fix: map output_pydantic/output_json to native structured output

* fix: map output_pydantic/output_json to native structured output

* test: add crew+tools+structured output integration test for Gemini

* fix: re-record stale cassette for test_crew_testing_function

* fix: re-record remaining stale cassettes for native structured output

* fix: enable native structured output for lite agent and fix mypy errors

.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 }}"}'

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

@@ -98,11 +98,6 @@ from crewai_tools.tools.mongodb_vector_search_tool.vector_search import (
     MongoDBVectorSearchTool,
 )
 from crewai_tools.tools.multion_tool.multion_tool import MultiOnTool
-from crewai_tools.tools.oceanbase_vector_search_tool.oceanbase_vector_search_tool import (
-    OceanBaseToolSchema,
-    OceanBaseVectorSearchConfig,
-    OceanBaseVectorSearchTool,
-)
 from crewai_tools.tools.mysql_search_tool.mysql_search_tool import MySQLSearchTool
 from crewai_tools.tools.nl2sql.nl2sql_tool import NL2SQLTool
 from crewai_tools.tools.ocr_tool.ocr_tool import OCRTool
@@ -248,9 +243,6 @@ __all__ = [
     "MongoDBVectorSearchTool",
     "MultiOnTool",
     "MySQLSearchTool",
-    "OceanBaseToolSchema",
-    "OceanBaseVectorSearchConfig",
-    "OceanBaseVectorSearchTool",
     "NL2SQLTool",
     "OCRTool",
     "OxylabsAmazonProductScraperTool",

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

@@ -87,11 +87,6 @@ from crewai_tools.tools.mongodb_vector_search_tool import (
     MongoDBVectorSearchConfig,
     MongoDBVectorSearchTool,
 )
-from crewai_tools.tools.oceanbase_vector_search_tool import (
-    OceanBaseToolSchema,
-    OceanBaseVectorSearchConfig,
-    OceanBaseVectorSearchTool,
-)
 from crewai_tools.tools.multion_tool.multion_tool import MultiOnTool
 from crewai_tools.tools.mysql_search_tool.mysql_search_tool import MySQLSearchTool
 from crewai_tools.tools.nl2sql.nl2sql_tool import NL2SQLTool
@@ -231,9 +226,6 @@ __all__ = [
     "MongoDBVectorSearchConfig",
     "MongoDBVectorSearchTool",
     "MultiOnTool",
-    "OceanBaseToolSchema",
-    "OceanBaseVectorSearchConfig",
-    "OceanBaseVectorSearchTool",
     "MySQLSearchTool",
     "NL2SQLTool",
     "OCRTool",

lib/crewai-tools/src/crewai_tools/tools/oceanbase_vector_search_tool/README.md

@@ -1,144 +0,0 @@
-# OceanBaseVectorSearchTool
-
-## Description
-
-This tool is designed for performing vector similarity searches within an OceanBase database. OceanBase is a distributed relational database developed by Ant Group that supports native vector indexing and search capabilities using HNSW (Hierarchical Navigable Small World) algorithm.
-
-Use this tool to find semantically similar documents to a given query by leveraging OceanBase's vector search functionality.
-
-For more information about OceanBase vector capabilities, see:
-https://en.oceanbase.com/docs/common-oceanbase-database-10000000001976351
-
-## Installation
-
-Install the crewai_tools package with OceanBase support by executing the following command in your terminal:
-
-```shell
-pip install crewai-tools[oceanbase]
-```
-
-or
-
-```shell
-uv add crewai-tools --extra oceanbase
-```
-
-## Example
-
-### Basic Usage
-
-```python
-from crewai_tools import OceanBaseVectorSearchTool
-
-tool = OceanBaseVectorSearchTool(
-    connection_uri="127.0.0.1:2881",
-    user="root@test",
-    password="",
-    db_name="test",
-    table_name="documents",
-)
-```
-
-### With Custom Configuration
-
-```python
-from crewai_tools import OceanBaseVectorSearchConfig, OceanBaseVectorSearchTool
-
-query_config = OceanBaseVectorSearchConfig(
-    limit=10,
-    distance_func="cosine",
-    distance_threshold=0.5,
-)
-
-tool = OceanBaseVectorSearchTool(
-    connection_uri="127.0.0.1:2881",
-    user="root@test",
-    password="your_password",
-    db_name="my_database",
-    table_name="my_documents",
-    vector_column_name="embedding",
-    text_column_name="content",
-    metadata_column_name="metadata",
-    query_config=query_config,
-    embedding_model="text-embedding-3-large",
-    dimensions=3072,
-)
-```
-
-### Adding the Tool to an Agent
-
-```python
-from crewai import Agent
-from crewai_tools import OceanBaseVectorSearchTool
-
-tool = OceanBaseVectorSearchTool(
-    connection_uri="127.0.0.1:2881",
-    user="root@test",
-    db_name="test",
-    table_name="documents",
-)
-
-rag_agent = Agent(
-    name="rag_agent",
-    role="You are a helpful assistant that can answer questions using the OceanBaseVectorSearchTool.",
-    goal="Answer user questions by searching relevant documents",
-    backstory="You have access to a knowledge base stored in OceanBase",
-    llm="gpt-4o-mini",
-    tools=[tool],
-)
-```
-
-### Preloading Documents
-
-```python
-from crewai_tools import OceanBaseVectorSearchTool
-import os
-
-tool = OceanBaseVectorSearchTool(
-    connection_uri="127.0.0.1:2881",
-    user="root@test",
-    db_name="test",
-    table_name="documents",
-)
-
-texts = []
-metadatas = []
-for filename in os.listdir("knowledge"):
-    with open(os.path.join("knowledge", filename), "r") as f:
-        texts.append(f.read())
-        metadatas.append({"source": filename})
-
-tool.add_texts(texts, metadatas=metadatas)
-```
-
-## Configuration Options
-
-### OceanBaseVectorSearchConfig
-
-| Parameter | Type | Default | Description |
-|-----------|------|---------|-------------|
-| `limit` | int | 4 | Number of documents to return |
-| `distance_func` | str | "l2" | Distance function: "l2", "cosine", or "inner_product" |
-| `distance_threshold` | float | None | Only return results with distance <= threshold |
-| `include_embeddings` | bool | False | Whether to include embedding vectors in results |
-
-### OceanBaseVectorSearchTool
-
-| Parameter | Type | Required | Description |
-|-----------|------|----------|-------------|
-| `connection_uri` | str | Yes | OceanBase connection URI (e.g., "127.0.0.1:2881") |
-| `user` | str | Yes | Username for connection (e.g., "root@test") |
-| `password` | str | No | Password for connection |
-| `db_name` | str | No | Database name (default: "test") |
-| `table_name` | str | Yes | Table containing vector data |
-| `vector_column_name` | str | No | Column with embeddings (default: "embedding") |
-| `text_column_name` | str | No | Column with text content (default: "text") |
-| `metadata_column_name` | str | No | Column with metadata (default: "metadata") |
-| `embedding_model` | str | No | OpenAI model for embeddings (default: "text-embedding-3-large") |
-| `dimensions` | int | No | Embedding dimensions (default: 1536) |
-| `query_config` | OceanBaseVectorSearchConfig | No | Search configuration |
-
-## Environment Variables
-
-- `OPENAI_API_KEY`: Required for generating embeddings
-- `AZURE_OPENAI_ENDPOINT`: Optional, for Azure OpenAI support

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

@@ -1,12 +0,0 @@
-from crewai_tools.tools.oceanbase_vector_search_tool.oceanbase_vector_search_tool import (
-    OceanBaseToolSchema,
-    OceanBaseVectorSearchConfig,
-    OceanBaseVectorSearchTool,
-)
-
-
-__all__ = [
-    "OceanBaseToolSchema",
-    "OceanBaseVectorSearchConfig",
-    "OceanBaseVectorSearchTool",
-]

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

@@ -1,267 +0,0 @@
-from __future__ import annotations
-
-import json
-from logging import getLogger
-import os
-from typing import Any
-
-from crewai.tools import BaseTool, EnvVar
-from pydantic import BaseModel, Field
-
-
-try:
-    import pyobvector  # noqa: F401
-
-    PYOBVECTOR_AVAILABLE = True
-except ImportError:
-    PYOBVECTOR_AVAILABLE = False
-
-logger = getLogger(__name__)
-
-
-class OceanBaseToolSchema(BaseModel):
-    """Input schema for OceanBase vector search tool."""
-
-    query: str = Field(
-        ...,
-        description="The query to search for relevant information in the OceanBase database.",
-    )
-
-
-class OceanBaseVectorSearchConfig(BaseModel):
-    """Configuration for OceanBase vector search queries."""
-
-    limit: int = Field(
-        default=4,
-        description="Number of documents to return.",
-    )
-    distance_threshold: float | None = Field(
-        default=None,
-        description="Only return results where distance is less than or equal to this threshold.",
-    )
-    distance_func: str = Field(
-        default="l2",
-        description="Distance function to use for similarity search. Options: 'l2', 'cosine', 'inner_product'.",
-    )
-    include_embeddings: bool = Field(
-        default=False,
-        description="Whether to include the embedding vector of each result.",
-    )
-
-
-class OceanBaseVectorSearchTool(BaseTool):
-    """Tool to perform vector search on OceanBase database."""
-
-    name: str = "OceanBaseVectorSearchTool"
-    description: str = (
-        "A tool to perform vector similarity search on an OceanBase database "
-        "for retrieving relevant information from stored documents."
-    )
-
-    args_schema: type[BaseModel] = OceanBaseToolSchema
-    query_config: OceanBaseVectorSearchConfig | None = Field(
-        default=None,
-        description="OceanBase vector search query configuration.",
-    )
-    embedding_model: str = Field(
-        default="text-embedding-3-large",
-        description="OpenAI embedding model to use for generating query embeddings.",
-    )
-    dimensions: int = Field(
-        default=1536,
-        description="Number of dimensions in the embedding vector.",
-    )
-    connection_uri: str = Field(
-        ...,
-        description="Connection URI for OceanBase (e.g., '127.0.0.1:2881').",
-    )
-    user: str = Field(
-        ...,
-        description="Username for OceanBase connection (e.g., 'root@test').",
-    )
-    password: str = Field(
-        default="",
-        description="Password for OceanBase connection.",
-    )
-    db_name: str = Field(
-        default="test",
-        description="Database name in OceanBase.",
-    )
-    table_name: str = Field(
-        ...,
-        description="Name of the table containing vector data.",
-    )
-    vector_column_name: str = Field(
-        default="embedding",
-        description="Name of the column containing vector embeddings.",
-    )
-    text_column_name: str = Field(
-        default="text",
-        description="Name of the column containing text content.",
-    )
-    metadata_column_name: str | None = Field(
-        default="metadata",
-        description="Name of the column containing metadata (optional).",
-    )
-    env_vars: list[EnvVar] = Field(
-        default_factory=lambda: [
-            EnvVar(
-                name="OPENAI_API_KEY",
-                description="API key for OpenAI embeddings",
-                required=True,
-            ),
-        ]
-    )
-    package_dependencies: list[str] = Field(default_factory=lambda: ["pyobvector"])
-
-    _client: Any = None
-    _openai_client: Any = None
-
-    def __init__(self, **kwargs: Any) -> None:
-        super().__init__(**kwargs)
-        if not PYOBVECTOR_AVAILABLE:
-            import click
-
-            if click.confirm(
-                "You are missing the 'pyobvector' package. Would you like to install it?"
-            ):
-                import subprocess
-
-                subprocess.run(["uv", "add", "pyobvector"], check=True)  # noqa: S607
-            else:
-                raise ImportError(
-                    "The 'pyobvector' package is required for OceanBaseVectorSearchTool."
-                )
-
-        if "AZURE_OPENAI_ENDPOINT" in os.environ:
-            from openai import AzureOpenAI
-
-            self._openai_client = AzureOpenAI()
-        elif "OPENAI_API_KEY" in os.environ:
-            from openai import Client
-
-            self._openai_client = Client()
-        else:
-            raise ValueError(
-                "OPENAI_API_KEY environment variable is required for OceanBaseVectorSearchTool."
-            )
-
-        from pyobvector import ObVecClient
-
-        self._client = ObVecClient(
-            uri=self.connection_uri,
-            user=self.user,
-            password=self.password,
-            db_name=self.db_name,
-        )
-
-    def _embed_text(self, text: str) -> list[float]:
-        """Generate embedding for the given text using OpenAI."""
-        response = self._openai_client.embeddings.create(
-            input=[text],
-            model=self.embedding_model,
-            dimensions=self.dimensions,
-        )
-        return response.data[0].embedding
-
-    def _get_distance_func(self) -> Any:
-        """Get the appropriate distance function from pyobvector."""
-        import pyobvector
-
-        config = self.query_config or OceanBaseVectorSearchConfig()
-        valid_distance_funcs = {
-            "l2": "l2_distance",
-            "cosine": "cosine_distance",
-            "inner_product": "inner_product",
-        }
-
-        func_name = valid_distance_funcs.get(config.distance_func, "l2_distance")
-        return getattr(pyobvector, func_name)
-
-    def _run(self, query: str) -> str:
-        """Execute vector search on OceanBase."""
-        try:
-            config = self.query_config or OceanBaseVectorSearchConfig()
-
-            query_vector = self._embed_text(query)
-
-            output_columns = [self.text_column_name]
-            if self.metadata_column_name:
-                output_columns.append(self.metadata_column_name)
-
-            results = self._client.ann_search(
-                table_name=self.table_name,
-                vec_data=query_vector,
-                vec_column_name=self.vector_column_name,
-                distance_func=self._get_distance_func(),
-                with_dist=True,
-                topk=config.limit,
-                output_column_names=output_columns,
-                distance_threshold=config.distance_threshold,
-            )
-
-            formatted_results = []
-            for row in results:
-                result_dict: dict[str, Any] = {}
-
-                if len(row) >= 1:
-                    result_dict["text"] = row[0]
-                if self.metadata_column_name and len(row) >= 2:
-                    result_dict["metadata"] = row[1]
-                if len(row) > len(output_columns):
-                    result_dict["distance"] = row[-1]
-
-                formatted_results.append(result_dict)
-
-            return json.dumps(formatted_results, indent=2, default=str)
-
-        except Exception as e:
-            logger.error(f"Error during OceanBase vector search: {e}")
-            return json.dumps({"error": str(e)})
-
-    def add_texts(
-        self,
-        texts: list[str],
-        metadatas: list[dict[str, Any]] | None = None,
-        ids: list[str] | None = None,
-    ) -> list[str]:
-        """Add texts with embeddings to the OceanBase table.
-
-        Args:
-            texts: List of text strings to add.
-            metadatas: Optional list of metadata dictionaries for each text.
-            ids: Optional list of unique IDs for each text.
-
-        Returns:
-            List of IDs for the added texts.
-        """
-        import uuid
-
-        if ids is None:
-            ids = [str(uuid.uuid4()) for _ in texts]
-
-        if metadatas is None:
-            metadatas = [{} for _ in texts]
-
-        data = []
-        for text, metadata, doc_id in zip(texts, metadatas, ids, strict=False):
-            embedding = self._embed_text(text)
-            row = {
-                "id": doc_id,
-                self.text_column_name: text,
-                self.vector_column_name: embedding,
-            }
-            if self.metadata_column_name:
-                row[self.metadata_column_name] = metadata
-            data.append(row)
-
-        self._client.insert(self.table_name, data=data)
-        return ids
-
-    def __del__(self) -> None:
-        """Cleanup clients on deletion."""
-        try:
-            if hasattr(self, "_openai_client") and self._openai_client:
-                self._openai_client.close()
-        except Exception as e:
-            logger.error(f"Error closing OpenAI client: {e}")

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

@@ -1,208 +0,0 @@
-import json
-import sys
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-from crewai_tools import OceanBaseVectorSearchConfig
-
-
-mock_pyobvector = MagicMock()
-mock_pyobvector.ObVecClient = MagicMock()
-mock_pyobvector.l2_distance = MagicMock(return_value="l2_func")
-mock_pyobvector.cosine_distance = MagicMock(return_value="cosine_func")
-mock_pyobvector.inner_product = MagicMock(return_value="ip_func")
-sys.modules["pyobvector"] = mock_pyobvector
-
-
-@pytest.fixture
-def mock_openai_client():
-    """Create a mock OpenAI client."""
-    mock_client = MagicMock()
-    mock_embedding = MagicMock()
-    mock_embedding.embedding = [0.1] * 1536
-    mock_response = MagicMock()
-    mock_response.data = [mock_embedding]
-    mock_client.embeddings.create.return_value = mock_response
-    return mock_client
-
-
-@pytest.fixture
-def mock_obvec_client():
-    """Create a mock OceanBase vector client."""
-    mock_client = MagicMock()
-    return mock_client
-
-
-@pytest.fixture
-def oceanbase_vector_search_tool(mock_openai_client, mock_obvec_client):
-    """Create an OceanBaseVectorSearchTool with mocked clients."""
-    from crewai_tools import OceanBaseVectorSearchTool
-
-    with patch.dict("os.environ", {"OPENAI_API_KEY": "test-key"}):
-        with patch(
-            "crewai_tools.tools.oceanbase_vector_search_tool.oceanbase_vector_search_tool.PYOBVECTOR_AVAILABLE",
-            True,
-        ):
-            mock_pyobvector.ObVecClient.return_value = mock_obvec_client
-            with patch("openai.Client") as mock_openai_class:
-                mock_openai_class.return_value = mock_openai_client
-                tool = OceanBaseVectorSearchTool(
-                    connection_uri="127.0.0.1:2881",
-                    user="root@test",
-                    password="",
-                    db_name="test",
-                    table_name="test_table",
-                )
-                tool._openai_client = mock_openai_client
-                tool._client = mock_obvec_client
-                yield tool
-
-
-def test_successful_query_execution(oceanbase_vector_search_tool, mock_obvec_client):
-    """Test successful vector search query execution."""
-    mock_obvec_client.ann_search.return_value = [
-        ("test document content", {"source": "test.txt"}, 0.1),
-        ("another document", {"source": "test2.txt"}, 0.2),
-    ]
-
-    results = json.loads(oceanbase_vector_search_tool._run(query="test query"))
-
-    assert len(results) == 2
-    assert results[0]["text"] == "test document content"
-    assert results[0]["metadata"] == {"source": "test.txt"}
-    assert results[0]["distance"] == 0.1
-
-
-def test_query_with_custom_config(mock_openai_client, mock_obvec_client):
-    """Test vector search with custom configuration."""
-    from crewai_tools import OceanBaseVectorSearchTool
-
-    query_config = OceanBaseVectorSearchConfig(
-        limit=10,
-        distance_func="cosine",
-        distance_threshold=0.5,
-    )
-
-    with patch.dict("os.environ", {"OPENAI_API_KEY": "test-key"}):
-        with patch(
-            "crewai_tools.tools.oceanbase_vector_search_tool.oceanbase_vector_search_tool.PYOBVECTOR_AVAILABLE",
-            True,
-        ):
-            mock_pyobvector.ObVecClient.return_value = mock_obvec_client
-            with patch("openai.Client") as mock_openai_class:
-                mock_openai_class.return_value = mock_openai_client
-                tool = OceanBaseVectorSearchTool(
-                    connection_uri="127.0.0.1:2881",
-                    user="root@test",
-                    db_name="test",
-                    table_name="test_table",
-                    query_config=query_config,
-                )
-                tool._openai_client = mock_openai_client
-                tool._client = mock_obvec_client
-
-    mock_obvec_client.ann_search.return_value = [("doc", {}, 0.3)]
-
-    tool._run(query="test")
-
-    call_kwargs = mock_obvec_client.ann_search.call_args.kwargs
-    assert call_kwargs["topk"] == 10
-    assert call_kwargs["distance_threshold"] == 0.5
-
-
-def test_add_texts(oceanbase_vector_search_tool, mock_obvec_client):
-    """Test adding texts to the OceanBase table."""
-    texts = ["document 1", "document 2"]
-    metadatas = [{"source": "file1.txt"}, {"source": "file2.txt"}]
-
-    result_ids = oceanbase_vector_search_tool.add_texts(texts, metadatas=metadatas)
-
-    assert len(result_ids) == 2
-    mock_obvec_client.insert.assert_called_once()
-    call_args = mock_obvec_client.insert.call_args
-    assert call_args[0][0] == "test_table"
-    assert len(call_args[1]["data"]) == 2
-
-
-def test_add_texts_without_metadata(oceanbase_vector_search_tool, mock_obvec_client):
-    """Test adding texts without metadata."""
-    texts = ["document 1", "document 2"]
-
-    result_ids = oceanbase_vector_search_tool.add_texts(texts)
-
-    assert len(result_ids) == 2
-    mock_obvec_client.insert.assert_called_once()
-
-
-def test_error_handling(oceanbase_vector_search_tool, mock_obvec_client):
-    """Test error handling during search."""
-    mock_obvec_client.ann_search.side_effect = Exception("Database connection error")
-
-    result = json.loads(oceanbase_vector_search_tool._run(query="test"))
-
-    assert "error" in result
-    assert "Database connection error" in result["error"]
-
-
-def test_config_defaults():
-    """Test OceanBaseVectorSearchConfig default values."""
-    config = OceanBaseVectorSearchConfig()
-
-    assert config.limit == 4
-    assert config.distance_func == "l2"
-    assert config.distance_threshold is None
-    assert config.include_embeddings is False
-
-
-def test_config_custom_values():
-    """Test OceanBaseVectorSearchConfig with custom values."""
-    config = OceanBaseVectorSearchConfig(
-        limit=20,
-        distance_func="cosine",
-        distance_threshold=0.8,
-        include_embeddings=True,
-    )
-
-    assert config.limit == 20
-    assert config.distance_func == "cosine"
-    assert config.distance_threshold == 0.8
-    assert config.include_embeddings is True
-
-
-def test_tool_schema():
-    """Test OceanBaseToolSchema validation."""
-    from crewai_tools import OceanBaseToolSchema
-
-    schema = OceanBaseToolSchema(query="test query")
-    assert schema.query == "test query"
-
-
-def test_tool_schema_requires_query():
-    """Test that OceanBaseToolSchema requires a query."""
-    from crewai_tools import OceanBaseToolSchema
-    from pydantic import ValidationError
-
-    with pytest.raises(ValidationError):
-        OceanBaseToolSchema()
-
-
-def test_distance_function_selection(oceanbase_vector_search_tool):
-    """Test that the correct distance function is selected."""
-    oceanbase_vector_search_tool.query_config = OceanBaseVectorSearchConfig(
-        distance_func="l2"
-    )
-    func = oceanbase_vector_search_tool._get_distance_func()
-    assert func == mock_pyobvector.l2_distance
-
-    oceanbase_vector_search_tool.query_config = OceanBaseVectorSearchConfig(
-        distance_func="cosine"
-    )
-    func = oceanbase_vector_search_tool._get_distance_func()
-    assert func == mock_pyobvector.cosine_distance
-
-    oceanbase_vector_search_tool.query_config = OceanBaseVectorSearchConfig(
-        distance_func="inner_product"
-    )
-    func = oceanbase_vector_search_tool._get_distance_func()
-    assert func == mock_pyobvector.inner_product

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

@@ -864,7 +864,11 @@ 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 +897,11 @@ 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
@@ -1712,7 +1720,8 @@ 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
             )
 
@@ -1937,14 +1946,15 @@ 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/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 []:

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/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(
@@ -593,11 +604,7 @@ class LiteAgent(FlowTrackable, BaseModel):
             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/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/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

@@ -18,6 +18,7 @@ from pydantic import (
     BaseModel as PydanticBaseModel,
     ConfigDict,
     Field,
+    ValidationError,
     create_model,
     field_validator,
 )
@@ -150,14 +151,37 @@ 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 kwargs and 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:
+        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 +203,7 @@ class BaseTool(BaseModel, ABC):
         Returns:
             The result of the tool execution.
         """
+        kwargs = self._validate_kwargs(kwargs)
         result = await self._arun(*args, **kwargs)
         self.current_usage_count += 1
         return result
@@ -331,6 +356,8 @@ class Tool(BaseTool, Generic[P, R]):
         Returns:
             The result of the tool execution.
         """
+        kwargs = self._validate_kwargs(kwargs)
+
         result = self.func(*args, **kwargs)
 
         if asyncio.iscoroutine(result):
@@ -361,6 +388,7 @@ class Tool(BaseTool, Generic[P, R]):
         Returns:
             The result of the tool execution.
         """
+        kwargs = self._validate_kwargs(kwargs)
         result = await self._arun(*args, **kwargs)
         self.current_usage_count += 1
         return result

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

@@ -1146,6 +1146,36 @@ 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/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/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/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 +232,204 @@ 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_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_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

@@ -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,
 )
 
@@ -922,3 +923,56 @@ 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/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., "1.10.0").
+
+    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 +901,77 @@ 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:
+                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"])
+                console.print("[green]✓[/green] Pushed docs updates")
+        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)"
+                )
+
         if not dry_run:
             with console.status(f"[cyan]Creating tag {tag_name}..."):
                 try:
@@ -660,11 +989,6 @@ 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 = [

lib/devtools/src/crewai_devtools/prompts.py

@@ -43,3 +43,18 @@ Instructions:
 
 Keep it professional and clear."""
 )
+
+
+TRANSLATE_RELEASE_NOTES_PROMPT = Template(
+    """Translate the following release notes into $language.
+
+$release_notes
+
+Instructions:
+- Translate all section headers and descriptions naturally
+- Keep markdown formatting (##, ###, -, etc.) exactly as-is
+- Keep all proper nouns, code identifiers, class names, and technical terms unchanged
+  (e.g. "CrewAI", "LiteAgent", "ChromaDB", "MCP", "@username")
+- Keep the ## Contributors section and GitHub usernames unchanged
+- Do not add or remove any content, only translate"""
+)

uv.lock

@@ -1471,48 +1471,48 @@ provides-extras = ["apify", "beautifulsoup4", "bedrock", "browserbase", "composi
 
 [[package]]
 name = "cryptography"
-version = "46.0.4"
+version = "46.0.5"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "cffi", marker = "platform_python_implementation != 'PyPy'" },
     { name = "typing-extensions", marker = "python_full_version < '3.11'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/78/19/f748958276519adf6a0c1e79e7b8860b4830dda55ccdf29f2719b5fc499c/cryptography-46.0.4.tar.gz", hash = "sha256:bfd019f60f8abc2ed1b9be4ddc21cfef059c841d86d710bb69909a688cbb8f59", size = 749301, upload-time = "2026-01-28T00:24:37.379Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/60/04/ee2a9e8542e4fa2773b81771ff8349ff19cdd56b7258a0cc442639052edb/cryptography-46.0.5.tar.gz", hash = "sha256:abace499247268e3757271b2f1e244b36b06f8515cf27c4d49468fc9eb16e93d", size = 750064, upload-time = "2026-02-10T19:18:38.255Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/8d/99/157aae7949a5f30d51fcb1a9851e8ebd5c74bf99b5285d8bb4b8b9ee641e/cryptography-46.0.4-cp311-abi3-macosx_10_9_universal2.whl", hash = "sha256:281526e865ed4166009e235afadf3a4c4cba6056f99336a99efba65336fd5485", size = 7173686, upload-time = "2026-01-28T00:23:07.515Z" },
-    { url = "https://files.pythonhosted.org/packages/87/91/874b8910903159043b5c6a123b7e79c4559ddd1896e38967567942635778/cryptography-46.0.4-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:5f14fba5bf6f4390d7ff8f086c566454bff0411f6d8aa7af79c88b6f9267aecc", size = 4275871, upload-time = "2026-01-28T00:23:09.439Z" },
-    { url = "https://files.pythonhosted.org/packages/c0/35/690e809be77896111f5b195ede56e4b4ed0435b428c2f2b6d35046fbb5e8/cryptography-46.0.4-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:47bcd19517e6389132f76e2d5303ded6cf3f78903da2158a671be8de024f4cd0", size = 4423124, upload-time = "2026-01-28T00:23:11.529Z" },
-    { url = "https://files.pythonhosted.org/packages/1a/5b/a26407d4f79d61ca4bebaa9213feafdd8806dc69d3d290ce24996d3cfe43/cryptography-46.0.4-cp311-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:01df4f50f314fbe7009f54046e908d1754f19d0c6d3070df1e6268c5a4af09fa", size = 4277090, upload-time = "2026-01-28T00:23:13.123Z" },
-    { url = "https://files.pythonhosted.org/packages/0c/d8/4bb7aec442a9049827aa34cee1aa83803e528fa55da9a9d45d01d1bb933e/cryptography-46.0.4-cp311-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:5aa3e463596b0087b3da0dbe2b2487e9fc261d25da85754e30e3b40637d61f81", size = 4947652, upload-time = "2026-01-28T00:23:14.554Z" },
-    { url = "https://files.pythonhosted.org/packages/2b/08/f83e2e0814248b844265802d081f2fac2f1cbe6cd258e72ba14ff006823a/cryptography-46.0.4-cp311-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:0a9ad24359fee86f131836a9ac3bffc9329e956624a2d379b613f8f8abaf5255", size = 4455157, upload-time = "2026-01-28T00:23:16.443Z" },
-    { url = "https://files.pythonhosted.org/packages/0a/05/19d849cf4096448779d2dcc9bb27d097457dac36f7273ffa875a93b5884c/cryptography-46.0.4-cp311-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:dc1272e25ef673efe72f2096e92ae39dea1a1a450dd44918b15351f72c5a168e", size = 3981078, upload-time = "2026-01-28T00:23:17.838Z" },
-    { url = "https://files.pythonhosted.org/packages/e6/89/f7bac81d66ba7cde867a743ea5b37537b32b5c633c473002b26a226f703f/cryptography-46.0.4-cp311-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:de0f5f4ec8711ebc555f54735d4c673fc34b65c44283895f1a08c2b49d2fd99c", size = 4276213, upload-time = "2026-01-28T00:23:19.257Z" },
-    { url = "https://files.pythonhosted.org/packages/da/9f/7133e41f24edd827020ad21b068736e792bc68eecf66d93c924ad4719fb3/cryptography-46.0.4-cp311-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:eeeb2e33d8dbcccc34d64651f00a98cb41b2dc69cef866771a5717e6734dfa32", size = 4912190, upload-time = "2026-01-28T00:23:21.244Z" },
-    { url = "https://files.pythonhosted.org/packages/a6/f7/6d43cbaddf6f65b24816e4af187d211f0bc536a29961f69faedc48501d8e/cryptography-46.0.4-cp311-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:3d425eacbc9aceafd2cb429e42f4e5d5633c6f873f5e567077043ef1b9bbf616", size = 4454641, upload-time = "2026-01-28T00:23:22.866Z" },
-    { url = "https://files.pythonhosted.org/packages/9e/4f/ebd0473ad656a0ac912a16bd07db0f5d85184924e14fc88feecae2492834/cryptography-46.0.4-cp311-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:91627ebf691d1ea3976a031b61fb7bac1ccd745afa03602275dda443e11c8de0", size = 4405159, upload-time = "2026-01-28T00:23:25.278Z" },
-    { url = "https://files.pythonhosted.org/packages/d1/f7/7923886f32dc47e27adeff8246e976d77258fd2aa3efdd1754e4e323bf49/cryptography-46.0.4-cp311-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:2d08bc22efd73e8854b0b7caff402d735b354862f1145d7be3b9c0f740fef6a0", size = 4666059, upload-time = "2026-01-28T00:23:26.766Z" },
-    { url = "https://files.pythonhosted.org/packages/eb/a7/0fca0fd3591dffc297278a61813d7f661a14243dd60f499a7a5b48acb52a/cryptography-46.0.4-cp311-abi3-win32.whl", hash = "sha256:82a62483daf20b8134f6e92898da70d04d0ef9a75829d732ea1018678185f4f5", size = 3026378, upload-time = "2026-01-28T00:23:28.317Z" },
-    { url = "https://files.pythonhosted.org/packages/2d/12/652c84b6f9873f0909374864a57b003686c642ea48c84d6c7e2c515e6da5/cryptography-46.0.4-cp311-abi3-win_amd64.whl", hash = "sha256:6225d3ebe26a55dbc8ead5ad1265c0403552a63336499564675b29eb3184c09b", size = 3478614, upload-time = "2026-01-28T00:23:30.275Z" },
-    { url = "https://files.pythonhosted.org/packages/56/f7/f648fdbb61d0d45902d3f374217451385edc7e7768d1b03ff1d0e5ffc17b/cryptography-46.0.4-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:a9556ba711f7c23f77b151d5798f3ac44a13455cc68db7697a1096e6d0563cab", size = 7169583, upload-time = "2026-01-28T00:23:56.558Z" },
-    { url = "https://files.pythonhosted.org/packages/d8/cc/8f3224cbb2a928de7298d6ed4790f5ebc48114e02bdc9559196bfb12435d/cryptography-46.0.4-cp38-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:8bf75b0259e87fa70bddc0b8b4078b76e7fd512fd9afae6c1193bcf440a4dbef", size = 4275419, upload-time = "2026-01-28T00:23:58.364Z" },
-    { url = "https://files.pythonhosted.org/packages/17/43/4a18faa7a872d00e4264855134ba82d23546c850a70ff209e04ee200e76f/cryptography-46.0.4-cp38-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:3c268a3490df22270955966ba236d6bc4a8f9b6e4ffddb78aac535f1a5ea471d", size = 4419058, upload-time = "2026-01-28T00:23:59.867Z" },
-    { url = "https://files.pythonhosted.org/packages/ee/64/6651969409821d791ba12346a124f55e1b76f66a819254ae840a965d4b9c/cryptography-46.0.4-cp38-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:812815182f6a0c1d49a37893a303b44eaac827d7f0d582cecfc81b6427f22973", size = 4278151, upload-time = "2026-01-28T00:24:01.731Z" },
-    { url = "https://files.pythonhosted.org/packages/20/0b/a7fce65ee08c3c02f7a8310cc090a732344066b990ac63a9dfd0a655d321/cryptography-46.0.4-cp38-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:a90e43e3ef65e6dcf969dfe3bb40cbf5aef0d523dff95bfa24256be172a845f4", size = 4939441, upload-time = "2026-01-28T00:24:03.175Z" },
-    { url = "https://files.pythonhosted.org/packages/db/a7/20c5701e2cd3e1dfd7a19d2290c522a5f435dd30957d431dcb531d0f1413/cryptography-46.0.4-cp38-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:a05177ff6296644ef2876fce50518dffb5bcdf903c85250974fc8bc85d54c0af", size = 4451617, upload-time = "2026-01-28T00:24:05.403Z" },
-    { url = "https://files.pythonhosted.org/packages/00/dc/3e16030ea9aa47b63af6524c354933b4fb0e352257c792c4deeb0edae367/cryptography-46.0.4-cp38-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:daa392191f626d50f1b136c9b4cf08af69ca8279d110ea24f5c2700054d2e263", size = 3977774, upload-time = "2026-01-28T00:24:06.851Z" },
-    { url = "https://files.pythonhosted.org/packages/42/c8/ad93f14118252717b465880368721c963975ac4b941b7ef88f3c56bf2897/cryptography-46.0.4-cp38-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:e07ea39c5b048e085f15923511d8121e4a9dc45cee4e3b970ca4f0d338f23095", size = 4277008, upload-time = "2026-01-28T00:24:08.926Z" },
-    { url = "https://files.pythonhosted.org/packages/00/cf/89c99698151c00a4631fbfcfcf459d308213ac29e321b0ff44ceeeac82f1/cryptography-46.0.4-cp38-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:d5a45ddc256f492ce42a4e35879c5e5528c09cd9ad12420828c972951d8e016b", size = 4903339, upload-time = "2026-01-28T00:24:12.009Z" },
-    { url = "https://files.pythonhosted.org/packages/03/c3/c90a2cb358de4ac9309b26acf49b2a100957e1ff5cc1e98e6c4996576710/cryptography-46.0.4-cp38-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:6bb5157bf6a350e5b28aee23beb2d84ae6f5be390b2f8ee7ea179cda077e1019", size = 4451216, upload-time = "2026-01-28T00:24:13.975Z" },
-    { url = "https://files.pythonhosted.org/packages/96/2c/8d7f4171388a10208671e181ca43cdc0e596d8259ebacbbcfbd16de593da/cryptography-46.0.4-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:dd5aba870a2c40f87a3af043e0dee7d9eb02d4aff88a797b48f2b43eff8c3ab4", size = 4404299, upload-time = "2026-01-28T00:24:16.169Z" },
-    { url = "https://files.pythonhosted.org/packages/e9/23/cbb2036e450980f65c6e0a173b73a56ff3bccd8998965dea5cc9ddd424a5/cryptography-46.0.4-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:93d8291da8d71024379ab2cb0b5c57915300155ad42e07f76bea6ad838d7e59b", size = 4664837, upload-time = "2026-01-28T00:24:17.629Z" },
-    { url = "https://files.pythonhosted.org/packages/0a/21/f7433d18fe6d5845329cbdc597e30caf983229c7a245bcf54afecc555938/cryptography-46.0.4-cp38-abi3-win32.whl", hash = "sha256:0563655cb3c6d05fb2afe693340bc050c30f9f34e15763361cf08e94749401fc", size = 3009779, upload-time = "2026-01-28T00:24:20.198Z" },
-    { url = "https://files.pythonhosted.org/packages/3a/6a/bd2e7caa2facffedf172a45c1a02e551e6d7d4828658c9a245516a598d94/cryptography-46.0.4-cp38-abi3-win_amd64.whl", hash = "sha256:fa0900b9ef9c49728887d1576fd8d9e7e3ea872fa9b25ef9b64888adc434e976", size = 3466633, upload-time = "2026-01-28T00:24:21.851Z" },
-    { url = "https://files.pythonhosted.org/packages/59/e0/f9c6c53e1f2a1c2507f00f2faba00f01d2f334b35b0fbfe5286715da2184/cryptography-46.0.4-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:766330cce7416c92b5e90c3bb71b1b79521760cdcfc3a6a1a182d4c9fab23d2b", size = 3476316, upload-time = "2026-01-28T00:24:24.144Z" },
-    { url = "https://files.pythonhosted.org/packages/27/7a/f8d2d13227a9a1a9fe9c7442b057efecffa41f1e3c51d8622f26b9edbe8f/cryptography-46.0.4-pp311-pypy311_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:c236a44acfb610e70f6b3e1c3ca20ff24459659231ef2f8c48e879e2d32b73da", size = 4216693, upload-time = "2026-01-28T00:24:25.758Z" },
-    { url = "https://files.pythonhosted.org/packages/c5/de/3787054e8f7972658370198753835d9d680f6cd4a39df9f877b57f0dd69c/cryptography-46.0.4-pp311-pypy311_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:8a15fb869670efa8f83cbffbc8753c1abf236883225aed74cd179b720ac9ec80", size = 4382765, upload-time = "2026-01-28T00:24:27.577Z" },
-    { url = "https://files.pythonhosted.org/packages/8a/5f/60e0afb019973ba6a0b322e86b3d61edf487a4f5597618a430a2a15f2d22/cryptography-46.0.4-pp311-pypy311_pp73-manylinux_2_34_aarch64.whl", hash = "sha256:fdc3daab53b212472f1524d070735b2f0c214239df131903bae1d598016fa822", size = 4216066, upload-time = "2026-01-28T00:24:29.056Z" },
-    { url = "https://files.pythonhosted.org/packages/81/8e/bf4a0de294f147fee66f879d9bae6f8e8d61515558e3d12785dd90eca0be/cryptography-46.0.4-pp311-pypy311_pp73-manylinux_2_34_x86_64.whl", hash = "sha256:44cc0675b27cadb71bdbb96099cca1fa051cd11d2ade09e5cd3a2edb929ed947", size = 4382025, upload-time = "2026-01-28T00:24:30.681Z" },
-    { url = "https://files.pythonhosted.org/packages/79/f4/9ceb90cfd6a3847069b0b0b353fd3075dc69b49defc70182d8af0c4ca390/cryptography-46.0.4-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:be8c01a7d5a55f9a47d1888162b76c8f49d62b234d88f0ff91a9fbebe32ffbc3", size = 3406043, upload-time = "2026-01-28T00:24:32.236Z" },
+    { url = "https://files.pythonhosted.org/packages/f7/81/b0bb27f2ba931a65409c6b8a8b358a7f03c0e46eceacddff55f7c84b1f3b/cryptography-46.0.5-cp311-abi3-macosx_10_9_universal2.whl", hash = "sha256:351695ada9ea9618b3500b490ad54c739860883df6c1f555e088eaf25b1bbaad", size = 7176289, upload-time = "2026-02-10T19:17:08.274Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/9e/6b4397a3e3d15123de3b1806ef342522393d50736c13b20ec4c9ea6693a6/cryptography-46.0.5-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:c18ff11e86df2e28854939acde2d003f7984f721eba450b56a200ad90eeb0e6b", size = 4275637, upload-time = "2026-02-10T19:17:10.53Z" },
+    { url = "https://files.pythonhosted.org/packages/63/e7/471ab61099a3920b0c77852ea3f0ea611c9702f651600397ac567848b897/cryptography-46.0.5-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:4d7e3d356b8cd4ea5aff04f129d5f66ebdc7b6f8eae802b93739ed520c47c79b", size = 4424742, upload-time = "2026-02-10T19:17:12.388Z" },
+    { url = "https://files.pythonhosted.org/packages/37/53/a18500f270342d66bf7e4d9f091114e31e5ee9e7375a5aba2e85a91e0044/cryptography-46.0.5-cp311-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:50bfb6925eff619c9c023b967d5b77a54e04256c4281b0e21336a130cd7fc263", size = 4277528, upload-time = "2026-02-10T19:17:13.853Z" },
+    { url = "https://files.pythonhosted.org/packages/22/29/c2e812ebc38c57b40e7c583895e73c8c5adb4d1e4a0cc4c5a4fdab2b1acc/cryptography-46.0.5-cp311-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:803812e111e75d1aa73690d2facc295eaefd4439be1023fefc4995eaea2af90d", size = 4947993, upload-time = "2026-02-10T19:17:15.618Z" },
+    { url = "https://files.pythonhosted.org/packages/6b/e7/237155ae19a9023de7e30ec64e5d99a9431a567407ac21170a046d22a5a3/cryptography-46.0.5-cp311-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:3ee190460e2fbe447175cda91b88b84ae8322a104fc27766ad09428754a618ed", size = 4456855, upload-time = "2026-02-10T19:17:17.221Z" },
+    { url = "https://files.pythonhosted.org/packages/2d/87/fc628a7ad85b81206738abbd213b07702bcbdada1dd43f72236ef3cffbb5/cryptography-46.0.5-cp311-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:f145bba11b878005c496e93e257c1e88f154d278d2638e6450d17e0f31e558d2", size = 3984635, upload-time = "2026-02-10T19:17:18.792Z" },
+    { url = "https://files.pythonhosted.org/packages/84/29/65b55622bde135aedf4565dc509d99b560ee4095e56989e815f8fd2aa910/cryptography-46.0.5-cp311-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:e9251e3be159d1020c4030bd2e5f84d6a43fe54b6c19c12f51cde9542a2817b2", size = 4277038, upload-time = "2026-02-10T19:17:20.256Z" },
+    { url = "https://files.pythonhosted.org/packages/bc/36/45e76c68d7311432741faf1fbf7fac8a196a0a735ca21f504c75d37e2558/cryptography-46.0.5-cp311-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:47fb8a66058b80e509c47118ef8a75d14c455e81ac369050f20ba0d23e77fee0", size = 4912181, upload-time = "2026-02-10T19:17:21.825Z" },
+    { url = "https://files.pythonhosted.org/packages/6d/1a/c1ba8fead184d6e3d5afcf03d569acac5ad063f3ac9fb7258af158f7e378/cryptography-46.0.5-cp311-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:4c3341037c136030cb46e4b1e17b7418ea4cbd9dd207e4a6f3b2b24e0d4ac731", size = 4456482, upload-time = "2026-02-10T19:17:25.133Z" },
+    { url = "https://files.pythonhosted.org/packages/f9/e5/3fb22e37f66827ced3b902cf895e6a6bc1d095b5b26be26bd13c441fdf19/cryptography-46.0.5-cp311-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:890bcb4abd5a2d3f852196437129eb3667d62630333aacc13dfd470fad3aaa82", size = 4405497, upload-time = "2026-02-10T19:17:26.66Z" },
+    { url = "https://files.pythonhosted.org/packages/1a/df/9d58bb32b1121a8a2f27383fabae4d63080c7ca60b9b5c88be742be04ee7/cryptography-46.0.5-cp311-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:80a8d7bfdf38f87ca30a5391c0c9ce4ed2926918e017c29ddf643d0ed2778ea1", size = 4667819, upload-time = "2026-02-10T19:17:28.569Z" },
+    { url = "https://files.pythonhosted.org/packages/ea/ed/325d2a490c5e94038cdb0117da9397ece1f11201f425c4e9c57fe5b9f08b/cryptography-46.0.5-cp311-abi3-win32.whl", hash = "sha256:60ee7e19e95104d4c03871d7d7dfb3d22ef8a9b9c6778c94e1c8fcc8365afd48", size = 3028230, upload-time = "2026-02-10T19:17:30.518Z" },
+    { url = "https://files.pythonhosted.org/packages/e9/5a/ac0f49e48063ab4255d9e3b79f5def51697fce1a95ea1370f03dc9db76f6/cryptography-46.0.5-cp311-abi3-win_amd64.whl", hash = "sha256:38946c54b16c885c72c4f59846be9743d699eee2b69b6988e0a00a01f46a61a4", size = 3480909, upload-time = "2026-02-10T19:17:32.083Z" },
+    { url = "https://files.pythonhosted.org/packages/e2/fa/a66aa722105ad6a458bebd64086ca2b72cdd361fed31763d20390f6f1389/cryptography-46.0.5-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:4108d4c09fbbf2789d0c926eb4152ae1760d5a2d97612b92d508d96c861e4d31", size = 7170514, upload-time = "2026-02-10T19:17:56.267Z" },
+    { url = "https://files.pythonhosted.org/packages/0f/04/c85bdeab78c8bc77b701bf0d9bdcf514c044e18a46dcff330df5448631b0/cryptography-46.0.5-cp38-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:7d1f30a86d2757199cb2d56e48cce14deddf1f9c95f1ef1b64ee91ea43fe2e18", size = 4275349, upload-time = "2026-02-10T19:17:58.419Z" },
+    { url = "https://files.pythonhosted.org/packages/5c/32/9b87132a2f91ee7f5223b091dc963055503e9b442c98fc0b8a5ca765fab0/cryptography-46.0.5-cp38-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:039917b0dc418bb9f6edce8a906572d69e74bd330b0b3fea4f79dab7f8ddd235", size = 4420667, upload-time = "2026-02-10T19:18:00.619Z" },
+    { url = "https://files.pythonhosted.org/packages/a1/a6/a7cb7010bec4b7c5692ca6f024150371b295ee1c108bdc1c400e4c44562b/cryptography-46.0.5-cp38-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:ba2a27ff02f48193fc4daeadf8ad2590516fa3d0adeeb34336b96f7fa64c1e3a", size = 4276980, upload-time = "2026-02-10T19:18:02.379Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/7c/c4f45e0eeff9b91e3f12dbd0e165fcf2a38847288fcfd889deea99fb7b6d/cryptography-46.0.5-cp38-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:61aa400dce22cb001a98014f647dc21cda08f7915ceb95df0c9eaf84b4b6af76", size = 4939143, upload-time = "2026-02-10T19:18:03.964Z" },
+    { url = "https://files.pythonhosted.org/packages/37/19/e1b8f964a834eddb44fa1b9a9976f4e414cbb7aa62809b6760c8803d22d1/cryptography-46.0.5-cp38-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:3ce58ba46e1bc2aac4f7d9290223cead56743fa6ab94a5d53292ffaac6a91614", size = 4453674, upload-time = "2026-02-10T19:18:05.588Z" },
+    { url = "https://files.pythonhosted.org/packages/db/ed/db15d3956f65264ca204625597c410d420e26530c4e2943e05a0d2f24d51/cryptography-46.0.5-cp38-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:420d0e909050490d04359e7fdb5ed7e667ca5c3c402b809ae2563d7e66a92229", size = 3978801, upload-time = "2026-02-10T19:18:07.167Z" },
+    { url = "https://files.pythonhosted.org/packages/41/e2/df40a31d82df0a70a0daf69791f91dbb70e47644c58581d654879b382d11/cryptography-46.0.5-cp38-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:582f5fcd2afa31622f317f80426a027f30dc792e9c80ffee87b993200ea115f1", size = 4276755, upload-time = "2026-02-10T19:18:09.813Z" },
+    { url = "https://files.pythonhosted.org/packages/33/45/726809d1176959f4a896b86907b98ff4391a8aa29c0aaaf9450a8a10630e/cryptography-46.0.5-cp38-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:bfd56bb4b37ed4f330b82402f6f435845a5f5648edf1ad497da51a8452d5d62d", size = 4901539, upload-time = "2026-02-10T19:18:11.263Z" },
+    { url = "https://files.pythonhosted.org/packages/99/0f/a3076874e9c88ecb2ecc31382f6e7c21b428ede6f55aafa1aa272613e3cd/cryptography-46.0.5-cp38-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:a3d507bb6a513ca96ba84443226af944b0f7f47dcc9a399d110cd6146481d24c", size = 4452794, upload-time = "2026-02-10T19:18:12.914Z" },
+    { url = "https://files.pythonhosted.org/packages/02/ef/ffeb542d3683d24194a38f66ca17c0a4b8bf10631feef44a7ef64e631b1a/cryptography-46.0.5-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:9f16fbdf4da055efb21c22d81b89f155f02ba420558db21288b3d0035bafd5f4", size = 4404160, upload-time = "2026-02-10T19:18:14.375Z" },
+    { url = "https://files.pythonhosted.org/packages/96/93/682d2b43c1d5f1406ed048f377c0fc9fc8f7b0447a478d5c65ab3d3a66eb/cryptography-46.0.5-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:ced80795227d70549a411a4ab66e8ce307899fad2220ce5ab2f296e687eacde9", size = 4667123, upload-time = "2026-02-10T19:18:15.886Z" },
+    { url = "https://files.pythonhosted.org/packages/45/2d/9c5f2926cb5300a8eefc3f4f0b3f3df39db7f7ce40c8365444c49363cbda/cryptography-46.0.5-cp38-abi3-win32.whl", hash = "sha256:02f547fce831f5096c9a567fd41bc12ca8f11df260959ecc7c3202555cc47a72", size = 3010220, upload-time = "2026-02-10T19:18:17.361Z" },
+    { url = "https://files.pythonhosted.org/packages/48/ef/0c2f4a8e31018a986949d34a01115dd057bf536905dca38897bacd21fac3/cryptography-46.0.5-cp38-abi3-win_amd64.whl", hash = "sha256:556e106ee01aa13484ce9b0239bca667be5004efb0aabbed28d353df86445595", size = 3467050, upload-time = "2026-02-10T19:18:18.899Z" },
+    { url = "https://files.pythonhosted.org/packages/eb/dd/2d9fdb07cebdf3d51179730afb7d5e576153c6744c3ff8fded23030c204e/cryptography-46.0.5-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:3b4995dc971c9fb83c25aa44cf45f02ba86f71ee600d81091c2f0cbae116b06c", size = 3476964, upload-time = "2026-02-10T19:18:20.687Z" },
+    { url = "https://files.pythonhosted.org/packages/e9/6f/6cc6cc9955caa6eaf83660b0da2b077c7fe8ff9950a3c5e45d605038d439/cryptography-46.0.5-pp311-pypy311_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:bc84e875994c3b445871ea7181d424588171efec3e185dced958dad9e001950a", size = 4218321, upload-time = "2026-02-10T19:18:22.349Z" },
+    { url = "https://files.pythonhosted.org/packages/3e/5d/c4da701939eeee699566a6c1367427ab91a8b7088cc2328c09dbee940415/cryptography-46.0.5-pp311-pypy311_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:2ae6971afd6246710480e3f15824ed3029a60fc16991db250034efd0b9fb4356", size = 4381786, upload-time = "2026-02-10T19:18:24.529Z" },
+    { url = "https://files.pythonhosted.org/packages/ac/97/a538654732974a94ff96c1db621fa464f455c02d4bb7d2652f4edc21d600/cryptography-46.0.5-pp311-pypy311_pp73-manylinux_2_34_aarch64.whl", hash = "sha256:d861ee9e76ace6cf36a6a89b959ec08e7bc2493ee39d07ffe5acb23ef46d27da", size = 4217990, upload-time = "2026-02-10T19:18:25.957Z" },
+    { url = "https://files.pythonhosted.org/packages/ae/11/7e500d2dd3ba891197b9efd2da5454b74336d64a7cc419aa7327ab74e5f6/cryptography-46.0.5-pp311-pypy311_pp73-manylinux_2_34_x86_64.whl", hash = "sha256:2b7a67c9cd56372f3249b39699f2ad479f6991e62ea15800973b956f4b73e257", size = 4381252, upload-time = "2026-02-10T19:18:27.496Z" },
+    { url = "https://files.pythonhosted.org/packages/bc/58/6b3d24e6b9bc474a2dcdee65dfd1f008867015408a271562e4b690561a4d/cryptography-46.0.5-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:8456928655f856c6e1533ff59d5be76578a7157224dbd9ce6872f25055ab9ab7", size = 3407605, upload-time = "2026-02-10T19:18:29.233Z" },
 ]
 
 [[package]]
@@ -4195,7 +4195,7 @@ wheels = [
 
 [[package]]
 name = "nltk"
-version = "3.9.2"
+version = "3.9.3"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "click" },
@@ -4203,9 +4203,9 @@ dependencies = [
     { name = "regex" },
     { name = "tqdm" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/f9/76/3a5e4312c19a028770f86fd7c058cf9f4ec4321c6cf7526bab998a5b683c/nltk-3.9.2.tar.gz", hash = "sha256:0f409e9b069ca4177c1903c3e843eef90c7e92992fa4931ae607da6de49e1419", size = 2887629, upload-time = "2025-10-01T07:19:23.764Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/e1/8f/915e1c12df07c70ed779d18ab83d065718a926e70d3ea33eb0cd66ffb7c0/nltk-3.9.3.tar.gz", hash = "sha256:cb5945d6424a98d694c2b9a0264519fab4363711065a46aa0ae7a2195b92e71f", size = 2923673, upload-time = "2026-02-24T12:05:53.833Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/60/90/81ac364ef94209c100e12579629dc92bf7a709a84af32f8c551b02c07e94/nltk-3.9.2-py3-none-any.whl", hash = "sha256:1e209d2b3009110635ed9709a67a1a3e33a10f799490fa71cf4bec218c11c88a", size = 1513404, upload-time = "2025-10-01T07:19:21.648Z" },
+    { url = "https://files.pythonhosted.org/packages/c2/7e/9af5a710a1236e4772de8dfcc6af942a561327bb9f42b5b4a24d0cf100fd/nltk-3.9.3-py3-none-any.whl", hash = "sha256:60b3db6e9995b3dd976b1f0fa7dec22069b2677e759c28eb69b62ddd44870522", size = 1525385, upload-time = "2026-02-24T12:05:46.54Z" },
 ]
 
 [[package]]