 사용하려면 프로젝트에 의존성으로 추가하세요:
+  ```bash
+  uv add 'crewai[litellm]'
+  ```
+</Info>
+
 ## 공급자 구성 예시
 
 CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양한 LLM 공급자를 지원합니다.
@@ -214,6 +223,11 @@ CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양
     | `meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8` | 128k | 4028 | 텍스트, 이미지     | 텍스트           |
     | `meta_llama/Llama-3.3-70B-Instruct`               | 128k | 4028       | 텍스트            | 텍스트           |
     | `meta_llama/Llama-3.3-8B-Instruct`                | 128k | 4028       | 텍스트            | 텍스트           |
+
+    **참고:** 이 제공자는 LiteLLM을 사용합니다. 프로젝트에 의존성으로 추가하세요:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Anthropic">
@@ -354,6 +368,11 @@ CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양
     | gemini-1.5-flash                 | 1M 토큰         | 밸런스 잡힌 멀티모달 모델, 대부분의 작업에 적합                         |
     | gemini-1.5-flash-8B              | 1M 토큰         | 가장 빠르고, 비용 효율적, 고빈도 작업에 적합                            |
     | gemini-1.5-pro                   | 2M 토큰         | 최고의 성능, 논리적 추론, 코딩, 창의적 협업 등 다양한 추론 작업에 적합   |
+
+    **참고:** 이 제공자는 LiteLLM을 사용합니다. 프로젝트에 의존성으로 추가하세요:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Azure">
@@ -439,6 +458,11 @@ CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양
         model="sagemaker/<my-endpoint>"
     )
     ```
+
+    **참고:** 이 제공자는 LiteLLM을 사용합니다. 프로젝트에 의존성으로 추가하세요:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Mistral">
@@ -454,6 +478,11 @@ CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양
         temperature=0.7
     )
     ```
+
+    **참고:** 이 제공자는 LiteLLM을 사용합니다. 프로젝트에 의존성으로 추가하세요:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Nvidia NIM">
@@ -540,6 +569,11 @@ CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양
     | rakuten/rakutenai-7b-instruct                                          | 1,024 토큰     | 언어 이해, 추론, 텍스트 생성이 탁월한 최첨단 LLM                         |
     | rakuten/rakutenai-7b-chat                                              | 1,024 토큰     | 언어 이해, 추론, 텍스트 생성이 탁월한 최첨단 LLM                         |
     | baichuan-inc/baichuan2-13b-chat                                        | 4,096 토큰     | 중국어 및 영어 대화, 코딩, 수학, 지시 따르기, 퀴즈 풀이 지원             |
+
+    **참고:** 이 제공자는 LiteLLM을 사용합니다. 프로젝트에 의존성으로 추가하세요:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Local NVIDIA NIM Deployed using WSL2">
@@ -580,6 +614,11 @@ CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양
 
         # ...
     ```
+
+    **참고:** 이 제공자는 LiteLLM을 사용합니다. 프로젝트에 의존성으로 추가하세요:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Groq">
@@ -601,6 +640,11 @@ CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양
     | Llama 3.1 70B/8B| 131,072 토큰      | 고성능, 대용량 문맥 작업         |
     | Llama 3.2 Series| 8,192 토큰        | 범용 작업                        |
     | Mixtral 8x7B    | 32,768 토큰       | 성능과 문맥의 균형               |
+
+    **참고:** 이 제공자는 LiteLLM을 사용합니다. 프로젝트에 의존성으로 추가하세요:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="IBM watsonx.ai">
@@ -623,6 +667,11 @@ CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양
         base_url="https://api.watsonx.ai/v1"
     )
     ```
+
+    **참고:** 이 제공자는 LiteLLM을 사용합니다. 프로젝트에 의존성으로 추가하세요:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Ollama (Local LLMs)">
@@ -636,6 +685,11 @@ CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양
         base_url="http://localhost:11434"
     )
     ```
+
+    **참고:** 이 제공자는 LiteLLM을 사용합니다. 프로젝트에 의존성으로 추가하세요:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Fireworks AI">
@@ -651,6 +705,11 @@ CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양
         temperature=0.7
     )
     ```
+
+    **참고:** 이 제공자는 LiteLLM을 사용합니다. 프로젝트에 의존성으로 추가하세요:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Perplexity AI">
@@ -666,6 +725,11 @@ CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양
         base_url="https://api.perplexity.ai/"
     )
     ```
+
+    **참고:** 이 제공자는 LiteLLM을 사용합니다. 프로젝트에 의존성으로 추가하세요:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Hugging Face">
@@ -680,6 +744,11 @@ CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양
         model="huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct"
     )
     ```
+
+    **참고:** 이 제공자는 LiteLLM을 사용합니다. 프로젝트에 의존성으로 추가하세요:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="SambaNova">
@@ -703,6 +772,11 @@ CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양
     | Llama 3.2 Series| 8,192 토큰         | 범용, 멀티모달 작업                  |
     | Llama 3.3 70B   | 최대 131,072 토큰   | 고성능, 높은 출력 품질               |
     | Qwen2 familly   | 8,192 토큰         | 고성능, 높은 출력 품질               |
+
+    **참고:** 이 제공자는 LiteLLM을 사용합니다. 프로젝트에 의존성으로 추가하세요:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Cerebras">
@@ -728,6 +802,11 @@ CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양
       - 속도와 품질의 우수한 밸런스
       - 긴 컨텍스트 윈도우 지원
     </Info>
+
+    **참고:** 이 제공자는 LiteLLM을 사용합니다. 프로젝트에 의존성으로 추가하세요:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Open Router">
@@ -750,6 +829,11 @@ CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양
       - openrouter/deepseek/deepseek-r1
       - openrouter/deepseek/deepseek-chat
     </Info>
+
+    **참고:** 이 제공자는 LiteLLM을 사용합니다. 프로젝트에 의존성으로 추가하세요:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Nebius AI Studio">
@@ -772,6 +856,11 @@ CrewAI는 고유한 기능, 인증 방법, 모델 역량을 제공하는 다양
       - 경쟁력 있는 가격
       - 속도와 품질의 우수한 밸런스
     </Info>
+
+    **참고:** 이 제공자는 LiteLLM을 사용합니다. 프로젝트에 의존성으로 추가하세요:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 </AccordionGroup>
 

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

@@ -176,6 +176,11 @@ Crew를 GitHub 저장소에 푸시해야 합니다. 아직 Crew를 만들지 않
       ![Set Environment Variables](/images/enterprise/set-env-variables.png)
     </Frame>
 
+    <Info>
+      프라이빗 Python 패키지를 사용하시나요? 여기에 레지스트리 자격 증명도 추가해야 합니다.
+      필요한 변수는 [프라이빗 패키지 레지스트리](/ko/enterprise/guides/private-package-registry)를 참조하세요.
+    </Info>
+
   </Step>
 
   <Step title="Crew 배포하기">

docs/ko/enterprise/guides/prepare-for-deployment.mdx

@@ -256,6 +256,12 @@ Crews와 Flows 모두 `src/project_name/main.py`에 진입점이 있습니다:
 1. **LLM API 키** (OpenAI, Anthropic, Google 등)
 2. **도구 API 키** - 외부 도구를 사용하는 경우 (Serper 등)
 
+<Info>
+  프로젝트가 **프라이빗 PyPI 레지스트리**의 패키지에 의존하는 경우, 레지스트리 인증 자격 증명도
+  환경 변수로 구성해야 합니다. 자세한 내용은
+  [프라이빗 패키지 레지스트리](/ko/enterprise/guides/private-package-registry) 가이드를 참조하세요.
+</Info>
+
 <Tip>
   구성 문제를 조기에 발견하기 위해 배포 전에 동일한 환경 변수로
   로컬에서 프로젝트를 테스트하세요.

docs/ko/enterprise/guides/private-package-registry.mdx

@@ -0,0 +1,261 @@
+---
+title: "프라이빗 패키지 레지스트리"
+description: "CrewAI AMP에서 인증된 PyPI 레지스트리의 프라이빗 Python 패키지 설치하기"
+icon: "lock"
+mode: "wide"
+---
+
+<Note>
+  이 가이드는 CrewAI AMP에 배포할 때 프라이빗 PyPI 레지스트리(Azure DevOps Artifacts, GitHub Packages,
+  GitLab, AWS CodeArtifact 등)에서 Python 패키지를 설치하도록 CrewAI 프로젝트를 구성하는 방법을 다룹니다.
+</Note>
+
+## 이 가이드가 필요한 경우
+
+프로젝트가 공개 PyPI가 아닌 프라이빗 레지스트리에 호스팅된 내부 또는 독점 Python 패키지에
+의존하는 경우, 다음을 수행해야 합니다:
+
+1. UV에 패키지를 **어디서** 찾을지 알려줍니다 (index URL)
+2. UV에 **어떤** 패키지가 해당 index에서 오는지 알려줍니다 (source 매핑)
+3. UV가 설치 중에 인증할 수 있도록 **자격 증명**을 제공합니다
+
+CrewAI AMP는 의존성 해결 및 설치에 [UV](https://docs.astral.sh/uv/)를 사용합니다.
+UV는 `pyproject.toml` 구성과 자격 증명용 환경 변수를 결합하여 인증된 프라이빗 레지스트리를 지원합니다.
+
+## 1단계: pyproject.toml 구성
+
+`pyproject.toml`에서 세 가지 요소가 함께 작동합니다:
+
+### 1a. 의존성 선언
+
+프라이빗 패키지를 다른 의존성과 마찬가지로 `[project.dependencies]`에 추가합니다:
+
+```toml
+[project]
+dependencies = [
+    "crewai[tools]>=0.100.1,<1.0.0",
+    "my-private-package>=1.2.0",
+]
+```
+
+### 1b. index 정의
+
+프라이빗 레지스트리를 `[[tool.uv.index]]` 아래에 명명된 index로 등록합니다:
+
+```toml
+[[tool.uv.index]]
+name = "my-private-registry"
+url = "https://pkgs.dev.azure.com/my-org/_packaging/my-feed/pypi/simple/"
+explicit = true
+```
+
+<Info>
+  `name` 필드는 중요합니다 — UV는 이를 사용하여 인증을 위한 환경 변수 이름을
+  구성합니다 (아래 [2단계](#2단계-인증-자격-증명-설정)를 참조하세요).
+
+  `explicit = true`를 설정하면 UV가 모든 패키지에 대해 이 index를 검색하지 않습니다 —
+  `[tool.uv.sources]`에서 명시적으로 매핑한 패키지만 검색합니다. 이렇게 하면 프라이빗
+  레지스트리에 대한 불필요한 쿼리를 방지하고 의존성 혼동 공격을 차단할 수 있습니다.
+</Info>
+
+### 1c. 패키지를 index에 매핑
+
+`[tool.uv.sources]`를 사용하여 프라이빗 index에서 해결해야 할 패키지를 UV에 알려줍니다:
+
+```toml
+[tool.uv.sources]
+my-private-package = { index = "my-private-registry" }
+```
+
+### 전체 예시
+
+```toml
+[project]
+name = "my-crew-project"
+version = "0.1.0"
+requires-python = ">=3.10,<=3.13"
+dependencies = [
+    "crewai[tools]>=0.100.1,<1.0.0",
+    "my-private-package>=1.2.0",
+]
+
+[tool.crewai]
+type = "crew"
+
+[[tool.uv.index]]
+name = "my-private-registry"
+url = "https://pkgs.dev.azure.com/my-org/_packaging/my-feed/pypi/simple/"
+explicit = true
+
+[tool.uv.sources]
+my-private-package = { index = "my-private-registry" }
+```
+
+`pyproject.toml`을 업데이트한 후 lock 파일을 다시 생성합니다:
+
+```bash
+uv lock
+```
+
+<Warning>
+  업데이트된 `uv.lock`을 항상 `pyproject.toml` 변경 사항과 함께 커밋하세요.
+  lock 파일은 배포에 필수입니다 — [배포 준비하기](/ko/enterprise/guides/prepare-for-deployment)를 참조하세요.
+</Warning>
+
+## 2단계: 인증 자격 증명 설정
+
+UV는 `pyproject.toml`에서 정의한 index 이름을 기반으로 한 명명 규칙을 따르는
+환경 변수를 사용하여 프라이빗 index에 인증합니다:
+
+```
+UV_INDEX_{UPPER_NAME}_USERNAME
+UV_INDEX_{UPPER_NAME}_PASSWORD
+```
+
+여기서 `{UPPER_NAME}`은 index 이름을 **대문자**로 변환하고 **하이픈을 언더스코어로 대체**한 것입니다.
+
+예를 들어, `my-private-registry`라는 이름의 index는 다음을 사용합니다:
+
+| 변수 | 값 |
+|------|-----|
+| `UV_INDEX_MY_PRIVATE_REGISTRY_USERNAME` | 레지스트리 사용자 이름 또는 토큰 이름 |
+| `UV_INDEX_MY_PRIVATE_REGISTRY_PASSWORD` | 레지스트리 비밀번호 또는 토큰/PAT |
+
+<Warning>
+  이 환경 변수는 CrewAI AMP **환경 변수** 설정을 통해 **반드시** 추가해야 합니다 —
+  전역적으로 또는 배포 수준에서. `.env` 파일에 설정하거나 프로젝트에 하드코딩할 수 없습니다.
+
+  아래 [AMP에서 환경 변수 설정](#amp에서-환경-변수-설정)을 참조하세요.
+</Warning>
+
+## 레지스트리 제공업체 참조
+
+아래 표는 일반적인 레지스트리 제공업체의 index URL 형식과 자격 증명 값을 보여줍니다.
+자리 표시자 값을 실제 조직 및 피드 세부 정보로 대체하세요.
+
+| 제공업체 | Index URL | 사용자 이름 | 비밀번호 |
+|---------|-----------|-----------|---------|
+| **Azure DevOps Artifacts** | `https://pkgs.dev.azure.com/{org}/_packaging/{feed}/pypi/simple/` | 비어 있지 않은 임의의 문자열 (예: `token`) | Packaging Read 범위의 Personal Access Token (PAT) |
+| **GitHub Packages** | `https://pypi.pkg.github.com/{owner}/simple/` | GitHub 사용자 이름 | `read:packages` 범위의 Personal Access Token (classic) |
+| **GitLab Package Registry** | `https://gitlab.com/api/v4/projects/{project_id}/packages/pypi/simple/` | `__token__` | `read_api` 범위의 Project 또는 Personal Access Token |
+| **AWS CodeArtifact** | `aws codeartifact get-repository-endpoint`의 URL 사용 | `aws` | `aws codeartifact get-authorization-token`의 토큰 |
+| **Google Artifact Registry** | `https://{region}-python.pkg.dev/{project}/{repo}/simple/` | `_json_key_base64` | Base64로 인코딩된 서비스 계정 키 |
+| **JFrog Artifactory** | `https://{instance}.jfrog.io/artifactory/api/pypi/{repo}/simple/` | 사용자 이름 또는 이메일 | API 키 또는 ID 토큰 |
+| **자체 호스팅 (devpi, Nexus 등)** | 레지스트리의 simple API URL | 레지스트리 사용자 이름 | 레지스트리 비밀번호 |
+
+<Tip>
+  **AWS CodeArtifact**의 경우 인증 토큰이 주기적으로 만료됩니다.
+  만료되면 `UV_INDEX_*_PASSWORD` 값을 갱신해야 합니다.
+  CI/CD 파이프라인에서 이를 자동화하는 것을 고려하세요.
+</Tip>
+
+## AMP에서 환경 변수 설정
+
+프라이빗 레지스트리 자격 증명은 CrewAI AMP에서 환경 변수로 구성해야 합니다.
+두 가지 옵션이 있습니다:
+
+<Tabs>
+  <Tab title="웹 인터페이스">
+    1. [CrewAI AMP](https://app.crewai.com)에 로그인합니다
+    2. 자동화로 이동합니다
+    3. **Environment Variables** 탭을 엽니다
+    4. 각 변수 (`UV_INDEX_*_USERNAME` 및 `UV_INDEX_*_PASSWORD`)에 값을 추가합니다
+
+    자세한 내용은 [AMP에 배포하기 — 환경 변수 설정하기](/ko/enterprise/guides/deploy-to-amp#환경-변수-설정하기) 단계를 참조하세요.
+  </Tab>
+  <Tab title="CLI 배포">
+    `crewai deploy create`를 실행하기 전에 로컬 `.env` 파일에 변수를 추가합니다.
+    CLI가 이를 안전하게 플랫폼으로 전송합니다:
+
+    ```bash
+    # .env
+    OPENAI_API_KEY=sk-...
+    UV_INDEX_MY_PRIVATE_REGISTRY_USERNAME=token
+    UV_INDEX_MY_PRIVATE_REGISTRY_PASSWORD=your-pat-here
+    ```
+
+    ```bash
+    crewai deploy create
+    ```
+  </Tab>
+</Tabs>
+
+<Warning>
+  자격 증명을 저장소에 **절대** 커밋하지 마세요. 모든 비밀 정보에는 AMP 환경 변수를 사용하세요.
+  `.env` 파일은 `.gitignore`에 포함되어야 합니다.
+</Warning>
+
+기존 배포의 자격 증명을 업데이트하려면 [Crew 업데이트하기 — 환경 변수](/ko/enterprise/guides/update-crew)를 참조하세요.
+
+## 전체 동작 흐름
+
+CrewAI AMP가 자동화를 빌드할 때, 해결 흐름은 다음과 같이 작동합니다:
+
+<Steps>
+  <Step title="빌드 시작">
+    AMP가 저장소를 가져오고 `pyproject.toml`과 `uv.lock`을 읽습니다.
+  </Step>
+  <Step title="UV가 의존성 해결">
+    UV가 `[tool.uv.sources]`를 읽어 각 패키지가 어떤 index에서 와야 하는지 결정합니다.
+  </Step>
+  <Step title="UV가 인증">
+    각 프라이빗 index에 대해 UV가 AMP에서 구성한 환경 변수에서
+    `UV_INDEX_{NAME}_USERNAME`과 `UV_INDEX_{NAME}_PASSWORD`를 조회합니다.
+  </Step>
+  <Step title="패키지 설치">
+    UV가 공개(PyPI) 및 프라이빗(레지스트리) 패키지를 모두 다운로드하고 설치합니다.
+  </Step>
+  <Step title="자동화 실행">
+    모든 의존성이 사용 가능한 상태에서 crew 또는 flow가 시작됩니다.
+  </Step>
+</Steps>
+
+## 문제 해결
+
+### 빌드 중 인증 오류
+
+**증상**: 프라이빗 패키지를 해결할 때 `401 Unauthorized` 또는 `403 Forbidden`으로 빌드가 실패합니다.
+
+**확인사항**:
+- `UV_INDEX_*` 환경 변수 이름이 index 이름과 정확히 일치하는지 확인합니다 (대문자, 하이픈 -> 언더스코어)
+- 자격 증명이 로컬 `.env`뿐만 아니라 AMP 환경 변수에 설정되어 있는지 확인합니다
+- 토큰/PAT에 패키지 피드에 필요한 읽기 권한이 있는지 확인합니다
+- 토큰이 만료되지 않았는지 확인합니다 (특히 AWS CodeArtifact의 경우)
+
+### 패키지를 찾을 수 없음
+
+**증상**: `No matching distribution found for my-private-package`.
+
+**확인사항**:
+- `pyproject.toml`의 index URL이 `/simple/`로 끝나는지 확인합니다
+- `[tool.uv.sources]` 항목이 올바른 패키지 이름을 올바른 index 이름에 매핑하는지 확인합니다
+- 패키지가 실제로 프라이빗 레지스트리에 게시되어 있는지 확인합니다
+- 동일한 자격 증명으로 로컬에서 `uv lock`을 실행하여 해결이 작동하는지 확인합니다
+
+### Lock 파일 충돌
+
+**증상**: 프라이빗 index를 추가한 후 `uv lock`이 실패하거나 예상치 못한 결과를 생성합니다.
+
+**해결책**: 로컬에서 자격 증명을 설정하고 다시 생성합니다:
+
+```bash
+export UV_INDEX_MY_PRIVATE_REGISTRY_USERNAME=token
+export UV_INDEX_MY_PRIVATE_REGISTRY_PASSWORD=your-pat
+uv lock
+```
+
+그런 다음 업데이트된 `uv.lock`을 커밋합니다.
+
+## 관련 가이드
+
+<CardGroup cols={3}>
+  <Card title="배포 준비하기" icon="clipboard-check" href="/ko/enterprise/guides/prepare-for-deployment">
+    배포 전에 프로젝트 구조와 의존성을 확인합니다.
+  </Card>
+  <Card title="AMP에 배포하기" icon="rocket" href="/ko/enterprise/guides/deploy-to-amp">
+    crew 또는 flow를 배포하고 환경 변수를 구성합니다.
+  </Card>
+  <Card title="Crew 업데이트하기" icon="arrows-rotate" href="/ko/enterprise/guides/update-crew">
+    환경 변수를 업데이트하고 실행 중인 배포에 변경 사항을 푸시합니다.
+  </Card>
+</CardGroup>

docs/ko/learn/llm-connections.mdx

@@ -7,7 +7,7 @@ mode: "wide"
 
 ## CrewAI를 LLM에 연결하기
 
-CrewAI는 LiteLLM을 사용하여 다양한 언어 모델(LLM)에 연결합니다. 이 통합은 높은 다양성을 제공하여, 여러 공급자의 모델을 간단하고 통합된 인터페이스로 사용할 수 있게 해줍니다.
+CrewAI는 가장 인기 있는 제공자(OpenAI, Anthropic, Google Gemini, Azure, AWS Bedrock)에 대해 네이티브 SDK 통합을 통해 LLM에 연결하며, 그 외 모든 제공자에 대해서는 LiteLLM을 유연한 폴백으로 사용합니다.
 
 <Note>
     기본적으로 CrewAI는 `gpt-4o-mini` 모델을 사용합니다. 이는 `OPENAI_MODEL_NAME` 환경 변수에 의해 결정되며, 설정되지 않은 경우 기본값은 "gpt-4o-mini"입니다.
@@ -41,6 +41,14 @@ LiteLLM은 다음을 포함하되 이에 국한되지 않는 다양한 프로바
 
 지원되는 프로바이더의 전체 및 최신 목록은 [LiteLLM 프로바이더 문서](https://docs.litellm.ai/docs/providers)를 참조하세요.
 
+<Info>
+  네이티브 통합에서 지원하지 않는 제공자를 사용하려면 LiteLLM을 프로젝트에 의존성으로 추가하세요:
+  ```bash
+  uv add 'crewai[litellm]'
+  ```
+  네이티브 제공자(OpenAI, Anthropic, Google Gemini, Azure, AWS Bedrock)는 자체 SDK extras를 사용합니다 — [공급자 구성 예시](/ko/concepts/llms#공급자-구성-예시)를 참조하세요.
+</Info>
+
 ## LLM 변경하기
 
 CrewAI agent에서 다른 LLM을 사용하려면 여러 가지 방법이 있습니다:

docs/ko/observability/tracing.mdx

@@ -35,7 +35,7 @@ crewai login
 아직 설치하지 않았다면 CLI 도구와 함께 CrewAI를 설치하세요:
 
 ```bash
-uv add crewai[tools]
+uv add 'crewai[tools]'
 ```
 
 그런 다음 CrewAI AMP 계정으로 CLI를 인증하세요:

docs/pt-BR/changelog.mdx

@@ -4,6 +4,56 @@ description: "Atualizações de produto, melhorias e correções do CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="26 fev 2026">
+  ## v1.10.0
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.10.0)
+
+  ## O que Mudou
+
+  ### Recursos
+  - Aprimorar a resolução da ferramenta MCP e eventos relacionados
+  - Atualizar a versão do lancedb e adicionar pacotes lance-namespace
+  - Aprimorar a análise e validação de argumentos JSON no CrewAgentExecutor e BaseTool
+  - Migrar o cliente HTTP da CLI de requests para httpx
+  - Adicionar documentação versionada
+  - Adicionar detecção de versões removidas para notas de versão
+  - Implementar tratamento de entrada do usuário em Flows
+  - Aprimorar a funcionalidade de auto-loop HITL nos testes de integração de feedback humano
+  - Adicionar started_event_id e definir no eventbus
+  - Atualizar automaticamente tools.specs
+
+  ### Correções de Bugs
+  - Validar kwargs da ferramenta mesmo quando vazios para evitar TypeError crípticos
+  - Preservar tipos nulos nos esquemas de parâmetros da ferramenta para LLM
+  - Mapear output_pydantic/output_json para saída estruturada nativa
+  - Garantir que callbacks sejam executados/aguardados se forem promessas
+  - Capturar o nome do método no contexto da exceção
+  - Preservar tipo enum no resultado do roteador; melhorar tipos
+  - Corrigir fluxos cíclicos que quebram silenciosamente quando o ID de persistência é passado nas entradas
+  - Corrigir o formato da flag da CLI de --skip-provider para --skip_provider
+  - Garantir que o fluxo de chamada da ferramenta OpenAI seja finalizado
+  - Resolver ponteiros $ref de esquema complexos nas ferramentas MCP
+  - Impor additionalProperties=false nos esquemas
+  - Rejeitar nomes de scripts reservados para pastas de equipe
+  - Resolver condição de corrida no teste de emissão de eventos de guardrail
+
+  ### Documentação
+  - Adicionar nota de dependência litellm para provedores de LLM não nativos
+  - Esclarecer o modelo de segurança NL2SQL e orientações de fortalecimento
+  - Adicionar 96 ações ausentes em 9 integrações
+
+  ### Refatoração
+  - Refatorar crew para provider
+  - Extrair HITL para padrão de provider
+  - Melhorar tipagem e registro de hooks
+
+  ## Contribuidores
+
+  @dependabot[bot], @github-actions[bot], @github-code-quality[bot], @greysonlalonde, @heitorado, @hobostay, @joaomdmoura, @johnvan7, @jonathansampson, @lorenzejay, @lucasgomide, @mattatcha, @mplachta, @nicoferdi96, @theCyberTech, @thiagomoretto, @vinibrsl
+
+</Update>
+
 <Update label="26 jan 2026">
   ## v1.9.0
 

docs/pt-BR/concepts/llms.mdx

@@ -105,6 +105,15 @@ Existem diferentes locais no código do CrewAI onde você pode especificar o mod
   </Tab>
 </Tabs>
 
+<Info>
+  O CrewAI oferece integrações nativas via SDK para OpenAI, Anthropic, Google (Gemini API), Azure e AWS Bedrock — sem necessidade de instalação extra além dos extras específicos do provedor (ex.: `uv add "crewai[openai]"`).
+
+  Todos os outros provedores são alimentados pelo **LiteLLM**. Se você planeja usar algum deles, adicione-o como dependência ao seu projeto:
+  ```bash
+  uv add 'crewai[litellm]'
+  ```
+</Info>
+
 ## Exemplos de Configuração de Provedores
 
 O CrewAI suporta uma grande variedade de provedores de LLM, cada um com recursos, métodos de autenticação e capacidades de modelo únicos.
@@ -214,6 +223,11 @@ Nesta seção, você encontrará exemplos detalhados que ajudam a selecionar, co
     | `meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8` | 128k | 4028 | Texto, Imagem | Texto |
     | `meta_llama/Llama-3.3-70B-Instruct` | 128k | 4028 | Texto | Texto |
     | `meta_llama/Llama-3.3-8B-Instruct` | 128k | 4028 | Texto | Texto |
+
+    **Nota:** Este provedor usa o LiteLLM. Adicione-o como dependência ao seu projeto:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Anthropic">
@@ -354,6 +368,11 @@ Nesta seção, você encontrará exemplos detalhados que ajudam a selecionar, co
     | gemini-1.5-flash                 | 1M tokens          | Modelo multimodal equilibrado, bom para maioria das tarefas         |
     | gemini-1.5-flash-8B              | 1M tokens          | Mais rápido, mais eficiente em custo, adequado para tarefas de alta frequência |
     | gemini-1.5-pro                   | 2M tokens          | Melhor desempenho para uma ampla variedade de tarefas de raciocínio, incluindo lógica, codificação e colaboração criativa |
+
+    **Nota:** Este provedor usa o LiteLLM. Adicione-o como dependência ao seu projeto:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Azure">
@@ -438,6 +457,11 @@ Nesta seção, você encontrará exemplos detalhados que ajudam a selecionar, co
         model="sagemaker/<my-endpoint>"
     )
     ```
+
+    **Nota:** Este provedor usa o LiteLLM. Adicione-o como dependência ao seu projeto:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Mistral">
@@ -453,6 +477,11 @@ Nesta seção, você encontrará exemplos detalhados que ajudam a selecionar, co
         temperature=0.7
     )
     ```
+
+    **Nota:** Este provedor usa o LiteLLM. Adicione-o como dependência ao seu projeto:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Nvidia NIM">
@@ -539,6 +568,11 @@ Nesta seção, você encontrará exemplos detalhados que ajudam a selecionar, co
     | rakuten/rakutenai-7b-instruct                                            | 1.024 tokens       | LLM topo de linha, compreensão, raciocínio e geração textual.|
     | rakuten/rakutenai-7b-chat                                                | 1.024 tokens       | LLM topo de linha, compreensão, raciocínio e geração textual.|
     | baichuan-inc/baichuan2-13b-chat                                          | 4.096 tokens       | Suporte a chat em chinês/inglês, programação, matemática, seguir instruções, resolver quizzes.|
+
+    **Nota:** Este provedor usa o LiteLLM. Adicione-o como dependência ao seu projeto:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Local NVIDIA NIM Deployed using WSL2">
@@ -579,6 +613,11 @@ Nesta seção, você encontrará exemplos detalhados que ajudam a selecionar, co
 
         # ...
     ```
+
+    **Nota:** Este provedor usa o LiteLLM. Adicione-o como dependência ao seu projeto:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Groq">
@@ -600,6 +639,11 @@ Nesta seção, você encontrará exemplos detalhados que ajudam a selecionar, co
     | Llama 3.1 70B/8B  | 131.072 tokens      | Alta performance e tarefas de contexto grande|
     | Llama 3.2 Série   | 8.192 tokens        | Tarefas gerais                          |
     | Mixtral 8x7B      | 32.768 tokens       | Equilíbrio entre performance e contexto  |
+
+    **Nota:** Este provedor usa o LiteLLM. Adicione-o como dependência ao seu projeto:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="IBM watsonx.ai">
@@ -622,6 +666,11 @@ Nesta seção, você encontrará exemplos detalhados que ajudam a selecionar, co
         base_url="https://api.watsonx.ai/v1"
     )
     ```
+
+    **Nota:** Este provedor usa o LiteLLM. Adicione-o como dependência ao seu projeto:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Ollama (LLMs Locais)">
@@ -635,6 +684,11 @@ Nesta seção, você encontrará exemplos detalhados que ajudam a selecionar, co
         base_url="http://localhost:11434"
     )
     ```
+
+    **Nota:** Este provedor usa o LiteLLM. Adicione-o como dependência ao seu projeto:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Fireworks AI">
@@ -650,6 +704,11 @@ Nesta seção, você encontrará exemplos detalhados que ajudam a selecionar, co
         temperature=0.7
     )
     ```
+
+    **Nota:** Este provedor usa o LiteLLM. Adicione-o como dependência ao seu projeto:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Perplexity AI">
@@ -665,6 +724,11 @@ Nesta seção, você encontrará exemplos detalhados que ajudam a selecionar, co
         base_url="https://api.perplexity.ai/"
     )
     ```
+
+    **Nota:** Este provedor usa o LiteLLM. Adicione-o como dependência ao seu projeto:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Hugging Face">
@@ -679,6 +743,11 @@ Nesta seção, você encontrará exemplos detalhados que ajudam a selecionar, co
         model="huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct"
     )
     ```
+
+    **Nota:** Este provedor usa o LiteLLM. Adicione-o como dependência ao seu projeto:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="SambaNova">
@@ -702,6 +771,11 @@ Nesta seção, você encontrará exemplos detalhados que ajudam a selecionar, co
     | Llama 3.2 Série   | 8.192 tokens              | Tarefas gerais e multimodais                 |
     | Llama 3.3 70B     | Até 131.072 tokens        | Desempenho e qualidade de saída elevada      |
     | Família Qwen2     | 8.192 tokens              | Desempenho e qualidade de saída elevada      |
+
+    **Nota:** Este provedor usa o LiteLLM. Adicione-o como dependência ao seu projeto:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Cerebras">
@@ -727,6 +801,11 @@ Nesta seção, você encontrará exemplos detalhados que ajudam a selecionar, co
       - Equilíbrio entre velocidade e qualidade
       - Suporte a longas janelas de contexto
     </Info>
+
+    **Nota:** Este provedor usa o LiteLLM. Adicione-o como dependência ao seu projeto:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 
   <Accordion title="Open Router">
@@ -749,6 +828,11 @@ Nesta seção, você encontrará exemplos detalhados que ajudam a selecionar, co
       - openrouter/deepseek/deepseek-r1
       - openrouter/deepseek/deepseek-chat
     </Info>
+
+    **Nota:** Este provedor usa o LiteLLM. Adicione-o como dependência ao seu projeto:
+    ```bash
+    uv add 'crewai[litellm]'
+    ```
   </Accordion>
 </AccordionGroup>
 

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

@@ -176,6 +176,11 @@ Você precisa enviar seu crew para um repositório do GitHub. Caso ainda não te
       ![Definir Variáveis de Ambiente](/images/enterprise/set-env-variables.png)
     </Frame>
 
+    <Info>
+      Usando pacotes Python privados? Você também precisará adicionar suas credenciais de registro aqui.
+      Consulte [Registros de Pacotes Privados](/pt-BR/enterprise/guides/private-package-registry) para as variáveis necessárias.
+    </Info>
+
   </Step>
 
   <Step title="Implante Seu Crew">

docs/pt-BR/enterprise/guides/prepare-for-deployment.mdx

@@ -256,6 +256,12 @@ Antes da implantação, certifique-se de ter:
 1. **Chaves de API de LLM** prontas (OpenAI, Anthropic, Google, etc.)
 2. **Chaves de API de ferramentas** se estiver usando ferramentas externas (Serper, etc.)
 
+<Info>
+  Se seu projeto depende de pacotes de um **registro PyPI privado**, você também precisará configurar
+  credenciais de autenticação do registro como variáveis de ambiente. Consulte o guia
+  [Registros de Pacotes Privados](/pt-BR/enterprise/guides/private-package-registry) para mais detalhes.
+</Info>
+
 <Tip>
   Teste seu projeto localmente com as mesmas variáveis de ambiente antes de implantar
   para detectar problemas de configuração antecipadamente.

docs/pt-BR/enterprise/guides/private-package-registry.mdx

@@ -0,0 +1,263 @@
+---
+title: "Registros de Pacotes Privados"
+description: "Instale pacotes Python privados de registros PyPI autenticados no CrewAI AMP"
+icon: "lock"
+mode: "wide"
+---
+
+<Note>
+  Este guia aborda como configurar seu projeto CrewAI para instalar pacotes Python
+  de registros PyPI privados (Azure DevOps Artifacts, GitHub Packages, GitLab, AWS CodeArtifact, etc.)
+  ao implantar no CrewAI AMP.
+</Note>
+
+## Quando Você Precisa Disso
+
+Se seu projeto depende de pacotes Python internos ou proprietários hospedados em um registro privado
+em vez do PyPI público, você precisará:
+
+1. Informar ao UV **onde** encontrar o pacote (uma URL de index)
+2. Informar ao UV **quais** pacotes vêm desse index (um mapeamento de source)
+3. Fornecer **credenciais** para que o UV possa autenticar durante a instalação
+
+O CrewAI AMP usa [UV](https://docs.astral.sh/uv/) para resolução e instalação de dependências.
+O UV suporta registros privados autenticados por meio da configuração do `pyproject.toml` combinada
+com variáveis de ambiente para credenciais.
+
+## Passo 1: Configurar o pyproject.toml
+
+Três elementos trabalham juntos no seu `pyproject.toml`:
+
+### 1a. Declarar a dependência
+
+Adicione o pacote privado ao seu `[project.dependencies]` como qualquer outra dependência:
+
+```toml
+[project]
+dependencies = [
+    "crewai[tools]>=0.100.1,<1.0.0",
+    "my-private-package>=1.2.0",
+]
+```
+
+### 1b. Definir o index
+
+Registre seu registro privado como um index nomeado em `[[tool.uv.index]]`:
+
+```toml
+[[tool.uv.index]]
+name = "my-private-registry"
+url = "https://pkgs.dev.azure.com/my-org/_packaging/my-feed/pypi/simple/"
+explicit = true
+```
+
+<Info>
+  O campo `name` é importante — o UV o utiliza para construir os nomes das variáveis de ambiente
+  para autenticação (veja o [Passo 2](#passo-2-configurar-credenciais-de-autenticação) abaixo).
+
+  Definir `explicit = true` significa que o UV não consultará esse index para todos os pacotes — apenas
+  os que você mapear explicitamente em `[tool.uv.sources]`. Isso evita consultas desnecessárias
+  ao seu registro privado e protege contra ataques de confusão de dependências.
+</Info>
+
+### 1c. Mapear o pacote para o index
+
+Informe ao UV quais pacotes devem ser resolvidos a partir do seu index privado usando `[tool.uv.sources]`:
+
+```toml
+[tool.uv.sources]
+my-private-package = { index = "my-private-registry" }
+```
+
+### Exemplo completo
+
+```toml
+[project]
+name = "my-crew-project"
+version = "0.1.0"
+requires-python = ">=3.10,<=3.13"
+dependencies = [
+    "crewai[tools]>=0.100.1,<1.0.0",
+    "my-private-package>=1.2.0",
+]
+
+[tool.crewai]
+type = "crew"
+
+[[tool.uv.index]]
+name = "my-private-registry"
+url = "https://pkgs.dev.azure.com/my-org/_packaging/my-feed/pypi/simple/"
+explicit = true
+
+[tool.uv.sources]
+my-private-package = { index = "my-private-registry" }
+```
+
+Após atualizar o `pyproject.toml`, regenere seu arquivo lock:
+
+```bash
+uv lock
+```
+
+<Warning>
+  Sempre faça commit do `uv.lock` atualizado junto com as alterações no `pyproject.toml`.
+  O arquivo lock é obrigatório para implantação — veja [Preparar para Implantação](/pt-BR/enterprise/guides/prepare-for-deployment).
+</Warning>
+
+## Passo 2: Configurar Credenciais de Autenticação
+
+O UV autentica em indexes privados usando variáveis de ambiente que seguem uma convenção de nomenclatura
+baseada no nome do index que você definiu no `pyproject.toml`:
+
+```
+UV_INDEX_{UPPER_NAME}_USERNAME
+UV_INDEX_{UPPER_NAME}_PASSWORD
+```
+
+Onde `{UPPER_NAME}` é o nome do seu index convertido para **maiúsculas** com **hifens substituídos por underscores**.
+
+Por exemplo, um index chamado `my-private-registry` usa:
+
+| Variável | Valor |
+|----------|-------|
+| `UV_INDEX_MY_PRIVATE_REGISTRY_USERNAME` | Seu nome de usuário ou nome do token do registro |
+| `UV_INDEX_MY_PRIVATE_REGISTRY_PASSWORD` | Sua senha ou token/PAT do registro |
+
+<Warning>
+  Essas variáveis de ambiente **devem** ser adicionadas pelas configurações de **Variáveis de Ambiente** do CrewAI AMP —
+  globalmente ou no nível da implantação. Elas não podem ser definidas em arquivos `.env` ou codificadas no seu projeto.
+
+  Veja [Configurar Variáveis de Ambiente no AMP](#configurar-variáveis-de-ambiente-no-amp) abaixo.
+</Warning>
+
+## Referência de Provedores de Registro
+
+A tabela abaixo mostra o formato da URL de index e os valores de credenciais para provedores de registro comuns.
+Substitua os valores de exemplo pelos detalhes reais da sua organização e feed.
+
+| Provedor | URL do Index | Usuário | Senha |
+|----------|-------------|---------|-------|
+| **Azure DevOps Artifacts** | `https://pkgs.dev.azure.com/{org}/_packaging/{feed}/pypi/simple/` | Qualquer string não vazia (ex: `token`) | Personal Access Token (PAT) com escopo Packaging Read |
+| **GitHub Packages** | `https://pypi.pkg.github.com/{owner}/simple/` | Nome de usuário do GitHub | Personal Access Token (classic) com escopo `read:packages` |
+| **GitLab Package Registry** | `https://gitlab.com/api/v4/projects/{project_id}/packages/pypi/simple/` | `__token__` | Project ou Personal Access Token com escopo `read_api` |
+| **AWS CodeArtifact** | Use a URL de `aws codeartifact get-repository-endpoint` | `aws` | Token de `aws codeartifact get-authorization-token` |
+| **Google Artifact Registry** | `https://{region}-python.pkg.dev/{project}/{repo}/simple/` | `_json_key_base64` | Chave de conta de serviço codificada em Base64 |
+| **JFrog Artifactory** | `https://{instance}.jfrog.io/artifactory/api/pypi/{repo}/simple/` | Nome de usuário ou email | Chave API ou token de identidade |
+| **Auto-hospedado (devpi, Nexus, etc.)** | URL da API simple do seu registro | Nome de usuário do registro | Senha do registro |
+
+<Tip>
+  Para **AWS CodeArtifact**, o token de autorização expira periodicamente.
+  Você precisará atualizar o valor de `UV_INDEX_*_PASSWORD` quando ele expirar.
+  Considere automatizar isso no seu pipeline de CI/CD.
+</Tip>
+
+## Configurar Variáveis de Ambiente no AMP
+
+As credenciais do registro privado devem ser configuradas como variáveis de ambiente no CrewAI AMP.
+Você tem duas opções:
+
+<Tabs>
+  <Tab title="Interface Web">
+    1. Faça login no [CrewAI AMP](https://app.crewai.com)
+    2. Navegue até sua automação
+    3. Abra a aba **Environment Variables**
+    4. Adicione cada variável (`UV_INDEX_*_USERNAME` e `UV_INDEX_*_PASSWORD`) com seu valor
+
+    Veja o passo [Deploy para AMP — Definir Variáveis de Ambiente](/pt-BR/enterprise/guides/deploy-to-amp#definir-as-variáveis-de-ambiente) para detalhes.
+  </Tab>
+  <Tab title="Implantação via CLI">
+    Adicione as variáveis ao seu arquivo `.env` local antes de executar `crewai deploy create`.
+    A CLI as transferirá com segurança para a plataforma:
+
+    ```bash
+    # .env
+    OPENAI_API_KEY=sk-...
+    UV_INDEX_MY_PRIVATE_REGISTRY_USERNAME=token
+    UV_INDEX_MY_PRIVATE_REGISTRY_PASSWORD=your-pat-here
+    ```
+
+    ```bash
+    crewai deploy create
+    ```
+  </Tab>
+</Tabs>
+
+<Warning>
+  **Nunca** faça commit de credenciais no seu repositório. Use variáveis de ambiente do AMP para todos os segredos.
+  O arquivo `.env` deve estar listado no `.gitignore`.
+</Warning>
+
+Para atualizar credenciais em uma implantação existente, veja [Atualizar Seu Crew — Variáveis de Ambiente](/pt-BR/enterprise/guides/update-crew).
+
+## Como Tudo se Conecta
+
+Quando o CrewAI AMP faz o build da sua automação, o fluxo de resolução funciona assim:
+
+<Steps>
+  <Step title="Build inicia">
+    O AMP busca seu repositório e lê o `pyproject.toml` e o `uv.lock`.
+  </Step>
+  <Step title="UV resolve dependências">
+    O UV lê `[tool.uv.sources]` para determinar de qual index cada pacote deve vir.
+  </Step>
+  <Step title="UV autentica">
+    Para cada index privado, o UV busca `UV_INDEX_{NAME}_USERNAME` e `UV_INDEX_{NAME}_PASSWORD`
+    nas variáveis de ambiente que você configurou no AMP.
+  </Step>
+  <Step title="Pacotes são instalados">
+    O UV baixa e instala todos os pacotes — tanto públicos (do PyPI) quanto privados (do seu registro).
+  </Step>
+  <Step title="Automação executa">
+    Seu crew ou flow inicia com todas as dependências disponíveis.
+  </Step>
+</Steps>
+
+## Solução de Problemas
+
+### Erros de Autenticação Durante o Build
+
+**Sintoma**: Build falha com `401 Unauthorized` ou `403 Forbidden` ao resolver um pacote privado.
+
+**Verifique**:
+- Os nomes das variáveis de ambiente `UV_INDEX_*` correspondem exatamente ao nome do seu index (maiúsculas, hifens -> underscores)
+- As credenciais estão definidas nas variáveis de ambiente do AMP, não apenas em um `.env` local
+- Seu token/PAT tem as permissões de leitura necessárias para o feed de pacotes
+- O token não expirou (especialmente relevante para AWS CodeArtifact)
+
+### Pacote Não Encontrado
+
+**Sintoma**: `No matching distribution found for my-private-package`.
+
+**Verifique**:
+- A URL do index no `pyproject.toml` termina com `/simple/`
+- A entrada `[tool.uv.sources]` mapeia o nome correto do pacote para o nome correto do index
+- O pacote está realmente publicado no seu registro privado
+- Execute `uv lock` localmente com as mesmas credenciais para verificar se a resolução funciona
+
+### Conflitos no Arquivo Lock
+
+**Sintoma**: `uv lock` falha ou produz resultados inesperados após adicionar um index privado.
+
+**Solução**: Defina as credenciais localmente e regenere:
+
+```bash
+export UV_INDEX_MY_PRIVATE_REGISTRY_USERNAME=token
+export UV_INDEX_MY_PRIVATE_REGISTRY_PASSWORD=your-pat
+uv lock
+```
+
+Em seguida, faça commit do `uv.lock` atualizado.
+
+## Guias Relacionados
+
+<CardGroup cols={3}>
+  <Card title="Preparar para Implantação" icon="clipboard-check" href="/pt-BR/enterprise/guides/prepare-for-deployment">
+    Verifique a estrutura do projeto e as dependências antes de implantar.
+  </Card>
+  <Card title="Deploy para AMP" icon="rocket" href="/pt-BR/enterprise/guides/deploy-to-amp">
+    Implante seu crew ou flow e configure variáveis de ambiente.
+  </Card>
+  <Card title="Atualizar Seu Crew" icon="arrows-rotate" href="/pt-BR/enterprise/guides/update-crew">
+    Atualize variáveis de ambiente e envie alterações para uma implantação em execução.
+  </Card>
+</CardGroup>

docs/pt-BR/learn/llm-connections.mdx

@@ -7,7 +7,7 @@ mode: "wide"
 
 ## Conecte o CrewAI a LLMs
 
-O CrewAI utiliza o LiteLLM para conectar-se a uma grande variedade de Modelos de Linguagem (LLMs). Essa integração proporciona grande versatilidade, permitindo que você utilize modelos de inúmeros provedores por meio de uma interface simples e unificada.
+O CrewAI conecta-se a LLMs por meio de integrações nativas via SDK para os provedores mais populares (OpenAI, Anthropic, Google Gemini, Azure e AWS Bedrock), e usa o LiteLLM como alternativa flexível para todos os demais provedores.
 
 <Note>
     Por padrão, o CrewAI usa o modelo `gpt-4o-mini`. Isso é determinado pela variável de ambiente `OPENAI_MODEL_NAME`, que tem como padrão "gpt-4o-mini" se não for definida.
@@ -40,6 +40,14 @@ O LiteLLM oferece suporte a uma ampla gama de provedores, incluindo, mas não se
 
 Para uma lista completa e sempre atualizada dos provedores suportados, consulte a [documentação de Provedores do LiteLLM](https://docs.litellm.ai/docs/providers).
 
+<Info>
+  Para usar qualquer provedor não coberto por uma integração nativa, adicione o LiteLLM como dependência ao seu projeto:
+  ```bash
+  uv add 'crewai[litellm]'
+  ```
+  Provedores nativos (OpenAI, Anthropic, Google Gemini, Azure, AWS Bedrock) usam seus próprios extras de SDK — consulte os [Exemplos de Configuração de Provedores](/pt-BR/concepts/llms#exemplos-de-configuração-de-provedores).
+</Info>
+
 ## Alterando a LLM
 
 Para utilizar uma LLM diferente com seus agentes CrewAI, você tem várias opções:

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

@@ -152,4 +152,4 @@ __all__ = [
     "wrap_file_source",
 ]
 
-__version__ = "1.9.3"
+__version__ = "1.10.1a1"

lib/crewai-tools/pyproject.toml

@@ -8,12 +8,10 @@ authors = [
 ]
 requires-python = ">=3.10, <3.14"
 dependencies = [
-    "lancedb~=0.5.4",
     "pytube~=15.0.0",
     "requests~=2.32.5",
     "docker~=7.1.0",
-    "crewai==1.9.3",
-    "lancedb~=0.5.4",
+    "crewai==1.10.1a1",
     "tiktoken~=0.8.0",
     "beautifulsoup4~=4.13.4",
     "python-docx~=1.2.0",

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

@@ -291,4 +291,4 @@ __all__ = [
     "ZapierActionTools",
 ]
 
-__version__ = "1.9.3"
+__version__ = "1.10.1a1"

lib/crewai-tools/tool.specs.json

@@ -20117,18 +20117,6 @@
       "humanized_name": "Web Automation Tool",
       "init_params_schema": {
         "$defs": {
-          "AvailableModel": {
-            "enum": [
-              "gpt-4o",
-              "gpt-4o-mini",
-              "claude-3-5-sonnet-latest",
-              "claude-3-7-sonnet-latest",
-              "computer-use-preview",
-              "gemini-2.0-flash"
-            ],
-            "title": "AvailableModel",
-            "type": "string"
-          },
           "EnvVar": {
             "properties": {
               "default": {
@@ -20206,17 +20194,6 @@
             "default": null,
             "title": "Model Api Key"
           },
-          "model_name": {
-            "anyOf": [
-              {
-                "$ref": "#/$defs/AvailableModel"
-              },
-              {
-                "type": "null"
-              }
-            ],
-            "default": "claude-3-7-sonnet-latest"
-          },
           "project_id": {
             "anyOf": [
               {

lib/crewai/pyproject.toml

@@ -42,7 +42,7 @@ dependencies = [
     "mcp~=1.26.0",
     "uv~=0.9.13",
     "aiosqlite~=0.21.0",
-    "lancedb>=0.4.0",
+    "lancedb>=0.29.2",
 ]
 
 [project.urls]
@@ -53,7 +53,7 @@ Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
 tools = [
-    "crewai-tools==1.9.3",
+    "crewai-tools==1.10.1a1",
 ]
 embeddings = [
     "tiktoken~=0.8.0"

lib/crewai/src/crewai/__init__.py

@@ -10,7 +10,6 @@ from crewai.flow.flow import Flow
 from crewai.knowledge.knowledge import Knowledge
 from crewai.llm import LLM
 from crewai.llms.base_llm import BaseLLM
-from crewai.memory.unified_memory import Memory
 from crewai.process import Process
 from crewai.task import Task
 from crewai.tasks.llm_guardrail import LLMGuardrail
@@ -41,7 +40,7 @@ def _suppress_pydantic_deprecation_warnings() -> None:
 
 _suppress_pydantic_deprecation_warnings()
 
-__version__ = "1.9.3"
+__version__ = "1.10.1a1"
 _telemetry_submitted = False
 
 
@@ -72,6 +71,25 @@ def _track_install_async() -> None:
 
 
 _track_install_async()
+
+_LAZY_IMPORTS: dict[str, tuple[str, str]] = {
+    "Memory": ("crewai.memory.unified_memory", "Memory"),
+}
+
+
+def __getattr__(name: str) -> Any:
+    """Lazily import heavy modules (e.g. Memory → lancedb) on first access."""
+    if name in _LAZY_IMPORTS:
+        module_path, attr = _LAZY_IMPORTS[name]
+        import importlib
+
+        mod = importlib.import_module(module_path)
+        val = getattr(mod, attr)
+        globals()[name] = val
+        return val
+    raise AttributeError(f"module 'crewai' has no attribute {name!r}")
+
+
 __all__ = [
     "LLM",
     "Agent",

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

@@ -8,11 +8,9 @@ import time
 from typing import (
     TYPE_CHECKING,
     Any,
-    Final,
     Literal,
     cast,
 )
-from urllib.parse import urlparse
 
 from pydantic import (
     BaseModel,
@@ -61,16 +59,8 @@ from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.lite_agent_output import LiteAgentOutput
 from crewai.llms.base_llm import BaseLLM
-from crewai.mcp import (
-    MCPClient,
-    MCPServerConfig,
-    MCPServerHTTP,
-    MCPServerSSE,
-    MCPServerStdio,
-)
-from crewai.mcp.transports.http import HTTPTransport
-from crewai.mcp.transports.sse import SSETransport
-from crewai.mcp.transports.stdio import StdioTransport
+from crewai.mcp import MCPServerConfig
+from crewai.mcp.tool_resolver import MCPToolResolver
 from crewai.rag.embeddings.types import EmbedderConfig
 from crewai.security.fingerprint import Fingerprint
 from crewai.tools.agent_tools.agent_tools import AgentTools
@@ -111,18 +101,8 @@ if TYPE_CHECKING:
     from crewai.utilities.types import LLMMessage
 
 
-# MCP Connection timeout constants (in seconds)
-MCP_CONNECTION_TIMEOUT: Final[int] = 10
-MCP_TOOL_EXECUTION_TIMEOUT: Final[int] = 30
-MCP_DISCOVERY_TIMEOUT: Final[int] = 15
-MCP_MAX_RETRIES: Final[int] = 3
-
 _passthrough_exceptions: tuple[type[Exception], ...] = ()
 
-# Simple in-memory cache for MCP tool schemas (duration: 5 minutes)
-_mcp_schema_cache: dict[str, Any] = {}
-_cache_ttl: Final[int] = 300  # 5 minutes
-
 
 class Agent(BaseAgent):
     """Represents an agent in a system.
@@ -154,7 +134,7 @@ class Agent(BaseAgent):
     model_config = ConfigDict()
 
     _times_executed: int = PrivateAttr(default=0)
-    _mcp_clients: list[Any] = PrivateAttr(default_factory=list)
+    _mcp_resolver: MCPToolResolver | None = PrivateAttr(default=None)
     _last_messages: list[LLMMessage] = PrivateAttr(default_factory=list)
     max_execution_time: int | None = Field(
         default=None,
@@ -384,10 +364,10 @@ class Agent(BaseAgent):
                 )
                 if unified_memory is not None:
                     query = task.description
-                    matches = unified_memory.recall(query, limit=10)
+                    matches = unified_memory.recall(query, limit=5)
                     if matches:
                         memory = "Relevant memories:\n" + "\n".join(
-                            f"- {m.record.content}" for m in matches
+                            m.format() for m in matches
                         )
                 if memory.strip() != "":
                     task_prompt += self.i18n.slice("memory").format(memory=memory)
@@ -622,10 +602,10 @@ class Agent(BaseAgent):
                 )
                 if unified_memory is not None:
                     query = task.description
-                    matches = unified_memory.recall(query, limit=10)
+                    matches = unified_memory.recall(query, limit=5)
                     if matches:
                         memory = "Relevant memories:\n" + "\n".join(
-                            f"- {m.record.content}" for m in matches
+                            m.format() for m in matches
                         )
                 if memory.strip() != "":
                     task_prompt += self.i18n.slice("memory").format(memory=memory)
@@ -864,7 +844,11 @@ class Agent(BaseAgent):
                 respect_context_window=self.respect_context_window,
                 request_within_rpm_limit=rpm_limit_fn,
                 callbacks=[TokenCalcHandler(self._token_process)],
-                response_model=task.response_model if task else None,
+                response_model=(
+                    task.response_model or task.output_pydantic or task.output_json
+                )
+                if task
+                else None,
             )
 
     def _update_executor_parameters(
@@ -893,7 +877,11 @@ class Agent(BaseAgent):
         self.agent_executor.stop = stop_words
         self.agent_executor.tools_names = get_tool_names(tools)
         self.agent_executor.tools_description = render_text_description_and_args(tools)
-        self.agent_executor.response_model = task.response_model if task else None
+        self.agent_executor.response_model = (
+            (task.response_model or task.output_pydantic or task.output_json)
+            if task
+            else None
+        )
 
         self.agent_executor.tools_handler = self.tools_handler
         self.agent_executor.request_within_rpm_limit = rpm_limit_fn
@@ -926,544 +914,17 @@ class Agent(BaseAgent):
     def get_mcp_tools(self, mcps: list[str | MCPServerConfig]) -> list[BaseTool]:
         """Convert MCP server references/configs to CrewAI tools.
 
-        Supports both string references (backwards compatible) and structured
-        configuration objects (MCPServerStdio, MCPServerHTTP, MCPServerSSE).
-
-        Args:
-            mcps: List of MCP server references (strings) or configurations.
-
-        Returns:
-            List of BaseTool instances from MCP servers.
+        Delegates to :class:`~crewai.mcp.tool_resolver.MCPToolResolver`.
         """
-        all_tools = []
-        clients = []
-
-        for mcp_config in mcps:
-            if isinstance(mcp_config, str):
-                tools = self._get_mcp_tools_from_string(mcp_config)
-            else:
-                tools, client = self._get_native_mcp_tools(mcp_config)
-                if client:
-                    clients.append(client)
-
-            all_tools.extend(tools)
-
-        # Store clients for cleanup
-        self._mcp_clients.extend(clients)
-        return all_tools
+        self._cleanup_mcp_clients()
+        self._mcp_resolver = MCPToolResolver(agent=self, logger=self._logger)
+        return self._mcp_resolver.resolve(mcps)
 
     def _cleanup_mcp_clients(self) -> None:
         """Cleanup MCP client connections after task execution."""
-        if not self._mcp_clients:
-            return
-
-        async def _disconnect_all() -> None:
-            for client in self._mcp_clients:
-                if client and hasattr(client, "connected") and client.connected:
-                    await client.disconnect()
-
-        try:
-            asyncio.run(_disconnect_all())
-        except Exception as e:
-            self._logger.log("error", f"Error during MCP client cleanup: {e}")
-        finally:
-            self._mcp_clients.clear()
-
-    def _get_mcp_tools_from_string(self, mcp_ref: str) -> list[BaseTool]:
-        """Get tools from legacy string-based MCP references.
-
-        This method maintains backwards compatibility with string-based
-        MCP references (https://... and crewai-amp:...).
-
-        Args:
-            mcp_ref: String reference to MCP server.
-
-        Returns:
-            List of BaseTool instances.
-        """
-        if mcp_ref.startswith("crewai-amp:"):
-            return self._get_amp_mcp_tools(mcp_ref)
-        if mcp_ref.startswith("https://"):
-            return self._get_external_mcp_tools(mcp_ref)
-        return []
-
-    def _get_external_mcp_tools(self, mcp_ref: str) -> list[BaseTool]:
-        """Get tools from external HTTPS MCP server with graceful error handling."""
-        from crewai.tools.mcp_tool_wrapper import MCPToolWrapper
-
-        # Parse server URL and optional tool name
-        if "#" in mcp_ref:
-            server_url, specific_tool = mcp_ref.split("#", 1)
-        else:
-            server_url, specific_tool = mcp_ref, None
-
-        server_params = {"url": server_url}
-        server_name = self._extract_server_name(server_url)
-
-        try:
-            # Get tool schemas with timeout and error handling
-            tool_schemas = self._get_mcp_tool_schemas(server_params)
-
-            if not tool_schemas:
-                self._logger.log(
-                    "warning", f"No tools discovered from MCP server: {server_url}"
-                )
-                return []
-
-            tools = []
-            for tool_name, schema in tool_schemas.items():
-                # Skip if specific tool requested and this isn't it
-                if specific_tool and tool_name != specific_tool:
-                    continue
-
-                try:
-                    wrapper = MCPToolWrapper(
-                        mcp_server_params=server_params,
-                        tool_name=tool_name,
-                        tool_schema=schema,
-                        server_name=server_name,
-                    )
-                    tools.append(wrapper)
-                except Exception as e:
-                    self._logger.log(
-                        "warning",
-                        f"Failed to create MCP tool wrapper for {tool_name}: {e}",
-                    )
-                    continue
-
-            if specific_tool and not tools:
-                self._logger.log(
-                    "warning",
-                    f"Specific tool '{specific_tool}' not found on MCP server: {server_url}",
-                )
-
-            return cast(list[BaseTool], tools)
-
-        except Exception as e:
-            self._logger.log(
-                "warning", f"Failed to connect to MCP server {server_url}: {e}"
-            )
-            return []
-
-    def _get_native_mcp_tools(
-        self, mcp_config: MCPServerConfig
-    ) -> tuple[list[BaseTool], Any | None]:
-        """Get tools from MCP server using structured configuration.
-
-        This method creates an MCP client based on the configuration type,
-        connects to the server, discovers tools, applies filtering, and
-        returns wrapped tools along with the client instance for cleanup.
-
-        Args:
-            mcp_config: MCP server configuration (MCPServerStdio, MCPServerHTTP, or MCPServerSSE).
-
-        Returns:
-            Tuple of (list of BaseTool instances, MCPClient instance for cleanup).
-        """
-        from crewai.tools.base_tool import BaseTool
-        from crewai.tools.mcp_native_tool import MCPNativeTool
-
-        transport: StdioTransport | HTTPTransport | SSETransport
-        if isinstance(mcp_config, MCPServerStdio):
-            transport = StdioTransport(
-                command=mcp_config.command,
-                args=mcp_config.args,
-                env=mcp_config.env,
-            )
-            server_name = f"{mcp_config.command}_{'_'.join(mcp_config.args)}"
-        elif isinstance(mcp_config, MCPServerHTTP):
-            transport = HTTPTransport(
-                url=mcp_config.url,
-                headers=mcp_config.headers,
-                streamable=mcp_config.streamable,
-            )
-            server_name = self._extract_server_name(mcp_config.url)
-        elif isinstance(mcp_config, MCPServerSSE):
-            transport = SSETransport(
-                url=mcp_config.url,
-                headers=mcp_config.headers,
-            )
-            server_name = self._extract_server_name(mcp_config.url)
-        else:
-            raise ValueError(f"Unsupported MCP server config type: {type(mcp_config)}")
-
-        client = MCPClient(
-            transport=transport,
-            cache_tools_list=mcp_config.cache_tools_list,
-        )
-
-        async def _setup_client_and_list_tools() -> list[dict[str, Any]]:
-            """Async helper to connect and list tools in same event loop."""
-
-            try:
-                if not client.connected:
-                    await client.connect()
-
-                tools_list = await client.list_tools()
-
-                try:
-                    await client.disconnect()
-                    # Small delay to allow background tasks to finish cleanup
-                    # This helps prevent "cancel scope in different task" errors
-                    # when asyncio.run() closes the event loop
-                    await asyncio.sleep(0.1)
-                except Exception as e:
-                    self._logger.log("error", f"Error during disconnect: {e}")
-
-                return tools_list
-            except Exception as e:
-                if client.connected:
-                    await client.disconnect()
-                    await asyncio.sleep(0.1)
-                raise RuntimeError(
-                    f"Error during setup client and list tools: {e}"
-                ) from e
-
-        try:
-            try:
-                asyncio.get_running_loop()
-                import concurrent.futures
-
-                with concurrent.futures.ThreadPoolExecutor() as executor:
-                    future = executor.submit(
-                        asyncio.run, _setup_client_and_list_tools()
-                    )
-                    tools_list = future.result()
-            except RuntimeError:
-                try:
-                    tools_list = asyncio.run(_setup_client_and_list_tools())
-                except RuntimeError as e:
-                    error_msg = str(e).lower()
-                    if "cancel scope" in error_msg or "task" in error_msg:
-                        raise ConnectionError(
-                            "MCP connection failed due to event loop cleanup issues. "
-                            "This may be due to authentication errors or server unavailability."
-                        ) from e
-                except asyncio.CancelledError as e:
-                    raise ConnectionError(
-                        "MCP connection was cancelled. This may indicate an authentication "
-                        "error or server unavailability."
-                    ) from e
-
-            if mcp_config.tool_filter:
-                filtered_tools = []
-                for tool in tools_list:
-                    if callable(mcp_config.tool_filter):
-                        try:
-                            from crewai.mcp.filters import ToolFilterContext
-
-                            context = ToolFilterContext(
-                                agent=self,
-                                server_name=server_name,
-                                run_context=None,
-                            )
-                            if mcp_config.tool_filter(context, tool):  # type: ignore[call-arg, arg-type]
-                                filtered_tools.append(tool)
-                        except (TypeError, AttributeError):
-                            if mcp_config.tool_filter(tool):  # type: ignore[call-arg, arg-type]
-                                filtered_tools.append(tool)
-                    else:
-                        # Not callable - include tool
-                        filtered_tools.append(tool)
-                tools_list = filtered_tools
-
-            tools = []
-            for tool_def in tools_list:
-                tool_name = tool_def.get("name", "")
-                if not tool_name:
-                    continue
-
-                # Convert inputSchema to Pydantic model if present
-                args_schema = None
-                if tool_def.get("inputSchema"):
-                    args_schema = self._json_schema_to_pydantic(
-                        tool_name, tool_def["inputSchema"]
-                    )
-
-                tool_schema = {
-                    "description": tool_def.get("description", ""),
-                    "args_schema": args_schema,
-                }
-
-                try:
-                    native_tool = MCPNativeTool(
-                        mcp_client=client,
-                        tool_name=tool_name,
-                        tool_schema=tool_schema,
-                        server_name=server_name,
-                    )
-                    tools.append(native_tool)
-                except Exception as e:
-                    self._logger.log("error", f"Failed to create native MCP tool: {e}")
-                    continue
-
-            return cast(list[BaseTool], tools), client
-        except Exception as e:
-            if client.connected:
-                asyncio.run(client.disconnect())
-
-            raise RuntimeError(f"Failed to get native MCP tools: {e}") from e
-
-    def _get_amp_mcp_tools(self, amp_ref: str) -> list[BaseTool]:
-        """Get tools from CrewAI AMP MCP marketplace."""
-        # Parse: "crewai-amp:mcp-name" or "crewai-amp:mcp-name#tool_name"
-        amp_part = amp_ref.replace("crewai-amp:", "")
-        if "#" in amp_part:
-            mcp_name, specific_tool = amp_part.split("#", 1)
-        else:
-            mcp_name, specific_tool = amp_part, None
-
-        # Call AMP API to get MCP server URLs
-        mcp_servers = self._fetch_amp_mcp_servers(mcp_name)
-
-        tools = []
-        for server_config in mcp_servers:
-            server_ref = server_config["url"]
-            if specific_tool:
-                server_ref += f"#{specific_tool}"
-            server_tools = self._get_external_mcp_tools(server_ref)
-            tools.extend(server_tools)
-
-        return tools
-
-    @staticmethod
-    def _extract_server_name(server_url: str) -> str:
-        """Extract clean server name from URL for tool prefixing."""
-
-        parsed = urlparse(server_url)
-        domain = parsed.netloc.replace(".", "_")
-        path = parsed.path.replace("/", "_").strip("_")
-        return f"{domain}_{path}" if path else domain
-
-    def _get_mcp_tool_schemas(
-        self, server_params: dict[str, Any]
-    ) -> dict[str, dict[str, Any]]:
-        """Get tool schemas from MCP server for wrapper creation with caching."""
-        server_url = server_params["url"]
-
-        # Check cache first
-        cache_key = server_url
-        current_time = time.time()
-
-        if cache_key in _mcp_schema_cache:
-            cached_data, cache_time = _mcp_schema_cache[cache_key]
-            if current_time - cache_time < _cache_ttl:
-                self._logger.log(
-                    "debug", f"Using cached MCP tool schemas for {server_url}"
-                )
-                return cached_data  # type: ignore[no-any-return]
-
-        try:
-            schemas = asyncio.run(self._get_mcp_tool_schemas_async(server_params))
-
-            # Cache successful results
-            _mcp_schema_cache[cache_key] = (schemas, current_time)
-
-            return schemas
-        except Exception as e:
-            # Log warning but don't raise - this allows graceful degradation
-            self._logger.log(
-                "warning", f"Failed to get MCP tool schemas from {server_url}: {e}"
-            )
-            return {}
-
-    async def _get_mcp_tool_schemas_async(
-        self, server_params: dict[str, Any]
-    ) -> dict[str, dict[str, Any]]:
-        """Async implementation of MCP tool schema retrieval with timeouts and retries."""
-        server_url = server_params["url"]
-        return await self._retry_mcp_discovery(
-            self._discover_mcp_tools_with_timeout, server_url
-        )
-
-    async def _retry_mcp_discovery(
-        self, operation_func: Any, server_url: str
-    ) -> dict[str, dict[str, Any]]:
-        """Retry MCP discovery operation with exponential backoff, avoiding try-except in loop."""
-        last_error = None
-
-        for attempt in range(MCP_MAX_RETRIES):
-            # Execute single attempt outside try-except loop structure
-            result, error, should_retry = await self._attempt_mcp_discovery(
-                operation_func, server_url
-            )
-
-            # Success case - return immediately
-            if result is not None:
-                return result
-
-            # Non-retryable error - raise immediately
-            if not should_retry:
-                raise RuntimeError(error)
-
-            # Retryable error - continue with backoff
-            last_error = error
-            if attempt < MCP_MAX_RETRIES - 1:
-                wait_time = 2**attempt  # Exponential backoff
-                await asyncio.sleep(wait_time)
-
-        raise RuntimeError(
-            f"Failed to discover MCP tools after {MCP_MAX_RETRIES} attempts: {last_error}"
-        )
-
-    @staticmethod
-    async def _attempt_mcp_discovery(
-        operation_func: Any, server_url: str
-    ) -> tuple[dict[str, dict[str, Any]] | None, str, bool]:
-        """Attempt single MCP discovery operation and return (result, error_message, should_retry)."""
-        try:
-            result = await operation_func(server_url)
-            return result, "", False
-
-        except ImportError:
-            return (
-                None,
-                "MCP library not available. Please install with: pip install mcp",
-                False,
-            )
-
-        except asyncio.TimeoutError:
-            return (
-                None,
-                f"MCP discovery timed out after {MCP_DISCOVERY_TIMEOUT} seconds",
-                True,
-            )
-
-        except Exception as e:
-            error_str = str(e).lower()
-
-            # Classify errors as retryable or non-retryable
-            if "authentication" in error_str or "unauthorized" in error_str:
-                return None, f"Authentication failed for MCP server: {e!s}", False
-            if "connection" in error_str or "network" in error_str:
-                return None, f"Network connection failed: {e!s}", True
-            if "json" in error_str or "parsing" in error_str:
-                return None, f"Server response parsing error: {e!s}", True
-            return None, f"MCP discovery error: {e!s}", False
-
-    async def _discover_mcp_tools_with_timeout(
-        self, server_url: str
-    ) -> dict[str, dict[str, Any]]:
-        """Discover MCP tools with timeout wrapper."""
-        return await asyncio.wait_for(
-            self._discover_mcp_tools(server_url), timeout=MCP_DISCOVERY_TIMEOUT
-        )
-
-    async def _discover_mcp_tools(self, server_url: str) -> dict[str, dict[str, Any]]:
-        """Discover tools from MCP server with proper timeout handling."""
-        from mcp import ClientSession
-        from mcp.client.streamable_http import streamablehttp_client
-
-        async with streamablehttp_client(server_url) as (read, write, _):
-            async with ClientSession(read, write) as session:
-                # Initialize the connection with timeout
-                await asyncio.wait_for(
-                    session.initialize(), timeout=MCP_CONNECTION_TIMEOUT
-                )
-
-                # List available tools with timeout
-                tools_result = await asyncio.wait_for(
-                    session.list_tools(),
-                    timeout=MCP_DISCOVERY_TIMEOUT - MCP_CONNECTION_TIMEOUT,
-                )
-
-                schemas = {}
-                for tool in tools_result.tools:
-                    args_schema = None
-                    if hasattr(tool, "inputSchema") and tool.inputSchema:
-                        args_schema = self._json_schema_to_pydantic(
-                            sanitize_tool_name(tool.name), tool.inputSchema
-                        )
-
-                    schemas[sanitize_tool_name(tool.name)] = {
-                        "description": getattr(tool, "description", ""),
-                        "args_schema": args_schema,
-                    }
-                return schemas
-
-    def _json_schema_to_pydantic(
-        self, tool_name: str, json_schema: dict[str, Any]
-    ) -> type:
-        """Convert JSON Schema to Pydantic model for tool arguments.
-
-        Args:
-            tool_name: Name of the tool (used for model naming)
-            json_schema: JSON Schema dict with 'properties', 'required', etc.
-
-        Returns:
-            Pydantic BaseModel class
-        """
-        from pydantic import Field, create_model
-
-        properties = json_schema.get("properties", {})
-        required_fields = json_schema.get("required", [])
-
-        field_definitions: dict[str, Any] = {}
-
-        for field_name, field_schema in properties.items():
-            field_type = self._json_type_to_python(field_schema)
-            field_description = field_schema.get("description", "")
-
-            is_required = field_name in required_fields
-
-            if is_required:
-                field_definitions[field_name] = (
-                    field_type,
-                    Field(..., description=field_description),
-                )
-            else:
-                field_definitions[field_name] = (
-                    field_type | None,
-                    Field(default=None, description=field_description),
-                )
-
-        model_name = f"{tool_name.replace('-', '_').replace(' ', '_')}Schema"
-        return create_model(model_name, **field_definitions)  # type: ignore[no-any-return]
-
-    def _json_type_to_python(self, field_schema: dict[str, Any]) -> type:
-        """Convert JSON Schema type to Python type.
-
-        Args:
-            field_schema: JSON Schema field definition
-
-        Returns:
-            Python type
-        """
-
-        json_type = field_schema.get("type")
-
-        if "anyOf" in field_schema:
-            types: list[type] = []
-            for option in field_schema["anyOf"]:
-                if "const" in option:
-                    types.append(str)
-                else:
-                    types.append(self._json_type_to_python(option))
-            unique_types = list(set(types))
-            if len(unique_types) > 1:
-                result: Any = unique_types[0]
-                for t in unique_types[1:]:
-                    result = result | t
-                return result  # type: ignore[no-any-return]
-            return unique_types[0]
-
-        type_mapping: dict[str | None, type] = {
-            "string": str,
-            "number": float,
-            "integer": int,
-            "boolean": bool,
-            "array": list,
-            "object": dict,
-        }
-
-        return type_mapping.get(json_type, Any)
-
-    @staticmethod
-    def _fetch_amp_mcp_servers(mcp_name: str) -> list[dict[str, Any]]:
-        """Fetch MCP server configurations from CrewAI AMP API."""
-        # TODO: Implement AMP API call to "integrations/mcps" endpoint
-        # Should return list of server configs with URLs
-        return []
+        if self._mcp_resolver is not None:
+            self._mcp_resolver.cleanup()
+            self._mcp_resolver = None
 
     @staticmethod
     def get_multimodal_tools() -> Sequence[BaseTool]:
@@ -1712,7 +1173,8 @@ class Agent(BaseAgent):
 
             existing_names = {sanitize_tool_name(t.name) for t in raw_tools}
             raw_tools.extend(
-                mt for mt in create_memory_tools(agent_memory)
+                mt
+                for mt in create_memory_tools(agent_memory)
                 if sanitize_tool_name(mt.name) not in existing_names
             )
 
@@ -1802,11 +1264,11 @@ class Agent(BaseAgent):
                     ),
                 )
                 start_time = time.time()
-                matches = agent_memory.recall(formatted_messages, limit=10)
+                matches = agent_memory.recall(formatted_messages, limit=5)
                 memory_block = ""
                 if matches:
                     memory_block = "Relevant memories:\n" + "\n".join(
-                        f"- {m.record.content}" for m in matches
+                        m.format() for m in matches
                     )
                 if memory_block:
                     formatted_messages += "\n\n" + self.i18n.slice("memory").format(
@@ -1937,14 +1399,15 @@ class Agent(BaseAgent):
             if isinstance(messages, str):
                 input_str = messages
             else:
-                input_str = "\n".join(
-                    str(msg.get("content", "")) for msg in messages if msg.get("content")
-                ) or "User request"
-            raw = (
-                f"Input: {input_str}\n"
-                f"Agent: {self.role}\n"
-                f"Result: {output_text}"
-            )
+                input_str = (
+                    "\n".join(
+                        str(msg.get("content", ""))
+                        for msg in messages
+                        if msg.get("content")
+                    )
+                    or "User request"
+                )
+            raw = f"Input: {input_str}\nAgent: {self.role}\nResult: {output_text}"
             extracted = agent_memory.extract_memories(raw)
             if extracted:
                 agent_memory.remember_many(extracted)

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

@@ -4,7 +4,8 @@ from abc import ABC, abstractmethod
 from collections.abc import Callable
 from copy import copy as shallow_copy
 from hashlib import md5
-from typing import Any, Literal
+import re
+from typing import Any, Final, Literal
 import uuid
 
 from pydantic import (
@@ -36,6 +37,11 @@ from crewai.utilities.rpm_controller import RPMController
 from crewai.utilities.string_utils import interpolate_only
 
 
+_SLUG_RE: Final[re.Pattern[str]] = re.compile(
+    r"^(?:crewai-amp:)?[a-zA-Z0-9][a-zA-Z0-9_-]*(?:#\w+)?$"
+)
+
+
 PlatformApp = Literal[
     "asana",
     "box",
@@ -197,7 +203,7 @@ class BaseAgent(BaseModel, ABC, metaclass=AgentMeta):
     )
     mcps: list[str | MCPServerConfig] | None = Field(
         default=None,
-        description="List of MCP server references. Supports 'https://server.com/path' for external servers and 'crewai-amp:mcp-name' for AMP marketplace. Use '#tool_name' suffix for specific tools.",
+        description="List of MCP server references. Supports 'https://server.com/path' for external servers and bare slugs like 'notion' for connected MCP integrations. Use '#tool_name' suffix for specific tools.",
     )
     memory: Any = Field(
         default=None,
@@ -276,14 +282,16 @@ class BaseAgent(BaseModel, ABC, metaclass=AgentMeta):
         validated_mcps: list[str | MCPServerConfig] = []
         for mcp in mcps:
             if isinstance(mcp, str):
-                if mcp.startswith(("https://", "crewai-amp:")):
+                if mcp.startswith("https://"):
+                    validated_mcps.append(mcp)
+                elif _SLUG_RE.match(mcp):
                     validated_mcps.append(mcp)
                 else:
                     raise ValueError(
-                        f"Invalid MCP reference: {mcp}. "
-                        "String references must start with 'https://' or 'crewai-amp:'"
+                        f"Invalid MCP reference: {mcp!r}. "
+                        "String references must be an 'https://' URL or a valid "
+                        "slug (e.g. 'notion', 'notion#search', 'crewai-amp:notion')."
                     )
-
             elif isinstance(mcp, (MCPServerConfig)):
                 validated_mcps.append(mcp)
             else:

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

@@ -30,7 +30,7 @@ class CrewAgentExecutorMixin:
         memory = getattr(self.agent, "memory", None) or (
             getattr(self.crew, "_memory", None) if self.crew else None
         )
-        if memory is None or not self.task:
+        if memory is None or not self.task or getattr(memory, "_read_only", False):
             return
         if (
             f"Action: {sanitize_tool_name('Delegate work to coworker')}"

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

@@ -50,6 +50,7 @@ from crewai.utilities.agent_utils import (
     handle_unknown_error,
     has_reached_max_iterations,
     is_context_length_exceeded,
+    parse_tool_call_args,
     process_llm_response,
     track_delegation_if_needed,
 )
@@ -894,13 +895,9 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
             ToolUsageStartedEvent,
         )
 
-        if isinstance(func_args, str):
-            try:
-                args_dict = json.loads(func_args)
-            except json.JSONDecodeError:
-                args_dict = {}
-        else:
-            args_dict = func_args
+        args_dict, parse_error = parse_tool_call_args(func_args, func_name, call_id, original_tool)
+        if parse_error is not None:
+            return parse_error
 
         if original_tool is None:
             for tool in self.original_tools or []:
@@ -1262,7 +1259,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         formatted_answer, tool_result
                     )
 
-                self._invoke_step_callback(formatted_answer)  # type: ignore[arg-type]
+                await self._ainvoke_step_callback(formatted_answer)  # type: ignore[arg-type]
                 self._append_message(formatted_answer.text)  # type: ignore[union-attr]
 
             except OutputParserError as e:
@@ -1377,7 +1374,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         output=answer,
                         text=answer,
                     )
-                    self._invoke_step_callback(formatted_answer)
+                    await self._ainvoke_step_callback(formatted_answer)
                     self._append_message(answer)  # Save final answer to messages
                     self._show_logs(formatted_answer)
                     return formatted_answer
@@ -1389,7 +1386,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         output=answer,
                         text=output_json,
                     )
-                    self._invoke_step_callback(formatted_answer)
+                    await self._ainvoke_step_callback(formatted_answer)
                     self._append_message(output_json)
                     self._show_logs(formatted_answer)
                     return formatted_answer
@@ -1400,7 +1397,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                     output=str(answer),
                     text=str(answer),
                 )
-                self._invoke_step_callback(formatted_answer)
+                await self._ainvoke_step_callback(formatted_answer)
                 self._append_message(str(answer))  # Save final answer to messages
                 self._show_logs(formatted_answer)
                 return formatted_answer
@@ -1494,7 +1491,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
     def _invoke_step_callback(
         self, formatted_answer: AgentAction | AgentFinish
     ) -> None:
-        """Invoke step callback.
+        """Invoke step callback (sync context).
 
         Args:
             formatted_answer: Current agent response.
@@ -1504,6 +1501,19 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
             if inspect.iscoroutine(cb_result):
                 asyncio.run(cb_result)
 
+    async def _ainvoke_step_callback(
+        self, formatted_answer: AgentAction | AgentFinish
+    ) -> None:
+        """Invoke step callback (async context).
+
+        Args:
+            formatted_answer: Current agent response.
+        """
+        if self.step_callback:
+            cb_result = self.step_callback(formatted_answer)
+            if inspect.iscoroutine(cb_result):
+                await cb_result
+
     def _append_message(
         self, text: str, role: Literal["user", "assistant", "system"] = "assistant"
     ) -> None:

lib/crewai/src/crewai/cli/constants.py

@@ -69,7 +69,7 @@ ENV_VARS: dict[str, list[dict[str, Any]]] = {
         },
         {
             "prompt": "Enter your AWS Region Name (press Enter to skip)",
-            "key_name": "AWS_REGION_NAME",
+            "key_name": "AWS_DEFAULT_REGION",
         },
     ],
     "azure": [

lib/crewai/src/crewai/cli/memory_tui.py

@@ -290,13 +290,20 @@ class MemoryTUI(App[None]):
         if self._memory is None:
             panel.update(self._init_error or "No memory loaded.")
             return
+        display_limit = 1000
         info = self._memory.info(path)
         self._last_scope_info = info
-        self._entries = self._memory.list_records(scope=path, limit=200)
+        self._entries = self._memory.list_records(scope=path, limit=display_limit)
         panel.update(_format_scope_info(info))
         panel.border_title = "Detail"
         entry_list = self.query_one("#entry-list", OptionList)
-        entry_list.border_title = f"Entries ({len(self._entries)})"
+        capped = info.record_count > display_limit
+        count_label = (
+            f"Entries (showing {display_limit} of {info.record_count} — display limit)"
+            if capped
+            else f"Entries ({len(self._entries)})"
+        )
+        entry_list.border_title = count_label
         self._populate_entry_list()
 
     def on_option_list_option_highlighted(
@@ -376,6 +383,11 @@ class MemoryTUI(App[None]):
                 return
 
             info_lines: list[str] = []
+            info_lines.append(
+                "[dim italic]Searched the full dataset"
+                + (f" within [bold]{scope}[/]" if scope else "")
+                + " using the recall flow (semantic + recency + importance).[/]\n"
+            )
             if not self._custom_embedder:
                 info_lines.append(
                     "[dim italic]Note: Using default OpenAI embedder. "

lib/crewai/src/crewai/cli/plus_api.py

@@ -190,6 +190,15 @@ class PlusAPI:
             timeout=30,
         )
 
+    def get_mcp_configs(self, slugs: list[str]) -> httpx.Response:
+        """Get MCP server configurations for the given slugs."""
+        return self._make_request(
+            "GET",
+            f"{self.INTEGRATIONS_RESOURCE}/mcp_configs",
+            params={"slugs": ",".join(slugs)},
+            timeout=30,
+        )
+
     def get_triggers(self) -> httpx.Response:
         """Get all available triggers from integrations."""
         return self._make_request("GET", f"{self.INTEGRATIONS_RESOURCE}/apps")

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]==1.9.3"
+    "crewai[tools]==1.10.1a1"
 ]
 
 [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]==1.9.3"
+    "crewai[tools]==1.10.1a1"
 ]
 
 [project.scripts]

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

@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]>=0.203.1"
+    "crewai[tools]==1.10.1a1"
 ]
 
 [tool.crewai]

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

@@ -63,6 +63,7 @@ from crewai.events.types.logging_events import (
     AgentLogsStartedEvent,
 )
 from crewai.events.types.mcp_events import (
+    MCPConfigFetchFailedEvent,
     MCPConnectionCompletedEvent,
     MCPConnectionFailedEvent,
     MCPConnectionStartedEvent,
@@ -165,6 +166,7 @@ __all__ = [
     "LiteAgentExecutionCompletedEvent",
     "LiteAgentExecutionErrorEvent",
     "LiteAgentExecutionStartedEvent",
+    "MCPConfigFetchFailedEvent",
     "MCPConnectionCompletedEvent",
     "MCPConnectionFailedEvent",
     "MCPConnectionStartedEvent",

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

@@ -68,6 +68,7 @@ from crewai.events.types.logging_events import (
     AgentLogsStartedEvent,
 )
 from crewai.events.types.mcp_events import (
+    MCPConfigFetchFailedEvent,
     MCPConnectionCompletedEvent,
     MCPConnectionFailedEvent,
     MCPConnectionStartedEvent,
@@ -665,6 +666,16 @@ class EventListener(BaseEventListener):
                 event.error_type,
             )
 
+        @crewai_event_bus.on(MCPConfigFetchFailedEvent)
+        def on_mcp_config_fetch_failed(
+            _: Any, event: MCPConfigFetchFailedEvent
+        ) -> None:
+            self.formatter.handle_mcp_config_fetch_failed(
+                event.slug,
+                event.error,
+                event.error_type,
+            )
+
         @crewai_event_bus.on(MCPToolExecutionStartedEvent)
         def on_mcp_tool_execution_started(
             _: Any, event: MCPToolExecutionStartedEvent

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

@@ -67,6 +67,7 @@ from crewai.events.types.llm_guardrail_events import (
     LLMGuardrailStartedEvent,
 )
 from crewai.events.types.mcp_events import (
+    MCPConfigFetchFailedEvent,
     MCPConnectionCompletedEvent,
     MCPConnectionFailedEvent,
     MCPConnectionStartedEvent,
@@ -181,4 +182,5 @@ EventTypes = (
     | MCPToolExecutionStartedEvent
     | MCPToolExecutionCompletedEvent
     | MCPToolExecutionFailedEvent
+    | MCPConfigFetchFailedEvent
 )

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

@@ -83,3 +83,16 @@ class MCPToolExecutionFailedEvent(MCPEvent):
     error_type: str | None = None  # "timeout", "validation", "server_error", etc.
     started_at: datetime | None = None
     failed_at: datetime | None = None
+
+
+class MCPConfigFetchFailedEvent(BaseEvent):
+    """Event emitted when fetching an AMP MCP server config fails.
+
+    This covers cases where the slug is not connected, the API call
+    failed, or native MCP resolution failed after config was fetched.
+    """
+
+    type: str = "mcp_config_fetch_failed"
+    slug: str
+    error: str
+    error_type: str | None = None  # "not_connected", "api_error", "connection_failed"

lib/crewai/src/crewai/events/utils/console_formatter.py

@@ -1512,6 +1512,34 @@ To enable tracing, do any one of these:
         self.print(panel)
         self.print()
 
+    def handle_mcp_config_fetch_failed(
+        self,
+        slug: str,
+        error: str = "",
+        error_type: str | None = None,
+    ) -> None:
+        """Handle MCP config fetch failed event (AMP resolution failures)."""
+        if not self.verbose:
+            return
+
+        content = Text()
+        content.append("MCP Config Fetch Failed\n\n", style="red bold")
+        content.append("Server: ", style="white")
+        content.append(f"{slug}\n", style="red")
+
+        if error_type:
+            content.append("Error Type: ", style="white")
+            content.append(f"{error_type}\n", style="red")
+
+        if error:
+            content.append("\nError: ", style="white bold")
+            error_preview = error[:500] + "..." if len(error) > 500 else error
+            content.append(f"{error_preview}\n", style="red")
+
+        panel = self.create_panel(content, "❌ MCP Config Failed", "red")
+        self.print(panel)
+        self.print()
+
     def handle_mcp_tool_execution_started(
         self,
         server_name: str,

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

@@ -66,6 +66,7 @@ from crewai.utilities.agent_utils import (
     has_reached_max_iterations,
     is_context_length_exceeded,
     is_inside_event_loop,
+    parse_tool_call_args,
     process_llm_response,
     track_delegation_if_needed,
 )
@@ -848,13 +849,9 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
         call_id, func_name, func_args = info
 
         # Parse arguments
-        if isinstance(func_args, str):
-            try:
-                args_dict = json.loads(func_args)
-            except json.JSONDecodeError:
-                args_dict = {}
-        else:
-            args_dict = func_args
+        args_dict, parse_error = parse_tool_call_args(func_args, func_name, call_id)
+        if parse_error is not None:
+            return parse_error
 
         # Get agent_key for event tracking
         agent_key = getattr(self.agent, "key", "unknown") if self.agent else "unknown"

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

@@ -16,7 +16,7 @@ from collections.abc import (
     Sequence,
     ValuesView,
 )
-from concurrent.futures import Future
+from concurrent.futures import Future, ThreadPoolExecutor
 import copy
 import enum
 import inspect
@@ -1739,7 +1739,12 @@ class Flow(Generic[T], metaclass=FlowMeta):
         async def _run_flow() -> Any:
             return await self.kickoff_async(inputs, input_files)
 
-        return asyncio.run(_run_flow())
+        try:
+            asyncio.get_running_loop()
+            with ThreadPoolExecutor(max_workers=1) as pool:
+                return pool.submit(asyncio.run, _run_flow()).result()
+        except RuntimeError:
+            return asyncio.run(_run_flow())
 
     async def kickoff_async(
         self,

lib/crewai/src/crewai/lite_agent.py

@@ -2,10 +2,10 @@ from __future__ import annotations
 
 import asyncio
 from collections.abc import Callable
-import time
 from functools import wraps
 import inspect
 import json
+import time
 from types import MethodType
 from typing import (
     TYPE_CHECKING,
@@ -49,15 +49,20 @@ from crewai.events.types.agent_events import (
     LiteAgentExecutionErrorEvent,
     LiteAgentExecutionStartedEvent,
 )
+from crewai.events.types.logging_events import AgentLogsExecutionEvent
 from crewai.events.types.memory_events import (
     MemoryRetrievalCompletedEvent,
     MemoryRetrievalFailedEvent,
     MemoryRetrievalStartedEvent,
 )
-from crewai.events.types.logging_events import AgentLogsExecutionEvent
 from crewai.flow.flow_trackable import FlowTrackable
 from crewai.hooks.llm_hooks import get_after_llm_call_hooks, get_before_llm_call_hooks
-from crewai.hooks.types import AfterLLMCallHookType, BeforeLLMCallHookType
+from crewai.hooks.types import (
+    AfterLLMCallHookCallable,
+    AfterLLMCallHookType,
+    BeforeLLMCallHookCallable,
+    BeforeLLMCallHookType,
+)
 from crewai.lite_agent_output import LiteAgentOutput
 from crewai.llm import LLM
 from crewai.llms.base_llm import BaseLLM
@@ -270,11 +275,11 @@ class LiteAgent(FlowTrackable, BaseModel):
     _guardrail: GuardrailCallable | None = PrivateAttr(default=None)
     _guardrail_retry_count: int = PrivateAttr(default=0)
     _callbacks: list[TokenCalcHandler] = PrivateAttr(default_factory=list)
-    _before_llm_call_hooks: list[BeforeLLMCallHookType] = PrivateAttr(
-        default_factory=get_before_llm_call_hooks
+    _before_llm_call_hooks: list[BeforeLLMCallHookType | BeforeLLMCallHookCallable] = (
+        PrivateAttr(default_factory=get_before_llm_call_hooks)
     )
-    _after_llm_call_hooks: list[AfterLLMCallHookType] = PrivateAttr(
-        default_factory=get_after_llm_call_hooks
+    _after_llm_call_hooks: list[AfterLLMCallHookType | AfterLLMCallHookCallable] = (
+        PrivateAttr(default_factory=get_after_llm_call_hooks)
     )
     _memory: Any = PrivateAttr(default=None)
 
@@ -440,12 +445,16 @@ class LiteAgent(FlowTrackable, BaseModel):
         return self.role
 
     @property
-    def before_llm_call_hooks(self) -> list[BeforeLLMCallHookType]:
+    def before_llm_call_hooks(
+        self,
+    ) -> list[BeforeLLMCallHookType | BeforeLLMCallHookCallable]:
         """Get the before_llm_call hooks for this agent."""
         return self._before_llm_call_hooks
 
     @property
-    def after_llm_call_hooks(self) -> list[AfterLLMCallHookType]:
+    def after_llm_call_hooks(
+        self,
+    ) -> list[AfterLLMCallHookType | AfterLLMCallHookCallable]:
         """Get the after_llm_call hooks for this agent."""
         return self._after_llm_call_hooks
 
@@ -482,11 +491,12 @@ class LiteAgent(FlowTrackable, BaseModel):
         # Inject memory tools once if memory is configured (mirrors Agent._prepare_kickoff)
         if self._memory is not None:
             from crewai.tools.memory_tools import create_memory_tools
-            from crewai.utilities.agent_utils import sanitize_tool_name
+            from crewai.utilities.string_utils import sanitize_tool_name
 
             existing_names = {sanitize_tool_name(t.name) for t in self._parsed_tools}
             memory_tools = [
-                mt for mt in create_memory_tools(self._memory)
+                mt
+                for mt in create_memory_tools(self._memory)
                 if sanitize_tool_name(mt.name) not in existing_names
             ]
             if memory_tools:
@@ -565,9 +575,10 @@ class LiteAgent(FlowTrackable, BaseModel):
             if memory_block:
                 formatted = self.i18n.slice("memory").format(memory=memory_block)
                 if self._messages and self._messages[0].get("role") == "system":
-                    self._messages[0]["content"] = (
-                        self._messages[0].get("content", "") + "\n\n" + formatted
-                    )
+                    existing_content = self._messages[0].get("content", "")
+                    if not isinstance(existing_content, str):
+                        existing_content = ""
+                    self._messages[0]["content"] = existing_content + "\n\n" + formatted
             crewai_event_bus.emit(
                 self,
                 event=MemoryRetrievalCompletedEvent(
@@ -588,16 +599,12 @@ class LiteAgent(FlowTrackable, BaseModel):
             )
 
     def _save_to_memory(self, output_text: str) -> None:
-        """Extract discrete memories from the run and remember each. No-op if _memory is None."""
-        if self._memory is None:
+        """Extract discrete memories from the run and remember each. No-op if _memory is None or read-only."""
+        if self._memory is None or getattr(self._memory, "_read_only", False):
             return
         input_str = self._get_last_user_content() or "User request"
         try:
-            raw = (
-                f"Input: {input_str}\n"
-                f"Agent: {self.role}\n"
-                f"Result: {output_text}"
-            )
+            raw = f"Input: {input_str}\nAgent: {self.role}\nResult: {output_text}"
             extracted = self._memory.extract_memories(raw)
             if extracted:
                 self._memory.remember_many(extracted, agent_role=self.role)
@@ -622,13 +629,20 @@ class LiteAgent(FlowTrackable, BaseModel):
         )
 
         # Execute the agent using invoke loop
-        agent_finish = self._invoke_loop()
+        active_response_format = response_format or self.response_format
+        agent_finish = self._invoke_loop(response_model=active_response_format)
         if self._memory is not None:
-            self._save_to_memory(agent_finish.output)
+            output_text = (
+                agent_finish.output.model_dump_json()
+                if isinstance(agent_finish.output, BaseModel)
+                else agent_finish.output
+            )
+            self._save_to_memory(output_text)
         formatted_result: BaseModel | None = None
 
-        active_response_format = response_format or self.response_format
-        if active_response_format:
+        if isinstance(agent_finish.output, BaseModel):
+            formatted_result = agent_finish.output
+        elif active_response_format:
             try:
                 model_schema = generate_model_description(active_response_format)
                 schema = json.dumps(model_schema, indent=2)
@@ -660,8 +674,13 @@ class LiteAgent(FlowTrackable, BaseModel):
             usage_metrics = self._token_process.get_summary()
 
         # Create output
+        raw_output = (
+            agent_finish.output.model_dump_json()
+            if isinstance(agent_finish.output, BaseModel)
+            else agent_finish.output
+        )
         output = LiteAgentOutput(
-            raw=agent_finish.output,
+            raw=raw_output,
             pydantic=formatted_result,
             agent_role=self.role,
             usage_metrics=usage_metrics.model_dump() if usage_metrics else None,
@@ -838,10 +857,15 @@ class LiteAgent(FlowTrackable, BaseModel):
 
         return formatted_messages
 
-    def _invoke_loop(self) -> AgentFinish:
+    def _invoke_loop(
+        self, response_model: type[BaseModel] | None = None
+    ) -> AgentFinish:
         """
         Run the agent's thought process until it reaches a conclusion or max iterations.
 
+        Args:
+            response_model: Optional Pydantic model for native structured output.
+
         Returns:
             AgentFinish: The final result of the agent execution.
         """
@@ -870,12 +894,19 @@ class LiteAgent(FlowTrackable, BaseModel):
                         printer=self._printer,
                         from_agent=self,
                         executor_context=self,
+                        response_model=response_model,
                         verbose=self.verbose,
                     )
 
                 except Exception as e:
                     raise e
 
+                if isinstance(answer, BaseModel):
+                    formatted_answer = AgentFinish(
+                        thought="", output=answer, text=answer.model_dump_json()
+                    )
+                    break
+
                 formatted_answer = process_llm_response(
                     cast(str, answer), self.use_stop_words
                 )
@@ -901,7 +932,7 @@ class LiteAgent(FlowTrackable, BaseModel):
                     )
 
                 self._append_message(formatted_answer.text, role="assistant")
-            except OutputParserError as e:  # noqa: PERF203
+            except OutputParserError as e:
                 if self.verbose:
                     self._printer.print(
                         content="Failed to parse LLM output. Retrying...",

lib/crewai/src/crewai/llm.py

@@ -427,7 +427,7 @@ class LLM(BaseLLM):
                 f"installed.\n\n"
                 f"To fix this, either:\n"
                 f"  1. Install LiteLLM for broad model support: "
-                f"uv add litellm\n"
+                f"uv add 'crewai[litellm]'\n"
                 f"or\n"
                 f"pip install litellm\n\n"
                 f"For more details, see: "

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

@@ -234,7 +234,7 @@ class BedrockCompletion(BaseLLM):
         aws_access_key_id: str | None = None,
         aws_secret_access_key: str | None = None,
         aws_session_token: str | None = None,
-        region_name: str = "us-east-1",
+        region_name: str | None = None,
         temperature: float | None = None,
         max_tokens: int | None = None,
         top_p: float | None = None,
@@ -287,15 +287,6 @@ class BedrockCompletion(BaseLLM):
             **kwargs,
         )
 
-        # Initialize Bedrock client with proper configuration
-        session = Session(
-            aws_access_key_id=aws_access_key_id or os.getenv("AWS_ACCESS_KEY_ID"),
-            aws_secret_access_key=aws_secret_access_key
-            or os.getenv("AWS_SECRET_ACCESS_KEY"),
-            aws_session_token=aws_session_token or os.getenv("AWS_SESSION_TOKEN"),
-            region_name=region_name,
-        )
-
         # Configure client with timeouts and retries following AWS best practices
         config = Config(
             read_timeout=300,
@@ -306,8 +297,12 @@ class BedrockCompletion(BaseLLM):
             tcp_keepalive=True,
         )
 
-        self.client = session.client("bedrock-runtime", config=config)
-        self.region_name = region_name
+        self.region_name = (
+            region_name
+            or os.getenv("AWS_DEFAULT_REGION")
+            or os.getenv("AWS_REGION_NAME")
+            or "us-east-1"
+        )
 
         self.aws_access_key_id = aws_access_key_id or os.getenv("AWS_ACCESS_KEY_ID")
         self.aws_secret_access_key = aws_secret_access_key or os.getenv(
@@ -315,6 +310,16 @@ class BedrockCompletion(BaseLLM):
         )
         self.aws_session_token = aws_session_token or os.getenv("AWS_SESSION_TOKEN")
 
+        # Initialize Bedrock client with proper configuration
+        session = Session(
+            aws_access_key_id=self.aws_access_key_id,
+            aws_secret_access_key=self.aws_secret_access_key,
+            aws_session_token=self.aws_session_token,
+            region_name=self.region_name,
+        )
+
+        self.client = session.client("bedrock-runtime", config=config)
+
         self._async_exit_stack = AsyncExitStack() if AIOBOTOCORE_AVAILABLE else None
         self._async_client_initialized = False
 

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

@@ -894,7 +894,7 @@ class GeminiCompletion(BaseLLM):
         content = self._extract_text_from_response(response)
 
         effective_response_model = None if self.tools else response_model
-        if not effective_response_model:
+        if not response_model:
             content = self._apply_stop_words(content)
 
         return self._finalize_completion_response(

lib/crewai/src/crewai/mcp/__init__.py

@@ -18,6 +18,7 @@ from crewai.mcp.filters import (
     create_dynamic_tool_filter,
     create_static_tool_filter,
 )
+from crewai.mcp.tool_resolver import MCPToolResolver
 from crewai.mcp.transports.base import BaseTransport, TransportType
 
 
@@ -28,6 +29,7 @@ __all__ = [
     "MCPServerHTTP",
     "MCPServerSSE",
     "MCPServerStdio",
+    "MCPToolResolver",
     "StaticToolFilter",
     "ToolFilter",
     "ToolFilterContext",

lib/crewai/src/crewai/mcp/client.py

@@ -6,7 +6,7 @@ from contextlib import AsyncExitStack
 from datetime import datetime
 import logging
 import time
-from typing import Any
+from typing import Any, NamedTuple
 
 from typing_extensions import Self
 
@@ -34,6 +34,13 @@ from crewai.mcp.transports.stdio import StdioTransport
 from crewai.utilities.string_utils import sanitize_tool_name
 
 
+class _MCPToolResult(NamedTuple):
+    """Internal result from an MCP tool call, carrying the ``isError`` flag."""
+
+    content: str
+    is_error: bool
+
+
 # MCP Connection timeout constants (in seconds)
 MCP_CONNECTION_TIMEOUT = 30  # Increased for slow servers
 MCP_TOOL_EXECUTION_TIMEOUT = 30
@@ -420,6 +427,7 @@ class MCPClient:
         return [
             {
                 "name": sanitize_tool_name(tool.name),
+                "original_name": tool.name,
                 "description": getattr(tool, "description", ""),
                 "inputSchema": getattr(tool, "inputSchema", {}),
             }
@@ -461,29 +469,46 @@ class MCPClient:
         )
 
         try:
-            result = await self._retry_operation(
+            tool_result: _MCPToolResult = await self._retry_operation(
                 lambda: self._call_tool_impl(tool_name, cleaned_arguments),
                 timeout=self.execution_timeout,
             )
 
-            completed_at = datetime.now()
-            execution_duration_ms = (completed_at - started_at).total_seconds() * 1000
-            crewai_event_bus.emit(
-                self,
-                MCPToolExecutionCompletedEvent(
-                    server_name=server_name,
-                    server_url=server_url,
-                    transport_type=transport_type,
-                    tool_name=tool_name,
-                    tool_args=cleaned_arguments,
-                    result=result,
-                    started_at=started_at,
-                    completed_at=completed_at,
-                    execution_duration_ms=execution_duration_ms,
-                ),
-            )
+            finished_at = datetime.now()
+            execution_duration_ms = (finished_at - started_at).total_seconds() * 1000
 
-            return result
+            if tool_result.is_error:
+                crewai_event_bus.emit(
+                    self,
+                    MCPToolExecutionFailedEvent(
+                        server_name=server_name,
+                        server_url=server_url,
+                        transport_type=transport_type,
+                        tool_name=tool_name,
+                        tool_args=cleaned_arguments,
+                        error=tool_result.content,
+                        error_type="tool_error",
+                        started_at=started_at,
+                        failed_at=finished_at,
+                    ),
+                )
+            else:
+                crewai_event_bus.emit(
+                    self,
+                    MCPToolExecutionCompletedEvent(
+                        server_name=server_name,
+                        server_url=server_url,
+                        transport_type=transport_type,
+                        tool_name=tool_name,
+                        tool_args=cleaned_arguments,
+                        result=tool_result.content,
+                        started_at=started_at,
+                        completed_at=finished_at,
+                        execution_duration_ms=execution_duration_ms,
+                    ),
+                )
+
+            return tool_result.content
         except Exception as e:
             failed_at = datetime.now()
             error_type = (
@@ -564,23 +589,27 @@ class MCPClient:
 
         return cleaned
 
-    async def _call_tool_impl(self, tool_name: str, arguments: dict[str, Any]) -> Any:
+    async def _call_tool_impl(
+        self, tool_name: str, arguments: dict[str, Any]
+    ) -> _MCPToolResult:
         """Internal implementation of call_tool."""
         result = await asyncio.wait_for(
             self.session.call_tool(tool_name, arguments),
             timeout=self.execution_timeout,
         )
 
+        is_error = getattr(result, "isError", False) or False
+
         # Extract result content
         if hasattr(result, "content") and result.content:
             if isinstance(result.content, list) and len(result.content) > 0:
                 content_item = result.content[0]
                 if hasattr(content_item, "text"):
-                    return str(content_item.text)
-                return str(content_item)
-            return str(result.content)
+                    return _MCPToolResult(str(content_item.text), is_error)
+                return _MCPToolResult(str(content_item), is_error)
+            return _MCPToolResult(str(result.content), is_error)
 
-        return str(result)
+        return _MCPToolResult(str(result), is_error)
 
     async def list_prompts(self) -> list[dict[str, Any]]:
         """List available prompts from MCP server.

lib/crewai/src/crewai/mcp/tool_resolver.py

@@ -0,0 +1,592 @@
+"""MCP tool resolution for CrewAI agents.
+
+This module extracts all MCP-related tool resolution logic from the Agent class
+into a standalone MCPToolResolver. It handles three flavours of MCP reference:
+
+  1. Native configs:   MCPServerStdio / MCPServerHTTP / MCPServerSSE objects.
+  2. HTTPS URLs:       e.g. "https://mcp.example.com/api"
+  3. AMP references:   e.g. "notion" or "notion#search" (legacy "crewai-amp:" prefix also works)
+"""
+
+from __future__ import annotations
+
+import asyncio
+import time
+from typing import TYPE_CHECKING, Any, Final, cast
+from urllib.parse import urlparse
+
+from crewai.mcp.client import MCPClient
+from crewai.mcp.config import (
+    MCPServerConfig,
+    MCPServerHTTP,
+    MCPServerSSE,
+    MCPServerStdio,
+)
+from crewai.mcp.transports.http import HTTPTransport
+from crewai.mcp.transports.sse import SSETransport
+from crewai.mcp.transports.stdio import StdioTransport
+
+
+if TYPE_CHECKING:
+    from crewai.tools.base_tool import BaseTool
+    from crewai.utilities.logger import Logger
+
+MCP_CONNECTION_TIMEOUT: Final[int] = 10
+MCP_TOOL_EXECUTION_TIMEOUT: Final[int] = 30
+MCP_DISCOVERY_TIMEOUT: Final[int] = 15
+MCP_MAX_RETRIES: Final[int] = 3
+
+_mcp_schema_cache: dict[str, Any] = {}
+_cache_ttl: Final[int] = 300  # 5 minutes
+
+
+class MCPToolResolver:
+    """Resolves MCP server references / configs into CrewAI ``BaseTool`` instances.
+
+    Typical lifecycle::
+
+        resolver = MCPToolResolver(agent=my_agent, logger=my_agent._logger)
+        tools = resolver.resolve(my_agent.mcps)
+        # … agent executes tasks using *tools* …
+        resolver.cleanup()
+
+    The resolver owns the MCP client connections it creates and is responsible
+    for tearing them down via :meth:`cleanup`.
+    """
+
+    def __init__(self, agent: Any, logger: Logger) -> None:
+        self._agent = agent
+        self._logger = logger
+        self._clients: list[Any] = []
+
+    @property
+    def clients(self) -> list[Any]:
+        return list(self._clients)
+
+    def resolve(self, mcps: list[str | MCPServerConfig]) -> list[BaseTool]:
+        """Convert MCP server references/configs to CrewAI tools."""
+        all_tools: list[BaseTool] = []
+        amp_refs: list[tuple[str, str | None]] = []
+
+        for mcp_config in mcps:
+            if isinstance(mcp_config, str) and mcp_config.startswith("https://"):
+                all_tools.extend(self._resolve_external(mcp_config))
+            elif isinstance(mcp_config, str):
+                amp_refs.append(self._parse_amp_ref(mcp_config))
+            else:
+                tools, client = self._resolve_native(mcp_config)
+                all_tools.extend(tools)
+                if client:
+                    self._clients.append(client)
+
+        if amp_refs:
+            tools, clients = self._resolve_amp(amp_refs)
+            all_tools.extend(tools)
+            self._clients.extend(clients)
+
+        return all_tools
+
+    def cleanup(self) -> None:
+        """Disconnect all MCP client connections."""
+        if not self._clients:
+            return
+
+        async def _disconnect_all() -> None:
+            for client in self._clients:
+                if client and hasattr(client, "connected") and client.connected:
+                    await client.disconnect()
+
+        try:
+            asyncio.run(_disconnect_all())
+        except Exception as e:
+            self._logger.log("error", f"Error during MCP client cleanup: {e}")
+        finally:
+            self._clients.clear()
+
+    @staticmethod
+    def _parse_amp_ref(mcp_config: str) -> tuple[str, str | None]:
+        """Parse an AMP reference into *(slug, optional tool name)*.
+
+        Accepts both bare slugs (``"notion"``, ``"notion#search"``) and the
+        legacy ``"crewai-amp:notion"`` form.
+        """
+        bare = mcp_config.removeprefix("crewai-amp:")
+        slug, _, specific_tool = bare.partition("#")
+        return slug, specific_tool or None
+
+    def _resolve_amp(
+        self, amp_refs: list[tuple[str, str | None]]
+    ) -> tuple[list[BaseTool], list[Any]]:
+        """Fetch AMP configs in bulk and return their tools and clients.
+
+        Resolves each unique slug only once (single connection per server),
+        then applies per-ref tool filters to select specific tools.
+        """
+        from crewai.events.event_bus import crewai_event_bus
+        from crewai.events.types.mcp_events import MCPConfigFetchFailedEvent
+
+        unique_slugs = list(dict.fromkeys(slug for slug, _ in amp_refs))
+        amp_configs_map = self._fetch_amp_mcp_configs(unique_slugs)
+
+        all_tools: list[BaseTool] = []
+        all_clients: list[Any] = []
+
+        resolved_cache: dict[str, tuple[list[BaseTool], Any | None]] = {}
+
+        for slug in unique_slugs:
+            config_dict = amp_configs_map.get(slug)
+            if not config_dict:
+                crewai_event_bus.emit(
+                    self,
+                    MCPConfigFetchFailedEvent(
+                        slug=slug,
+                        error=f"Config for '{slug}' not found. Make sure it is connected in your account.",
+                        error_type="not_connected",
+                    ),
+                )
+                continue
+
+            mcp_server_config = self._build_mcp_config_from_dict(config_dict)
+
+            try:
+                tools, client = self._resolve_native(mcp_server_config)
+                resolved_cache[slug] = (tools, client)
+                if client:
+                    all_clients.append(client)
+            except Exception as e:
+                crewai_event_bus.emit(
+                    self,
+                    MCPConfigFetchFailedEvent(
+                        slug=slug,
+                        error=str(e),
+                        error_type="connection_failed",
+                    ),
+                )
+
+        for slug, specific_tool in amp_refs:
+            cached = resolved_cache.get(slug)
+            if not cached:
+                continue
+
+            slug_tools, _ = cached
+            if specific_tool:
+                all_tools.extend(
+                    t for t in slug_tools if t.name.endswith(f"_{specific_tool}")
+                )
+            else:
+                all_tools.extend(slug_tools)
+
+        return all_tools, all_clients
+
+    def _fetch_amp_mcp_configs(self, slugs: list[str]) -> dict[str, dict[str, Any]]:
+        """Fetch MCP server configurations via CrewAI+ API.
+
+        Sends a GET request to the CrewAI+ mcps/configs endpoint with
+        comma-separated slugs. CrewAI+ proxies the request to crewai-oauth.
+
+        API-level failures return ``{}``; individual slugs will then
+        surface as ``MCPConfigFetchFailedEvent`` in :meth:`_resolve_amp`.
+        """
+        import httpx
+
+        try:
+            from crewai_tools.tools.crewai_platform_tools.misc import (
+                get_platform_integration_token,
+            )
+
+            from crewai.cli.plus_api import PlusAPI
+
+            plus_api = PlusAPI(api_key=get_platform_integration_token())
+            response = plus_api.get_mcp_configs(slugs)
+
+            if response.status_code == 200:
+                configs: dict[str, dict[str, Any]] = response.json().get("configs", {})
+                return configs
+
+            self._logger.log(
+                "debug",
+                f"Failed to fetch MCP configs: HTTP {response.status_code}",
+            )
+            return {}
+
+        except httpx.HTTPError as e:
+            self._logger.log("debug", f"Failed to fetch MCP configs: {e}")
+            return {}
+        except Exception as e:
+            self._logger.log("debug", f"Cannot fetch AMP MCP configs: {e}")
+            return {}
+
+    def _resolve_external(self, mcp_ref: str) -> list[BaseTool]:
+        """Resolve an HTTPS MCP server URL into tools."""
+        from crewai.tools.mcp_tool_wrapper import MCPToolWrapper
+
+        if "#" in mcp_ref:
+            server_url, specific_tool = mcp_ref.split("#", 1)
+        else:
+            server_url, specific_tool = mcp_ref, None
+
+        server_params = {"url": server_url}
+        server_name = self._extract_server_name(server_url)
+
+        try:
+            tool_schemas = self._get_mcp_tool_schemas(server_params)
+
+            if not tool_schemas:
+                self._logger.log(
+                    "warning", f"No tools discovered from MCP server: {server_url}"
+                )
+                return []
+
+            tools = []
+            for tool_name, schema in tool_schemas.items():
+                if specific_tool and tool_name != specific_tool:
+                    continue
+
+                try:
+                    wrapper = MCPToolWrapper(
+                        mcp_server_params=server_params,
+                        tool_name=tool_name,
+                        tool_schema=schema,
+                        server_name=server_name,
+                    )
+                    tools.append(wrapper)
+                except Exception as e:
+                    self._logger.log(
+                        "warning",
+                        f"Failed to create MCP tool wrapper for {tool_name}: {e}",
+                    )
+                    continue
+
+            if specific_tool and not tools:
+                self._logger.log(
+                    "warning",
+                    f"Specific tool '{specific_tool}' not found on MCP server: {server_url}",
+                )
+
+            return cast(list[BaseTool], tools)
+
+        except Exception as e:
+            self._logger.log(
+                "warning", f"Failed to connect to MCP server {server_url}: {e}"
+            )
+            return []
+
+    def _resolve_native(
+        self, mcp_config: MCPServerConfig
+    ) -> tuple[list[BaseTool], Any | None]:
+        """Resolve an ``MCPServerConfig`` into tools, returning the client for cleanup."""
+        from crewai.tools.base_tool import BaseTool
+        from crewai.tools.mcp_native_tool import MCPNativeTool
+
+        transport: StdioTransport | HTTPTransport | SSETransport
+        if isinstance(mcp_config, MCPServerStdio):
+            transport = StdioTransport(
+                command=mcp_config.command,
+                args=mcp_config.args,
+                env=mcp_config.env,
+            )
+            server_name = f"{mcp_config.command}_{'_'.join(mcp_config.args)}"
+        elif isinstance(mcp_config, MCPServerHTTP):
+            transport = HTTPTransport(
+                url=mcp_config.url,
+                headers=mcp_config.headers,
+                streamable=mcp_config.streamable,
+            )
+            server_name = self._extract_server_name(mcp_config.url)
+        elif isinstance(mcp_config, MCPServerSSE):
+            transport = SSETransport(
+                url=mcp_config.url,
+                headers=mcp_config.headers,
+            )
+            server_name = self._extract_server_name(mcp_config.url)
+        else:
+            raise ValueError(f"Unsupported MCP server config type: {type(mcp_config)}")
+
+        client = MCPClient(
+            transport=transport,
+            cache_tools_list=mcp_config.cache_tools_list,
+        )
+
+        async def _setup_client_and_list_tools() -> list[dict[str, Any]]:
+            try:
+                if not client.connected:
+                    await client.connect()
+
+                tools_list = await client.list_tools()
+
+                try:
+                    await client.disconnect()
+                    await asyncio.sleep(0.1)
+                except Exception as e:
+                    self._logger.log("error", f"Error during disconnect: {e}")
+
+                return tools_list
+            except Exception as e:
+                if client.connected:
+                    await client.disconnect()
+                    await asyncio.sleep(0.1)
+                raise RuntimeError(
+                    f"Error during setup client and list tools: {e}"
+                ) from e
+
+        try:
+            try:
+                asyncio.get_running_loop()
+                import concurrent.futures
+
+                with concurrent.futures.ThreadPoolExecutor() as executor:
+                    future = executor.submit(
+                        asyncio.run, _setup_client_and_list_tools()
+                    )
+                    tools_list = future.result()
+            except RuntimeError:
+                try:
+                    tools_list = asyncio.run(_setup_client_and_list_tools())
+                except RuntimeError as e:
+                    error_msg = str(e).lower()
+                    if "cancel scope" in error_msg or "task" in error_msg:
+                        raise ConnectionError(
+                            "MCP connection failed due to event loop cleanup issues. "
+                            "This may be due to authentication errors or server unavailability."
+                        ) from e
+                except asyncio.CancelledError as e:
+                    raise ConnectionError(
+                        "MCP connection was cancelled. This may indicate an authentication "
+                        "error or server unavailability."
+                    ) from e
+
+            if mcp_config.tool_filter:
+                filtered_tools = []
+                for tool in tools_list:
+                    if callable(mcp_config.tool_filter):
+                        try:
+                            from crewai.mcp.filters import ToolFilterContext
+
+                            context = ToolFilterContext(
+                                agent=self._agent,
+                                server_name=server_name,
+                                run_context=None,
+                            )
+                            if mcp_config.tool_filter(context, tool):  # type: ignore[call-arg, arg-type]
+                                filtered_tools.append(tool)
+                        except (TypeError, AttributeError):
+                            if mcp_config.tool_filter(tool):  # type: ignore[call-arg, arg-type]
+                                filtered_tools.append(tool)
+                    else:
+                        filtered_tools.append(tool)
+                tools_list = filtered_tools
+
+            tools = []
+            for tool_def in tools_list:
+                tool_name = tool_def.get("name", "")
+                original_tool_name = tool_def.get("original_name", tool_name)
+                if not tool_name:
+                    continue
+
+                args_schema = None
+                if tool_def.get("inputSchema"):
+                    args_schema = self._json_schema_to_pydantic(
+                        tool_name, tool_def["inputSchema"]
+                    )
+
+                tool_schema = {
+                    "description": tool_def.get("description", ""),
+                    "args_schema": args_schema,
+                }
+
+                try:
+                    native_tool = MCPNativeTool(
+                        mcp_client=client,
+                        tool_name=tool_name,
+                        tool_schema=tool_schema,
+                        server_name=server_name,
+                        original_tool_name=original_tool_name,
+                    )
+                    tools.append(native_tool)
+                except Exception as e:
+                    self._logger.log("error", f"Failed to create native MCP tool: {e}")
+                    continue
+
+            return cast(list[BaseTool], tools), client
+        except Exception as e:
+            if client.connected:
+                asyncio.run(client.disconnect())
+
+            raise RuntimeError(f"Failed to get native MCP tools: {e}") from e
+
+    @staticmethod
+    def _build_mcp_config_from_dict(
+        config_dict: dict[str, Any],
+    ) -> MCPServerConfig:
+        """Convert a config dict from crewai-oauth into an MCPServerConfig."""
+        config_type = config_dict.get("type", "http")
+
+        if config_type == "sse":
+            return MCPServerSSE(
+                url=config_dict["url"],
+                headers=config_dict.get("headers"),
+                cache_tools_list=config_dict.get("cache_tools_list", False),
+            )
+
+        return MCPServerHTTP(
+            url=config_dict["url"],
+            headers=config_dict.get("headers"),
+            streamable=config_dict.get("streamable", True),
+            cache_tools_list=config_dict.get("cache_tools_list", False),
+        )
+
+    @staticmethod
+    def _extract_server_name(server_url: str) -> str:
+        """Extract clean server name from URL for tool prefixing."""
+        parsed = urlparse(server_url)
+        domain = parsed.netloc.replace(".", "_")
+        path = parsed.path.replace("/", "_").strip("_")
+        return f"{domain}_{path}" if path else domain
+
+    def _get_mcp_tool_schemas(
+        self, server_params: dict[str, Any]
+    ) -> dict[str, dict[str, Any]]:
+        """Get tool schemas from MCP server with caching."""
+        server_url = server_params["url"]
+
+        cache_key = server_url
+        current_time = time.time()
+
+        if cache_key in _mcp_schema_cache:
+            cached_data, cache_time = _mcp_schema_cache[cache_key]
+            if current_time - cache_time < _cache_ttl:
+                self._logger.log(
+                    "debug", f"Using cached MCP tool schemas for {server_url}"
+                )
+                return cached_data  # type: ignore[no-any-return]
+
+        try:
+            schemas = asyncio.run(self._get_mcp_tool_schemas_async(server_params))
+            _mcp_schema_cache[cache_key] = (schemas, current_time)
+            return schemas
+        except Exception as e:
+            self._logger.log(
+                "warning", f"Failed to get MCP tool schemas from {server_url}: {e}"
+            )
+            return {}
+
+    async def _get_mcp_tool_schemas_async(
+        self, server_params: dict[str, Any]
+    ) -> dict[str, dict[str, Any]]:
+        """Async implementation of MCP tool schema retrieval."""
+        server_url = server_params["url"]
+        return await self._retry_mcp_discovery(
+            self._discover_mcp_tools_with_timeout, server_url
+        )
+
+    async def _retry_mcp_discovery(
+        self, operation_func: Any, server_url: str
+    ) -> dict[str, dict[str, Any]]:
+        """Retry MCP discovery with exponential backoff."""
+        last_error = None
+
+        for attempt in range(MCP_MAX_RETRIES):
+            result, error, should_retry = await self._attempt_mcp_discovery(
+                operation_func, server_url
+            )
+
+            if result is not None:
+                return result
+
+            if not should_retry:
+                raise RuntimeError(error)
+
+            last_error = error
+            if attempt < MCP_MAX_RETRIES - 1:
+                wait_time = 2**attempt
+                await asyncio.sleep(wait_time)
+
+        raise RuntimeError(
+            f"Failed to discover MCP tools after {MCP_MAX_RETRIES} attempts: {last_error}"
+        )
+
+    @staticmethod
+    async def _attempt_mcp_discovery(
+        operation_func: Any, server_url: str
+    ) -> tuple[dict[str, dict[str, Any]] | None, str, bool]:
+        """Attempt single MCP discovery; returns *(result, error_message, should_retry)*."""
+        try:
+            result = await operation_func(server_url)
+            return result, "", False
+
+        except ImportError:
+            return (
+                None,
+                "MCP library not available. Please install with: pip install mcp",
+                False,
+            )
+
+        except asyncio.TimeoutError:
+            return (
+                None,
+                f"MCP discovery timed out after {MCP_DISCOVERY_TIMEOUT} seconds",
+                True,
+            )
+
+        except Exception as e:
+            error_str = str(e).lower()
+
+            if "authentication" in error_str or "unauthorized" in error_str:
+                return None, f"Authentication failed for MCP server: {e!s}", False
+            if "connection" in error_str or "network" in error_str:
+                return None, f"Network connection failed: {e!s}", True
+            if "json" in error_str or "parsing" in error_str:
+                return None, f"Server response parsing error: {e!s}", True
+            return None, f"MCP discovery error: {e!s}", False
+
+    async def _discover_mcp_tools_with_timeout(
+        self, server_url: str
+    ) -> dict[str, dict[str, Any]]:
+        """Discover MCP tools with timeout wrapper."""
+        return await asyncio.wait_for(
+            self._discover_mcp_tools(server_url), timeout=MCP_DISCOVERY_TIMEOUT
+        )
+
+    async def _discover_mcp_tools(self, server_url: str) -> dict[str, dict[str, Any]]:
+        """Discover tools from an MCP server (HTTPS / streamable-HTTP path)."""
+        from mcp import ClientSession
+        from mcp.client.streamable_http import streamablehttp_client
+
+        from crewai.utilities.string_utils import sanitize_tool_name
+
+        async with streamablehttp_client(server_url) as (read, write, _):
+            async with ClientSession(read, write) as session:
+                await asyncio.wait_for(
+                    session.initialize(), timeout=MCP_CONNECTION_TIMEOUT
+                )
+
+                tools_result = await asyncio.wait_for(
+                    session.list_tools(),
+                    timeout=MCP_DISCOVERY_TIMEOUT - MCP_CONNECTION_TIMEOUT,
+                )
+
+                schemas = {}
+                for tool in tools_result.tools:
+                    args_schema = None
+                    if hasattr(tool, "inputSchema") and tool.inputSchema:
+                        args_schema = self._json_schema_to_pydantic(
+                            sanitize_tool_name(tool.name), tool.inputSchema
+                        )
+
+                    schemas[sanitize_tool_name(tool.name)] = {
+                        "description": getattr(tool, "description", ""),
+                        "args_schema": args_schema,
+                    }
+                return schemas
+
+    @staticmethod
+    def _json_schema_to_pydantic(tool_name: str, json_schema: dict[str, Any]) -> type:
+        """Convert JSON Schema to a Pydantic model for tool arguments."""
+        from crewai.utilities.pydantic_schema_utils import create_model_from_schema
+
+        model_name = f"{tool_name.replace('-', '_').replace(' ', '_')}Schema"
+        return create_model_from_schema(
+            json_schema,
+            model_name=model_name,
+            enrich_descriptions=True,
+        )

lib/crewai/src/crewai/memory/__init__.py

@@ -1,6 +1,14 @@
-"""Memory module: unified Memory with LLM analysis and pluggable storage."""
+"""Memory module: unified Memory with LLM analysis and pluggable storage.
+
+Heavy dependencies are lazily imported so that
+``import crewai`` does not initialise at runtime — critical for
+Celery pre-fork and similar deployment patterns.
+"""
+
+from __future__ import annotations
+
+from typing import Any
 
-from crewai.memory.encoding_flow import EncodingFlow
 from crewai.memory.memory_scope import MemoryScope, MemorySlice
 from crewai.memory.types import (
     MemoryMatch,
@@ -10,7 +18,24 @@ from crewai.memory.types import (
     embed_text,
     embed_texts,
 )
-from crewai.memory.unified_memory import Memory
+
+_LAZY_IMPORTS: dict[str, tuple[str, str]] = {
+    "Memory": ("crewai.memory.unified_memory", "Memory"),
+    "EncodingFlow": ("crewai.memory.encoding_flow", "EncodingFlow"),
+}
+
+
+def __getattr__(name: str) -> Any:
+    """Lazily import Memory / EncodingFlow to avoid pulling in lancedb at import time."""
+    if name in _LAZY_IMPORTS:
+        import importlib
+
+        module_path, attr = _LAZY_IMPORTS[name]
+        mod = importlib.import_module(module_path)
+        val = getattr(mod, attr)
+        globals()[name] = val
+        return val
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
 
 
 __all__ = [

lib/crewai/src/crewai/memory/memory_scope.py

@@ -145,7 +145,7 @@ class MemoryScope:
 
 
 class MemorySlice:
-    """View over multiple scopes: recall searches all, remember requires explicit scope unless read_only."""
+    """View over multiple scopes: recall searches all, remember is a no-op when read_only."""
 
     def __init__(
         self,
@@ -160,7 +160,7 @@ class MemorySlice:
             memory: The underlying Memory instance.
             scopes: List of scope paths to include.
             categories: Optional category filter for recall.
-            read_only: If True, remember() raises PermissionError.
+            read_only: If True, remember() is a silent no-op.
         """
         self._memory = memory
         self._scopes = [s.rstrip("/") or "/" for s in scopes]
@@ -176,10 +176,10 @@ class MemorySlice:
         importance: float | None = None,
         source: str | None = None,
         private: bool = False,
-    ) -> MemoryRecord:
-        """Remember into an explicit scope. Required when read_only=False."""
+    ) -> MemoryRecord | None:
+        """Remember into an explicit scope. No-op when read_only=True."""
         if self._read_only:
-            raise PermissionError("This MemorySlice is read-only")
+            return None
         return self._memory.remember(
             content,
             scope=scope,

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

@@ -53,6 +53,7 @@ class LanceDBStorage:
         path: str | Path | None = None,
         table_name: str = "memories",
         vector_dim: int | None = None,
+        compact_every: int = 100,
     ) -> None:
         """Initialize LanceDB storage.
 
@@ -64,6 +65,10 @@ class LanceDBStorage:
             vector_dim: Dimensionality of the embedding vector. When ``None``
                   (default), the dimension is auto-detected from the existing
                   table schema or from the first saved embedding.
+            compact_every: Number of ``save()`` calls between automatic
+                  background compactions.  Each ``save()`` creates one new
+                  fragment file; compaction merges them, keeping query
+                  performance consistent.  Set to 0 to disable.
         """
         if path is None:
             storage_dir = os.environ.get("CREWAI_STORAGE_DIR")
@@ -78,6 +83,22 @@ class LanceDBStorage:
         self._table_name = table_name
         self._db = lancedb.connect(str(self._path))
 
+        # On macOS and Linux the default per-process open-file limit is 256.
+        # A LanceDB table stores one file per fragment (one fragment per save()
+        # call by default).  With hundreds of fragments, a single full-table
+        # scan opens all of them simultaneously, exhausting the limit.
+        # Raise it proactively so scans on large tables never hit OS error 24.
+        try:
+            import resource
+            soft, hard = resource.getrlimit(resource.RLIMIT_NOFILE)
+            if soft < 4096:
+                resource.setrlimit(resource.RLIMIT_NOFILE, (min(hard, 4096), hard))
+        except Exception:  # noqa: S110
+            pass  # Windows or already at the max hard limit — safe to ignore
+
+        self._compact_every = compact_every
+        self._save_count = 0
+
         # Get or create a shared write lock for this database path.
         resolved = str(self._path.resolve())
         with LanceDBStorage._path_locks_guard:
@@ -91,6 +112,11 @@ class LanceDBStorage:
         try:
             self._table: lancedb.table.Table | None = self._db.open_table(self._table_name)
             self._vector_dim: int = self._infer_dim_from_table(self._table)
+            # Best-effort: create the scope index if it doesn't exist yet.
+            self._ensure_scope_index()
+            # Compact in the background if the table has accumulated many
+            # fragments from previous runs (each save() creates one).
+            self._compact_if_needed()
         except Exception:
             self._table = None
             self._vector_dim = vector_dim or 0  # 0 = not yet known
@@ -178,6 +204,56 @@ class LanceDBStorage:
         table.delete("id = '__schema_placeholder__'")
         return table
 
+    def _ensure_scope_index(self) -> None:
+        """Create a BTREE scalar index on the ``scope`` column if not present.
+
+        A scalar index lets LanceDB skip a full table scan when filtering by
+        scope prefix, which is the hot path for ``list_records``,
+        ``get_scope_info``, and ``list_scopes``.  The call is best-effort:
+        if the table is empty or the index already exists the exception is
+        swallowed silently.
+        """
+        if self._table is None:
+            return
+        try:
+            self._table.create_scalar_index("scope", index_type="BTREE", replace=False)
+        except Exception:  # noqa: S110
+            pass  # index already exists, table empty, or unsupported version
+
+    # ------------------------------------------------------------------
+    # Automatic background compaction
+    # ------------------------------------------------------------------
+
+    def _compact_if_needed(self) -> None:
+        """Spawn a background compaction on startup.
+
+        Called whenever an existing table is opened so that fragments
+        accumulated in previous sessions are silently merged before the
+        first query.  ``optimize()`` returns quickly when the table is
+        already compact, so the cost is negligible in the common case.
+        """
+        if self._table is None or self._compact_every <= 0:
+            return
+        self._compact_async()
+
+    def _compact_async(self) -> None:
+        """Fire-and-forget: compact the table in a daemon background thread."""
+        threading.Thread(
+            target=self._compact_safe,
+            daemon=True,
+            name="lancedb-compact",
+        ).start()
+
+    def _compact_safe(self) -> None:
+        """Run ``table.optimize()`` in a background thread, absorbing errors."""
+        try:
+            if self._table is not None:
+                self._table.optimize()
+                # Refresh the scope index so new fragments are covered.
+                self._ensure_scope_index()
+        except Exception:
+            _logger.debug("LanceDB background compaction failed", exc_info=True)
+
     def _ensure_table(self, vector_dim: int | None = None) -> lancedb.table.Table:
         """Return the table, creating it lazily if needed.
 
@@ -239,6 +315,7 @@ class LanceDBStorage:
             if r.embedding and len(r.embedding) > 0:
                 dim = len(r.embedding)
                 break
+        is_new_table = self._table is None
         with self._write_lock:
             self._ensure_table(vector_dim=dim)
             rows = [self._record_to_row(r) for r in records]
@@ -246,6 +323,13 @@ class LanceDBStorage:
                 if r["vector"] is None or len(r["vector"]) != self._vector_dim:
                     r["vector"] = [0.0] * self._vector_dim
             self._retry_write("add", rows)
+        # Create the scope index on the first save so it covers the initial dataset.
+        if is_new_table:
+            self._ensure_scope_index()
+        # Auto-compact every N saves so fragment files don't pile up.
+        self._save_count += 1
+        if self._compact_every > 0 and self._save_count % self._compact_every == 0:
+            self._compact_async()
 
     def update(self, record: MemoryRecord) -> None:
         """Update a record by ID. Preserves created_at, updates last_accessed."""
@@ -261,6 +345,10 @@ class LanceDBStorage:
     def touch_records(self, record_ids: list[str]) -> None:
         """Update last_accessed to now for the given record IDs.
 
+        Uses a single batch ``table.update()`` call instead of N
+        delete-and-re-add cycles, which is both faster and avoids
+        unnecessary write amplification.
+
         Args:
             record_ids: IDs of records to touch.
         """
@@ -268,25 +356,20 @@ class LanceDBStorage:
             return
         with self._write_lock:
             now = datetime.utcnow().isoformat()
-            for rid in record_ids:
-                safe_id = str(rid).replace("'", "''")
-                rows = (
-                    self._table.search([0.0] * self._vector_dim)
-                    .where(f"id = '{safe_id}'")
-                    .limit(1)
-                    .to_list()
-                )
-                if rows:
-                    rows[0]["last_accessed"] = now
-                    self._retry_write("delete", f"id = '{safe_id}'")
-                    self._retry_write("add", [rows[0]])
+            safe_ids = [str(rid).replace("'", "''") for rid in record_ids]
+            ids_expr = ", ".join(f"'{rid}'" for rid in safe_ids)
+            self._retry_write(
+                "update",
+                where=f"id IN ({ids_expr})",
+                values={"last_accessed": now},
+            )
 
     def get_record(self, record_id: str) -> MemoryRecord | None:
         """Return a single record by ID, or None if not found."""
         if self._table is None:
             return None
         safe_id = str(record_id).replace("'", "''")
-        rows = self._table.search([0.0] * self._vector_dim).where(f"id = '{safe_id}'").limit(1).to_list()
+        rows = self._table.search().where(f"id = '{safe_id}'").limit(1).to_list()
         if not rows:
             return None
         return self._row_to_record(rows[0])
@@ -374,13 +457,31 @@ class LanceDBStorage:
             self._retry_write("delete", where_expr)
             return before - self._table.count_rows()
 
-    def _scan_rows(self, scope_prefix: str | None = None, limit: int = _SCAN_ROWS_LIMIT) -> list[dict[str, Any]]:
-        """Scan rows optionally filtered by scope prefix."""
+    def _scan_rows(
+        self,
+        scope_prefix: str | None = None,
+        limit: int = _SCAN_ROWS_LIMIT,
+        columns: list[str] | None = None,
+    ) -> list[dict[str, Any]]:
+        """Scan rows optionally filtered by scope prefix.
+
+        Uses a full table scan (no vector query) so the limit is applied after
+        the scope filter, not to ANN candidates before filtering.
+
+        Args:
+            scope_prefix: Optional scope path prefix to filter by.
+            limit: Maximum number of rows to return (applied after filtering).
+            columns: Optional list of column names to fetch.  Pass only the
+                columns you need for metadata operations to avoid reading the
+                heavy ``vector`` column unnecessarily.
+        """
         if self._table is None:
             return []
-        q = self._table.search([0.0] * self._vector_dim)
+        q = self._table.search()
         if scope_prefix is not None and scope_prefix.strip("/"):
             q = q.where(f"scope LIKE '{scope_prefix.rstrip('/')}%'")
+        if columns is not None:
+            q = q.select(columns)
         return q.limit(limit).to_list()
 
     def list_records(
@@ -406,7 +507,10 @@ class LanceDBStorage:
         prefix = scope if scope != "/" else ""
         if prefix and not prefix.startswith("/"):
             prefix = "/" + prefix
-        rows = self._scan_rows(prefix or None)
+        rows = self._scan_rows(
+            prefix or None,
+            columns=["scope", "categories_str", "created_at"],
+        )
         if not rows:
             return ScopeInfo(
                 path=scope or "/",
@@ -453,7 +557,7 @@ class LanceDBStorage:
     def list_scopes(self, parent: str = "/") -> list[str]:
         parent = parent.rstrip("/") or ""
         prefix = (parent + "/") if parent else "/"
-        rows = self._scan_rows(prefix if prefix != "/" else None)
+        rows = self._scan_rows(prefix if prefix != "/" else None, columns=["scope"])
         children: set[str] = set()
         for row in rows:
             sc = str(row.get("scope", ""))
@@ -465,7 +569,7 @@ class LanceDBStorage:
         return sorted(children)
 
     def list_categories(self, scope_prefix: str | None = None) -> dict[str, int]:
-        rows = self._scan_rows(scope_prefix)
+        rows = self._scan_rows(scope_prefix, columns=["categories_str"])
         counts: dict[str, int] = {}
         for row in rows:
             cat_str = row.get("categories_str") or "[]"
@@ -498,6 +602,21 @@ class LanceDBStorage:
         if prefix:
             self._table.delete(f"scope >= '{prefix}' AND scope < '{prefix}/\uFFFF'")
 
+    def optimize(self) -> None:
+        """Compact the table synchronously and refresh the scope index.
+
+        Under normal usage this is called automatically in the background
+        (every ``compact_every`` saves and on startup when the table is
+        fragmented).  Call this explicitly only when you need the compaction
+        to be complete before the next operation — for example immediately
+        after a large bulk import, before a latency-sensitive recall.
+        It is a no-op if the table does not exist.
+        """
+        if self._table is None:
+            return
+        self._table.optimize()
+        self._ensure_scope_index()
+
     async def asave(self, records: list[MemoryRecord]) -> None:
         self.save(records)
 

lib/crewai/src/crewai/memory/types.py

@@ -87,6 +87,22 @@ class MemoryMatch(BaseModel):
         description="Information the system looked for but could not find.",
     )
 
+    def format(self) -> str:
+        """Format this match as a human-readable string including metadata.
+
+        Returns:
+            A multi-line string with score, content, categories, and non-empty
+            metadata fields.
+        """
+        lines = [f"- (score={self.score:.2f}) {self.record.content}"]
+        if self.record.categories:
+            lines.append(f"  categories: {', '.join(self.record.categories)}")
+        if self.record.metadata:
+            for key, value in self.record.metadata.items():
+                if value is not None:
+                    lines.append(f"  {key}: {value}")
+        return "\n".join(lines)
+
 
 class ScopeInfo(BaseModel):
     """Information about a scope in the memory hierarchy."""
@@ -291,7 +307,7 @@ def embed_text(embedder: Any, text: str) -> list[float]:
         return []
     first = result[0]
     if hasattr(first, "tolist"):
-        return first.tolist()
+        return list(first.tolist())
     if isinstance(first, list):
         return [float(x) for x in first]
     return list(first)

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

@@ -6,7 +6,7 @@ from concurrent.futures import Future, ThreadPoolExecutor
 from datetime import datetime
 import threading
 import time
-from typing import Any, Literal
+from typing import TYPE_CHECKING, Any, Literal
 
 from crewai.events.event_bus import crewai_event_bus
 from crewai.events.types.memory_events import (
@@ -21,7 +21,6 @@ from crewai.llms.base_llm import BaseLLM
 from crewai.memory.analyze import extract_memories_from_content
 from crewai.memory.recall_flow import RecallFlow
 from crewai.memory.storage.backend import StorageBackend
-from crewai.memory.storage.lancedb_storage import LanceDBStorage
 from crewai.memory.types import (
     MemoryConfig,
     MemoryMatch,
@@ -30,13 +29,20 @@ from crewai.memory.types import (
     compute_composite_score,
     embed_text,
 )
+from crewai.rag.embeddings.factory import build_embedder
+from crewai.rag.embeddings.providers.openai.types import OpenAIProviderSpec
 
 
-def _default_embedder() -> Any:
+if TYPE_CHECKING:
+    from chromadb.utils.embedding_functions.openai_embedding_function import (
+        OpenAIEmbeddingFunction,
+    )
+
+
+def _default_embedder() -> OpenAIEmbeddingFunction:
     """Build default OpenAI embedder for memory."""
-    from crewai.rag.embeddings.factory import build_embedder
-
-    return build_embedder({"provider": "openai", "config": {}})
+    spec: OpenAIProviderSpec = {"provider": "openai", "config": {}}
+    return build_embedder(spec)
 
 
 class Memory:
@@ -88,6 +94,10 @@ class Memory:
         # Queries shorter than this skip LLM analysis (saving ~1-3s).
         # Longer queries (full task descriptions) benefit from LLM distillation.
         query_analysis_threshold: int = 200,
+        # When True, all write operations (remember, remember_many) are silently
+        # skipped. Useful for sharing a read-only view of memory across agents
+        # without any of them persisting new memories.
+        read_only: bool = False,
     ) -> None:
         """Initialize Memory.
 
@@ -107,7 +117,9 @@ class Memory:
             complex_query_threshold: For complex queries, explore deeper below this confidence.
             exploration_budget: Number of LLM-driven exploration rounds during deep recall.
             query_analysis_threshold: Queries shorter than this skip LLM analysis during deep recall.
+            read_only: If True, remember() and remember_many() are silent no-ops.
         """
+        self._read_only = read_only
         self._config = MemoryConfig(
             recency_weight=recency_weight,
             semantic_weight=semantic_weight,
@@ -130,14 +142,15 @@ class Memory:
         self._llm_instance: BaseLLM | None = None if isinstance(llm, str) else llm
         self._embedder_config: Any = embedder
         self._embedder_instance: Any = (
-            embedder if (embedder is not None and not isinstance(embedder, dict)) else None
+            embedder
+            if (embedder is not None and not isinstance(embedder, dict))
+            else None
         )
 
-        # Storage is initialized eagerly (local, no API key needed).
-        if storage == "lancedb":
-            self._storage = LanceDBStorage()
-        elif isinstance(storage, str):
-            self._storage = LanceDBStorage(path=storage)
+        if isinstance(storage, str):
+            from crewai.memory.storage.lancedb_storage import LanceDBStorage
+
+            self._storage = LanceDBStorage() if storage == "lancedb" else LanceDBStorage(path=storage)
         else:
             self._storage = storage
 
@@ -160,12 +173,17 @@ class Memory:
             from crewai.llm import LLM
 
             try:
-                self._llm_instance = LLM(model=self._llm_config)
+                model_name = (
+                    self._llm_config
+                    if isinstance(self._llm_config, str)
+                    else str(self._llm_config)
+                )
+                self._llm_instance = LLM(model=model_name)
             except Exception as e:
                 raise RuntimeError(
                     f"Memory requires an LLM for analysis but initialization failed: {e}\n\n"
                     "To fix this, do one of the following:\n"
-                    '  - Set OPENAI_API_KEY for the default model (gpt-4o-mini)\n'
+                    "  - Set OPENAI_API_KEY for the default model (gpt-4o-mini)\n"
                     '  - Pass a different model: Memory(llm="anthropic/claude-3-haiku-20240307")\n'
                     '  - Pass any LLM instance: Memory(llm=LLM(model="your-model"))\n'
                     "  - To skip LLM analysis, pass all fields explicitly to remember()\n"
@@ -180,8 +198,6 @@ class Memory:
         if self._embedder_instance is None:
             try:
                 if isinstance(self._embedder_config, dict):
-                    from crewai.rag.embeddings.factory import build_embedder
-
                     self._embedder_instance = build_embedder(self._embedder_config)
                 else:
                     self._embedder_instance = _default_embedder()
@@ -317,7 +333,7 @@ class Memory:
         source: str | None = None,
         private: bool = False,
         agent_role: str | None = None,
-    ) -> MemoryRecord:
+    ) -> MemoryRecord | None:
         """Store a single item in memory (synchronous).
 
         Routes through the same serialized save pool as ``remember_many``
@@ -335,11 +351,13 @@ class Memory:
             agent_role: Optional agent role for event metadata.
 
         Returns:
-            The created MemoryRecord.
+            The created MemoryRecord, or None if this memory is read-only.
 
         Raises:
             Exception: On save failure (events emitted).
         """
+        if self._read_only:
+            return None
         _source_type = "unified_memory"
         try:
             crewai_event_bus.emit(
@@ -356,7 +374,13 @@ class Memory:
             # then immediately wait for the result.
             future = self._submit_save(
                 self._encode_batch,
-                [content], scope, categories, metadata, importance, source, private,
+                [content],
+                scope,
+                categories,
+                metadata,
+                importance,
+                source,
+                private,
             )
             records = future.result()
             record = records[0] if records else None
@@ -420,13 +444,19 @@ class Memory:
         Returns:
             Empty list (records are not available until the background save completes).
         """
-        if not contents:
+        if not contents or self._read_only:
             return []
 
         self._submit_save(
             self._background_encode_batch,
-            contents, scope, categories, metadata,
-            importance, source, private, agent_role,
+            contents,
+            scope,
+            categories,
+            metadata,
+            importance,
+            source,
+            private,
+            agent_role,
         )
         return []
 
@@ -566,14 +596,13 @@ class Memory:
                     # Privacy filter
                     if not include_private:
                         raw = [
-                            (r, s) for r, s in raw
+                            (r, s)
+                            for r, s in raw
                             if not r.private or r.source == source
                         ]
                     results = []
                     for r, s in raw:
-                        composite, reasons = compute_composite_score(
-                            r, s, self._config
-                        )
+                        composite, reasons = compute_composite_score(r, s, self._config)
                         results.append(
                             MemoryMatch(
                                 record=r,
@@ -739,7 +768,9 @@ class Memory:
             limit: Maximum number of records to return.
             offset: Number of records to skip (for pagination).
         """
-        return self._storage.list_records(scope_prefix=scope, limit=limit, offset=offset)
+        return self._storage.list_records(
+            scope_prefix=scope, limit=limit, offset=offset
+        )
 
     def info(self, path: str = "/") -> ScopeInfo:
         """Return scope info for path."""
@@ -781,7 +812,7 @@ class Memory:
         importance: float | None = None,
         source: str | None = None,
         private: bool = False,
-    ) -> MemoryRecord:
+    ) -> MemoryRecord | None:
         """Async remember: delegates to sync for now."""
         return self.remember(
             content,

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

@@ -216,6 +216,10 @@ def build_embedder_from_dict(
 def build_embedder_from_dict(spec: ONNXProviderSpec) -> ONNXMiniLM_L6_V2: ...
 
 
+@overload
+def build_embedder_from_dict(spec: dict[str, Any]) -> EmbeddingFunction[Any]: ...
+
+
 def build_embedder_from_dict(spec):  # type: ignore[no-untyped-def]
     """Build an embedding function instance from a dictionary specification.
 
@@ -341,6 +345,10 @@ def build_embedder(spec: Text2VecProviderSpec) -> Text2VecEmbeddingFunction: ...
 def build_embedder(spec: ONNXProviderSpec) -> ONNXMiniLM_L6_V2: ...
 
 
+@overload
+def build_embedder(spec: dict[str, Any]) -> EmbeddingFunction[Any]: ...
+
+
 def build_embedder(spec):  # type: ignore[no-untyped-def]
     """Build an embedding function from either a provider spec or a provider instance.
 

lib/crewai/src/crewai/task.py

@@ -586,16 +586,29 @@ class Task(BaseModel):
 
             self._post_agent_execution(agent)
 
-            if not self._guardrails and not self._guardrail:
+            if isinstance(result, BaseModel):
+                raw = result.model_dump_json()
+                if self.output_pydantic:
+                    pydantic_output = result
+                    json_output = None
+                elif self.output_json:
+                    pydantic_output = None
+                    json_output = result.model_dump()
+                else:
+                    pydantic_output = None
+                    json_output = None
+            elif not self._guardrails and not self._guardrail:
+                raw = result
                 pydantic_output, json_output = self._export_output(result)
             else:
+                raw = result
                 pydantic_output, json_output = None, None
 
             task_output = TaskOutput(
                 name=self.name or self.description,
                 description=self.description,
                 expected_output=self.expected_output,
-                raw=result,
+                raw=raw,
                 pydantic=pydantic_output,
                 json_dict=json_output,
                 agent=agent.role,
@@ -687,16 +700,29 @@ class Task(BaseModel):
 
             self._post_agent_execution(agent)
 
-            if not self._guardrails and not self._guardrail:
+            if isinstance(result, BaseModel):
+                raw = result.model_dump_json()
+                if self.output_pydantic:
+                    pydantic_output = result
+                    json_output = None
+                elif self.output_json:
+                    pydantic_output = None
+                    json_output = result.model_dump()
+                else:
+                    pydantic_output = None
+                    json_output = None
+            elif not self._guardrails and not self._guardrail:
+                raw = result
                 pydantic_output, json_output = self._export_output(result)
             else:
+                raw = result
                 pydantic_output, json_output = None, None
 
             task_output = TaskOutput(
                 name=self.name or self.description,
                 description=self.description,
                 expected_output=self.expected_output,
-                raw=result,
+                raw=raw,
                 pydantic=pydantic_output,
                 json_dict=json_output,
                 agent=agent.role,

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

@@ -150,14 +150,38 @@ class BaseTool(BaseModel, ABC):
 
         super().model_post_init(__context)
 
+    def _validate_kwargs(self, kwargs: dict[str, Any]) -> dict[str, Any]:
+        """Validate keyword arguments against args_schema if present.
+
+        Args:
+            kwargs: The keyword arguments to validate.
+
+        Returns:
+            Validated (and possibly coerced) keyword arguments.
+
+        Raises:
+            ValueError: If validation against args_schema fails.
+        """
+        if self.args_schema is not None and self.args_schema.model_fields:
+            try:
+                validated = self.args_schema.model_validate(kwargs)
+                return validated.model_dump()
+            except Exception as e:
+                raise ValueError(
+                    f"Tool '{self.name}' arguments validation failed: {e}"
+                ) from e
+        return kwargs
+
     def run(
         self,
         *args: Any,
         **kwargs: Any,
     ) -> Any:
+        if not args:
+            kwargs = self._validate_kwargs(kwargs)
+
         result = self._run(*args, **kwargs)
 
-        # If _run is async, we safely run it
         if asyncio.iscoroutine(result):
             result = asyncio.run(result)
 
@@ -179,6 +203,8 @@ class BaseTool(BaseModel, ABC):
         Returns:
             The result of the tool execution.
         """
+        if not args:
+            kwargs = self._validate_kwargs(kwargs)
         result = await self._arun(*args, **kwargs)
         self.current_usage_count += 1
         return result
@@ -331,6 +357,9 @@ class Tool(BaseTool, Generic[P, R]):
         Returns:
             The result of the tool execution.
         """
+        if not args:
+            kwargs = self._validate_kwargs(kwargs)  # type: ignore[assignment]
+
         result = self.func(*args, **kwargs)
 
         if asyncio.iscoroutine(result):
@@ -361,6 +390,8 @@ class Tool(BaseTool, Generic[P, R]):
         Returns:
             The result of the tool execution.
         """
+        if not args:
+            kwargs = self._validate_kwargs(kwargs)  # type: ignore[assignment]
         result = await self._arun(*args, **kwargs)
         self.current_usage_count += 1
         return result

lib/crewai/src/crewai/tools/mcp_native_tool.py

@@ -27,14 +27,16 @@ class MCPNativeTool(BaseTool):
         tool_name: str,
         tool_schema: dict[str, Any],
         server_name: str,
+        original_tool_name: str | None = None,
     ) -> None:
         """Initialize native MCP tool.
 
         Args:
             mcp_client: MCPClient instance with active session.
-            tool_name: Original name of the tool on the MCP server.
+            tool_name: Name of the tool (may be prefixed).
             tool_schema: Schema information for the tool.
             server_name: Name of the MCP server for prefixing.
+            original_tool_name: Original name of the tool on the MCP server.
         """
         # Create tool name with server prefix to avoid conflicts
         prefixed_name = f"{server_name}_{tool_name}"
@@ -57,7 +59,7 @@ class MCPNativeTool(BaseTool):
 
         # Set instance attributes after super().__init__
         self._mcp_client = mcp_client
-        self._original_tool_name = tool_name
+        self._original_tool_name = original_tool_name or tool_name
         self._server_name = server_name
         # self._logger = logging.getLogger(__name__)
 

lib/crewai/src/crewai/tools/memory_tools.py

@@ -20,14 +20,6 @@ class RecallMemorySchema(BaseModel):
             "or multiple items to search for several things at once."
         ),
     )
-    scope: str | None = Field(
-        default=None,
-        description="Optional scope to narrow the search (e.g. /project/alpha)",
-    )
-    depth: str = Field(
-        default="shallow",
-        description="'shallow' for fast vector search, 'deep' for LLM-analyzed retrieval",
-    )
 
 
 class RecallMemoryTool(BaseTool):
@@ -41,32 +33,27 @@ class RecallMemoryTool(BaseTool):
     def _run(
         self,
         queries: list[str] | str,
-        scope: str | None = None,
-        depth: str = "shallow",
         **kwargs: Any,
     ) -> str:
         """Search memory for relevant information.
 
         Args:
             queries: One or more search queries (string or list of strings).
-            scope: Optional scope prefix to narrow the search.
-            depth: "shallow" for fast vector search, "deep" for LLM-analyzed retrieval.
 
         Returns:
             Formatted string of matching memories, or a message if none found.
         """
         if isinstance(queries, str):
             queries = [queries]
-        actual_depth = depth if depth in ("shallow", "deep") else "shallow"
 
         all_lines: list[str] = []
         seen_ids: set[str] = set()
         for query in queries:
-            matches = self.memory.recall(query, scope=scope, limit=5, depth=actual_depth)
+            matches = self.memory.recall(query)
             for m in matches:
                 if m.record.id not in seen_ids:
                     seen_ids.add(m.record.id)
-                    all_lines.append(f"- (score={m.score:.2f}) {m.record.content}")
+                    all_lines.append(m.format())
 
         if not all_lines:
             return "No relevant memories found."
@@ -117,20 +104,28 @@ class RememberTool(BaseTool):
 def create_memory_tools(memory: Any) -> list[BaseTool]:
     """Create Recall and Remember tools for the given memory instance.
 
+    When memory is read-only (``_read_only=True``), only the RecallMemoryTool
+    is returned — the RememberTool is omitted so agents are never offered a
+    save capability they cannot use.
+
     Args:
         memory: A Memory, MemoryScope, or MemorySlice instance.
 
     Returns:
-        List containing a RecallMemoryTool and a RememberTool.
+        List containing a RecallMemoryTool and, if not read-only, a RememberTool.
     """
     i18n = get_i18n()
-    return [
+    tools: list[BaseTool] = [
         RecallMemoryTool(
             memory=memory,
             description=i18n.tools("recall_memory"),
         ),
-        RememberTool(
-            memory=memory,
-            description=i18n.tools("save_to_memory"),
-        ),
     ]
+    if not getattr(memory, "_read_only", False):
+        tools.append(
+            RememberTool(
+                memory=memory,
+                description=i18n.tools("save_to_memory"),
+            )
+        )
+    return tools

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

@@ -168,7 +168,9 @@ def convert_tools_to_openai_schema(
         parameters: dict[str, Any] = {}
         if hasattr(tool, "args_schema") and tool.args_schema is not None:
             try:
-                schema_output = generate_model_description(tool.args_schema)
+                schema_output = generate_model_description(
+                    tool.args_schema, strip_null_types=False
+                )
                 parameters = schema_output.get("json_schema", {}).get("schema", {})
                 # Remove title and description from schema root as they're redundant
                 parameters.pop("title", None)
@@ -1146,6 +1148,36 @@ def extract_tool_call_info(
     return None
 
 
+def parse_tool_call_args(
+    func_args: dict[str, Any] | str,
+    func_name: str,
+    call_id: str,
+    original_tool: Any = None,
+) -> tuple[dict[str, Any], None] | tuple[None, dict[str, Any]]:
+    """Parse tool call arguments from a JSON string or dict.
+
+    Returns:
+        ``(args_dict, None)`` on success, or ``(None, error_result)`` on
+        JSON parse failure where ``error_result`` is a ready-to-return dict
+        with the same shape as ``_execute_single_native_tool_call`` return values.
+    """
+    if isinstance(func_args, str):
+        try:
+            return json.loads(func_args), None
+        except json.JSONDecodeError as e:
+            return None, {
+                "call_id": call_id,
+                "func_name": func_name,
+                "result": (
+                    f"Error: Failed to parse tool arguments as JSON: {e}. "
+                    f"Please provide valid JSON arguments for the '{func_name}' tool."
+                ),
+                "from_cache": False,
+                "original_tool": original_tool,
+            }
+    return func_args, None
+
+
 def _setup_before_llm_call_hooks(
     executor_context: CrewAgentExecutor | AgentExecutor | LiteAgent | None,
     printer: Printer,

lib/crewai/src/crewai/utilities/llm_utils.py

@@ -69,7 +69,7 @@ def create_llm(
 UNACCEPTED_ATTRIBUTES: Final[list[str]] = [
     "AWS_ACCESS_KEY_ID",
     "AWS_SECRET_ACCESS_KEY",
-    "AWS_REGION_NAME",
+    "AWS_DEFAULT_REGION",
 ]
 
 
@@ -146,7 +146,7 @@ def _llm_via_environment_or_fallback() -> LLM | None:
     unaccepted_attributes = [
         "AWS_ACCESS_KEY_ID",
         "AWS_SECRET_ACCESS_KEY",
-        "AWS_REGION_NAME",
+        "AWS_DEFAULT_REGION",
     ]
     set_provider = model_name.partition("/")[0] if "/" in model_name else "openai"
 

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

@@ -417,7 +417,11 @@ def strip_null_from_types(schema: dict[str, Any]) -> dict[str, Any]:
     return schema
 
 
-def generate_model_description(model: type[BaseModel]) -> ModelDescription:
+def generate_model_description(
+    model: type[BaseModel],
+    *,
+    strip_null_types: bool = True,
+) -> ModelDescription:
     """Generate JSON schema description of a Pydantic model.
 
     This function takes a Pydantic model class and returns its JSON schema,
@@ -426,6 +430,9 @@ def generate_model_description(model: type[BaseModel]) -> ModelDescription:
 
     Args:
         model: A Pydantic model class.
+        strip_null_types: When ``True`` (default), remove ``null`` from
+            ``anyOf`` / ``type`` arrays.  Set to ``False`` to allow sending ``null`` for
+            optional fields.
 
     Returns:
         A ModelDescription with JSON schema representation of the model.
@@ -442,7 +449,9 @@ def generate_model_description(model: type[BaseModel]) -> ModelDescription:
     json_schema = fix_discriminator_mappings(json_schema)
     json_schema = convert_oneof_to_anyof(json_schema)
     json_schema = ensure_all_properties_required(json_schema)
-    json_schema = strip_null_from_types(json_schema)
+
+    if strip_null_types:
+        json_schema = strip_null_from_types(json_schema)
 
     return {
         "type": "json_schema",
@@ -482,10 +491,66 @@ FORMAT_TYPE_MAP: dict[str, type[Any]] = {
 }
 
 
+def build_rich_field_description(prop_schema: dict[str, Any]) -> str:
+    """Build a comprehensive field description including constraints.
+
+    Embeds format, enum, pattern, min/max, and example constraints into the
+    description text so that LLMs can understand tool parameter requirements
+    without inspecting the raw JSON Schema.
+
+    Args:
+        prop_schema: Property schema with description and constraints.
+
+    Returns:
+        Enhanced description with format, enum, and other constraints.
+    """
+    parts: list[str] = []
+
+    description = prop_schema.get("description", "")
+    if description:
+        parts.append(description)
+
+    format_type = prop_schema.get("format")
+    if format_type:
+        parts.append(f"Format: {format_type}")
+
+    enum_values = prop_schema.get("enum")
+    if enum_values:
+        enum_str = ", ".join(repr(v) for v in enum_values)
+        parts.append(f"Allowed values: [{enum_str}]")
+
+    pattern = prop_schema.get("pattern")
+    if pattern:
+        parts.append(f"Pattern: {pattern}")
+
+    minimum = prop_schema.get("minimum")
+    maximum = prop_schema.get("maximum")
+    if minimum is not None:
+        parts.append(f"Minimum: {minimum}")
+    if maximum is not None:
+        parts.append(f"Maximum: {maximum}")
+
+    min_length = prop_schema.get("minLength")
+    max_length = prop_schema.get("maxLength")
+    if min_length is not None:
+        parts.append(f"Min length: {min_length}")
+    if max_length is not None:
+        parts.append(f"Max length: {max_length}")
+
+    examples = prop_schema.get("examples")
+    if examples:
+        examples_str = ", ".join(repr(e) for e in examples[:3])
+        parts.append(f"Examples: {examples_str}")
+
+    return ". ".join(parts) if parts else ""
+
+
 def create_model_from_schema(  # type: ignore[no-any-unimported]
     json_schema: dict[str, Any],
     *,
     root_schema: dict[str, Any] | None = None,
+    model_name: str | None = None,
+    enrich_descriptions: bool = False,
     __config__: ConfigDict | None = None,
     __base__: type[BaseModel] | None = None,
     __module__: str = __name__,
@@ -503,6 +568,13 @@ def create_model_from_schema(  # type: ignore[no-any-unimported]
         json_schema: A dictionary representing the JSON schema.
         root_schema: The root schema containing $defs. If not provided, the
             current schema is treated as the root schema.
+        model_name: Override for the model name. If not provided, the schema
+            ``title`` field is used, falling back to ``"DynamicModel"``.
+        enrich_descriptions: When True, augment field descriptions with
+            constraint info (format, enum, pattern, min/max, examples) via
+            :func:`build_rich_field_description`.  Useful for LLM-facing tool
+            schemas where constraints in the description help the model
+            understand parameter requirements.
         __config__: Pydantic configuration for the generated model.
         __base__: Base class for the generated model. Defaults to BaseModel.
         __module__: Module name for the generated model class.
@@ -539,10 +611,14 @@ def create_model_from_schema(  # type: ignore[no-any-unimported]
         if "title" not in json_schema and "title" in (root_schema or {}):
             json_schema["title"] = (root_schema or {}).get("title")
 
-    model_name = json_schema.get("title") or "DynamicModel"
+    effective_name = model_name or json_schema.get("title") or "DynamicModel"
     field_definitions = {
         name: _json_schema_to_pydantic_field(
-            name, prop, json_schema.get("required", []), effective_root
+            name,
+            prop,
+            json_schema.get("required", []),
+            effective_root,
+            enrich_descriptions=enrich_descriptions,
         )
         for name, prop in (json_schema.get("properties", {}) or {}).items()
     }
@@ -550,7 +626,7 @@ def create_model_from_schema(  # type: ignore[no-any-unimported]
     effective_config = __config__ or ConfigDict(extra="forbid")
 
     return create_model_base(
-        model_name,
+        effective_name,
         __config__=effective_config,
         __base__=__base__,
         __module__=__module__,
@@ -565,6 +641,8 @@ def _json_schema_to_pydantic_field(
     json_schema: dict[str, Any],
     required: list[str],
     root_schema: dict[str, Any],
+    *,
+    enrich_descriptions: bool = False,
 ) -> Any:
     """Convert a JSON schema property to a Pydantic field definition.
 
@@ -573,20 +651,29 @@ def _json_schema_to_pydantic_field(
         json_schema: The JSON schema for this field.
         required: List of required field names.
         root_schema: The root schema for resolving $ref.
+        enrich_descriptions: When True, embed constraints in the description.
 
     Returns:
         A tuple of (type, Field) for use with create_model.
     """
-    type_ = _json_schema_to_pydantic_type(json_schema, root_schema, name_=name.title())
-    description = json_schema.get("description")
-    examples = json_schema.get("examples")
+    type_ = _json_schema_to_pydantic_type(
+        json_schema, root_schema, name_=name.title(), enrich_descriptions=enrich_descriptions
+    )
     is_required = name in required
 
     field_params: dict[str, Any] = {}
     schema_extra: dict[str, Any] = {}
 
-    if description:
-        field_params["description"] = description
+    if enrich_descriptions:
+        rich_desc = build_rich_field_description(json_schema)
+        if rich_desc:
+            field_params["description"] = rich_desc
+    else:
+        description = json_schema.get("description")
+        if description:
+            field_params["description"] = description
+
+    examples = json_schema.get("examples")
     if examples:
         schema_extra["examples"] = examples
 
@@ -702,6 +789,7 @@ def _json_schema_to_pydantic_type(
     root_schema: dict[str, Any],
     *,
     name_: str | None = None,
+    enrich_descriptions: bool = False,
 ) -> Any:
     """Convert a JSON schema to a Python/Pydantic type.
 
@@ -709,6 +797,7 @@ def _json_schema_to_pydantic_type(
         json_schema: The JSON schema to convert.
         root_schema: The root schema for resolving $ref.
         name_: Optional name for nested models.
+        enrich_descriptions: Propagated to nested model creation.
 
     Returns:
         A Python type corresponding to the JSON schema.
@@ -716,7 +805,9 @@ def _json_schema_to_pydantic_type(
     ref = json_schema.get("$ref")
     if ref:
         ref_schema = _resolve_ref(ref, root_schema)
-        return _json_schema_to_pydantic_type(ref_schema, root_schema, name_=name_)
+        return _json_schema_to_pydantic_type(
+            ref_schema, root_schema, name_=name_, enrich_descriptions=enrich_descriptions
+        )
 
     enum_values = json_schema.get("enum")
     if enum_values:
@@ -731,7 +822,10 @@ def _json_schema_to_pydantic_type(
     if any_of_schemas:
         any_of_types = [
             _json_schema_to_pydantic_type(
-                schema, root_schema, name_=f"{name_ or 'Union'}Option{i}"
+                schema,
+                root_schema,
+                name_=f"{name_ or 'Union'}Option{i}",
+                enrich_descriptions=enrich_descriptions,
             )
             for i, schema in enumerate(any_of_schemas)
         ]
@@ -741,10 +835,14 @@ def _json_schema_to_pydantic_type(
     if all_of_schemas:
         if len(all_of_schemas) == 1:
             return _json_schema_to_pydantic_type(
-                all_of_schemas[0], root_schema, name_=name_
+                all_of_schemas[0], root_schema, name_=name_,
+                enrich_descriptions=enrich_descriptions,
             )
         merged = _merge_all_of_schemas(all_of_schemas, root_schema)
-        return _json_schema_to_pydantic_type(merged, root_schema, name_=name_)
+        return _json_schema_to_pydantic_type(
+            merged, root_schema, name_=name_,
+            enrich_descriptions=enrich_descriptions,
+        )
 
     type_ = json_schema.get("type")
 
@@ -760,7 +858,8 @@ def _json_schema_to_pydantic_type(
         items_schema = json_schema.get("items")
         if items_schema:
             item_type = _json_schema_to_pydantic_type(
-                items_schema, root_schema, name_=name_
+                items_schema, root_schema, name_=name_,
+                enrich_descriptions=enrich_descriptions,
             )
             return list[item_type]  # type: ignore[valid-type]
         return list
@@ -770,7 +869,10 @@ def _json_schema_to_pydantic_type(
             json_schema_ = json_schema.copy()
             if json_schema_.get("title") is None:
                 json_schema_["title"] = name_ or "DynamicModel"
-            return create_model_from_schema(json_schema_, root_schema=root_schema)
+            return create_model_from_schema(
+                json_schema_, root_schema=root_schema,
+                enrich_descriptions=enrich_descriptions,
+            )
         return dict
     if type_ == "null":
         return None

lib/crewai/tests/agents/test_lite_agent.py

@@ -659,7 +659,7 @@ def test_agent_kickoff_with_platform_tools(mock_get, mock_post):
 
 
 @patch.dict("os.environ", {"EXA_API_KEY": "test_exa_key"})
-@patch("crewai.agent.Agent._get_external_mcp_tools")
+@patch("crewai.agent.Agent.get_mcp_tools")
 @pytest.mark.vcr()
 def test_agent_kickoff_with_mcp_tools(mock_get_mcp_tools):
     """Test that Agent.kickoff() properly integrates MCP tools with LiteAgent"""
@@ -691,7 +691,7 @@ def test_agent_kickoff_with_mcp_tools(mock_get_mcp_tools):
     assert result.raw is not None
 
     # Verify MCP tools were retrieved
-    mock_get_mcp_tools.assert_called_once_with("https://mcp.exa.ai/mcp?api_key=test_exa_key&profile=research")
+    mock_get_mcp_tools.assert_called_once_with(["https://mcp.exa.ai/mcp?api_key=test_exa_key&profile=research"])
 
 
 # ============================================================================
@@ -1136,6 +1136,7 @@ def test_lite_agent_memory_instance_recall_and_save_called():
         successful_requests=1,
     )
     mock_memory = Mock()
+    mock_memory._read_only = False
     mock_memory.recall.return_value = []
     mock_memory.extract_memories.return_value = ["Fact one.", "Fact two."]
 

lib/crewai/tests/agents/test_native_tool_calling.py

@@ -11,7 +11,7 @@ import os
 import threading
 import time
 from collections import Counter
-from unittest.mock import patch
+from unittest.mock import Mock, patch
 
 import pytest
 from pydantic import BaseModel, Field
@@ -1129,3 +1129,150 @@ class TestMaxUsageCountWithNativeToolCalling:
         # Verify the requested calls occurred while keeping usage bounded.
         assert tool.current_usage_count >= 2
         assert tool.current_usage_count <= tool.max_usage_count
+
+
+# =============================================================================
+# JSON Parse Error Handling Tests
+# =============================================================================
+
+
+class TestNativeToolCallingJsonParseError:
+    """Tests that malformed JSON tool arguments produce clear errors
+    instead of silently dropping all arguments."""
+
+    def _make_executor(self, tools: list[BaseTool]) -> "CrewAgentExecutor":
+        """Create a minimal CrewAgentExecutor with mocked dependencies."""
+        from crewai.agents.crew_agent_executor import CrewAgentExecutor
+        from crewai.tools.base_tool import to_langchain
+
+        structured_tools = to_langchain(tools)
+        mock_agent = Mock()
+        mock_agent.key = "test_agent"
+        mock_agent.role = "tester"
+        mock_agent.verbose = False
+        mock_agent.fingerprint = None
+        mock_agent.tools_results = []
+
+        mock_task = Mock()
+        mock_task.name = "test"
+        mock_task.description = "test"
+        mock_task.id = "test-id"
+
+        executor = object.__new__(CrewAgentExecutor)
+        executor.agent = mock_agent
+        executor.task = mock_task
+        executor.crew = Mock()
+        executor.tools = structured_tools
+        executor.original_tools = tools
+        executor.tools_handler = None
+        executor._printer = Mock()
+        executor.messages = []
+
+        return executor
+
+    def test_malformed_json_returns_parse_error(self) -> None:
+        """Malformed JSON args must return a descriptive error, not silently become {}."""
+
+        class CodeTool(BaseTool):
+            name: str = "execute_code"
+            description: str = "Run code"
+
+            def _run(self, code: str) -> str:
+                return f"ran: {code}"
+
+        tool = CodeTool()
+        executor = self._make_executor([tool])
+
+        from crewai.utilities.agent_utils import convert_tools_to_openai_schema
+        _, available_functions = convert_tools_to_openai_schema([tool])
+
+        malformed_json = '{"code": "print("hello")"}'
+
+        result = executor._execute_single_native_tool_call(
+            call_id="call_123",
+            func_name="execute_code",
+            func_args=malformed_json,
+            available_functions=available_functions,
+        )
+
+        assert "Failed to parse tool arguments as JSON" in result["result"]
+        assert tool.current_usage_count == 0
+
+    def test_valid_json_still_executes_normally(self) -> None:
+        """Valid JSON args should execute the tool as before."""
+
+        class CodeTool(BaseTool):
+            name: str = "execute_code"
+            description: str = "Run code"
+
+            def _run(self, code: str) -> str:
+                return f"ran: {code}"
+
+        tool = CodeTool()
+        executor = self._make_executor([tool])
+
+        from crewai.utilities.agent_utils import convert_tools_to_openai_schema
+        _, available_functions = convert_tools_to_openai_schema([tool])
+
+        valid_json = '{"code": "print(1)"}'
+
+        result = executor._execute_single_native_tool_call(
+            call_id="call_456",
+            func_name="execute_code",
+            func_args=valid_json,
+            available_functions=available_functions,
+        )
+
+        assert result["result"] == "ran: print(1)"
+
+    def test_dict_args_bypass_json_parsing(self) -> None:
+        """When func_args is already a dict, no JSON parsing occurs."""
+
+        class CodeTool(BaseTool):
+            name: str = "execute_code"
+            description: str = "Run code"
+
+            def _run(self, code: str) -> str:
+                return f"ran: {code}"
+
+        tool = CodeTool()
+        executor = self._make_executor([tool])
+
+        from crewai.utilities.agent_utils import convert_tools_to_openai_schema
+        _, available_functions = convert_tools_to_openai_schema([tool])
+
+        result = executor._execute_single_native_tool_call(
+            call_id="call_789",
+            func_name="execute_code",
+            func_args={"code": "x = 42"},
+            available_functions=available_functions,
+        )
+
+        assert result["result"] == "ran: x = 42"
+
+    def test_schema_validation_catches_missing_args_on_native_path(self) -> None:
+        """The native function calling path should now enforce args_schema,
+        catching missing required fields before _run is called."""
+
+        class StrictTool(BaseTool):
+            name: str = "strict_tool"
+            description: str = "A tool with required args"
+
+            def _run(self, code: str, language: str) -> str:
+                return f"{language}: {code}"
+
+        tool = StrictTool()
+        executor = self._make_executor([tool])
+
+        from crewai.utilities.agent_utils import convert_tools_to_openai_schema
+        _, available_functions = convert_tools_to_openai_schema([tool])
+
+        result = executor._execute_single_native_tool_call(
+            call_id="call_schema",
+            func_name="strict_tool",
+            func_args={"code": "print(1)"},
+            available_functions=available_functions,
+        )
+
+        assert "Error" in result["result"]
+        assert "validation failed" in result["result"].lower() or "missing" in result["result"].lower()

lib/crewai/tests/cassettes/llms/google/test_gemini_crew_structured_output_with_tools.yaml

@@ -0,0 +1,197 @@
+interactions:
+- request:
+    body: '{"contents": [{"parts": [{"text": "\nCurrent Task: Calculate 15 + 27 using
+      your add_numbers tool. Report the result.\n\nThis is the expected criteria for
+      your final answer: A structured calculation result\nyou MUST return the actual
+      complete content as the final answer, not a summary.\nFormat your final answer
+      according to the following OpenAPI schema: {\n  \"properties\": {\n    \"operation\":
+      {\n      \"description\": \"The mathematical operation performed\",\n      \"title\":
+      \"Operation\",\n      \"type\": \"string\"\n    },\n    \"result\": {\n      \"description\":
+      \"The result of the calculation\",\n      \"title\": \"Result\",\n      \"type\":
+      \"integer\"\n    },\n    \"explanation\": {\n      \"description\": \"Brief
+      explanation of the calculation\",\n      \"title\": \"Explanation\",\n      \"type\":
+      \"string\"\n    }\n  },\n  \"required\": [\n    \"operation\",\n    \"result\",\n    \"explanation\"\n  ],\n  \"title\":
+      \"CalculationResult\",\n  \"type\": \"object\",\n  \"additionalProperties\":
+      false\n}\n\nIMPORTANT: Preserve the original content exactly as-is. Do NOT rewrite,
+      paraphrase, or modify the meaning of the content. Only structure it to match
+      the schema format.\n\nDo not include the OpenAPI schema in the final output.
+      Ensure the final output does not include any code block markers like ```json
+      or ```python."}], "role": "user"}], "systemInstruction": {"parts": [{"text":
+      "You are Calculator. You are a calculator assistant that uses tools to compute
+      results.\nYour personal goal is: Perform calculations using available tools"}],
+      "role": "user"}, "tools": [{"functionDeclarations": [{"description": "Add two
+      numbers together and return the sum.", "name": "add_numbers", "parameters_json_schema":
+      {"properties": {"a": {"title": "A", "type": "integer"}, "b": {"title": "B",
+      "type": "integer"}}, "required": ["a", "b"], "type": "object", "additionalProperties":
+      false}}, {"description": "Use this tool to provide your final structured response.
+      Call this tool when you have gathered all necessary information and are ready
+      to provide the final answer in the required format.", "name": "structured_output",
+      "parameters_json_schema": {"properties": {"operation": {"description": "The
+      mathematical operation performed", "title": "Operation", "type": "string"},
+      "result": {"description": "The result of the calculation", "title": "Result",
+      "type": "integer"}, "explanation": {"description": "Brief explanation of the
+      calculation", "title": "Explanation", "type": "string"}}, "required": ["operation",
+      "result", "explanation"], "title": "CalculationResult", "type": "object", "additionalProperties":
+      false, "propertyOrdering": ["operation", "result", "explanation"]}}]}], "generationConfig":
+      {"stopSequences": ["\nObservation:"]}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '2763'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      x-goog-api-client:
+      - google-genai-sdk/1.49.0 gl-python/3.13.12
+      x-goog-api-key:
+      - X-GOOG-API-KEY-XXX
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-001:generateContent
+  response:
+    body:
+      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
+        [\n          {\n            \"functionCall\": {\n              \"name\": \"add_numbers\",\n
+        \             \"args\": {\n                \"a\": 15,\n                \"b\":
+        27\n              }\n            }\n          }\n        ],\n        \"role\":
+        \"model\"\n      },\n      \"finishReason\": \"STOP\",\n      \"avgLogprobs\":
+        4.3579145442760951e-06\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
+        377,\n    \"candidatesTokenCount\": 7,\n    \"totalTokenCount\": 384,\n    \"promptTokensDetails\":
+        [\n      {\n        \"modality\": \"TEXT\",\n        \"tokenCount\": 377\n
+        \     }\n    ],\n    \"candidatesTokensDetails\": [\n      {\n        \"modality\":
+        \"TEXT\",\n        \"tokenCount\": 7\n      }\n    ]\n  },\n  \"modelVersion\":
+        \"gemini-2.0-flash-001\",\n  \"responseId\": \"vVefaYDSOouXjMcPicLCsQY\"\n}\n"
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Wed, 25 Feb 2026 20:12:46 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=718
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      X-Frame-Options:
+      - X-FRAME-OPTIONS-XXX
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"contents": [{"parts": [{"text": "\nCurrent Task: Calculate 15 + 27 using
+      your add_numbers tool. Report the result.\n\nThis is the expected criteria for
+      your final answer: A structured calculation result\nyou MUST return the actual
+      complete content as the final answer, not a summary.\nFormat your final answer
+      according to the following OpenAPI schema: {\n  \"properties\": {\n    \"operation\":
+      {\n      \"description\": \"The mathematical operation performed\",\n      \"title\":
+      \"Operation\",\n      \"type\": \"string\"\n    },\n    \"result\": {\n      \"description\":
+      \"The result of the calculation\",\n      \"title\": \"Result\",\n      \"type\":
+      \"integer\"\n    },\n    \"explanation\": {\n      \"description\": \"Brief
+      explanation of the calculation\",\n      \"title\": \"Explanation\",\n      \"type\":
+      \"string\"\n    }\n  },\n  \"required\": [\n    \"operation\",\n    \"result\",\n    \"explanation\"\n  ],\n  \"title\":
+      \"CalculationResult\",\n  \"type\": \"object\",\n  \"additionalProperties\":
+      false\n}\n\nIMPORTANT: Preserve the original content exactly as-is. Do NOT rewrite,
+      paraphrase, or modify the meaning of the content. Only structure it to match
+      the schema format.\n\nDo not include the OpenAPI schema in the final output.
+      Ensure the final output does not include any code block markers like ```json
+      or ```python."}], "role": "user"}, {"parts": [{"functionCall": {"args": {"a":
+      15, "b": 27}, "name": "add_numbers"}}], "role": "model"}, {"parts": [{"functionResponse":
+      {"name": "add_numbers", "response": {"result": 42}}}], "role": "user"}, {"parts":
+      [{"text": "Analyze the tool result. If requirements are met, provide the Final
+      Answer. Otherwise, call the next tool. Deliver only the answer without meta-commentary."}],
+      "role": "user"}], "systemInstruction": {"parts": [{"text": "You are Calculator.
+      You are a calculator assistant that uses tools to compute results.\nYour personal
+      goal is: Perform calculations using available tools"}], "role": "user"}, "tools":
+      [{"functionDeclarations": [{"description": "Add two numbers together and return
+      the sum.", "name": "add_numbers", "parameters_json_schema": {"properties": {"a":
+      {"title": "A", "type": "integer"}, "b": {"title": "B", "type": "integer"}},
+      "required": ["a", "b"], "type": "object", "additionalProperties": false}}, {"description":
+      "Use this tool to provide your final structured response. Call this tool when
+      you have gathered all necessary information and are ready to provide the final
+      answer in the required format.", "name": "structured_output", "parameters_json_schema":
+      {"properties": {"operation": {"description": "The mathematical operation performed",
+      "title": "Operation", "type": "string"}, "result": {"description": "The result
+      of the calculation", "title": "Result", "type": "integer"}, "explanation": {"description":
+      "Brief explanation of the calculation", "title": "Explanation", "type": "string"}},
+      "required": ["operation", "result", "explanation"], "title": "CalculationResult",
+      "type": "object", "additionalProperties": false, "propertyOrdering": ["operation",
+      "result", "explanation"]}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '3166'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      x-goog-api-client:
+      - google-genai-sdk/1.49.0 gl-python/3.13.12
+      x-goog-api-key:
+      - X-GOOG-API-KEY-XXX
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-001:generateContent
+  response:
+    body:
+      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
+        [\n          {\n            \"functionCall\": {\n              \"name\": \"structured_output\",\n
+        \             \"args\": {\n                \"result\": 42,\n                \"explanation\":
+        \"15 + 27 = 42\",\n                \"operation\": \"addition\"\n              }\n
+        \           }\n          }\n        ],\n        \"role\": \"model\"\n      },\n
+        \     \"finishReason\": \"STOP\",\n      \"avgLogprobs\": -0.07498827245500353\n
+        \   }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\": 421,\n    \"candidatesTokenCount\":
+        18,\n    \"totalTokenCount\": 439,\n    \"promptTokensDetails\": [\n      {\n
+        \       \"modality\": \"TEXT\",\n        \"tokenCount\": 421\n      }\n    ],\n
+        \   \"candidatesTokensDetails\": [\n      {\n        \"modality\": \"TEXT\",\n
+        \       \"tokenCount\": 18\n      }\n    ]\n  },\n  \"modelVersion\": \"gemini-2.0-flash-001\",\n
+        \ \"responseId\": \"vlefac7bJb6TjMcPzYWh0Ag\"\n}\n"
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Wed, 25 Feb 2026 20:12:47 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=774
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      X-Frame-Options:
+      - X-FRAME-OPTIONS-XXX
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/test_custom_converter_cls.yaml

@@ -1,97 +1,120 @@
 interactions:
 - request:
-    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
-      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}'
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
+      scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expected criteria for your final
+      answer: The score of the title.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\nFormat your final answer according to the
+      following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nIMPORTANT:
+      Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or
+      modify the meaning of the content. Only structure it to match the schema format.\n\nDo
+      not include the OpenAPI schema in the final output. Ensure the final output
+      does not include any code block markers like ```json or ```python.\n\nProvide
+      your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}'
     headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate, zstd
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
       connection:
       - keep-alive
       content-length:
-      - '1394'
+      - '1421'
       content-type:
       - application/json
       host:
       - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.109.1
       x-stainless-arch:
-      - arm64
+      - X-STAINLESS-ARCH-XXX
       x-stainless-async:
       - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
       x-stainless-lang:
       - python
       x-stainless-os:
-      - MacOS
+      - X-STAINLESS-OS-XXX
       x-stainless-package-version:
-      - 1.109.1
+      - 1.83.0
       x-stainless-read-timeout:
-      - '600'
+      - X-STAINLESS-READ-TIMEOUT-XXX
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.12.9
+      - 3.13.12
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-CYg0OJQX3eMkY3pcrZz7iSh2HHTPF\",\n  \"object\": \"chat.completion\",\n  \"created\": 1762380656,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal Answer: {\\\"score\\\":4}\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 294,\n    \"completion_tokens\": 18,\n    \"total_tokens\": 312,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\": \"fp_4c2851f862\"\n}\n"
+      string: "{\n  \"id\": \"chatcmpl-DDDzfvCsU0fZWdxFwjGh6dmaEheAW\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772044427,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"score\\\":4}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        276,\n    \"completion_tokens\": 5,\n    \"total_tokens\": 281,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n"
     headers:
       CF-RAY:
-      - REDACTED-RAY
+      - CF-RAY-XXX
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Wed, 05 Nov 2025 22:10:56 GMT
+      - Wed, 25 Feb 2026 18:33:48 GMT
       Server:
       - cloudflare
-      Set-Cookie:
-      - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:40:56 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Strict-Transport-Security:
-      - max-age=31536000; includeSubDomains; preload
+      - STS-XXX
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       access-control-expose-headers:
-      - X-Request-ID
+      - ACCESS-CONTROL-XXX
       alt-svc:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
       openai-organization:
-      - user-hortuttj2f3qtmxyik2zxf4q
+      - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '770'
+      - '552'
       openai-project:
-      - proj_fL4UBWR1CMpAAdgzaSKqsVvA
+      - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '796'
+      set-cookie:
+      - SET-COOKIE-XXX
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:
-      - '500'
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
       x-ratelimit-limit-tokens:
-      - '200000'
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
       x-ratelimit-remaining-requests:
-      - '499'
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
       x-ratelimit-remaining-tokens:
-      - '199687'
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
       x-ratelimit-reset-requests:
-      - 120ms
+      - X-RATELIMIT-RESET-REQUESTS-XXX
       x-ratelimit-reset-tokens:
-      - 93ms
+      - X-RATELIMIT-RESET-TOKENS-XXX
       x-request-id:
-      - req_REDACTED
+      - X-REQUEST-ID-XXX
     status:
       code: 200
       message: OK

lib/crewai/tests/cassettes/test_guardrail_when_an_error_occurs.yaml

@@ -1,189 +1,121 @@
 interactions:
 - request:
-    body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test Backstory\nYour personal goal is: Test Goal\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: Gather information about available books on the First World War\n\nThis is the expected criteria for your final answer: A list of available books on the First World War\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    body: '{"messages":[{"role":"system","content":"You are Test Agent. Test Backstory\nYour
+      personal goal is: Test Goal"},{"role":"user","content":"\nCurrent Task: Gather
+      information about available books on the First World War\n\nThis is the expected
+      criteria for your final answer: A list of available books on the First World
+      War\nyou MUST return the actual complete content as the final answer, not a
+      summary.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}'
     headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
       connection:
       - keep-alive
       content-length:
-      - '903'
+      - '465'
       content-type:
       - application/json
       host:
       - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.68.2
       x-stainless-arch:
-      - arm64
+      - X-STAINLESS-ARCH-XXX
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - MacOS
+      - X-STAINLESS-OS-XXX
       x-stainless-package-version:
-      - 1.68.2
-      x-stainless-raw-response:
-      - 'true'
+      - 1.83.0
       x-stainless-read-timeout:
-      - '600.0'
+      - X-STAINLESS-READ-TIMEOUT-XXX
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.12.9
+      - 3.13.12
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-BReRV6HdeL9wUgmKwfAZfVjuGdpAo\",\n  \"object\": \"chat.completion\",\n  \"created\": 1745930017,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal Answer: Here is a comprehensive list of available books on the First World War:\\n\\n1. **\\\"The Sleepwalkers: How Europe Went to War in 1914\\\" by Christopher Clark**  \\n   This book delves into the complex factors that led to the outbreak of the war, offering insights into the political and social dynamics of early 20th century Europe.\\n\\n2. **\\\"A World Undone: The Story of the Great War, 1914 to 1918\\\" by G.J. Meyer**  \\n   Meyer's expansive narrative covers the entire war with a focus on both military strategies and the human experiences endured by soldiers and civilians alike.\\n\\n3. **\\\"All Quiet on the Western Front\\\" by Erich Maria\
-        \ Remarque**  \\n   A poignant novel that captures the resilience and trauma experienced by German soldiers during World War I, based on the author's own experiences.\\n\\n4. **\\\"The First World War\\\" by John Keegan**  \\n   Keegan provides a detailed military history of the war, featuring insights on battles, strategies, and the overall impact on global affairs.\\n\\n5. **\\\"Goodbye to All That\\\" by Robert Graves**  \\n   This autobiography recounts the author's experiences as a soldier during the war, offering a personal and critical perspective on the conflicts and the post-war era.\\n\\n6. **\\\"Catastrophe 1914: Europe Goes to War\\\" by Max Hastings**  \\n   Hastings chronicles the events leading up to World War I and the early battles, detailing the war's initial impact on European societies.\\n\\n7. **\\\"The War That Ended Peace: The Road to 1914\\\" by Margaret MacMillan**  \\n   MacMillan explores the political and historical factors that contributed to the outbreak\
-        \ of war, emphasizing the decisions made by leaders across Europe.\\n\\n8. **\\\"The First World War: A Complete History\\\" by Martin Gilbert**  \\n   This complete history takes readers through the entirety of the war, from its causes to its aftermath, using a wide range of sources.\\n\\n9. **\\\"1914: The Year the World Ended\\\" by Paul Ham**  \\n   Ham focuses on the pivotal year of 1914 and the early war's devastation, analyzing its long-lasting effects on the world.\\n\\n10. **\\\"War Horse\\\" by Michael Morpurgo**  \\n    This children's novel tells the story of a horse and his experiences during the war, highlighting the bond between animals and humans amidst the chaos.\\n\\nEach of these books offers unique perspectives and rich details about the First World War, making them valuable resources for anyone interested in this pivotal period in history.\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\"\
-        : \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 170,\n    \"completion_tokens\": 534,\n    \"total_tokens\": 704,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\": \"fp_dbaca60df0\"\n}\n"
+      string: "{\n  \"id\": \"chatcmpl-DDGA6ArRnT0S8ME2I1R4x9Mo4JyGJ\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772052762,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Here is a list of available books on
+        the First World War:\\n\\n1. \\\"The Guns of August\\\" by Barbara W. Tuchman\\n2.
+        \\\"A World Undone: The Story of the Great War, 1914 to 1918\\\" by G.J. Meyer\\n3.
+        \\\"The First World War\\\" by John Keegan\\n4. \\\"The Sleepwalkers: How
+        Europe Went to War in 1914\\\" by Christopher Clark\\n5. \\\"To End All Wars:
+        A Story of Loyalty and Rebellion, 1914-1918\\\" by Adam Hochschild\\n6. \\\"World
+        War I: The Definitive Visual History\\\" by R.G. Grant\\n7. \\\"Catastrophe
+        1914: Europe Goes to War\\\" by Max Hastings\\n8. \\\"The Great War and Modern
+        Memory\\\" by Paul Fussell\\n9. \\\"Paris 1919: Six Months That Changed the
+        World\\\" by Margaret MacMillan\\n10. \\\"The Pity of War: Explaining World
+        War I\\\" by Niall Ferguson\\n\\nIf you need further details on any of these
+        titles, feel free to ask.\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 84,\n    \"completion_tokens\":
+        230,\n    \"total_tokens\": 314,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n"
     headers:
       CF-RAY:
-      - 937ed42dee2e621f-GRU
+      - CF-RAY-XXX
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Tue, 29 Apr 2025 12:33:48 GMT
+      - Wed, 25 Feb 2026 20:52:46 GMT
       Server:
       - cloudflare
-      Set-Cookie:
-      - __cf_bm=mLRCnpdB3n_6medIZWHnUu8MNRGZsD6riaRhN47PK74-1745930028-1.0.1.1-M2lDM1_V9hNCK0MZrBnFalF3lndC3JkS8zhDOGww_LmOrgdpU9fZLpNZUmyinCQOnlCjDjDYJUECM82ffT1anqBiO1NoDeNp91EPKiK7s.8; path=/; expires=Tue, 29-Apr-25 13:03:48 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      - _cfuvid=eTrj_ZhCx2XuylS5vYROwUlPrJBwOyrbS2Ki.msl45E-1745930028010-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Strict-Transport-Security:
+      - STS-XXX
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       access-control-expose-headers:
-      - X-Request-ID
+      - ACCESS-CONTROL-XXX
       alt-svc:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
       openai-organization:
-      - crewai-iuxna1
+      - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '10856'
+      - '3250'
+      openai-project:
+      - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
+      set-cookie:
+      - SET-COOKIE-XXX
+      x-openai-proxy-wasm:
+      - v0.1
       x-ratelimit-limit-requests:
-      - '30000'
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
       x-ratelimit-limit-tokens:
-      - '150000000'
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
       x-ratelimit-remaining-requests:
-      - '29999'
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
       x-ratelimit-remaining-tokens:
-      - '149999807'
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
       x-ratelimit-reset-requests:
-      - 2ms
+      - X-RATELIMIT-RESET-REQUESTS-XXX
       x-ratelimit-reset-tokens:
-      - 0s
+      - X-RATELIMIT-RESET-TOKENS-XXX
       x-request-id:
-      - req_bc2d62d8325b2bdd3e98544a66389132
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"messages": [{"role": "system", "content": "You are Guardrail Agent. You are a expert at validating the output of a task. By providing effective feedback if the output is not valid.\nYour personal goal is: Validate the output of the task\n\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!\nIMPORTANT: Your final answer MUST contain all the information requested in the following format: {\n  \"valid\": bool,\n  \"feedback\": str | None\n}\n\nIMPORTANT: Ensure the final output does not include any code block markers like ```json or ```python."}, {"role": "user", "content": "\n        Ensure the following task result complies with the given guardrail.\n\n        Task result:\n        Here is a comprehensive list of available books on
-      the First World War:\n\n1. **\"The Sleepwalkers: How Europe Went to War in 1914\" by Christopher Clark**  \n   This book delves into the complex factors that led to the outbreak of the war, offering insights into the political and social dynamics of early 20th century Europe.\n\n2. **\"A World Undone: The Story of the Great War, 1914 to 1918\" by G.J. Meyer**  \n   Meyer''s expansive narrative covers the entire war with a focus on both military strategies and the human experiences endured by soldiers and civilians alike.\n\n3. **\"All Quiet on the Western Front\" by Erich Maria Remarque**  \n   A poignant novel that captures the resilience and trauma experienced by German soldiers during World War I, based on the author''s own experiences.\n\n4. **\"The First World War\" by John Keegan**  \n   Keegan provides a detailed military history of the war, featuring insights on battles, strategies, and the overall impact on global affairs.\n\n5. **\"Goodbye to All That\" by Robert Graves**  \n   This
-      autobiography recounts the author''s experiences as a soldier during the war, offering a personal and critical perspective on the conflicts and the post-war era.\n\n6. **\"Catastrophe 1914: Europe Goes to War\" by Max Hastings**  \n   Hastings chronicles the events leading up to World War I and the early battles, detailing the war''s initial impact on European societies.\n\n7. **\"The War That Ended Peace: The Road to 1914\" by Margaret MacMillan**  \n   MacMillan explores the political and historical factors that contributed to the outbreak of war, emphasizing the decisions made by leaders across Europe.\n\n8. **\"The First World War: A Complete History\" by Martin Gilbert**  \n   This complete history takes readers through the entirety of the war, from its causes to its aftermath, using a wide range of sources.\n\n9. **\"1914: The Year the World Ended\" by Paul Ham**  \n   Ham focuses on the pivotal year of 1914 and the early war''s devastation, analyzing its long-lasting effects
-      on the world.\n\n10. **\"War Horse\" by Michael Morpurgo**  \n    This children''s novel tells the story of a horse and his experiences during the war, highlighting the bond between animals and humans amidst the chaos.\n\nEach of these books offers unique perspectives and rich details about the First World War, making them valuable resources for anyone interested in this pivotal period in history.\n\n        Guardrail:\n        Ensure the authors are from Italy\n        \n        Your task:\n        - Confirm if the Task result complies with the guardrail.\n        - If not, provide clear feedback explaining what is wrong (e.g., by how much it violates the rule, or what specific part fails).\n        - Focus only on identifying issues \u2014 do not propose corrections.\n        - If the Task result complies with the guardrail, saying that is valid\n        "}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '3917'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=mLRCnpdB3n_6medIZWHnUu8MNRGZsD6riaRhN47PK74-1745930028-1.0.1.1-M2lDM1_V9hNCK0MZrBnFalF3lndC3JkS8zhDOGww_LmOrgdpU9fZLpNZUmyinCQOnlCjDjDYJUECM82ffT1anqBiO1NoDeNp91EPKiK7s.8; _cfuvid=eTrj_ZhCx2XuylS5vYROwUlPrJBwOyrbS2Ki.msl45E-1745930028010-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.68.2
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.68.2
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-read-timeout:
-      - '600.0'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.9
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: "{\n  \"id\": \"chatcmpl-BReTBRCAvSDG5VMdtF9ZjByy7lqSJ\",\n  \"object\": \"chat.completion\",\n  \"created\": 1745930121,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"Thought: I now can give a great answer  \\nFinal Answer: {\\n  \\\"valid\\\": false,\\n  \\\"feedback\\\": \\\"None of the authors listed in the task result are from Italy. All the authors mentioned are from other countries, such as Germany, the UK, and the US.\\\"\\n}\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 797,\n    \"completion_tokens\": 60,\n    \"total_tokens\": 857,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"\
-        audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\": \"fp_0392822090\"\n}\n"
-    headers:
-      CF-RAY:
-      - 937ed6bd68faa435-GRU
-      Connection:
-      - keep-alive
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 29 Apr 2025 12:35:23 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '1138'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '30000'
-      x-ratelimit-limit-tokens:
-      - '150000000'
-      x-ratelimit-remaining-requests:
-      - '29999'
-      x-ratelimit-remaining-tokens:
-      - '149999072'
-      x-ratelimit-reset-requests:
-      - 2ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_2ba1be014a5974ba354aff564e26516a
+      - X-REQUEST-ID-XXX
     status:
       code: 200
       message: OK

lib/crewai/tests/cassettes/test_json_property_without_output_json.yaml

@@ -1,11 +1,14 @@
 interactions:
 - request:
-    body: '{"trace_id": "4ced1ade-0d34-4d28-a47d-61011b1f3582", "execution_type": "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null, "crew_name": "crew", "flow_name": null, "crewai_version": "1.2.1", "privacy_level": "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count": 0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-10-31T07:25:08.937105+00:00"}, "ephemeral_trace_id": "4ced1ade-0d34-4d28-a47d-61011b1f3582"}'
+    body: '{"trace_id": "4ced1ade-0d34-4d28-a47d-61011b1f3582", "execution_type":
+      "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null,
+      "crew_name": "crew", "flow_name": null, "crewai_version": "1.2.1", "privacy_level":
+      "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count":
+      0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-10-31T07:25:08.937105+00:00"},
+      "ephemeral_trace_id": "4ced1ade-0d34-4d28-a47d-61011b1f3582"}'
     headers:
       Accept:
       - '*/*'
-      Accept-Encoding:
-      - gzip, deflate, zstd
       Connection:
       - keep-alive
       Content-Length:
@@ -13,11 +16,13 @@ interactions:
       Content-Type:
       - application/json
       User-Agent:
-      - CrewAI-CLI/1.2.1
+      - X-USER-AGENT-XXX
       X-Crewai-Organization-Id:
       - 73c2b193-f579-422c-84c7-76a39a1da77f
       X-Crewai-Version:
       - 1.2.1
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
     method: POST
     uri: https://app.crewai.com/crewai_plus/api/v1/tracing/ephemeral/batches
   response:
@@ -35,46 +40,60 @@ interactions:
       cache-control:
       - no-store
       content-security-policy:
-      - 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/ https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net https://js.hscollectedforms.net
-        https://js.usemessages.com https://snap.licdn.com https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data: *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com; connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com https://api.hubspot.com
-        https://forms.hscollectedforms.net https://api.hubapi.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509 https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self'' *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com https://drive.google.com https://slides.google.com https://accounts.google.com https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/ https://www.youtube.com https://share.descript.com'
+      - CSP-FILTERED
       etag:
-      - W/"684f9dff2cfefa325ac69ea38dba2309"
+      - ETAG-XXX
       expires:
       - '0'
       permissions-policy:
-      - camera=(), microphone=(self), geolocation=()
+      - PERMISSIONS-POLICY-XXX
       pragma:
       - no-cache
       referrer-policy:
-      - strict-origin-when-cross-origin
+      - REFERRER-POLICY-XXX
       strict-transport-security:
-      - max-age=63072000; includeSubDomains
+      - STS-XXX
       vary:
       - Accept
       x-content-type-options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       x-frame-options:
-      - SAMEORIGIN
+      - X-FRAME-OPTIONS-XXX
       x-permitted-cross-domain-policies:
-      - none
+      - X-PERMITTED-XXX
       x-request-id:
-      - 630cda16-c991-4ed0-b534-16c03eb2ffca
+      - X-REQUEST-ID-XXX
       x-runtime:
-      - '0.072382'
+      - X-RUNTIME-XXX
       x-xss-protection:
-      - 1; mode=block
+      - X-XSS-PROTECTION-XXX
     status:
       code: 201
       message: Created
 - request:
-    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer contains only the content in the following format: {\n  \"properties\": {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
-      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nEnsure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}'
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
+      scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo
+      give my best complete final answer to the task respond using the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
+      answer must be the great and the most complete as possible, it must be outcome
+      described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expected criteria for your final
+      answer: The score of the title.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\nEnsure your final answer contains only
+      the content in the following format: {\n  \"properties\": {\n    \"score\":
+      {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\":
+      [\n    \"score\"\n  ],\n  \"title\": \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\":
+      false\n}\n\nEnsure the final output does not include any code block markers
+      like ```json or ```python.\n\nBegin! This is VERY important to you, use the
+      tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}'
     headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate, zstd
+      - ACCEPT-ENCODING-XXX
       connection:
       - keep-alive
       content-length:
@@ -83,20 +102,18 @@ interactions:
       - application/json
       host:
       - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.109.1
       x-stainless-arch:
-      - arm64
+      - X-STAINLESS-ARCH-XXX
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - MacOS
+      - X-STAINLESS-OS-XXX
       x-stainless-package-version:
       - 1.109.1
       x-stainless-read-timeout:
-      - '600'
+      - X-STAINLESS-READ-TIMEOUT-XXX
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
@@ -107,10 +124,21 @@ interactions:
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-CWdnRkRPYTVe5JfVO7aC1cdVfqIdd\",\n  \"object\": \"chat.completion\",\n  \"created\": 1761895509,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\n{\\n  \\\"score\\\": 4\\n}\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 281,\n    \"completion_tokens\": 19,\n    \"total_tokens\": 300,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\": \"fp_4c2851f862\"\n}\n"
+      string: "{\n  \"id\": \"chatcmpl-CWdnRkRPYTVe5JfVO7aC1cdVfqIdd\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1761895509,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\n{\\n
+        \ \\\"score\\\": 4\\n}\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 281,\n    \"completion_tokens\":
+        19,\n    \"total_tokens\": 300,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_4c2851f862\"\n}\n"
     headers:
       CF-RAY:
-      - 99716ab4788dea35-FCO
+      - CF-RAY-XXX
       Connection:
       - keep-alive
       Content-Type:
@@ -120,26 +148,25 @@ interactions:
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=S.q8_0ONHDHBHNOJdMZHwJDue9lKhWQHpKuP2lsspx4-1761895510-1.0.1.1-QUDxMm9SVfRT2R188bLcvxUd6SXIBmZgnz3D35UF95nNg8zX5Gzdg2OmU.uo29rqaGatjupcLPNMyhfOqeoyhNQ28Zz1ESSQLq0y70x3IvM; path=/; expires=Fri, 31-Oct-25 07:55:10 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      - _cfuvid=TvP4GePeQO8E5c_xWNGzJb84f940MFRG_lZ_0hWAc5M-1761895510432-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      - SET-COOKIE-XXX
       Strict-Transport-Security:
-      - max-age=31536000; includeSubDomains; preload
+      - STS-XXX
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       access-control-expose-headers:
-      - X-Request-ID
+      - ACCESS-CONTROL-XXX
       alt-svc:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
       openai-organization:
-      - crewai-iuxna1
+      - OPENAI-ORG-XXX
       openai-processing-ms:
       - '569'
       openai-project:
-      - proj_xitITlrFeen7zjNSzML82h9x
+      - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
       x-envoy-upstream-service-time:
@@ -149,40 +176,119 @@ interactions:
       x-ratelimit-limit-project-tokens:
       - '150000000'
       x-ratelimit-limit-requests:
-      - '30000'
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
       x-ratelimit-limit-tokens:
-      - '150000000'
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
       x-ratelimit-remaining-project-tokens:
       - '149999700'
       x-ratelimit-remaining-requests:
-      - '29999'
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
       x-ratelimit-remaining-tokens:
-      - '149999700'
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
       x-ratelimit-reset-project-tokens:
       - 0s
       x-ratelimit-reset-requests:
-      - 2ms
+      - X-RATELIMIT-RESET-REQUESTS-XXX
       x-ratelimit-reset-tokens:
-      - 0s
+      - X-RATELIMIT-RESET-TOKENS-XXX
       x-request-id:
-      - req_393e029e99d54ab0b4e7c69c5cba099f
+      - X-REQUEST-ID-XXX
     status:
       code: 200
       message: OK
 - request:
-    body: '{"events": [{"event_id": "ea607d3f-c9ff-4aa8-babb-a84eb6d16663", "timestamp": "2025-10-31T07:25:08.935640+00:00", "type": "crew_kickoff_started", "event_data": {"timestamp": "2025-10-31T07:25:08.935640+00:00", "type": "crew_kickoff_started", "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, "task_id": null, "task_name": null, "agent_id": null, "agent_role": null, "crew_name": "crew", "crew": null, "inputs": null}}, {"event_id": "8e792d78-fe9c-4601-a7b4-7b105fa8fb40", "timestamp": "2025-10-31T07:25:08.937816+00:00", "type": "task_started", "event_data": {"task_description": "Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''", "expected_output": "The score of the title.", "task_name": "Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''", "context": "", "agent_role": "Scorer", "task_id": "677cf2dd-96a9-4eac-9140-0ecaba9609f7"}}, {"event_id": "a2fcdfee-a395-4dc8-99b8-ba3d8d843a70",
-      "timestamp": "2025-10-31T07:25:08.938816+00:00", "type": "agent_execution_started", "event_data": {"agent_role": "Scorer", "agent_goal": "Score the title", "agent_backstory": "You''re an expert scorer, specialized in scoring titles."}}, {"event_id": "b0ba7582-6ea0-4b66-a64a-0a1e38d57502", "timestamp": "2025-10-31T07:25:08.938996+00:00", "type": "llm_call_started", "event_data": {"timestamp": "2025-10-31T07:25:08.938996+00:00", "type": "llm_call_started", "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, "task_id": "677cf2dd-96a9-4eac-9140-0ecaba9609f7", "task_name": "Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''", "agent_id": "8d6e3481-36fa-4fca-9665-977e6d76a969", "agent_role": "Scorer", "from_task": null, "from_agent": null, "model": "gpt-4.1-mini", "messages": [{"role": "system", "content": "You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score
-      the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer contains only the content in the following format: {\n  \"properties\": {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\": \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nEnsure the final output does not include any
-      code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "tools": null, "callbacks": ["<crewai.utilities.token_counter_callback.TokenCalcHandler object at 0x11da36000>"], "available_functions": null}}, {"event_id": "ab6b168b-d954-494f-ae58-d9ef7a1941dc", "timestamp": "2025-10-31T07:25:10.466669+00:00", "type": "llm_call_completed", "event_data": {"timestamp": "2025-10-31T07:25:10.466669+00:00", "type": "llm_call_completed", "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, "task_id": "677cf2dd-96a9-4eac-9140-0ecaba9609f7", "task_name": "Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''", "agent_id": "8d6e3481-36fa-4fca-9665-977e6d76a969", "agent_role": "Scorer", "from_task": null, "from_agent": null, "messages": [{"role": "system", "content": "You are Scorer. You''re an expert
-      scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer contains only the content in the following format: {\n  \"properties\": {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\": \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\":
-      false\n}\n\nEnsure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "response": "Thought: I now can give a great answer\n{\n  \"score\": 4\n}", "call_type": "<LLMCallType.LLM_CALL: ''llm_call''>", "model": "gpt-4.1-mini"}}, {"event_id": "0b8a17b6-e7d2-464d-a969-56dd705a40ef", "timestamp": "2025-10-31T07:25:10.466933+00:00", "type": "agent_execution_completed", "event_data": {"agent_role": "Scorer", "agent_goal": "Score the title", "agent_backstory": "You''re an expert scorer, specialized in scoring titles."}}, {"event_id": "b835b8e7-992b-4364-9ff8-25c81203ef77", "timestamp": "2025-10-31T07:25:10.467175+00:00", "type": "task_completed", "event_data": {"task_description": "Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''", "task_name": "Give me an integer score
-      between 1-5 for the following title: ''The impact of AI in the future of work''", "task_id": "677cf2dd-96a9-4eac-9140-0ecaba9609f7", "output_raw": "Thought: I now can give a great answer\n{\n  \"score\": 4\n}", "output_format": "OutputFormat.PYDANTIC", "agent_role": "Scorer"}}, {"event_id": "a9973b74-9ca6-46c3-b219-0b11ffa9e210", "timestamp": "2025-10-31T07:25:10.469421+00:00", "type": "crew_kickoff_completed", "event_data": {"timestamp": "2025-10-31T07:25:10.469421+00:00", "type": "crew_kickoff_completed", "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, "task_id": null, "task_name": null, "agent_id": null, "agent_role": null, "crew_name": "crew", "crew": null, "output": {"description": "Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''", "name": "Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''", "expected_output": "The score of the title.",
-      "summary": "Give me an integer score between 1-5 for the following...", "raw": "Thought: I now can give a great answer\n{\n  \"score\": 4\n}", "pydantic": {}, "json_dict": null, "agent": "Scorer", "output_format": "pydantic"}, "total_tokens": 300}}], "batch_metadata": {"events_count": 8, "batch_sequence": 1, "is_final_batch": false}}'
+    body: '{"events": [{"event_id": "ea607d3f-c9ff-4aa8-babb-a84eb6d16663", "timestamp":
+      "2025-10-31T07:25:08.935640+00:00", "type": "crew_kickoff_started", "event_data":
+      {"timestamp": "2025-10-31T07:25:08.935640+00:00", "type": "crew_kickoff_started",
+      "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
+      "task_id": null, "task_name": null, "agent_id": null, "agent_role": null, "crew_name":
+      "crew", "crew": null, "inputs": null}}, {"event_id": "8e792d78-fe9c-4601-a7b4-7b105fa8fb40",
+      "timestamp": "2025-10-31T07:25:08.937816+00:00", "type": "task_started", "event_data":
+      {"task_description": "Give me an integer score between 1-5 for the following
+      title: ''The impact of AI in the future of work''", "expected_output": "The
+      score of the title.", "task_name": "Give me an integer score between 1-5 for
+      the following title: ''The impact of AI in the future of work''", "context":
+      "", "agent_role": "Scorer", "task_id": "677cf2dd-96a9-4eac-9140-0ecaba9609f7"}},
+      {"event_id": "a2fcdfee-a395-4dc8-99b8-ba3d8d843a70", "timestamp": "2025-10-31T07:25:08.938816+00:00",
+      "type": "agent_execution_started", "event_data": {"agent_role": "Scorer", "agent_goal":
+      "Score the title", "agent_backstory": "You''re an expert scorer, specialized
+      in scoring titles."}}, {"event_id": "b0ba7582-6ea0-4b66-a64a-0a1e38d57502",
+      "timestamp": "2025-10-31T07:25:08.938996+00:00", "type": "llm_call_started",
+      "event_data": {"timestamp": "2025-10-31T07:25:08.938996+00:00", "type": "llm_call_started",
+      "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
+      "task_id": "677cf2dd-96a9-4eac-9140-0ecaba9609f7", "task_name": "Give me an
+      integer score between 1-5 for the following title: ''The impact of AI in the
+      future of work''", "agent_id": "8d6e3481-36fa-4fca-9665-977e6d76a969", "agent_role":
+      "Scorer", "from_task": null, "from_agent": null, "model": "gpt-4.1-mini", "messages":
+      [{"role": "system", "content": "You are Scorer. You''re an expert scorer, specialized
+      in scoring titles.\nYour personal goal is: Score the title\nTo give my best
+      complete final answer to the task respond using the exact following format:\n\nThought:
+      I now can give a great answer\nFinal Answer: Your final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expected criteria for your final
+      answer: The score of the title.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\nEnsure your final answer contains only
+      the content in the following format: {\n  \"properties\": {\n    \"score\":
+      {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\":
+      [\n    \"score\"\n  ],\n  \"title\": \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\":
+      false\n}\n\nEnsure the final output does not include any code block markers
+      like ```json or ```python.\n\nBegin! This is VERY important to you, use the
+      tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
+      "tools": null, "callbacks": ["<crewai.utilities.token_counter_callback.TokenCalcHandler
+      object at 0x11da36000>"], "available_functions": null}}, {"event_id": "ab6b168b-d954-494f-ae58-d9ef7a1941dc",
+      "timestamp": "2025-10-31T07:25:10.466669+00:00", "type": "llm_call_completed",
+      "event_data": {"timestamp": "2025-10-31T07:25:10.466669+00:00", "type": "llm_call_completed",
+      "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
+      "task_id": "677cf2dd-96a9-4eac-9140-0ecaba9609f7", "task_name": "Give me an
+      integer score between 1-5 for the following title: ''The impact of AI in the
+      future of work''", "agent_id": "8d6e3481-36fa-4fca-9665-977e6d76a969", "agent_role":
+      "Scorer", "from_task": null, "from_agent": null, "messages": [{"role": "system",
+      "content": "You are Scorer. You''re an expert scorer, specialized in scoring
+      titles.\nYour personal goal is: Score the title\nTo give my best complete final
+      answer to the task respond using the exact following format:\n\nThought: I now
+      can give a great answer\nFinal Answer: Your final answer must be the great and
+      the most complete as possible, it must be outcome described.\n\nI MUST use these
+      formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task:
+      Give me an integer score between 1-5 for the following title: ''The impact of
+      AI in the future of work''\n\nThis is the expected criteria for your final answer:
+      The score of the title.\nyou MUST return the actual complete content as the
+      final answer, not a summary.\nEnsure your final answer contains only the content
+      in the following format: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nEnsure
+      the final output does not include any code block markers like ```json or ```python.\n\nBegin!
+      This is VERY important to you, use the tools available and give your best Final
+      Answer, your job depends on it!\n\nThought:"}], "response": "Thought: I now
+      can give a great answer\n{\n  \"score\": 4\n}", "call_type": "<LLMCallType.LLM_CALL:
+      ''llm_call''>", "model": "gpt-4.1-mini"}}, {"event_id": "0b8a17b6-e7d2-464d-a969-56dd705a40ef",
+      "timestamp": "2025-10-31T07:25:10.466933+00:00", "type": "agent_execution_completed",
+      "event_data": {"agent_role": "Scorer", "agent_goal": "Score the title", "agent_backstory":
+      "You''re an expert scorer, specialized in scoring titles."}}, {"event_id": "b835b8e7-992b-4364-9ff8-25c81203ef77",
+      "timestamp": "2025-10-31T07:25:10.467175+00:00", "type": "task_completed", "event_data":
+      {"task_description": "Give me an integer score between 1-5 for the following
+      title: ''The impact of AI in the future of work''", "task_name": "Give me an
+      integer score between 1-5 for the following title: ''The impact of AI in the
+      future of work''", "task_id": "677cf2dd-96a9-4eac-9140-0ecaba9609f7", "output_raw":
+      "Thought: I now can give a great answer\n{\n  \"score\": 4\n}", "output_format":
+      "OutputFormat.PYDANTIC", "agent_role": "Scorer"}}, {"event_id": "a9973b74-9ca6-46c3-b219-0b11ffa9e210",
+      "timestamp": "2025-10-31T07:25:10.469421+00:00", "type": "crew_kickoff_completed",
+      "event_data": {"timestamp": "2025-10-31T07:25:10.469421+00:00", "type": "crew_kickoff_completed",
+      "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
+      "task_id": null, "task_name": null, "agent_id": null, "agent_role": null, "crew_name":
+      "crew", "crew": null, "output": {"description": "Give me an integer score between
+      1-5 for the following title: ''The impact of AI in the future of work''", "name":
+      "Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''", "expected_output": "The score of the title.",
+      "summary": "Give me an integer score between 1-5 for the following...", "raw":
+      "Thought: I now can give a great answer\n{\n  \"score\": 4\n}", "pydantic":
+      {}, "json_dict": null, "agent": "Scorer", "output_format": "pydantic"}, "total_tokens":
+      300}}], "batch_metadata": {"events_count": 8, "batch_sequence": 1, "is_final_batch":
+      false}}'
     headers:
       Accept:
       - '*/*'
-      Accept-Encoding:
-      - gzip, deflate, zstd
       Connection:
       - keep-alive
       Content-Length:
@@ -190,11 +296,13 @@ interactions:
       Content-Type:
       - application/json
       User-Agent:
-      - CrewAI-CLI/1.2.1
+      - X-USER-AGENT-XXX
       X-Crewai-Organization-Id:
       - 73c2b193-f579-422c-84c7-76a39a1da77f
       X-Crewai-Version:
       - 1.2.1
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
     method: POST
     uri: https://app.crewai.com/crewai_plus/api/v1/tracing/ephemeral/batches/4ced1ade-0d34-4d28-a47d-61011b1f3582/events
   response:
@@ -212,35 +320,33 @@ interactions:
       cache-control:
       - no-store
       content-security-policy:
-      - 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/ https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net https://js.hscollectedforms.net
-        https://js.usemessages.com https://snap.licdn.com https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data: *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com; connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com https://api.hubspot.com
-        https://forms.hscollectedforms.net https://api.hubapi.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509 https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self'' *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com https://drive.google.com https://slides.google.com https://accounts.google.com https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/ https://www.youtube.com https://share.descript.com'
+      - CSP-FILTERED
       etag:
-      - W/"be223998b84365d3a863f942c880adfb"
+      - ETAG-XXX
       expires:
       - '0'
       permissions-policy:
-      - camera=(), microphone=(self), geolocation=()
+      - PERMISSIONS-POLICY-XXX
       pragma:
       - no-cache
       referrer-policy:
-      - strict-origin-when-cross-origin
+      - REFERRER-POLICY-XXX
       strict-transport-security:
-      - max-age=63072000; includeSubDomains
+      - STS-XXX
       vary:
       - Accept
       x-content-type-options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       x-frame-options:
-      - SAMEORIGIN
+      - X-FRAME-OPTIONS-XXX
       x-permitted-cross-domain-policies:
-      - none
+      - X-PERMITTED-XXX
       x-request-id:
-      - 9c19d6df-9190-4764-afed-f3444939d2e4
+      - X-REQUEST-ID-XXX
       x-runtime:
-      - '0.123911'
+      - X-RUNTIME-XXX
       x-xss-protection:
-      - 1; mode=block
+      - X-XSS-PROTECTION-XXX
     status:
       code: 200
       message: OK
@@ -249,8 +355,6 @@ interactions:
     headers:
       Accept:
       - '*/*'
-      Accept-Encoding:
-      - gzip, deflate, zstd
       Connection:
       - keep-alive
       Content-Length:
@@ -258,11 +362,13 @@ interactions:
       Content-Type:
       - application/json
       User-Agent:
-      - CrewAI-CLI/1.2.1
+      - X-USER-AGENT-XXX
       X-Crewai-Organization-Id:
       - 73c2b193-f579-422c-84c7-76a39a1da77f
       X-Crewai-Version:
       - 1.2.1
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
     method: PATCH
     uri: https://app.crewai.com/crewai_plus/api/v1/tracing/ephemeral/batches/4ced1ade-0d34-4d28-a47d-61011b1f3582/finalize
   response:
@@ -280,35 +386,167 @@ interactions:
       cache-control:
       - no-store
       content-security-policy:
-      - 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/ https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net https://js.hscollectedforms.net
-        https://js.usemessages.com https://snap.licdn.com https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data: *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com; connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com https://api.hubspot.com
-        https://forms.hscollectedforms.net https://api.hubapi.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509 https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self'' *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com https://drive.google.com https://slides.google.com https://accounts.google.com https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/ https://www.youtube.com https://share.descript.com'
+      - CSP-FILTERED
       etag:
-      - W/"bff97e21bd1971750dcfdb102fba9dcd"
+      - ETAG-XXX
       expires:
       - '0'
       permissions-policy:
-      - camera=(), microphone=(self), geolocation=()
+      - PERMISSIONS-POLICY-XXX
       pragma:
       - no-cache
       referrer-policy:
-      - strict-origin-when-cross-origin
+      - REFERRER-POLICY-XXX
       strict-transport-security:
-      - max-age=63072000; includeSubDomains
+      - STS-XXX
       vary:
       - Accept
       x-content-type-options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       x-frame-options:
-      - SAMEORIGIN
+      - X-FRAME-OPTIONS-XXX
       x-permitted-cross-domain-policies:
-      - none
+      - X-PERMITTED-XXX
       x-request-id:
-      - 2b6cd38d-78fa-4676-94ff-80e3bcf48a03
+      - X-REQUEST-ID-XXX
       x-runtime:
-      - '0.064858'
+      - X-RUNTIME-XXX
       x-xss-protection:
-      - 1; mode=block
+      - X-XSS-PROTECTION-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
+      scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expected criteria for your final
+      answer: The score of the title.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\nFormat your final answer according to the
+      following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nIMPORTANT:
+      Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or
+      modify the meaning of the content. Only structure it to match the schema format.\n\nDo
+      not include the OpenAPI schema in the final output. Ensure the final output
+      does not include any code block markers like ```json or ```python.\n\nProvide
+      your complete response:"},{"role":"system","content":"You are Scorer. You''re
+      an expert scorer, specialized in scoring titles.\nYour personal goal is: Score
+      the title"},{"role":"user","content":"\nCurrent Task: Give me an integer score
+      between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis
+      is the expected criteria for your final answer: The score of the title.\nyou
+      MUST return the actual complete content as the final answer, not a summary.\nFormat
+      your final answer according to the following OpenAPI schema: {\n  \"properties\":
+      {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\":
+      [\n    \"score\"\n  ],\n  \"title\": \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\":
+      false\n}\n\nIMPORTANT: Preserve the original content exactly as-is. Do NOT rewrite,
+      paraphrase, or modify the meaning of the content. Only structure it to match
+      the schema format.\n\nDo not include the OpenAPI schema in the final output.
+      Ensure the final output does not include any code block markers like ```json
+      or ```python.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '2541'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.12
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-DDE0D15NvBLDvn8Wy68ZscARhqMaX\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772044461,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"score\\\":4}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        513,\n    \"completion_tokens\": 5,\n    \"total_tokens\": 518,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 25 Feb 2026 18:34:21 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '477'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      set-cookie:
+      - SET-COOKIE-XXX
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
     status:
       code: 200
       message: OK

lib/crewai/tests/cassettes/test_output_json_dict_hierarchical.yaml

@@ -426,4 +426,121 @@ interactions:
     status:
       code: 200
       message: OK
+- request:
+    body: '{"messages":[{"role":"user","content":"Thought: I now can give a great
+      answer\nFinal Answer: I would assign a score of 4 to the title \"The impact
+      of AI in the future of work.\" The title is very relevant and timely, as artificial
+      intelligence is a major transformative force affecting the labor market and
+      employment trends. It is clear and concise, effectively highlighting the focus
+      on AI''s influence on the future of work. However, while it is engaging and
+      implies substantial potential impact, it could be slightly more specific or
+      dynamic to reach an excellent level. Overall, it meets very good standards for
+      potential impact, engagement, relevance, and clarity."}],"model":"gpt-4o","tool_choice":{"type":"function","function":{"name":"ScoreOutput"}},"tools":[{"type":"function","function":{"name":"ScoreOutput","description":"Correctly
+      extracted `ScoreOutput` with all the required parameters with correct types","parameters":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"type":"object"}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1034'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.12
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-DDE0G4tjiC8Je3BD8xhWMey7kZF66\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772044464,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+        \           \"id\": \"call_x95I7UxdCvFccZ87imExKzu9\",\n            \"type\":
+        \"function\",\n            \"function\": {\n              \"name\": \"ScoreOutput\",\n
+        \             \"arguments\": \"{\\\"score\\\":4}\"\n            }\n          }\n
+        \       ],\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
+        \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+        \ \"usage\": {\n    \"prompt_tokens\": 188,\n    \"completion_tokens\": 5,\n
+        \   \"total_tokens\": 193,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_64dfa806c7\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 25 Feb 2026 18:34:24 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '385'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      set-cookie:
+      - SET-COOKIE-XXX
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
 version: 1

lib/crewai/tests/cassettes/test_output_json_dict_sequential.yaml

@@ -1,98 +1,120 @@
 interactions:
 - request:
-    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
-      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}'
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
+      scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expected criteria for your final
+      answer: The score of the title.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\nFormat your final answer according to the
+      following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nIMPORTANT:
+      Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or
+      modify the meaning of the content. Only structure it to match the schema format.\n\nDo
+      not include the OpenAPI schema in the final output. Ensure the final output
+      does not include any code block markers like ```json or ```python.\n\nProvide
+      your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}'
     headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate, zstd
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
       connection:
       - keep-alive
       content-length:
-      - '1394'
+      - '1421'
       content-type:
       - application/json
       host:
       - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.109.1
       x-stainless-arch:
-      - arm64
+      - X-STAINLESS-ARCH-XXX
       x-stainless-async:
       - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
       x-stainless-lang:
       - python
       x-stainless-os:
-      - MacOS
+      - X-STAINLESS-OS-XXX
       x-stainless-package-version:
-      - 1.109.1
+      - 1.83.0
       x-stainless-read-timeout:
-      - '600'
+      - X-STAINLESS-READ-TIMEOUT-XXX
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.12.9
+      - 3.13.12
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-CYg0UpOvDuMqlqYkt9WW8lQSkyatz\",\n  \"object\": \"chat.completion\",\n  \"created\": 1762380662,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal Answer: {\\n  \\\"score\\\": 4\\n}\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 294,\n    \"completion_tokens\": 22,\n    \"total_tokens\": 316,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\": \"fp_4c2851f862\"\
-        \n}\n"
+      string: "{\n  \"id\": \"chatcmpl-DDE5QUOVeJDiOh6TuObUjh32f7Q0g\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772044784,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"score\\\":4}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        276,\n    \"completion_tokens\": 5,\n    \"total_tokens\": 281,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n"
     headers:
       CF-RAY:
-      - REDACTED-RAY
+      - CF-RAY-XXX
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Wed, 05 Nov 2025 22:11:02 GMT
+      - Wed, 25 Feb 2026 18:39:44 GMT
       Server:
       - cloudflare
-      Set-Cookie:
-      - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:41:02 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Strict-Transport-Security:
-      - max-age=31536000; includeSubDomains; preload
+      - STS-XXX
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       access-control-expose-headers:
-      - X-Request-ID
+      - ACCESS-CONTROL-XXX
       alt-svc:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
       openai-organization:
-      - user-hortuttj2f3qtmxyik2zxf4q
+      - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '864'
+      - '303'
       openai-project:
-      - proj_fL4UBWR1CMpAAdgzaSKqsVvA
+      - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '3087'
+      set-cookie:
+      - SET-COOKIE-XXX
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:
-      - '500'
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
       x-ratelimit-limit-tokens:
-      - '200000'
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
       x-ratelimit-remaining-requests:
-      - '499'
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
       x-ratelimit-remaining-tokens:
-      - '199687'
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
       x-ratelimit-reset-requests:
-      - 120ms
+      - X-RATELIMIT-RESET-REQUESTS-XXX
       x-ratelimit-reset-tokens:
-      - 93ms
+      - X-RATELIMIT-RESET-TOKENS-XXX
       x-request-id:
-      - req_REDACTED
+      - X-REQUEST-ID-XXX
     status:
       code: 200
       message: OK

lib/crewai/tests/cassettes/test_output_json_hierarchical.yaml

@@ -427,4 +427,122 @@ interactions:
     status:
       code: 200
       message: OK
+- request:
+    body: '{"messages":[{"role":"user","content":"Thought: The title \"The impact
+      of AI in the future of work\" is highly relevant given the widespread and ongoing
+      discussions about AI''s role in transforming workplaces globally. It is clear
+      and concise, directly indicating the subject and scope, which helps the reader
+      understand what to expect. In terms of engagement, it has strong potential to
+      attract interest from professionals, researchers, and the general public curious
+      about how AI will shape jobs and employment trends. Although it is somewhat
+      broad and could be more specific to a particular aspect of work or type of AI,
+      it remains focused enough to be effective as a general overview title.\n\nFinal
+      Answer: 4"}],"model":"gpt-4o","tool_choice":{"type":"function","function":{"name":"ScoreOutput"}},"tools":[{"type":"function","function":{"name":"ScoreOutput","description":"Correctly
+      extracted `ScoreOutput` with all the required parameters with correct types","parameters":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"type":"object"}}}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1077'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.12
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-DDE0FPRrXCbAAssWcvT9wUojN8yPa\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772044463,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+        \           \"id\": \"call_237IZJqLGcX4N5MZYEd6Wz2n\",\n            \"type\":
+        \"function\",\n            \"function\": {\n              \"name\": \"ScoreOutput\",\n
+        \             \"arguments\": \"{\\\"score\\\":4}\"\n            }\n          }\n
+        \       ],\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
+        \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+        \ \"usage\": {\n    \"prompt_tokens\": 191,\n    \"completion_tokens\": 5,\n
+        \   \"total_tokens\": 196,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_64dfa806c7\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 25 Feb 2026 18:34:23 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '365'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      set-cookie:
+      - SET-COOKIE-XXX
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
 version: 1

lib/crewai/tests/cassettes/test_output_json_sequential.yaml

@@ -1,12 +1,29 @@
 interactions:
 - request:
-    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
-      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}'
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
+      scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo
+      give my best complete final answer to the task respond using the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
+      answer must be the great and the most complete as possible, it must be outcome
+      described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expected criteria for your final
+      answer: The score of the title.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\nEnsure your final answer strictly adheres
+      to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nDo
+      not include the OpenAPI schema in the final output. Ensure the final output
+      does not include any code block markers like ```json or ```python.\n\nBegin!
+      This is VERY important to you, use the tools available and give your best Final
+      Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}'
     headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate, zstd
+      - ACCEPT-ENCODING-XXX
       connection:
       - keep-alive
       content-length:
@@ -15,20 +32,18 @@ interactions:
       - application/json
       host:
       - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.109.1
       x-stainless-arch:
-      - arm64
+      - X-STAINLESS-ARCH-XXX
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - MacOS
+      - X-STAINLESS-OS-XXX
       x-stainless-package-version:
       - 1.109.1
       x-stainless-read-timeout:
-      - '600'
+      - X-STAINLESS-READ-TIMEOUT-XXX
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
@@ -39,11 +54,21 @@ interactions:
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-CYg0P4wugCaRcXw9kmLG3BAMBmkA0\",\n  \"object\": \"chat.completion\",\n  \"created\": 1762380657,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal Answer: {\\n  \\\"score\\\": 4\\n}\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 294,\n    \"completion_tokens\": 22,\n    \"total_tokens\": 316,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\": \"fp_4c2851f862\"\
-        \n}\n"
+      string: "{\n  \"id\": \"chatcmpl-CYg0P4wugCaRcXw9kmLG3BAMBmkA0\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1762380657,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+        Answer: {\\n  \\\"score\\\": 4\\n}\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 294,\n    \"completion_tokens\":
+        22,\n    \"total_tokens\": 316,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_4c2851f862\"\n}\n"
     headers:
       CF-RAY:
-      - REDACTED-RAY
+      - CF-RAY-XXX
       Connection:
       - keep-alive
       Content-Type:
@@ -53,26 +78,25 @@ interactions:
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:40:57 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      - SET-COOKIE-XXX
       Strict-Transport-Security:
-      - max-age=31536000; includeSubDomains; preload
+      - STS-XXX
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       access-control-expose-headers:
-      - X-Request-ID
+      - ACCESS-CONTROL-XXX
       alt-svc:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
       openai-organization:
-      - user-hortuttj2f3qtmxyik2zxf4q
+      - OPENAI-ORG-XXX
       openai-processing-ms:
       - '537'
       openai-project:
-      - proj_fL4UBWR1CMpAAdgzaSKqsVvA
+      - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
       x-envoy-upstream-service-time:
@@ -80,19 +104,153 @@ interactions:
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:
-      - '500'
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
       x-ratelimit-limit-tokens:
-      - '200000'
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
       x-ratelimit-remaining-requests:
-      - '499'
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
       x-ratelimit-remaining-tokens:
-      - '199687'
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
       x-ratelimit-reset-requests:
-      - 120ms
+      - X-RATELIMIT-RESET-REQUESTS-XXX
       x-ratelimit-reset-tokens:
-      - 93ms
+      - X-RATELIMIT-RESET-TOKENS-XXX
       x-request-id:
-      - req_REDACTED
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
+      scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expected criteria for your final
+      answer: The score of the title.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\nFormat your final answer according to the
+      following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nIMPORTANT:
+      Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or
+      modify the meaning of the content. Only structure it to match the schema format.\n\nDo
+      not include the OpenAPI schema in the final output. Ensure the final output
+      does not include any code block markers like ```json or ```python.\n\nProvide
+      your complete response:"},{"role":"system","content":"You are Scorer. You''re
+      an expert scorer, specialized in scoring titles.\nYour personal goal is: Score
+      the title"},{"role":"user","content":"\nCurrent Task: Give me an integer score
+      between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis
+      is the expected criteria for your final answer: The score of the title.\nyou
+      MUST return the actual complete content as the final answer, not a summary.\nFormat
+      your final answer according to the following OpenAPI schema: {\n  \"properties\":
+      {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\":
+      [\n    \"score\"\n  ],\n  \"title\": \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\":
+      false\n}\n\nIMPORTANT: Preserve the original content exactly as-is. Do NOT rewrite,
+      paraphrase, or modify the meaning of the content. Only structure it to match
+      the schema format.\n\nDo not include the OpenAPI schema in the final output.
+      Ensure the final output does not include any code block markers like ```json
+      or ```python.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '2541'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.12
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-DDDzz40VXTe9AsmG5ZSlL0IufvYKz\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772044447,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"score\\\":4}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        513,\n    \"completion_tokens\": 5,\n    \"total_tokens\": 518,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 25 Feb 2026 18:34:07 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '426'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      set-cookie:
+      - SET-COOKIE-XXX
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
     status:
       code: 200
       message: OK

lib/crewai/tests/cassettes/test_output_json_to_another_task.yaml

@@ -1,194 +1,254 @@
 interactions:
 - request:
-    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
-      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}'
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
+      scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expected criteria for your final
+      answer: The score of the title.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\nFormat your final answer according to the
+      following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nIMPORTANT:
+      Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or
+      modify the meaning of the content. Only structure it to match the schema format.\n\nDo
+      not include the OpenAPI schema in the final output. Ensure the final output
+      does not include any code block markers like ```json or ```python.\n\nProvide
+      your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}'
     headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate, zstd
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
       connection:
       - keep-alive
       content-length:
-      - '1394'
+      - '1421'
       content-type:
       - application/json
       host:
       - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.109.1
       x-stainless-arch:
-      - arm64
+      - X-STAINLESS-ARCH-XXX
       x-stainless-async:
       - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
       x-stainless-lang:
       - python
       x-stainless-os:
-      - MacOS
+      - X-STAINLESS-OS-XXX
       x-stainless-package-version:
-      - 1.109.1
+      - 1.83.0
       x-stainless-read-timeout:
-      - '600'
+      - X-STAINLESS-READ-TIMEOUT-XXX
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.12.9
+      - 3.13.12
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-CYg0M3aPReBrUikkn7QiHFyZG8ETn\",\n  \"object\": \"chat.completion\",\n  \"created\": 1762380654,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal Answer: {\\n  \\\"score\\\": 4\\n}\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 294,\n    \"completion_tokens\": 22,\n    \"total_tokens\": 316,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\": \"fp_4c2851f862\"\
-        \n}\n"
+      string: "{\n  \"id\": \"chatcmpl-DDE5OBoRr3j1NGXkef0waj9TCBmLb\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772044782,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"score\\\":4}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        276,\n    \"completion_tokens\": 5,\n    \"total_tokens\": 281,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n"
     headers:
       CF-RAY:
-      - REDACTED-RAY
+      - CF-RAY-XXX
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Wed, 05 Nov 2025 22:10:54 GMT
+      - Wed, 25 Feb 2026 18:39:42 GMT
       Server:
       - cloudflare
-      Set-Cookie:
-      - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:40:54 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Strict-Transport-Security:
-      - max-age=31536000; includeSubDomains; preload
+      - STS-XXX
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       access-control-expose-headers:
-      - X-Request-ID
+      - ACCESS-CONTROL-XXX
       alt-svc:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
       openai-organization:
-      - user-hortuttj2f3qtmxyik2zxf4q
+      - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '730'
+      - '435'
       openai-project:
-      - proj_fL4UBWR1CMpAAdgzaSKqsVvA
+      - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '754'
+      set-cookie:
+      - SET-COOKIE-XXX
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:
-      - '500'
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
       x-ratelimit-limit-tokens:
-      - '200000'
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
       x-ratelimit-remaining-requests:
-      - '499'
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
       x-ratelimit-remaining-tokens:
-      - '199687'
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
       x-ratelimit-reset-requests:
-      - 120ms
+      - X-RATELIMIT-RESET-REQUESTS-XXX
       x-ratelimit-reset-tokens:
-      - 93ms
+      - X-RATELIMIT-RESET-TOKENS-XXX
       x-request-id:
-      - req_REDACTED
+      - X-REQUEST-ID-XXX
     status:
       code: 200
       message: OK
 - request:
-    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Given the score the title ''The impact of AI in the future of work'' got, give me an integer score between 1-5 for the following title: ''Return of the Jedi''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\":
-      [\n    \"score\"\n  ],\n  \"title\": \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nThis is the context you''re working with:\n{\n  \"score\": 4\n}\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}'
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
+      scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expected criteria for your final
+      answer: The score of the title.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\nFormat your final answer according to the
+      following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nIMPORTANT:
+      Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or
+      modify the meaning of the content. Only structure it to match the schema format.\n\nDo
+      not include the OpenAPI schema in the final output. Ensure the final output
+      does not include any code block markers like ```json or ```python.\n\nProvide
+      your complete response:"},{"role":"assistant","content":"{\"score\":4}"},{"role":"system","content":"You
+      are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal
+      goal is: Score the title"},{"role":"user","content":"\nCurrent Task: Given the
+      score the title ''The impact of AI in the future of work'' got, give me an integer
+      score between 1-5 for the following title: ''Return of the Jedi''\n\nThis is
+      the expected criteria for your final answer: The score of the title.\nyou MUST
+      return the actual complete content as the final answer, not a summary.\nFormat
+      your final answer according to the following OpenAPI schema: {\n  \"properties\":
+      {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\":
+      [\n    \"score\"\n  ],\n  \"title\": \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\":
+      false\n}\n\nIMPORTANT: Preserve the original content exactly as-is. Do NOT rewrite,
+      paraphrase, or modify the meaning of the content. Only structure it to match
+      the schema format.\n\nDo not include the OpenAPI schema in the final output.
+      Ensure the final output does not include any code block markers like ```json
+      or ```python.\n\nThis is the context you''re working with:\n{\"score\":4}\n\nProvide
+      your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}'
     headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate, zstd
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
       connection:
       - keep-alive
       content-length:
-      - '1512'
+      - '2699'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=REDACTED; _cfuvid=REDACTED
+      - COOKIE-XXX
       host:
       - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.109.1
       x-stainless-arch:
-      - arm64
+      - X-STAINLESS-ARCH-XXX
       x-stainless-async:
       - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
       x-stainless-lang:
       - python
       x-stainless-os:
-      - MacOS
+      - X-STAINLESS-OS-XXX
       x-stainless-package-version:
-      - 1.109.1
+      - 1.83.0
       x-stainless-read-timeout:
-      - '600'
+      - X-STAINLESS-READ-TIMEOUT-XXX
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.12.9
+      - 3.13.12
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-CYg0MEYp1MebCu2eCMBqCwXtNYTbD\",\n  \"object\": \"chat.completion\",\n  \"created\": 1762380654,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal Answer: {\\n  \\\"score\\\": 3\\n}\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 324,\n    \"completion_tokens\": 22,\n    \"total_tokens\": 346,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\": \"fp_4c2851f862\"\
-        \n}\n"
+      string: "{\n  \"id\": \"chatcmpl-DDE5OEawexwaazoOAgn4QD9W8roe6\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772044782,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"score\\\":3}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        552,\n    \"completion_tokens\": 5,\n    \"total_tokens\": 557,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n"
     headers:
       CF-RAY:
-      - REDACTED-RAY
+      - CF-RAY-XXX
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Wed, 05 Nov 2025 22:10:55 GMT
+      - Wed, 25 Feb 2026 18:39:43 GMT
       Server:
       - cloudflare
       Strict-Transport-Security:
-      - max-age=31536000; includeSubDomains; preload
+      - STS-XXX
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       access-control-expose-headers:
-      - X-Request-ID
+      - ACCESS-CONTROL-XXX
       alt-svc:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
       openai-organization:
-      - user-hortuttj2f3qtmxyik2zxf4q
+      - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '983'
+      - '309'
       openai-project:
-      - proj_fL4UBWR1CMpAAdgzaSKqsVvA
+      - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '1002'
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:
-      - '500'
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
       x-ratelimit-limit-tokens:
-      - '200000'
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
       x-ratelimit-remaining-requests:
-      - '499'
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
       x-ratelimit-remaining-tokens:
-      - '199659'
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
       x-ratelimit-reset-requests:
-      - 120ms
+      - X-RATELIMIT-RESET-REQUESTS-XXX
       x-ratelimit-reset-tokens:
-      - 102ms
+      - X-RATELIMIT-RESET-TOKENS-XXX
       x-request-id:
-      - req_REDACTED
+      - X-REQUEST-ID-XXX
     status:
       code: 200
       message: OK

lib/crewai/tests/cassettes/test_output_pydantic_hierarchical.yaml

@@ -10,28 +10,29 @@ interactions:
       Task: Give me an integer score between 1-5 for the following title: ''The impact
       of AI in the future of work''\n\nThis is the expected criteria for your final
       answer: The score of the title.\nyou MUST return the actual complete content
-      as the final answer, not a summary.\nEnsure your final answer strictly adheres
-      to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      as the final answer, not a summary.\nFormat your final answer according to the
+      following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
       \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
-      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nDo
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nIMPORTANT:
+      Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or
+      modify the meaning of the content. Only structure it to match the schema format.\n\nDo
       not include the OpenAPI schema in the final output. Ensure the final output
-      does not include any code block markers like ```json or ```python.\n\nThis is
-      VERY important to you, your job depends on it!"}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"Delegate_work_to_coworker","description":"Delegate
+      does not include any code block markers like ```json or ```python."}],"model":"gpt-4o","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false,"tool_choice":"auto","tools":[{"type":"function","function":{"name":"delegate_work_to_coworker","description":"Delegate
       a specific task to one of the following coworkers: Scorer\nThe input to this
       tool should be the coworker, the task you want them to do, and ALL necessary
       context to execute the task, they know nothing about the task, so share absolutely
-      everything you know, don''t reference things but instead explain them.","parameters":{"properties":{"task":{"description":"The
+      everything you know, don''t reference things but instead explain them.","strict":true,"parameters":{"properties":{"task":{"description":"The
       task to delegate","title":"Task","type":"string"},"context":{"description":"The
       context for the task","title":"Context","type":"string"},"coworker":{"description":"The
-      role/name of the coworker to delegate to","title":"Coworker","type":"string"}},"required":["task","context","coworker"],"type":"object"}}},{"type":"function","function":{"name":"Ask_question_to_coworker","description":"Ask
+      role/name of the coworker to delegate to","title":"Coworker","type":"string"}},"required":["task","context","coworker"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"ask_question_to_coworker","description":"Ask
       a specific question to one of the following coworkers: Scorer\nThe input to
       this tool should be the coworker, the question you have for them, and ALL necessary
       context to ask the question properly, they know nothing about the question,
       so share absolutely everything you know, don''t reference things but instead
-      explain them.","parameters":{"properties":{"question":{"description":"The question
-      to ask","title":"Question","type":"string"},"context":{"description":"The context
-      for the question","title":"Context","type":"string"},"coworker":{"description":"The
-      role/name of the coworker to ask","title":"Coworker","type":"string"}},"required":["question","context","coworker"],"type":"object"}}}]}'
+      explain them.","strict":true,"parameters":{"properties":{"question":{"description":"The
+      question to ask","title":"Question","type":"string"},"context":{"description":"The
+      context for the question","title":"Context","type":"string"},"coworker":{"description":"The
+      role/name of the coworker to ask","title":"Coworker","type":"string"}},"required":["question","context","coworker"],"type":"object","additionalProperties":false}}}]}'
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -44,7 +45,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '2959'
+      - '3415'
       content-type:
       - application/json
       host:
@@ -53,6 +54,8 @@ interactions:
       - X-STAINLESS-ARCH-XXX
       x-stainless-async:
       - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
       x-stainless-lang:
       - python
       x-stainless-os:
@@ -66,31 +69,33 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.3
+      - 3.13.12
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-D0u1dSPVqe5art2HXWibsPOp3SOti\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1769107733,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      string: "{\n  \"id\": \"chatcmpl-DDG9wKD6IRmnAwBS1tw4NMVccsPnZ\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772052752,\n  \"model\": \"gpt-4o-2024-08-06\",\n
         \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
         \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
-        \           \"id\": \"call_AEHe6pv1NqguBRA5q9CHVSn3\",\n            \"type\":
-        \"function\",\n            \"function\": {\n              \"name\": \"Delegate_work_to_coworker\",\n
-        \             \"arguments\": \"{\\\"task\\\":\\\"Provide an integer score
-        between 1-5 for the title 'The impact of AI in the future of work'. The score
-        should reflect how engaging, relevant, and thought-provoking the title is.\\\",\\\"context\\\":\\\"You
-        need to evaluate how well the title 'The impact of AI in the future of work'
-        meets the criteria of being engaging, relevant, and thought-provoking in the
-        context of emerging technologies and their implications on future work environments.\\\",\\\"coworker\\\":\\\"Scorer\\\"}\"\n
-        \           }\n          }\n        ],\n        \"refusal\": null,\n        \"annotations\":
-        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"tool_calls\"\n
-        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 562,\n    \"completion_tokens\":
-        111,\n    \"total_tokens\": 673,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        \           \"id\": \"call_VzfUuCi89kzEC9gJgiMCz5B2\",\n            \"type\":
+        \"function\",\n            \"function\": {\n              \"name\": \"delegate_work_to_coworker\",\n
+        \             \"arguments\": \"{\\\"task\\\":\\\"Evaluate the title 'The impact
+        of AI in the future of work' and give an integer score between 1-5 based on
+        how compelling or effective the title is.\\\",\\\"context\\\":\\\"You are
+        asked to evaluate a title 'The impact of AI in the future of work' and provide
+        an integer score between 1-5. The criteria for evaluation include how informative,
+        engaging, relevant, and clear the title is. Additionally, consider how the
+        title may attract the intended audience's interest and its potential impact
+        on readers.\\\",\\\"coworker\\\":\\\"Scorer\\\"}\"\n            }\n          }\n
+        \       ],\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
+        \     \"logprobs\": null,\n      \"finish_reason\": \"tool_calls\"\n    }\n
+        \ ],\n  \"usage\": {\n    \"prompt_tokens\": 613,\n    \"completion_tokens\":
+        127,\n    \"total_tokens\": 740,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
         0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
         {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
         0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-        \"default\",\n  \"system_fingerprint\": \"fp_deacdd5f6f\"\n}\n"
+        \"default\",\n  \"system_fingerprint\": \"fp_64dfa806c7\"\n}\n"
     headers:
       CF-RAY:
       - CF-RAY-XXX
@@ -99,11 +104,9 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 22 Jan 2026 18:48:56 GMT
+      - Wed, 25 Feb 2026 20:52:34 GMT
       Server:
       - cloudflare
-      Set-Cookie:
-      - SET-COOKIE-XXX
       Strict-Transport-Security:
       - STS-XXX
       Transfer-Encoding:
@@ -119,146 +122,13 @@ interactions:
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '3849'
+      - '2259'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '3973'
-      x-openai-proxy-wasm:
-      - v0.1
-      x-ratelimit-limit-requests:
-      - X-RATELIMIT-LIMIT-REQUESTS-XXX
-      x-ratelimit-limit-tokens:
-      - X-RATELIMIT-LIMIT-TOKENS-XXX
-      x-ratelimit-remaining-requests:
-      - X-RATELIMIT-REMAINING-REQUESTS-XXX
-      x-ratelimit-remaining-tokens:
-      - X-RATELIMIT-REMAINING-TOKENS-XXX
-      x-ratelimit-reset-requests:
-      - X-RATELIMIT-RESET-REQUESTS-XXX
-      x-ratelimit-reset-tokens:
-      - X-RATELIMIT-RESET-TOKENS-XXX
-      x-request-id:
-      - X-REQUEST-ID-XXX
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
-      scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo
-      give my best complete final answer to the task respond using the exact following
-      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
-      answer must be the great and the most complete as possible, it must be outcome
-      described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent
-      Task: Provide an integer score between 1-5 for the title ''The impact of AI
-      in the future of work''. The score should reflect how engaging, relevant, and
-      thought-provoking the title is.\n\nThis is the expected criteria for your final
-      answer: Your best answer to your coworker asking you this, accounting for the
-      context shared.\nyou MUST return the actual complete content as the final answer,
-      not a summary.\n\nThis is the context you''re working with:\nYou need to evaluate
-      how well the title ''The impact of AI in the future of work'' meets the criteria
-      of being engaging, relevant, and thought-provoking in the context of emerging
-      technologies and their implications on future work environments.\n\nBegin! This
-      is VERY important to you, use the tools available and give your best Final Answer,
-      your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}'
-    headers:
-      User-Agent:
-      - X-USER-AGENT-XXX
-      accept:
-      - application/json
-      accept-encoding:
-      - ACCEPT-ENCODING-XXX
-      authorization:
-      - AUTHORIZATION-XXX
-      connection:
-      - keep-alive
-      content-length:
-      - '1348'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      x-stainless-arch:
-      - X-STAINLESS-ARCH-XXX
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - X-STAINLESS-OS-XXX
-      x-stainless-package-version:
-      - 1.83.0
-      x-stainless-read-timeout:
-      - X-STAINLESS-READ-TIMEOUT-XXX
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.13.3
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: "{\n  \"id\": \"chatcmpl-D0u1hKGQrrJVYOcW1tAlQMgAjcaDX\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1769107737,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
-        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
-        Answer: The title 'The impact of AI in the future of work' is highly relevant
-        given the current and growing significance of artificial intelligence in transforming
-        work environments across industries. It is engaging because AI's influence
-        on future employment is a topic of widespread interest and concern, prompting
-        readers to explore its implications. Furthermore, it is thought-provoking
-        as it invites consideration of both the opportunities and challenges AI presents
-        for the workforce, including changes in job roles, skills, and economic structures.
-        However, the title could be more captivating or specific to heighten curiosity
-        and emphasize particular aspects of AI's impact. Overall, it effectively meets
-        the criteria but could be slightly enhanced for maximum engagement. Considering
-        all factors, I would score it a 4 out of 5.\",\n        \"refusal\": null,\n
-        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
-        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 264,\n    \"completion_tokens\":
-        160,\n    \"total_tokens\": 424,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
-        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
-        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
-        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-        \"default\",\n  \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
-    headers:
-      CF-RAY:
-      - CF-RAY-XXX
-      Connection:
-      - keep-alive
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 22 Jan 2026 18:49:00 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
+      set-cookie:
       - SET-COOKIE-XXX
-      Strict-Transport-Security:
-      - STS-XXX
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - X-CONTENT-TYPE-XXX
-      access-control-expose-headers:
-      - ACCESS-CONTROL-XXX
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-organization:
-      - OPENAI-ORG-XXX
-      openai-processing-ms:
-      - '3273'
-      openai-project:
-      - OPENAI-PROJECT-XXX
-      openai-version:
-      - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '3299'
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:
@@ -289,47 +159,29 @@ interactions:
       Task: Give me an integer score between 1-5 for the following title: ''The impact
       of AI in the future of work''\n\nThis is the expected criteria for your final
       answer: The score of the title.\nyou MUST return the actual complete content
-      as the final answer, not a summary.\nEnsure your final answer strictly adheres
-      to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      as the final answer, not a summary.\nFormat your final answer according to the
+      following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
       \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
-      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nDo
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nIMPORTANT:
+      Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or
+      modify the meaning of the content. Only structure it to match the schema format.\n\nDo
       not include the OpenAPI schema in the final output. Ensure the final output
-      does not include any code block markers like ```json or ```python.\n\nThis is
-      VERY important to you, your job depends on it!"},{"role":"assistant","content":null,"tool_calls":[{"id":"call_AEHe6pv1NqguBRA5q9CHVSn3","type":"function","function":{"name":"Delegate_work_to_coworker","arguments":"{\"task\":\"Provide
-      an integer score between 1-5 for the title ''The impact of AI in the future
-      of work''. The score should reflect how engaging, relevant, and thought-provoking
-      the title is.\",\"context\":\"You need to evaluate how well the title ''The
-      impact of AI in the future of work'' meets the criteria of being engaging, relevant,
-      and thought-provoking in the context of emerging technologies and their implications
-      on future work environments.\",\"coworker\":\"Scorer\"}"}}]},{"role":"tool","tool_call_id":"call_AEHe6pv1NqguBRA5q9CHVSn3","content":"The
-      title ''The impact of AI in the future of work'' is highly relevant given the
-      current and growing significance of artificial intelligence in transforming
-      work environments across industries. It is engaging because AI''s influence
-      on future employment is a topic of widespread interest and concern, prompting
-      readers to explore its implications. Furthermore, it is thought-provoking as
-      it invites consideration of both the opportunities and challenges AI presents
-      for the workforce, including changes in job roles, skills, and economic structures.
-      However, the title could be more captivating or specific to heighten curiosity
-      and emphasize particular aspects of AI''s impact. Overall, it effectively meets
-      the criteria but could be slightly enhanced for maximum engagement. Considering
-      all factors, I would score it a 4 out of 5."},{"role":"user","content":"Analyze
-      the tool result. If requirements are met, provide the Final Answer. Otherwise,
-      call the next tool. Deliver only the answer without meta-commentary."}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"Delegate_work_to_coworker","description":"Delegate
+      does not include any code block markers like ```json or ```python."}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"delegate_work_to_coworker","description":"Delegate
       a specific task to one of the following coworkers: Scorer\nThe input to this
       tool should be the coworker, the task you want them to do, and ALL necessary
       context to execute the task, they know nothing about the task, so share absolutely
-      everything you know, don''t reference things but instead explain them.","parameters":{"properties":{"task":{"description":"The
+      everything you know, don''t reference things but instead explain them.","strict":true,"parameters":{"properties":{"task":{"description":"The
       task to delegate","title":"Task","type":"string"},"context":{"description":"The
       context for the task","title":"Context","type":"string"},"coworker":{"description":"The
-      role/name of the coworker to delegate to","title":"Coworker","type":"string"}},"required":["task","context","coworker"],"type":"object"}}},{"type":"function","function":{"name":"Ask_question_to_coworker","description":"Ask
+      role/name of the coworker to delegate to","title":"Coworker","type":"string"}},"required":["task","context","coworker"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"ask_question_to_coworker","description":"Ask
       a specific question to one of the following coworkers: Scorer\nThe input to
       this tool should be the coworker, the question you have for them, and ALL necessary
       context to ask the question properly, they know nothing about the question,
       so share absolutely everything you know, don''t reference things but instead
-      explain them.","parameters":{"properties":{"question":{"description":"The question
-      to ask","title":"Question","type":"string"},"context":{"description":"The context
-      for the question","title":"Context","type":"string"},"coworker":{"description":"The
-      role/name of the coworker to ask","title":"Coworker","type":"string"}},"required":["question","context","coworker"],"type":"object"}}}]}'
+      explain them.","strict":true,"parameters":{"properties":{"question":{"description":"The
+      question to ask","title":"Question","type":"string"},"context":{"description":"The
+      context for the question","title":"Context","type":"string"},"coworker":{"description":"The
+      role/name of the coworker to ask","title":"Coworker","type":"string"}},"required":["question","context","coworker"],"type":"object","additionalProperties":false}}}]}'
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -342,7 +194,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '4694'
+      - '3151'
       content-type:
       - application/json
       cookie:
@@ -366,22 +218,31 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.3
+      - 3.13.12
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-D0u1kZrAEdxxk1GHhh8iEvvddrv5C\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1769107740,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      string: "{\n  \"id\": \"chatcmpl-DDG9zJ5ZtuBIJLBxuTBqV4pYyaAf3\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772052755,\n  \"model\": \"gpt-4o-2024-08-06\",\n
         \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-        \"assistant\",\n        \"content\": \"{\\\"score\\\":4}\",\n        \"refusal\":
-        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
-        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-        868,\n    \"completion_tokens\": 6,\n    \"total_tokens\": 874,\n    \"prompt_tokens_details\":
-        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+        \           \"id\": \"call_IdyahKEb4Ez9fWTlL0SWNU97\",\n            \"type\":
+        \"function\",\n            \"function\": {\n              \"name\": \"ask_question_to_coworker\",\n
+        \             \"arguments\": \"{\\\"question\\\":\\\"What score would you
+        give between 1-5 to the following title: 'The impact of AI in the future of
+        work' and why?\\\",\\\"context\\\":\\\"Your task is to evaluate the title
+        based on its ability to intrigue, its clarity, and relevance. You need to
+        provide an integer score between 1 and 5 for this title, considering these
+        aspects.\\\",\\\"coworker\\\":\\\"Scorer\\\"}\"\n            }\n          }\n
+        \       ],\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
+        \     \"logprobs\": null,\n      \"finish_reason\": \"tool_calls\"\n    }\n
+        \ ],\n  \"usage\": {\n    \"prompt_tokens\": 581,\n    \"completion_tokens\":
+        97,\n    \"total_tokens\": 678,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
         {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
         0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-        \"default\",\n  \"system_fingerprint\": \"fp_deacdd5f6f\"\n}\n"
+        \"default\",\n  \"system_fingerprint\": \"fp_18e61aa3bc\"\n}\n"
     headers:
       CF-RAY:
       - CF-RAY-XXX
@@ -390,7 +251,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 22 Jan 2026 18:49:00 GMT
+      - Wed, 25 Feb 2026 20:52:36 GMT
       Server:
       - cloudflare
       Strict-Transport-Security:
@@ -408,13 +269,299 @@ interactions:
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '480'
+      - '1686'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
+      scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent
+      Task: What score would you give between 1-5 to the following title: ''The impact
+      of AI in the future of work'' and why?\n\nThis is the expected criteria for
+      your final answer: Your best answer to your coworker asking you this, accounting
+      for the context shared.\nyou MUST return the actual complete content as the
+      final answer, not a summary.\n\nThis is the context you''re working with:\nYour
+      task is to evaluate the title based on its ability to intrigue, its clarity,
+      and relevance. You need to provide an integer score between 1 and 5 for this
+      title, considering these aspects.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '831'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.12
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-DDGA1eLxVsUvh5Ptopxsrctx3s8fF\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772052757,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"I would give the title \\\"The impact
+        of AI in the future of work\\\" a score of 4 out of 5.\\n\\nHere's why:\\n\\n-
+        **Clarity:** The title is clear and straightforward; it immediately tells
+        the reader that the focus is on how AI will influence the work landscape going
+        forward. There is no ambiguity about the subject matter.\\n\\n- **Relevance:**
+        The topic is highly relevant in today's context, as AI technologies are rapidly
+        transforming industries and workplace dynamics. This makes the title timely
+        and likely to attract interest from professionals, academics, and anyone curious
+        about technological impacts on employment.\\n\\n- **Intrigue:** While the
+        title is clear and relevant, it lacks a bit of punch or uniqueness that might
+        make it stand out more. It's somewhat generic\u2014many articles use similar
+        phrasing. Adding an element that hints at specific insights or a fresh perspective
+        could increase intrigue.\\n\\nOverall, the title effectively conveys the subject
+        and relevance but could be slightly improved with more compelling language
+        to boost interest.\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 164,\n    \"completion_tokens\":
+        198,\n    \"total_tokens\": 362,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 25 Feb 2026 20:52:41 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '4344'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      set-cookie:
+      - SET-COOKIE-XXX
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: "{\"messages\":[{\"role\":\"system\",\"content\":\"You are Crew Manager.
+      You are a seasoned manager with a knack for getting the best out of your team.\\nYou
+      are also known for your ability to delegate work to the right people, and to
+      ask the right questions to get the best out of your team.\\nEven though you
+      don't perform tasks by yourself, you have a lot of experience in the field,
+      which allows you to properly evaluate the work of your team members.\\nYour
+      personal goal is: Manage the team to complete the task in the best way possible.\"},{\"role\":\"user\",\"content\":\"\\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: 'The impact
+      of AI in the future of work'\\n\\nThis is the expected criteria for your final
+      answer: The score of the title.\\nyou MUST return the actual complete content
+      as the final answer, not a summary.\\nFormat your final answer according to
+      the following OpenAPI schema: {\\n  \\\"properties\\\": {\\n    \\\"score\\\":
+      {\\n      \\\"title\\\": \\\"Score\\\",\\n      \\\"type\\\": \\\"integer\\\"\\n
+      \   }\\n  },\\n  \\\"required\\\": [\\n    \\\"score\\\"\\n  ],\\n  \\\"title\\\":
+      \\\"ScoreOutput\\\",\\n  \\\"type\\\": \\\"object\\\",\\n  \\\"additionalProperties\\\":
+      false\\n}\\n\\nIMPORTANT: Preserve the original content exactly as-is. Do NOT
+      rewrite, paraphrase, or modify the meaning of the content. Only structure it
+      to match the schema format.\\n\\nDo not include the OpenAPI schema in the final
+      output. Ensure the final output does not include any code block markers like
+      ```json or ```python.\"},{\"role\":\"assistant\",\"content\":null,\"tool_calls\":[{\"id\":\"call_IdyahKEb4Ez9fWTlL0SWNU97\",\"type\":\"function\",\"function\":{\"name\":\"ask_question_to_coworker\",\"arguments\":\"{\\\"question\\\":\\\"What
+      score would you give between 1-5 to the following title: 'The impact of AI in
+      the future of work' and why?\\\",\\\"context\\\":\\\"Your task is to evaluate
+      the title based on its ability to intrigue, its clarity, and relevance. You
+      need to provide an integer score between 1 and 5 for this title, considering
+      these aspects.\\\",\\\"coworker\\\":\\\"Scorer\\\"}\"}}]},{\"role\":\"tool\",\"tool_call_id\":\"call_IdyahKEb4Ez9fWTlL0SWNU97\",\"name\":\"ask_question_to_coworker\",\"content\":\"I
+      would give the title \\\"The impact of AI in the future of work\\\" a score
+      of 4 out of 5.\\n\\nHere's why:\\n\\n- **Clarity:** The title is clear and straightforward;
+      it immediately tells the reader that the focus is on how AI will influence the
+      work landscape going forward. There is no ambiguity about the subject matter.\\n\\n-
+      **Relevance:** The topic is highly relevant in today's context, as AI technologies
+      are rapidly transforming industries and workplace dynamics. This makes the title
+      timely and likely to attract interest from professionals, academics, and anyone
+      curious about technological impacts on employment.\\n\\n- **Intrigue:** While
+      the title is clear and relevant, it lacks a bit of punch or uniqueness that
+      might make it stand out more. It's somewhat generic\u2014many articles use similar
+      phrasing. Adding an element that hints at specific insights or a fresh perspective
+      could increase intrigue.\\n\\nOverall, the title effectively conveys the subject
+      and relevance but could be slightly improved with more compelling language to
+      boost interest.\"},{\"role\":\"user\",\"content\":\"Analyze the tool result.
+      If requirements are met, provide the Final Answer. Otherwise, call the next
+      tool. Deliver only the answer without meta-commentary.\"}],\"model\":\"gpt-4o\",\"response_format\":{\"type\":\"json_schema\",\"json_schema\":{\"schema\":{\"properties\":{\"score\":{\"title\":\"Score\",\"type\":\"integer\"}},\"required\":[\"score\"],\"title\":\"ScoreOutput\",\"type\":\"object\",\"additionalProperties\":false},\"name\":\"ScoreOutput\",\"strict\":true}},\"stream\":false,\"tool_choice\":\"auto\",\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"delegate_work_to_coworker\",\"description\":\"Delegate
+      a specific task to one of the following coworkers: Scorer\\nThe input to this
+      tool should be the coworker, the task you want them to do, and ALL necessary
+      context to execute the task, they know nothing about the task, so share absolutely
+      everything you know, don't reference things but instead explain them.\",\"strict\":true,\"parameters\":{\"properties\":{\"task\":{\"description\":\"The
+      task to delegate\",\"title\":\"Task\",\"type\":\"string\"},\"context\":{\"description\":\"The
+      context for the task\",\"title\":\"Context\",\"type\":\"string\"},\"coworker\":{\"description\":\"The
+      role/name of the coworker to delegate to\",\"title\":\"Coworker\",\"type\":\"string\"}},\"required\":[\"task\",\"context\",\"coworker\"],\"type\":\"object\",\"additionalProperties\":false}}},{\"type\":\"function\",\"function\":{\"name\":\"ask_question_to_coworker\",\"description\":\"Ask
+      a specific question to one of the following coworkers: Scorer\\nThe input to
+      this tool should be the coworker, the question you have for them, and ALL necessary
+      context to ask the question properly, they know nothing about the question,
+      so share absolutely everything you know, don't reference things but instead
+      explain them.\",\"strict\":true,\"parameters\":{\"properties\":{\"question\":{\"description\":\"The
+      question to ask\",\"title\":\"Question\",\"type\":\"string\"},\"context\":{\"description\":\"The
+      context for the question\",\"title\":\"Context\",\"type\":\"string\"},\"coworker\":{\"description\":\"The
+      role/name of the coworker to ask\",\"title\":\"Coworker\",\"type\":\"string\"}},\"required\":[\"question\",\"context\",\"coworker\"],\"type\":\"object\",\"additionalProperties\":false}}}]}"
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '5297'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.12
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-DDGA5qDbleuzKoN7uVs5MFOC6X5DG\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772052761,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"score\\\":4}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        956,\n    \"completion_tokens\": 10,\n    \"total_tokens\": 966,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_64dfa806c7\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 25 Feb 2026 20:52:42 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '508'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '503'
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:

lib/crewai/tests/cassettes/test_output_pydantic_sequential.yaml

@@ -1,98 +1,120 @@
 interactions:
 - request:
-    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
-      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}'
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
+      scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expected criteria for your final
+      answer: The score of the title.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\nFormat your final answer according to the
+      following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nIMPORTANT:
+      Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or
+      modify the meaning of the content. Only structure it to match the schema format.\n\nDo
+      not include the OpenAPI schema in the final output. Ensure the final output
+      does not include any code block markers like ```json or ```python.\n\nProvide
+      your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}'
     headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate, zstd
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
       connection:
       - keep-alive
       content-length:
-      - '1394'
+      - '1421'
       content-type:
       - application/json
       host:
       - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.109.1
       x-stainless-arch:
-      - arm64
+      - X-STAINLESS-ARCH-XXX
       x-stainless-async:
       - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
       x-stainless-lang:
       - python
       x-stainless-os:
-      - MacOS
+      - X-STAINLESS-OS-XXX
       x-stainless-package-version:
-      - 1.109.1
+      - 1.83.0
       x-stainless-read-timeout:
-      - '600'
+      - X-STAINLESS-READ-TIMEOUT-XXX
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.12.9
+      - 3.13.12
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-CYg0ICsr8nVjoOoVFpnOLUh71LgfJ\",\n  \"object\": \"chat.completion\",\n  \"created\": 1762380650,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal Answer: {\\n  \\\"score\\\": 4\\n}\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 294,\n    \"completion_tokens\": 22,\n    \"total_tokens\": 316,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\": \"fp_4c2851f862\"\
-        \n}\n"
+      string: "{\n  \"id\": \"chatcmpl-DDDxMk9AEzSz8xZnza3XoSeijSI5R\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772044284,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"score\\\":4}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        276,\n    \"completion_tokens\": 5,\n    \"total_tokens\": 281,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n"
     headers:
       CF-RAY:
-      - REDACTED-RAY
+      - CF-RAY-XXX
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Wed, 05 Nov 2025 22:10:50 GMT
+      - Wed, 25 Feb 2026 18:31:25 GMT
       Server:
       - cloudflare
-      Set-Cookie:
-      - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:40:50 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Strict-Transport-Security:
-      - max-age=31536000; includeSubDomains; preload
+      - STS-XXX
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       access-control-expose-headers:
-      - X-Request-ID
+      - ACCESS-CONTROL-XXX
       alt-svc:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
       openai-organization:
-      - user-hortuttj2f3qtmxyik2zxf4q
+      - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '482'
+      - '385'
       openai-project:
-      - proj_fL4UBWR1CMpAAdgzaSKqsVvA
+      - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '495'
+      set-cookie:
+      - SET-COOKIE-XXX
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:
-      - '500'
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
       x-ratelimit-limit-tokens:
-      - '200000'
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
       x-ratelimit-remaining-requests:
-      - '499'
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
       x-ratelimit-remaining-tokens:
-      - '199687'
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
       x-ratelimit-reset-requests:
-      - 120ms
+      - X-RATELIMIT-RESET-REQUESTS-XXX
       x-ratelimit-reset-tokens:
-      - 93ms
+      - X-RATELIMIT-RESET-TOKENS-XXX
       x-request-id:
-      - req_REDACTED
+      - X-REQUEST-ID-XXX
     status:
       code: 200
       message: OK

lib/crewai/tests/cassettes/test_output_pydantic_to_another_task.yaml

@@ -1,192 +1,254 @@
 interactions:
 - request:
-    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
-      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4o"}'
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
+      scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expected criteria for your final
+      answer: The score of the title.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\nFormat your final answer according to the
+      following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nIMPORTANT:
+      Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or
+      modify the meaning of the content. Only structure it to match the schema format.\n\nDo
+      not include the OpenAPI schema in the final output. Ensure the final output
+      does not include any code block markers like ```json or ```python.\n\nProvide
+      your complete response:"}],"model":"gpt-4o","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}'
     headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate, zstd
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
       connection:
       - keep-alive
       content-length:
-      - '1388'
+      - '1415'
       content-type:
       - application/json
       host:
       - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.109.1
       x-stainless-arch:
-      - arm64
+      - X-STAINLESS-ARCH-XXX
       x-stainless-async:
       - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
       x-stainless-lang:
       - python
       x-stainless-os:
-      - MacOS
+      - X-STAINLESS-OS-XXX
       x-stainless-package-version:
-      - 1.109.1
+      - 1.83.0
       x-stainless-read-timeout:
-      - '600'
+      - X-STAINLESS-READ-TIMEOUT-XXX
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.12.9
+      - 3.13.12
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-CYg0Jd7eOJXIC6Yc1xB0F6Ve3KK1M\",\n  \"object\": \"chat.completion\",\n  \"created\": 1762380651,\n  \"model\": \"gpt-4o-2024-08-06\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"I now can give a great answer\\nFinal Answer: {\\\"score\\\": 4}\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 294,\n    \"completion_tokens\": 17,\n    \"total_tokens\": 311,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\": \"fp_65564d8ba5\"\n}\n"
+      string: "{\n  \"id\": \"chatcmpl-DDDxNULmWtIUe1SAGHcArDXYSifV8\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772044285,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"score\\\":4}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        276,\n    \"completion_tokens\": 5,\n    \"total_tokens\": 281,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_9e0d253e63\"\n}\n"
     headers:
       CF-RAY:
-      - REDACTED-RAY
+      - CF-RAY-XXX
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Wed, 05 Nov 2025 22:10:52 GMT
+      - Wed, 25 Feb 2026 18:31:26 GMT
       Server:
       - cloudflare
-      Set-Cookie:
-      - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:40:52 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Strict-Transport-Security:
-      - max-age=31536000; includeSubDomains; preload
+      - STS-XXX
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       access-control-expose-headers:
-      - X-Request-ID
+      - ACCESS-CONTROL-XXX
       alt-svc:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
       openai-organization:
-      - user-hortuttj2f3qtmxyik2zxf4q
+      - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '1337'
+      - '364'
       openai-project:
-      - proj_fL4UBWR1CMpAAdgzaSKqsVvA
+      - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '1487'
+      set-cookie:
+      - SET-COOKIE-XXX
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:
-      - '500'
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
       x-ratelimit-limit-tokens:
-      - '30000'
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
       x-ratelimit-remaining-requests:
-      - '499'
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
       x-ratelimit-remaining-tokens:
-      - '29687'
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
       x-ratelimit-reset-requests:
-      - 120ms
+      - X-RATELIMIT-RESET-REQUESTS-XXX
       x-ratelimit-reset-tokens:
-      - 626ms
+      - X-RATELIMIT-RESET-TOKENS-XXX
       x-request-id:
-      - req_REDACTED
+      - X-REQUEST-ID-XXX
     status:
       code: 200
       message: OK
 - request:
-    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Given the score the title ''The impact of AI in the future of work'' got, give me an integer score between 1-5 for the following title: ''Return of the Jedi'', you MUST give it a score, use your best judgment\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
-      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\": \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nThis is the context you''re working with:\n{\"score\": 4}\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4o"}'
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
+      scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expected criteria for your final
+      answer: The score of the title.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\nFormat your final answer according to the
+      following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nIMPORTANT:
+      Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or
+      modify the meaning of the content. Only structure it to match the schema format.\n\nDo
+      not include the OpenAPI schema in the final output. Ensure the final output
+      does not include any code block markers like ```json or ```python.\n\nProvide
+      your complete response:"},{"role":"assistant","content":"{\"score\":4}"},{"role":"system","content":"You
+      are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal
+      goal is: Score the title"},{"role":"user","content":"\nCurrent Task: Given the
+      score the title ''The impact of AI in the future of work'' got, give me an integer
+      score between 1-5 for the following title: ''Return of the Jedi'', you MUST
+      give it a score, use your best judgment\n\nThis is the expected criteria for
+      your final answer: The score of the title.\nyou MUST return the actual complete
+      content as the final answer, not a summary.\nFormat your final answer according
+      to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nIMPORTANT:
+      Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or
+      modify the meaning of the content. Only structure it to match the schema format.\n\nDo
+      not include the OpenAPI schema in the final output. Ensure the final output
+      does not include any code block markers like ```json or ```python.\n\nThis is
+      the context you''re working with:\n{\"score\":4}\n\nProvide your complete response:"}],"model":"gpt-4o","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}'
     headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate, zstd
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
       connection:
       - keep-alive
       content-length:
-      - '1550'
+      - '2743'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=REDACTED; _cfuvid=REDACTED
+      - COOKIE-XXX
       host:
       - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.109.1
       x-stainless-arch:
-      - arm64
+      - X-STAINLESS-ARCH-XXX
       x-stainless-async:
       - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
       x-stainless-lang:
       - python
       x-stainless-os:
-      - MacOS
+      - X-STAINLESS-OS-XXX
       x-stainless-package-version:
-      - 1.109.1
+      - 1.83.0
       x-stainless-read-timeout:
-      - '600'
+      - X-STAINLESS-READ-TIMEOUT-XXX
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.12.9
+      - 3.13.12
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-CYg0KidOU2tphhqhW69ygSBSubHBQ\",\n  \"object\": \"chat.completion\",\n  \"created\": 1762380652,\n  \"model\": \"gpt-4o-2024-08-06\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"I now can give a great answer\\nFinal Answer: {\\\"score\\\": 5}\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 333,\n    \"completion_tokens\": 17,\n    \"total_tokens\": 350,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\": \"fp_a788c5aef0\"\n}\n"
+      string: "{\n  \"id\": \"chatcmpl-DDDxOIf7hV4pRmOxmlsA7bO8L2z5w\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772044286,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"score\\\":5}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        564,\n    \"completion_tokens\": 5,\n    \"total_tokens\": 569,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_9e0d253e63\"\n}\n"
     headers:
       CF-RAY:
-      - REDACTED-RAY
+      - CF-RAY-XXX
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Wed, 05 Nov 2025 22:10:53 GMT
+      - Wed, 25 Feb 2026 18:31:27 GMT
       Server:
       - cloudflare
       Strict-Transport-Security:
-      - max-age=31536000; includeSubDomains; preload
+      - STS-XXX
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       access-control-expose-headers:
-      - X-Request-ID
+      - ACCESS-CONTROL-XXX
       alt-svc:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
       openai-organization:
-      - user-hortuttj2f3qtmxyik2zxf4q
+      - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '1009'
+      - '393'
       openai-project:
-      - proj_fL4UBWR1CMpAAdgzaSKqsVvA
+      - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '1106'
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:
-      - '500'
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
       x-ratelimit-limit-tokens:
-      - '30000'
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
       x-ratelimit-remaining-requests:
-      - '499'
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
       x-ratelimit-remaining-tokens:
-      - '29647'
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
       x-ratelimit-reset-requests:
-      - 120ms
+      - X-RATELIMIT-RESET-REQUESTS-XXX
       x-ratelimit-reset-tokens:
-      - 706ms
+      - X-RATELIMIT-RESET-TOKENS-XXX
       x-request-id:
-      - req_REDACTED
+      - X-REQUEST-ID-XXX
     status:
       code: 200
       message: OK

lib/crewai/tests/cassettes/test_save_task_json_output.yaml

@@ -1,11 +1,14 @@
 interactions:
 - request:
-    body: '{"trace_id": "00000000-0000-0000-0000-000000000000", "execution_type": "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null, "crew_name": "crew", "flow_name": null, "crewai_version": "1.3.0", "privacy_level": "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count": 0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-11-05T22:10:38.307164+00:00"}, "ephemeral_trace_id": "00000000-0000-0000-0000-000000000000"}'
+    body: '{"trace_id": "00000000-0000-0000-0000-000000000000", "execution_type":
+      "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null,
+      "crew_name": "crew", "flow_name": null, "crewai_version": "1.3.0", "privacy_level":
+      "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count":
+      0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-11-05T22:10:38.307164+00:00"},
+      "ephemeral_trace_id": "00000000-0000-0000-0000-000000000000"}'
     headers:
       Accept:
       - '*/*'
-      Accept-Encoding:
-      - gzip, deflate, zstd
       Connection:
       - keep-alive
       Content-Length:
@@ -13,14 +16,18 @@ interactions:
       Content-Type:
       - application/json
       User-Agent:
-      - CrewAI-CLI/1.3.0
+      - X-USER-AGENT-XXX
       X-Crewai-Version:
       - 1.3.0
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
     method: POST
     uri: https://app.crewai.com/crewai_plus/api/v1/tracing/ephemeral/batches
   response:
     body:
-      string: '{"id": "00000000-0000-0000-0000-000000000000","ephemeral_trace_id": "00000000-0000-0000-0000-000000000000","execution_type":"crew","crew_name":"crew","flow_name":null,"status":"running","duration_ms":null,"crewai_version":"1.3.0","total_events":0,"execution_context":{"crew_fingerprint":null,"crew_name":"crew","flow_name":null,"crewai_version":"1.3.0","privacy_level":"standard"},"created_at":"2025-11-05T22:10:38.904Z","updated_at":"2025-11-05T22:10:38.904Z","access_code": "TRACE-0000000000","user_identifier":null}'
+      string: '{"id": "00000000-0000-0000-0000-000000000000","ephemeral_trace_id":
+        "00000000-0000-0000-0000-000000000000","execution_type":"crew","crew_name":"crew","flow_name":null,"status":"running","duration_ms":null,"crewai_version":"1.3.0","total_events":0,"execution_context":{"crew_fingerprint":null,"crew_name":"crew","flow_name":null,"crewai_version":"1.3.0","privacy_level":"standard"},"created_at":"2025-11-05T22:10:38.904Z","updated_at":"2025-11-05T22:10:38.904Z","access_code":
+        "TRACE-0000000000","user_identifier":null}'
     headers:
       Connection:
       - keep-alive
@@ -33,46 +40,61 @@ interactions:
       cache-control:
       - no-store
       content-security-policy:
-      - 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/ https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net https://js.hscollectedforms.net
-        https://js.usemessages.com https://snap.licdn.com https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data: *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com; connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com https://api.hubspot.com
-        https://forms.hscollectedforms.net https://api.hubapi.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509 https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self'' *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com https://drive.google.com https://slides.google.com https://accounts.google.com https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/ https://www.youtube.com https://share.descript.com'
+      - CSP-FILTERED
       etag:
-      - W/"06db9ad73130a1da388846e83fc98135"
+      - ETAG-XXX
       expires:
       - '0'
       permissions-policy:
-      - camera=(), microphone=(self), geolocation=()
+      - PERMISSIONS-POLICY-XXX
       pragma:
       - no-cache
       referrer-policy:
-      - strict-origin-when-cross-origin
+      - REFERRER-POLICY-XXX
       strict-transport-security:
-      - max-age=63072000; includeSubDomains
+      - STS-XXX
       vary:
       - Accept
       x-content-type-options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       x-frame-options:
-      - SAMEORIGIN
+      - X-FRAME-OPTIONS-XXX
       x-permitted-cross-domain-policies:
-      - none
+      - X-PERMITTED-XXX
       x-request-id:
-      - 34f34729-198e-482e-8c87-163a997bc3f4
+      - X-REQUEST-ID-XXX
       x-runtime:
-      - '0.239932'
+      - X-RUNTIME-XXX
       x-xss-protection:
-      - 1; mode=block
+      - X-XSS-PROTECTION-XXX
     status:
       code: 201
       message: Created
 - request:
-    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
-      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}'
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
+      scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo
+      give my best complete final answer to the task respond using the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
+      answer must be the great and the most complete as possible, it must be outcome
+      described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expected criteria for your final
+      answer: The score of the title.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\nEnsure your final answer strictly adheres
+      to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nDo
+      not include the OpenAPI schema in the final output. Ensure the final output
+      does not include any code block markers like ```json or ```python.\n\nBegin!
+      This is VERY important to you, use the tools available and give your best Final
+      Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}'
     headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate, zstd
+      - ACCEPT-ENCODING-XXX
       connection:
       - keep-alive
       content-length:
@@ -81,20 +103,18 @@ interactions:
       - application/json
       host:
       - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.109.1
       x-stainless-arch:
-      - arm64
+      - X-STAINLESS-ARCH-XXX
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - MacOS
+      - X-STAINLESS-OS-XXX
       x-stainless-package-version:
       - 1.109.1
       x-stainless-read-timeout:
-      - '600'
+      - X-STAINLESS-READ-TIMEOUT-XXX
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
@@ -105,11 +125,21 @@ interactions:
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-CYg0656gofDPbkHnqVBtb4a5cX4I0\",\n  \"object\": \"chat.completion\",\n  \"created\": 1762380638,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal Answer: {\\n  \\\"score\\\": 4\\n}\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 294,\n    \"completion_tokens\": 22,\n    \"total_tokens\": 316,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\": \"fp_4c2851f862\"\
-        \n}\n"
+      string: "{\n  \"id\": \"chatcmpl-CYg0656gofDPbkHnqVBtb4a5cX4I0\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1762380638,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+        Answer: {\\n  \\\"score\\\": 4\\n}\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 294,\n    \"completion_tokens\":
+        22,\n    \"total_tokens\": 316,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_4c2851f862\"\n}\n"
     headers:
       CF-RAY:
-      - REDACTED-RAY
+      - CF-RAY-XXX
       Connection:
       - keep-alive
       Content-Type:
@@ -119,26 +149,25 @@ interactions:
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:40:39 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      - SET-COOKIE-XXX
       Strict-Transport-Security:
-      - max-age=31536000; includeSubDomains; preload
+      - STS-XXX
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       access-control-expose-headers:
-      - X-Request-ID
+      - ACCESS-CONTROL-XXX
       alt-svc:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
       openai-organization:
-      - user-hortuttj2f3qtmxyik2zxf4q
+      - OPENAI-ORG-XXX
       openai-processing-ms:
       - '491'
       openai-project:
-      - proj_fL4UBWR1CMpAAdgzaSKqsVvA
+      - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
       x-envoy-upstream-service-time:
@@ -146,19 +175,153 @@ interactions:
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:
-      - '500'
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
       x-ratelimit-limit-tokens:
-      - '200000'
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
       x-ratelimit-remaining-requests:
-      - '499'
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
       x-ratelimit-remaining-tokens:
-      - '199687'
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
       x-ratelimit-reset-requests:
-      - 120ms
+      - X-RATELIMIT-RESET-REQUESTS-XXX
       x-ratelimit-reset-tokens:
-      - 93ms
+      - X-RATELIMIT-RESET-TOKENS-XXX
       x-request-id:
-      - req_REDACTED
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
+      scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expected criteria for your final
+      answer: The score of the title.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\nFormat your final answer according to the
+      following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nIMPORTANT:
+      Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or
+      modify the meaning of the content. Only structure it to match the schema format.\n\nDo
+      not include the OpenAPI schema in the final output. Ensure the final output
+      does not include any code block markers like ```json or ```python.\n\nProvide
+      your complete response:"},{"role":"system","content":"You are Scorer. You''re
+      an expert scorer, specialized in scoring titles.\nYour personal goal is: Score
+      the title"},{"role":"user","content":"\nCurrent Task: Give me an integer score
+      between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis
+      is the expected criteria for your final answer: The score of the title.\nyou
+      MUST return the actual complete content as the final answer, not a summary.\nFormat
+      your final answer according to the following OpenAPI schema: {\n  \"properties\":
+      {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\":
+      [\n    \"score\"\n  ],\n  \"title\": \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\":
+      false\n}\n\nIMPORTANT: Preserve the original content exactly as-is. Do NOT rewrite,
+      paraphrase, or modify the meaning of the content. Only structure it to match
+      the schema format.\n\nDo not include the OpenAPI schema in the final output.
+      Ensure the final output does not include any code block markers like ```json
+      or ```python.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '2541'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.12
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-DDDzycCKiyLb7UfPI2tKGyQAw8LGi\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772044446,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"score\\\":4}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        513,\n    \"completion_tokens\": 5,\n    \"total_tokens\": 518,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 25 Feb 2026 18:34:07 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '497'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      set-cookie:
+      - SET-COOKIE-XXX
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
     status:
       code: 200
       message: OK

lib/crewai/tests/cassettes/test_save_task_output.yaml

@@ -1,106 +1,110 @@
 interactions:
 - request:
-    body: '{"messages": [{"role": "system", "content": "You are Scorer. You''re an
-      expert scorer, specialized in scoring titles.\nYour personal goal is: Score
-      the title\nTo give my best complete final answer to the task use the exact following
-      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
-      answer must be the great and the most complete as possible, it must be outcome
-      described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
-      "content": "\nCurrent Task: Give me an integer score between 1-5 for the following
-      title: ''The impact of AI in the future of work''\n\nThis is the expect criteria
-      for your final answer: The score of the title.\nyou MUST return the actual complete
-      content as the final answer, not a summary.\n\nBegin! This is VERY important
-      to you, use the tools available and give your best Final Answer, your job depends
-      on it!\n\nThought:"}], "model": "gpt-4o"}'
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
+      scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expected criteria for your final
+      answer: The score of the title.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}'
     headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
       connection:
       - keep-alive
       content-length:
-      - '915'
+      - '522'
       content-type:
       - application/json
-      cookie:
-      - __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
-        _cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
       host:
       - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.47.0
       x-stainless-arch:
-      - arm64
+      - X-STAINLESS-ARCH-XXX
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - MacOS
+      - X-STAINLESS-OS-XXX
       x-stainless-package-version:
-      - 1.47.0
-      x-stainless-raw-response:
-      - 'true'
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.7
+      - 3.13.12
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-AB7gKOb785BSjHMwGUL7QpXJHDfmJ\",\n  \"object\"\
-        : \"chat.completion\",\n  \"created\": 1727214500,\n  \"model\": \"gpt-4o-2024-05-13\"\
-        ,\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n  \
-        \      \"role\": \"assistant\",\n        \"content\": \"Thought: I now can\
-        \ give a great answer\\nFinal Answer: 4\",\n        \"refusal\": null\n  \
-        \    },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n  \
-        \  }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 186,\n    \"completion_tokens\"\
-        : 15,\n    \"total_tokens\": 201,\n    \"completion_tokens_details\": {\n\
-        \      \"reasoning_tokens\": 0\n    }\n  },\n  \"system_fingerprint\": \"\
-        fp_52a7f40b0b\"\n}\n"
+      string: "{\n  \"id\": \"chatcmpl-DDG9vqGZskrNpGfY0XnTHvzJGDu5u\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772052751,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"4\",\n        \"refusal\": null,\n
+        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 101,\n    \"completion_tokens\":
+        1,\n    \"total_tokens\": 102,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n"
     headers:
-      CF-Cache-Status:
-      - DYNAMIC
       CF-RAY:
-      - 8c85fa63ed091cf3-GRU
+      - CF-RAY-XXX
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Tue, 24 Sep 2024 21:48:21 GMT
+      - Wed, 25 Feb 2026 20:52:32 GMT
       Server:
       - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       access-control-expose-headers:
-      - X-Request-ID
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
       openai-organization:
-      - crewai-iuxna1
+      - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '199'
+      - '276'
+      openai-project:
+      - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
+      set-cookie:
+      - SET-COOKIE-XXX
+      x-openai-proxy-wasm:
+      - v0.1
       x-ratelimit-limit-requests:
-      - '10000'
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
       x-ratelimit-limit-tokens:
-      - '30000000'
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
       x-ratelimit-remaining-requests:
-      - '9999'
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
       x-ratelimit-remaining-tokens:
-      - '29999781'
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
       x-ratelimit-reset-requests:
-      - 6ms
+      - X-RATELIMIT-RESET-REQUESTS-XXX
       x-ratelimit-reset-tokens:
-      - 0s
+      - X-RATELIMIT-RESET-TOKENS-XXX
       x-request-id:
-      - req_93411fed8e9bb5607df0dbc5d178f2cb
+      - X-REQUEST-ID-XXX
     status:
       code: 200
       message: OK

lib/crewai/tests/cassettes/test_save_task_pydantic_output.yaml

@@ -1,12 +1,29 @@
 interactions:
 - request:
-    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
-      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}'
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
+      scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo
+      give my best complete final answer to the task respond using the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
+      answer must be the great and the most complete as possible, it must be outcome
+      described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expected criteria for your final
+      answer: The score of the title.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\nEnsure your final answer strictly adheres
+      to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nDo
+      not include the OpenAPI schema in the final output. Ensure the final output
+      does not include any code block markers like ```json or ```python.\n\nBegin!
+      This is VERY important to you, use the tools available and give your best Final
+      Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}'
     headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate, zstd
+      - ACCEPT-ENCODING-XXX
       connection:
       - keep-alive
       content-length:
@@ -15,20 +32,18 @@ interactions:
       - application/json
       host:
       - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.109.1
       x-stainless-arch:
-      - arm64
+      - X-STAINLESS-ARCH-XXX
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - MacOS
+      - X-STAINLESS-OS-XXX
       x-stainless-package-version:
       - 1.109.1
       x-stainless-read-timeout:
-      - '600'
+      - X-STAINLESS-READ-TIMEOUT-XXX
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
@@ -39,11 +54,25 @@ interactions:
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-CYg0PI2q4kRtIkqoIwCl9TVmZiD0o\",\n  \"object\": \"chat.completion\",\n  \"created\": 1762380657,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"Thought: The title \\\"The impact of AI in the future of work\\\" is clear, relevant, and concise. It accurately reflects a significant and current topic that is likely to attract interest. However, it could be more specific about the type of impact or scope to make it more compelling. Overall, it is a strong and effective title.\\n\\nFinal Answer: {\\n  \\\"score\\\": 4\\n}\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 294,\n    \"completion_tokens\": 80,\n    \"total_tokens\": 374,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n    \
-        \  \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\": \"fp_4c2851f862\"\n}\n"
+      string: "{\n  \"id\": \"chatcmpl-CYg0PI2q4kRtIkqoIwCl9TVmZiD0o\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1762380657,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: The title \\\"The impact of
+        AI in the future of work\\\" is clear, relevant, and concise. It accurately
+        reflects a significant and current topic that is likely to attract interest.
+        However, it could be more specific about the type of impact or scope to make
+        it more compelling. Overall, it is a strong and effective title.\\n\\nFinal
+        Answer: {\\n  \\\"score\\\": 4\\n}\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 294,\n    \"completion_tokens\":
+        80,\n    \"total_tokens\": 374,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_4c2851f862\"\n}\n"
     headers:
       CF-RAY:
-      - REDACTED-RAY
+      - CF-RAY-XXX
       Connection:
       - keep-alive
       Content-Type:
@@ -53,26 +82,25 @@ interactions:
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:40:59 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      - SET-COOKIE-XXX
       Strict-Transport-Security:
-      - max-age=31536000; includeSubDomains; preload
+      - STS-XXX
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       access-control-expose-headers:
-      - X-Request-ID
+      - ACCESS-CONTROL-XXX
       alt-svc:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
       openai-organization:
-      - user-hortuttj2f3qtmxyik2zxf4q
+      - OPENAI-ORG-XXX
       openai-processing-ms:
       - '1476'
       openai-project:
-      - proj_fL4UBWR1CMpAAdgzaSKqsVvA
+      - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
       x-envoy-upstream-service-time:
@@ -80,29 +108,32 @@ interactions:
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:
-      - '500'
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
       x-ratelimit-limit-tokens:
-      - '200000'
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
       x-ratelimit-remaining-requests:
-      - '499'
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
       x-ratelimit-remaining-tokens:
-      - '199687'
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
       x-ratelimit-reset-requests:
-      - 120ms
+      - X-RATELIMIT-RESET-REQUESTS-XXX
       x-ratelimit-reset-tokens:
-      - 93ms
+      - X-RATELIMIT-RESET-TOKENS-XXX
       x-request-id:
-      - req_REDACTED
+      - X-REQUEST-ID-XXX
     status:
       code: 200
       message: OK
 - request:
-    body: '{"trace_id": "c682f49d-bb6b-49d9-84b7-06e1881d37cd", "execution_type": "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null, "crew_name": "crew", "flow_name": null, "crewai_version": "1.4.1", "privacy_level": "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count": 0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-11-15T21:20:09.431751+00:00"}, "ephemeral_trace_id": "c682f49d-bb6b-49d9-84b7-06e1881d37cd"}'
+    body: '{"trace_id": "c682f49d-bb6b-49d9-84b7-06e1881d37cd", "execution_type":
+      "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null,
+      "crew_name": "crew", "flow_name": null, "crewai_version": "1.4.1", "privacy_level":
+      "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count":
+      0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-11-15T21:20:09.431751+00:00"},
+      "ephemeral_trace_id": "c682f49d-bb6b-49d9-84b7-06e1881d37cd"}'
     headers:
       Accept:
       - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
       Connection:
       - keep-alive
       Content-Length:
@@ -110,11 +141,13 @@ interactions:
       Content-Type:
       - application/json
       User-Agent:
-      - CrewAI-CLI/1.4.1
+      - X-USER-AGENT-XXX
       X-Crewai-Organization-Id:
       - 73c2b193-f579-422c-84c7-76a39a1da77f
       X-Crewai-Version:
       - 1.4.1
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
     method: POST
     uri: https://app.crewai.com/crewai_plus/api/v1/tracing/ephemeral/batches
   response:
@@ -132,36 +165,168 @@ interactions:
       cache-control:
       - no-store
       content-security-policy:
-      - 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/ https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net https://js.hscollectedforms.net
-        https://js.usemessages.com https://snap.licdn.com https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data: *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com; connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com https://api.hubspot.com
-        https://forms.hscollectedforms.net https://api.hubapi.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509 https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self'' *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com https://drive.google.com https://slides.google.com https://accounts.google.com https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/ https://www.youtube.com https://share.descript.com'
+      - CSP-FILTERED
       etag:
-      - W/"e8d1e903c8c6ec2f765163c0c03bed79"
+      - ETAG-XXX
       expires:
       - '0'
       permissions-policy:
-      - camera=(), microphone=(self), geolocation=()
+      - PERMISSIONS-POLICY-XXX
       pragma:
       - no-cache
       referrer-policy:
-      - strict-origin-when-cross-origin
+      - REFERRER-POLICY-XXX
       strict-transport-security:
-      - max-age=63072000; includeSubDomains
+      - STS-XXX
       vary:
       - Accept
       x-content-type-options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
       x-frame-options:
-      - SAMEORIGIN
+      - X-FRAME-OPTIONS-XXX
       x-permitted-cross-domain-policies:
-      - none
+      - X-PERMITTED-XXX
       x-request-id:
-      - 5ea5f513-c359-4a92-a84a-08ad44d9857b
+      - X-REQUEST-ID-XXX
       x-runtime:
-      - '0.044665'
+      - X-RUNTIME-XXX
       x-xss-protection:
-      - 1; mode=block
+      - X-XSS-PROTECTION-XXX
     status:
       code: 201
       message: Created
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
+      scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expected criteria for your final
+      answer: The score of the title.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\nFormat your final answer according to the
+      following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
+      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nIMPORTANT:
+      Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or
+      modify the meaning of the content. Only structure it to match the schema format.\n\nDo
+      not include the OpenAPI schema in the final output. Ensure the final output
+      does not include any code block markers like ```json or ```python.\n\nProvide
+      your complete response:"},{"role":"system","content":"You are Scorer. You''re
+      an expert scorer, specialized in scoring titles.\nYour personal goal is: Score
+      the title"},{"role":"user","content":"\nCurrent Task: Give me an integer score
+      between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis
+      is the expected criteria for your final answer: The score of the title.\nyou
+      MUST return the actual complete content as the final answer, not a summary.\nFormat
+      your final answer according to the following OpenAPI schema: {\n  \"properties\":
+      {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\":
+      [\n    \"score\"\n  ],\n  \"title\": \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\":
+      false\n}\n\nIMPORTANT: Preserve the original content exactly as-is. Do NOT rewrite,
+      paraphrase, or modify the meaning of the content. Only structure it to match
+      the schema format.\n\nDo not include the OpenAPI schema in the final output.
+      Ensure the final output does not include any code block markers like ```json
+      or ```python.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '2541'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.12
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-DDE0GSLDtGruDzwtl2bwlAXUmvmHG\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772044464,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"score\\\":4}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        513,\n    \"completion_tokens\": 5,\n    \"total_tokens\": 518,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 25 Feb 2026 18:34:25 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '530'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      set-cookie:
+      - SET-COOKIE-XXX
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
 version: 1

lib/crewai/tests/cassettes/test_task_guardrail_process_output.yaml

@@ -3,11 +3,7 @@ interactions:
     body: "{\"messages\":[{\"role\":\"system\",\"content\":\"You are Guardrail Agent.
       You are a expert at validating the output of a task. By providing effective
       feedback if the output is not valid.\\nYour personal goal is: Validate the output
-      of the task\\nTo give my best complete final answer to the task respond using
-      the exact following format:\\n\\nThought: I now can give a great answer\\nFinal
-      Answer: Your final answer must be the great and the most complete as possible,
-      it must be outcome described.\\n\\nI MUST use these formats, my job depends
-      on it!\"},{\"role\":\"user\",\"content\":\"\\nCurrent Task: \\n        Ensure
+      of the task\"},{\"role\":\"user\",\"content\":\"\\nCurrent Task: \\n        Ensure
       the following task result complies with the given guardrail.\\n\\n        Task
       result:\\n        \\n        Lorem Ipsum is simply dummy text of the printing
       and typesetting industry. Lorem Ipsum has been the industry's standard dummy
@@ -17,8 +13,9 @@ interactions:
       what is wrong (e.g., by how much it violates the rule, or what specific part
       fails).\\n        - Focus only on identifying issues \u2014 do not propose corrections.\\n
       \       - If the Task result complies with the guardrail, saying that is valid\\n
-      \       \\n\\nBegin! This is VERY important to you, use the tools available
-      and give your best Final Answer, your job depends on it!\\n\\nThought:\"}],\"model\":\"gpt-4o\"}"
+      \       \\n\\nProvide your complete response:\"}],\"model\":\"gpt-4o\",\"response_format\":{\"type\":\"json_schema\",\"json_schema\":{\"schema\":{\"properties\":{\"valid\":{\"description\":\"Whether
+      the task output complies with the guardrail\",\"title\":\"Valid\",\"type\":\"boolean\"},\"feedback\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"description\":\"A
+      feedback about the task output if it is not valid\",\"title\":\"Feedback\"}},\"required\":[\"valid\",\"feedback\"],\"title\":\"LLMGuardrailResult\",\"type\":\"object\",\"additionalProperties\":false},\"name\":\"LLMGuardrailResult\",\"strict\":true}},\"stream\":false}"
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -31,7 +28,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1467'
+      - '1567'
       content-type:
       - application/json
       host:
@@ -40,142 +37,6 @@ interactions:
       - X-STAINLESS-ARCH-XXX
       x-stainless-async:
       - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - X-STAINLESS-OS-XXX
-      x-stainless-package-version:
-      - 1.83.0
-      x-stainless-read-timeout:
-      - X-STAINLESS-READ-TIMEOUT-XXX
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.13.3
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: "{\n  \"id\": \"chatcmpl-Cy7yHRYTZi8yzRbcODnKr92keLKCb\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1768446357,\n  \"model\": \"gpt-4o-2024-08-06\",\n
-        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-        \"assistant\",\n        \"content\": \"The task result provided has more than
-        10 words. I will count the words to verify this.\\n\\nThe task result is the
-        following text:\\n\\\"Lorem Ipsum is simply dummy text of the printing and
-        typesetting industry. Lorem Ipsum has been the industry's standard dummy text
-        ever\\\"\\n\\nCounting the words:\\n\\n1. Lorem \\n2. Ipsum \\n3. is \\n4.
-        simply \\n5. dummy \\n6. text \\n7. of \\n8. the \\n9. printing \\n10. and
-        \\n11. typesetting \\n12. industry. \\n13. Lorem \\n14. Ipsum \\n15. has \\n16.
-        been \\n17. the \\n18. industry's \\n19. standard \\n20. dummy \\n21. text
-        \\n22. ever\\n\\nThe total word count is 22.\\n\\nThought: I now can give
-        a great answer\\nFinal Answer: The task result does not comply with the guardrail.
-        It contains 22 words, which exceeds the limit of 10 words.\",\n        \"refusal\":
-        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
-        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-        285,\n    \"completion_tokens\": 195,\n    \"total_tokens\": 480,\n    \"prompt_tokens_details\":
-        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
-        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
-        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-        \"default\",\n  \"system_fingerprint\": \"fp_deacdd5f6f\"\n}\n"
-    headers:
-      CF-RAY:
-      - CF-RAY-XXX
-      Connection:
-      - keep-alive
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 15 Jan 2026 03:05:59 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - SET-COOKIE-XXX
-      Strict-Transport-Security:
-      - STS-XXX
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - X-CONTENT-TYPE-XXX
-      access-control-expose-headers:
-      - ACCESS-CONTROL-XXX
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      content-length:
-      - '1557'
-      openai-organization:
-      - OPENAI-ORG-XXX
-      openai-processing-ms:
-      - '2130'
-      openai-project:
-      - OPENAI-PROJECT-XXX
-      openai-version:
-      - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '2147'
-      x-openai-proxy-wasm:
-      - v0.1
-      x-ratelimit-limit-requests:
-      - X-RATELIMIT-LIMIT-REQUESTS-XXX
-      x-ratelimit-limit-tokens:
-      - X-RATELIMIT-LIMIT-TOKENS-XXX
-      x-ratelimit-remaining-requests:
-      - X-RATELIMIT-REMAINING-REQUESTS-XXX
-      x-ratelimit-remaining-tokens:
-      - X-RATELIMIT-REMAINING-TOKENS-XXX
-      x-ratelimit-reset-requests:
-      - X-RATELIMIT-RESET-REQUESTS-XXX
-      x-ratelimit-reset-tokens:
-      - X-RATELIMIT-RESET-TOKENS-XXX
-      x-request-id:
-      - X-REQUEST-ID-XXX
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"messages":[{"role":"system","content":"Ensure your final answer strictly
-      adheres to the following OpenAPI schema: {\n  \"type\": \"json_schema\",\n  \"json_schema\":
-      {\n    \"name\": \"LLMGuardrailResult\",\n    \"strict\": true,\n    \"schema\":
-      {\n      \"properties\": {\n        \"valid\": {\n          \"description\":
-      \"Whether the task output complies with the guardrail\",\n          \"title\":
-      \"Valid\",\n          \"type\": \"boolean\"\n        },\n        \"feedback\":
-      {\n          \"anyOf\": [\n            {\n              \"type\": \"string\"\n            },\n            {\n              \"type\":
-      \"null\"\n            }\n          ],\n          \"default\": null,\n          \"description\":
-      \"A feedback about the task output if it is not valid\",\n          \"title\":
-      \"Feedback\"\n        }\n      },\n      \"required\": [\n        \"valid\",\n        \"feedback\"\n      ],\n      \"title\":
-      \"LLMGuardrailResult\",\n      \"type\": \"object\",\n      \"additionalProperties\":
-      false\n    }\n  }\n}\n\nDo not include the OpenAPI schema in the final output.
-      Ensure the final output does not include any code block markers like ```json
-      or ```python."},{"role":"user","content":"The task result does not comply with
-      the guardrail. It contains 22 words, which exceeds the limit of 10 words."}],"model":"gpt-4o","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"valid":{"description":"Whether
-      the task output complies with the guardrail","title":"Valid","type":"boolean"},"feedback":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"A
-      feedback about the task output if it is not valid","title":"Feedback"}},"required":["valid","feedback"],"title":"LLMGuardrailResult","type":"object","additionalProperties":false},"name":"LLMGuardrailResult","strict":true}},"stream":false}'
-    headers:
-      User-Agent:
-      - X-USER-AGENT-XXX
-      accept:
-      - application/json
-      accept-encoding:
-      - ACCEPT-ENCODING-XXX
-      authorization:
-      - AUTHORIZATION-XXX
-      connection:
-      - keep-alive
-      content-length:
-      - '1835'
-      content-type:
-      - application/json
-      cookie:
-      - COOKIE-XXX
-      host:
-      - api.openai.com
-      x-stainless-arch:
-      - X-STAINLESS-ARCH-XXX
-      x-stainless-async:
-      - 'false'
       x-stainless-helper-method:
       - beta.chat.completions.parse
       x-stainless-lang:
@@ -191,23 +52,24 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.3
+      - 3.13.12
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-Cy7yJiPCk4fXuogyT5e8XeGRLCSf8\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1768446359,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      string: "{\n  \"id\": \"chatcmpl-DDGANa7LCEtvfCZsEly4mNksTjCX3\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772052779,\n  \"model\": \"gpt-4o-2024-08-06\",\n
         \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
         \"assistant\",\n        \"content\": \"{\\\"valid\\\":false,\\\"feedback\\\":\\\"The
-        task output exceeds the word limit of 10 words by containing 22 words.\\\"}\",\n
-        \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
-        null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-        363,\n    \"completion_tokens\": 25,\n    \"total_tokens\": 388,\n    \"prompt_tokens_details\":
-        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        task result contains more than 10 words. Specifically, it has 20 words, which
+        exceeds the guardrail limit by 10 words.\\\"}\",\n        \"refusal\": null,\n
+        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 290,\n    \"completion_tokens\":
+        37,\n    \"total_tokens\": 327,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
         {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
         0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-        \"default\",\n  \"system_fingerprint\": \"fp_a0e9480a2f\"\n}\n"
+        \"default\",\n  \"system_fingerprint\": \"fp_64dfa806c7\"\n}\n"
     headers:
       CF-RAY:
       - CF-RAY-XXX
@@ -216,7 +78,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 15 Jan 2026 03:05:59 GMT
+      - Wed, 25 Feb 2026 20:53:00 GMT
       Server:
       - cloudflare
       Strict-Transport-Security:
@@ -231,18 +93,16 @@ interactions:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
-      content-length:
-      - '913'
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '488'
+      - '1108'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '507'
+      set-cookie:
+      - SET-COOKIE-XXX
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:
@@ -266,11 +126,7 @@ interactions:
     body: "{\"messages\":[{\"role\":\"system\",\"content\":\"You are Guardrail Agent.
       You are a expert at validating the output of a task. By providing effective
       feedback if the output is not valid.\\nYour personal goal is: Validate the output
-      of the task\\nTo give my best complete final answer to the task respond using
-      the exact following format:\\n\\nThought: I now can give a great answer\\nFinal
-      Answer: Your final answer must be the great and the most complete as possible,
-      it must be outcome described.\\n\\nI MUST use these formats, my job depends
-      on it!\"},{\"role\":\"user\",\"content\":\"\\nCurrent Task: \\n        Ensure
+      of the task\"},{\"role\":\"user\",\"content\":\"\\nCurrent Task: \\n        Ensure
       the following task result complies with the given guardrail.\\n\\n        Task
       result:\\n        \\n        Lorem Ipsum is simply dummy text of the printing
       and typesetting industry. Lorem Ipsum has been the industry's standard dummy
@@ -280,8 +136,9 @@ interactions:
       explaining what is wrong (e.g., by how much it violates the rule, or what specific
       part fails).\\n        - Focus only on identifying issues \u2014 do not propose
       corrections.\\n        - If the Task result complies with the guardrail, saying
-      that is valid\\n        \\n\\nBegin! This is VERY important to you, use the
-      tools available and give your best Final Answer, your job depends on it!\\n\\nThought:\"}],\"model\":\"gpt-4o\"}"
+      that is valid\\n        \\n\\nProvide your complete response:\"}],\"model\":\"gpt-4o\",\"response_format\":{\"type\":\"json_schema\",\"json_schema\":{\"schema\":{\"properties\":{\"valid\":{\"description\":\"Whether
+      the task output complies with the guardrail\",\"title\":\"Valid\",\"type\":\"boolean\"},\"feedback\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"description\":\"A
+      feedback about the task output if it is not valid\",\"title\":\"Feedback\"}},\"required\":[\"valid\",\"feedback\"],\"title\":\"LLMGuardrailResult\",\"type\":\"object\",\"additionalProperties\":false},\"name\":\"LLMGuardrailResult\",\"strict\":true}},\"stream\":false}"
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -294,7 +151,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1468'
+      - '1568'
       content-type:
       - application/json
       host:
@@ -303,144 +160,6 @@ interactions:
       - X-STAINLESS-ARCH-XXX
       x-stainless-async:
       - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - X-STAINLESS-OS-XXX
-      x-stainless-package-version:
-      - 1.83.0
-      x-stainless-read-timeout:
-      - X-STAINLESS-READ-TIMEOUT-XXX
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.13.3
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: "{\n  \"id\": \"chatcmpl-Cy7yKa0rmi2YoTLpyXt9hjeLt2rTI\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1768446360,\n  \"model\": \"gpt-4o-2024-08-06\",\n
-        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-        \"assistant\",\n        \"content\": \"First, I'll count the number of words
-        in the Task result to ensure it complies with the guardrail. \\n\\nThe Task
-        result is: \\\"Lorem Ipsum is simply dummy text of the printing and typesetting
-        industry. Lorem Ipsum has been the industry's standard dummy text ever.\\\"\\n\\nBy
-        counting the words: \\n1. Lorem\\n2. Ipsum\\n3. is\\n4. simply\\n5. dummy\\n6.
-        text\\n7. of\\n8. the\\n9. printing\\n10. and\\n11. typesetting\\n12. industry\\n13.
-        Lorem\\n14. Ipsum\\n15. has\\n16. been\\n17. the\\n18. industry's\\n19. standard\\n20.
-        dummy\\n21. text\\n22. ever\\n\\nThere are 22 words total in the Task result.\\n\\nI
-        need to verify if the count of 22 words is less than the guardrail limit of
-        500 words.\\n\\nThought: I now can give a great answer\\nFinal Answer: The
-        Task result complies with the guardrail as it contains 22 words, which is
-        less than the 500-word limit. Therefore, the output is valid.\",\n        \"refusal\":
-        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
-        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-        285,\n    \"completion_tokens\": 227,\n    \"total_tokens\": 512,\n    \"prompt_tokens_details\":
-        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
-        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
-        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-        \"default\",\n  \"system_fingerprint\": \"fp_deacdd5f6f\"\n}\n"
-    headers:
-      CF-RAY:
-      - CF-RAY-XXX
-      Connection:
-      - keep-alive
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 15 Jan 2026 03:06:02 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - SET-COOKIE-XXX
-      Strict-Transport-Security:
-      - STS-XXX
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - X-CONTENT-TYPE-XXX
-      access-control-expose-headers:
-      - ACCESS-CONTROL-XXX
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      content-length:
-      - '1668'
-      openai-organization:
-      - OPENAI-ORG-XXX
-      openai-processing-ms:
-      - '2502'
-      openai-project:
-      - OPENAI-PROJECT-XXX
-      openai-version:
-      - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '2522'
-      x-openai-proxy-wasm:
-      - v0.1
-      x-ratelimit-limit-requests:
-      - X-RATELIMIT-LIMIT-REQUESTS-XXX
-      x-ratelimit-limit-tokens:
-      - X-RATELIMIT-LIMIT-TOKENS-XXX
-      x-ratelimit-remaining-requests:
-      - X-RATELIMIT-REMAINING-REQUESTS-XXX
-      x-ratelimit-remaining-tokens:
-      - X-RATELIMIT-REMAINING-TOKENS-XXX
-      x-ratelimit-reset-requests:
-      - X-RATELIMIT-RESET-REQUESTS-XXX
-      x-ratelimit-reset-tokens:
-      - X-RATELIMIT-RESET-TOKENS-XXX
-      x-request-id:
-      - X-REQUEST-ID-XXX
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"messages":[{"role":"system","content":"Ensure your final answer strictly
-      adheres to the following OpenAPI schema: {\n  \"type\": \"json_schema\",\n  \"json_schema\":
-      {\n    \"name\": \"LLMGuardrailResult\",\n    \"strict\": true,\n    \"schema\":
-      {\n      \"properties\": {\n        \"valid\": {\n          \"description\":
-      \"Whether the task output complies with the guardrail\",\n          \"title\":
-      \"Valid\",\n          \"type\": \"boolean\"\n        },\n        \"feedback\":
-      {\n          \"anyOf\": [\n            {\n              \"type\": \"string\"\n            },\n            {\n              \"type\":
-      \"null\"\n            }\n          ],\n          \"default\": null,\n          \"description\":
-      \"A feedback about the task output if it is not valid\",\n          \"title\":
-      \"Feedback\"\n        }\n      },\n      \"required\": [\n        \"valid\",\n        \"feedback\"\n      ],\n      \"title\":
-      \"LLMGuardrailResult\",\n      \"type\": \"object\",\n      \"additionalProperties\":
-      false\n    }\n  }\n}\n\nDo not include the OpenAPI schema in the final output.
-      Ensure the final output does not include any code block markers like ```json
-      or ```python."},{"role":"user","content":"The Task result complies with the
-      guardrail as it contains 22 words, which is less than the 500-word limit. Therefore,
-      the output is valid."}],"model":"gpt-4o","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"valid":{"description":"Whether
-      the task output complies with the guardrail","title":"Valid","type":"boolean"},"feedback":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"A
-      feedback about the task output if it is not valid","title":"Feedback"}},"required":["valid","feedback"],"title":"LLMGuardrailResult","type":"object","additionalProperties":false},"name":"LLMGuardrailResult","strict":true}},"stream":false}'
-    headers:
-      User-Agent:
-      - X-USER-AGENT-XXX
-      accept:
-      - application/json
-      accept-encoding:
-      - ACCEPT-ENCODING-XXX
-      authorization:
-      - AUTHORIZATION-XXX
-      connection:
-      - keep-alive
-      content-length:
-      - '1864'
-      content-type:
-      - application/json
-      cookie:
-      - COOKIE-XXX
-      host:
-      - api.openai.com
-      x-stainless-arch:
-      - X-STAINLESS-ARCH-XXX
-      x-stainless-async:
-      - 'false'
       x-stainless-helper-method:
       - beta.chat.completions.parse
       x-stainless-lang:
@@ -456,22 +175,22 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.3
+      - 3.13.12
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-Cy7yMAjNYSCz2foZPEcSVCuapzF8y\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1768446362,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      string: "{\n  \"id\": \"chatcmpl-DDGAO7HbV6K3Iy0lQA058TOzTDoVa\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1772052780,\n  \"model\": \"gpt-4o-2024-08-06\",\n
         \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
         \"assistant\",\n        \"content\": \"{\\\"valid\\\":true,\\\"feedback\\\":null}\",\n
         \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
         null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-        369,\n    \"completion_tokens\": 9,\n    \"total_tokens\": 378,\n    \"prompt_tokens_details\":
+        290,\n    \"completion_tokens\": 9,\n    \"total_tokens\": 299,\n    \"prompt_tokens_details\":
         {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
         {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
         0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-        \"default\",\n  \"system_fingerprint\": \"fp_a0e9480a2f\"\n}\n"
+        \"default\",\n  \"system_fingerprint\": \"fp_1d6b4c17c3\"\n}\n"
     headers:
       CF-RAY:
       - CF-RAY-XXX
@@ -480,7 +199,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 15 Jan 2026 03:06:03 GMT
+      - Wed, 25 Feb 2026 20:53:01 GMT
       Server:
       - cloudflare
       Strict-Transport-Security:
@@ -495,18 +214,16 @@ interactions:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
-      content-length:
-      - '837'
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '413'
+      - '386'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '650'
+      set-cookie:
+      - SET-COOKIE-XXX
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:

lib/crewai/tests/llms/bedrock/test_bedrock.py

@@ -437,17 +437,36 @@ def test_bedrock_aws_credentials_configuration():
     """
     Test that AWS credentials configuration works properly
     """
+    aws_access_key_id = "test-access-key"
+    aws_secret_access_key = "test-secret-key"
+    aws_region_name = "us-east-1"
+
+
     # Test with environment variables
     with patch.dict(os.environ, {
-        "AWS_ACCESS_KEY_ID": "test-access-key",
-        "AWS_SECRET_ACCESS_KEY": "test-secret-key",
-        "AWS_DEFAULT_REGION": "us-east-1"
+        "AWS_ACCESS_KEY_ID": aws_access_key_id,
+        "AWS_SECRET_ACCESS_KEY": aws_secret_access_key,
+        "AWS_DEFAULT_REGION": aws_region_name
     }):
         llm = LLM(model="bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0")
 
         from crewai.llms.providers.bedrock.completion import BedrockCompletion
         assert isinstance(llm, BedrockCompletion)
-        assert llm.region_name == "us-east-1"
+        assert llm.region_name == aws_region_name
+        assert llm.aws_access_key_id == aws_access_key_id
+        assert llm.aws_secret_access_key == aws_secret_access_key
+
+      # Test with litellm environment variables
+    with patch.dict(os.environ, {
+        "AWS_ACCESS_KEY_ID": aws_access_key_id,
+        "AWS_SECRET_ACCESS_KEY": aws_secret_access_key,
+        "AWS_REGION_NAME": aws_region_name
+    }):
+        llm = LLM(model="bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0")
+
+        from crewai.llms.providers.bedrock.completion import BedrockCompletion
+        assert isinstance(llm, BedrockCompletion)
+        assert llm.region_name == aws_region_name
 
     # Test with explicit credentials
     llm_explicit = LLM(

lib/crewai/tests/llms/google/test_google.py

@@ -957,6 +957,47 @@ def test_gemini_agent_kickoff_structured_output_with_tools():
 
 
 
+@pytest.mark.vcr()
+def test_gemini_crew_structured_output_with_tools():
+    """
+    Test that a crew with Gemini can use both tools and output_pydantic on a task.
+    """
+    from pydantic import BaseModel, Field
+    from crewai.tools import tool
+
+    class CalculationResult(BaseModel):
+        operation: str = Field(description="The mathematical operation performed")
+        result: int = Field(description="The result of the calculation")
+        explanation: str = Field(description="Brief explanation of the calculation")
+
+    @tool
+    def add_numbers(a: int, b: int) -> int:
+        """Add two numbers together and return the sum."""
+        return a + b
+
+    agent = Agent(
+        role="Calculator",
+        goal="Perform calculations using available tools",
+        backstory="You are a calculator assistant that uses tools to compute results.",
+        llm=LLM(model="google/gemini-2.0-flash-001"),
+        tools=[add_numbers],
+    )
+
+    task = Task(
+        description="Calculate 15 + 27 using your add_numbers tool. Report the result.",
+        expected_output="A structured calculation result",
+        output_pydantic=CalculationResult,
+        agent=agent,
+    )
+
+    crew = Crew(agents=[agent], tasks=[task])
+    result = crew.kickoff()
+
+    assert result.pydantic is not None, "Expected pydantic output but got None"
+    assert isinstance(result.pydantic, CalculationResult)
+    assert result.pydantic.result == 42, f"Expected 42 but got {result.pydantic.result}"
+
+
 def test_gemini_stop_words_not_applied_to_structured_output():
     """
     Test that stop words are NOT applied when response_model is provided.

lib/crewai/tests/mcp/test_amp_mcp.py

@@ -0,0 +1,373 @@
+"""Tests for AMP MCP config fetching and tool resolution."""
+
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import pytest
+from crewai.agent.core import Agent
+from crewai.mcp.config import MCPServerHTTP, MCPServerSSE
+from crewai.mcp.tool_resolver import MCPToolResolver
+from crewai.tools.base_tool import BaseTool
+
+
+@pytest.fixture
+def agent():
+    return Agent(
+        role="Test Agent",
+        goal="Test goal",
+        backstory="Test backstory",
+    )
+
+
+@pytest.fixture
+def resolver(agent):
+    return MCPToolResolver(agent=agent, logger=agent._logger)
+
+
+@pytest.fixture
+def mock_tool_definitions():
+    return [
+        {
+            "name": "search",
+            "description": "Search tool",
+            "inputSchema": {
+                "type": "object",
+                "properties": {
+                    "query": {"type": "string", "description": "Search query"}
+                },
+                "required": ["query"],
+            },
+        },
+        {
+            "name": "create_page",
+            "description": "Create a page",
+            "inputSchema": {},
+        },
+    ]
+
+
+class TestBuildMCPConfigFromDict:
+    def test_builds_http_config(self):
+        config_dict = {
+            "type": "http",
+            "url": "https://mcp.example.com/api",
+            "headers": {"Authorization": "Bearer token123"},
+            "streamable": True,
+            "cache_tools_list": False,
+        }
+
+        result = MCPToolResolver._build_mcp_config_from_dict(config_dict)
+
+        assert isinstance(result, MCPServerHTTP)
+        assert result.url == "https://mcp.example.com/api"
+        assert result.headers == {"Authorization": "Bearer token123"}
+        assert result.streamable is True
+        assert result.cache_tools_list is False
+
+    def test_builds_sse_config(self):
+        config_dict = {
+            "type": "sse",
+            "url": "https://mcp.example.com/sse",
+            "headers": {"Authorization": "Bearer token123"},
+            "cache_tools_list": True,
+        }
+
+        result = MCPToolResolver._build_mcp_config_from_dict(config_dict)
+
+        assert isinstance(result, MCPServerSSE)
+        assert result.url == "https://mcp.example.com/sse"
+        assert result.headers == {"Authorization": "Bearer token123"}
+        assert result.cache_tools_list is True
+
+    def test_defaults_to_http(self):
+        config_dict = {
+            "url": "https://mcp.example.com/api",
+        }
+
+        result = MCPToolResolver._build_mcp_config_from_dict(config_dict)
+
+        assert isinstance(result, MCPServerHTTP)
+        assert result.streamable is True
+
+    def test_http_defaults(self):
+        config_dict = {
+            "type": "http",
+            "url": "https://mcp.example.com/api",
+        }
+
+        result = MCPToolResolver._build_mcp_config_from_dict(config_dict)
+
+        assert result.headers is None
+        assert result.streamable is True
+        assert result.cache_tools_list is False
+
+
+class TestFetchAmpMCPConfigs:
+    @patch("crewai.cli.plus_api.PlusAPI")
+    @patch("crewai_tools.tools.crewai_platform_tools.misc.get_platform_integration_token", return_value="test-api-key")
+    def test_fetches_configs_successfully(self, mock_get_token, mock_plus_api_class, resolver):
+        mock_response = MagicMock()
+        mock_response.status_code = 200
+        mock_response.json.return_value = {
+            "configs": {
+                "notion": {
+                    "type": "sse",
+                    "url": "https://mcp.notion.so/sse",
+                    "headers": {"Authorization": "Bearer notion-token"},
+                },
+                "github": {
+                    "type": "http",
+                    "url": "https://mcp.github.com/api",
+                    "headers": {"Authorization": "Bearer gh-token"},
+                },
+            },
+        }
+        mock_plus_api = MagicMock()
+        mock_plus_api.get_mcp_configs.return_value = mock_response
+        mock_plus_api_class.return_value = mock_plus_api
+
+        result = resolver._fetch_amp_mcp_configs(["notion", "github"])
+
+        assert "notion" in result
+        assert "github" in result
+        assert result["notion"]["url"] == "https://mcp.notion.so/sse"
+        mock_plus_api_class.assert_called_once_with(api_key="test-api-key")
+        mock_plus_api.get_mcp_configs.assert_called_once_with(["notion", "github"])
+
+    @patch("crewai.cli.plus_api.PlusAPI")
+    @patch("crewai_tools.tools.crewai_platform_tools.misc.get_platform_integration_token", return_value="test-api-key")
+    def test_omits_missing_slugs(self, mock_get_token, mock_plus_api_class, resolver):
+        mock_response = MagicMock()
+        mock_response.status_code = 200
+        mock_response.json.return_value = {
+            "configs": {"notion": {"type": "sse", "url": "https://mcp.notion.so/sse"}},
+        }
+        mock_plus_api = MagicMock()
+        mock_plus_api.get_mcp_configs.return_value = mock_response
+        mock_plus_api_class.return_value = mock_plus_api
+
+        result = resolver._fetch_amp_mcp_configs(["notion", "missing-server"])
+
+        assert "notion" in result
+        assert "missing-server" not in result
+
+    @patch("crewai.cli.plus_api.PlusAPI")
+    @patch("crewai_tools.tools.crewai_platform_tools.misc.get_platform_integration_token", return_value="test-api-key")
+    def test_returns_empty_on_http_error(self, mock_get_token, mock_plus_api_class, resolver):
+        mock_response = MagicMock()
+        mock_response.status_code = 500
+        mock_plus_api = MagicMock()
+        mock_plus_api.get_mcp_configs.return_value = mock_response
+        mock_plus_api_class.return_value = mock_plus_api
+
+        result = resolver._fetch_amp_mcp_configs(["notion"])
+
+        assert result == {}
+
+    @patch("crewai.cli.plus_api.PlusAPI")
+    @patch("crewai_tools.tools.crewai_platform_tools.misc.get_platform_integration_token", return_value="test-api-key")
+    def test_returns_empty_on_network_error(self, mock_get_token, mock_plus_api_class, resolver):
+        import httpx
+
+        mock_plus_api = MagicMock()
+        mock_plus_api.get_mcp_configs.side_effect = httpx.ConnectError("Connection refused")
+        mock_plus_api_class.return_value = mock_plus_api
+
+        result = resolver._fetch_amp_mcp_configs(["notion"])
+
+        assert result == {}
+
+    @patch("crewai_tools.tools.crewai_platform_tools.misc.get_platform_integration_token", side_effect=Exception("No token"))
+    def test_returns_empty_when_no_token(self, mock_get_token, resolver):
+        result = resolver._fetch_amp_mcp_configs(["notion"])
+
+        assert result == {}
+
+
+class TestParseAmpRef:
+    def test_bare_slug(self):
+        slug, tool = MCPToolResolver._parse_amp_ref("notion")
+        assert slug == "notion"
+        assert tool is None
+
+    def test_bare_slug_with_tool(self):
+        slug, tool = MCPToolResolver._parse_amp_ref("notion#search")
+        assert slug == "notion"
+        assert tool == "search"
+
+    def test_bare_slug_with_empty_tool(self):
+        slug, tool = MCPToolResolver._parse_amp_ref("notion#")
+        assert slug == "notion"
+        assert tool is None
+
+    def test_legacy_prefix_slug(self):
+        slug, tool = MCPToolResolver._parse_amp_ref("crewai-amp:notion")
+        assert slug == "notion"
+        assert tool is None
+
+    def test_legacy_prefix_with_tool(self):
+        slug, tool = MCPToolResolver._parse_amp_ref("crewai-amp:notion#search")
+        assert slug == "notion"
+        assert tool == "search"
+
+
+class TestGetMCPToolsAmpIntegration:
+    @patch("crewai.mcp.tool_resolver.MCPClient")
+    @patch.object(MCPToolResolver, "_fetch_amp_mcp_configs")
+    def test_single_request_for_multiple_amp_refs(
+        self, mock_fetch, mock_client_class, agent, mock_tool_definitions
+    ):
+        mock_fetch.return_value = {
+            "notion": {
+                "type": "sse",
+                "url": "https://mcp.notion.so/sse",
+                "headers": {"Authorization": "Bearer token"},
+            },
+            "github": {
+                "type": "http",
+                "url": "https://mcp.github.com/api",
+                "headers": {"Authorization": "Bearer gh-token"},
+                "streamable": True,
+            },
+        }
+
+        mock_client = AsyncMock()
+        mock_client.list_tools = AsyncMock(return_value=mock_tool_definitions)
+        mock_client.connected = False
+        mock_client.connect = AsyncMock()
+        mock_client.disconnect = AsyncMock()
+        mock_client_class.return_value = mock_client
+
+        tools = agent.get_mcp_tools(["notion", "github"])
+
+        mock_fetch.assert_called_once_with(["notion", "github"])
+        assert len(tools) == 4  # 2 tools per server
+
+    @patch("crewai.mcp.tool_resolver.MCPClient")
+    @patch.object(MCPToolResolver, "_fetch_amp_mcp_configs")
+    def test_tool_filter_with_hash_syntax(
+        self, mock_fetch, mock_client_class, agent, mock_tool_definitions
+    ):
+        mock_fetch.return_value = {
+            "notion": {
+                "type": "sse",
+                "url": "https://mcp.notion.so/sse",
+                "headers": {"Authorization": "Bearer token"},
+            },
+        }
+
+        mock_client = AsyncMock()
+        mock_client.list_tools = AsyncMock(return_value=mock_tool_definitions)
+        mock_client.connected = False
+        mock_client.connect = AsyncMock()
+        mock_client.disconnect = AsyncMock()
+        mock_client_class.return_value = mock_client
+
+        tools = agent.get_mcp_tools(["notion#search"])
+
+        mock_fetch.assert_called_once_with(["notion"])
+        assert len(tools) == 1
+        assert tools[0].name == "mcp_notion_so_sse_search"
+
+    @patch("crewai.mcp.tool_resolver.MCPClient")
+    @patch.object(MCPToolResolver, "_fetch_amp_mcp_configs")
+    def test_deduplicates_slugs(
+        self, mock_fetch, mock_client_class, agent, mock_tool_definitions
+    ):
+        mock_fetch.return_value = {
+            "notion": {
+                "type": "sse",
+                "url": "https://mcp.notion.so/sse",
+                "headers": {"Authorization": "Bearer token"},
+            },
+        }
+
+        mock_client = AsyncMock()
+        mock_client.list_tools = AsyncMock(return_value=mock_tool_definitions)
+        mock_client.connected = False
+        mock_client.connect = AsyncMock()
+        mock_client.disconnect = AsyncMock()
+        mock_client_class.return_value = mock_client
+
+        tools = agent.get_mcp_tools(["notion#search", "notion#create_page"])
+
+        mock_fetch.assert_called_once_with(["notion"])
+        assert len(tools) == 2
+
+    @patch.object(MCPToolResolver, "_fetch_amp_mcp_configs")
+    def test_skips_missing_configs_gracefully(self, mock_fetch, agent):
+        mock_fetch.return_value = {}
+
+        tools = agent.get_mcp_tools(["missing-server"])
+
+        assert tools == []
+
+    @patch("crewai.mcp.tool_resolver.MCPClient")
+    @patch.object(MCPToolResolver, "_fetch_amp_mcp_configs")
+    def test_legacy_crewai_amp_prefix_still_works(
+        self, mock_fetch, mock_client_class, agent, mock_tool_definitions
+    ):
+        mock_fetch.return_value = {
+            "notion": {
+                "type": "sse",
+                "url": "https://mcp.notion.so/sse",
+                "headers": {"Authorization": "Bearer token"},
+            },
+        }
+
+        mock_client = AsyncMock()
+        mock_client.list_tools = AsyncMock(return_value=mock_tool_definitions)
+        mock_client.connected = False
+        mock_client.connect = AsyncMock()
+        mock_client.disconnect = AsyncMock()
+        mock_client_class.return_value = mock_client
+
+        tools = agent.get_mcp_tools(["crewai-amp:notion"])
+
+        mock_fetch.assert_called_once_with(["notion"])
+        assert len(tools) == 2
+
+    @patch("crewai.mcp.tool_resolver.MCPClient")
+    @patch.object(MCPToolResolver, "_fetch_amp_mcp_configs")
+    @patch.object(MCPToolResolver, "_resolve_external")
+    def test_non_amp_items_unaffected(
+        self,
+        mock_external,
+        mock_fetch,
+        mock_client_class,
+        agent,
+        mock_tool_definitions,
+    ):
+        mock_fetch.return_value = {
+            "notion": {
+                "type": "sse",
+                "url": "https://mcp.notion.so/sse",
+            },
+        }
+
+        mock_client = AsyncMock()
+        mock_client.list_tools = AsyncMock(return_value=mock_tool_definitions)
+        mock_client.connected = False
+        mock_client.connect = AsyncMock()
+        mock_client.disconnect = AsyncMock()
+        mock_client_class.return_value = mock_client
+
+        mock_external_tool = MagicMock(spec=BaseTool)
+        mock_external.return_value = [mock_external_tool]
+
+        http_config = MCPServerHTTP(
+            url="https://other.mcp.com/api",
+            headers={"Authorization": "Bearer other"},
+        )
+
+        tools = agent.get_mcp_tools(
+            [
+                "notion",
+                "https://external.mcp.com/api",
+                http_config,
+            ]
+        )
+
+        mock_fetch.assert_called_once_with(["notion"])
+        mock_external.assert_called_once_with("https://external.mcp.com/api")
+        # 2 from notion + 1 from external + 2 from http_config
+        assert len(tools) == 5

lib/crewai/tests/mcp/test_mcp_config.py

@@ -1,5 +1,5 @@
 import asyncio
-from unittest.mock import AsyncMock, MagicMock, patch
+from unittest.mock import AsyncMock, patch
 
 import pytest
 from crewai.agent.core import Agent
@@ -46,7 +46,7 @@ def test_agent_with_stdio_mcp_config(mock_tool_definitions):
     )
 
 
-    with patch("crewai.agent.core.MCPClient") as mock_client_class:
+    with patch("crewai.mcp.tool_resolver.MCPClient") as mock_client_class:
         mock_client = AsyncMock()
         mock_client.list_tools = AsyncMock(return_value=mock_tool_definitions)
         mock_client.connected = False  # Will trigger connect
@@ -82,7 +82,7 @@ def test_agent_with_http_mcp_config(mock_tool_definitions):
         mcps=[http_config],
     )
 
-    with patch("crewai.agent.core.MCPClient") as mock_client_class:
+    with patch("crewai.mcp.tool_resolver.MCPClient") as mock_client_class:
         mock_client = AsyncMock()
         mock_client.list_tools = AsyncMock(return_value=mock_tool_definitions)
         mock_client.connected = False  # Will trigger connect
@@ -117,7 +117,7 @@ def test_agent_with_sse_mcp_config(mock_tool_definitions):
         mcps=[sse_config],
     )
 
-    with patch("crewai.agent.core.MCPClient") as mock_client_class:
+    with patch("crewai.mcp.tool_resolver.MCPClient") as mock_client_class:
         mock_client = AsyncMock()
         mock_client.list_tools = AsyncMock(return_value=mock_tool_definitions)
         mock_client.connected = False
@@ -141,7 +141,7 @@ def test_mcp_tool_execution_in_sync_context(mock_tool_definitions):
     """Test MCPNativeTool execution in synchronous context (normal crew execution)."""
     http_config = MCPServerHTTP(url="https://api.example.com/mcp")
 
-    with patch("crewai.agent.core.MCPClient") as mock_client_class:
+    with patch("crewai.mcp.tool_resolver.MCPClient") as mock_client_class:
         mock_client = AsyncMock()
         mock_client.list_tools = AsyncMock(return_value=mock_tool_definitions)
         mock_client.connected = False
@@ -173,7 +173,7 @@ async def test_mcp_tool_execution_in_async_context(mock_tool_definitions):
     """Test MCPNativeTool execution in async context (e.g., from a Flow)."""
     http_config = MCPServerHTTP(url="https://api.example.com/mcp")
 
-    with patch("crewai.agent.core.MCPClient") as mock_client_class:
+    with patch("crewai.mcp.tool_resolver.MCPClient") as mock_client_class:
         mock_client = AsyncMock()
         mock_client.list_tools = AsyncMock(return_value=mock_tool_definitions)
         mock_client.connected = False

lib/crewai/tests/memory/test_unified_memory.py

@@ -218,14 +218,15 @@ def test_memory_slice_recall(tmp_path: Path, mock_embedder: MagicMock) -> None:
     assert isinstance(matches, list)
 
 
-def test_memory_slice_remember_raises_when_read_only(tmp_path: Path, mock_embedder: MagicMock) -> None:
+def test_memory_slice_remember_is_noop_when_read_only(tmp_path: Path, mock_embedder: MagicMock) -> None:
     from crewai.memory.unified_memory import Memory
     from crewai.memory.memory_scope import MemorySlice
 
     mem = Memory(storage=str(tmp_path / "db7"), llm=MagicMock(), embedder=mock_embedder)
     sl = MemorySlice(mem, ["/a"], read_only=True)
-    with pytest.raises(PermissionError):
-        sl.remember("x", scope="/a")
+    result = sl.remember("x", scope="/a")
+    assert result is None
+    assert mem.list_records() == []
 
 
 # --- Flow memory ---
@@ -318,6 +319,7 @@ def test_executor_save_to_memory_calls_extract_then_remember_per_item() -> None:
     from crewai.agents.parser import AgentFinish
 
     mock_memory = MagicMock()
+    mock_memory._read_only = False
     mock_memory.extract_memories.return_value = ["Fact A.", "Fact B."]
 
     mock_agent = MagicMock()
@@ -358,6 +360,7 @@ def test_executor_save_to_memory_skips_delegation_output() -> None:
     from crewai.utilities.string_utils import sanitize_tool_name
 
     mock_memory = MagicMock()
+    mock_memory._read_only = False
     mock_agent = MagicMock()
     mock_agent.memory = mock_memory
     mock_agent._logger = MagicMock()

lib/crewai/tests/test_task.py

@@ -759,11 +759,11 @@ def test_custom_converter_cls():
 
     crew = Crew(agents=[scorer], tasks=[task])
 
-    with patch.object(
-        ScoreConverter, "to_pydantic", return_value=ScoreOutput(score=5)
-    ) as mock_to_pydantic:
-        crew.kickoff()
-        mock_to_pydantic.assert_called_once()
+    # With native structured output, the LLM returns a BaseModel directly,
+    # so the converter is bypassed. Verify the output is valid instead.
+    result = crew.kickoff()
+    assert isinstance(result.pydantic, ScoreOutput)
+    assert isinstance(result.pydantic.score, int)
 
 
 @pytest.mark.vcr()

lib/crewai/tests/tools/test_base_tool.py

@@ -3,6 +3,8 @@ from typing import Callable
 from unittest.mock import patch
 
 import pytest
+from pydantic import BaseModel, Field
+
 from crewai.agent import Agent
 from crewai.crew import Crew
 from crewai.task import Task
@@ -230,3 +232,218 @@ def test_max_usage_count_is_respected():
     crew.kickoff()
     assert tool.max_usage_count == 5
     assert tool.current_usage_count == 5
+
+
+# =============================================================================
+# Schema Validation in run() Tests
+# =============================================================================
+
+
+class CodeExecutorInput(BaseModel):
+    code: str = Field(description="The code to execute")
+    language: str = Field(default="python", description="Programming language")
+
+
+class CodeExecutorTool(BaseTool):
+    name: str = "code_executor"
+    description: str = "Execute code snippets"
+    args_schema: type[BaseModel] = CodeExecutorInput
+
+    def _run(self, code: str, language: str = "python") -> str:
+        return f"Executed {language}: {code}"
+
+
+class TestBaseToolRunValidation:
+    """Tests for args_schema validation in BaseTool.run()."""
+
+    def test_run_with_valid_kwargs_passes_validation(self) -> None:
+        """Valid keyword arguments should pass schema validation and execute."""
+        t = CodeExecutorTool()
+        result = t.run(code="print('hello')")
+        assert result == "Executed python: print('hello')"
+
+    def test_run_with_all_kwargs_passes_validation(self) -> None:
+        """All keyword arguments including optional ones should pass."""
+        t = CodeExecutorTool()
+        result = t.run(code="console.log('hi')", language="javascript")
+        assert result == "Executed javascript: console.log('hi')"
+
+    def test_run_with_no_args_raises_validation_error(self) -> None:
+        """Calling run() with no arguments should raise a clear ValueError,
+        not a cryptic TypeError about missing positional arguments (GH-4611)."""
+        t = CodeExecutorTool()
+        with pytest.raises(ValueError, match="validation failed"):
+            t.run()
+
+    def test_run_with_missing_required_kwarg_raises(self) -> None:
+        """Missing required kwargs should raise ValueError from schema validation."""
+        t = CodeExecutorTool()
+        with pytest.raises(ValueError, match="validation failed"):
+            t.run(language="python")
+
+    def test_run_with_wrong_field_name_raises(self) -> None:
+        """Kwargs not matching any schema field should trigger validation error
+        for missing required fields."""
+        t = CodeExecutorTool()
+        with pytest.raises(ValueError, match="validation failed"):
+            t.run(wrong_arg="value")
+
+    def test_run_with_positional_args_skips_validation(self) -> None:
+        """Positional-arg calls should bypass schema validation (backwards compat)."""
+        class SimpleTool(BaseTool):
+            name: str = "simple"
+            description: str = "A simple tool"
+
+            def _run(self, question: str) -> str:
+                return question
+
+        t = SimpleTool()
+        result = t.run("What is life?")
+        assert result == "What is life?"
+
+    def test_run_strips_extra_kwargs_from_llm(self) -> None:
+        """Extra kwargs not in the schema should be silently stripped,
+        preventing unexpected-keyword crashes in _run."""
+        t = CodeExecutorTool()
+        result = t.run(code="1+1", extra_hallucinated_field="junk")
+        assert result == "Executed python: 1+1"
+
+    def test_run_increments_usage_after_validation(self) -> None:
+        """Usage count should still increment after validated execution."""
+        t = CodeExecutorTool()
+        assert t.current_usage_count == 0
+        t.run(code="x = 1")
+        assert t.current_usage_count == 1
+
+    def test_run_does_not_increment_usage_on_validation_error(self) -> None:
+        """Usage count should NOT increment when validation fails."""
+        t = CodeExecutorTool()
+        assert t.current_usage_count == 0
+        with pytest.raises(ValueError):
+            t.run(wrong="bad")
+        assert t.current_usage_count == 0
+
+
+class TestToolDecoratorRunValidation:
+    """Tests for args_schema validation in Tool.run() (decorator-based tools)."""
+
+    def test_decorator_tool_run_validates_kwargs(self) -> None:
+        """Decorator-created tools should also validate kwargs against schema."""
+        @tool("execute_code")
+        def execute_code(code: str, language: str = "python") -> str:
+            """Execute a code snippet."""
+            return f"Executed {language}: {code}"
+
+        result = execute_code.run(code="x = 1")
+        assert result == "Executed python: x = 1"
+
+    def test_decorator_tool_run_rejects_missing_required(self) -> None:
+        """Decorator tools should reject missing required args via validation."""
+        @tool("execute_code")
+        def execute_code(code: str) -> str:
+            """Execute a code snippet."""
+            return f"Executed: {code}"
+
+        with pytest.raises(ValueError, match="validation failed"):
+            execute_code.run(wrong_arg="value")
+
+    def test_decorator_tool_positional_args_still_work(self) -> None:
+        """Positional args to decorator tools should bypass validation."""
+        @tool("greet")
+        def greet(name: str) -> str:
+            """Greet someone."""
+            return f"Hello, {name}!"
+
+        result = greet.run("World")
+        assert result == "Hello, World!"
+
+
+# =============================================================================
+# Async arun() Schema Validation Tests
+# =============================================================================
+
+
+class AsyncCodeExecutorTool(BaseTool):
+    name: str = "async_code_executor"
+    description: str = "Execute code snippets asynchronously"
+    args_schema: type[BaseModel] = CodeExecutorInput
+
+    async def _arun(self, code: str, language: str = "python") -> str:
+        return f"Async executed {language}: {code}"
+
+    def _run(self, code: str, language: str = "python") -> str:
+        return f"Executed {language}: {code}"
+
+
+class TestBaseToolArunValidation:
+    """Tests for args_schema validation in BaseTool.arun()."""
+
+    @pytest.mark.asyncio
+    async def test_arun_with_valid_kwargs_passes_validation(self) -> None:
+        """Valid keyword arguments should pass schema validation in arun."""
+        t = AsyncCodeExecutorTool()
+        result = await t.arun(code="print('hello')")
+        assert result == "Async executed python: print('hello')"
+
+    @pytest.mark.asyncio
+    async def test_arun_with_no_args_raises_validation_error(self) -> None:
+        """Calling arun() with no arguments should raise a clear ValueError (GH-4611)."""
+        t = AsyncCodeExecutorTool()
+        with pytest.raises(ValueError, match="validation failed"):
+            await t.arun()
+
+    @pytest.mark.asyncio
+    async def test_arun_with_missing_required_kwarg_raises(self) -> None:
+        """Missing required kwargs should raise ValueError in arun."""
+        t = AsyncCodeExecutorTool()
+        with pytest.raises(ValueError, match="validation failed"):
+            await t.arun(language="python")
+
+    @pytest.mark.asyncio
+    async def test_arun_with_wrong_field_name_raises(self) -> None:
+        """Kwargs not matching schema fields should trigger validation error in arun."""
+        t = AsyncCodeExecutorTool()
+        with pytest.raises(ValueError, match="validation failed"):
+            await t.arun(wrong_arg="value")
+
+    @pytest.mark.asyncio
+    async def test_arun_strips_extra_kwargs(self) -> None:
+        """Extra kwargs not in the schema should be stripped in arun."""
+        t = AsyncCodeExecutorTool()
+        result = await t.arun(code="1+1", extra_field="junk")
+        assert result == "Async executed python: 1+1"
+
+    @pytest.mark.asyncio
+    async def test_arun_does_not_increment_usage_on_validation_error(self) -> None:
+        """Usage count should NOT increment when arun validation fails."""
+        t = AsyncCodeExecutorTool()
+        assert t.current_usage_count == 0
+        with pytest.raises(ValueError):
+            await t.arun(wrong="bad")
+        assert t.current_usage_count == 0
+
+
+class TestToolDecoratorArunValidation:
+    """Tests for args_schema validation in Tool.arun() (decorator-based async tools)."""
+
+    @pytest.mark.asyncio
+    async def test_async_decorator_tool_arun_validates_kwargs(self) -> None:
+        """Async decorator tools should validate kwargs in arun."""
+        @tool("async_execute")
+        async def async_execute(code: str, language: str = "python") -> str:
+            """Execute code asynchronously."""
+            return f"Async {language}: {code}"
+
+        result = await async_execute.arun(code="x = 1")
+        assert result == "Async python: x = 1"
+
+    @pytest.mark.asyncio
+    async def test_async_decorator_tool_arun_rejects_missing_required(self) -> None:
+        """Async decorator tools should reject missing required args in arun."""
+        @tool("async_execute")
+        async def async_execute(code: str) -> str:
+            """Execute code asynchronously."""
+            return f"Async: {code}"
+
+        with pytest.raises(ValueError, match="validation failed"):
+            await async_execute.arun(wrong_arg="value")

lib/crewai/tests/utilities/test_agent_utils.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 import asyncio
-from typing import Any
+from typing import Any, Literal, Optional
 from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
@@ -17,6 +17,7 @@ from crewai.utilities.agent_utils import (
     _format_messages_for_summary,
     _split_messages_into_chunks,
     convert_tools_to_openai_schema,
+    parse_tool_call_args,
     summarize_messages,
 )
 
@@ -234,6 +235,79 @@ def _make_mock_i18n() -> MagicMock:
     }.get(key, "")
     return mock_i18n
 
+class MCPStyleInput(BaseModel):
+    """Input schema mimicking an MCP tool with optional fields."""
+
+    query: str = Field(description="Search query")
+    filter_type: Optional[Literal["internal", "user"]] = Field(
+        default=None, description="Filter type"
+    )
+    page_id: Optional[str] = Field(
+        default=None, description="Page UUID"
+    )
+
+
+class MCPStyleTool(BaseTool):
+    """A tool mimicking MCP tool schemas with optional fields."""
+
+    name: str = "mcp_search"
+    description: str = "Search with optional filters"
+    args_schema: type[BaseModel] = MCPStyleInput
+
+    def _run(self, **kwargs: Any) -> str:
+        return "result"
+
+
+class TestOptionalFieldsPreserveNull:
+    """Tests that optional tool fields preserve null in the schema."""
+
+    def test_optional_string_allows_null(self) -> None:
+        """Optional[str] fields should include null in the schema so the LLM
+        can send null instead of being forced to guess a value."""
+        tools = [MCPStyleTool()]
+        schemas, _ = convert_tools_to_openai_schema(tools)
+
+        params = schemas[0]["function"]["parameters"]
+        page_id_prop = params["properties"]["page_id"]
+
+        assert "anyOf" in page_id_prop
+        type_options = [opt.get("type") for opt in page_id_prop["anyOf"]]
+        assert "string" in type_options
+        assert "null" in type_options
+
+    def test_optional_literal_allows_null(self) -> None:
+        """Optional[Literal[...]] fields should include null."""
+        tools = [MCPStyleTool()]
+        schemas, _ = convert_tools_to_openai_schema(tools)
+
+        params = schemas[0]["function"]["parameters"]
+        filter_prop = params["properties"]["filter_type"]
+
+        assert "anyOf" in filter_prop
+        has_null = any(opt.get("type") == "null" for opt in filter_prop["anyOf"])
+        assert has_null
+
+    def test_required_field_stays_non_null(self) -> None:
+        """Required fields without Optional should NOT have null."""
+        tools = [MCPStyleTool()]
+        schemas, _ = convert_tools_to_openai_schema(tools)
+
+        params = schemas[0]["function"]["parameters"]
+        query_prop = params["properties"]["query"]
+
+        assert query_prop.get("type") == "string"
+        assert "anyOf" not in query_prop
+
+    def test_all_fields_in_required_for_strict_mode(self) -> None:
+        """All fields (including optional) must be in required for strict mode."""
+        tools = [MCPStyleTool()]
+        schemas, _ = convert_tools_to_openai_schema(tools)
+
+        params = schemas[0]["function"]["parameters"]
+        assert "query" in params["required"]
+        assert "filter_type" in params["required"]
+        assert "page_id" in params["required"]
+
 
 class TestSummarizeMessages:
     """Tests for summarize_messages function."""
@@ -922,3 +996,56 @@ class TestParallelSummarizationVCR:
         assert summary_msg["role"] == "user"
         assert "files" in summary_msg
         assert "report.pdf" in summary_msg["files"]
+
+
+class TestParseToolCallArgs:
+    """Unit tests for parse_tool_call_args."""
+
+    def test_valid_json_string_returns_dict(self) -> None:
+        args_dict, error = parse_tool_call_args('{"code": "print(1)"}', "run_code", "call_1")
+        assert error is None
+        assert args_dict == {"code": "print(1)"}
+
+    def test_malformed_json_returns_error_dict(self) -> None:
+        args_dict, error = parse_tool_call_args('{"code": "print("hi")"}', "run_code", "call_1")
+        assert args_dict is None
+        assert error is not None
+        assert error["call_id"] == "call_1"
+        assert error["func_name"] == "run_code"
+        assert error["from_cache"] is False
+        assert "Failed to parse tool arguments as JSON" in error["result"]
+        assert "run_code" in error["result"]
+
+    def test_malformed_json_preserves_original_tool(self) -> None:
+        mock_tool = object()
+        _, error = parse_tool_call_args("{bad}", "my_tool", "call_2", original_tool=mock_tool)
+        assert error is not None
+        assert error["original_tool"] is mock_tool
+
+    def test_malformed_json_original_tool_defaults_to_none(self) -> None:
+        _, error = parse_tool_call_args("{bad}", "my_tool", "call_3")
+        assert error is not None
+        assert error["original_tool"] is None
+
+    def test_dict_input_returned_directly(self) -> None:
+        func_args = {"code": "x = 42"}
+        args_dict, error = parse_tool_call_args(func_args, "run_code", "call_4")
+        assert error is None
+        assert args_dict == {"code": "x = 42"}
+
+    def test_empty_dict_input_returned_directly(self) -> None:
+        args_dict, error = parse_tool_call_args({}, "run_code", "call_5")
+        assert error is None
+        assert args_dict == {}
+
+    def test_valid_json_with_nested_values(self) -> None:
+        args_dict, error = parse_tool_call_args(
+            '{"query": "hello", "options": {"limit": 10}}', "search", "call_6"
+        )
+        assert error is None
+        assert args_dict == {"query": "hello", "options": {"limit": 10}}
+
+    def test_error_result_has_correct_keys(self) -> None:
+        _, error = parse_tool_call_args("{bad json}", "tool", "call_7")
+        assert error is not None
+        assert set(error.keys()) == {"call_id", "func_name", "result", "from_cache", "original_tool"}

lib/crewai/tests/utilities/test_llm_utils.py

@@ -81,7 +81,7 @@ def test_create_llm_from_env_with_unaccepted_attributes() -> None:
             "OPENAI_API_KEY": "fake-key",
             "AWS_ACCESS_KEY_ID": "fake-access-key",
             "AWS_SECRET_ACCESS_KEY": "fake-secret-key",
-            "AWS_REGION_NAME": "us-west-2",
+            "AWS_DEFAULT_REGION": "us-west-2",
         },
     ):
         llm = create_llm(llm_value=None)
@@ -89,7 +89,7 @@ def test_create_llm_from_env_with_unaccepted_attributes() -> None:
         assert llm.model == "gpt-3.5-turbo"
         assert not hasattr(llm, "AWS_ACCESS_KEY_ID")
         assert not hasattr(llm, "AWS_SECRET_ACCESS_KEY")
-        assert not hasattr(llm, "AWS_REGION_NAME")
+        assert not hasattr(llm, "AWS_DEFAULT_REGION")
 
 
 def test_create_llm_with_partial_attributes() -> None:

lib/crewai/tests/utilities/test_pydantic_schema_utils.py

@@ -0,0 +1,884 @@
+"""Tests for pydantic_schema_utils module.
+
+Covers:
+- create_model_from_schema: type mapping, required/optional, enums, formats,
+  nested objects, arrays, unions, allOf, $ref, model_name, enrich_descriptions
+- Schema transformation helpers: resolve_refs, force_additional_properties_false,
+  strip_unsupported_formats, ensure_type_in_schemas, convert_oneof_to_anyof,
+  ensure_all_properties_required, strip_null_from_types, build_rich_field_description
+- End-to-end MCP tool schema conversion
+"""
+
+from __future__ import annotations
+
+import datetime
+from copy import deepcopy
+from typing import Any
+
+import pytest
+from pydantic import BaseModel
+
+from crewai.utilities.pydantic_schema_utils import (
+    build_rich_field_description,
+    convert_oneof_to_anyof,
+    create_model_from_schema,
+    ensure_all_properties_required,
+    ensure_type_in_schemas,
+    force_additional_properties_false,
+    resolve_refs,
+    strip_null_from_types,
+    strip_unsupported_formats,
+)
+
+
+class TestSimpleTypes:
+    def test_string_field(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {"name": {"type": "string"}},
+            "required": ["name"],
+        }
+        Model = create_model_from_schema(schema)
+        obj = Model(name="Alice")
+        assert obj.name == "Alice"
+
+    def test_integer_field(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {"count": {"type": "integer"}},
+            "required": ["count"],
+        }
+        Model = create_model_from_schema(schema)
+        obj = Model(count=42)
+        assert obj.count == 42
+
+    def test_number_field(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {"score": {"type": "number"}},
+            "required": ["score"],
+        }
+        Model = create_model_from_schema(schema)
+        obj = Model(score=3.14)
+        assert obj.score == pytest.approx(3.14)
+
+    def test_boolean_field(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {"active": {"type": "boolean"}},
+            "required": ["active"],
+        }
+        Model = create_model_from_schema(schema)
+        assert Model(active=True).active is True
+
+    def test_null_field(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {"value": {"type": "null"}},
+            "required": ["value"],
+        }
+        Model = create_model_from_schema(schema)
+        obj = Model(value=None)
+        assert obj.value is None
+
+
+class TestRequiredOptional:
+    def test_required_field_has_no_default(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {"name": {"type": "string"}},
+            "required": ["name"],
+        }
+        Model = create_model_from_schema(schema)
+        with pytest.raises(Exception):
+            Model()
+
+    def test_optional_field_defaults_to_none(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {"name": {"type": "string"}},
+            "required": [],
+        }
+        Model = create_model_from_schema(schema)
+        obj = Model()
+        assert obj.name is None
+
+    def test_mixed_required_optional(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "id": {"type": "integer"},
+                "label": {"type": "string"},
+            },
+            "required": ["id"],
+        }
+        Model = create_model_from_schema(schema)
+        obj = Model(id=1)
+        assert obj.id == 1
+        assert obj.label is None
+
+
+class TestEnumLiteral:
+    def test_string_enum(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "color": {"type": "string", "enum": ["red", "green", "blue"]},
+            },
+            "required": ["color"],
+        }
+        Model = create_model_from_schema(schema)
+        obj = Model(color="red")
+        assert obj.color == "red"
+
+    def test_string_enum_rejects_invalid(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "color": {"type": "string", "enum": ["red", "green", "blue"]},
+            },
+            "required": ["color"],
+        }
+        Model = create_model_from_schema(schema)
+        with pytest.raises(Exception):
+            Model(color="yellow")
+
+    def test_const_value(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "kind": {"const": "fixed"},
+            },
+            "required": ["kind"],
+        }
+        Model = create_model_from_schema(schema)
+        obj = Model(kind="fixed")
+        assert obj.kind == "fixed"
+
+
+class TestFormatMapping:
+    def test_date_format(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "birthday": {"type": "string", "format": "date"},
+            },
+            "required": ["birthday"],
+        }
+        Model = create_model_from_schema(schema)
+        obj = Model(birthday=datetime.date(2000, 1, 15))
+        assert obj.birthday == datetime.date(2000, 1, 15)
+
+    def test_datetime_format(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "created_at": {"type": "string", "format": "date-time"},
+            },
+            "required": ["created_at"],
+        }
+        Model = create_model_from_schema(schema)
+        dt = datetime.datetime(2025, 6, 1, 12, 0, 0)
+        obj = Model(created_at=dt)
+        assert obj.created_at == dt
+
+    def test_time_format(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "alarm": {"type": "string", "format": "time"},
+            },
+            "required": ["alarm"],
+        }
+        Model = create_model_from_schema(schema)
+        t = datetime.time(8, 30)
+        obj = Model(alarm=t)
+        assert obj.alarm == t
+
+
+class TestNestedObjects:
+    def test_nested_object_creates_model(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "address": {
+                    "type": "object",
+                    "properties": {
+                        "street": {"type": "string"},
+                        "city": {"type": "string"},
+                    },
+                    "required": ["street", "city"],
+                },
+            },
+            "required": ["address"],
+        }
+        Model = create_model_from_schema(schema)
+        obj = Model(address={"street": "123 Main", "city": "Springfield"})
+        assert obj.address.street == "123 Main"
+        assert obj.address.city == "Springfield"
+
+    def test_object_without_properties_returns_dict(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "metadata": {"type": "object"},
+            },
+            "required": ["metadata"],
+        }
+        Model = create_model_from_schema(schema)
+        obj = Model(metadata={"key": "value"})
+        assert obj.metadata == {"key": "value"}
+
+
+class TestTypedArrays:
+    def test_array_of_strings(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "tags": {"type": "array", "items": {"type": "string"}},
+            },
+            "required": ["tags"],
+        }
+        Model = create_model_from_schema(schema)
+        obj = Model(tags=["a", "b", "c"])
+        assert obj.tags == ["a", "b", "c"]
+
+    def test_array_of_objects(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "items": {
+                    "type": "array",
+                    "items": {
+                        "type": "object",
+                        "properties": {"id": {"type": "integer"}},
+                        "required": ["id"],
+                    },
+                },
+            },
+            "required": ["items"],
+        }
+        Model = create_model_from_schema(schema)
+        obj = Model(items=[{"id": 1}, {"id": 2}])
+        assert len(obj.items) == 2
+        assert obj.items[0].id == 1
+
+    def test_untyped_array(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {"data": {"type": "array"}},
+            "required": ["data"],
+        }
+        Model = create_model_from_schema(schema)
+        obj = Model(data=[1, "two", 3.0])
+        assert obj.data == [1, "two", 3.0]
+
+
+class TestUnionTypes:
+    def test_anyof_string_or_integer(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "value": {
+                    "anyOf": [{"type": "string"}, {"type": "integer"}],
+                },
+            },
+            "required": ["value"],
+        }
+        Model = create_model_from_schema(schema)
+        assert Model(value="hello").value == "hello"
+        assert Model(value=42).value == 42
+
+    def test_oneof(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "value": {
+                    "oneOf": [{"type": "string"}, {"type": "number"}],
+                },
+            },
+            "required": ["value"],
+        }
+        Model = create_model_from_schema(schema)
+        assert Model(value="hello").value == "hello"
+        assert Model(value=3.14).value == pytest.approx(3.14)
+
+
+class TestAllOfMerging:
+    def test_allof_merges_properties(self) -> None:
+        schema = {
+            "type": "object",
+            "allOf": [
+                {
+                    "type": "object",
+                    "properties": {"name": {"type": "string"}},
+                    "required": ["name"],
+                },
+                {
+                    "type": "object",
+                    "properties": {"age": {"type": "integer"}},
+                    "required": ["age"],
+                },
+            ],
+        }
+        Model = create_model_from_schema(schema)
+        obj = Model(name="Alice", age=30)
+        assert obj.name == "Alice"
+        assert obj.age == 30
+
+    def test_single_allof(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "item": {
+                    "allOf": [
+                        {
+                            "type": "object",
+                            "properties": {"id": {"type": "integer"}},
+                            "required": ["id"],
+                        }
+                    ]
+                }
+            },
+            "required": ["item"],
+        }
+        Model = create_model_from_schema(schema)
+        obj = Model(item={"id": 1})
+        assert obj.item.id == 1
+
+
+# ---------------------------------------------------------------------------
+# $ref resolution
+# ---------------------------------------------------------------------------
+
+
+class TestRefResolution:
+    def test_ref_in_property(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "item": {"$ref": "#/$defs/Item"},
+            },
+            "required": ["item"],
+            "$defs": {
+                "Item": {
+                    "type": "object",
+                    "title": "Item",
+                    "properties": {"name": {"type": "string"}},
+                    "required": ["name"],
+                },
+            },
+        }
+        Model = create_model_from_schema(schema)
+        obj = Model(item={"name": "Widget"})
+        assert obj.item.name == "Widget"
+
+
+# ---------------------------------------------------------------------------
+# model_name parameter
+# ---------------------------------------------------------------------------
+
+
+class TestModelName:
+    def test_model_name_override(self) -> None:
+        schema = {
+            "type": "object",
+            "title": "OriginalName",
+            "properties": {"x": {"type": "integer"}},
+            "required": ["x"],
+        }
+        Model = create_model_from_schema(schema, model_name="CustomSchema")
+        assert Model.__name__ == "CustomSchema"
+
+    def test_model_name_fallback_to_title(self) -> None:
+        schema = {
+            "type": "object",
+            "title": "FromTitle",
+            "properties": {"x": {"type": "integer"}},
+            "required": ["x"],
+        }
+        Model = create_model_from_schema(schema)
+        assert Model.__name__ == "FromTitle"
+
+    def test_model_name_fallback_to_dynamic(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {"x": {"type": "integer"}},
+            "required": ["x"],
+        }
+        Model = create_model_from_schema(schema)
+        assert Model.__name__ == "DynamicModel"
+
+
+# ---------------------------------------------------------------------------
+# enrich_descriptions
+# ---------------------------------------------------------------------------
+
+
+class TestEnrichDescriptions:
+    def test_enriched_description_includes_constraints(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "score": {
+                    "type": "integer",
+                    "description": "The score value",
+                    "minimum": 0,
+                    "maximum": 100,
+                },
+            },
+            "required": ["score"],
+        }
+        Model = create_model_from_schema(schema, enrich_descriptions=True)
+        field_info = Model.model_fields["score"]
+        assert "Minimum: 0" in field_info.description
+        assert "Maximum: 100" in field_info.description
+        assert "The score value" in field_info.description
+
+    def test_default_does_not_enrich(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "score": {
+                    "type": "integer",
+                    "description": "The score value",
+                    "minimum": 0,
+                },
+            },
+            "required": ["score"],
+        }
+        Model = create_model_from_schema(schema, enrich_descriptions=False)
+        field_info = Model.model_fields["score"]
+        assert field_info.description == "The score value"
+
+    def test_enriched_description_propagates_to_nested(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "config": {
+                    "type": "object",
+                    "properties": {
+                        "level": {
+                            "type": "integer",
+                            "description": "Level",
+                            "minimum": 1,
+                            "maximum": 10,
+                        },
+                    },
+                    "required": ["level"],
+                },
+            },
+            "required": ["config"],
+        }
+        Model = create_model_from_schema(schema, enrich_descriptions=True)
+        nested_model = Model.model_fields["config"].annotation
+        nested_field = nested_model.model_fields["level"]
+        assert "Minimum: 1" in nested_field.description
+        assert "Maximum: 10" in nested_field.description
+
+
+# ---------------------------------------------------------------------------
+# Edge cases
+# ---------------------------------------------------------------------------
+
+
+class TestEdgeCases:
+    def test_empty_properties(self) -> None:
+        schema = {"type": "object", "properties": {}, "required": []}
+        Model = create_model_from_schema(schema)
+        obj = Model()
+        assert obj is not None
+
+    def test_no_properties_key(self) -> None:
+        schema = {"type": "object"}
+        Model = create_model_from_schema(schema)
+        obj = Model()
+        assert obj is not None
+
+    def test_unknown_type_raises(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "weird": {"type": "hyperspace"},
+            },
+            "required": ["weird"],
+        }
+        with pytest.raises(ValueError, match="Unsupported JSON schema type"):
+            create_model_from_schema(schema)
+
+
+# ---------------------------------------------------------------------------
+# build_rich_field_description
+# ---------------------------------------------------------------------------
+
+
+class TestBuildRichFieldDescription:
+    def test_description_only(self) -> None:
+        assert build_rich_field_description({"description": "A name"}) == "A name"
+
+    def test_empty_schema(self) -> None:
+        assert build_rich_field_description({}) == ""
+
+    def test_format(self) -> None:
+        desc = build_rich_field_description({"format": "date-time"})
+        assert "Format: date-time" in desc
+
+    def test_enum(self) -> None:
+        desc = build_rich_field_description({"enum": ["a", "b"]})
+        assert "Allowed values:" in desc
+        assert "'a'" in desc
+        assert "'b'" in desc
+
+    def test_pattern(self) -> None:
+        desc = build_rich_field_description({"pattern": "^[a-z]+$"})
+        assert "Pattern: ^[a-z]+$" in desc
+
+    def test_min_max(self) -> None:
+        desc = build_rich_field_description({"minimum": 0, "maximum": 100})
+        assert "Minimum: 0" in desc
+        assert "Maximum: 100" in desc
+
+    def test_min_max_length(self) -> None:
+        desc = build_rich_field_description({"minLength": 1, "maxLength": 255})
+        assert "Min length: 1" in desc
+        assert "Max length: 255" in desc
+
+    def test_examples(self) -> None:
+        desc = build_rich_field_description({"examples": ["foo", "bar", "baz", "extra"]})
+        assert "Examples:" in desc
+        assert "'foo'" in desc
+        assert "'baz'" in desc
+        # Only first 3 shown
+        assert "'extra'" not in desc
+
+    def test_combined_constraints(self) -> None:
+        desc = build_rich_field_description({
+            "description": "A score",
+            "minimum": 0,
+            "maximum": 10,
+            "format": "int32",
+        })
+        assert desc.startswith("A score")
+        assert "Minimum: 0" in desc
+        assert "Maximum: 10" in desc
+        assert "Format: int32" in desc
+
+
+# ---------------------------------------------------------------------------
+# Schema transformation functions
+# ---------------------------------------------------------------------------
+
+
+class TestResolveRefs:
+    def test_basic_ref_resolution(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {"item": {"$ref": "#/$defs/Item"}},
+            "$defs": {
+                "Item": {"type": "object", "properties": {"id": {"type": "integer"}}},
+            },
+        }
+        resolved = resolve_refs(schema)
+        assert "$ref" not in resolved["properties"]["item"]
+        assert resolved["properties"]["item"]["type"] == "object"
+
+    def test_nested_ref_resolution(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {"wrapper": {"$ref": "#/$defs/Wrapper"}},
+            "$defs": {
+                "Wrapper": {
+                    "type": "object",
+                    "properties": {"inner": {"$ref": "#/$defs/Inner"}},
+                },
+                "Inner": {"type": "string"},
+            },
+        }
+        resolved = resolve_refs(schema)
+        wrapper = resolved["properties"]["wrapper"]
+        assert wrapper["properties"]["inner"]["type"] == "string"
+
+    def test_missing_ref_raises(self) -> None:
+        schema = {
+            "properties": {"x": {"$ref": "#/$defs/Missing"}},
+            "$defs": {},
+        }
+        with pytest.raises(KeyError, match="Missing"):
+            resolve_refs(schema)
+
+    def test_no_refs_unchanged(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {"name": {"type": "string"}},
+        }
+        resolved = resolve_refs(schema)
+        assert resolved == schema
+
+
+class TestForceAdditionalPropertiesFalse:
+    def test_adds_to_object(self) -> None:
+        schema = {"type": "object", "properties": {"x": {"type": "integer"}}}
+        result = force_additional_properties_false(deepcopy(schema))
+        assert result["additionalProperties"] is False
+
+    def test_adds_empty_properties_and_required(self) -> None:
+        schema = {"type": "object"}
+        result = force_additional_properties_false(deepcopy(schema))
+        assert result["properties"] == {}
+        assert result["required"] == []
+
+    def test_recursive_nested_objects(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "child": {
+                    "type": "object",
+                    "properties": {"id": {"type": "integer"}},
+                },
+            },
+        }
+        result = force_additional_properties_false(deepcopy(schema))
+        assert result["additionalProperties"] is False
+        assert result["properties"]["child"]["additionalProperties"] is False
+
+    def test_does_not_affect_non_objects(self) -> None:
+        schema = {"type": "string"}
+        result = force_additional_properties_false(deepcopy(schema))
+        assert "additionalProperties" not in result
+
+
+class TestStripUnsupportedFormats:
+    def test_removes_email_format(self) -> None:
+        schema = {"type": "string", "format": "email"}
+        result = strip_unsupported_formats(deepcopy(schema))
+        assert "format" not in result
+
+    def test_keeps_date_time(self) -> None:
+        schema = {"type": "string", "format": "date-time"}
+        result = strip_unsupported_formats(deepcopy(schema))
+        assert result["format"] == "date-time"
+
+    def test_keeps_date(self) -> None:
+        schema = {"type": "string", "format": "date"}
+        result = strip_unsupported_formats(deepcopy(schema))
+        assert result["format"] == "date"
+
+    def test_removes_uri_format(self) -> None:
+        schema = {"type": "string", "format": "uri"}
+        result = strip_unsupported_formats(deepcopy(schema))
+        assert "format" not in result
+
+    def test_recursive(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "email": {"type": "string", "format": "email"},
+                "created": {"type": "string", "format": "date-time"},
+            },
+        }
+        result = strip_unsupported_formats(deepcopy(schema))
+        assert "format" not in result["properties"]["email"]
+        assert result["properties"]["created"]["format"] == "date-time"
+
+
+class TestEnsureTypeInSchemas:
+    def test_empty_schema_in_anyof_gets_type(self) -> None:
+        schema = {"anyOf": [{}, {"type": "string"}]}
+        result = ensure_type_in_schemas(deepcopy(schema))
+        assert result["anyOf"][0] == {"type": "object"}
+
+    def test_empty_schema_in_oneof_gets_type(self) -> None:
+        schema = {"oneOf": [{}, {"type": "integer"}]}
+        result = ensure_type_in_schemas(deepcopy(schema))
+        assert result["oneOf"][0] == {"type": "object"}
+
+    def test_non_empty_unchanged(self) -> None:
+        schema = {"anyOf": [{"type": "string"}, {"type": "integer"}]}
+        result = ensure_type_in_schemas(deepcopy(schema))
+        assert result == schema
+
+
+class TestConvertOneofToAnyof:
+    def test_converts_top_level(self) -> None:
+        schema = {"oneOf": [{"type": "string"}, {"type": "integer"}]}
+        result = convert_oneof_to_anyof(deepcopy(schema))
+        assert "oneOf" not in result
+        assert "anyOf" in result
+        assert len(result["anyOf"]) == 2
+
+    def test_converts_nested(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "value": {"oneOf": [{"type": "string"}, {"type": "number"}]},
+            },
+        }
+        result = convert_oneof_to_anyof(deepcopy(schema))
+        assert "anyOf" in result["properties"]["value"]
+        assert "oneOf" not in result["properties"]["value"]
+
+
+class TestEnsureAllPropertiesRequired:
+    def test_makes_all_required(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {"a": {"type": "string"}, "b": {"type": "integer"}},
+            "required": ["a"],
+        }
+        result = ensure_all_properties_required(deepcopy(schema))
+        assert set(result["required"]) == {"a", "b"}
+
+    def test_recursive(self) -> None:
+        schema = {
+            "type": "object",
+            "properties": {
+                "child": {
+                    "type": "object",
+                    "properties": {"x": {"type": "integer"}, "y": {"type": "integer"}},
+                    "required": [],
+                },
+            },
+        }
+        result = ensure_all_properties_required(deepcopy(schema))
+        assert set(result["properties"]["child"]["required"]) == {"x", "y"}
+
+
+class TestStripNullFromTypes:
+    def test_strips_null_from_anyof(self) -> None:
+        schema = {
+            "anyOf": [{"type": "string"}, {"type": "null"}],
+        }
+        result = strip_null_from_types(deepcopy(schema))
+        assert "anyOf" not in result
+        assert result["type"] == "string"
+
+    def test_strips_null_from_type_array(self) -> None:
+        schema = {"type": ["string", "null"]}
+        result = strip_null_from_types(deepcopy(schema))
+        assert result["type"] == "string"
+
+    def test_multiple_non_null_in_anyof(self) -> None:
+        schema = {
+            "anyOf": [{"type": "string"}, {"type": "integer"}, {"type": "null"}],
+        }
+        result = strip_null_from_types(deepcopy(schema))
+        assert len(result["anyOf"]) == 2
+
+    def test_no_null_unchanged(self) -> None:
+        schema = {"type": "string"}
+        result = strip_null_from_types(deepcopy(schema))
+        assert result == schema
+
+
+class TestEndToEndMCPSchema:
+    """Realistic MCP tool schema exercising multiple features simultaneously."""
+
+    MCP_SCHEMA: dict[str, Any] = {
+        "type": "object",
+        "properties": {
+            "query": {
+                "type": "string",
+                "description": "Search query",
+                "minLength": 1,
+                "maxLength": 500,
+            },
+            "max_results": {
+                "type": "integer",
+                "description": "Maximum results",
+                "minimum": 1,
+                "maximum": 100,
+            },
+            "format": {
+                "type": "string",
+                "enum": ["json", "csv", "xml"],
+                "description": "Output format",
+            },
+            "filters": {
+                "type": "object",
+                "properties": {
+                    "date_from": {"type": "string", "format": "date"},
+                    "date_to": {"type": "string", "format": "date"},
+                    "categories": {
+                        "type": "array",
+                        "items": {"type": "string"},
+                    },
+                },
+                "required": ["date_from"],
+            },
+            "sort_order": {
+                "anyOf": [{"type": "string"}, {"type": "null"}],
+            },
+        },
+        "required": ["query", "format", "filters"],
+    }
+
+    def test_model_creation(self) -> None:
+        Model = create_model_from_schema(self.MCP_SCHEMA)
+        assert Model is not None
+        assert issubclass(Model, BaseModel)
+
+    def test_valid_input_accepted(self) -> None:
+        Model = create_model_from_schema(self.MCP_SCHEMA)
+        obj = Model(
+            query="test search",
+            format="json",
+            filters={"date_from": "2025-01-01"},
+        )
+        assert obj.query == "test search"
+        assert obj.format == "json"
+
+    def test_invalid_enum_rejected(self) -> None:
+        Model = create_model_from_schema(self.MCP_SCHEMA)
+        with pytest.raises(Exception):
+            Model(
+                query="test",
+                format="yaml",
+                filters={"date_from": "2025-01-01"},
+            )
+
+    def test_model_name_for_mcp_tool(self) -> None:
+        Model = create_model_from_schema(
+            self.MCP_SCHEMA, model_name="search_toolSchema"
+        )
+        assert Model.__name__ == "search_toolSchema"
+
+    def test_enriched_descriptions_for_mcp(self) -> None:
+        Model = create_model_from_schema(
+            self.MCP_SCHEMA, enrich_descriptions=True
+        )
+        query_field = Model.model_fields["query"]
+        assert "Min length: 1" in query_field.description
+        assert "Max length: 500" in query_field.description
+
+        max_results_field = Model.model_fields["max_results"]
+        assert "Minimum: 1" in max_results_field.description
+        assert "Maximum: 100" in max_results_field.description
+
+        format_field = Model.model_fields["format"]
+        assert "Allowed values:" in format_field.description
+
+    def test_optional_fields_accept_none(self) -> None:
+        Model = create_model_from_schema(self.MCP_SCHEMA)
+        obj = Model(
+            query="test",
+            format="csv",
+            filters={"date_from": "2025-01-01"},
+            max_results=None,
+            sort_order=None,
+        )
+        assert obj.max_results is None
+        assert obj.sort_order is None
+
+    def test_nested_filters_validated(self) -> None:
+        Model = create_model_from_schema(self.MCP_SCHEMA)
+        obj = Model(
+            query="test",
+            format="xml",
+            filters={
+                "date_from": "2025-01-01",
+                "date_to": "2025-12-31",
+                "categories": ["news", "tech"],
+            },
+        )
+        assert obj.filters.date_from == datetime.date(2025, 1, 1)
+        assert obj.filters.categories == ["news", "tech"]

lib/devtools/src/crewai_devtools/__init__.py

@@ -1,3 +1,3 @@
 """CrewAI development tools."""
 
-__version__ = "1.9.3"
+__version__ = "1.10.1a1"

lib/devtools/src/crewai_devtools/cli.py

@@ -14,7 +14,7 @@ from rich.markdown import Markdown
 from rich.panel import Panel
 from rich.prompt import Confirm
 
-from crewai_devtools.prompts import RELEASE_NOTES_PROMPT
+from crewai_devtools.prompts import RELEASE_NOTES_PROMPT, TRANSLATE_RELEASE_NOTES_PROMPT
 
 
 load_dotenv()
@@ -191,6 +191,248 @@ def update_pyproject_dependencies(file_path: Path, new_version: str) -> bool:
     return False
 
 
+def add_docs_version(docs_json_path: Path, version: str) -> bool:
+    """Add a new version to the Mintlify docs.json versioning config.
+
+    Copies the current default version's tabs into a new version entry,
+    sets the new version as default, and marks the previous default as
+    non-default. Operates on all languages.
+
+    Args:
+        docs_json_path: Path to docs/docs.json.
+        version: Version string (e.g., "1.10.1b1").
+
+    Returns:
+        True if docs.json was updated, False otherwise.
+    """
+    import json
+
+    if not docs_json_path.exists():
+        return False
+
+    data = json.loads(docs_json_path.read_text())
+    version_label = f"v{version}"
+    updated = False
+
+    for lang in data.get("navigation", {}).get("languages", []):
+        versions = lang.get("versions", [])
+        if not versions:
+            continue
+
+        # Skip if this version already exists for this language
+        if any(v.get("version") == version_label for v in versions):
+            continue
+
+        # Find the current default and copy its tabs
+        default_version = next(
+            (v for v in versions if v.get("default")),
+            versions[0],
+        )
+
+        new_version = {
+            "version": version_label,
+            "default": True,
+            "tabs": default_version.get("tabs", []),
+        }
+
+        # Remove default flag from old default
+        default_version.pop("default", None)
+
+        # Insert new version at the beginning
+        versions.insert(0, new_version)
+        updated = True
+
+    if not updated:
+        return False
+
+    docs_json_path.write_text(json.dumps(data, indent=2, ensure_ascii=False) + "\n")
+    return True
+
+
+_PT_BR_MONTHS = {
+    1: "jan",
+    2: "fev",
+    3: "mar",
+    4: "abr",
+    5: "mai",
+    6: "jun",
+    7: "jul",
+    8: "ago",
+    9: "set",
+    10: "out",
+    11: "nov",
+    12: "dez",
+}
+
+_CHANGELOG_LOCALES: dict[str, dict[str, str]] = {
+    "en": {
+        "link_text": "View release on GitHub",
+        "language_name": "English",
+    },
+    "pt-BR": {
+        "link_text": "Ver release no GitHub",
+        "language_name": "Brazilian Portuguese",
+    },
+    "ko": {
+        "link_text": "GitHub 릴리스 보기",
+        "language_name": "Korean",
+    },
+}
+
+
+def translate_release_notes(
+    release_notes: str,
+    lang: str,
+    client: OpenAI,
+) -> str:
+    """Translate release notes into the target language using OpenAI.
+
+    Args:
+        release_notes: English release notes markdown.
+        lang: Language code (e.g., "pt-BR", "ko").
+        client: OpenAI client instance.
+
+    Returns:
+        Translated release notes, or original on failure.
+    """
+    locale_cfg = _CHANGELOG_LOCALES.get(lang)
+    if not locale_cfg:
+        return release_notes
+
+    language_name = locale_cfg["language_name"]
+    prompt = TRANSLATE_RELEASE_NOTES_PROMPT.substitute(
+        language=language_name,
+        release_notes=release_notes,
+    )
+
+    try:
+        response = client.chat.completions.create(
+            model="gpt-4o-mini",
+            messages=[
+                {
+                    "role": "system",
+                    "content": f"You are a professional translator. Translate technical documentation into {language_name}.",
+                },
+                {"role": "user", "content": prompt},
+            ],
+            temperature=0.3,
+        )
+        return response.choices[0].message.content or release_notes
+    except Exception as e:
+        console.print(
+            f"[yellow]Warning:[/yellow] Could not translate to {language_name}: {e}"
+        )
+        return release_notes
+
+
+def _format_changelog_date(lang: str) -> str:
+    """Format today's date for a changelog entry in the given language."""
+    from datetime import datetime
+
+    now = datetime.now()
+    if lang == "ko":
+        return f"{now.year}년 {now.month}월 {now.day}일"
+    if lang == "pt-BR":
+        return f"{now.day:02d} {_PT_BR_MONTHS[now.month]} {now.year}"
+    return now.strftime("%b %d, %Y")
+
+
+def update_changelog(
+    changelog_path: Path,
+    version: str,
+    release_notes: str,
+    lang: str = "en",
+) -> bool:
+    """Prepend a new release entry to a docs changelog file.
+
+    Args:
+        changelog_path: Path to the changelog.mdx file.
+        version: Version string (e.g., "1.9.3").
+        release_notes: Markdown release notes content.
+        lang: Language code for localized date/link text.
+
+    Returns:
+        True if changelog was updated, False otherwise.
+    """
+    if not changelog_path.exists():
+        return False
+
+    locale_cfg = _CHANGELOG_LOCALES.get(lang, _CHANGELOG_LOCALES["en"])
+    date_label = _format_changelog_date(lang)
+    link_text = locale_cfg["link_text"]
+
+    # Indent each non-empty line with 2 spaces to match <Update> block format
+    indented_lines = []
+    for line in release_notes.splitlines():
+        if line.strip():
+            indented_lines.append(f"  {line}")
+        else:
+            indented_lines.append("")
+    indented_notes = "\n".join(indented_lines)
+
+    entry = (
+        f'<Update label="{date_label}">\n'
+        f"  ## v{version}\n"
+        f"\n"
+        f"  [{link_text}]"
+        f"(https://github.com/crewAIInc/crewAI/releases/tag/{version})\n"
+        f"\n"
+        f"{indented_notes}\n"
+        f"\n"
+        f"</Update>"
+    )
+
+    content = changelog_path.read_text()
+
+    # Insert after the frontmatter closing ---
+    parts = content.split("---", 2)
+    if len(parts) >= 3:
+        new_content = (
+            parts[0]
+            + "---"
+            + parts[1]
+            + "---\n"
+            + entry
+            + "\n\n"
+            + parts[2].lstrip("\n")
+        )
+    else:
+        new_content = entry + "\n\n" + content
+
+    changelog_path.write_text(new_content)
+    return True
+
+
+def update_template_dependencies(templates_dir: Path, new_version: str) -> list[Path]:
+    """Update crewai dependency versions in CLI template pyproject.toml files.
+
+    Handles both pinned (==) and minimum (>=) version specifiers,
+    as well as extras like [tools].
+
+    Args:
+        templates_dir: Path to the CLI templates directory.
+        new_version: New version string.
+
+    Returns:
+        List of paths that were updated.
+    """
+    import re
+
+    updated = []
+    for pyproject in templates_dir.rglob("pyproject.toml"):
+        content = pyproject.read_text()
+        new_content = re.sub(
+            r'"crewai(\[tools\])?(==|>=)[^"]*"',
+            lambda m: f'"crewai{(m.group(1) or "")!s}=={new_version}"',
+            content,
+        )
+        if new_content != content:
+            pyproject.write_text(new_content)
+            updated.append(pyproject)
+
+    return updated
+
+
 def find_version_files(base_path: Path) -> list[Path]:
     """Find all __init__.py files that contain __version__.
 
@@ -394,6 +636,22 @@ def bump(version: str, dry_run: bool, no_push: bool, no_commit: bool) -> None:
                 "[yellow]Warning:[/yellow] No __version__ attributes found to update"
             )
 
+        # Update CLI template pyproject.toml files
+        templates_dir = lib_dir / "crewai" / "src" / "crewai" / "cli" / "templates"
+        if templates_dir.exists():
+            if dry_run:
+                for tpl in templates_dir.rglob("pyproject.toml"):
+                    console.print(
+                        f"[dim][DRY RUN][/dim] Would update template: {tpl.relative_to(cwd)}"
+                    )
+            else:
+                tpl_updated = update_template_dependencies(templates_dir, version)
+                for tpl in tpl_updated:
+                    console.print(
+                        f"[green]✓[/green] Updated template: {tpl.relative_to(cwd)}"
+                    )
+                    updated_files.append(tpl)
+
         if not dry_run:
             console.print("\nSyncing workspace...")
             run_command(["uv", "sync"])
@@ -575,9 +833,9 @@ def tag(dry_run: bool, no_edit: bool) -> None:
 
             github_contributors = get_github_contributors(commit_range)
 
-            if commits.strip():
-                client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
+            openai_client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
 
+            if commits.strip():
                 contributors_section = ""
                 if github_contributors:
                     contributors_section = f"\n\n## Contributors\n\n{', '.join([f'@{u}' for u in github_contributors])}"
@@ -588,7 +846,7 @@ def tag(dry_run: bool, no_edit: bool) -> None:
                     contributors_section=contributors_section,
                 )
 
-                response = client.chat.completions.create(
+                response = openai_client.chat.completions.create(
                     model="gpt-4o-mini",
                     messages=[
                         {
@@ -643,6 +901,143 @@ def tag(dry_run: bool, no_edit: bool) -> None:
                 "\n[green]✓[/green] Using generated release notes without editing"
             )
 
+        is_prerelease = any(
+            indicator in version.lower()
+            for indicator in ["a", "b", "rc", "alpha", "beta", "dev"]
+        )
+
+        # Update docs: changelogs + version switcher
+        docs_json_path = cwd / "docs" / "docs.json"
+        changelog_langs = ["en", "pt-BR", "ko"]
+        if not dry_run:
+            docs_files_staged = []
+
+            for lang in changelog_langs:
+                cl_path = cwd / "docs" / lang / "changelog.mdx"
+                if lang == "en":
+                    notes_for_lang = release_notes
+                else:
+                    console.print(f"[dim]Translating release notes to {lang}...[/dim]")
+                    notes_for_lang = translate_release_notes(
+                        release_notes, lang, openai_client
+                    )
+                if update_changelog(cl_path, version, notes_for_lang, lang=lang):
+                    console.print(
+                        f"[green]✓[/green] Updated {cl_path.relative_to(cwd)}"
+                    )
+                    docs_files_staged.append(str(cl_path))
+                else:
+                    console.print(
+                        f"[yellow]Warning:[/yellow] Changelog not found at {cl_path.relative_to(cwd)}"
+                    )
+
+            if not is_prerelease:
+                if add_docs_version(docs_json_path, version):
+                    console.print(
+                        f"[green]✓[/green] Added v{version} to docs version switcher"
+                    )
+                    docs_files_staged.append(str(docs_json_path))
+                else:
+                    console.print(
+                        f"[yellow]Warning:[/yellow] docs.json not found at {docs_json_path.relative_to(cwd)}"
+                    )
+
+            if docs_files_staged:
+                docs_branch = f"docs/changelog-v{version}"
+                run_command(["git", "checkout", "-b", docs_branch])
+                for f in docs_files_staged:
+                    run_command(["git", "add", f])
+                run_command(
+                    [
+                        "git",
+                        "commit",
+                        "-m",
+                        f"docs: update changelog and version for v{version}",
+                    ]
+                )
+                console.print("[green]✓[/green] Committed docs updates")
+
+                run_command(["git", "push", "-u", "origin", docs_branch])
+                console.print(f"[green]✓[/green] Pushed branch {docs_branch}")
+
+                run_command(
+                    [
+                        "gh",
+                        "pr",
+                        "create",
+                        "--base",
+                        "main",
+                        "--title",
+                        f"docs: update changelog and version for v{version}",
+                        "--body",
+                        "",
+                    ]
+                )
+                console.print("[green]✓[/green] Created docs PR")
+
+                run_command(
+                    [
+                        "gh",
+                        "pr",
+                        "merge",
+                        docs_branch,
+                        "--squash",
+                        "--auto",
+                        "--delete-branch",
+                    ]
+                )
+                console.print("[green]✓[/green] Enabled auto-merge on docs PR")
+
+                import time
+
+                console.print("[cyan]Waiting for PR checks to pass and merge...[/cyan]")
+                while True:
+                    time.sleep(10)
+                    try:
+                        state = run_command(
+                            [
+                                "gh",
+                                "pr",
+                                "view",
+                                docs_branch,
+                                "--json",
+                                "state",
+                                "--jq",
+                                ".state",
+                            ]
+                        )
+                    except subprocess.CalledProcessError:
+                        state = ""
+
+                    if state == "MERGED":
+                        break
+
+                    console.print("[dim]Still waiting for PR to merge...[/dim]")
+
+                console.print("[green]✓[/green] Docs PR merged")
+
+                run_command(["git", "checkout", "main"])
+                run_command(["git", "pull"])
+                console.print("[green]✓[/green] main branch updated with docs changes")
+        else:
+            for lang in changelog_langs:
+                cl_path = cwd / "docs" / lang / "changelog.mdx"
+                translated = " (translated)" if lang != "en" else ""
+                console.print(
+                    f"[dim][DRY RUN][/dim] Would update {cl_path.relative_to(cwd)}{translated}"
+                )
+            if not is_prerelease:
+                console.print(
+                    f"[dim][DRY RUN][/dim] Would add v{version} to docs version switcher"
+                )
+            else:
+                console.print(
+                    "[dim][DRY RUN][/dim] Skipping docs version (pre-release)"
+                )
+            console.print(
+                f"[dim][DRY RUN][/dim] Would create branch docs/changelog-v{version}, PR, and merge"
+            )
+
         if not dry_run:
             with console.status(f"[cyan]Creating tag {tag_name}..."):
                 try:
@@ -660,11 +1055,6 @@ def tag(dry_run: bool, no_edit: bool) -> None:
                     sys.exit(1)
             console.print(f"[green]✓[/green] Pushed tag {tag_name}")
 
-            is_prerelease = any(
-                indicator in version.lower()
-                for indicator in ["a", "b", "rc", "alpha", "beta", "dev"]
-            )
-
             with console.status("[cyan]Creating GitHub Release..."):
                 try:
                     gh_cmd = [