regen cassette

* Added a new utility function to remove OpenAI-specific fields from schemas, ensuring compatibility with Gemini and Bedrock APIs.
* Updated BedrockCompletion and GeminiCompletion classes to utilize this function for cleaning parameters before API calls.
* Introduced tests to validate the functionality of the new utility, ensuring it correctly strips incompatible fields while preserving required properties.

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/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/bedrock/completion.py

@@ -1948,6 +1948,9 @@ class BedrockCompletion(BaseLLM):
     ) -> list[ConverseToolTypeDef]:
         """Convert CrewAI tools to Converse API format following AWS specification."""
         from crewai.llms.providers.utils.common import safe_tool_conversion
+        from crewai.utilities.pydantic_schema_utils import (
+            strip_openai_specific_schema_fields,
+        )
 
         converse_tools: list[ConverseToolTypeDef] = []
 
@@ -1961,6 +1964,7 @@ class BedrockCompletion(BaseLLM):
                 }
 
                 if parameters and isinstance(parameters, dict):
+                    parameters = strip_openai_specific_schema_fields(parameters)
                     input_schema: ToolInputSchema = {"json": parameters}
                     tool_spec["inputSchema"] = input_schema
 

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

@@ -529,10 +529,16 @@ class GeminiCompletion(BaseLLM):
         gemini_tools = []
 
         from crewai.llms.providers.utils.common import safe_tool_conversion
+        from crewai.utilities.pydantic_schema_utils import (
+            strip_openai_specific_schema_fields,
+        )
 
         for tool in tools:
             name, description, parameters = safe_tool_conversion(tool, "Gemini")
 
+            if parameters:
+                parameters = strip_openai_specific_schema_fields(parameters)
+
             function_declaration = types.FunctionDeclaration(
                 name=name,
                 description=description,
@@ -894,7 +900,7 @@ 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/utilities/agent_utils.py

@@ -168,7 +168,9 @@ def convert_tools_to_openai_schema(
         parameters: dict[str, Any] = {}
         if hasattr(tool, "args_schema") and tool.args_schema is not None:
             try:
-                schema_output = generate_model_description(tool.args_schema)
+                schema_output = generate_model_description(
+                    tool.args_schema, strip_null_types=False
+                )
                 parameters = schema_output.get("json_schema", {}).get("schema", {})
                 # Remove title and description from schema root as they're redundant
                 parameters.pop("title", None)

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

@@ -417,7 +417,40 @@ def strip_null_from_types(schema: dict[str, Any]) -> dict[str, Any]:
     return schema
 
 
-def generate_model_description(model: type[BaseModel]) -> ModelDescription:
+def strip_openai_specific_schema_fields(schema: dict[str, Any]) -> dict[str, Any]:
+    """Remove OpenAI strict-mode fields that are incompatible with other providers.
+
+    OpenAI strict mode requires ``additionalProperties: false`` on every object
+    and all properties listed in ``required``.  Gemini and Bedrock reject these
+    fields with schema validation errors, so we strip them before handing off to
+    non-OpenAI providers.
+
+    Specifically removes (recursively):
+    - ``additionalProperties`` — not supported by Gemini / Bedrock tool schemas
+
+    Args:
+        schema: JSON schema dictionary (mutated in place and returned).
+
+    Returns:
+        The modified schema.
+    """
+    if isinstance(schema, dict):
+        schema.pop("additionalProperties", None)
+        for value in schema.values():
+            if isinstance(value, dict):
+                strip_openai_specific_schema_fields(value)
+            elif isinstance(value, list):
+                for item in value:
+                    if isinstance(item, dict):
+                        strip_openai_specific_schema_fields(item)
+    return schema
+
+
+def generate_model_description(
+    model: type[BaseModel],
+    *,
+    strip_null_types: bool = True,
+) -> ModelDescription:
     """Generate JSON schema description of a Pydantic model.
 
     This function takes a Pydantic model class and returns its JSON schema,
@@ -426,6 +459,9 @@ def generate_model_description(model: type[BaseModel]) -> ModelDescription:
 
     Args:
         model: A Pydantic model class.
+        strip_null_types: When ``True`` (default), remove ``null`` from
+            ``anyOf`` / ``type`` arrays.  Set to ``False`` to allow sending ``null`` for
+            optional fields.
 
     Returns:
         A ModelDescription with JSON schema representation of the model.
@@ -442,7 +478,9 @@ def generate_model_description(model: type[BaseModel]) -> ModelDescription:
     json_schema = fix_discriminator_mappings(json_schema)
     json_schema = convert_oneof_to_anyof(json_schema)
     json_schema = ensure_all_properties_required(json_schema)
-    json_schema = strip_null_from_types(json_schema)
+
+    if strip_null_types:
+        json_schema = strip_null_from_types(json_schema)
 
     return {
         "type": "json_schema",

lib/crewai/tests/agents/test_native_tool_calling.py

@@ -559,6 +559,39 @@ class TestAnthropicNativeToolCalling:
         _assert_tools_overlapped()
 
 
+_MCP_OPTIONAL_FIELDS_TOOL_DEFS = [
+    {
+        "name": "filtered_search",
+        "description": (
+            "Search a knowledge base. Pass null for any filter you don't need."
+        ),
+        "inputSchema": {
+            "type": "object",
+            "properties": {
+                "query": {
+                    "type": "string",
+                    "description": "Search query string",
+                },
+                "filter_type": {
+                    "anyOf": [
+                        {"type": "string", "enum": ["news", "blog", "docs"]},
+                        {"type": "null"},
+                    ],
+                    "default": None,
+                    "description": "Optional content-type filter",
+                },
+                "page_id": {
+                    "anyOf": [{"type": "string"}, {"type": "null"}],
+                    "default": None,
+                    "description": "Optional page UUID",
+                },
+            },
+            "required": ["query"],
+        },
+    }
+]
+
+
 # =============================================================================
 # Google/Gemini Provider Tests
 # =============================================================================
@@ -796,6 +829,9 @@ class TestAzureNativeToolCalling:
         _assert_tools_overlapped()
 
 
+    
+
+
 # =============================================================================
 # Bedrock Provider Tests
 # =============================================================================
@@ -929,6 +965,135 @@ class TestNativeToolCallingBehavior:
         assert hasattr(llm, "supports_function_calling")
         assert llm.supports_function_calling() is True
 
+    @pytest.mark.vcr()
+    def test_gemini_mcp_tool_with_optional_fields_no_schema_error(self) -> None:
+        """MCP tools with Optional fields must not cause Gemini schema validation errors.
+
+        Regression test for https://github.com/crewAIInc/crewAI/issues/4472.
+
+        Before the fix, generate_model_description() added additionalProperties:false
+        to the tool schema. Gemini rejects this field, raising:
+          "value at properties.<field> must be a list"
+
+        With the fix, strip_openai_specific_schema_fields() removes it before the
+        schema is sent to the Gemini API.
+
+        To record the cassette:
+            RUN_LIVE_GEMINI_TESTS=true GOOGLE_API_KEY=<key> \\
+            uv run pytest tests/agents/test_native_tool_calling.py \\
+                ::TestGeminiNativeToolCalling::test_gemini_mcp_tool_with_optional_fields_no_schema_error \\
+                --record-mode=once -v
+        """
+        from unittest.mock import AsyncMock, patch
+
+        from crewai.mcp.config import MCPServerStdio
+
+        stdio_config = MCPServerStdio(command="python", args=["fake_mcp_server.py"])
+
+        agent = Agent(
+            role="Knowledge Researcher",
+            goal="Search a knowledge base and return relevant results",
+            backstory="You are a helpful researcher who uses the filtered_search tool.",
+            mcps=[stdio_config],
+            llm=LLM(model="gemini/gemini-2.5-flash"),
+            verbose=False,
+            max_iter=3,
+        )
+
+        with patch("crewai.agent.core.MCPClient") as mock_client_class:
+            mock_client = AsyncMock()
+            mock_client.list_tools = AsyncMock(
+                return_value=_MCP_OPTIONAL_FIELDS_TOOL_DEFS
+            )
+            mock_client.connected = False
+            mock_client.connect = AsyncMock()
+            mock_client.disconnect = AsyncMock()
+            mock_client.call_tool = AsyncMock(
+                return_value="Search results: Introduction to agents, Tool integration guide"
+            )
+            mock_client_class.return_value = mock_client
+
+            task = Task(
+                description=(
+                    "Search the knowledge base for information about CrewAI agents. "
+                    "No filters needed — just a general search."
+                ),
+                expected_output="A brief summary of relevant search results.",
+                agent=agent,
+            )
+
+            crew = Crew(agents=[agent], tasks=[task])
+            result = crew.kickoff()
+
+        assert result is not None
+        assert result.raw is not None
+
+    @pytest.mark.vcr()
+    def test_bedrock_mcp_tool_with_optional_fields_no_schema_error(self) -> None:
+        """MCP tools with Optional fields must not cause Bedrock schema validation errors.
+
+        Regression test for https://github.com/crewAIInc/crewAI/issues/4472.
+
+        Before the fix, generate_model_description() added additionalProperties:false
+        to the tool schema. The Bedrock Converse API rejects this field, raising:
+          "JSON schema is invalid"
+
+        With the fix, strip_openai_specific_schema_fields() removes it before the
+        schema is sent to Bedrock.
+
+        Note: MCPClient is mocked — no Bedrock credentials are needed to run this
+        test. The LLM call is replayed from the VCR cassette.
+
+        To record the cassette:
+            AWS_ACCESS_KEY_ID=<key> AWS_SECRET_ACCESS_KEY=<secret> AWS_DEFAULT_REGION=us-east-1 \\
+            uv run pytest tests/agents/test_native_tool_calling.py \\
+                ::TestNativeToolCallingBehavior::test_bedrock_mcp_tool_with_optional_fields_no_schema_error \\
+                --record-mode=once -v
+        """
+        from unittest.mock import AsyncMock, patch
+
+        from crewai.mcp.config import MCPServerStdio
+
+        stdio_config = MCPServerStdio(command="python", args=["fake_mcp_server.py"])
+
+        agent = Agent(
+            role="Knowledge Researcher",
+            goal="Search a knowledge base and return relevant results",
+            backstory="You are a helpful researcher who uses the filtered_search tool.",
+            mcps=[stdio_config],
+            llm=LLM(model="bedrock/anthropic.claude-3-haiku-20240307-v1:0"),
+            verbose=False,
+            max_iter=3,
+        )
+
+        with patch("crewai.agent.core.MCPClient") as mock_client_class:
+            mock_client = AsyncMock()
+            mock_client.list_tools = AsyncMock(
+                return_value=_MCP_OPTIONAL_FIELDS_TOOL_DEFS
+            )
+            mock_client.connected = False
+            mock_client.connect = AsyncMock()
+            mock_client.disconnect = AsyncMock()
+            mock_client.call_tool = AsyncMock(
+                return_value="Search results: Introduction to agents, Tool integration guide"
+            )
+            mock_client_class.return_value = mock_client
+
+            task = Task(
+                description=(
+                    "Search the knowledge base for information about CrewAI agents. "
+                    "No filters needed — just a general search."
+                ),
+                expected_output="A brief summary of relevant search results.",
+                agent=agent,
+            )
+
+            crew = Crew(agents=[agent], tasks=[task])
+            result = crew.kickoff()
+
+        assert result is not None
+        assert result.raw is not None
+
 
 # =============================================================================
 # Token Usage Tests

lib/crewai/tests/cassettes/agents/TestNativeToolCallingBehavior.test_bedrock_mcp_tool_with_optional_fields_no_schema_error.yaml

@@ -0,0 +1,128 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": [{"text": "\nCurrent Task: Search
+      the knowledge base for information about CrewAI agents. No filters needed \u2014
+      just a general search.\n\nThis is the expected criteria for your final answer:
+      A brief summary of relevant search results.\nyou MUST return the actual complete
+      content as the final answer, not a summary."}]}], "inferenceConfig": {"stopSequences":
+      ["\nObservation:"]}, "system": [{"text": "You are Knowledge Researcher. You
+      are a helpful researcher who uses the filtered_search tool.\nYour personal goal
+      is: Search a knowledge base and return relevant results"}], "toolConfig": {"tools":
+      [{"toolSpec": {"name": "python_fake_mcp_server_py_filtered_search", "description":
+      "Search a knowledge base. Pass null for any filter you don''t need.", "inputSchema":
+      {"json": {"properties": {"query": {"description": "Search query string", "title":
+      "Query", "type": "string"}, "filter_type": {"anyOf": [{"type": "string"}, {"type":
+      "object"}, {"type": "null"}], "default": null, "description": "Optional content-type
+      filter", "title": "Filter Type"}, "page_id": {"anyOf": [{"type": "string"},
+      {"type": "object"}, {"type": "null"}], "default": null, "description": "Optional
+      page UUID", "title": "Page Id"}}, "required": ["query", "filter_type", "page_id"],
+      "type": "object"}}}}]}}'
+    headers:
+      Content-Length:
+      - '1324'
+      Content-Type:
+      - !!binary |
+        YXBwbGljYXRpb24vanNvbg==
+      User-Agent:
+      - X-USER-AGENT-XXX
+      amz-sdk-invocation-id:
+      - AMZ-SDK-INVOCATION-ID-XXX
+      amz-sdk-request:
+      - !!binary |
+        YXR0ZW1wdD0x
+      authorization:
+      - AUTHORIZATION-XXX
+      x-amz-date:
+      - X-AMZ-DATE-XXX
+    method: POST
+    uri: https://bedrock-runtime.us-east-1.amazonaws.com/model/anthropic.claude-3-haiku-20240307-v1%3A0/converse
+  response:
+    body:
+      string: '{"metrics":{"latencyMs":1866},"output":{"message":{"content":[{"text":"Understood.
+        Here is the search query to find information about CrewAI agents in the knowledge
+        base:"},{"toolUse":{"input":{"query":"CrewAI agents","filter_type":null,"page_id":null},"name":"python_fake_mcp_server_py_filtered_search","toolUseId":"tooluse_DH3PzO6KYfG8Zn9tGJZrvL"}}],"role":"assistant"}},"stopReason":"tool_use","usage":{"inputTokens":572,"outputTokens":129,"serverToolUsage":{},"totalTokens":701}}'
+    headers:
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '483'
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 25 Feb 2026 23:49:21 GMT
+      x-amzn-RequestId:
+      - X-AMZN-REQUESTID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "user", "content": [{"text": "\nCurrent Task: Search
+      the knowledge base for information about CrewAI agents. No filters needed \u2014
+      just a general search.\n\nThis is the expected criteria for your final answer:
+      A brief summary of relevant search results.\nyou MUST return the actual complete
+      content as the final answer, not a summary."}]}, {"role": "assistant", "content":
+      [{"toolUse": {"toolUseId": "tooluse_DH3PzO6KYfG8Zn9tGJZrvL", "name": "python_fake_mcp_server_py_filtered_search",
+      "input": {}}}]}, {"role": "user", "content": [{"toolResult": {"toolUseId": "tooluse_DH3PzO6KYfG8Zn9tGJZrvL",
+      "content": [{"text": "Search results: Introduction to agents, Tool integration
+      guide"}]}}]}, {"role": "user", "content": [{"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."}]}], "inferenceConfig":
+      {"stopSequences": ["\nObservation:"]}, "system": [{"text": "You are Knowledge
+      Researcher. You are a helpful researcher who uses the filtered_search tool.\nYour
+      personal goal is: Search a knowledge base and return relevant results"}], "toolConfig":
+      {"tools": [{"toolSpec": {"name": "python_fake_mcp_server_py_filtered_search",
+      "description": "Search a knowledge base. Pass null for any filter you don''t
+      need.", "inputSchema": {"json": {"properties": {"query": {"description": "Search
+      query string", "title": "Query", "type": "string"}, "filter_type": {"anyOf":
+      [{"type": "string"}, {"type": "object"}, {"type": "null"}], "default": null,
+      "description": "Optional content-type filter", "title": "Filter Type"}, "page_id":
+      {"anyOf": [{"type": "string"}, {"type": "object"}, {"type": "null"}], "default":
+      null, "description": "Optional page UUID", "title": "Page Id"}}, "required":
+      ["query", "filter_type", "page_id"], "type": "object"}}}}]}}'
+    headers:
+      Content-Length:
+      - '1873'
+      Content-Type:
+      - !!binary |
+        YXBwbGljYXRpb24vanNvbg==
+      User-Agent:
+      - X-USER-AGENT-XXX
+      amz-sdk-invocation-id:
+      - AMZ-SDK-INVOCATION-ID-XXX
+      amz-sdk-request:
+      - !!binary |
+        YXR0ZW1wdD0x
+      authorization:
+      - AUTHORIZATION-XXX
+      x-amz-date:
+      - X-AMZ-DATE-XXX
+    method: POST
+    uri: https://bedrock-runtime.us-east-1.amazonaws.com/model/anthropic.claude-3-haiku-20240307-v1%3A0/converse
+  response:
+    body:
+      string: '{"metrics":{"latencyMs":2324},"output":{"message":{"content":[{"text":"<result>\nIntroduction
+        to agents:\nCrewAI agents are autonomous software entities that can perform
+        a variety of tasks within a larger system or application. They are designed
+        to be modular, scalable, and highly configurable, allowing them to be integrated
+        into a wide range of use cases. Agents can handle tasks such as data processing,
+        decision-making, and event-driven automation.\n\nTool integration guide:\nThe
+        CrewAI tool integration guide provides detailed instructions on how to integrate
+        CrewAI agents into your existing software systems and workflows. It covers
+        topics such as agent deployment, configuration, communication protocols, and
+        monitoring/reporting. The guide includes code samples and best practices to
+        ensure seamless integration.\n</result>"}],"role":"assistant"}},"stopReason":"end_turn","usage":{"inputTokens":680,"outputTokens":154,"serverToolUsage":{},"totalTokens":834}}'
+    headers:
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '969'
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 25 Feb 2026 23:49:24 GMT
+      x-amzn-RequestId:
+      - X-AMZN-REQUESTID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestNativeToolCallingBehavior.test_gemini_mcp_tool_with_optional_fields_no_schema_error.yaml

@@ -0,0 +1,161 @@
+interactions:
+- request:
+    body: '{"contents": [{"parts": [{"text": "\nCurrent Task: Search the knowledge
+      base for information about CrewAI agents. No filters needed \u2014 just a general
+      search.\n\nThis is the expected criteria for your final answer: A brief summary
+      of relevant search results.\nyou MUST return the actual complete content as
+      the final answer, not a summary."}], "role": "user"}], "systemInstruction":
+      {"parts": [{"text": "You are Knowledge Researcher. You are a helpful researcher
+      who uses the filtered_search tool.\nYour personal goal is: Search a knowledge
+      base and return relevant results"}], "role": "user"}, "tools": [{"functionDeclarations":
+      [{"description": "Search a knowledge base. Pass null for any filter you don''t
+      need.", "name": "python_fake_mcp_server_py_filtered_search", "parameters_json_schema":
+      {"properties": {"query": {"description": "Search query string", "title": "Query",
+      "type": "string"}, "filter_type": {"anyOf": [{"type": "string"}, {"type": "object"},
+      {"type": "null"}], "default": null, "description": "Optional content-type filter",
+      "title": "Filter Type"}, "page_id": {"anyOf": [{"type": "string"}, {"type":
+      "object"}, {"type": "null"}], "default": null, "description": "Optional page
+      UUID", "title": "Page Id"}}, "required": ["query", "filter_type", "page_id"],
+      "type": "object"}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1360'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      x-goog-api-client:
+      - google-genai-sdk/1.49.0 gl-python/3.13.3
+      x-goog-api-key:
+      - X-GOOG-API-KEY-XXX
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
+  response:
+    body:
+      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
+        [\n          {\n            \"functionCall\": {\n              \"name\": \"python_fake_mcp_server_py_filtered_search\",\n
+        \             \"args\": {\n                \"query\": \"CrewAI agents\"\n
+        \             }\n            },\n            \"thoughtSignature\": \"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\"\n
+        \         }\n        ],\n        \"role\": \"model\"\n      },\n      \"finishReason\":
+        \"STOP\",\n      \"index\": 0,\n      \"finishMessage\": \"Model generated
+        function call(s).\"\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
+        203,\n    \"candidatesTokenCount\": 28,\n    \"totalTokenCount\": 361,\n    \"promptTokensDetails\":
+        [\n      {\n        \"modality\": \"TEXT\",\n        \"tokenCount\": 203\n
+        \     }\n    ],\n    \"thoughtsTokenCount\": 130\n  },\n  \"modelVersion\":
+        \"gemini-2.5-flash\",\n  \"responseId\": \"bICfafeTH_T5-8YP8rnE6Qo\"\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 23:06:21 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=1210
+      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: Search the knowledge
+      base for information about CrewAI agents. No filters needed \u2014 just a general
+      search.\n\nThis is the expected criteria for your final answer: A brief summary
+      of relevant search results.\nyou MUST return the actual complete content as
+      the final answer, not a summary."}], "role": "user"}, {"parts": [{"functionCall":
+      {"args": {"query": "CrewAI agents"}, "name": "python_fake_mcp_server_py_filtered_search"}}],
+      "role": "model"}, {"parts": [{"functionResponse": {"name": "python_fake_mcp_server_py_filtered_search",
+      "response": {"result": "Search results: Introduction to agents, Tool integration
+      guide"}}}], "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 Knowledge Researcher. You are a helpful researcher
+      who uses the filtered_search tool.\nYour personal goal is: Search a knowledge
+      base and return relevant results"}], "role": "user"}, "tools": [{"functionDeclarations":
+      [{"description": "Search a knowledge base. Pass null for any filter you don''t
+      need.", "name": "python_fake_mcp_server_py_filtered_search", "parameters_json_schema":
+      {"properties": {"query": {"description": "Search query string", "title": "Query",
+      "type": "string"}, "filter_type": {"anyOf": [{"type": "string"}, {"type": "object"},
+      {"type": "null"}], "default": null, "description": "Optional content-type filter",
+      "title": "Filter Type"}, "page_id": {"anyOf": [{"type": "string"}, {"type":
+      "object"}, {"type": "null"}], "default": null, "description": "Optional page
+      UUID", "title": "Page Id"}}, "required": ["query", "filter_type", "page_id"],
+      "type": "object"}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1893'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      x-goog-api-client:
+      - google-genai-sdk/1.49.0 gl-python/3.13.3
+      x-goog-api-key:
+      - X-GOOG-API-KEY-XXX
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
+  response:
+    body:
+      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
+        [\n          {\n            \"text\": \"Search results: Introduction to agents,
+        Tool integration guide\"\n          }\n        ],\n        \"role\": \"model\"\n
+        \     },\n      \"finishReason\": \"STOP\",\n      \"index\": 0\n    }\n  ],\n
+        \ \"usageMetadata\": {\n    \"promptTokenCount\": 299,\n    \"candidatesTokenCount\":
+        10,\n    \"totalTokenCount\": 309,\n    \"promptTokensDetails\": [\n      {\n
+        \       \"modality\": \"TEXT\",\n        \"tokenCount\": 299\n      }\n    ]\n
+        \ },\n  \"modelVersion\": \"gemini-2.5-flash\",\n  \"responseId\": \"bYCfacPnLsD4-8YP6p64sQs\"\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 23:06:22 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=380
+      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/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/utilities/test_agent_utils.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 import asyncio
-from typing import Any
+from typing import Any, Literal, Optional
 from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
@@ -235,6 +235,178 @@ def _make_mock_i18n() -> MagicMock:
     }.get(key, "")
     return mock_i18n
 
+class MCPStyleInput(BaseModel):
+    """Input schema mimicking an MCP tool with optional fields."""
+
+    query: str = Field(description="Search query")
+    filter_type: Optional[Literal["internal", "user"]] = Field(
+        default=None, description="Filter type"
+    )
+    page_id: Optional[str] = Field(
+        default=None, description="Page UUID"
+    )
+
+
+class MCPStyleTool(BaseTool):
+    """A tool mimicking MCP tool schemas with optional fields."""
+
+    name: str = "mcp_search"
+    description: str = "Search with optional filters"
+    args_schema: type[BaseModel] = MCPStyleInput
+
+    def _run(self, **kwargs: Any) -> str:
+        return "result"
+
+
+class TestOptionalFieldsPreserveNull:
+    """Tests that optional tool fields preserve null in the schema."""
+
+    def test_optional_string_allows_null(self) -> None:
+        """Optional[str] fields should include null in the schema so the LLM
+        can send null instead of being forced to guess a value."""
+        tools = [MCPStyleTool()]
+        schemas, _ = convert_tools_to_openai_schema(tools)
+
+        params = schemas[0]["function"]["parameters"]
+        page_id_prop = params["properties"]["page_id"]
+
+        assert "anyOf" in page_id_prop
+        type_options = [opt.get("type") for opt in page_id_prop["anyOf"]]
+        assert "string" in type_options
+        assert "null" in type_options
+
+    def test_optional_literal_allows_null(self) -> None:
+        """Optional[Literal[...]] fields should include null."""
+        tools = [MCPStyleTool()]
+        schemas, _ = convert_tools_to_openai_schema(tools)
+
+        params = schemas[0]["function"]["parameters"]
+        filter_prop = params["properties"]["filter_type"]
+
+        assert "anyOf" in filter_prop
+        has_null = any(opt.get("type") == "null" for opt in filter_prop["anyOf"])
+        assert has_null
+
+    def test_required_field_stays_non_null(self) -> None:
+        """Required fields without Optional should NOT have null."""
+        tools = [MCPStyleTool()]
+        schemas, _ = convert_tools_to_openai_schema(tools)
+
+        params = schemas[0]["function"]["parameters"]
+        query_prop = params["properties"]["query"]
+
+        assert query_prop.get("type") == "string"
+        assert "anyOf" not in query_prop
+
+    def test_all_fields_in_required_for_strict_mode(self) -> None:
+        """All fields (including optional) must be in required for strict mode."""
+        tools = [MCPStyleTool()]
+        schemas, _ = convert_tools_to_openai_schema(tools)
+
+        params = schemas[0]["function"]["parameters"]
+        assert "query" in params["required"]
+        assert "filter_type" in params["required"]
+        assert "page_id" in params["required"]
+
+
+class TestStripOpenAISpecificSchemaFields:
+    """Tests for strip_openai_specific_schema_fields.
+
+    All tests call the real schema pipeline with real tool instances —
+    no mocking of internal functions.
+    """
+
+    def test_removes_additional_properties_at_root(self) -> None:
+        """additionalProperties must be absent after stripping."""
+        from crewai.utilities.pydantic_schema_utils import (
+            strip_openai_specific_schema_fields,
+        )
+
+        tools = [MCPStyleTool()]
+        schemas, _ = convert_tools_to_openai_schema(tools)
+        params = schemas[0]["function"]["parameters"]
+
+        # Confirm it's present in the OpenAI-format schema
+        assert params.get("additionalProperties") is False
+
+        clean = strip_openai_specific_schema_fields(params)
+        assert "additionalProperties" not in clean
+
+    def test_removes_additional_properties_recursively(self) -> None:
+        """Nested objects must also have additionalProperties removed."""
+        from crewai.utilities.pydantic_schema_utils import (
+            strip_openai_specific_schema_fields,
+        )
+
+        class NestedInput(BaseModel):
+            config: dict[str, Any] = Field(default_factory=dict)
+            query: str = Field(description="query")
+
+        class NestedTool(BaseTool):
+            name: str = "nested_tool"
+            description: str = "tool with nested object"
+            args_schema: type[BaseModel] = NestedInput
+
+            def _run(self, **kwargs: Any) -> str:
+                return "ok"
+
+        schemas, _ = convert_tools_to_openai_schema([NestedTool()])
+        params = schemas[0]["function"]["parameters"]
+        clean = strip_openai_specific_schema_fields(params)
+
+        def has_additional_properties(obj: Any) -> bool:
+            if isinstance(obj, dict):
+                if "additionalProperties" in obj:
+                    return True
+                return any(has_additional_properties(v) for v in obj.values())
+            if isinstance(obj, list):
+                return any(has_additional_properties(i) for i in obj)
+            return False
+
+        assert not has_additional_properties(clean)
+
+    def test_preserves_required_and_properties(self) -> None:
+        """required and properties must survive the strip."""
+        from crewai.utilities.pydantic_schema_utils import (
+            strip_openai_specific_schema_fields,
+        )
+
+        tools = [MCPStyleTool()]
+        schemas, _ = convert_tools_to_openai_schema(tools)
+        params = schemas[0]["function"]["parameters"]
+        clean = strip_openai_specific_schema_fields(params)
+
+        assert "properties" in clean
+        assert "required" in clean
+        assert "query" in clean["properties"]
+
+    def test_gemini_bedrock_path_extracts_clean_parameters(self) -> None:
+        """extract_tool_info returns the same parameters dict that
+        strip_openai_specific_schema_fields will clean — verifying the
+        full Gemini/Bedrock conversion pipeline produces a valid schema."""
+        from crewai.llms.providers.utils.common import extract_tool_info
+        from crewai.utilities.pydantic_schema_utils import (
+            strip_openai_specific_schema_fields,
+        )
+
+        tools = [MCPStyleTool()]
+        schemas, _ = convert_tools_to_openai_schema(tools)
+
+        # extract_tool_info is what Gemini/Bedrock call internally
+        _name, _desc, parameters = extract_tool_info(schemas[0])
+
+        assert parameters.get("additionalProperties") is False, (
+            "Raw OpenAI schema should have additionalProperties=false"
+        )
+
+        clean = strip_openai_specific_schema_fields(parameters)
+        assert "additionalProperties" not in clean
+        # null types preserved for optional fields
+        assert any(
+            opt.get("type") == "null"
+            for opt in clean["properties"]["page_id"].get("anyOf", [])
+        )
+
 
 class TestSummarizeMessages:
     """Tests for summarize_messages function."""