wip

- Convert enum constraints to Literal types
- Handle format constraints (date, date-time)
- Preserve original MCP tool names for server calls

lib/crewai/pyproject.toml

@@ -14,7 +14,7 @@ dependencies = [
     "instructor>=1.3.3",
     # Text Processing
     "pdfplumber~=0.11.4",
-    "regex~=2026.1.15",
+    "regex~=2024.9.11",
     # Telemetry and Monitoring
     "opentelemetry-api~=1.34.0",
     "opentelemetry-sdk~=1.34.0",
@@ -36,7 +36,7 @@ dependencies = [
     "json5~=0.10.0",
     "portalocker~=2.7.0",
     "pydantic-settings~=2.10.1",
-    "mcp~=1.26.0",
+    "mcp~=1.23.1",
     "uv~=0.9.13",
     "aiosqlite~=0.21.0",
 ]

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

@@ -24,6 +24,7 @@ from pydantic import (
 )
 from typing_extensions import Self
 
+from crewai.agent.json_schema_converter import JSONSchemaConverter
 from crewai.agent.utils import (
     ahandle_knowledge_retrieval,
     apply_training_data,
@@ -1178,6 +1179,7 @@ class Agent(BaseAgent):
             tools = []
             for tool_def in tools_list:
                 tool_name = tool_def.get("name", "")
+                original_tool_name = tool_def.get("original_name", tool_name)
                 if not tool_name:
                     continue
 
@@ -1199,6 +1201,7 @@ class Agent(BaseAgent):
                         tool_name=tool_name,
                         tool_schema=tool_schema,
                         server_name=server_name,
+                        original_tool_name=original_tool_name,
                     )
                     tools.append(native_tool)
                 except Exception as e:
@@ -1213,26 +1216,63 @@ class Agent(BaseAgent):
             raise RuntimeError(f"Failed to get native MCP tools: {e}") from e
 
     def _get_amp_mcp_tools(self, amp_ref: str) -> list[BaseTool]:
-        """Get tools from CrewAI AMP MCP marketplace."""
-        # Parse: "crewai-amp:mcp-name" or "crewai-amp:mcp-name#tool_name"
+        """Get tools from CrewAI AMP MCP via crewai-oauth service.
+
+        Fetches MCP server configuration with tokens injected from crewai-oauth,
+        then uses _get_native_mcp_tools to connect and discover tools.
+        """
+        # Parse: "crewai-amp:mcp-slug" or "crewai-amp:mcp-slug#tool_name"
         amp_part = amp_ref.replace("crewai-amp:", "")
         if "#" in amp_part:
-            mcp_name, specific_tool = amp_part.split("#", 1)
+            mcp_slug, specific_tool = amp_part.split("#", 1)
         else:
-            mcp_name, specific_tool = amp_part, None
+            mcp_slug, specific_tool = amp_part, None
 
-        # Call AMP API to get MCP server URLs
-        mcp_servers = self._fetch_amp_mcp_servers(mcp_name)
+        # Fetch MCP config from crewai-oauth (with tokens injected)
+        mcp_config_dict = self._fetch_amp_mcp_config(mcp_slug)
 
-        tools = []
-        for server_config in mcp_servers:
-            server_ref = server_config["url"]
-            if specific_tool:
-                server_ref += f"#{specific_tool}"
-            server_tools = self._get_external_mcp_tools(server_ref)
-            tools.extend(server_tools)
+        if not mcp_config_dict:
+            self._logger.log(
+                "warning", f"Failed to fetch MCP config for '{mcp_slug}' from crewai-oauth"
+            )
+            return []
 
-        return tools
+        # Convert dict to MCPServerConfig (MCPServerHTTP or MCPServerSSE)
+        config_type = mcp_config_dict.get("type", "http")
+
+        if config_type == "sse":
+            mcp_config = MCPServerSSE(
+                url=mcp_config_dict["url"],
+                headers=mcp_config_dict.get("headers"),
+                cache_tools_list=mcp_config_dict.get("cache_tools_list", False),
+            )
+        else:
+            mcp_config = MCPServerHTTP(
+                url=mcp_config_dict["url"],
+                headers=mcp_config_dict.get("headers"),
+                streamable=mcp_config_dict.get("streamable", True),
+                cache_tools_list=mcp_config_dict.get("cache_tools_list", False),
+            )
+
+        # Apply tool filter if specific tool requested
+        if specific_tool:
+            from crewai.mcp.filters import create_static_tool_filter
+
+            mcp_config.tool_filter = create_static_tool_filter(
+                allowed_tool_names=[specific_tool]
+            )
+
+        # Use native MCP tools to connect and discover tools
+        try:
+            tools, client = self._get_native_mcp_tools(mcp_config)
+            if client:
+                self._mcp_clients.append(client)
+            return tools
+        except Exception as e:
+            self._logger.log(
+                "warning", f"Failed to get MCP tools from '{mcp_slug}': {e}"
+            )
+            return []
 
     @staticmethod
     def _extract_server_name(server_url: str) -> str:
@@ -1389,6 +1429,9 @@ class Agent(BaseAgent):
                     }
                 return schemas
 
+    # Shared JSON Schema converter instance
+    _schema_converter: JSONSchemaConverter = JSONSchemaConverter()
+
     def _json_schema_to_pydantic(
         self, tool_name: str, json_schema: dict[str, Any]
     ) -> type:
@@ -1401,77 +1444,62 @@ class Agent(BaseAgent):
         Returns:
             Pydantic BaseModel class
         """
-        from pydantic import Field, create_model
+        return self._schema_converter.json_schema_to_pydantic(tool_name, json_schema)
 
-        properties = json_schema.get("properties", {})
-        required_fields = json_schema.get("required", [])
+    def _fetch_amp_mcp_config(self, mcp_slug: str) -> dict[str, Any] | None:
+        """Fetch MCP server configuration from crewai-oauth service.
 
-        field_definitions: dict[str, Any] = {}
+        Returns MCPServerConfig dict with tokens injected, ready for use with
+        _get_native_mcp_tools.
 
-        for field_name, field_schema in properties.items():
-            field_type = self._json_type_to_python(field_schema)
-            field_description = field_schema.get("description", "")
-
-            is_required = field_name in required_fields
-
-            if is_required:
-                field_definitions[field_name] = (
-                    field_type,
-                    Field(..., description=field_description),
-                )
-            else:
-                field_definitions[field_name] = (
-                    field_type | None,
-                    Field(default=None, description=field_description),
-                )
-
-        model_name = f"{tool_name.replace('-', '_').replace(' ', '_')}Schema"
-        return create_model(model_name, **field_definitions)  # type: ignore[no-any-return]
-
-    def _json_type_to_python(self, field_schema: dict[str, Any]) -> type:
-        """Convert JSON Schema type to Python type.
+        Environment variables:
+            CREWAI_OAUTH_URL: Base URL of crewai-oauth service
+            CREWAI_OAUTH_API_KEY: API key for authenticating with crewai-oauth
 
         Args:
-            field_schema: JSON Schema field definition
+            mcp_slug: The MCP server slug (e.g., "notion-mcp-abc123")
 
         Returns:
-            Python type
+            Dict with type, url, headers, streamable, cache_tools_list, or None if failed.
         """
+        import os
 
-        json_type = field_schema.get("type")
+        import requests
 
-        if "anyOf" in field_schema:
-            types: list[type] = []
-            for option in field_schema["anyOf"]:
-                if "const" in option:
-                    types.append(str)
-                else:
-                    types.append(self._json_type_to_python(option))
-            unique_types = list(set(types))
-            if len(unique_types) > 1:
-                result: Any = unique_types[0]
-                for t in unique_types[1:]:
-                    result = result | t
-                return result  # type: ignore[no-any-return]
-            return unique_types[0]
+        try:
+            endpoint = f"http://localhost:8787/mcps/{mcp_slug}/config"
+            response = requests.get(
+                endpoint,
+                headers={"Authorization": "Bearer 6b327f9ebe62726590f8de8f624cf018ad4765fecb7373f9db475a940ad546d0"},
+                timeout=30,
+            )
 
-        type_mapping: dict[str | None, type] = {
-            "string": str,
-            "number": float,
-            "integer": int,
-            "boolean": bool,
-            "array": list,
-            "object": dict,
-        }
+            if response.status_code == 200:
+                return response.json()
+            elif response.status_code == 400:
+                error_data = response.json()
+                self._logger.log(
+                    "warning",
+                    f"MCP '{mcp_slug}' is not connected: {error_data.get('error_description', 'Unknown error')}",
+                )
+                return None
+            elif response.status_code == 404:
+                self._logger.log(
+                    "warning", f"MCP server '{mcp_slug}' not found in crewai-oauth"
+                )
+                return None
+            else:
+                self._logger.log(
+                    "warning",
+                    f"Failed to fetch MCP config from crewai-oauth: HTTP {response.status_code}",
+                )
+                return None
 
-        return type_mapping.get(json_type, Any)
-
-    @staticmethod
-    def _fetch_amp_mcp_servers(mcp_name: str) -> list[dict[str, Any]]:
-        """Fetch MCP server configurations from CrewAI AMP API."""
-        # TODO: Implement AMP API call to "integrations/mcps" endpoint
-        # Should return list of server configs with URLs
-        return []
+        except requests.exceptions.RequestException as e:
+            self._logger.log(
+                "warning", f"Failed to connect to crewai-oauth: {e}"
+            )
+            return None
 
     @staticmethod
     def get_multimodal_tools() -> Sequence[BaseTool]:

lib/crewai/src/crewai/agent/json_schema_converter.py

@@ -0,0 +1,399 @@
+from typing import Any, Literal, Type, Union, get_args
+from pydantic import Field, create_model
+from pydantic.fields import FieldInfo
+import datetime
+import uuid
+
+
+class JSONSchemaConverter:
+    """Converts JSON Schema definitions to Python/Pydantic types."""
+
+    def json_schema_to_pydantic(
+        self, tool_name: str, json_schema: dict[str, Any]
+    ) -> Type[Any]:
+        """Convert JSON Schema to Pydantic model for tool arguments.
+
+        Args:
+            tool_name: Name of the tool (used for model naming)
+            json_schema: JSON Schema dict with 'properties', 'required', etc.
+
+        Returns:
+            Pydantic BaseModel class
+        """
+        properties = json_schema.get("properties", {})
+        required_fields = json_schema.get("required", [])
+
+        model_name = f"{tool_name.replace('-', '_').replace(' ', '_')}Schema"
+        return self._create_pydantic_model(model_name, properties, required_fields)
+
+    def _json_type_to_python(
+        self, field_schema: dict[str, Any], field_name: str = "Field"
+    ) -> Type[Any]:
+        """Convert JSON Schema type to Python type, handling nested structures.
+
+        Args:
+            field_schema: JSON Schema field definition
+            field_name: Name of the field (used for nested model naming)
+
+        Returns:
+            Python type (may be a dynamically created Pydantic model for objects/arrays)
+        """
+        if not field_schema:
+            return Any
+
+        # Handle $ref if needed
+        if "$ref" in field_schema:
+            # You might want to implement reference resolution here
+            return Any
+
+        # Handle enum constraint - create Literal type
+        if "enum" in field_schema:
+            return self._handle_enum(field_schema)
+
+        # Handle different schema constructs in order of precedence
+        if "allOf" in field_schema:
+            return self._handle_allof(field_schema, field_name)
+
+        if "anyOf" in field_schema or "oneOf" in field_schema:
+            return self._handle_union_schemas(field_schema, field_name)
+
+        json_type = field_schema.get("type")
+
+        if isinstance(json_type, list):
+            return self._handle_type_union(json_type)
+
+        if json_type == "array":
+            return self._handle_array_type(field_schema, field_name)
+
+        if json_type == "object":
+            return self._handle_object_type(field_schema, field_name)
+
+        # Handle format for string types
+        if json_type == "string" and "format" in field_schema:
+            return self._get_formatted_type(field_schema["format"])
+
+        return self._get_simple_type(json_type)
+
+    def _get_formatted_type(self, format_type: str) -> Type[Any]:
+        """Get Python type for JSON Schema format constraint.
+
+        Args:
+            format_type: JSON Schema format string (date, date-time, email, etc.)
+
+        Returns:
+            Appropriate Python type for the format
+        """
+        format_mapping: dict[str, Type[Any]] = {
+            "date": datetime.date,
+            "date-time": datetime.datetime,
+            "time": datetime.time,
+            "email": str,  # Could use EmailStr from pydantic
+            "uri": str,
+            "uuid": str,  # Could use UUID
+            "hostname": str,
+            "ipv4": str,
+            "ipv6": str,
+        }
+        return format_mapping.get(format_type, str)
+
+    def _handle_enum(self, field_schema: dict[str, Any]) -> Type[Any]:
+        """Handle enum constraint by creating a Literal type.
+
+        Args:
+            field_schema: Schema containing enum values
+
+        Returns:
+            Literal type with enum values
+        """
+        enum_values = field_schema.get("enum", [])
+
+        if not enum_values:
+            return str
+
+        # Filter out None values for the Literal type
+        non_null_values = [v for v in enum_values if v is not None]
+
+        if not non_null_values:
+            return type(None)
+
+        # Create Literal type with enum values
+        # For strings, create Literal["value1", "value2", ...]
+        if all(isinstance(v, str) for v in non_null_values):
+            literal_type = Literal[tuple(non_null_values)]  # type: ignore[valid-type]
+            # If null is in enum, make it optional
+            if None in enum_values:
+                return literal_type | None  # type: ignore[return-value]
+            return literal_type  # type: ignore[return-value]
+
+        # For mixed types or non-strings, fall back to the base type
+        json_type = field_schema.get("type", "string")
+        return self._get_simple_type(json_type)
+
+    def _handle_allof(
+        self, field_schema: dict[str, Any], field_name: str
+    ) -> Type[Any]:
+        """Handle allOf schema composition by merging all schemas.
+
+        Args:
+            field_schema: Schema containing allOf
+            field_name: Name for the generated model
+
+        Returns:
+            Merged Pydantic model or basic type
+        """
+        merged_properties: dict[str, Any] = {}
+        merged_required: list[str] = []
+        found_type: str | None = None
+
+        for sub_schema in field_schema["allOf"]:
+            # Collect type information
+            if sub_schema.get("type"):
+                found_type = sub_schema.get("type")
+
+            # Merge properties
+            if sub_schema.get("properties"):
+                merged_properties.update(sub_schema["properties"])
+
+            # Merge required fields
+            if sub_schema.get("required"):
+                merged_required.extend(sub_schema["required"])
+
+            # Handle nested anyOf/oneOf - merge properties from all variants
+            for union_key in ("anyOf", "oneOf"):
+                if union_key in sub_schema:
+                    for variant in sub_schema[union_key]:
+                        if variant.get("properties"):
+                            # Merge variant properties (will be optional)
+                            for prop_name, prop_schema in variant["properties"].items():
+                                if prop_name not in merged_properties:
+                                    merged_properties[prop_name] = prop_schema
+
+        # If we found properties, create a merged object model
+        if merged_properties:
+            return self._create_pydantic_model(
+                field_name, merged_properties, merged_required
+            )
+
+        # Fallback: return the found type or dict
+        if found_type == "object":
+            return dict
+        elif found_type == "array":
+            return list
+        return dict  # Default for complex allOf
+
+    def _handle_union_schemas(
+        self, field_schema: dict[str, Any], field_name: str
+    ) -> Type[Any]:
+        """Handle anyOf/oneOf union schemas.
+
+        Args:
+            field_schema: Schema containing anyOf or oneOf
+            field_name: Name for nested types
+
+        Returns:
+            Union type combining all options
+        """
+        key = "anyOf" if "anyOf" in field_schema else "oneOf"
+        types: list[Type[Any]] = []
+
+        for option in field_schema[key]:
+            if "const" in option:
+                # For const values, use string type
+                # Could use Literal[option["const"]] for more precision
+                types.append(str)
+            else:
+                types.append(self._json_type_to_python(option, field_name))
+
+        return self._build_union_type(types)
+
+    def _handle_type_union(self, json_types: list[str]) -> Type[Any]:
+        """Handle union types from type arrays.
+
+        Args:
+            json_types: List of JSON Schema type strings
+
+        Returns:
+            Union of corresponding Python types
+        """
+        type_mapping: dict[str, Type[Any]] = {
+            "string": str,
+            "number": float,
+            "integer": int,
+            "boolean": bool,
+            "null": type(None),
+            "array": list,
+            "object": dict,
+        }
+
+        types = [type_mapping.get(t, Any) for t in json_types]
+        return self._build_union_type(types)
+
+    def _handle_array_type(
+        self, field_schema: dict[str, Any], field_name: str
+    ) -> Type[Any]:
+        """Handle array type with typed items.
+
+        Args:
+            field_schema: Schema with type="array"
+            field_name: Name for item types
+
+        Returns:
+            list or list[ItemType]
+        """
+        items_schema = field_schema.get("items")
+        if items_schema:
+            item_type = self._json_type_to_python(items_schema, f"{field_name}Item")
+            return list[item_type]  # type: ignore[valid-type]
+        return list
+
+    def _handle_object_type(
+        self, field_schema: dict[str, Any], field_name: str
+    ) -> Type[Any]:
+        """Handle object type with properties.
+
+        Args:
+            field_schema: Schema with type="object"
+            field_name: Name for the generated model
+
+        Returns:
+            Pydantic model or dict
+        """
+        properties = field_schema.get("properties")
+        if properties:
+            required_fields = field_schema.get("required", [])
+            return self._create_pydantic_model(field_name, properties, required_fields)
+
+        # Object without properties (e.g., additionalProperties only)
+        return dict
+
+    def _create_pydantic_model(
+        self,
+        field_name: str,
+        properties: dict[str, Any],
+        required_fields: list[str],
+    ) -> Type[Any]:
+        """Create a Pydantic model from properties.
+
+        Args:
+            field_name: Base name for the model
+            properties: Property schemas
+            required_fields: List of required property names
+
+        Returns:
+            Dynamically created Pydantic model
+        """
+        model_name = f"Generated_{field_name}_{uuid.uuid4().hex[:8]}"
+        field_definitions: dict[str, Any] = {}
+
+        for prop_name, prop_schema in properties.items():
+            prop_type = self._json_type_to_python(prop_schema, prop_name.title())
+            prop_description = self._build_field_description(prop_schema)
+            is_required = prop_name in required_fields
+
+            if is_required:
+                field_definitions[prop_name] = (
+                    prop_type,
+                    Field(..., description=prop_description),
+                )
+            else:
+                field_definitions[prop_name] = (
+                    prop_type | None,
+                    Field(default=None, description=prop_description),
+                )
+
+        return create_model(model_name, **field_definitions)  # type: ignore[return-value]
+
+    def _build_field_description(self, prop_schema: dict[str, Any]) -> str:
+        """Build a comprehensive field description including constraints.
+
+        Args:
+            prop_schema: Property schema with description and constraints
+
+        Returns:
+            Enhanced description with format, enum, and other constraints
+        """
+        parts: list[str] = []
+
+        # Start with the original description
+        description = prop_schema.get("description", "")
+        if description:
+            parts.append(description)
+
+        # Add format constraint
+        format_type = prop_schema.get("format")
+        if format_type:
+            parts.append(f"Format: {format_type}")
+
+        # Add enum constraint (if not already handled by Literal type)
+        enum_values = prop_schema.get("enum")
+        if enum_values:
+            enum_str = ", ".join(repr(v) for v in enum_values)
+            parts.append(f"Allowed values: [{enum_str}]")
+
+        # Add pattern constraint
+        pattern = prop_schema.get("pattern")
+        if pattern:
+            parts.append(f"Pattern: {pattern}")
+
+        # Add min/max constraints
+        minimum = prop_schema.get("minimum")
+        maximum = prop_schema.get("maximum")
+        if minimum is not None:
+            parts.append(f"Minimum: {minimum}")
+        if maximum is not None:
+            parts.append(f"Maximum: {maximum}")
+
+        min_length = prop_schema.get("minLength")
+        max_length = prop_schema.get("maxLength")
+        if min_length is not None:
+            parts.append(f"Min length: {min_length}")
+        if max_length is not None:
+            parts.append(f"Max length: {max_length}")
+
+        # Add examples if available
+        examples = prop_schema.get("examples")
+        if examples:
+            examples_str = ", ".join(repr(e) for e in examples[:3])  # Limit to 3
+            parts.append(f"Examples: {examples_str}")
+
+        return ". ".join(parts) if parts else ""
+
+    def _get_simple_type(self, json_type: str | None) -> Type[Any]:
+        """Map simple JSON Schema types to Python types.
+
+        Args:
+            json_type: JSON Schema type string
+
+        Returns:
+            Corresponding Python type
+        """
+        simple_type_mapping: dict[str | None, Type[Any]] = {
+            "string": str,
+            "number": float,
+            "integer": int,
+            "boolean": bool,
+            "null": type(None),
+        }
+
+        return simple_type_mapping.get(json_type, Any)
+
+    def _build_union_type(self, types: list[Type[Any]]) -> Type[Any]:
+        """Build a union type from a list of types.
+
+        Args:
+            types: List of Python types to combine
+
+        Returns:
+            Union type or single type if only one unique type
+        """
+        # Remove duplicates while preserving order
+        unique_types = list(dict.fromkeys(types))
+
+        if len(unique_types) == 1:
+            return unique_types[0]
+
+        # Build union using | operator
+        result = unique_types[0]
+        for t in unique_types[1:]:
+            result = result | t
+        return result  # type: ignore[no-any-return]

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

@@ -37,10 +37,9 @@ class BaseAgentAdapter(BaseAgent, ABC):
             tools: Optional list of BaseTool instances to be configured
         """
 
-    @abstractmethod
-    def configure_structured_output(self, task: Any) -> None:
+    def configure_structured_output(self, structured_output: Any) -> None:
         """Configure the structured output for the specific agent implementation.
 
         Args:
-            task: The task object containing output format specifications.
+            structured_output: The structured output to be configured
         """

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

@@ -814,7 +814,6 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                 agent_key=agent_key,
             ),
         )
-        error_event_emitted = False
 
         track_delegation_if_needed(func_name, args_dict, self.task)
 
@@ -897,7 +896,6 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                             error=e,
                         ),
                     )
-                    error_event_emitted = True
         elif max_usage_reached and original_tool:
             # Return error message when max usage limit is reached
             result = f"Tool '{func_name}' has reached its usage limit of {original_tool.max_usage_count} times and cannot be used anymore."
@@ -925,20 +923,20 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                     color="red",
                 )
 
-        if not error_event_emitted:
-            crewai_event_bus.emit(
-                self,
-                event=ToolUsageFinishedEvent(
-                    output=result,
-                    tool_name=func_name,
-                    tool_args=args_dict,
-                    from_agent=self.agent,
-                    from_task=self.task,
-                    agent_key=agent_key,
-                    started_at=started_at,
-                    finished_at=datetime.now(),
-                ),
-            )
+        # Emit tool usage finished event
+        crewai_event_bus.emit(
+            self,
+            event=ToolUsageFinishedEvent(
+                output=result,
+                tool_name=func_name,
+                tool_args=args_dict,
+                from_agent=self.agent,
+                from_task=self.task,
+                agent_key=agent_key,
+                started_at=started_at,
+                finished_at=datetime.now(),
+            ),
+        )
 
         # Append tool result message
         tool_message: LLMMessage = {
@@ -1009,7 +1007,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
             raise
 
         if self.ask_for_human_input:
-            formatted_answer = await self._ahandle_human_feedback(formatted_answer)
+            formatted_answer = self._handle_human_feedback(formatted_answer)
 
         self._create_short_term_memory(formatted_answer)
         self._create_long_term_memory(formatted_answer)
@@ -1508,20 +1506,6 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         provider = get_provider()
         return provider.handle_feedback(formatted_answer, self)
 
-    async def _ahandle_human_feedback(
-        self, formatted_answer: AgentFinish
-    ) -> AgentFinish:
-        """Process human feedback asynchronously via the configured provider.
-
-        Args:
-            formatted_answer: Initial agent result.
-
-        Returns:
-            Final answer after feedback.
-        """
-        provider = get_provider()
-        return await provider.handle_feedback_async(formatted_answer, self)
-
     def _is_training_mode(self) -> bool:
         """Check if training mode is active.
 

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

@@ -1,8 +1,6 @@
-import os
 from typing import Any
 from urllib.parse import urljoin
-
-import httpx
+import os
 import requests
 
 from crewai.cli.config import Settings
@@ -35,11 +33,7 @@ class PlusAPI:
         if settings.org_uuid:
             self.headers["X-Crewai-Organization-Id"] = settings.org_uuid
 
-        self.base_url = (
-            os.getenv("CREWAI_PLUS_URL")
-            or str(settings.enterprise_base_url)
-            or DEFAULT_CREWAI_ENTERPRISE_URL
-        )
+        self.base_url = os.getenv("CREWAI_PLUS_URL") or str(settings.enterprise_base_url) or DEFAULT_CREWAI_ENTERPRISE_URL
 
     def _make_request(
         self, method: str, endpoint: str, **kwargs: Any
@@ -55,10 +49,8 @@ class PlusAPI:
     def get_tool(self, handle: str) -> requests.Response:
         return self._make_request("GET", f"{self.TOOLS_RESOURCE}/{handle}")
 
-    async def get_agent(self, handle: str) -> httpx.Response:
-        url = urljoin(self.base_url, f"{self.AGENTS_RESOURCE}/{handle}")
-        async with httpx.AsyncClient() as client:
-            return await client.get(url, headers=self.headers)
+    def get_agent(self, handle: str) -> requests.Response:
+        return self._make_request("GET", f"{self.AGENTS_RESOURCE}/{handle}")
 
     def publish_tool(
         self,

lib/crewai/src/crewai/context.py

@@ -43,23 +43,3 @@ def platform_context(integration_token: str) -> Generator[None, Any, None]:
         yield
     finally:
         _platform_integration_token.reset(token)
-
-
-_current_task_id: contextvars.ContextVar[str | None] = contextvars.ContextVar(
-    "current_task_id", default=None
-)
-
-
-def set_current_task_id(task_id: str | None) -> contextvars.Token[str | None]:
-    """Set the current task ID in the context. Returns a token for reset."""
-    return _current_task_id.set(task_id)
-
-
-def reset_current_task_id(token: contextvars.Token[str | None]) -> None:
-    """Reset the current task ID to its previous value."""
-    _current_task_id.reset(token)
-
-
-def get_current_task_id() -> str | None:
-    """Get the current task ID from the context."""
-    return _current_task_id.get()

lib/crewai/src/crewai/core/providers/human_input.py

@@ -2,9 +2,7 @@
 
 from __future__ import annotations
 
-import asyncio
 from contextvars import ContextVar, Token
-import sys
 from typing import TYPE_CHECKING, Protocol, runtime_checkable
 
 
@@ -48,21 +46,13 @@ class ExecutorContext(Protocol):
         ...
 
 
-class AsyncExecutorContext(ExecutorContext, Protocol):
-    """Extended context for executors that support async invocation."""
-
-    async def _ainvoke_loop(self) -> AgentFinish:
-        """Invoke the agent loop asynchronously and return the result."""
-        ...
-
-
 @runtime_checkable
 class HumanInputProvider(Protocol):
     """Protocol for human input handling.
 
     Implementations handle the full feedback flow:
     - Sync: prompt user, loop until satisfied
-    - Async: use non-blocking I/O and async invoke loop
+    - Async: raise exception for external handling
     """
 
     def setup_messages(self, context: ExecutorContext) -> bool:
@@ -96,7 +86,7 @@ class HumanInputProvider(Protocol):
         formatted_answer: AgentFinish,
         context: ExecutorContext,
     ) -> AgentFinish:
-        """Handle the full human feedback flow synchronously.
+        """Handle the full human feedback flow.
 
         Args:
             formatted_answer: The agent's current answer.
@@ -110,25 +100,6 @@ class HumanInputProvider(Protocol):
         """
         ...
 
-    async def handle_feedback_async(
-        self,
-        formatted_answer: AgentFinish,
-        context: AsyncExecutorContext,
-    ) -> AgentFinish:
-        """Handle the full human feedback flow asynchronously.
-
-        Uses non-blocking I/O for user prompts and async invoke loop
-        for agent re-execution.
-
-        Args:
-            formatted_answer: The agent's current answer.
-            context: Async executor context for callbacks.
-
-        Returns:
-            The final answer after feedback processing.
-        """
-        ...
-
     @staticmethod
     def _get_output_string(answer: AgentFinish) -> str:
         """Extract output string from answer.
@@ -145,7 +116,7 @@ class HumanInputProvider(Protocol):
 
 
 class SyncHumanInputProvider(HumanInputProvider):
-    """Default human input provider with sync and async support."""
+    """Default synchronous human input via terminal."""
 
     def setup_messages(self, context: ExecutorContext) -> bool:
         """Use standard message setup.
@@ -186,33 +157,6 @@ class SyncHumanInputProvider(HumanInputProvider):
 
         return self._handle_regular_feedback(formatted_answer, feedback, context)
 
-    async def handle_feedback_async(
-        self,
-        formatted_answer: AgentFinish,
-        context: AsyncExecutorContext,
-    ) -> AgentFinish:
-        """Handle feedback asynchronously without blocking the event loop.
-
-        Args:
-            formatted_answer: The agent's current answer.
-            context: Async executor context for callbacks.
-
-        Returns:
-            The final answer after feedback processing.
-        """
-        feedback = await self._prompt_input_async(context.crew)
-
-        if context._is_training_mode():
-            return await self._handle_training_feedback_async(
-                formatted_answer, feedback, context
-            )
-
-        return await self._handle_regular_feedback_async(
-            formatted_answer, feedback, context
-        )
-
-    # ── Sync helpers ──────────────────────────────────────────────────
-
     @staticmethod
     def _handle_training_feedback(
         initial_answer: AgentFinish,
@@ -265,62 +209,6 @@ class SyncHumanInputProvider(HumanInputProvider):
 
         return answer
 
-    # ── Async helpers ─────────────────────────────────────────────────
-
-    @staticmethod
-    async def _handle_training_feedback_async(
-        initial_answer: AgentFinish,
-        feedback: str,
-        context: AsyncExecutorContext,
-    ) -> AgentFinish:
-        """Process training feedback asynchronously (single iteration).
-
-        Args:
-            initial_answer: The agent's initial answer.
-            feedback: Human feedback string.
-            context: Async executor context for callbacks.
-
-        Returns:
-            Improved answer after processing feedback.
-        """
-        context._handle_crew_training_output(initial_answer, feedback)
-        context.messages.append(context._format_feedback_message(feedback))
-        improved_answer = await context._ainvoke_loop()
-        context._handle_crew_training_output(improved_answer)
-        context.ask_for_human_input = False
-        return improved_answer
-
-    async def _handle_regular_feedback_async(
-        self,
-        current_answer: AgentFinish,
-        initial_feedback: str,
-        context: AsyncExecutorContext,
-    ) -> AgentFinish:
-        """Process regular feedback with async iteration loop.
-
-        Args:
-            current_answer: The agent's current answer.
-            initial_feedback: Initial human feedback string.
-            context: Async executor context for callbacks.
-
-        Returns:
-            Final answer after all feedback iterations.
-        """
-        feedback = initial_feedback
-        answer = current_answer
-
-        while context.ask_for_human_input:
-            if feedback.strip() == "":
-                context.ask_for_human_input = False
-            else:
-                context.messages.append(context._format_feedback_message(feedback))
-                answer = await context._ainvoke_loop()
-                feedback = await self._prompt_input_async(context.crew)
-
-        return answer
-
-    # ── I/O ───────────────────────────────────────────────────────────
-
     @staticmethod
     def _prompt_input(crew: Crew | None) -> str:
         """Show rich panel and prompt for input.
@@ -374,79 +262,6 @@ class SyncHumanInputProvider(HumanInputProvider):
         finally:
             formatter.resume_live_updates()
 
-    @staticmethod
-    async def _prompt_input_async(crew: Crew | None) -> str:
-        """Show rich panel and prompt for input without blocking the event loop.
-
-        Args:
-            crew: The crew instance for context.
-
-        Returns:
-            User input string from terminal.
-        """
-        from rich.panel import Panel
-        from rich.text import Text
-
-        from crewai.events.event_listener import event_listener
-
-        formatter = event_listener.formatter
-        formatter.pause_live_updates()
-
-        try:
-            if crew and getattr(crew, "_train", False):
-                prompt_text = (
-                    "TRAINING MODE: Provide feedback to improve the agent's performance.\n\n"
-                    "This will be used to train better versions of the agent.\n"
-                    "Please provide detailed feedback about the result quality and reasoning process."
-                )
-                title = "🎓 Training Feedback Required"
-            else:
-                prompt_text = (
-                    "Provide feedback on the Final Result above.\n\n"
-                    "• If you are happy with the result, simply hit Enter without typing anything.\n"
-                    "• Otherwise, provide specific improvement requests.\n"
-                    "• You can provide multiple rounds of feedback until satisfied."
-                )
-                title = "💬 Human Feedback Required"
-
-            content = Text()
-            content.append(prompt_text, style="yellow")
-
-            prompt_panel = Panel(
-                content,
-                title=title,
-                border_style="yellow",
-                padding=(1, 2),
-            )
-            formatter.console.print(prompt_panel)
-
-            response = await _async_readline()
-            if response.strip() != "":
-                formatter.console.print("\n[cyan]Processing your feedback...[/cyan]")
-            return response
-        finally:
-            formatter.resume_live_updates()
-
-
-async def _async_readline() -> str:
-    """Read a line from stdin using the event loop's native I/O.
-
-    Falls back to asyncio.to_thread on platforms where piping stdin
-    is unsupported.
-
-    Returns:
-        The line read from stdin, with trailing newline stripped.
-    """
-    loop = asyncio.get_running_loop()
-    try:
-        reader = asyncio.StreamReader()
-        protocol = asyncio.StreamReaderProtocol(reader)
-        await loop.connect_read_pipe(lambda: protocol, sys.stdin)
-        raw = await reader.readline()
-        return raw.decode().rstrip("\n")
-    except (OSError, NotImplementedError, ValueError):
-        return await asyncio.to_thread(input)
-
 
 _provider: ContextVar[HumanInputProvider | None] = ContextVar(
     "human_input_provider",

lib/crewai/src/crewai/crew.py

@@ -751,8 +751,6 @@ class Crew(FlowTrackable, BaseModel):
             for after_callback in self.after_kickoff_callbacks:
                 result = after_callback(result)
 
-            result = self._post_kickoff(result)
-
             self.usage_metrics = self.calculate_usage_metrics()
 
             return result
@@ -766,9 +764,6 @@ class Crew(FlowTrackable, BaseModel):
             clear_files(self.id)
             detach(token)
 
-    def _post_kickoff(self, result: CrewOutput) -> CrewOutput:
-        return result
-
     def kickoff_for_each(
         self,
         inputs: list[dict[str, Any]],
@@ -941,8 +936,6 @@ class Crew(FlowTrackable, BaseModel):
             for after_callback in self.after_kickoff_callbacks:
                 result = after_callback(result)
 
-            result = self._post_kickoff(result)
-
             self.usage_metrics = self.calculate_usage_metrics()
 
             return result
@@ -1188,9 +1181,6 @@ class Crew(FlowTrackable, BaseModel):
             self.manager_agent = manager
         manager.crew = self
 
-    def _get_execution_start_index(self, tasks: list[Task]) -> int | None:
-        return None
-
     def _execute_tasks(
         self,
         tasks: list[Task],
@@ -1207,9 +1197,6 @@ class Crew(FlowTrackable, BaseModel):
         Returns:
             CrewOutput: Final output of the crew
         """
-        custom_start = self._get_execution_start_index(tasks)
-        if custom_start is not None:
-            start_index = custom_start
 
         task_outputs: list[TaskOutput] = []
         futures: list[tuple[Task, Future[TaskOutput], int]] = []
@@ -1318,10 +1305,8 @@ class Crew(FlowTrackable, BaseModel):
         if files:
             supported_types: list[str] = []
             if agent and agent.llm and agent.llm.supports_multimodal():
-                provider = (
-                    getattr(agent.llm, "provider", None)
-                    or getattr(agent.llm, "model", None)
-                    or "openai"
+                provider = getattr(agent.llm, "provider", None) or getattr(
+                    agent.llm, "model", "openai"
                 )
                 api = getattr(agent.llm, "api", None)
                 supported_types = get_supported_content_types(provider, api)
@@ -1517,7 +1502,6 @@ class Crew(FlowTrackable, BaseModel):
         final_string_output = final_task_output.raw
         self._finish_execution(final_string_output)
         self.token_usage = self.calculate_usage_metrics()
-        crewai_event_bus.flush()
         crewai_event_bus.emit(
             self,
             CrewKickoffCompletedEvent(
@@ -2027,13 +2011,7 @@ class Crew(FlowTrackable, BaseModel):
     @staticmethod
     def _show_tracing_disabled_message() -> None:
         """Show a message when tracing is disabled."""
-        from crewai.events.listeners.tracing.utils import (
-            has_user_declined_tracing,
-            should_suppress_tracing_messages,
-        )
-
-        if should_suppress_tracing_messages():
-            return
+        from crewai.events.listeners.tracing.utils import has_user_declined_tracing
 
         console = Console()
 

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

@@ -195,7 +195,6 @@ __all__ = [
     "ToolUsageFinishedEvent",
     "ToolUsageStartedEvent",
     "ToolValidateInputErrorEvent",
-    "_extension_exports",
     "crewai_event_bus",
 ]
 
@@ -211,29 +210,14 @@ _AGENT_EVENT_MAPPING = {
     "LiteAgentExecutionStartedEvent": "crewai.events.types.agent_events",
 }
 
-_extension_exports: dict[str, Any] = {}
-
 
 def __getattr__(name: str) -> Any:
-    """Lazy import for agent events and registered extensions."""
+    """Lazy import for agent events to avoid circular imports."""
     if name in _AGENT_EVENT_MAPPING:
         import importlib
 
         module_path = _AGENT_EVENT_MAPPING[name]
         module = importlib.import_module(module_path)
         return getattr(module, name)
-
-    if name in _extension_exports:
-        import importlib
-
-        value = _extension_exports[name]
-        if isinstance(value, str):
-            module_path, _, attr_name = value.rpartition(".")
-            if module_path:
-                module = importlib.import_module(module_path)
-                return getattr(module, attr_name)
-            return importlib.import_module(value)
-        return value
-
     msg = f"module {__name__!r} has no attribute {name!r}"
     raise AttributeError(msg)

lib/crewai/src/crewai/events/base_events.py

@@ -63,7 +63,6 @@ class BaseEvent(BaseModel):
     parent_event_id: str | None = None
     previous_event_id: str | None = None
     triggered_by_event_id: str | None = None
-    started_event_id: str | None = None
     emission_sequence: int | None = None
 
     def to_json(self, exclude: set[str] | None = None) -> Serializable:

lib/crewai/src/crewai/events/event_bus.py

@@ -227,39 +227,6 @@ class CrewAIEventsBus:
 
         return decorator
 
-    def off(
-        self,
-        event_type: type[BaseEvent],
-        handler: Callable[..., Any],
-    ) -> None:
-        """Unregister an event handler for a specific event type.
-
-        Args:
-            event_type: The event class to stop listening for
-            handler: The handler function to unregister
-        """
-        with self._rwlock.w_locked():
-            if event_type in self._sync_handlers:
-                existing_sync = self._sync_handlers[event_type]
-                if handler in existing_sync:
-                    self._sync_handlers[event_type] = existing_sync - {handler}
-                    if not self._sync_handlers[event_type]:
-                        del self._sync_handlers[event_type]
-
-            if event_type in self._async_handlers:
-                existing_async = self._async_handlers[event_type]
-                if handler in existing_async:
-                    self._async_handlers[event_type] = existing_async - {handler}
-                    if not self._async_handlers[event_type]:
-                        del self._async_handlers[event_type]
-
-            if event_type in self._handler_dependencies:
-                self._handler_dependencies[event_type].pop(handler, None)
-                if not self._handler_dependencies[event_type]:
-                    del self._handler_dependencies[event_type]
-
-            self._execution_plan_cache.pop(event_type, None)
-
     def _call_handlers(
         self,
         source: Any,
@@ -407,8 +374,7 @@ class CrewAIEventsBus:
                 if popped is None:
                     handle_empty_pop(event_type_name)
                 else:
-                    popped_event_id, popped_type = popped
-                    event.started_event_id = popped_event_id
+                    _, popped_type = popped
                     expected_start = VALID_EVENT_PAIRS.get(event_type_name)
                     if expected_start and popped_type and popped_type != expected_start:
                         handle_mismatch(event_type_name, popped_type, expected_start)
@@ -570,52 +536,24 @@ class CrewAIEventsBus:
             ...     # Do stuff...
             ... # Handlers are cleared after the context
         """
-        with self._rwlock.r_locked():
-            saved_sync: dict[type[BaseEvent], frozenset[SyncHandler]] = dict(
-                self._sync_handlers
-            )
-            saved_async: dict[type[BaseEvent], frozenset[AsyncHandler]] = dict(
-                self._async_handlers
-            )
-            saved_deps: dict[type[BaseEvent], dict[Handler, list[Depends[Any]]]] = {
-                event_type: dict(handlers)
-                for event_type, handlers in self._handler_dependencies.items()
-            }
-
-        for event_type, sync_handlers in saved_sync.items():
-            for sync_handler in sync_handlers:
-                self.off(event_type, sync_handler)
-
-        for event_type, async_handlers in saved_async.items():
-            for async_handler in async_handlers:
-                self.off(event_type, async_handler)
+        with self._rwlock.w_locked():
+            prev_sync = self._sync_handlers
+            prev_async = self._async_handlers
+            prev_deps = self._handler_dependencies
+            prev_cache = self._execution_plan_cache
+            self._sync_handlers = {}
+            self._async_handlers = {}
+            self._handler_dependencies = {}
+            self._execution_plan_cache = {}
 
         try:
             yield
         finally:
-            with self._rwlock.r_locked():
-                current_sync = dict(self._sync_handlers)
-                current_async = dict(self._async_handlers)
-
-            for event_type, cur_sync in current_sync.items():
-                orig_sync = saved_sync.get(event_type, frozenset())
-                for new_handler in cur_sync - orig_sync:
-                    self.off(event_type, new_handler)
-
-            for event_type, cur_async in current_async.items():
-                orig_async = saved_async.get(event_type, frozenset())
-                for new_async_handler in cur_async - orig_async:
-                    self.off(event_type, new_async_handler)
-
-            for event_type, sync_handlers in saved_sync.items():
-                for sync_handler in sync_handlers:
-                    deps = saved_deps.get(event_type, {}).get(sync_handler)
-                    self._register_handler(event_type, sync_handler, deps)
-
-            for event_type, async_handlers in saved_async.items():
-                for async_handler in async_handlers:
-                    deps = saved_deps.get(event_type, {}).get(async_handler)
-                    self._register_handler(event_type, async_handler, deps)
+            with self._rwlock.w_locked():
+                self._sync_handlers = prev_sync
+                self._async_handlers = prev_async
+                self._handler_dependencies = prev_deps
+                self._execution_plan_cache = prev_cache
 
     def shutdown(self, wait: bool = True) -> None:
         """Gracefully shutdown the event loop and wait for all tasks to finish.

lib/crewai/src/crewai/events/listeners/tracing/trace_listener.py

@@ -797,13 +797,7 @@ class TraceCollectionListener(BaseEventListener):
         from rich.console import Console
         from rich.panel import Panel
 
-        from crewai.events.listeners.tracing.utils import (
-            has_user_declined_tracing,
-            should_suppress_tracing_messages,
-        )
-
-        if should_suppress_tracing_messages():
-            return
+        from crewai.events.listeners.tracing.utils import has_user_declined_tracing
 
         console = Console()
 

lib/crewai/src/crewai/events/listeners/tracing/utils.py

@@ -1,4 +1,3 @@
-from collections.abc import Callable
 from contextvars import ContextVar, Token
 from datetime import datetime
 import getpass
@@ -27,35 +26,6 @@ logger = logging.getLogger(__name__)
 
 _tracing_enabled: ContextVar[bool | None] = ContextVar("_tracing_enabled", default=None)
 
-_first_time_trace_hook: ContextVar[Callable[[], bool] | None] = ContextVar(
-    "_first_time_trace_hook", default=None
-)
-
-_suppress_tracing_messages: ContextVar[bool] = ContextVar(
-    "_suppress_tracing_messages", default=False
-)
-
-
-def set_suppress_tracing_messages(suppress: bool) -> object:
-    """Set whether to suppress tracing-related console messages.
-
-    Args:
-        suppress: True to suppress messages, False to show them.
-
-    Returns:
-        A token that can be used to restore the previous value.
-    """
-    return _suppress_tracing_messages.set(suppress)
-
-
-def should_suppress_tracing_messages() -> bool:
-    """Check if tracing messages should be suppressed.
-
-    Returns:
-        True if messages should be suppressed, False otherwise.
-    """
-    return _suppress_tracing_messages.get()
-
 
 def should_enable_tracing(*, override: bool | None = None) -> bool:
     """Determine if tracing should be enabled.
@@ -437,13 +407,10 @@ def truncate_messages(
 def should_auto_collect_first_time_traces() -> bool:
     """True if we should auto-collect traces for first-time user.
 
+
     Returns:
         True if first-time user AND telemetry not disabled AND tracing not explicitly enabled, False otherwise.
     """
-    hook = _first_time_trace_hook.get()
-    if hook is not None:
-        return hook()
-
     if _is_test_environment():
         return False
 
@@ -465,9 +432,6 @@ def prompt_user_for_trace_viewing(timeout_seconds: int = 20) -> bool:
     if _is_test_environment():
         return False
 
-    if should_suppress_tracing_messages():
-        return False
-
     try:
         import threading
 

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

@@ -16,7 +16,7 @@ class ToolUsageEvent(BaseEvent):
     tool_name: str
     tool_args: dict[str, Any] | str
     tool_class: str | None = None
-    run_attempts: int = 0
+    run_attempts: int | None = None
     delegations: int | None = None
     agent: Any | None = None
     task_name: str | None = None
@@ -26,7 +26,7 @@ class ToolUsageEvent(BaseEvent):
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
-    def __init__(self, **data: Any) -> None:
+    def __init__(self, **data):
         if data.get("from_task"):
             task = data["from_task"]
             data["task_id"] = str(task.id)
@@ -96,10 +96,10 @@ class ToolExecutionErrorEvent(BaseEvent):
     type: str = "tool_execution_error"
     tool_name: str
     tool_args: dict[str, Any]
-    tool_class: Callable[..., Any]
+    tool_class: Callable
     agent: Any | None = None
 
-    def __init__(self, **data: Any) -> None:
+    def __init__(self, **data):
         super().__init__(**data)
         # Set fingerprint data from the agent
         if self.agent and hasattr(self.agent, "fingerprint") and self.agent.fingerprint:

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

@@ -1,4 +1,3 @@
-from contextvars import ContextVar
 import os
 import threading
 from typing import Any, ClassVar, cast
@@ -11,36 +10,6 @@ from rich.text import Text
 from crewai.cli.version import is_newer_version_available
 
 
-_disable_version_check: ContextVar[bool] = ContextVar(
-    "_disable_version_check", default=False
-)
-
-_suppress_console_output: ContextVar[bool] = ContextVar(
-    "_suppress_console_output", default=False
-)
-
-
-def set_suppress_console_output(suppress: bool) -> object:
-    """Set whether to suppress all console output.
-
-    Args:
-        suppress: True to suppress output, False to show it.
-
-    Returns:
-        A token that can be used to restore the previous value.
-    """
-    return _suppress_console_output.set(suppress)
-
-
-def should_suppress_console_output() -> bool:
-    """Check if console output should be suppressed.
-
-    Returns:
-        True if output should be suppressed, False otherwise.
-    """
-    return _suppress_console_output.get()
-
-
 class ConsoleFormatter:
     tool_usage_counts: ClassVar[dict[str, int]] = {}
 
@@ -77,15 +46,9 @@ class ConsoleFormatter:
         if not self.verbose:
             return
 
-        if _disable_version_check.get():
-            return
-
         if os.getenv("CI", "").lower() in ("true", "1"):
             return
 
-        if os.getenv("CREWAI_DISABLE_VERSION_CHECK", "").lower() in ("true", "1"):
-            return
-
         try:
             is_newer, current, latest = is_newer_version_available()
             if is_newer and latest:
@@ -113,12 +76,8 @@ To update, run: uv sync --upgrade-package crewai"""
         from crewai.events.listeners.tracing.utils import (
             has_user_declined_tracing,
             is_tracing_enabled_in_context,
-            should_suppress_tracing_messages,
         )
 
-        if should_suppress_tracing_messages():
-            return
-
         if not is_tracing_enabled_in_context():
             if has_user_declined_tracing():
                 message = """Info: Tracing is disabled.
@@ -170,8 +129,6 @@ To enable tracing, do any one of these:
 
     def print(self, *args: Any, **kwargs: Any) -> None:
         """Print to console. Simplified to only handle panel-based output."""
-        if should_suppress_console_output():
-            return
         # Skip blank lines during streaming
         if len(args) == 0 and self._is_streaming:
             return
@@ -528,9 +485,6 @@ To enable tracing, do any one of these:
         if not self.verbose:
             return
 
-        if should_suppress_console_output():
-            return
-
         self._is_streaming = True
         self._last_stream_call_type = call_type
 

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

@@ -18,7 +18,6 @@ from crewai.agents.parser import (
     AgentFinish,
     OutputParserError,
 )
-from crewai.core.providers.human_input import get_provider
 from crewai.events.event_bus import crewai_event_bus
 from crewai.events.listeners.tracing.utils import (
     is_tracing_enabled_in_context,
@@ -32,8 +31,7 @@ from crewai.events.types.tool_usage_events import (
     ToolUsageFinishedEvent,
     ToolUsageStartedEvent,
 )
-from crewai.flow.flow import Flow, StateProxy, listen, or_, router, start
-from crewai.flow.types import FlowMethodName
+from crewai.flow.flow import Flow, listen, or_, router, start
 from crewai.hooks.llm_hooks import (
     get_after_llm_call_hooks,
     get_before_llm_call_hooks,
@@ -43,12 +41,7 @@ from crewai.hooks.tool_hooks import (
     get_after_tool_call_hooks,
     get_before_tool_call_hooks,
 )
-from crewai.hooks.types import (
-    AfterLLMCallHookCallable,
-    AfterLLMCallHookType,
-    BeforeLLMCallHookCallable,
-    BeforeLLMCallHookType,
-)
+from crewai.hooks.types import AfterLLMCallHookType, BeforeLLMCallHookType
 from crewai.utilities.agent_utils import (
     convert_tools_to_openai_schema,
     enforce_rpm_limit,
@@ -198,12 +191,8 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
 
         self._instance_id = str(uuid4())[:8]
 
-        self.before_llm_call_hooks: list[
-            BeforeLLMCallHookType | BeforeLLMCallHookCallable
-        ] = []
-        self.after_llm_call_hooks: list[
-            AfterLLMCallHookType | AfterLLMCallHookCallable
-        ] = []
+        self.before_llm_call_hooks: list[BeforeLLMCallHookType] = []
+        self.after_llm_call_hooks: list[AfterLLMCallHookType] = []
         self.before_llm_call_hooks.extend(get_before_llm_call_hooks())
         self.after_llm_call_hooks.extend(get_after_llm_call_hooks())
 
@@ -218,71 +207,6 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
             )
         self._state = AgentReActState()
 
-    @property
-    def messages(self) -> list[LLMMessage]:
-        """Delegate to state for ExecutorContext conformance."""
-        return self._state.messages
-
-    @messages.setter
-    def messages(self, value: list[LLMMessage]) -> None:
-        """Delegate to state for ExecutorContext conformance."""
-        if self._flow_initialized and hasattr(self, "_state_lock"):
-            with self._state_lock:
-                self._state.messages = value
-        else:
-            self._state.messages = value
-
-    @property
-    def ask_for_human_input(self) -> bool:
-        """Delegate to state for ExecutorContext conformance."""
-        return self._state.ask_for_human_input
-
-    @ask_for_human_input.setter
-    def ask_for_human_input(self, value: bool) -> None:
-        """Delegate to state for ExecutorContext conformance."""
-        self._state.ask_for_human_input = value
-
-    def _invoke_loop(self) -> AgentFinish:
-        """Invoke the agent loop and return the result.
-
-        Required by ExecutorContext protocol.
-        """
-        self._state.iterations = 0
-        self._state.is_finished = False
-        self._state.current_answer = None
-
-        self.kickoff()
-
-        answer = self._state.current_answer
-        if not isinstance(answer, AgentFinish):
-            raise RuntimeError("Agent loop did not produce a final answer")
-        return answer
-
-    async def _ainvoke_loop(self) -> AgentFinish:
-        """Invoke the agent loop asynchronously and return the result.
-
-        Required by AsyncExecutorContext protocol.
-        """
-        self._state.iterations = 0
-        self._state.is_finished = False
-        self._state.current_answer = None
-
-        await self.akickoff()
-
-        answer = self._state.current_answer
-        if not isinstance(answer, AgentFinish):
-            raise RuntimeError("Agent loop did not produce a final answer")
-        return answer
-
-    def _format_feedback_message(self, feedback: str) -> LLMMessage:
-        """Format feedback as a message for the LLM.
-
-        Required by ExecutorContext protocol.
-        """
-        return format_message_for_llm(
-            self._i18n.slice("feedback_instructions").format(feedback=feedback)
-        )
-
     def _ensure_flow_initialized(self) -> None:
         """Ensure Flow.__init__() has been called.
 
@@ -374,10 +298,18 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
         Flow initialization is deferred to prevent event emission during agent setup.
         Returns the temporary state until invoke() is called.
         """
-        if self._flow_initialized and hasattr(self, "_state_lock"):
-            return StateProxy(self._state, self._state_lock)  # type: ignore[return-value]
         return self._state
 
+    @property
+    def messages(self) -> list[LLMMessage]:
+        """Compatibility property for mixin - returns state messages."""
+        return self._state.messages
+
+    @messages.setter
+    def messages(self, value: list[LLMMessage]) -> None:
+        """Set state messages."""
+        self._state.messages = value
+
     @property
     def iterations(self) -> int:
         """Compatibility property for mixin - returns state iterations."""
@@ -484,14 +416,15 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
             raise
 
     @listen("continue_reasoning_native")
-    def call_llm_native_tools(self) -> None:
+    def call_llm_native_tools(
+        self,
+    ) -> Literal["native_tool_calls", "native_finished", "context_error"]:
         """Execute LLM call with native function calling.
 
         Always calls the LLM so it can read reflection prompts and decide
         whether to provide a final answer or request more tools.
 
-        Note: This is a listener, not a router. The route_native_tool_result
-        router fires after this to determine the next step based on state.
+        Returns routing decision based on whether tool calls or final answer.
         """
         try:
             # Clear pending tools - LLM will decide what to do next after reading
@@ -521,7 +454,8 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
             if isinstance(answer, list) and answer and self._is_tool_call_list(answer):
                 # Store tool calls for sequential processing
                 self.state.pending_tool_calls = list(answer)
-                return  # Router will check pending_tool_calls
+
+                return "native_tool_calls"
 
             if isinstance(answer, BaseModel):
                 self.state.current_answer = AgentFinish(
@@ -531,7 +465,7 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
                 )
                 self._invoke_step_callback(self.state.current_answer)
                 self._append_message_to_state(answer.model_dump_json())
-                return  # Router will check current_answer
+                return "native_finished"
 
             # Text response - this is the final answer
             if isinstance(answer, str):
@@ -542,7 +476,8 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
                 )
                 self._invoke_step_callback(self.state.current_answer)
                 self._append_message_to_state(answer)
-                return  # Router will check current_answer
+
+                return "native_finished"
 
             # Unexpected response type, treat as final answer
             self.state.current_answer = AgentFinish(
@@ -552,12 +487,13 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
             )
             self._invoke_step_callback(self.state.current_answer)
             self._append_message_to_state(str(answer))
-            # Router will check current_answer
+
+            return "native_finished"
 
         except Exception as e:
             if is_context_length_exceeded(e):
                 self._last_context_error = e
-                return  # Router will check _last_context_error
+                return "context_error"
             if e.__class__.__module__.startswith("litellm"):
                 raise e
             handle_unknown_error(self._printer, e, verbose=self.agent.verbose)
@@ -570,22 +506,6 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
             return "execute_tool"
         return "agent_finished"
 
-    @router(call_llm_native_tools)
-    def route_native_tool_result(
-        self,
-    ) -> Literal["native_tool_calls", "native_finished", "context_error"]:
-        """Route based on LLM response for native tool calling.
-
-        Checks state set by call_llm_native_tools to determine next step.
-        This router is needed because only router return values trigger
-        downstream listeners.
-        """
-        if self._last_context_error is not None:
-            return "context_error"
-        if self.state.pending_tool_calls:
-            return "native_tool_calls"
-        return "native_finished"
-
     @listen("execute_tool")
     def execute_tool_action(self) -> Literal["tool_completed", "tool_result_is_final"]:
         """Execute the tool action and handle the result."""
@@ -769,7 +689,6 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
                     agent_key=agent_key,
                 ),
             )
-            error_event_emitted = False
 
             track_delegation_if_needed(func_name, args_dict, self.task)
 
@@ -845,7 +764,6 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
                                 error=e,
                             ),
                         )
-                        error_event_emitted = True
             elif max_usage_reached and original_tool:
                 # Return error message when max usage limit is reached
                 result = f"Tool '{func_name}' has reached its usage limit of {original_tool.max_usage_count} times and cannot be used anymore."
@@ -874,20 +792,20 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
                         color="red",
                     )
 
-            if not error_event_emitted:
-                crewai_event_bus.emit(
-                    self,
-                    event=ToolUsageFinishedEvent(
-                        output=result,
-                        tool_name=func_name,
-                        tool_args=args_dict,
-                        from_agent=self.agent,
-                        from_task=self.task,
-                        agent_key=agent_key,
-                        started_at=started_at,
-                        finished_at=datetime.now(),
-                    ),
-                )
+            # Emit tool usage finished event
+            crewai_event_bus.emit(
+                self,
+                event=ToolUsageFinishedEvent(
+                    output=result,
+                    tool_name=func_name,
+                    tool_args=args_dict,
+                    from_agent=self.agent,
+                    from_task=self.task,
+                    agent_key=agent_key,
+                    started_at=started_at,
+                    finished_at=datetime.now(),
+                ),
+            )
 
             # Append tool result message
             tool_message: LLMMessage = {
@@ -943,11 +861,9 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
         self.state.iterations += 1
         return "initialized"
 
-    @listen(or_("initialized", "tool_completed", "native_tool_completed"))
+    @listen("initialized")
     def continue_iteration(self) -> Literal["check_iteration"]:
         """Bridge listener that connects iteration loop back to iteration check."""
-        if self._flow_initialized:
-            self._discard_or_listener(FlowMethodName("continue_iteration"))
         return "check_iteration"
 
     @router(or_(initialize_reasoning, continue_iteration))
@@ -1189,7 +1105,7 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
                 )
 
             if self.state.ask_for_human_input:
-                formatted_answer = await self._ahandle_human_feedback(formatted_answer)
+                formatted_answer = self._handle_human_feedback(formatted_answer)
 
             self._create_short_term_memory(formatted_answer)
             self._create_long_term_memory(formatted_answer)
@@ -1403,22 +1319,17 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
         Returns:
             Final answer after feedback.
         """
-        provider = get_provider()
-        return provider.handle_feedback(formatted_answer, self)
+        output_str = (
+            str(formatted_answer.output)
+            if isinstance(formatted_answer.output, BaseModel)
+            else formatted_answer.output
+        )
+        human_feedback = self._ask_human_input(output_str)
 
-    async def _ahandle_human_feedback(
-        self, formatted_answer: AgentFinish
-    ) -> AgentFinish:
-        """Process human feedback asynchronously and refine answer.
+        if self._is_training_mode():
+            return self._handle_training_feedback(formatted_answer, human_feedback)
 
-        Args:
-            formatted_answer: Initial agent result.
-
-        Returns:
-            Final answer after feedback.
-        """
-        provider = get_provider()
-        return await provider.handle_feedback_async(formatted_answer, self)
+        return self._handle_regular_feedback(formatted_answer, human_feedback)
 
     def _is_training_mode(self) -> bool:
         """Check if training mode is active.
@@ -1428,6 +1339,101 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
         """
         return bool(self.crew and self.crew._train)
 
+    def _handle_training_feedback(
+        self, initial_answer: AgentFinish, feedback: str
+    ) -> AgentFinish:
+        """Process training feedback and generate improved answer.
+
+        Args:
+            initial_answer: Initial agent output.
+            feedback: Training feedback.
+
+        Returns:
+            Improved answer.
+        """
+        self._handle_crew_training_output(initial_answer, feedback)
+        self.state.messages.append(
+            format_message_for_llm(
+                self._i18n.slice("feedback_instructions").format(feedback=feedback)
+            )
+        )
+
+        # Re-run flow for improved answer
+        self.state.iterations = 0
+        self.state.is_finished = False
+        self.state.current_answer = None
+
+        self.kickoff()
+
+        # Get improved answer from state
+        improved_answer = self.state.current_answer
+        if not isinstance(improved_answer, AgentFinish):
+            raise RuntimeError(
+                "Training feedback iteration did not produce final answer"
+            )
+
+        self._handle_crew_training_output(improved_answer)
+        self.state.ask_for_human_input = False
+        return improved_answer
+
+    def _handle_regular_feedback(
+        self, current_answer: AgentFinish, initial_feedback: str
+    ) -> AgentFinish:
+        """Process regular feedback iteratively until user is satisfied.
+
+        Args:
+            current_answer: Current agent output.
+            initial_feedback: Initial user feedback.
+
+        Returns:
+            Final answer after iterations.
+        """
+        feedback = initial_feedback
+        answer = current_answer
+
+        while self.state.ask_for_human_input:
+            if feedback.strip() == "":
+                self.state.ask_for_human_input = False
+            else:
+                answer = self._process_feedback_iteration(feedback)
+                output_str = (
+                    str(answer.output)
+                    if isinstance(answer.output, BaseModel)
+                    else answer.output
+                )
+                feedback = self._ask_human_input(output_str)
+
+        return answer
+
+    def _process_feedback_iteration(self, feedback: str) -> AgentFinish:
+        """Process a single feedback iteration and generate updated response.
+
+        Args:
+            feedback: User feedback.
+
+        Returns:
+            Updated agent response.
+        """
+        self.state.messages.append(
+            format_message_for_llm(
+                self._i18n.slice("feedback_instructions").format(feedback=feedback)
+            )
+        )
+
+        # Re-run flow
+        self.state.iterations = 0
+        self.state.is_finished = False
+        self.state.current_answer = None
+
+        self.kickoff()
+
+        # Get answer from state
+        answer = self.state.current_answer
+        if not isinstance(answer, AgentFinish):
+            raise RuntimeError("Feedback iteration did not produce final answer")
+
+        return answer
+
     @classmethod
     def __get_pydantic_core_schema__(
         cls, _source_type: Any, _handler: GetCoreSchemaHandler

lib/crewai/src/crewai/flow/async_feedback/__init__.py

@@ -28,8 +28,6 @@ Example:
     ```
 """
 
-from typing import Any
-
 from crewai.flow.async_feedback.providers import ConsoleProvider
 from crewai.flow.async_feedback.types import (
     HumanFeedbackPending,
@@ -43,15 +41,4 @@ __all__ = [
     "HumanFeedbackPending",
     "HumanFeedbackProvider",
     "PendingFeedbackContext",
-    "_extension_exports",
 ]
-
-_extension_exports: dict[str, Any] = {}
-
-
-def __getattr__(name: str) -> Any:
-    """Support extensions via dynamic attribute lookup."""
-    if name in _extension_exports:
-        return _extension_exports[name]
-    msg = f"module {__name__!r} has no attribute {name!r}"
-    raise AttributeError(msg)

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

@@ -7,14 +7,7 @@ for building event-driven workflows with conditional execution and routing.
 from __future__ import annotations
 
 import asyncio
-from collections.abc import (
-    Callable,
-    ItemsView,
-    Iterator,
-    KeysView,
-    Sequence,
-    ValuesView,
-)
+from collections.abc import Callable, Sequence
 from concurrent.futures import Future
 import copy
 import inspect
@@ -52,7 +45,6 @@ from crewai.events.listeners.tracing.utils import (
     has_user_declined_tracing,
     set_tracing_enabled,
     should_enable_tracing,
-    should_suppress_tracing_messages,
 )
 from crewai.events.types.flow_events import (
     FlowCreatedEvent,
@@ -416,132 +408,6 @@ def and_(*conditions: str | FlowCondition | Callable[..., Any]) -> FlowCondition
     return {"type": AND_CONDITION, "conditions": processed_conditions}
 
 
-class LockedListProxy(Generic[T]):
-    """Thread-safe proxy for list operations.
-
-    Wraps a list and uses a lock for all mutating operations.
-    """
-
-    def __init__(self, lst: list[T], lock: threading.Lock) -> None:
-        self._list = lst
-        self._lock = lock
-
-    def append(self, item: T) -> None:
-        with self._lock:
-            self._list.append(item)
-
-    def extend(self, items: list[T]) -> None:
-        with self._lock:
-            self._list.extend(items)
-
-    def insert(self, index: int, item: T) -> None:
-        with self._lock:
-            self._list.insert(index, item)
-
-    def remove(self, item: T) -> None:
-        with self._lock:
-            self._list.remove(item)
-
-    def pop(self, index: int = -1) -> T:
-        with self._lock:
-            return self._list.pop(index)
-
-    def clear(self) -> None:
-        with self._lock:
-            self._list.clear()
-
-    def __setitem__(self, index: int, value: T) -> None:
-        with self._lock:
-            self._list[index] = value
-
-    def __delitem__(self, index: int) -> None:
-        with self._lock:
-            del self._list[index]
-
-    def __getitem__(self, index: int) -> T:
-        return self._list[index]
-
-    def __len__(self) -> int:
-        return len(self._list)
-
-    def __iter__(self) -> Iterator[T]:
-        return iter(self._list)
-
-    def __contains__(self, item: object) -> bool:
-        return item in self._list
-
-    def __repr__(self) -> str:
-        return repr(self._list)
-
-    def __bool__(self) -> bool:
-        return bool(self._list)
-
-
-class LockedDictProxy(Generic[T]):
-    """Thread-safe proxy for dict operations.
-
-    Wraps a dict and uses a lock for all mutating operations.
-    """
-
-    def __init__(self, d: dict[str, T], lock: threading.Lock) -> None:
-        self._dict = d
-        self._lock = lock
-
-    def __setitem__(self, key: str, value: T) -> None:
-        with self._lock:
-            self._dict[key] = value
-
-    def __delitem__(self, key: str) -> None:
-        with self._lock:
-            del self._dict[key]
-
-    def pop(self, key: str, *default: T) -> T:
-        with self._lock:
-            return self._dict.pop(key, *default)
-
-    def update(self, other: dict[str, T]) -> None:
-        with self._lock:
-            self._dict.update(other)
-
-    def clear(self) -> None:
-        with self._lock:
-            self._dict.clear()
-
-    def setdefault(self, key: str, default: T) -> T:
-        with self._lock:
-            return self._dict.setdefault(key, default)
-
-    def __getitem__(self, key: str) -> T:
-        return self._dict[key]
-
-    def __len__(self) -> int:
-        return len(self._dict)
-
-    def __iter__(self) -> Iterator[str]:
-        return iter(self._dict)
-
-    def __contains__(self, key: object) -> bool:
-        return key in self._dict
-
-    def keys(self) -> KeysView[str]:
-        return self._dict.keys()
-
-    def values(self) -> ValuesView[T]:
-        return self._dict.values()
-
-    def items(self) -> ItemsView[str, T]:
-        return self._dict.items()
-
-    def get(self, key: str, default: T | None = None) -> T | None:
-        return self._dict.get(key, default)
-
-    def __repr__(self) -> str:
-        return repr(self._dict)
-
-    def __bool__(self) -> bool:
-        return bool(self._dict)
-
-
 class StateProxy(Generic[T]):
     """Proxy that provides thread-safe access to flow state.
 
@@ -556,13 +422,7 @@ class StateProxy(Generic[T]):
         object.__setattr__(self, "_proxy_lock", lock)
 
     def __getattr__(self, name: str) -> Any:
-        value = getattr(object.__getattribute__(self, "_proxy_state"), name)
-        lock = object.__getattribute__(self, "_proxy_lock")
-        if isinstance(value, list):
-            return LockedListProxy(value, lock)
-        if isinstance(value, dict):
-            return LockedDictProxy(value, lock)
-        return value
+        return getattr(object.__getattribute__(self, "_proxy_state"), name)
 
     def __setattr__(self, name: str, value: Any) -> None:
         if name in ("_proxy_state", "_proxy_lock"):
@@ -1732,6 +1592,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
                 reset_emission_counter()
                 reset_last_event_id()
 
+            # Emit FlowStartedEvent and log the start of the flow.
             if not self.suppress_flow_events:
                 future = crewai_event_bus.emit(
                     self,
@@ -1742,10 +1603,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
                     ),
                 )
                 if future:
-                    try:
-                        await asyncio.wrap_future(future)
-                    except Exception:
-                        logger.warning("FlowStartedEvent handler failed", exc_info=True)
+                    self._event_futures.append(future)
                 self._log_flow_event(
                     f"Flow started with ID: {self.flow_id}", color="bold magenta"
                 )
@@ -1837,12 +1695,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
 
             final_output = self._method_outputs[-1] if self._method_outputs else None
 
-            if self._event_futures:
-                await asyncio.gather(
-                    *[asyncio.wrap_future(f) for f in self._event_futures]
-                )
-                self._event_futures.clear()
-
             if not self.suppress_flow_events:
                 future = crewai_event_bus.emit(
                     self,
@@ -1854,12 +1706,13 @@ class Flow(Generic[T], metaclass=FlowMeta):
                     ),
                 )
                 if future:
-                    try:
-                        await asyncio.wrap_future(future)
-                    except Exception:
-                        logger.warning(
-                            "FlowFinishedEvent handler failed", exc_info=True
-                        )
+                    self._event_futures.append(future)
+
+            if self._event_futures:
+                await asyncio.gather(
+                    *[asyncio.wrap_future(f) for f in self._event_futures]
+                )
+                self._event_futures.clear()
 
             if not self.suppress_flow_events:
                 trace_listener = TraceCollectionListener()
@@ -1934,14 +1787,40 @@ class Flow(Generic[T], metaclass=FlowMeta):
             await self._execute_listeners(start_method_name, result, finished_event_id)
             # Then execute listeners for the router result (e.g., "approved")
             router_result_trigger = FlowMethodName(str(result))
-            listener_result = (
-                self.last_human_feedback
-                if self.last_human_feedback is not None
-                else result
-            )
-            await self._execute_listeners(
-                router_result_trigger, listener_result, finished_event_id
+            listeners_for_result = self._find_triggered_methods(
+                router_result_trigger, router_only=False
             )
+            if listeners_for_result:
+                # Pass the HumanFeedbackResult if available
+                listener_result = (
+                    self.last_human_feedback
+                    if self.last_human_feedback is not None
+                    else result
+                )
+                racing_group = self._get_racing_group_for_listeners(
+                    listeners_for_result
+                )
+                if racing_group:
+                    racing_members, _ = racing_group
+                    other_listeners = [
+                        name
+                        for name in listeners_for_result
+                        if name not in racing_members
+                    ]
+                    await self._execute_racing_listeners(
+                        racing_members,
+                        other_listeners,
+                        listener_result,
+                        finished_event_id,
+                    )
+                else:
+                    tasks = [
+                        self._execute_single_listener(
+                            listener_name, listener_result, finished_event_id
+                        )
+                        for listener_name in listeners_for_result
+                    ]
+                    await asyncio.gather(*tasks)
         else:
             await self._execute_listeners(start_method_name, result, finished_event_id)
 
@@ -2147,14 +2026,15 @@ class Flow(Generic[T], metaclass=FlowMeta):
                 router_input = router_result_to_feedback.get(
                     str(current_trigger), current_result
                 )
-                (
-                    router_result,
-                    current_triggering_event_id,
-                ) = await self._execute_single_listener(
+                current_triggering_event_id = await self._execute_single_listener(
                     router_name, router_input, current_triggering_event_id
                 )
+                # After executing router, the router's result is the path
+                router_result = (
+                    self._method_outputs[-1] if self._method_outputs else None
+                )
                 if router_result:  # Only add non-None results
-                    router_results.append(FlowMethodName(str(router_result)))
+                    router_results.append(router_result)
                     # If this was a human_feedback router, map the outcome to the feedback
                     if self.last_human_feedback is not None:
                         router_result_to_feedback[str(router_result)] = (
@@ -2194,14 +2074,12 @@ class Flow(Generic[T], metaclass=FlowMeta):
                             racing_members,
                             other_listeners,
                             listener_result,
-                            current_triggering_event_id,
+                            triggering_event_id,
                         )
                     else:
                         tasks = [
                             self._execute_single_listener(
-                                listener_name,
-                                listener_result,
-                                current_triggering_event_id,
+                                listener_name, listener_result, triggering_event_id
                             )
                             for listener_name in listeners_triggered
                         ]
@@ -2384,7 +2262,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
         listener_name: FlowMethodName,
         result: Any,
         triggering_event_id: str | None = None,
-    ) -> tuple[Any, str | None]:
+    ) -> str | None:
         """Executes a single listener method with proper event handling.
 
         This internal method manages the execution of an individual listener,
@@ -2397,9 +2275,8 @@ class Flow(Generic[T], metaclass=FlowMeta):
                 used for causal chain tracking.
 
         Returns:
-            A tuple of (listener_result, event_id) where listener_result is the return
-            value of the listener method and event_id is the MethodExecutionFinishedEvent
-            id, or (None, None) if skipped during resumption.
+            The event_id of the MethodExecutionFinishedEvent emitted by this listener,
+            or None if events are suppressed.
 
         Note:
             - Inspects method signature to determine if it accepts the trigger result
@@ -2425,7 +2302,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
                         ):
                             # This conditional start was executed, continue its chain
                             await self._execute_start_method(start_method_name)
-                return (None, None)
+                return None
             # For cyclic flows, clear from completed to allow re-execution
             self._completed_methods.discard(listener_name)
             # Also clear from fired OR listeners for cyclic flows
@@ -2463,7 +2340,46 @@ class Flow(Generic[T], metaclass=FlowMeta):
                 listener_name, listener_result, finished_event_id
             )
 
-            return (listener_result, finished_event_id)
+            # If this listener is also a router (e.g., has @human_feedback with emit),
+            # we need to trigger listeners for the router result as well
+            if listener_name in self._routers and listener_result is not None:
+                router_result_trigger = FlowMethodName(str(listener_result))
+                listeners_for_result = self._find_triggered_methods(
+                    router_result_trigger, router_only=False
+                )
+                if listeners_for_result:
+                    # Pass the HumanFeedbackResult if available
+                    feedback_result = (
+                        self.last_human_feedback
+                        if self.last_human_feedback is not None
+                        else listener_result
+                    )
+                    racing_group = self._get_racing_group_for_listeners(
+                        listeners_for_result
+                    )
+                    if racing_group:
+                        racing_members, _ = racing_group
+                        other_listeners = [
+                            name
+                            for name in listeners_for_result
+                            if name not in racing_members
+                        ]
+                        await self._execute_racing_listeners(
+                            racing_members,
+                            other_listeners,
+                            feedback_result,
+                            finished_event_id,
+                        )
+                    else:
+                        tasks = [
+                            self._execute_single_listener(
+                                name, feedback_result, finished_event_id
+                            )
+                            for name in listeners_for_result
+                        ]
+                        await asyncio.gather(*tasks)
+
+            return finished_event_id
 
         except Exception as e:
             # Don't log HumanFeedbackPending as an error - it's expected control flow
@@ -2710,8 +2626,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
     @staticmethod
     def _show_tracing_disabled_message() -> None:
         """Show a message when tracing is disabled."""
-        if should_suppress_tracing_messages():
-            return
 
         console = Console()
 

lib/crewai/src/crewai/hooks/llm_hooks.py

@@ -3,12 +3,7 @@ from __future__ import annotations
 from typing import TYPE_CHECKING, Any, cast
 
 from crewai.events.event_listener import event_listener
-from crewai.hooks.types import (
-    AfterLLMCallHookCallable,
-    AfterLLMCallHookType,
-    BeforeLLMCallHookCallable,
-    BeforeLLMCallHookType,
-)
+from crewai.hooks.types import AfterLLMCallHookType, BeforeLLMCallHookType
 from crewai.utilities.printer import Printer
 
 
@@ -154,12 +149,12 @@ class LLMCallHookContext:
             event_listener.formatter.resume_live_updates()
 
 
-_before_llm_call_hooks: list[BeforeLLMCallHookType | BeforeLLMCallHookCallable] = []
-_after_llm_call_hooks: list[AfterLLMCallHookType | AfterLLMCallHookCallable] = []
+_before_llm_call_hooks: list[BeforeLLMCallHookType] = []
+_after_llm_call_hooks: list[AfterLLMCallHookType] = []
 
 
 def register_before_llm_call_hook(
-    hook: BeforeLLMCallHookType | BeforeLLMCallHookCallable,
+    hook: BeforeLLMCallHookType,
 ) -> None:
     """Register a global before_llm_call hook.
 
@@ -195,7 +190,7 @@ def register_before_llm_call_hook(
 
 
 def register_after_llm_call_hook(
-    hook: AfterLLMCallHookType | AfterLLMCallHookCallable,
+    hook: AfterLLMCallHookType,
 ) -> None:
     """Register a global after_llm_call hook.
 
@@ -222,9 +217,7 @@ def register_after_llm_call_hook(
     _after_llm_call_hooks.append(hook)
 
 
-def get_before_llm_call_hooks() -> list[
-    BeforeLLMCallHookType | BeforeLLMCallHookCallable
-]:
+def get_before_llm_call_hooks() -> list[BeforeLLMCallHookType]:
     """Get all registered global before_llm_call hooks.
 
     Returns:
@@ -233,7 +226,7 @@ def get_before_llm_call_hooks() -> list[
     return _before_llm_call_hooks.copy()
 
 
-def get_after_llm_call_hooks() -> list[AfterLLMCallHookType | AfterLLMCallHookCallable]:
+def get_after_llm_call_hooks() -> list[AfterLLMCallHookType]:
     """Get all registered global after_llm_call hooks.
 
     Returns:
@@ -243,7 +236,7 @@ def get_after_llm_call_hooks() -> list[AfterLLMCallHookType | AfterLLMCallHookCa
 
 
 def unregister_before_llm_call_hook(
-    hook: BeforeLLMCallHookType | BeforeLLMCallHookCallable,
+    hook: BeforeLLMCallHookType,
 ) -> bool:
     """Unregister a specific global before_llm_call hook.
 
@@ -269,7 +262,7 @@ def unregister_before_llm_call_hook(
 
 
 def unregister_after_llm_call_hook(
-    hook: AfterLLMCallHookType | AfterLLMCallHookCallable,
+    hook: AfterLLMCallHookType,
 ) -> bool:
     """Unregister a specific global after_llm_call hook.
 

lib/crewai/src/crewai/hooks/tool_hooks.py

@@ -3,12 +3,7 @@ from __future__ import annotations
 from typing import TYPE_CHECKING, Any
 
 from crewai.events.event_listener import event_listener
-from crewai.hooks.types import (
-    AfterToolCallHookCallable,
-    AfterToolCallHookType,
-    BeforeToolCallHookCallable,
-    BeforeToolCallHookType,
-)
+from crewai.hooks.types import AfterToolCallHookType, BeforeToolCallHookType
 from crewai.utilities.printer import Printer
 
 
@@ -117,12 +112,12 @@ class ToolCallHookContext:
 
 
 # Global hook registries
-_before_tool_call_hooks: list[BeforeToolCallHookType | BeforeToolCallHookCallable] = []
-_after_tool_call_hooks: list[AfterToolCallHookType | AfterToolCallHookCallable] = []
+_before_tool_call_hooks: list[BeforeToolCallHookType] = []
+_after_tool_call_hooks: list[AfterToolCallHookType] = []
 
 
 def register_before_tool_call_hook(
-    hook: BeforeToolCallHookType | BeforeToolCallHookCallable,
+    hook: BeforeToolCallHookType,
 ) -> None:
     """Register a global before_tool_call hook.
 
@@ -159,7 +154,7 @@ def register_before_tool_call_hook(
 
 
 def register_after_tool_call_hook(
-    hook: AfterToolCallHookType | AfterToolCallHookCallable,
+    hook: AfterToolCallHookType,
 ) -> None:
     """Register a global after_tool_call hook.
 
@@ -189,9 +184,7 @@ def register_after_tool_call_hook(
     _after_tool_call_hooks.append(hook)
 
 
-def get_before_tool_call_hooks() -> list[
-    BeforeToolCallHookType | BeforeToolCallHookCallable
-]:
+def get_before_tool_call_hooks() -> list[BeforeToolCallHookType]:
     """Get all registered global before_tool_call hooks.
 
     Returns:
@@ -200,9 +193,7 @@ def get_before_tool_call_hooks() -> list[
     return _before_tool_call_hooks.copy()
 
 
-def get_after_tool_call_hooks() -> list[
-    AfterToolCallHookType | AfterToolCallHookCallable
-]:
+def get_after_tool_call_hooks() -> list[AfterToolCallHookType]:
     """Get all registered global after_tool_call hooks.
 
     Returns:
@@ -212,7 +203,7 @@ def get_after_tool_call_hooks() -> list[
 
 
 def unregister_before_tool_call_hook(
-    hook: BeforeToolCallHookType | BeforeToolCallHookCallable,
+    hook: BeforeToolCallHookType,
 ) -> bool:
     """Unregister a specific global before_tool_call hook.
 
@@ -238,7 +229,7 @@ def unregister_before_tool_call_hook(
 
 
 def unregister_after_tool_call_hook(
-    hook: AfterToolCallHookType | AfterToolCallHookCallable,
+    hook: AfterToolCallHookType,
 ) -> bool:
     """Unregister a specific global after_tool_call hook.
 

lib/crewai/src/crewai/knowledge/source/utils/__init__.py

@@ -1 +0,0 @@
-"""Knowledge source utilities."""

lib/crewai/src/crewai/knowledge/source/utils/source_helper.py

@@ -1,70 +0,0 @@
-"""Helper utilities for knowledge sources."""
-
-from typing import Any, ClassVar
-
-from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
-from crewai.knowledge.source.csv_knowledge_source import CSVKnowledgeSource
-from crewai.knowledge.source.excel_knowledge_source import ExcelKnowledgeSource
-from crewai.knowledge.source.json_knowledge_source import JSONKnowledgeSource
-from crewai.knowledge.source.pdf_knowledge_source import PDFKnowledgeSource
-from crewai.knowledge.source.text_file_knowledge_source import TextFileKnowledgeSource
-
-
-class SourceHelper:
-    """Helper class for creating and managing knowledge sources."""
-
-    SUPPORTED_FILE_TYPES: ClassVar[list[str]] = [
-        ".csv",
-        ".pdf",
-        ".json",
-        ".txt",
-        ".xlsx",
-        ".xls",
-    ]
-
-    _FILE_TYPE_MAP: ClassVar[dict[str, type[BaseKnowledgeSource]]] = {
-        ".csv": CSVKnowledgeSource,
-        ".pdf": PDFKnowledgeSource,
-        ".json": JSONKnowledgeSource,
-        ".txt": TextFileKnowledgeSource,
-        ".xlsx": ExcelKnowledgeSource,
-        ".xls": ExcelKnowledgeSource,
-    }
-
-    @classmethod
-    def is_supported_file(cls, file_path: str) -> bool:
-        """Check if a file type is supported.
-
-        Args:
-            file_path: Path to the file.
-
-        Returns:
-            True if the file type is supported.
-        """
-        return file_path.lower().endswith(tuple(cls.SUPPORTED_FILE_TYPES))
-
-    @classmethod
-    def get_source(
-        cls, file_path: str, metadata: dict[str, Any] | None = None
-    ) -> BaseKnowledgeSource:
-        """Create appropriate KnowledgeSource based on file extension.
-
-        Args:
-            file_path: Path to the file.
-            metadata: Optional metadata to attach to the source.
-
-        Returns:
-            The appropriate KnowledgeSource instance.
-
-        Raises:
-            ValueError: If the file type is not supported.
-        """
-        if not cls.is_supported_file(file_path):
-            raise ValueError(f"Unsupported file type: {file_path}")
-
-        lower_path = file_path.lower()
-        for ext, source_cls in cls._FILE_TYPE_MAP.items():
-            if lower_path.endswith(ext):
-                return source_cls(file_path=[file_path], metadata=metadata)
-
-        raise ValueError(f"Unsupported file type: {file_path}")

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

@@ -420,6 +420,7 @@ class MCPClient:
         return [
             {
                 "name": sanitize_tool_name(tool.name),
+                "original_name": tool.name,
                 "description": getattr(tool, "description", ""),
                 "inputSchema": getattr(tool, "inputSchema", {}),
             }

lib/crewai/src/crewai/project/crew_base.py

@@ -27,8 +27,6 @@ if TYPE_CHECKING:
     from crewai import Agent, Task
     from crewai.agents.cache.cache_handler import CacheHandler
     from crewai.crews.crew_output import CrewOutput
-    from crewai.hooks.llm_hooks import LLMCallHookContext
-    from crewai.hooks.tool_hooks import ToolCallHookContext
     from crewai.project.wrappers import (
         CrewInstance,
         OutputJsonClass,
@@ -36,8 +34,6 @@ if TYPE_CHECKING:
     )
     from crewai.tasks.task_output import TaskOutput
 
-_post_initialize_crew_hooks: list[Callable[[Any], None]] = []
-
 
 class AgentConfig(TypedDict, total=False):
     """Type definition for agent configuration dictionary.
@@ -270,9 +266,6 @@ class CrewBaseMeta(type):
         instance.map_all_agent_variables()
         instance.map_all_task_variables()
 
-        for hook in _post_initialize_crew_hooks:
-            hook(instance)
-
         original_methods = {
             name: method
             for name, method in cls.__dict__.items()
@@ -492,61 +485,47 @@ def _register_crew_hooks(instance: CrewInstance, cls: type) -> None:
             if has_agent_filter:
                 agents_filter = hook_method._filter_agents
 
-                def make_filtered_before_llm(
-                    bound_fn: Callable[[LLMCallHookContext], bool | None],
-                    agents_list: list[str],
-                ) -> Callable[[LLMCallHookContext], bool | None]:
-                    def filtered(context: LLMCallHookContext) -> bool | None:
+                def make_filtered_before_llm(bound_fn, agents_list):
+                    def filtered(context):
                         if context.agent and context.agent.role not in agents_list:
                             return None
                         return bound_fn(context)
 
                     return filtered
 
-                before_llm_hook = make_filtered_before_llm(bound_hook, agents_filter)
+                final_hook = make_filtered_before_llm(bound_hook, agents_filter)
             else:
-                before_llm_hook = bound_hook
+                final_hook = bound_hook
 
-            register_before_llm_call_hook(before_llm_hook)
-            instance._registered_hook_functions.append(
-                ("before_llm_call", before_llm_hook)
-            )
+            register_before_llm_call_hook(final_hook)
+            instance._registered_hook_functions.append(("before_llm_call", final_hook))
 
         if hasattr(hook_method, "is_after_llm_call_hook"):
             if has_agent_filter:
                 agents_filter = hook_method._filter_agents
 
-                def make_filtered_after_llm(
-                    bound_fn: Callable[[LLMCallHookContext], str | None],
-                    agents_list: list[str],
-                ) -> Callable[[LLMCallHookContext], str | None]:
-                    def filtered(context: LLMCallHookContext) -> str | None:
+                def make_filtered_after_llm(bound_fn, agents_list):
+                    def filtered(context):
                         if context.agent and context.agent.role not in agents_list:
                             return None
                         return bound_fn(context)
 
                     return filtered
 
-                after_llm_hook = make_filtered_after_llm(bound_hook, agents_filter)
+                final_hook = make_filtered_after_llm(bound_hook, agents_filter)
             else:
-                after_llm_hook = bound_hook
+                final_hook = bound_hook
 
-            register_after_llm_call_hook(after_llm_hook)
-            instance._registered_hook_functions.append(
-                ("after_llm_call", after_llm_hook)
-            )
+            register_after_llm_call_hook(final_hook)
+            instance._registered_hook_functions.append(("after_llm_call", final_hook))
 
         if hasattr(hook_method, "is_before_tool_call_hook"):
             if has_tool_filter or has_agent_filter:
                 tools_filter = getattr(hook_method, "_filter_tools", None)
                 agents_filter = getattr(hook_method, "_filter_agents", None)
 
-                def make_filtered_before_tool(
-                    bound_fn: Callable[[ToolCallHookContext], bool | None],
-                    tools_list: list[str] | None,
-                    agents_list: list[str] | None,
-                ) -> Callable[[ToolCallHookContext], bool | None]:
-                    def filtered(context: ToolCallHookContext) -> bool | None:
+                def make_filtered_before_tool(bound_fn, tools_list, agents_list):
+                    def filtered(context):
                         if tools_list and context.tool_name not in tools_list:
                             return None
                         if (
@@ -559,28 +538,22 @@ def _register_crew_hooks(instance: CrewInstance, cls: type) -> None:
 
                     return filtered
 
-                before_tool_hook = make_filtered_before_tool(
+                final_hook = make_filtered_before_tool(
                     bound_hook, tools_filter, agents_filter
                 )
             else:
-                before_tool_hook = bound_hook
+                final_hook = bound_hook
 
-            register_before_tool_call_hook(before_tool_hook)
-            instance._registered_hook_functions.append(
-                ("before_tool_call", before_tool_hook)
-            )
+            register_before_tool_call_hook(final_hook)
+            instance._registered_hook_functions.append(("before_tool_call", final_hook))
 
         if hasattr(hook_method, "is_after_tool_call_hook"):
             if has_tool_filter or has_agent_filter:
                 tools_filter = getattr(hook_method, "_filter_tools", None)
                 agents_filter = getattr(hook_method, "_filter_agents", None)
 
-                def make_filtered_after_tool(
-                    bound_fn: Callable[[ToolCallHookContext], str | None],
-                    tools_list: list[str] | None,
-                    agents_list: list[str] | None,
-                ) -> Callable[[ToolCallHookContext], str | None]:
-                    def filtered(context: ToolCallHookContext) -> str | None:
+                def make_filtered_after_tool(bound_fn, tools_list, agents_list):
+                    def filtered(context):
                         if tools_list and context.tool_name not in tools_list:
                             return None
                         if (
@@ -593,16 +566,14 @@ def _register_crew_hooks(instance: CrewInstance, cls: type) -> None:
 
                     return filtered
 
-                after_tool_hook = make_filtered_after_tool(
+                final_hook = make_filtered_after_tool(
                     bound_hook, tools_filter, agents_filter
                 )
             else:
-                after_tool_hook = bound_hook
+                final_hook = bound_hook
 
-            register_after_tool_call_hook(after_tool_hook)
-            instance._registered_hook_functions.append(
-                ("after_tool_call", after_tool_hook)
-            )
+            register_after_tool_call_hook(final_hook)
+            instance._registered_hook_functions.append(("after_tool_call", final_hook))
 
     instance._hooks_being_registered = False
 

lib/crewai/src/crewai/project/wrappers.py

@@ -72,8 +72,6 @@ class CrewInstance(Protocol):
     __crew_metadata__: CrewMetadata
     _mcp_server_adapter: Any
     _all_methods: dict[str, Callable[..., Any]]
-    _registered_hook_functions: list[tuple[str, Callable[..., Any]]]
-    _hooks_being_registered: bool
     agents: list[Agent]
     tasks: list[Task]
     base_directory: Path

lib/crewai/src/crewai/task.py

@@ -31,7 +31,6 @@ from pydantic_core import PydanticCustomError
 from typing_extensions import Self
 
 from crewai.agents.agent_builder.base_agent import BaseAgent
-from crewai.context import reset_current_task_id, set_current_task_id
 from crewai.core.providers.content_processor import process_content
 from crewai.events.event_bus import crewai_event_bus
 from crewai.events.types.task_events import (
@@ -562,7 +561,6 @@ class Task(BaseModel):
         tools: list[Any] | None,
     ) -> TaskOutput:
         """Run the core execution logic of the task asynchronously."""
-        task_id_token = set_current_task_id(str(self.id))
         self._store_input_files()
         try:
             agent = agent or self.agent
@@ -650,7 +648,6 @@ class Task(BaseModel):
             raise e  # Re-raise the exception after emitting the event
         finally:
             clear_task_files(self.id)
-            reset_current_task_id(task_id_token)
 
     def _execute_core(
         self,
@@ -659,7 +656,6 @@ class Task(BaseModel):
         tools: list[Any] | None,
     ) -> TaskOutput:
         """Run the core execution logic of the task."""
-        task_id_token = set_current_task_id(str(self.id))
         self._store_input_files()
         try:
             agent = agent or self.agent
@@ -748,7 +744,6 @@ class Task(BaseModel):
             raise e  # Re-raise the exception after emitting the event
         finally:
             clear_task_files(self.id)
-            reset_current_task_id(task_id_token)
 
     def _post_agent_execution(self, agent: BaseAgent) -> None:
         pass

lib/crewai/src/crewai/tasks/hallucination_guardrail.py

@@ -6,7 +6,6 @@ Classes:
     HallucinationGuardrail: Placeholder guardrail that validates task outputs.
 """
 
-from collections.abc import Callable
 from typing import Any
 
 from crewai.llm import LLM
@@ -14,36 +13,32 @@ from crewai.tasks.task_output import TaskOutput
 from crewai.utilities.logger import Logger
 
 
-_validate_output_hook: Callable[..., tuple[bool, Any]] | None = None
-
-
 class HallucinationGuardrail:
     """Placeholder for the HallucinationGuardrail feature.
 
     Attributes:
-        context: Optional reference context that outputs would be checked against.
+        context: The reference context that outputs would be checked against.
         llm: The language model that would be used for evaluation.
         threshold: Optional minimum faithfulness score that would be required to pass.
         tool_response: Optional tool response information that would be used in evaluation.
 
     Examples:
-        >>> # Basic usage without context (uses task expected_output as context)
-        >>> guardrail = HallucinationGuardrail(llm=agent.llm)
-
-        >>> # With context for reference
+        >>> # Basic usage with default verdict logic
         >>> guardrail = HallucinationGuardrail(
-        ...     llm=agent.llm,
         ...     context="AI helps with various tasks including analysis and generation.",
+        ...     llm=agent.llm,
         ... )
 
         >>> # With custom threshold for stricter validation
         >>> strict_guardrail = HallucinationGuardrail(
+        ...     context="Quantum computing uses qubits in superposition.",
         ...     llm=agent.llm,
-        ...     threshold=8.0,  # Require score >= 8 to pass
+        ...     threshold=8.0,  # Would require score >= 8 to pass in enterprise version
         ... )
 
         >>> # With tool response for additional context
         >>> guardrail_with_tools = HallucinationGuardrail(
+        ...     context="The current weather data",
         ...     llm=agent.llm,
         ...     tool_response="Weather API returned: Temperature 22°C, Humidity 65%",
         ... )
@@ -51,17 +46,16 @@ class HallucinationGuardrail:
 
     def __init__(
         self,
+        context: str,
         llm: LLM,
-        context: str | None = None,
         threshold: float | None = None,
         tool_response: str = "",
     ):
         """Initialize the HallucinationGuardrail placeholder.
 
         Args:
+            context: The reference context that outputs would be checked against.
             llm: The language model that would be used for evaluation.
-            context: Optional reference context that outputs would be checked against.
-                If not provided, the task's expected_output will be used as context.
             threshold: Optional minimum faithfulness score that would be required to pass.
             tool_response: Optional tool response information that would be used in evaluation.
         """
@@ -84,17 +78,16 @@ class HallucinationGuardrail:
     def __call__(self, task_output: TaskOutput) -> tuple[bool, Any]:
         """Validate a task output against hallucination criteria.
 
+        In the open source, this method always returns that the output is valid.
+
         Args:
             task_output: The output to be validated.
 
         Returns:
             A tuple containing:
-                - True if validation passed, False otherwise
-                - The raw task output if valid, or error feedback if invalid
+                - True
+                - The raw task output
         """
-        if callable(_validate_output_hook):
-            return _validate_output_hook(self, task_output)
-
         self._logger.log(
             "warning",
             "Premium hallucination detection skipped (use for free at https://app.crewai.com)\n",

lib/crewai/src/crewai/tasks/llm_guardrail.py

@@ -1,10 +1,6 @@
-import asyncio
-from collections.abc import Coroutine
-import inspect
 from typing import Any
 
 from pydantic import BaseModel, Field
-from typing_extensions import TypeIs
 
 from crewai.agent import Agent
 from crewai.lite_agent_output import LiteAgentOutput
@@ -12,13 +8,6 @@ from crewai.llms.base_llm import BaseLLM
 from crewai.tasks.task_output import TaskOutput
 
 
-def _is_coroutine(
-    obj: LiteAgentOutput | Coroutine[Any, Any, LiteAgentOutput],
-) -> TypeIs[Coroutine[Any, Any, LiteAgentOutput]]:
-    """Check if obj is a coroutine for type narrowing."""
-    return inspect.iscoroutine(obj)
-
-
 class LLMGuardrailResult(BaseModel):
     valid: bool = Field(
         description="Whether the task output complies with the guardrail"
@@ -73,10 +62,7 @@ class LLMGuardrail:
         - If the Task result complies with the guardrail, saying that is valid
         """
 
-        kickoff_result = agent.kickoff(query, response_format=LLMGuardrailResult)
-        if _is_coroutine(kickoff_result):
-            return asyncio.run(kickoff_result)
-        return kickoff_result
+        return agent.kickoff(query, response_format=LLMGuardrailResult)
 
     def __call__(self, task_output: TaskOutput) -> tuple[bool, Any]:
         """Validates the output of a task based on specified criteria.

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

@@ -903,7 +903,7 @@ class Telemetry:
                         {
                             "id": str(task.id),
                             "description": task.description,
-                            "output": task.output.raw if task.output else "",
+                            "output": task.output.raw_output,
                         }
                         for task in crew.tasks
                     ]
@@ -923,9 +923,6 @@ class Telemetry:
             value: The attribute value.
         """
 
-        if span is None:
-            return
-
         def _operation() -> None:
             return span.set_attribute(key, value)
 

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

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

lib/crewai/src/crewai/tools/tool_usage.py

@@ -270,7 +270,6 @@ class ToolUsage:
         result = None  # type: ignore
         should_retry = False
         available_tool = None
-        error_event_emitted = False
 
         try:
             if self.tools_handler and self.tools_handler.cache:
@@ -409,7 +408,6 @@ class ToolUsage:
 
                 except Exception as e:
                     self.on_tool_error(tool=tool, tool_calling=calling, e=e)
-                    error_event_emitted = True
                     self._run_attempts += 1
                     if self._run_attempts > self._max_parsing_attempts:
                         self._telemetry.tool_usage_error(llm=self.function_calling_llm)
@@ -437,7 +435,7 @@ class ToolUsage:
                 result = self._format_result(result=result)
 
         finally:
-            if started_event_emitted and not error_event_emitted:
+            if started_event_emitted:
                 self.on_tool_use_finished(
                     tool=tool,
                     tool_calling=calling,
@@ -502,7 +500,6 @@ class ToolUsage:
         result = None  # type: ignore
         should_retry = False
         available_tool = None
-        error_event_emitted = False
 
         try:
             if self.tools_handler and self.tools_handler.cache:
@@ -641,7 +638,6 @@ class ToolUsage:
 
                 except Exception as e:
                     self.on_tool_error(tool=tool, tool_calling=calling, e=e)
-                    error_event_emitted = True
                     self._run_attempts += 1
                     if self._run_attempts > self._max_parsing_attempts:
                         self._telemetry.tool_usage_error(llm=self.function_calling_llm)
@@ -669,7 +665,7 @@ class ToolUsage:
                 result = self._format_result(result=result)
 
         finally:
-            if started_event_emitted and not error_event_emitted:
+            if started_event_emitted:
                 self.on_tool_use_finished(
                     tool=tool,
                     tool_calling=calling,

lib/crewai/src/crewai/types/hitl.py

@@ -0,0 +1,37 @@
+"""Human-in-the-loop (HITL) type definitions.
+
+This module provides type definitions for human-in-the-loop interactions
+in crew executions.
+"""
+
+from typing import TypedDict
+
+
+class HITLResumeInfo(TypedDict, total=False):
+    """HITL resume information passed from flow to crew.
+
+    Attributes:
+        task_id: Unique identifier for the task.
+        crew_execution_id: Unique identifier for the crew execution.
+        task_key: Key identifying the specific task.
+        task_output: Output from the task before human intervention.
+        human_feedback: Feedback provided by the human.
+        previous_messages: History of messages in the conversation.
+    """
+
+    task_id: str
+    crew_execution_id: str
+    task_key: str
+    task_output: str
+    human_feedback: str
+    previous_messages: list[dict[str, str]]
+
+
+class CrewInputsWithHITL(TypedDict, total=False):
+    """Crew inputs that may contain HITL resume information.
+
+    Attributes:
+        _hitl_resume: Optional HITL resume information for continuing execution.
+    """
+
+    _hitl_resume: HITLResumeInfo

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

@@ -42,8 +42,6 @@ if TYPE_CHECKING:
     from crewai.llm import LLM
     from crewai.task import Task
 
-_create_plus_client_hook: Callable[[], Any] | None = None
-
 
 class SummaryContent(TypedDict):
     """Structure for summary content entries.
@@ -93,11 +91,7 @@ def parse_tools(tools: list[BaseTool]) -> list[CrewStructuredTool]:
 
     for tool in tools:
         if isinstance(tool, CrewAITool):
-            structured_tool = tool.to_structured_tool()
-            structured_tool.current_usage_count = 0
-            if structured_tool._original_tool:
-                structured_tool._original_tool.current_usage_count = 0
-            tools_list.append(structured_tool)
+            tools_list.append(tool.to_structured_tool())
         else:
             raise ValueError("Tool is not a CrewStructuredTool or BaseTool")
 
@@ -824,15 +818,12 @@ def load_agent_from_repository(from_repository: str) -> dict[str, Any]:
     if from_repository:
         import importlib
 
-        if callable(_create_plus_client_hook):
-            client = _create_plus_client_hook()
-        else:
-            from crewai.cli.authentication.token import get_auth_token
-            from crewai.cli.plus_api import PlusAPI
+        from crewai.cli.authentication.token import get_auth_token
+        from crewai.cli.plus_api import PlusAPI
 
-            client = PlusAPI(api_key=get_auth_token())
+        client = PlusAPI(api_key=get_auth_token())
         _print_current_organization()
-        response = asyncio.run(client.get_agent(from_repository))
+        response = client.get_agent(from_repository)
         if response.status_code == 404:
             raise AgentRepositoryError(
                 f"Agent {from_repository} does not exist, make sure the name is correct or the agent is available on your organization."

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

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from collections import defaultdict
-from typing import TYPE_CHECKING, Any
+from typing import TYPE_CHECKING
 
 from pydantic import BaseModel, Field, InstanceOf
 from rich.box import HEAVY_EDGE
@@ -36,13 +36,7 @@ class CrewEvaluator:
         iteration: The current iteration of the evaluation.
     """
 
-    def __init__(
-        self,
-        crew: Crew,
-        eval_llm: InstanceOf[BaseLLM] | str | None = None,
-        openai_model_name: str | None = None,
-        llm: InstanceOf[BaseLLM] | str | None = None,
-    ) -> None:
+    def __init__(self, crew: Crew, eval_llm: InstanceOf[BaseLLM]) -> None:
         self.crew = crew
         self.llm = eval_llm
         self.tasks_scores: defaultdict[int, list[float]] = defaultdict(list)
@@ -92,9 +86,7 @@ class CrewEvaluator:
         """
         self.iteration = iteration
 
-    def print_crew_evaluation_result(
-        self, token_usage: list[dict[str, Any]] | None = None
-    ) -> None:
+    def print_crew_evaluation_result(self) -> None:
         """
         Prints the evaluation result of the crew in a table.
         A Crew with 2 tasks using the command crewai test -n 3
@@ -212,7 +204,7 @@ class CrewEvaluator:
                 CrewTestResultEvent(
                     quality=quality_score,
                     execution_duration=current_task.execution_duration,
-                    model=getattr(self.llm, "model", str(self.llm)),
+                    model=self.llm.model,
                     crew_name=self.crew.name,
                     crew=self.crew,
                 ),

lib/crewai/src/crewai/utilities/printer.py

@@ -4,8 +4,6 @@ from __future__ import annotations
 
 from typing import TYPE_CHECKING, Final, Literal, NamedTuple
 
-from crewai.events.utils.console_formatter import should_suppress_console_output
-
 
 if TYPE_CHECKING:
     from _typeshed import SupportsWrite
@@ -79,8 +77,6 @@ class Printer:
             file: A file-like object (stream); defaults to the current sys.stdout.
             flush: Whether to forcibly flush the stream.
         """
-        if should_suppress_console_output():
-            return
         if isinstance(content, str):
             content = [ColoredText(content, color)]
         print(

lib/crewai/src/crewai/utilities/serialization.py

@@ -19,7 +19,6 @@ def to_serializable(
     exclude: set[str] | None = None,
     max_depth: int = 5,
     _current_depth: int = 0,
-    _ancestors: set[int] | None = None,
 ) -> Serializable:
     """Converts a Python object into a JSON-compatible representation.
 
@@ -32,7 +31,6 @@ def to_serializable(
         exclude: Set of keys to exclude from the result.
         max_depth: Maximum recursion depth. Defaults to 5.
         _current_depth: Current recursion depth (for internal use).
-        _ancestors: Set of ancestor object ids for cycle detection (for internal use).
 
     Returns:
         Serializable: A JSON-compatible structure.
@@ -43,29 +41,16 @@ def to_serializable(
     if exclude is None:
         exclude = set()
 
-    if _ancestors is None:
-        _ancestors = set()
-
     if isinstance(obj, (str, int, float, bool, type(None))):
         return obj
     if isinstance(obj, uuid.UUID):
         return str(obj)
     if isinstance(obj, (date, datetime)):
         return obj.isoformat()
-
-    object_id = id(obj)
-    if object_id in _ancestors:
-        return f"<circular_ref:{type(obj).__name__}>"
-    new_ancestors = _ancestors | {object_id}
-
     if isinstance(obj, (list, tuple, set)):
         return [
             to_serializable(
-                item,
-                exclude=exclude,
-                max_depth=max_depth,
-                _current_depth=_current_depth + 1,
-                _ancestors=new_ancestors,
+                item, max_depth=max_depth, _current_depth=_current_depth + 1
             )
             for item in obj
         ]
@@ -76,7 +61,6 @@ def to_serializable(
                 exclude=exclude,
                 max_depth=max_depth,
                 _current_depth=_current_depth + 1,
-                _ancestors=new_ancestors,
             )
             for key, value in obj.items()
             if key not in exclude
@@ -87,16 +71,12 @@ def to_serializable(
                 obj=obj.model_dump(exclude=exclude),
                 max_depth=max_depth,
                 _current_depth=_current_depth + 1,
-                _ancestors=new_ancestors,
             )
         except Exception:
             try:
                 return {
                     _to_serializable_key(k): to_serializable(
-                        v,
-                        max_depth=max_depth,
-                        _current_depth=_current_depth + 1,
-                        _ancestors=new_ancestors,
+                        v, max_depth=max_depth, _current_depth=_current_depth + 1
                     )
                     for k, v in obj.__dict__.items()
                     if k not in (exclude or set())

lib/crewai/tests/agents/agent_adapters/test_base_agent_adapter.py

@@ -51,10 +51,6 @@ class ConcreteAgentAdapter(BaseAgentAdapter):
         # Dummy implementation for MCP tools
         return []
 
-    def configure_structured_output(self, task: Any) -> None:
-        # Dummy implementation for structured output
-        pass
-
     async def aexecute_task(
         self,
         task: Any,

lib/crewai/tests/agents/test_lite_agent.py

@@ -606,10 +606,9 @@ def test_lite_agent_with_invalid_llm():
 
 
 @patch.dict("os.environ", {"CREWAI_PLATFORM_INTEGRATION_TOKEN": "test_token"})
-@patch("crewai_tools.tools.crewai_platform_tools.crewai_platform_action_tool.requests.post")
 @patch("crewai_tools.tools.crewai_platform_tools.crewai_platform_tool_builder.requests.get")
 @pytest.mark.vcr()
-def test_agent_kickoff_with_platform_tools(mock_get, mock_post):
+def test_agent_kickoff_with_platform_tools(mock_get):
     """Test that Agent.kickoff() properly integrates platform tools with LiteAgent"""
     mock_response = Mock()
     mock_response.raise_for_status.return_value = None
@@ -633,15 +632,6 @@ def test_agent_kickoff_with_platform_tools(mock_get, mock_post):
     }
     mock_get.return_value = mock_response
 
-    # Mock the platform tool execution
-    mock_post_response = Mock()
-    mock_post_response.ok = True
-    mock_post_response.json.return_value = {
-        "success": True,
-        "issue_url": "https://github.com/test/repo/issues/1"
-    }
-    mock_post.return_value = mock_post_response
-
     agent = Agent(
         role="Test Agent",
         goal="Test goal",

lib/crewai/tests/cassettes/agents/test_agent_kickoff_with_platform_tools.yaml

@@ -1,227 +1,98 @@
 interactions:
 - request:
-    body: '{"messages":[{"role":"system","content":"You are Test Agent. Test backstory\nYour
-      personal goal is: Test goal"},{"role":"user","content":"\nCurrent Task: Create
-      a GitHub issue"}],"model":"gpt-3.5-turbo","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_issue","description":"Create
-      a GitHub issue","strict":true,"parameters":{"additionalProperties":false,"properties":{"title":{"description":"Issue
-      title","title":"Title","type":"string"},"body":{"default":null,"description":"Issue
-      body","title":"Body","type":"string"}},"required":["title","body"],"type":"object"}}}]}'
+    body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test backstory\nYour personal goal is: Test goal\n\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: create_issue\nTool Arguments: {''title'': {''description'': ''Issue title'', ''type'': ''str''}, ''body'': {''description'': ''Issue body'', ''type'': ''Union[str, NoneType]''}}\nTool Description: Create a GitHub issue\nDetailed Parameter Structure:\nObject with properties:\n  - title: Issue title (required)\n  - body: Issue body (optional)\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought: you should always think about what to do\nAction: the action to take, only one name of [create_issue], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce all necessary information
+      is gathered, return the following format:\n\n```\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n```"}, {"role": "user", "content": "Create a GitHub issue"}], "model": "gpt-3.5-turbo", "stream": false}'
     headers:
-      User-Agent:
-      - X-USER-AGENT-XXX
       accept:
       - application/json
       accept-encoding:
-      - ACCEPT-ENCODING-XXX
-      authorization:
-      - AUTHORIZATION-XXX
+      - gzip, deflate
       connection:
       - keep-alive
       content-length:
-      - '596'
+      - '1233'
       content-type:
       - application/json
       host:
       - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.109.1
       x-stainless-arch:
-      - X-STAINLESS-ARCH-XXX
+      - arm64
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - X-STAINLESS-OS-XXX
+      - MacOS
       x-stainless-package-version:
-      - 1.83.0
+      - 1.109.1
       x-stainless-read-timeout:
-      - X-STAINLESS-READ-TIMEOUT-XXX
+      - '600'
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.5
+      - 3.13.3
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-D6L3fqygkUIZ3bN4wvSpAhdaSk7MF\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1770403287,\n  \"model\": \"gpt-3.5-turbo-0125\",\n
-        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
-        \           \"id\": \"call_RuWuYzjzgRL3byVGhLlPi0rq\",\n            \"type\":
-        \"function\",\n            \"function\": {\n              \"name\": \"create_issue\",\n
-        \             \"arguments\": \"{\\\"title\\\":\\\"Test issue\\\",\\\"body\\\":\\\"This
-        is a test issue created for testing purposes.\\\"}\"\n            }\n          }\n
-        \       ],\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
-        \     \"logprobs\": null,\n      \"finish_reason\": \"tool_calls\"\n    }\n
-        \ ],\n  \"usage\": {\n    \"prompt_tokens\": 93,\n    \"completion_tokens\":
-        28,\n    \"total_tokens\": 121,\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\": null\n}\n"
+      string: "{\n  \"id\": \"chatcmpl-CULxKTEIB85AVItcEQ09z4Xi0JCID\",\n  \"object\": \"chat.completion\",\n  \"created\": 1761350274,\n  \"model\": \"gpt-3.5-turbo-0125\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"I will need more specific information to create a GitHub issue. Could you please provide more details such as the title and body of the issue you would like to create?\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 255,\n    \"completion_tokens\": 33,\n    \"total_tokens\": 288,\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\": null\n}\n"
     headers:
       CF-RAY:
-      - CF-RAY-XXX
+      - 993d6b4be9862379-SJC
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Fri, 06 Feb 2026 18:41:28 GMT
+      - Fri, 24 Oct 2025 23:57:54 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - SET-COOKIE-XXX
+      - __cf_bm=WY9bgemMDI_hUYISAPlQ2a.DBGeZfM6AjVEa3SKNg1c-1761350274-1.0.1.1-K3Qm2cl6IlDAgmocoKZ8IMUTmue6Q81hH9stECprUq_SM8LF8rR9d1sHktvRCN3.jEM.twEuFFYDNpBnN8NBRJFZcea1yvpm8Uo0G_UhyDs; path=/; expires=Sat, 25-Oct-25 00:27:54 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      - _cfuvid=JklLS4i3hBGELpS9cz1KMpTbj72hCwP41LyXDSxWIv8-1761350274521-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Strict-Transport-Security:
-      - STS-XXX
+      - max-age=31536000; includeSubDomains; preload
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
-      - X-CONTENT-TYPE-XXX
+      - nosniff
       access-control-expose-headers:
-      - ACCESS-CONTROL-XXX
+      - X-Request-ID
       alt-svc:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
       openai-organization:
-      - OPENAI-ORG-XXX
+      - crewai-iuxna1
       openai-processing-ms:
-      - '1406'
+      - '487'
       openai-project:
-      - OPENAI-PROJECT-XXX
+      - proj_xitITlrFeen7zjNSzML82h9x
       openai-version:
       - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '526'
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:
-      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      - '10000'
       x-ratelimit-limit-tokens:
-      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      - '50000000'
       x-ratelimit-remaining-requests:
-      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      - '9999'
       x-ratelimit-remaining-tokens:
-      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      - '49999727'
       x-ratelimit-reset-requests:
-      - X-RATELIMIT-RESET-REQUESTS-XXX
+      - 6ms
       x-ratelimit-reset-tokens:
-      - X-RATELIMIT-RESET-TOKENS-XXX
+      - 0s
       x-request-id:
-      - X-REQUEST-ID-XXX
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"messages":[{"role":"system","content":"You are Test Agent. Test backstory\nYour
-      personal goal is: Test goal"},{"role":"user","content":"\nCurrent Task: Create
-      a GitHub issue"},{"role":"assistant","content":null,"tool_calls":[{"id":"call_RuWuYzjzgRL3byVGhLlPi0rq","type":"function","function":{"name":"create_issue","arguments":"{\"title\":\"Test
-      issue\",\"body\":\"This is a test issue created for testing purposes.\"}"}}]},{"role":"tool","tool_call_id":"call_RuWuYzjzgRL3byVGhLlPi0rq","name":"create_issue","content":"{\n  \"success\":
-      true,\n  \"issue_url\": \"https://github.com/test/repo/issues/1\"\n}"}],"model":"gpt-3.5-turbo","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_issue","description":"Create
-      a GitHub issue","strict":true,"parameters":{"additionalProperties":false,"properties":{"title":{"description":"Issue
-      title","title":"Title","type":"string"},"body":{"default":null,"description":"Issue
-      body","title":"Body","type":"string"}},"required":["title","body"],"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:
-      - '1028'
-      content-type:
-      - application/json
-      cookie:
-      - COOKIE-XXX
-      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:
-      - 3.13.5
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: "{\n  \"id\": \"chatcmpl-D6L3hfuBxk36LIb3ekD1IVwFD5VVL\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1770403289,\n  \"model\": \"gpt-3.5-turbo-0125\",\n
-        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-        \"assistant\",\n        \"content\": \"I have successfully created a GitHub
-        issue for testing purposes. You can view the issue at this URL: [Test issue](https://github.com/test/repo/issues/1)\",\n
-        \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
-        null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-        154,\n    \"completion_tokens\": 36,\n    \"total_tokens\": 190,\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\": null\n}\n"
-    headers:
-      CF-RAY:
-      - CF-RAY-XXX
-      Connection:
-      - keep-alive
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 06 Feb 2026 18:41:29 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:
-      - '888'
-      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
+      - req_1708dc0928c64882aaa5bc2c168c140f
     status:
       code: 200
       message: OK

lib/crewai/tests/cassettes/agents/test_guardrail_reached_attempt_limit.yaml

@@ -1,428 +1,400 @@
 interactions:
 - request:
-    body: '{"messages":[{"role":"system","content":"You are Sports Analyst. You are
-      an expert at gathering and organizing information. You carefully collect details
-      and present them in a structured way.\nYour personal goal is: Gather information
-      about the best soccer players"},{"role":"user","content":"\nCurrent Task: Top
-      10 best players in the world?\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}'
+    body: '{"messages": [{"role": "system", "content": "You are Sports Analyst. You are an expert at gathering and organizing information. You carefully collect details and present them in a structured way.\nYour personal goal is: Gather information about the best soccer players\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!"}, {"role": "user", "content": "Top 10 best players in the world?"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
     headers:
-      User-Agent:
-      - X-USER-AGENT-XXX
       accept:
       - application/json
       accept-encoding:
-      - ACCEPT-ENCODING-XXX
-      authorization:
-      - AUTHORIZATION-XXX
+      - gzip, deflate, zstd
       connection:
       - keep-alive
       content-length:
-      - '404'
+      - '694'
       content-type:
       - application/json
       host:
       - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.78.0
       x-stainless-arch:
-      - X-STAINLESS-ARCH-XXX
+      - arm64
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - X-STAINLESS-OS-XXX
+      - MacOS
       x-stainless-package-version:
-      - 1.83.0
+      - 1.78.0
+      x-stainless-raw-response:
+      - 'true'
       x-stainless-read-timeout:
-      - X-STAINLESS-READ-TIMEOUT-XXX
+      - '600.0'
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.5
+      - 3.12.9
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-D6L3hzoRVVEa07HZsM9wpi2RVRKQp\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1770403289,\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 structured list of the top
-        10 best soccer players in the world as of 2024, based on recent performances,
-        awards, and overall impact on the game:\\n\\n1. **Kylian Mbapp\xE9**  \\n
-        \  - Nationality: French  \\n   - Club: Paris Saint-Germain (PSG)  \\n   -
-        Position: Forward  \\n   - Key Highlights: Multiple Ligue 1 titles, World
-        Cup winner (2018), known for speed, dribbling, and scoring prowess.\\n\\n2.
-        **Erling Haaland**  \\n   - Nationality: Norwegian  \\n   - Club: Manchester
-        City  \\n   - Position: Striker  \\n   - Key Highlights: Premier League Golden
-        Boot winner, incredible goal-scoring record, physical presence, and finishing
-        skills.\\n\\n3. **Lionel Messi**  \\n   - Nationality: Argentine  \\n   -
-        Club: Inter Miami  \\n   - Position: Forward/Attacking Midfielder  \\n   -
-        Key Highlights: Seven Ballon d\u2019Or awards, World Cup winner (2022), exceptional
-        playmaking and dribbling ability.\\n\\n4. **Kevin De Bruyne**  \\n   - Nationality:
-        Belgian  \\n   - Club: Manchester City  \\n   - Position: Midfielder  \\n
-        \  - Key Highlights: One of the best playmakers globally, assists leader,
-        consistent high-level performance in the Premier League.\\n\\n5. **Robert
-        Lewandowski**  \\n   - Nationality: Polish  \\n   - Club: FC Barcelona  \\n
-        \  - Position: Striker  \\n   - Key Highlights: Exceptional goal-scoring record,
-        multiple Bundesliga top scorer awards, key figure in Bayern Munich\u2019s
-        dominance before transferring.\\n\\n6. **Karim Benzema**  \\n   - Nationality:
-        French  \\n   - Club: Al-Ittihad  \\n   - Position: Striker  \\n   - Key Highlights:
-        Ballon d\u2019Or winner (2022), excellent technical skills, leadership at
-        Real Madrid before recent transfer.\\n\\n7. **Mohamed Salah**  \\n   - Nationality:
-        Egyptian  \\n   - Club: Liverpool  \\n   - Position: Forward  \\n   - Key
-        Highlights: Premier League Golden Boot winner, known for speed, dribbling,
-        and goal-scoring consistency.\\n\\n8. **Vin\xEDcius J\xFAnior**  \\n   - Nationality:
-        Brazilian  \\n   - Club: Real Madrid  \\n   - Position: Winger  \\n   - Key
-        Highlights: Key player for Real Madrid, exceptional dribbling and pace, rising
-        star in world football.\\n\\n9. **Jude Bellingham**  \\n   - Nationality:
-        English  \\n   - Club: Real Madrid  \\n   - Position: Midfielder  \\n   -
-        Key Highlights: Young talent with maturity beyond years, influential midfielder
-        with great vision and work rate.\\n\\n10. **Thibaut Courtois**  \\n    - Nationality:
-        Belgian  \\n    - Club: Real Madrid  \\n    - Position: Goalkeeper  \\n    -
-        Key Highlights: One of the best goalkeepers globally, crucial performances
-        in La Liga and Champions League.\\n\\nThese rankings consider individual talent,
-        recent achievements, influence on matches, and overall contribution to club
-        and country.\",\n        \"refusal\": null,\n        \"annotations\": []\n
-        \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
-        \ ],\n  \"usage\": {\n    \"prompt_tokens\": 68,\n    \"completion_tokens\":
-        621,\n    \"total_tokens\": 689,\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_75546bd1a7\"\n}\n"
+      string: "{\n  \"id\": \"chatcmpl-BgufUtDqGzvqPZx2NmkqqxdW4G8rQ\",\n  \"object\": \"chat.completion\",\n  \"created\": 1749567308,\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: The top 10 best soccer players in the world, as of October 2023, can be identified based on their recent performances, skills, impact on games, and overall contributions to their teams. Here is the structured list:\\n\\n1. **Lionel Messi (Inter Miami CF)**\\n   - Position: Forward\\n   - Key Attributes: Dribbling, vision, goal-scoring ability.\\n   - Achievements: Multiple Ballon d'Or winner, Copa America champion, World Cup champion (2022).\\n\\n2. **Kylian Mbappé (Paris Saint-Germain)**\\n   - Position: Forward\\n   - Key Attributes: Speed, technique, finishing.\\n   - Achievements: FIFA World Cup champion (2018), Ligue 1 titles, multiple\
+        \ domestic cups.\\n\\n3. **Erling Haaland (Manchester City)**\\n   - Position: Forward\\n   - Key Attributes: Power, speed, goal-scoring instinct.\\n   - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\\n\\n4. **Kevin De Bruyne (Manchester City)**\\n   - Position: Midfielder\\n   - Key Attributes: Passing, vision, creativity.\\n   - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\\n\\n5. **Karim Benzema (Al-Ittihad)**\\n   - Position: Forward\\n   - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\\n   - Achievements: 2022 Ballon d'Or winner, multiple Champions Leagues with Real Madrid.\\n\\n6. **Neymar Jr. (Al Hilal)**\\n   - Position: Forward\\n   - Key Attributes: Flair, dribbling, creativity.\\n   - Achievements: Multiple domestic league titles, Champions League runner-up.\\n\\n7. **Robert Lewandowski (FC Barcelona)**\\n   - Position: Forward\\n   - Key Attributes: Finishing,\
+        \ positioning, aerial ability.\\n   - Achievements: FIFA Best Men's Player, multiple Bundesliga titles, La Liga champion (2023).\\n\\n8. **Mohamed Salah (Liverpool)**\\n   - Position: Forward\\n   - Key Attributes: Speed, finishing, dribbling.\\n   - Achievements: Premier League champion, FA Cup, UEFA Champions League winner.\\n\\n9. **Vinícius Júnior (Real Madrid)**\\n   - Position: Forward\\n   - Key Attributes: Speed, dribbling, creativity.\\n   - Achievements: UEFA Champions League winner (2022), La Liga champion (2023).\\n\\n10. **Luka Modrić (Real Madrid)**\\n    - Position: Midfielder\\n    - Key Attributes: Passing, vision, tactical intelligence.\\n    - Achievements: Multiple Champions League titles, Ballon d'Or winner (2018).\\n\\nThis list is compiled based on their current form, past performances, and contributions to their respective teams in both domestic and international competitions. Player rankings can vary based on personal opinion and specific criteria used for\
+        \ evaluation, but these players have consistently been regarded as some of the best in the world as of October 2023.\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 122,\n    \"completion_tokens\": 643,\n    \"total_tokens\": 765,\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_34a54ae93c\"\n}\n"
     headers:
       CF-RAY:
-      - CF-RAY-XXX
+      - 94d9b5400dcd624b-GRU
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Fri, 06 Feb 2026 18:41:40 GMT
+      - Tue, 10 Jun 2025 14:55:42 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - SET-COOKIE-XXX
-      Strict-Transport-Security:
-      - STS-XXX
+      - __cf_bm=8Yv8F0ZCFAo2lf.qoqxao70yxyjVvIV90zQqVF6bVzQ-1749567342-1.0.1.1-fZgnv3RDfunvCO1koxwwFJrHnxSx_rwS_FHvQ6xxDPpKHwYr7dTqIQLZrNgSX5twGyK4F22rUmkuiS6KMVogcinChk8lmHtJBTUVTFjr2KU; path=/; expires=Tue, 10-Jun-25 15:25:42 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      - _cfuvid=wzh8YnmXvLq1G0RcIVijtzboQtCZyIe2uZiochkBLqE-1749567342267-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
-      - X-CONTENT-TYPE-XXX
+      - nosniff
       access-control-expose-headers:
-      - ACCESS-CONTROL-XXX
+      - X-Request-ID
       alt-svc:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
       openai-organization:
-      - OPENAI-ORG-XXX
+      - crewai-iuxna1
       openai-processing-ms:
-      - '10634'
-      openai-project:
-      - OPENAI-PROJECT-XXX
+      - '33288'
       openai-version:
       - '2020-10-01'
-      x-openai-proxy-wasm:
-      - v0.1
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-envoy-upstream-service-time:
+      - '33292'
       x-ratelimit-limit-requests:
-      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      - '30000'
       x-ratelimit-limit-tokens:
-      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      - '150000000'
       x-ratelimit-remaining-requests:
-      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      - '29999'
       x-ratelimit-remaining-tokens:
-      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      - '149999859'
       x-ratelimit-reset-requests:
-      - X-RATELIMIT-RESET-REQUESTS-XXX
+      - 2ms
       x-ratelimit-reset-tokens:
-      - X-RATELIMIT-RESET-TOKENS-XXX
+      - 0s
       x-request-id:
-      - X-REQUEST-ID-XXX
+      - req_6a587ea22edef774ecdada790a320cab
     status:
       code: 200
       message: OK
 - request:
-    body: '{"messages":[{"role":"system","content":"You are Sports Analyst. You are
-      an expert at gathering and organizing information. You carefully collect details
-      and present them in a structured way.\nYour personal goal is: Gather information
-      about the best soccer players"},{"role":"user","content":"\nCurrent Task: Top
-      10 best players in the world?\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}'
+    body: '{"messages": [{"role": "system", "content": "You are Sports Analyst. You are an expert at gathering and organizing information. You carefully collect details and present them in a structured way.\nYour personal goal is: Gather information about the best soccer players\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!"}, {"role": "user", "content": "Top 10 best players in the world?"}, {"role": "assistant", "content": "Thought: I now can give a great answer  \nFinal Answer: The top 10 best soccer players in the world, as of October 2023, can be identified based on their recent performances, skills, impact on games, and overall contributions to their teams. Here is the structured list:\n\n1. **Lionel Messi (Inter Miami CF)**\n   -
+      Position: Forward\n   - Key Attributes: Dribbling, vision, goal-scoring ability.\n   - Achievements: Multiple Ballon d''Or winner, Copa America champion, World Cup champion (2022).\n\n2. **Kylian Mbapp\u00e9 (Paris Saint-Germain)**\n   - Position: Forward\n   - Key Attributes: Speed, technique, finishing.\n   - Achievements: FIFA World Cup champion (2018), Ligue 1 titles, multiple domestic cups.\n\n3. **Erling Haaland (Manchester City)**\n   - Position: Forward\n   - Key Attributes: Power, speed, goal-scoring instinct.\n   - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\n\n4. **Kevin De Bruyne (Manchester City)**\n   - Position: Midfielder\n   - Key Attributes: Passing, vision, creativity.\n   - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\n\n5. **Karim Benzema (Al-Ittihad)**\n   - Position: Forward\n   - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\n   - Achievements:
+      2022 Ballon d''Or winner, multiple Champions Leagues with Real Madrid.\n\n6. **Neymar Jr. (Al Hilal)**\n   - Position: Forward\n   - Key Attributes: Flair, dribbling, creativity.\n   - Achievements: Multiple domestic league titles, Champions League runner-up.\n\n7. **Robert Lewandowski (FC Barcelona)**\n   - Position: Forward\n   - Key Attributes: Finishing, positioning, aerial ability.\n   - Achievements: FIFA Best Men''s Player, multiple Bundesliga titles, La Liga champion (2023).\n\n8. **Mohamed Salah (Liverpool)**\n   - Position: Forward\n   - Key Attributes: Speed, finishing, dribbling.\n   - Achievements: Premier League champion, FA Cup, UEFA Champions League winner.\n\n9. **Vin\u00edcius J\u00fanior (Real Madrid)**\n   - Position: Forward\n   - Key Attributes: Speed, dribbling, creativity.\n   - Achievements: UEFA Champions League winner (2022), La Liga champion (2023).\n\n10. **Luka Modri\u0107 (Real Madrid)**\n    - Position: Midfielder\n    - Key Attributes: Passing, vision,
+      tactical intelligence.\n    - Achievements: Multiple Champions League titles, Ballon d''Or winner (2018).\n\nThis list is compiled based on their current form, past performances, and contributions to their respective teams in both domestic and international competitions. Player rankings can vary based on personal opinion and specific criteria used for evaluation, but these players have consistently been regarded as some of the best in the world as of October 2023."}, {"role": "user", "content": "You are not allowed to include Brazilian players"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
     headers:
-      User-Agent:
-      - X-USER-AGENT-XXX
       accept:
       - application/json
       accept-encoding:
-      - ACCEPT-ENCODING-XXX
-      authorization:
-      - AUTHORIZATION-XXX
+      - gzip, deflate, zstd
       connection:
       - keep-alive
       content-length:
-      - '404'
+      - '3594'
       content-type:
       - application/json
       cookie:
-      - COOKIE-XXX
+      - __cf_bm=8Yv8F0ZCFAo2lf.qoqxao70yxyjVvIV90zQqVF6bVzQ-1749567342-1.0.1.1-fZgnv3RDfunvCO1koxwwFJrHnxSx_rwS_FHvQ6xxDPpKHwYr7dTqIQLZrNgSX5twGyK4F22rUmkuiS6KMVogcinChk8lmHtJBTUVTFjr2KU; _cfuvid=wzh8YnmXvLq1G0RcIVijtzboQtCZyIe2uZiochkBLqE-1749567342267-0.0.1.1-604800000
       host:
       - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.78.0
       x-stainless-arch:
-      - X-STAINLESS-ARCH-XXX
+      - arm64
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - X-STAINLESS-OS-XXX
+      - MacOS
       x-stainless-package-version:
-      - 1.83.0
+      - 1.78.0
+      x-stainless-raw-response:
+      - 'true'
       x-stainless-read-timeout:
-      - X-STAINLESS-READ-TIMEOUT-XXX
+      - '600.0'
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.5
+      - 3.12.9
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-D6L3sn9nSnGGOMKrS88avliVF7XTv\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1770403300,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
-        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-        \"assistant\",\n        \"content\": \"Certainly! Here's a structured list
-        of the top 10 best soccer players in the world as of 2024, considering their
-        performance, skills, achievements, and impact in recent seasons:\\n\\n###
-        Top 10 Best Soccer Players in the World (2024)\\n\\n| Rank | Player Name         |
-        Nationality | Club (2023/24 Season)      | Position         | Key Attributes
-        \                  | Recent Achievements                  |\\n|-------|---------------------|-------------|----------------------------|------------------|---------------------------------|------------------------------------|\\n|
-        1     | Lionel Messi        | Argentina   | Paris Saint-Germain (PSG)   |
-        Forward/Playmaker| Dribbling, Vision, Free kicks   | 2023 World Cup Golden
-        Ball, Club Successes |\\n| 2     | Kylian Mbapp\xE9       | France      |
-        Paris Saint-Germain (PSG)   | Forward          | Speed, Finishing, Dribbling
-        \    | Ligue 1 Top Scorer, World Cup Winner 2018|\\n| 3     | Erling Haaland
-        \     | Norway      | Manchester City             | Striker          | Strength,
-        Finishing, Positioning| Premier League Golden Boot, Champions League Impact|\\n|
-        4     | Kevin De Bruyne     | Belgium     | Manchester City             |
-        Midfielder       | Passing, Vision, Creativity     | Premier League Titles,
-        Key Playmaker|\\n| 5     | Robert Lewandowski  | Poland      | FC Barcelona
-        \              | Striker          | Finishing, Positioning, Composure| La
-        Liga Top Scorer, Consistent Scorer|\\n| 6     | Neymar Jr.          | Brazil
-        \     | Al-Hilal                   | Forward/Winger   | Dribbling, Creativity,
-        Flair    | Copa America Titles, Club Success |\\n| 7     | Mohamed Salah       |
-        Egypt       | Liverpool                  | Forward/Winger   | Pace, Finishing,
-        Work Rate      | Premier League Golden Boot, Champions League Winner|\\n|
-        8     | Vin\xEDcius Jr.        | Brazil      | Real Madrid                |
-        Winger           | Speed, Dribbling, Crossing     | La Liga Titles, UEFA Champions
-        League Winner|\\n| 9     | Luka Modri\u0107         | Croatia     | Real Madrid
-        \               | Midfielder       | Passing, Control, Experience    | Ballon
-        d\u2019Or 2018, Multiple Champions League Titles|\\n| 10    | Karim Benzema
-        \      | France      | Al-Ittihad                | Striker          | Finishing,
-        Link-up Play, Movements| Ballon d\u2019Or 2022, UEFA Champions League Top
-        Scorer |\\n\\n### Notes:\\n- The rankings reflect a combination of individual
-        skill, recent performance, consistency, and influence on the game.\\n- Players\u2019
-        clubs are based on the 2023/24 season affiliations.\\n- Achievements highlight
-        recent titles, awards, or standout contributions.\\n\\nIf you would like me
-        to focus on specific leagues, historical players, or emerging talents, just
-        let me know!\",\n        \"refusal\": null,\n        \"annotations\": []\n
-        \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
-        \ ],\n  \"usage\": {\n    \"prompt_tokens\": 68,\n    \"completion_tokens\":
-        605,\n    \"total_tokens\": 673,\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_75546bd1a7\"\n}\n"
+      string: "{\n  \"id\": \"chatcmpl-BgugJkCDtB2EfvAMiIFK0reeLKFBl\",\n  \"object\": \"chat.completion\",\n  \"created\": 1749567359,\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: Here is an updated list of the top 10 best soccer players in the world as of October 2023, excluding Brazilian players:\\n\\n1. **Lionel Messi (Inter Miami CF)**\\n   - Position: Forward\\n   - Key Attributes: Dribbling, vision, goal-scoring ability.\\n   - Achievements: Multiple Ballon d'Or winner, Copa America champion, World Cup champion (2022).\\n\\n2. **Kylian Mbappé (Paris Saint-Germain)**\\n   - Position: Forward\\n   - Key Attributes: Speed, technique, finishing.\\n   - Achievements: FIFA World Cup champion (2018), Ligue 1 titles, multiple domestic cups.\\n\\n3. **Erling Haaland (Manchester City)**\\n   - Position: Forward\\\
+        n   - Key Attributes: Power, speed, goal-scoring instinct.\\n   - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\\n\\n4. **Kevin De Bruyne (Manchester City)**\\n   - Position: Midfielder\\n   - Key Attributes: Passing, vision, creativity.\\n   - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\\n\\n5. **Karim Benzema (Al-Ittihad)**\\n   - Position: Forward\\n   - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\\n   - Achievements: 2022 Ballon d'Or winner, multiple Champions Leagues with Real Madrid.\\n\\n6. **Robert Lewandowski (FC Barcelona)**\\n   - Position: Forward\\n   - Key Attributes: Finishing, positioning, aerial ability.\\n   - Achievements: FIFA Best Men's Player, multiple Bundesliga titles, La Liga champion (2023).\\n\\n7. **Mohamed Salah (Liverpool)**\\n   - Position: Forward\\n   - Key Attributes: Speed, finishing, dribbling.\\n   - Achievements: Premier League\
+        \ champion, FA Cup, UEFA Champions League winner.\\n\\n8. **Vinícius Júnior (Real Madrid)**\\n   - Position: Forward\\n   - Key Attributes: Speed, dribbling, creativity.\\n   - Achievements: UEFA Champions League winner (2022), La Liga champion (2023).\\n\\n9. **Luka Modrić (Real Madrid)**\\n   - Position: Midfielder\\n   - Key Attributes: Passing, vision, tactical intelligence.\\n   - Achievements: Multiple Champions League titles, Ballon d'Or winner (2018).\\n\\n10. **Harry Kane (Bayern Munich)**\\n    - Position: Forward\\n    - Key Attributes: Goal-scoring, technique, playmaking.\\n    - Achievements: Golden Boot winner, Premier League titles, UEFA European Championship runner-up.\\n\\nThis list has been adjusted to exclude Brazilian players and focuses on those who have made significant impacts in their clubs and on the international stage as of October 2023. Each player is recognized for their exceptional skills, performances, and achievements.\",\n        \"refusal\": null,\n\
+        \        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 781,\n    \"completion_tokens\": 610,\n    \"total_tokens\": 1391,\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_34a54ae93c\"\n}\n"
     headers:
       CF-RAY:
-      - CF-RAY-XXX
+      - 94d9b6782db84d3b-GRU
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Fri, 06 Feb 2026 18:41:49 GMT
+      - Tue, 10 Jun 2025 14:56:30 GMT
       Server:
       - cloudflare
-      Strict-Transport-Security:
-      - STS-XXX
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
-      - X-CONTENT-TYPE-XXX
+      - nosniff
       access-control-expose-headers:
-      - ACCESS-CONTROL-XXX
+      - X-Request-ID
       alt-svc:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
       openai-organization:
-      - OPENAI-ORG-XXX
+      - crewai-iuxna1
       openai-processing-ms:
-      - '9044'
-      openai-project:
-      - OPENAI-PROJECT-XXX
+      - '31484'
       openai-version:
       - '2020-10-01'
-      x-openai-proxy-wasm:
-      - v0.1
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-envoy-upstream-service-time:
+      - '31490'
       x-ratelimit-limit-requests:
-      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      - '30000'
       x-ratelimit-limit-tokens:
-      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      - '150000000'
       x-ratelimit-remaining-requests:
-      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      - '29999'
       x-ratelimit-remaining-tokens:
-      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      - '149999166'
       x-ratelimit-reset-requests:
-      - X-RATELIMIT-RESET-REQUESTS-XXX
+      - 2ms
       x-ratelimit-reset-tokens:
-      - X-RATELIMIT-RESET-TOKENS-XXX
+      - 0s
       x-request-id:
-      - X-REQUEST-ID-XXX
+      - req_aa737cf40bb76af9f458bfd35f7a77a1
     status:
       code: 200
       message: OK
 - request:
-    body: '{"messages":[{"role":"system","content":"You are Sports Analyst. You are
-      an expert at gathering and organizing information. You carefully collect details
-      and present them in a structured way.\nYour personal goal is: Gather information
-      about the best soccer players"},{"role":"user","content":"\nCurrent Task: Top
-      10 best players in the world?\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}'
+    body: '{"messages": [{"role": "system", "content": "You are Sports Analyst. You are an expert at gathering and organizing information. You carefully collect details and present them in a structured way.\nYour personal goal is: Gather information about the best soccer players\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!"}, {"role": "user", "content": "Top 10 best players in the world?"}, {"role": "assistant", "content": "Thought: I now can give a great answer  \nFinal Answer: The top 10 best soccer players in the world, as of October 2023, can be identified based on their recent performances, skills, impact on games, and overall contributions to their teams. Here is the structured list:\n\n1. **Lionel Messi (Inter Miami CF)**\n   -
+      Position: Forward\n   - Key Attributes: Dribbling, vision, goal-scoring ability.\n   - Achievements: Multiple Ballon d''Or winner, Copa America champion, World Cup champion (2022).\n\n2. **Kylian Mbapp\u00e9 (Paris Saint-Germain)**\n   - Position: Forward\n   - Key Attributes: Speed, technique, finishing.\n   - Achievements: FIFA World Cup champion (2018), Ligue 1 titles, multiple domestic cups.\n\n3. **Erling Haaland (Manchester City)**\n   - Position: Forward\n   - Key Attributes: Power, speed, goal-scoring instinct.\n   - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\n\n4. **Kevin De Bruyne (Manchester City)**\n   - Position: Midfielder\n   - Key Attributes: Passing, vision, creativity.\n   - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\n\n5. **Karim Benzema (Al-Ittihad)**\n   - Position: Forward\n   - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\n   - Achievements:
+      2022 Ballon d''Or winner, multiple Champions Leagues with Real Madrid.\n\n6. **Neymar Jr. (Al Hilal)**\n   - Position: Forward\n   - Key Attributes: Flair, dribbling, creativity.\n   - Achievements: Multiple domestic league titles, Champions League runner-up.\n\n7. **Robert Lewandowski (FC Barcelona)**\n   - Position: Forward\n   - Key Attributes: Finishing, positioning, aerial ability.\n   - Achievements: FIFA Best Men''s Player, multiple Bundesliga titles, La Liga champion (2023).\n\n8. **Mohamed Salah (Liverpool)**\n   - Position: Forward\n   - Key Attributes: Speed, finishing, dribbling.\n   - Achievements: Premier League champion, FA Cup, UEFA Champions League winner.\n\n9. **Vin\u00edcius J\u00fanior (Real Madrid)**\n   - Position: Forward\n   - Key Attributes: Speed, dribbling, creativity.\n   - Achievements: UEFA Champions League winner (2022), La Liga champion (2023).\n\n10. **Luka Modri\u0107 (Real Madrid)**\n    - Position: Midfielder\n    - Key Attributes: Passing, vision,
+      tactical intelligence.\n    - Achievements: Multiple Champions League titles, Ballon d''Or winner (2018).\n\nThis list is compiled based on their current form, past performances, and contributions to their respective teams in both domestic and international competitions. Player rankings can vary based on personal opinion and specific criteria used for evaluation, but these players have consistently been regarded as some of the best in the world as of October 2023."}, {"role": "user", "content": "You are not allowed to include Brazilian players"}, {"role": "assistant", "content": "Thought: I now can give a great answer  \nFinal Answer: Here is an updated list of the top 10 best soccer players in the world as of October 2023, excluding Brazilian players:\n\n1. **Lionel Messi (Inter Miami CF)**\n   - Position: Forward\n   - Key Attributes: Dribbling, vision, goal-scoring ability.\n   - Achievements: Multiple Ballon d''Or winner, Copa America champion, World Cup champion (2022).\n\n2.
+      **Kylian Mbapp\u00e9 (Paris Saint-Germain)**\n   - Position: Forward\n   - Key Attributes: Speed, technique, finishing.\n   - Achievements: FIFA World Cup champion (2018), Ligue 1 titles, multiple domestic cups.\n\n3. **Erling Haaland (Manchester City)**\n   - Position: Forward\n   - Key Attributes: Power, speed, goal-scoring instinct.\n   - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\n\n4. **Kevin De Bruyne (Manchester City)**\n   - Position: Midfielder\n   - Key Attributes: Passing, vision, creativity.\n   - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\n\n5. **Karim Benzema (Al-Ittihad)**\n   - Position: Forward\n   - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\n   - Achievements: 2022 Ballon d''Or winner, multiple Champions Leagues with Real Madrid.\n\n6. **Robert Lewandowski (FC Barcelona)**\n   - Position: Forward\n   - Key Attributes: Finishing, positioning,
+      aerial ability.\n   - Achievements: FIFA Best Men''s Player, multiple Bundesliga titles, La Liga champion (2023).\n\n7. **Mohamed Salah (Liverpool)**\n   - Position: Forward\n   - Key Attributes: Speed, finishing, dribbling.\n   - Achievements: Premier League champion, FA Cup, UEFA Champions League winner.\n\n8. **Vin\u00edcius J\u00fanior (Real Madrid)**\n   - Position: Forward\n   - Key Attributes: Speed, dribbling, creativity.\n   - Achievements: UEFA Champions League winner (2022), La Liga champion (2023).\n\n9. **Luka Modri\u0107 (Real Madrid)**\n   - Position: Midfielder\n   - Key Attributes: Passing, vision, tactical intelligence.\n   - Achievements: Multiple Champions League titles, Ballon d''Or winner (2018).\n\n10. **Harry Kane (Bayern Munich)**\n    - Position: Forward\n    - Key Attributes: Goal-scoring, technique, playmaking.\n    - Achievements: Golden Boot winner, Premier League titles, UEFA European Championship runner-up.\n\nThis list has been adjusted to exclude Brazilian
+      players and focuses on those who have made significant impacts in their clubs and on the international stage as of October 2023. Each player is recognized for their exceptional skills, performances, and achievements."}, {"role": "user", "content": "You are not allowed to include Brazilian players"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
     headers:
-      User-Agent:
-      - X-USER-AGENT-XXX
       accept:
       - application/json
       accept-encoding:
-      - ACCEPT-ENCODING-XXX
-      authorization:
-      - AUTHORIZATION-XXX
+      - gzip, deflate, zstd
       connection:
       - keep-alive
       content-length:
-      - '404'
+      - '6337'
       content-type:
       - application/json
       cookie:
-      - COOKIE-XXX
+      - __cf_bm=8Yv8F0ZCFAo2lf.qoqxao70yxyjVvIV90zQqVF6bVzQ-1749567342-1.0.1.1-fZgnv3RDfunvCO1koxwwFJrHnxSx_rwS_FHvQ6xxDPpKHwYr7dTqIQLZrNgSX5twGyK4F22rUmkuiS6KMVogcinChk8lmHtJBTUVTFjr2KU; _cfuvid=wzh8YnmXvLq1G0RcIVijtzboQtCZyIe2uZiochkBLqE-1749567342267-0.0.1.1-604800000
       host:
       - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.78.0
       x-stainless-arch:
-      - X-STAINLESS-ARCH-XXX
+      - arm64
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - X-STAINLESS-OS-XXX
+      - MacOS
       x-stainless-package-version:
-      - 1.83.0
+      - 1.78.0
+      x-stainless-raw-response:
+      - 'true'
       x-stainless-read-timeout:
-      - X-STAINLESS-READ-TIMEOUT-XXX
+      - '600.0'
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.5
+      - 3.12.9
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-D6L4102eMwTEPeHxfyN9Kh7rjBoX6\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1770403309,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
-        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-        \"assistant\",\n        \"content\": \"Certainly! Here is a list of the top
-        10 best soccer players in the world as of 2024, considering their recent performances,
-        skills, impact, and accolades:\\n\\n1. **Lionel Messi**  \\n   - Nationality:
-        Argentine  \\n   - Position: Forward  \\n   - Key Achievements: 7 Ballon d'Or
-        awards, led Argentina to 2021 Copa Am\xE9rica victory and 2022 FIFA World
-        Cup triumph, exceptional dribbling and playmaking skills.\\n\\n2. **Kylian
-        Mbapp\xE9**  \\n   - Nationality: French  \\n   - Position: Forward  \\n   -
-        Key Achievements: FIFA World Cup winner (2018), multiple Ligue 1 titles, known
-        for incredible speed, finishing, and consistency.\\n\\n3. **Erling Haaland**
-        \ \\n   - Nationality: Norwegian  \\n   - Position: Striker  \\n   - Key Achievements:
-        Premier League Golden Boot winner (2022-23), prolific goal scorer, physical
-        presence, and finishing ability.\\n\\n4. **Karim Benzema**  \\n   - Nationality:
-        French  \\n   - Position: Forward  \\n   - Key Achievements: 2022 Ballon d'Or
-        winner, key player for Real Madrid\u2019s recent Champions League victories,
-        excellent technical skills and leadership.\\n\\n5. **Kevin De Bruyne**  \\n
-        \  - Nationality: Belgian  \\n   - Position: Midfielder  \\n   - Key Achievements:
-        Premier League playmaker, known for vision, passing accuracy, and creativity.\\n\\n6.
-        **Robert Lewandowski**  \\n   - Nationality: Polish  \\n   - Position: Striker
-        \ \\n   - Key Achievements: Multiple Bundesliga top scorer titles, consistent
-        goal scorer, known for positioning and finishing.\\n\\n7. **Neymar Jr.**  \\n
-        \  - Nationality: Brazilian  \\n   - Position: Forward  \\n   - Key Achievements:
-        Exceptional dribbling, creativity, and flair; multiple domestic titles and
-        Copa Libertadores winner.\\n\\n8. **Mohamed Salah**  \\n   - Nationality:
-        Egyptian  \\n   - Position: Forward  \\n   - Key Achievements: Premier League
-        Golden Boot, consistent goal scoring with Liverpool, known for speed and finishing.\\n\\n9.
-        **Luka Modri\u0107**  \\n   - Nationality: Croatian  \\n   - Position: Midfielder
-        \ \\n   - Key Achievements: 2018 Ballon d\u2019Or winner, pivotal midfield
-        maestro, excellent passing and control.\\n\\n10. **Thibaut Courtois**  \\n
-        \   - Nationality: Belgian  \\n    - Position: Goalkeeper  \\n    - Key Achievements:
-        Exceptional shot-stopper, key player in Real Madrid's recent successes.\\n\\nThis
-        list includes a blend of forwards, midfielders, and a goalkeeper, showcasing
-        the best talents in various positions worldwide. The rankings may vary slightly
-        depending on current form and opinions, but these players consistently rank
-        among the best globally.\",\n        \"refusal\": null,\n        \"annotations\":
-        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
-        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 68,\n    \"completion_tokens\":
-        575,\n    \"total_tokens\": 643,\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_75546bd1a7\"\n}\n"
+      string: "{\n  \"id\": \"chatcmpl-BgugsAmyI50uQ6SpCp89ZZY4eD1Pz\",\n  \"object\": \"chat.completion\",\n  \"created\": 1749567394,\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: Here is the revised list of the top 10 best soccer players in the world as of October 2023, explicitly excluding Brazilian players:\\n\\n1. **Lionel Messi (Inter Miami CF)**\\n   - Position: Forward\\n   - Key Attributes: Dribbling, vision, goal-scoring ability.\\n   - Achievements: Multiple Ballon d'Or winner, Copa America champion, World Cup champion (2022).\\n\\n2. **Kylian Mbappé (Paris Saint-Germain)**\\n   - Position: Forward\\n   - Key Attributes: Speed, technique, finishing.\\n   - Achievements: FIFA World Cup champion (2018), multiple Ligue 1 titles, and various domestic cups.\\n\\n3. **Erling Haaland (Manchester City)**\\n\
+        \   - Position: Forward\\n   - Key Attributes: Power, speed, goal-scoring instinct.\\n   - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\\n\\n4. **Kevin De Bruyne (Manchester City)**\\n   - Position: Midfielder\\n   - Key Attributes: Passing, vision, creativity.\\n   - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\\n\\n5. **Karim Benzema (Al-Ittihad)**\\n   - Position: Forward\\n   - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\\n   - Achievements: 2022 Ballon d'Or winner, multiple Champions Leagues with Real Madrid.\\n\\n6. **Robert Lewandowski (FC Barcelona)**\\n   - Position: Forward\\n   - Key Attributes: Finishing, positioning, aerial ability.\\n   - Achievements: FIFA Best Men's Player, multiple Bundesliga titles, La Liga champion (2023).\\n\\n7. **Mohamed Salah (Liverpool)**\\n   - Position: Forward\\n   - Key Attributes: Speed, finishing, dribbling.\\n   -\
+        \ Achievements: Premier League champion, FA Cup, UEFA Champions League winner.\\n\\n8. **Luka Modrić (Real Madrid)**\\n   - Position: Midfielder\\n   - Key Attributes: Passing, vision, tactical intelligence.\\n   - Achievements: Multiple Champions League titles, Ballon d'Or winner (2018).\\n\\n9. **Harry Kane (Bayern Munich)**\\n   - Position: Forward\\n   - Key Attributes: Goal-scoring, technique, playmaking.\\n   - Achievements: Golden Boot winner, Premier League titles, UEFA European Championship runner-up.\\n\\n10. **Rodri (Manchester City)**\\n    - Position: Midfielder\\n    - Key Attributes: Defensive skills, passing, positional awareness.\\n    - Achievements: Premier League titles, UEFA Champions League winner (2023).\\n\\nThis list is curated while adhering to the restriction of excluding Brazilian players. Each player included has demonstrated exceptional skills and remarkable performances, solidifying their status as some of the best in the world as of October 2023.\"\
+        ,\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 1407,\n    \"completion_tokens\": 605,\n    \"total_tokens\": 2012,\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_62a23a81ef\"\n}\n"
     headers:
       CF-RAY:
-      - CF-RAY-XXX
+      - 94d9b7561f204d3b-GRU
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Fri, 06 Feb 2026 18:41:57 GMT
+      - Tue, 10 Jun 2025 14:56:46 GMT
       Server:
       - cloudflare
-      Strict-Transport-Security:
-      - STS-XXX
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
-      - X-CONTENT-TYPE-XXX
+      - nosniff
       access-control-expose-headers:
-      - ACCESS-CONTROL-XXX
+      - X-Request-ID
       alt-svc:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
       openai-organization:
-      - OPENAI-ORG-XXX
+      - crewai-iuxna1
       openai-processing-ms:
-      - '7948'
-      openai-project:
-      - OPENAI-PROJECT-XXX
+      - '12189'
       openai-version:
       - '2020-10-01'
-      x-openai-proxy-wasm:
-      - v0.1
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-envoy-upstream-service-time:
+      - '12193'
       x-ratelimit-limit-requests:
-      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      - '30000'
       x-ratelimit-limit-tokens:
-      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      - '150000000'
       x-ratelimit-remaining-requests:
-      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      - '29999'
       x-ratelimit-remaining-tokens:
-      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      - '149998513'
       x-ratelimit-reset-requests:
-      - X-RATELIMIT-RESET-REQUESTS-XXX
+      - 2ms
       x-ratelimit-reset-tokens:
-      - X-RATELIMIT-RESET-TOKENS-XXX
+      - 0s
       x-request-id:
-      - X-REQUEST-ID-XXX
+      - req_1098f5a5384f4a26aecf0c9e4e4d1fc0
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Sports Analyst. You are an expert at gathering and organizing information. You carefully collect details and present them in a structured way.\nYour personal goal is: Gather information about the best soccer players\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!"}, {"role": "user", "content": "Top 10 best players in the world?"}, {"role": "assistant", "content": "Thought: I now can give a great answer  \nFinal Answer: The top 10 best soccer players in the world, as of October 2023, can be identified based on their recent performances, skills, impact on games, and overall contributions to their teams. Here is the structured list:\n\n1. **Lionel Messi (Inter Miami CF)**\n   -
+      Position: Forward\n   - Key Attributes: Dribbling, vision, goal-scoring ability.\n   - Achievements: Multiple Ballon d''Or winner, Copa America champion, World Cup champion (2022).\n\n2. **Kylian Mbapp\u00e9 (Paris Saint-Germain)**\n   - Position: Forward\n   - Key Attributes: Speed, technique, finishing.\n   - Achievements: FIFA World Cup champion (2018), Ligue 1 titles, multiple domestic cups.\n\n3. **Erling Haaland (Manchester City)**\n   - Position: Forward\n   - Key Attributes: Power, speed, goal-scoring instinct.\n   - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\n\n4. **Kevin De Bruyne (Manchester City)**\n   - Position: Midfielder\n   - Key Attributes: Passing, vision, creativity.\n   - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\n\n5. **Karim Benzema (Al-Ittihad)**\n   - Position: Forward\n   - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\n   - Achievements:
+      2022 Ballon d''Or winner, multiple Champions Leagues with Real Madrid.\n\n6. **Neymar Jr. (Al Hilal)**\n   - Position: Forward\n   - Key Attributes: Flair, dribbling, creativity.\n   - Achievements: Multiple domestic league titles, Champions League runner-up.\n\n7. **Robert Lewandowski (FC Barcelona)**\n   - Position: Forward\n   - Key Attributes: Finishing, positioning, aerial ability.\n   - Achievements: FIFA Best Men''s Player, multiple Bundesliga titles, La Liga champion (2023).\n\n8. **Mohamed Salah (Liverpool)**\n   - Position: Forward\n   - Key Attributes: Speed, finishing, dribbling.\n   - Achievements: Premier League champion, FA Cup, UEFA Champions League winner.\n\n9. **Vin\u00edcius J\u00fanior (Real Madrid)**\n   - Position: Forward\n   - Key Attributes: Speed, dribbling, creativity.\n   - Achievements: UEFA Champions League winner (2022), La Liga champion (2023).\n\n10. **Luka Modri\u0107 (Real Madrid)**\n    - Position: Midfielder\n    - Key Attributes: Passing, vision,
+      tactical intelligence.\n    - Achievements: Multiple Champions League titles, Ballon d''Or winner (2018).\n\nThis list is compiled based on their current form, past performances, and contributions to their respective teams in both domestic and international competitions. Player rankings can vary based on personal opinion and specific criteria used for evaluation, but these players have consistently been regarded as some of the best in the world as of October 2023."}, {"role": "user", "content": "You are not allowed to include Brazilian players"}, {"role": "assistant", "content": "Thought: I now can give a great answer  \nFinal Answer: Here is an updated list of the top 10 best soccer players in the world as of October 2023, excluding Brazilian players:\n\n1. **Lionel Messi (Inter Miami CF)**\n   - Position: Forward\n   - Key Attributes: Dribbling, vision, goal-scoring ability.\n   - Achievements: Multiple Ballon d''Or winner, Copa America champion, World Cup champion (2022).\n\n2.
+      **Kylian Mbapp\u00e9 (Paris Saint-Germain)**\n   - Position: Forward\n   - Key Attributes: Speed, technique, finishing.\n   - Achievements: FIFA World Cup champion (2018), Ligue 1 titles, multiple domestic cups.\n\n3. **Erling Haaland (Manchester City)**\n   - Position: Forward\n   - Key Attributes: Power, speed, goal-scoring instinct.\n   - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\n\n4. **Kevin De Bruyne (Manchester City)**\n   - Position: Midfielder\n   - Key Attributes: Passing, vision, creativity.\n   - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\n\n5. **Karim Benzema (Al-Ittihad)**\n   - Position: Forward\n   - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\n   - Achievements: 2022 Ballon d''Or winner, multiple Champions Leagues with Real Madrid.\n\n6. **Robert Lewandowski (FC Barcelona)**\n   - Position: Forward\n   - Key Attributes: Finishing, positioning,
+      aerial ability.\n   - Achievements: FIFA Best Men''s Player, multiple Bundesliga titles, La Liga champion (2023).\n\n7. **Mohamed Salah (Liverpool)**\n   - Position: Forward\n   - Key Attributes: Speed, finishing, dribbling.\n   - Achievements: Premier League champion, FA Cup, UEFA Champions League winner.\n\n8. **Vin\u00edcius J\u00fanior (Real Madrid)**\n   - Position: Forward\n   - Key Attributes: Speed, dribbling, creativity.\n   - Achievements: UEFA Champions League winner (2022), La Liga champion (2023).\n\n9. **Luka Modri\u0107 (Real Madrid)**\n   - Position: Midfielder\n   - Key Attributes: Passing, vision, tactical intelligence.\n   - Achievements: Multiple Champions League titles, Ballon d''Or winner (2018).\n\n10. **Harry Kane (Bayern Munich)**\n    - Position: Forward\n    - Key Attributes: Goal-scoring, technique, playmaking.\n    - Achievements: Golden Boot winner, Premier League titles, UEFA European Championship runner-up.\n\nThis list has been adjusted to exclude Brazilian
+      players and focuses on those who have made significant impacts in their clubs and on the international stage as of October 2023. Each player is recognized for their exceptional skills, performances, and achievements."}, {"role": "user", "content": "You are not allowed to include Brazilian players"}, {"role": "assistant", "content": "Thought: I now can give a great answer  \nFinal Answer: Here is the revised list of the top 10 best soccer players in the world as of October 2023, explicitly excluding Brazilian players:\n\n1. **Lionel Messi (Inter Miami CF)**\n   - Position: Forward\n   - Key Attributes: Dribbling, vision, goal-scoring ability.\n   - Achievements: Multiple Ballon d''Or winner, Copa America champion, World Cup champion (2022).\n\n2. **Kylian Mbapp\u00e9 (Paris Saint-Germain)**\n   - Position: Forward\n   - Key Attributes: Speed, technique, finishing.\n   - Achievements: FIFA World Cup champion (2018), multiple Ligue 1 titles, and various domestic cups.\n\n3. **Erling Haaland
+      (Manchester City)**\n   - Position: Forward\n   - Key Attributes: Power, speed, goal-scoring instinct.\n   - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\n\n4. **Kevin De Bruyne (Manchester City)**\n   - Position: Midfielder\n   - Key Attributes: Passing, vision, creativity.\n   - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\n\n5. **Karim Benzema (Al-Ittihad)**\n   - Position: Forward\n   - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\n   - Achievements: 2022 Ballon d''Or winner, multiple Champions Leagues with Real Madrid.\n\n6. **Robert Lewandowski (FC Barcelona)**\n   - Position: Forward\n   - Key Attributes: Finishing, positioning, aerial ability.\n   - Achievements: FIFA Best Men''s Player, multiple Bundesliga titles, La Liga champion (2023).\n\n7. **Mohamed Salah (Liverpool)**\n   - Position: Forward\n   - Key Attributes: Speed, finishing, dribbling.\n   - Achievements:
+      Premier League champion, FA Cup, UEFA Champions League winner.\n\n8. **Luka Modri\u0107 (Real Madrid)**\n   - Position: Midfielder\n   - Key Attributes: Passing, vision, tactical intelligence.\n   - Achievements: Multiple Champions League titles, Ballon d''Or winner (2018).\n\n9. **Harry Kane (Bayern Munich)**\n   - Position: Forward\n   - Key Attributes: Goal-scoring, technique, playmaking.\n   - Achievements: Golden Boot winner, Premier League titles, UEFA European Championship runner-up.\n\n10. **Rodri (Manchester City)**\n    - Position: Midfielder\n    - Key Attributes: Defensive skills, passing, positional awareness.\n    - Achievements: Premier League titles, UEFA Champions League winner (2023).\n\nThis list is curated while adhering to the restriction of excluding Brazilian players. Each player included has demonstrated exceptional skills and remarkable performances, solidifying their status as some of the best in the world as of October 2023."}, {"role": "user", "content":
+      "You are not allowed to include Brazilian players"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '9093'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=8Yv8F0ZCFAo2lf.qoqxao70yxyjVvIV90zQqVF6bVzQ-1749567342-1.0.1.1-fZgnv3RDfunvCO1koxwwFJrHnxSx_rwS_FHvQ6xxDPpKHwYr7dTqIQLZrNgSX5twGyK4F22rUmkuiS6KMVogcinChk8lmHtJBTUVTFjr2KU; _cfuvid=wzh8YnmXvLq1G0RcIVijtzboQtCZyIe2uZiochkBLqE-1749567342267-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.78.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.78.0
+      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-BguhCefN1bN2OeYRo5ChhUqNBLUda\",\n  \"object\": \"chat.completion\",\n  \"created\": 1749567414,\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: Here is a refined list of the top 10 best soccer players in the world as of October 2023, ensuring that no Brazilian players are included:\\n\\n1. **Lionel Messi (Inter Miami CF)**\\n   - Position: Forward\\n   - Key Attributes: Dribbling, vision, goal-scoring ability.\\n   - Achievements: Multiple Ballon d'Or winner, Copa America champion, World Cup champion (2022).\\n\\n2. **Kylian Mbappé (Paris Saint-Germain)**\\n   - Position: Forward\\n   - Key Attributes: Speed, technique, finishing.\\n   - Achievements: FIFA World Cup champion (2018), multiple Ligue 1 titles, various domestic cups.\\n\\n3. **Erling Haaland (Manchester City)**\\\
+        n   - Position: Forward\\n   - Key Attributes: Power, speed, goal-scoring instinct.\\n   - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\\n\\n4. **Kevin De Bruyne (Manchester City)**\\n   - Position: Midfielder\\n   - Key Attributes: Passing, vision, creativity.\\n   - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\\n\\n5. **Karim Benzema (Al-Ittihad)**\\n   - Position: Forward\\n   - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\\n   - Achievements: 2022 Ballon d'Or winner, multiple Champions Leagues with Real Madrid.\\n\\n6. **Robert Lewandowski (FC Barcelona)**\\n   - Position: Forward\\n   - Key Attributes: Finishing, positioning, aerial ability.\\n   - Achievements: FIFA Best Men's Player, multiple Bundesliga titles, La Liga champion (2023).\\n\\n7. **Mohamed Salah (Liverpool)**\\n   - Position: Forward\\n   - Key Attributes: Speed, finishing, dribbling.\\n   -\
+        \ Achievements: Premier League champion, FA Cup, UEFA Champions League winner.\\n\\n8. **Luka Modrić (Real Madrid)**\\n   - Position: Midfielder\\n   - Key Attributes: Passing, vision, tactical intelligence.\\n   - Achievements: Multiple Champions League titles, Ballon d'Or winner (2018).\\n\\n9. **Harry Kane (Bayern Munich)**\\n   - Position: Forward\\n   - Key Attributes: Goal-scoring, technique, playmaking.\\n   - Achievements: Golden Boot winner, multiple Premier League titles, UEFA European Championship runner-up.\\n\\n10. **Son Heung-min (Tottenham Hotspur)**\\n    - Position: Forward\\n    - Key Attributes: Speed, finishing, playmaking.\\n    - Achievements: Premier League Golden Boot winner, multiple domestic cup titles.\\n\\nThis list has been carefully revised to exclude all Brazilian players while highlighting some of the most talented individuals in soccer as of October 2023. Each player has showcased remarkable effectiveness and skill, contributing significantly to their\
+        \ teams on both domestic and international stages.\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 2028,\n    \"completion_tokens\": 614,\n    \"total_tokens\": 2642,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 1280,\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_34a54ae93c\"\n}\n"
+    headers:
+      CF-RAY:
+      - 94d9b7d24d991d2c-GRU
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 10 Jun 2025 14:57:29 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:
+      - '35291'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-envoy-upstream-service-time:
+      - '35294'
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149997855'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_4676152d4227ac1825d1240ddef231d6
     status:
       code: 200
       message: OK

lib/crewai/tests/cassettes/agents/test_lite_agent_inside_flow_sync.yaml

@@ -1,8 +1,14 @@
 interactions:
 - request:
     body: '{"messages":[{"role":"system","content":"You are Test Agent. A helpful
-      test assistant\nYour personal goal is: Answer questions"},{"role":"user","content":"\nCurrent
-      Task: What is 2+2? Reply with just the number.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+      test assistant\nYour personal goal is: Answer questions\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:
+      What is 2+2? Reply with just the number.\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"}'
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -15,7 +21,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '272'
+      - '673'
       content-type:
       - application/json
       host:
@@ -37,22 +43,23 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.5
+      - 3.13.3
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-D6L4AzMHXLXDfyclWS6fJSwS0cvOl\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1770403318,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      string: "{\n  \"id\": \"chatcmpl-Cy7b0HjL79y39EkUcMLrRhPFe3XGj\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768444914,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\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\": 50,\n    \"completion_tokens\":
-        1,\n    \"total_tokens\": 51,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+        Answer: 4\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
+        \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+        \ \"usage\": {\n    \"prompt_tokens\": 136,\n    \"completion_tokens\": 13,\n
+        \   \"total_tokens\": 149,\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_f4ae844694\"\n}\n"
+        \"default\",\n  \"system_fingerprint\": \"fp_8bbc38b4db\"\n}\n"
     headers:
       CF-RAY:
       - CF-RAY-XXX
@@ -61,7 +68,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 06 Feb 2026 18:41:58 GMT
+      - Thu, 15 Jan 2026 02:41:55 GMT
       Server:
       - cloudflare
       Set-Cookie:
@@ -78,14 +85,18 @@ interactions:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
+      content-length:
+      - '857'
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '264'
+      - '341'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '358'
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:

lib/crewai/tests/cassettes/agents/test_lite_agent_standalone_still_works.yaml

@@ -1,8 +1,14 @@
 interactions:
 - request:
     body: '{"messages":[{"role":"system","content":"You are Standalone Agent. A helpful
-      assistant\nYour personal goal is: Answer questions"},{"role":"user","content":"\nCurrent
-      Task: What is 5+5? Reply with just the number.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+      assistant\nYour personal goal is: Answer questions\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:
+      What is 5+5? Reply with just the number.\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"}'
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -15,7 +21,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '273'
+      - '674'
       content-type:
       - application/json
       host:
@@ -37,22 +43,23 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.5
+      - 3.13.3
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-D6L3cLs2ndBaXV2wnqYCdi6X1ykvv\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1770403284,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      string: "{\n  \"id\": \"chatcmpl-Cy7azhPwUHQ0p5tdhxSAmLPoE8UgC\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768444913,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
         \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-        \"assistant\",\n        \"content\": \"10\",\n        \"refusal\": null,\n
-        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
-        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 50,\n    \"completion_tokens\":
-        1,\n    \"total_tokens\": 51,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+        Answer: 10\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
+        \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+        \ \"usage\": {\n    \"prompt_tokens\": 136,\n    \"completion_tokens\": 13,\n
+        \   \"total_tokens\": 149,\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_f4ae844694\"\n}\n"
+        \"default\",\n  \"system_fingerprint\": \"fp_29330a9688\"\n}\n"
     headers:
       CF-RAY:
       - CF-RAY-XXX
@@ -61,7 +68,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 06 Feb 2026 18:41:25 GMT
+      - Thu, 15 Jan 2026 02:41:54 GMT
       Server:
       - cloudflare
       Set-Cookie:
@@ -78,14 +85,18 @@ interactions:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
+      content-length:
+      - '858'
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '270'
+      - '455'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '583'
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:

lib/crewai/tests/cassettes/agents/test_multiple_agents_in_same_flow.yaml

@@ -1,8 +1,13 @@
 interactions:
 - request:
     body: '{"messages":[{"role":"system","content":"You are First Agent. A friendly
-      greeter\nYour personal goal is: Greet users"},{"role":"user","content":"\nCurrent
-      Task: Say hello\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+      greeter\nYour personal goal is: Greet users\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: Say
+      hello\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"}'
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -15,7 +20,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '231'
+      - '632'
       content-type:
       - application/json
       host:
@@ -37,22 +42,24 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.5
+      - 3.13.3
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-D6L4A8Aad6P1YUxWjQpvyltn8GaKT\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1770403318,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      string: "{\n  \"id\": \"chatcmpl-CyRKzgODZ9yn3F9OkaXsscLk2Ln3N\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768520801,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
         \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-        \"assistant\",\n        \"content\": \"Hello! \U0001F60A How are you today?\",\n
-        \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
-        null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-        41,\n    \"completion_tokens\": 8,\n    \"total_tokens\": 49,\n    \"prompt_tokens_details\":
+        \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+        Answer: Hello! Welcome! I'm so glad to see you here. If you need any assistance
+        or have any questions, feel free to ask. Have a wonderful day!\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        127,\n    \"completion_tokens\": 43,\n    \"total_tokens\": 170,\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_f4ae844694\"\n}\n"
+        \"default\",\n  \"system_fingerprint\": \"fp_c4585b5b9c\"\n}\n"
     headers:
       CF-RAY:
       - CF-RAY-XXX
@@ -61,7 +68,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 06 Feb 2026 18:41:58 GMT
+      - Thu, 15 Jan 2026 23:46:42 GMT
       Server:
       - cloudflare
       Set-Cookie:
@@ -78,14 +85,18 @@ interactions:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
+      content-length:
+      - '990'
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '325'
+      - '880'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '1160'
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:
@@ -107,8 +118,13 @@ interactions:
       message: OK
 - request:
     body: '{"messages":[{"role":"system","content":"You are Second Agent. A polite
-      farewell agent\nYour personal goal is: Say goodbye"},{"role":"user","content":"\nCurrent
-      Task: Say goodbye\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
+      farewell agent\nYour personal goal is: Say goodbye\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:
+      Say goodbye\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"}'
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -121,7 +137,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '239'
+      - '640'
       content-type:
       - application/json
       host:
@@ -143,24 +159,27 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.5
+      - 3.13.3
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-D6L4BLMYC3ODccwbKfBIdtrEyd3no\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1770403319,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      string: "{\n  \"id\": \"chatcmpl-CyRL1Ua2PkK5xXPp3KeF0AnGAk3JP\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768520803,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
         \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-        \"assistant\",\n        \"content\": \"Thank you for the time we've spent
-        together! I wish you all the best in your future endeavors. Take care, and
-        until we meet again, goodbye!\",\n        \"refusal\": null,\n        \"annotations\":
+        \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+        Answer: As we reach the end of our conversation, I want to express my gratitude
+        for the time we've shared. It's been a pleasure assisting you, and I hope
+        you found our interaction helpful and enjoyable. Remember, whenever you need
+        assistance, I'm just a message away. Wishing you all the best in your future
+        endeavors. Goodbye and take care!\",\n        \"refusal\": null,\n        \"annotations\":
         []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
-        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 40,\n    \"completion_tokens\":
-        31,\n    \"total_tokens\": 71,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 126,\n    \"completion_tokens\":
+        79,\n    \"total_tokens\": 205,\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_f4ae844694\"\n}\n"
+        \"default\",\n  \"system_fingerprint\": \"fp_29330a9688\"\n}\n"
     headers:
       CF-RAY:
       - CF-RAY-XXX
@@ -169,7 +188,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 06 Feb 2026 18:41:59 GMT
+      - Thu, 15 Jan 2026 23:46:44 GMT
       Server:
       - cloudflare
       Set-Cookie:
@@ -186,14 +205,18 @@ interactions:
       - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
+      content-length:
+      - '1189'
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '726'
+      - '1363'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '1605'
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:

lib/crewai/tests/cassettes/agents/test_native_tool_calling_error_handling.yaml

@@ -2,8 +2,9 @@ interactions:
 - request:
     body: '{"messages":[{"role":"system","content":"You are Calculator. You calculate
       things.\nYour personal goal is: Perform calculations efficiently"},{"role":"user","content":"\nCurrent
-      Task: Use the failing_tool to do something."}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"failing_tool","description":"This
-      tool always fails","strict":true,"parameters":{"properties":{},"type":"object","additionalProperties":false,"required":[]}}}]}'
+      Task: Use the failing_tool to do something.\n\nThis is VERY important to you,
+      your job depends on it!"}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"failing_tool","description":"This
+      tool always fails","parameters":{"properties":{},"type":"object"}}}]}'
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -16,7 +17,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '476'
+      - '477'
       content-type:
       - application/json
       host:
@@ -38,26 +39,26 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.5
+      - 3.13.3
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-D6L3dV6acwapgRyxmnzGfuOXemtjJ\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1770403285,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      string: "{\n  \"id\": \"chatcmpl-D0vm2JDsOmy0czXPAr4vnw3wvuqYZ\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769114454,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
         \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
         \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
-        \           \"id\": \"call_GCdaOdo32pr1sSk4RzO0tiB9\",\n            \"type\":
+        \           \"id\": \"call_8xr8rPUDWzLfQ3LOWPHtBUjK\",\n            \"type\":
         \"function\",\n            \"function\": {\n              \"name\": \"failing_tool\",\n
         \             \"arguments\": \"{}\"\n            }\n          }\n        ],\n
         \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
         null,\n      \"finish_reason\": \"tool_calls\"\n    }\n  ],\n  \"usage\":
-        {\n    \"prompt_tokens\": 65,\n    \"completion_tokens\": 11,\n    \"total_tokens\":
-        76,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\":
+        {\n    \"prompt_tokens\": 78,\n    \"completion_tokens\": 11,\n    \"total_tokens\":
+        89,\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_6c0d1490cb\"\n}\n"
+        \"default\",\n  \"system_fingerprint\": \"fp_c4585b5b9c\"\n}\n"
     headers:
       CF-RAY:
       - CF-RAY-XXX
@@ -66,7 +67,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 06 Feb 2026 18:41:25 GMT
+      - Thu, 22 Jan 2026 20:40:54 GMT
       Server:
       - cloudflare
       Set-Cookie:
@@ -86,11 +87,13 @@ interactions:
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '436'
+      - '593'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '621'
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:
@@ -113,9 +116,12 @@ interactions:
 - request:
     body: '{"messages":[{"role":"system","content":"You are Calculator. You calculate
       things.\nYour personal goal is: Perform calculations efficiently"},{"role":"user","content":"\nCurrent
-      Task: Use the failing_tool to do something."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_GCdaOdo32pr1sSk4RzO0tiB9","type":"function","function":{"name":"failing_tool","arguments":"{}"}}]},{"role":"tool","tool_call_id":"call_GCdaOdo32pr1sSk4RzO0tiB9","name":"failing_tool","content":"Error
-      executing tool: This tool always fails"}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"failing_tool","description":"This
-      tool always fails","strict":true,"parameters":{"properties":{},"type":"object","additionalProperties":false,"required":[]}}}]}'
+      Task: Use the failing_tool to do something.\n\nThis is VERY important to you,
+      your job depends on it!"},{"role":"assistant","content":null,"tool_calls":[{"id":"call_8xr8rPUDWzLfQ3LOWPHtBUjK","type":"function","function":{"name":"failing_tool","arguments":"{}"}}]},{"role":"tool","tool_call_id":"call_8xr8rPUDWzLfQ3LOWPHtBUjK","content":"Error
+      executing tool: This tool always fails"},{"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-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"failing_tool","description":"This
+      tool always fails","parameters":{"properties":{},"type":"object"}}}]}'
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -128,7 +134,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '778'
+      - '941'
       content-type:
       - application/json
       cookie:
@@ -152,25 +158,22 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.5
+      - 3.13.3
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-D6L3dhjDZOoihHvXvRpbJD3ReGu0z\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1770403285,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      string: "{\n  \"id\": \"chatcmpl-D0vm3xcywoKBW75bhBXfkGJNim6Th\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769114455,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
         \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-        \"assistant\",\n        \"content\": \"The attempt to use the failing tool
-        resulted in an error, as expected since it is designed to always fail. If
-        there's anything else you would like to calculate or explore, please let me
-        know!\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
-        \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
-        \ \"usage\": {\n    \"prompt_tokens\": 93,\n    \"completion_tokens\": 40,\n
-        \   \"total_tokens\": 133,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
-        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        \"assistant\",\n        \"content\": \"Error: This tool always fails.\",\n
+        \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
+        null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        141,\n    \"completion_tokens\": 8,\n    \"total_tokens\": 149,\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_6c0d1490cb\"\n}\n"
+        \"default\",\n  \"system_fingerprint\": \"fp_c4585b5b9c\"\n}\n"
     headers:
       CF-RAY:
       - CF-RAY-XXX
@@ -179,7 +182,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 06 Feb 2026 18:41:26 GMT
+      - Thu, 22 Jan 2026 20:40:55 GMT
       Server:
       - cloudflare
       Strict-Transport-Security:
@@ -197,11 +200,13 @@ interactions:
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '776'
+      - '420'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
       - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '436'
       x-openai-proxy-wasm:
       - v0.1
       x-ratelimit-limit-requests:

lib/crewai/tests/cassettes/llms/anthropic/test_anthropic_agent_kickoff_structured_output_with_tools.yaml

@@ -43,15 +43,15 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.5
+      - 3.13.3
       x-stainless-timeout:
       - NOT_GIVEN
     method: POST
     uri: https://api.anthropic.com/v1/messages
   response:
     body:
-      string: '{"model":"claude-3-5-haiku-20241022","id":"msg_01A41GpDoJbZLUhR8dQzUcUX","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01UNPdzpayoWyqDYVE7fR5oA","name":"structured_output","input":{"operation":"Addition","result":42,"explanation":"Added
-        15 and 27 together"}}],"stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":573,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":75,"service_tier":"standard","inference_geo":"not_available"}}'
+      string: '{"model":"claude-3-5-haiku-20241022","id":"msg_0149zKBgM47utdBdrfJjM6YZ","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_011jnBYLgtzXqdmSi7JDyQHj","name":"structured_output","input":{"operation":"Addition","result":42,"explanation":"Adding
+        15 and 27 together results in 42"}}],"stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":573,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":79,"service_tier":"standard"}}'
     headers:
       CF-RAY:
       - CF-RAY-XXX
@@ -62,7 +62,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 06 Feb 2026 18:41:25 GMT
+      - Fri, 30 Jan 2026 18:56:15 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -88,7 +88,7 @@ interactions:
       anthropic-ratelimit-requests-remaining:
       - '3999'
       anthropic-ratelimit-requests-reset:
-      - '2026-02-06T18:41:24Z'
+      - '2026-01-30T18:56:14Z'
       anthropic-ratelimit-tokens-limit:
       - ANTHROPIC-RATELIMIT-TOKENS-LIMIT-XXX
       anthropic-ratelimit-tokens-remaining:
@@ -102,7 +102,7 @@ interactions:
       strict-transport-security:
       - STS-XXX
       x-envoy-upstream-service-time:
-      - '1247'
+      - '1473'
     status:
       code: 200
       message: OK

lib/crewai/tests/cassettes/llms/anthropic/test_anthropic_agent_kickoff_structured_output_without_tools.yaml

@@ -44,20 +44,21 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.5
+      - 3.13.3
       x-stainless-timeout:
       - NOT_GIVEN
     method: POST
     uri: https://api.anthropic.com/v1/messages
   response:
     body:
-      string: '{"model":"claude-3-5-haiku-20241022","id":"msg_016wrV83wm3FLYD4JoTy2Piw","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01V6Pzr7eGfuG4Q3mc25ZXwN","name":"structured_output","input":{"topic":"Benefits
+      string: '{"model":"claude-3-5-haiku-20241022","id":"msg_013iHkpmto99iyH5kDvn8uER","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Kpda2DzHBqWq9a2FS2Bdw6","name":"structured_output","input":{"topic":"Benefits
         of Remote Work","summary":"Remote work offers significant advantages for both
-        employees and employers, transforming traditional workplace dynamics.","key_points":["Increased
-        flexibility in work schedule","Reduced commute time and transportation costs","Improved
-        work-life balance","Higher productivity for many employees","Cost savings
-        for companies on office infrastructure","Expanded talent pool for hiring","Enhanced
-        employee job satisfaction"]}}],"stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":589,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":142,"service_tier":"standard","inference_geo":"not_available"}}'
+        employees and employers, transforming traditional work paradigms by providing
+        flexibility, increased productivity, and cost savings.","key_points":["Increased
+        employee flexibility and work-life balance","Reduced commuting time and associated
+        stress","Cost savings for companies on office infrastructure","Access to a
+        global talent pool","Higher employee productivity and job satisfaction","Lower
+        carbon footprint due to reduced travel"]}}],"stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":589,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":153,"service_tier":"standard"}}'
     headers:
       CF-RAY:
       - CF-RAY-XXX
@@ -68,7 +69,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 06 Feb 2026 18:41:28 GMT
+      - Fri, 30 Jan 2026 18:56:19 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -94,7 +95,7 @@ interactions:
       anthropic-ratelimit-requests-remaining:
       - '3999'
       anthropic-ratelimit-requests-reset:
-      - '2026-02-06T18:41:26Z'
+      - '2026-01-30T18:56:16Z'
       anthropic-ratelimit-tokens-limit:
       - ANTHROPIC-RATELIMIT-TOKENS-LIMIT-XXX
       anthropic-ratelimit-tokens-remaining:
@@ -108,7 +109,7 @@ interactions:
       strict-transport-security:
       - STS-XXX
       x-envoy-upstream-service-time:
-      - '2650'
+      - '3107'
     status:
       code: 200
       message: OK

lib/crewai/tests/cli/test_plus_api.py

@@ -1,8 +1,6 @@
 import os
 import unittest
-from unittest.mock import ANY, AsyncMock, MagicMock, patch
-
-import pytest
+from unittest.mock import ANY, MagicMock, patch
 
 from crewai.cli.plus_api import PlusAPI
 
@@ -70,6 +68,37 @@ class TestPlusAPI(unittest.TestCase):
         )
         self.assertEqual(response, mock_response)
 
+    @patch("crewai.cli.plus_api.PlusAPI._make_request")
+    def test_get_agent(self, mock_make_request):
+        mock_response = MagicMock()
+        mock_make_request.return_value = mock_response
+
+        response = self.api.get_agent("test_agent_handle")
+        mock_make_request.assert_called_once_with(
+            "GET", "/crewai_plus/api/v1/agents/test_agent_handle"
+        )
+        self.assertEqual(response, mock_response)
+
+    @patch("crewai.cli.plus_api.Settings")
+    @patch("requests.Session.request")
+    def test_get_agent_with_org_uuid(self, mock_make_request, mock_settings_class):
+        mock_settings = MagicMock()
+        mock_settings.org_uuid = self.org_uuid
+        mock_settings.enterprise_base_url = os.getenv('CREWAI_PLUS_URL')
+        mock_settings_class.return_value = mock_settings
+        # re-initialize Client
+        self.api = PlusAPI(self.api_key)
+
+        mock_response = MagicMock()
+        mock_make_request.return_value = mock_response
+
+        response = self.api.get_agent("test_agent_handle")
+
+        self.assert_request_with_org_id(
+            mock_make_request, "GET", "/crewai_plus/api/v1/agents/test_agent_handle"
+        )
+        self.assertEqual(response, mock_response)
+
     @patch("crewai.cli.plus_api.PlusAPI._make_request")
     def test_get_tool(self, mock_make_request):
         mock_response = MagicMock()
@@ -309,49 +338,3 @@ class TestPlusAPI(unittest.TestCase):
             custom_api.base_url,
             "https://custom-url-from-env.com",
         )
-
-
-@pytest.mark.asyncio
-@patch("httpx.AsyncClient")
-async def test_get_agent(mock_async_client_class):
-    api = PlusAPI("test_api_key")
-    mock_response = MagicMock()
-    mock_client_instance = AsyncMock()
-    mock_client_instance.get.return_value = mock_response
-    mock_async_client_class.return_value.__aenter__.return_value = mock_client_instance
-
-    response = await api.get_agent("test_agent_handle")
-
-    mock_client_instance.get.assert_called_once_with(
-        f"{api.base_url}/crewai_plus/api/v1/agents/test_agent_handle",
-        headers=api.headers,
-    )
-    assert response == mock_response
-
-
-@pytest.mark.asyncio
-@patch("httpx.AsyncClient")
-@patch("crewai.cli.plus_api.Settings")
-async def test_get_agent_with_org_uuid(mock_settings_class, mock_async_client_class):
-    org_uuid = "test-org-uuid"
-    mock_settings = MagicMock()
-    mock_settings.org_uuid = org_uuid
-    mock_settings.enterprise_base_url = os.getenv("CREWAI_PLUS_URL")
-    mock_settings_class.return_value = mock_settings
-
-    api = PlusAPI("test_api_key")
-
-    mock_response = MagicMock()
-    mock_client_instance = AsyncMock()
-    mock_client_instance.get.return_value = mock_response
-    mock_async_client_class.return_value.__aenter__.return_value = mock_client_instance
-
-    response = await api.get_agent("test_agent_handle")
-
-    mock_client_instance.get.assert_called_once_with(
-        f"{api.base_url}/crewai_plus/api/v1/agents/test_agent_handle",
-        headers=api.headers,
-    )
-    assert "X-Crewai-Organization-Id" in api.headers
-    assert api.headers["X-Crewai-Organization-Id"] == org_uuid
-    assert response == mock_response

lib/crewai/tests/events/test_event_context.py

@@ -177,40 +177,4 @@ class TestTriggeredByScope:
                 raise ValueError("test error")
         except ValueError:
             pass
-        assert get_triggering_event_id() is None
-
-
-def test_agent_scope_preserved_after_tool_error_event() -> None:
-    from crewai.events import crewai_event_bus
-    from crewai.events.types.tool_usage_events import (
-        ToolUsageErrorEvent,
-        ToolUsageStartedEvent,
-    )
-
-    push_event_scope("crew-1", "crew_kickoff_started")
-    push_event_scope("task-1", "task_started")
-    push_event_scope("agent-1", "agent_execution_started")
-
-    crewai_event_bus.emit(
-        None,
-        ToolUsageStartedEvent(
-            tool_name="test_tool",
-            tool_args={},
-            agent_key="test_agent",
-        )
-    )
-
-    crewai_event_bus.emit(
-        None,
-        ToolUsageErrorEvent(
-            tool_name="test_tool",
-            tool_args={},
-            agent_key="test_agent",
-            error=ValueError("test error"),
-        )
-    )
-
-    crewai_event_bus.flush()
-
-    assert get_current_parent_id() == "agent-1"
-
+        assert get_triggering_event_id() is None

lib/crewai/tests/memory/test_external_memory.py

@@ -308,7 +308,6 @@ def test_external_memory_search_events(
         "parent_event_id": None,
         "previous_event_id": ANY,
         "triggered_by_event_id": None,
-        "started_event_id": ANY,
         "emission_sequence": ANY,
         "query": "test value",
         "limit": 3,
@@ -331,7 +330,6 @@ def test_external_memory_search_events(
         "parent_event_id": ANY,
         "previous_event_id": ANY,
         "triggered_by_event_id": None,
-        "started_event_id": ANY,
         "emission_sequence": ANY,
         "query": "test value",
         "results": [],
@@ -392,7 +390,6 @@ def test_external_memory_save_events(
         "parent_event_id": None,
         "previous_event_id": ANY,
         "triggered_by_event_id": None,
-        "started_event_id": ANY,
         "emission_sequence": ANY,
         "value": "saving value",
         "metadata": {"task": "test_task"},
@@ -414,7 +411,6 @@ def test_external_memory_save_events(
         "parent_event_id": ANY,
         "previous_event_id": ANY,
         "triggered_by_event_id": None,
-        "started_event_id": ANY,
         "emission_sequence": ANY,
         "value": "saving value",
         "metadata": {"task": "test_task"},

lib/crewai/tests/memory/test_long_term_memory.py

@@ -74,7 +74,6 @@ def test_long_term_memory_save_events(long_term_memory):
         "parent_event_id": None,
         "previous_event_id": ANY,
         "triggered_by_event_id": None,
-        "started_event_id": ANY,
         "emission_sequence": ANY,
         "value": "test_task",
         "metadata": {"task": "test_task", "quality": 0.5},
@@ -95,7 +94,6 @@ def test_long_term_memory_save_events(long_term_memory):
         "parent_event_id": None,
         "previous_event_id": ANY,
         "triggered_by_event_id": None,
-        "started_event_id": ANY,
         "emission_sequence": ANY,
         "value": "test_task",
         "metadata": {
@@ -155,7 +153,6 @@ def test_long_term_memory_search_events(long_term_memory):
         "parent_event_id": None,
         "previous_event_id": ANY,
         "triggered_by_event_id": None,
-        "started_event_id": ANY,
         "emission_sequence": ANY,
         "query": "test query",
         "limit": 5,
@@ -178,7 +175,6 @@ def test_long_term_memory_search_events(long_term_memory):
         "parent_event_id": ANY,
         "previous_event_id": ANY,
         "triggered_by_event_id": None,
-        "started_event_id": ANY,
         "emission_sequence": ANY,
         "query": "test query",
         "results": None,

lib/crewai/tests/memory/test_short_term_memory.py

@@ -85,7 +85,6 @@ def test_short_term_memory_search_events(short_term_memory):
         "parent_event_id": None,
         "previous_event_id": ANY,
         "triggered_by_event_id": None,
-        "started_event_id": ANY,
         "emission_sequence": ANY,
         "query": "test value",
         "limit": 3,
@@ -108,7 +107,6 @@ def test_short_term_memory_search_events(short_term_memory):
         "parent_event_id": None,
         "previous_event_id": ANY,
         "triggered_by_event_id": None,
-        "started_event_id": ANY,
         "emission_sequence": ANY,
         "query": "test value",
         "results": [],
@@ -166,7 +164,6 @@ def test_short_term_memory_save_events(short_term_memory):
         "parent_event_id": None,
         "previous_event_id": ANY,
         "triggered_by_event_id": None,
-        "started_event_id": ANY,
         "emission_sequence": ANY,
         "value": "test value",
         "metadata": {"task": "test_task"},
@@ -188,7 +185,6 @@ def test_short_term_memory_save_events(short_term_memory):
         "parent_event_id": None,
         "previous_event_id": ANY,
         "triggered_by_event_id": None,
-        "started_event_id": ANY,
         "emission_sequence": ANY,
         "value": "test value",
         "metadata": {"task": "test_task"},

lib/crewai/tests/test_human_feedback_integration.py

@@ -157,176 +157,6 @@ class TestMultiStepFlows:
 
         assert execution_order == ["generate", "review", "finalize"]
 
-    def test_chained_router_feedback_steps(self):
-        """Test that a router outcome can trigger another router method.
-
-        Regression test: @listen("outcome") combined with @human_feedback(emit=...)
-        creates a method that is both a listener and a router. The flow must find
-        and execute it when the upstream router emits the matching outcome.
-        """
-        execution_order: list[str] = []
-
-        class ChainedRouterFlow(Flow):
-            @start()
-            @human_feedback(
-                message="First review:",
-                emit=["approved", "rejected"],
-                llm="gpt-4o-mini",
-            )
-            def draft(self):
-                execution_order.append("draft")
-                return "draft content"
-
-            @listen("approved")
-            @human_feedback(
-                message="Final review:",
-                emit=["publish", "revise"],
-                llm="gpt-4o-mini",
-            )
-            def final_review(self, prev: HumanFeedbackResult):
-                execution_order.append("final_review")
-                return "final content"
-
-            @listen("rejected")
-            def on_rejected(self, prev: HumanFeedbackResult):
-                execution_order.append("on_rejected")
-                return "rejected"
-
-            @listen("publish")
-            def on_publish(self, prev: HumanFeedbackResult):
-                execution_order.append("on_publish")
-                return "published"
-
-            @listen("revise")
-            def on_revise(self, prev: HumanFeedbackResult):
-                execution_order.append("on_revise")
-                return "revised"
-
-        flow = ChainedRouterFlow()
-
-        with (
-            patch.object(
-                flow,
-                "_request_human_feedback",
-                side_effect=["looks good", "ship it"],
-            ),
-            patch.object(
-                flow,
-                "_collapse_to_outcome",
-                side_effect=["approved", "publish"],
-            ),
-        ):
-            result = flow.kickoff()
-
-        assert execution_order == ["draft", "final_review", "on_publish"]
-        assert result == "published"
-        assert len(flow.human_feedback_history) == 2
-        assert flow.human_feedback_history[0].outcome == "approved"
-        assert flow.human_feedback_history[1].outcome == "publish"
-
-    def test_chained_router_rejected_path(self):
-        """Test that a start-router outcome routes to a non-router listener."""
-        execution_order: list[str] = []
-
-        class ChainedRouterFlow(Flow):
-            @start()
-            @human_feedback(
-                message="Review:",
-                emit=["approved", "rejected"],
-                llm="gpt-4o-mini",
-            )
-            def draft(self):
-                execution_order.append("draft")
-                return "draft"
-
-            @listen("approved")
-            @human_feedback(
-                message="Final:",
-                emit=["publish", "revise"],
-                llm="gpt-4o-mini",
-            )
-            def final_review(self, prev: HumanFeedbackResult):
-                execution_order.append("final_review")
-                return "final"
-
-            @listen("rejected")
-            def on_rejected(self, prev: HumanFeedbackResult):
-                execution_order.append("on_rejected")
-                return "rejected"
-
-        flow = ChainedRouterFlow()
-
-        with (
-            patch.object(
-                flow, "_request_human_feedback", return_value="bad"
-            ),
-            patch.object(
-                flow, "_collapse_to_outcome", return_value="rejected"
-            ),
-        ):
-            result = flow.kickoff()
-
-        assert execution_order == ["draft", "on_rejected"]
-        assert result == "rejected"
-        assert len(flow.human_feedback_history) == 1
-        assert flow.human_feedback_history[0].outcome == "rejected"
-
-    def test_router_and_non_router_listeners_for_same_outcome(self):
-        """Test that both router and non-router listeners fire for the same outcome."""
-        execution_order: list[str] = []
-
-        class MixedListenerFlow(Flow):
-            @start()
-            @human_feedback(
-                message="Review:",
-                emit=["approved", "rejected"],
-                llm="gpt-4o-mini",
-            )
-            def draft(self):
-                execution_order.append("draft")
-                return "draft"
-
-            @listen("approved")
-            @human_feedback(
-                message="Final:",
-                emit=["publish", "revise"],
-                llm="gpt-4o-mini",
-            )
-            def router_listener(self, prev: HumanFeedbackResult):
-                execution_order.append("router_listener")
-                return "final"
-
-            @listen("approved")
-            def plain_listener(self, prev: HumanFeedbackResult):
-                execution_order.append("plain_listener")
-                return "logged"
-
-            @listen("publish")
-            def on_publish(self, prev: HumanFeedbackResult):
-                execution_order.append("on_publish")
-                return "published"
-
-        flow = MixedListenerFlow()
-
-        with (
-            patch.object(
-                flow,
-                "_request_human_feedback",
-                side_effect=["approve it", "publish it"],
-            ),
-            patch.object(
-                flow,
-                "_collapse_to_outcome",
-                side_effect=["approved", "publish"],
-            ),
-        ):
-            flow.kickoff()
-
-        assert "draft" in execution_order
-        assert "router_listener" in execution_order
-        assert "plain_listener" in execution_order
-        assert "on_publish" in execution_order
-
 
 class TestStateManagement:
     """Tests for state management with human feedback."""

lib/crewai/tests/tools/test_tool_usage.py

@@ -10,9 +10,7 @@ from crewai import Agent, Task
 from crewai.events.event_bus import crewai_event_bus
 from crewai.events.types.tool_usage_events import (
     ToolSelectionErrorEvent,
-    ToolUsageErrorEvent,
     ToolUsageFinishedEvent,
-    ToolUsageStartedEvent,
     ToolValidateInputErrorEvent,
 )
 from crewai.tools import BaseTool
@@ -746,78 +744,3 @@ def test_tool_usage_finished_event_with_cached_result():
     assert isinstance(event.started_at, datetime.datetime)
     assert isinstance(event.finished_at, datetime.datetime)
     assert event.type == "tool_usage_finished"
-
-
-def test_tool_error_does_not_emit_finished_event():
-    from crewai.tools.tool_calling import ToolCalling
-
-    class FailingTool(BaseTool):
-        name: str = "Failing Tool"
-        description: str = "A tool that always fails"
-
-        def _run(self, **kwargs) -> str:
-            raise ValueError("Intentional failure")
-
-    failing_tool = FailingTool().to_structured_tool()
-
-    mock_agent = MagicMock()
-    mock_agent.key = "test_agent_key"
-    mock_agent.role = "test_agent_role"
-    mock_agent._original_role = "test_agent_role"
-    mock_agent.verbose = False
-    mock_agent.fingerprint = None
-    mock_agent.i18n.tools.return_value = {"name": "Add Image"}
-    mock_agent.i18n.errors.return_value = "Error: {error}"
-    mock_agent.i18n.slice.return_value = "Available tools: {tool_names}"
-
-    mock_task = MagicMock()
-    mock_task.delegations = 0
-    mock_task.name = "Test Task"
-    mock_task.description = "A test task"
-    mock_task.id = "test-task-id"
-
-    mock_action = MagicMock()
-    mock_action.tool = "failing_tool"
-    mock_action.tool_input = "{}"
-
-    tool_usage = ToolUsage(
-        tools_handler=MagicMock(cache=None, last_used_tool=None),
-        tools=[failing_tool],
-        task=mock_task,
-        function_calling_llm=None,
-        agent=mock_agent,
-        action=mock_action,
-    )
-
-    started_events = []
-    error_events = []
-    finished_events = []
-    error_received = threading.Event()
-
-    @crewai_event_bus.on(ToolUsageStartedEvent)
-    def on_started(source, event):
-        if event.tool_name == "failing_tool":
-            started_events.append(event)
-
-    @crewai_event_bus.on(ToolUsageErrorEvent)
-    def on_error(source, event):
-        if event.tool_name == "failing_tool":
-            error_events.append(event)
-            error_received.set()
-
-    @crewai_event_bus.on(ToolUsageFinishedEvent)
-    def on_finished(source, event):
-        if event.tool_name == "failing_tool":
-            finished_events.append(event)
-
-    tool_calling = ToolCalling(tool_name="failing_tool", arguments={})
-    tool_usage.use(calling=tool_calling, tool_string="Action: failing_tool")
-
-    assert error_received.wait(timeout=5), "Timeout waiting for error event"
-    crewai_event_bus.flush()
-
-    assert len(started_events) >= 1, "Expected at least one ToolUsageStartedEvent"
-    assert len(error_events) >= 1, "Expected at least one ToolUsageErrorEvent"
-    assert len(finished_events) == 0, (
-        "ToolUsageFinishedEvent should NOT be emitted after ToolUsageErrorEvent"
-    )

uv.lock

@@ -1295,7 +1295,7 @@ requires-dist = [
     { name = "json5", specifier = "~=0.10.0" },
     { name = "jsonref", specifier = "~=1.1.0" },
     { name = "litellm", marker = "extra == 'litellm'", specifier = ">=1.74.9,<3" },
-    { name = "mcp", specifier = "~=1.26.0" },
+    { name = "mcp", specifier = "~=1.23.1" },
     { name = "mem0ai", marker = "extra == 'mem0'", specifier = "~=0.1.94" },
     { name = "openai", specifier = ">=1.83.0,<3" },
     { name = "openpyxl", specifier = "~=3.1.5" },
@@ -1311,7 +1311,7 @@ requires-dist = [
     { name = "pyjwt", specifier = ">=2.9.0,<3" },
     { name = "python-dotenv", specifier = "~=1.1.1" },
     { name = "qdrant-client", extras = ["fastembed"], marker = "extra == 'qdrant'", specifier = "~=1.14.3" },
-    { name = "regex", specifier = "~=2026.1.15" },
+    { name = "regex", specifier = "~=2024.9.11" },
     { name = "tiktoken", marker = "extra == 'embeddings'", specifier = "~=0.8.0" },
     { name = "tokenizers", specifier = "~=0.20.3" },
     { name = "tomli", specifier = "~=2.0.2" },
@@ -3777,7 +3777,7 @@ wheels = [
 
 [[package]]
 name = "mcp"
-version = "1.26.0"
+version = "1.23.3"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "anyio" },
@@ -3795,9 +3795,9 @@ dependencies = [
     { name = "typing-inspection" },
     { name = "uvicorn", marker = "sys_platform != 'emscripten'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/fc/6d/62e76bbb8144d6ed86e202b5edd8a4cb631e7c8130f3f4893c3f90262b10/mcp-1.26.0.tar.gz", hash = "sha256:db6e2ef491eecc1a0d93711a76f28dec2e05999f93afd48795da1c1137142c66", size = 608005, upload-time = "2026-01-24T19:40:32.468Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/a7/a4/d06a303f45997e266f2c228081abe299bbcba216cb806128e2e49095d25f/mcp-1.23.3.tar.gz", hash = "sha256:b3b0da2cc949950ce1259c7bfc1b081905a51916fcd7c8182125b85e70825201", size = 600697, upload-time = "2025-12-09T16:04:37.351Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/fd/d9/eaa1f80170d2b7c5ba23f3b59f766f3a0bb41155fbc32a69adfa1adaaef9/mcp-1.26.0-py3-none-any.whl", hash = "sha256:904a21c33c25aa98ddbeb47273033c435e595bbacfdb177f4bd87f6dceebe1ca", size = 233615, upload-time = "2026-01-24T19:40:30.652Z" },
+    { url = "https://files.pythonhosted.org/packages/32/c6/13c1a26b47b3f3a3b480783001ada4268917c9f42d78a079c336da2e75e5/mcp-1.23.3-py3-none-any.whl", hash = "sha256:32768af4b46a1b4f7df34e2bfdf5c6011e7b63d7f1b0e321d0fdef4cd6082031", size = 231570, upload-time = "2025-12-09T16:04:35.56Z" },
 ]
 
 [[package]]
@@ -6792,91 +6792,71 @@ wheels = [
 
 [[package]]
 name = "regex"
-version = "2026.1.15"
+version = "2024.9.11"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/0b/86/07d5056945f9ec4590b518171c4254a5925832eb727b56d3c38a7476f316/regex-2026.1.15.tar.gz", hash = "sha256:164759aa25575cbc0651bef59a0b18353e54300d79ace8084c818ad8ac72b7d5", size = 414811, upload-time = "2026-01-14T23:18:02.775Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/f9/38/148df33b4dbca3bd069b963acab5e0fa1a9dbd6820f8c322d0dd6faeff96/regex-2024.9.11.tar.gz", hash = "sha256:6c188c307e8433bcb63dc1915022deb553b4203a70722fc542c363bf120a01fd", size = 399403, upload-time = "2024-09-11T19:00:09.814Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ea/d2/e6ee96b7dff201a83f650241c52db8e5bd080967cb93211f57aa448dc9d6/regex-2026.1.15-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:4e3dd93c8f9abe8aa4b6c652016da9a3afa190df5ad822907efe6b206c09896e", size = 488166, upload-time = "2026-01-14T23:13:46.408Z" },
-    { url = "https://files.pythonhosted.org/packages/23/8a/819e9ce14c9f87af026d0690901b3931f3101160833e5d4c8061fa3a1b67/regex-2026.1.15-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:97499ff7862e868b1977107873dd1a06e151467129159a6ffd07b66706ba3a9f", size = 290632, upload-time = "2026-01-14T23:13:48.688Z" },
-    { url = "https://files.pythonhosted.org/packages/d5/c3/23dfe15af25d1d45b07dfd4caa6003ad710dcdcb4c4b279909bdfe7a2de8/regex-2026.1.15-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:0bda75ebcac38d884240914c6c43d8ab5fb82e74cde6da94b43b17c411aa4c2b", size = 288500, upload-time = "2026-01-14T23:13:50.503Z" },
-    { url = "https://files.pythonhosted.org/packages/c6/31/1adc33e2f717df30d2f4d973f8776d2ba6ecf939301efab29fca57505c95/regex-2026.1.15-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:7dcc02368585334f5bc81fc73a2a6a0bbade60e7d83da21cead622faf408f32c", size = 781670, upload-time = "2026-01-14T23:13:52.453Z" },
-    { url = "https://files.pythonhosted.org/packages/23/ce/21a8a22d13bc4adcb927c27b840c948f15fc973e21ed2346c1bd0eae22dc/regex-2026.1.15-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:693b465171707bbe882a7a05de5e866f33c76aa449750bee94a8d90463533cc9", size = 850820, upload-time = "2026-01-14T23:13:54.894Z" },
-    { url = "https://files.pythonhosted.org/packages/6c/4f/3eeacdf587a4705a44484cd0b30e9230a0e602811fb3e2cc32268c70d509/regex-2026.1.15-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:b0d190e6f013ea938623a58706d1469a62103fb2a241ce2873a9906e0386582c", size = 898777, upload-time = "2026-01-14T23:13:56.908Z" },
-    { url = "https://files.pythonhosted.org/packages/79/a9/1898a077e2965c35fc22796488141a22676eed2d73701e37c73ad7c0b459/regex-2026.1.15-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:5ff818702440a5878a81886f127b80127f5d50563753a28211482867f8318106", size = 791750, upload-time = "2026-01-14T23:13:58.527Z" },
-    { url = "https://files.pythonhosted.org/packages/4c/84/e31f9d149a178889b3817212827f5e0e8c827a049ff31b4b381e76b26e2d/regex-2026.1.15-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:f052d1be37ef35a54e394de66136e30fa1191fab64f71fc06ac7bc98c9a84618", size = 782674, upload-time = "2026-01-14T23:13:59.874Z" },
-    { url = "https://files.pythonhosted.org/packages/d2/ff/adf60063db24532add6a1676943754a5654dcac8237af024ede38244fd12/regex-2026.1.15-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:6bfc31a37fd1592f0c4fc4bfc674b5c42e52efe45b4b7a6a14f334cca4bcebe4", size = 767906, upload-time = "2026-01-14T23:14:01.298Z" },
-    { url = "https://files.pythonhosted.org/packages/af/3e/e6a216cee1e2780fec11afe7fc47b6f3925d7264e8149c607ac389fd9b1a/regex-2026.1.15-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:3d6ce5ae80066b319ae3bc62fd55a557c9491baa5efd0d355f0de08c4ba54e79", size = 774798, upload-time = "2026-01-14T23:14:02.715Z" },
-    { url = "https://files.pythonhosted.org/packages/0f/98/23a4a8378a9208514ed3efc7e7850c27fa01e00ed8557c958df0335edc4a/regex-2026.1.15-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:1704d204bd42b6bb80167df0e4554f35c255b579ba99616def38f69e14a5ccb9", size = 845861, upload-time = "2026-01-14T23:14:04.824Z" },
-    { url = "https://files.pythonhosted.org/packages/f8/57/d7605a9d53bd07421a8785d349cd29677fe660e13674fa4c6cbd624ae354/regex-2026.1.15-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:e3174a5ed4171570dc8318afada56373aa9289eb6dc0d96cceb48e7358b0e220", size = 755648, upload-time = "2026-01-14T23:14:06.371Z" },
-    { url = "https://files.pythonhosted.org/packages/6f/76/6f2e24aa192da1e299cc1101674a60579d3912391867ce0b946ba83e2194/regex-2026.1.15-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:87adf5bd6d72e3e17c9cb59ac4096b1faaf84b7eb3037a5ffa61c4b4370f0f13", size = 836250, upload-time = "2026-01-14T23:14:08.343Z" },
-    { url = "https://files.pythonhosted.org/packages/11/3a/1f2a1d29453299a7858eab7759045fc3d9d1b429b088dec2dc85b6fa16a2/regex-2026.1.15-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:e85dc94595f4d766bd7d872a9de5ede1ca8d3063f3bdf1e2c725f5eb411159e3", size = 779919, upload-time = "2026-01-14T23:14:09.954Z" },
-    { url = "https://files.pythonhosted.org/packages/c0/67/eab9bc955c9dcc58e9b222c801e39cff7ca0b04261792a2149166ce7e792/regex-2026.1.15-cp310-cp310-win32.whl", hash = "sha256:21ca32c28c30d5d65fc9886ff576fc9b59bbca08933e844fa2363e530f4c8218", size = 265888, upload-time = "2026-01-14T23:14:11.35Z" },
-    { url = "https://files.pythonhosted.org/packages/1d/62/31d16ae24e1f8803bddb0885508acecaec997fcdcde9c243787103119ae4/regex-2026.1.15-cp310-cp310-win_amd64.whl", hash = "sha256:3038a62fc7d6e5547b8915a3d927a0fbeef84cdbe0b1deb8c99bbd4a8961b52a", size = 277830, upload-time = "2026-01-14T23:14:12.908Z" },
-    { url = "https://files.pythonhosted.org/packages/e5/36/5d9972bccd6417ecd5a8be319cebfd80b296875e7f116c37fb2a2deecebf/regex-2026.1.15-cp310-cp310-win_arm64.whl", hash = "sha256:505831646c945e3e63552cc1b1b9b514f0e93232972a2d5bedbcc32f15bc82e3", size = 270376, upload-time = "2026-01-14T23:14:14.782Z" },
-    { url = "https://files.pythonhosted.org/packages/d0/c9/0c80c96eab96948363d270143138d671d5731c3a692b417629bf3492a9d6/regex-2026.1.15-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:1ae6020fb311f68d753b7efa9d4b9a5d47a5d6466ea0d5e3b5a471a960ea6e4a", size = 488168, upload-time = "2026-01-14T23:14:16.129Z" },
-    { url = "https://files.pythonhosted.org/packages/17/f0/271c92f5389a552494c429e5cc38d76d1322eb142fb5db3c8ccc47751468/regex-2026.1.15-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:eddf73f41225942c1f994914742afa53dc0d01a6e20fe14b878a1b1edc74151f", size = 290636, upload-time = "2026-01-14T23:14:17.715Z" },
-    { url = "https://files.pythonhosted.org/packages/a0/f9/5f1fd077d106ca5655a0f9ff8f25a1ab55b92128b5713a91ed7134ff688e/regex-2026.1.15-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:1e8cd52557603f5c66a548f69421310886b28b7066853089e1a71ee710e1cdc1", size = 288496, upload-time = "2026-01-14T23:14:19.326Z" },
-    { url = "https://files.pythonhosted.org/packages/b5/e1/8f43b03a4968c748858ec77f746c286d81f896c2e437ccf050ebc5d3128c/regex-2026.1.15-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5170907244b14303edc5978f522f16c974f32d3aa92109fabc2af52411c9433b", size = 793503, upload-time = "2026-01-14T23:14:20.922Z" },
-    { url = "https://files.pythonhosted.org/packages/8d/4e/a39a5e8edc5377a46a7c875c2f9a626ed3338cb3bb06931be461c3e1a34a/regex-2026.1.15-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:2748c1ec0663580b4510bd89941a31560b4b439a0b428b49472a3d9944d11cd8", size = 860535, upload-time = "2026-01-14T23:14:22.405Z" },
-    { url = "https://files.pythonhosted.org/packages/dc/1c/9dce667a32a9477f7a2869c1c767dc00727284a9fa3ff5c09a5c6c03575e/regex-2026.1.15-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:2f2775843ca49360508d080eaa87f94fa248e2c946bbcd963bb3aae14f333413", size = 907225, upload-time = "2026-01-14T23:14:23.897Z" },
-    { url = "https://files.pythonhosted.org/packages/a4/3c/87ca0a02736d16b6262921425e84b48984e77d8e4e572c9072ce96e66c30/regex-2026.1.15-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d9ea2604370efc9a174c1b5dcc81784fb040044232150f7f33756049edfc9026", size = 800526, upload-time = "2026-01-14T23:14:26.039Z" },
-    { url = "https://files.pythonhosted.org/packages/4b/ff/647d5715aeea7c87bdcbd2f578f47b415f55c24e361e639fe8c0cc88878f/regex-2026.1.15-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0dcd31594264029b57bf16f37fd7248a70b3b764ed9e0839a8f271b2d22c0785", size = 773446, upload-time = "2026-01-14T23:14:28.109Z" },
-    { url = "https://files.pythonhosted.org/packages/af/89/bf22cac25cb4ba0fe6bff52ebedbb65b77a179052a9d6037136ae93f42f4/regex-2026.1.15-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:c08c1f3e34338256732bd6938747daa3c0d5b251e04b6e43b5813e94d503076e", size = 783051, upload-time = "2026-01-14T23:14:29.929Z" },
-    { url = "https://files.pythonhosted.org/packages/1e/f4/6ed03e71dca6348a5188363a34f5e26ffd5db1404780288ff0d79513bce4/regex-2026.1.15-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:e43a55f378df1e7a4fa3547c88d9a5a9b7113f653a66821bcea4718fe6c58763", size = 854485, upload-time = "2026-01-14T23:14:31.366Z" },
-    { url = "https://files.pythonhosted.org/packages/d9/9a/8e8560bd78caded8eb137e3e47612430a05b9a772caf60876435192d670a/regex-2026.1.15-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:f82110ab962a541737bd0ce87978d4c658f06e7591ba899192e2712a517badbb", size = 762195, upload-time = "2026-01-14T23:14:32.802Z" },
-    { url = "https://files.pythonhosted.org/packages/38/6b/61fc710f9aa8dfcd764fe27d37edfaa023b1a23305a0d84fccd5adb346ea/regex-2026.1.15-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:27618391db7bdaf87ac6c92b31e8f0dfb83a9de0075855152b720140bda177a2", size = 845986, upload-time = "2026-01-14T23:14:34.898Z" },
-    { url = "https://files.pythonhosted.org/packages/fd/2e/fbee4cb93f9d686901a7ca8d94285b80405e8c34fe4107f63ffcbfb56379/regex-2026.1.15-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:bfb0d6be01fbae8d6655c8ca21b3b72458606c4aec9bbc932db758d47aba6db1", size = 788992, upload-time = "2026-01-14T23:14:37.116Z" },
-    { url = "https://files.pythonhosted.org/packages/ed/14/3076348f3f586de64b1ab75a3fbabdaab7684af7f308ad43be7ef1849e55/regex-2026.1.15-cp311-cp311-win32.whl", hash = "sha256:b10e42a6de0e32559a92f2f8dc908478cc0fa02838d7dbe764c44dca3fa13569", size = 265893, upload-time = "2026-01-14T23:14:38.426Z" },
-    { url = "https://files.pythonhosted.org/packages/0f/19/772cf8b5fc803f5c89ba85d8b1870a1ca580dc482aa030383a9289c82e44/regex-2026.1.15-cp311-cp311-win_amd64.whl", hash = "sha256:e9bf3f0bbdb56633c07d7116ae60a576f846efdd86a8848f8d62b749e1209ca7", size = 277840, upload-time = "2026-01-14T23:14:39.785Z" },
-    { url = "https://files.pythonhosted.org/packages/78/84/d05f61142709474da3c0853222d91086d3e1372bcdab516c6fd8d80f3297/regex-2026.1.15-cp311-cp311-win_arm64.whl", hash = "sha256:41aef6f953283291c4e4e6850607bd71502be67779586a61472beacb315c97ec", size = 270374, upload-time = "2026-01-14T23:14:41.592Z" },
-    { url = "https://files.pythonhosted.org/packages/92/81/10d8cf43c807d0326efe874c1b79f22bfb0fb226027b0b19ebc26d301408/regex-2026.1.15-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:4c8fcc5793dde01641a35905d6731ee1548f02b956815f8f1cab89e515a5bdf1", size = 489398, upload-time = "2026-01-14T23:14:43.741Z" },
-    { url = "https://files.pythonhosted.org/packages/90/b0/7c2a74e74ef2a7c32de724658a69a862880e3e4155cba992ba04d1c70400/regex-2026.1.15-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:bfd876041a956e6a90ad7cdb3f6a630c07d491280bfeed4544053cd434901681", size = 291339, upload-time = "2026-01-14T23:14:45.183Z" },
-    { url = "https://files.pythonhosted.org/packages/19/4d/16d0773d0c818417f4cc20aa0da90064b966d22cd62a8c46765b5bd2d643/regex-2026.1.15-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:9250d087bc92b7d4899ccd5539a1b2334e44eee85d848c4c1aef8e221d3f8c8f", size = 289003, upload-time = "2026-01-14T23:14:47.25Z" },
-    { url = "https://files.pythonhosted.org/packages/c6/e4/1fc4599450c9f0863d9406e944592d968b8d6dfd0d552a7d569e43bceada/regex-2026.1.15-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c8a154cf6537ebbc110e24dabe53095e714245c272da9c1be05734bdad4a61aa", size = 798656, upload-time = "2026-01-14T23:14:48.77Z" },
-    { url = "https://files.pythonhosted.org/packages/b2/e6/59650d73a73fa8a60b3a590545bfcf1172b4384a7df2e7fe7b9aab4e2da9/regex-2026.1.15-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:8050ba2e3ea1d8731a549e83c18d2f0999fbc99a5f6bd06b4c91449f55291804", size = 864252, upload-time = "2026-01-14T23:14:50.528Z" },
-    { url = "https://files.pythonhosted.org/packages/6e/ab/1d0f4d50a1638849a97d731364c9a80fa304fec46325e48330c170ee8e80/regex-2026.1.15-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:0bf065240704cb8951cc04972cf107063917022511273e0969bdb34fc173456c", size = 912268, upload-time = "2026-01-14T23:14:52.952Z" },
-    { url = "https://files.pythonhosted.org/packages/dd/df/0d722c030c82faa1d331d1921ee268a4e8fb55ca8b9042c9341c352f17fa/regex-2026.1.15-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c32bef3e7aeee75746748643667668ef941d28b003bfc89994ecf09a10f7a1b5", size = 803589, upload-time = "2026-01-14T23:14:55.182Z" },
-    { url = "https://files.pythonhosted.org/packages/66/23/33289beba7ccb8b805c6610a8913d0131f834928afc555b241caabd422a9/regex-2026.1.15-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:d5eaa4a4c5b1906bd0d2508d68927f15b81821f85092e06f1a34a4254b0e1af3", size = 775700, upload-time = "2026-01-14T23:14:56.707Z" },
-    { url = "https://files.pythonhosted.org/packages/e7/65/bf3a42fa6897a0d3afa81acb25c42f4b71c274f698ceabd75523259f6688/regex-2026.1.15-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:86c1077a3cc60d453d4084d5b9649065f3bf1184e22992bd322e1f081d3117fb", size = 787928, upload-time = "2026-01-14T23:14:58.312Z" },
-    { url = "https://files.pythonhosted.org/packages/f4/f5/13bf65864fc314f68cdd6d8ca94adcab064d4d39dbd0b10fef29a9da48fc/regex-2026.1.15-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:2b091aefc05c78d286657cd4db95f2e6313375ff65dcf085e42e4c04d9c8d410", size = 858607, upload-time = "2026-01-14T23:15:00.657Z" },
-    { url = "https://files.pythonhosted.org/packages/a3/31/040e589834d7a439ee43fb0e1e902bc81bd58a5ba81acffe586bb3321d35/regex-2026.1.15-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:57e7d17f59f9ebfa9667e6e5a1c0127b96b87cb9cede8335482451ed00788ba4", size = 763729, upload-time = "2026-01-14T23:15:02.248Z" },
-    { url = "https://files.pythonhosted.org/packages/9b/84/6921e8129687a427edf25a34a5594b588b6d88f491320b9de5b6339a4fcb/regex-2026.1.15-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:c6c4dcdfff2c08509faa15d36ba7e5ef5fcfab25f1e8f85a0c8f45bc3a30725d", size = 850697, upload-time = "2026-01-14T23:15:03.878Z" },
-    { url = "https://files.pythonhosted.org/packages/8a/87/3d06143d4b128f4229158f2de5de6c8f2485170c7221e61bf381313314b2/regex-2026.1.15-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:cf8ff04c642716a7f2048713ddc6278c5fd41faa3b9cab12607c7abecd012c22", size = 789849, upload-time = "2026-01-14T23:15:06.102Z" },
-    { url = "https://files.pythonhosted.org/packages/77/69/c50a63842b6bd48850ebc7ab22d46e7a2a32d824ad6c605b218441814639/regex-2026.1.15-cp312-cp312-win32.whl", hash = "sha256:82345326b1d8d56afbe41d881fdf62f1926d7264b2fc1537f99ae5da9aad7913", size = 266279, upload-time = "2026-01-14T23:15:07.678Z" },
-    { url = "https://files.pythonhosted.org/packages/f2/36/39d0b29d087e2b11fd8191e15e81cce1b635fcc845297c67f11d0d19274d/regex-2026.1.15-cp312-cp312-win_amd64.whl", hash = "sha256:4def140aa6156bc64ee9912383d4038f3fdd18fee03a6f222abd4de6357ce42a", size = 277166, upload-time = "2026-01-14T23:15:09.257Z" },
-    { url = "https://files.pythonhosted.org/packages/28/32/5b8e476a12262748851fa8ab1b0be540360692325975b094e594dfebbb52/regex-2026.1.15-cp312-cp312-win_arm64.whl", hash = "sha256:c6c565d9a6e1a8d783c1948937ffc377dd5771e83bd56de8317c450a954d2056", size = 270415, upload-time = "2026-01-14T23:15:10.743Z" },
-    { url = "https://files.pythonhosted.org/packages/f8/2e/6870bb16e982669b674cce3ee9ff2d1d46ab80528ee6bcc20fb2292efb60/regex-2026.1.15-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:e69d0deeb977ffe7ed3d2e4439360089f9c3f217ada608f0f88ebd67afb6385e", size = 489164, upload-time = "2026-01-14T23:15:13.962Z" },
-    { url = "https://files.pythonhosted.org/packages/dc/67/9774542e203849b0286badf67199970a44ebdb0cc5fb739f06e47ada72f8/regex-2026.1.15-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:3601ffb5375de85a16f407854d11cca8fe3f5febbe3ac78fb2866bb220c74d10", size = 291218, upload-time = "2026-01-14T23:15:15.647Z" },
-    { url = "https://files.pythonhosted.org/packages/b2/87/b0cda79f22b8dee05f774922a214da109f9a4c0eca5da2c9d72d77ea062c/regex-2026.1.15-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:4c5ef43b5c2d4114eb8ea424bb8c9cec01d5d17f242af88b2448f5ee81caadbc", size = 288895, upload-time = "2026-01-14T23:15:17.788Z" },
-    { url = "https://files.pythonhosted.org/packages/3b/6a/0041f0a2170d32be01ab981d6346c83a8934277d82c780d60b127331f264/regex-2026.1.15-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:968c14d4f03e10b2fd960f1d5168c1f0ac969381d3c1fcc973bc45fb06346599", size = 798680, upload-time = "2026-01-14T23:15:19.342Z" },
-    { url = "https://files.pythonhosted.org/packages/58/de/30e1cfcdbe3e891324aa7568b7c968771f82190df5524fabc1138cb2d45a/regex-2026.1.15-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:56a5595d0f892f214609c9f76b41b7428bed439d98dc961efafdd1354d42baae", size = 864210, upload-time = "2026-01-14T23:15:22.005Z" },
-    { url = "https://files.pythonhosted.org/packages/64/44/4db2f5c5ca0ccd40ff052ae7b1e9731352fcdad946c2b812285a7505ca75/regex-2026.1.15-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:0bf650f26087363434c4e560011f8e4e738f6f3e029b85d4904c50135b86cfa5", size = 912358, upload-time = "2026-01-14T23:15:24.569Z" },
-    { url = "https://files.pythonhosted.org/packages/79/b6/e6a5665d43a7c42467138c8a2549be432bad22cbd206f5ec87162de74bd7/regex-2026.1.15-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:18388a62989c72ac24de75f1449d0fb0b04dfccd0a1a7c1c43af5eb503d890f6", size = 803583, upload-time = "2026-01-14T23:15:26.526Z" },
-    { url = "https://files.pythonhosted.org/packages/e7/53/7cd478222169d85d74d7437e74750005e993f52f335f7c04ff7adfda3310/regex-2026.1.15-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:6d220a2517f5893f55daac983bfa9fe998a7dbcaee4f5d27a88500f8b7873788", size = 775782, upload-time = "2026-01-14T23:15:29.352Z" },
-    { url = "https://files.pythonhosted.org/packages/ca/b5/75f9a9ee4b03a7c009fe60500fe550b45df94f0955ca29af16333ef557c5/regex-2026.1.15-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:c9c08c2fbc6120e70abff5d7f28ffb4d969e14294fb2143b4b5c7d20e46d1714", size = 787978, upload-time = "2026-01-14T23:15:31.295Z" },
-    { url = "https://files.pythonhosted.org/packages/72/b3/79821c826245bbe9ccbb54f6eadb7879c722fd3e0248c17bfc90bf54e123/regex-2026.1.15-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:7ef7d5d4bd49ec7364315167a4134a015f61e8266c6d446fc116a9ac4456e10d", size = 858550, upload-time = "2026-01-14T23:15:33.558Z" },
-    { url = "https://files.pythonhosted.org/packages/4a/85/2ab5f77a1c465745bfbfcb3ad63178a58337ae8d5274315e2cc623a822fa/regex-2026.1.15-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:6e42844ad64194fa08d5ccb75fe6a459b9b08e6d7296bd704460168d58a388f3", size = 763747, upload-time = "2026-01-14T23:15:35.206Z" },
-    { url = "https://files.pythonhosted.org/packages/6d/84/c27df502d4bfe2873a3e3a7cf1bdb2b9cc10284d1a44797cf38bed790470/regex-2026.1.15-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:cfecdaa4b19f9ca534746eb3b55a5195d5c95b88cac32a205e981ec0a22b7d31", size = 850615, upload-time = "2026-01-14T23:15:37.523Z" },
-    { url = "https://files.pythonhosted.org/packages/7d/b7/658a9782fb253680aa8ecb5ccbb51f69e088ed48142c46d9f0c99b46c575/regex-2026.1.15-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:08df9722d9b87834a3d701f3fca570b2be115654dbfd30179f30ab2f39d606d3", size = 789951, upload-time = "2026-01-14T23:15:39.582Z" },
-    { url = "https://files.pythonhosted.org/packages/fc/2a/5928af114441e059f15b2f63e188bd00c6529b3051c974ade7444b85fcda/regex-2026.1.15-cp313-cp313-win32.whl", hash = "sha256:d426616dae0967ca225ab12c22274eb816558f2f99ccb4a1d52ca92e8baf180f", size = 266275, upload-time = "2026-01-14T23:15:42.108Z" },
-    { url = "https://files.pythonhosted.org/packages/4f/16/5bfbb89e435897bff28cf0352a992ca719d9e55ebf8b629203c96b6ce4f7/regex-2026.1.15-cp313-cp313-win_amd64.whl", hash = "sha256:febd38857b09867d3ed3f4f1af7d241c5c50362e25ef43034995b77a50df494e", size = 277145, upload-time = "2026-01-14T23:15:44.244Z" },
-    { url = "https://files.pythonhosted.org/packages/56/c1/a09ff7392ef4233296e821aec5f78c51be5e91ffde0d163059e50fd75835/regex-2026.1.15-cp313-cp313-win_arm64.whl", hash = "sha256:8e32f7896f83774f91499d239e24cebfadbc07639c1494bb7213983842348337", size = 270411, upload-time = "2026-01-14T23:15:45.858Z" },
-    { url = "https://files.pythonhosted.org/packages/3c/38/0cfd5a78e5c6db00e6782fdae70458f89850ce95baa5e8694ab91d89744f/regex-2026.1.15-cp313-cp313t-macosx_10_13_universal2.whl", hash = "sha256:ec94c04149b6a7b8120f9f44565722c7ae31b7a6d2275569d2eefa76b83da3be", size = 492068, upload-time = "2026-01-14T23:15:47.616Z" },
-    { url = "https://files.pythonhosted.org/packages/50/72/6c86acff16cb7c959c4355826bbf06aad670682d07c8f3998d9ef4fee7cd/regex-2026.1.15-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:40c86d8046915bb9aeb15d3f3f15b6fd500b8ea4485b30e1bbc799dab3fe29f8", size = 292756, upload-time = "2026-01-14T23:15:49.307Z" },
-    { url = "https://files.pythonhosted.org/packages/4e/58/df7fb69eadfe76526ddfce28abdc0af09ffe65f20c2c90932e89d705153f/regex-2026.1.15-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:726ea4e727aba21643205edad8f2187ec682d3305d790f73b7a51c7587b64bdd", size = 291114, upload-time = "2026-01-14T23:15:51.484Z" },
-    { url = "https://files.pythonhosted.org/packages/ed/6c/a4011cd1cf96b90d2cdc7e156f91efbd26531e822a7fbb82a43c1016678e/regex-2026.1.15-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1cb740d044aff31898804e7bf1181cc72c03d11dfd19932b9911ffc19a79070a", size = 807524, upload-time = "2026-01-14T23:15:53.102Z" },
-    { url = "https://files.pythonhosted.org/packages/1d/25/a53ffb73183f69c3e9f4355c4922b76d2840aee160af6af5fac229b6201d/regex-2026.1.15-cp313-cp313t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:05d75a668e9ea16f832390d22131fe1e8acc8389a694c8febc3e340b0f810b93", size = 873455, upload-time = "2026-01-14T23:15:54.956Z" },
-    { url = "https://files.pythonhosted.org/packages/66/0b/8b47fc2e8f97d9b4a851736f3890a5f786443aa8901061c55f24c955f45b/regex-2026.1.15-cp313-cp313t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:d991483606f3dbec93287b9f35596f41aa2e92b7c2ebbb935b63f409e243c9af", size = 915007, upload-time = "2026-01-14T23:15:57.041Z" },
-    { url = "https://files.pythonhosted.org/packages/c2/fa/97de0d681e6d26fabe71968dbee06dd52819e9a22fdce5dac7256c31ed84/regex-2026.1.15-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:194312a14819d3e44628a44ed6fea6898fdbecb0550089d84c403475138d0a09", size = 812794, upload-time = "2026-01-14T23:15:58.916Z" },
-    { url = "https://files.pythonhosted.org/packages/22/38/e752f94e860d429654aa2b1c51880bff8dfe8f084268258adf9151cf1f53/regex-2026.1.15-cp313-cp313t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:fe2fda4110a3d0bc163c2e0664be44657431440722c5c5315c65155cab92f9e5", size = 781159, upload-time = "2026-01-14T23:16:00.817Z" },
-    { url = "https://files.pythonhosted.org/packages/e9/a7/d739ffaef33c378fc888302a018d7f81080393d96c476b058b8c64fd2b0d/regex-2026.1.15-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:124dc36c85d34ef2d9164da41a53c1c8c122cfb1f6e1ec377a1f27ee81deb794", size = 795558, upload-time = "2026-01-14T23:16:03.267Z" },
-    { url = "https://files.pythonhosted.org/packages/3e/c4/542876f9a0ac576100fc73e9c75b779f5c31e3527576cfc9cb3009dcc58a/regex-2026.1.15-cp313-cp313t-musllinux_1_2_ppc64le.whl", hash = "sha256:a1774cd1981cd212506a23a14dba7fdeaee259f5deba2df6229966d9911e767a", size = 868427, upload-time = "2026-01-14T23:16:05.646Z" },
-    { url = "https://files.pythonhosted.org/packages/fc/0f/d5655bea5b22069e32ae85a947aa564912f23758e112cdb74212848a1a1b/regex-2026.1.15-cp313-cp313t-musllinux_1_2_riscv64.whl", hash = "sha256:b5f7d8d2867152cdb625e72a530d2ccb48a3d199159144cbdd63870882fb6f80", size = 769939, upload-time = "2026-01-14T23:16:07.542Z" },
-    { url = "https://files.pythonhosted.org/packages/20/06/7e18a4fa9d326daeda46d471a44ef94201c46eaa26dbbb780b5d92cbfdda/regex-2026.1.15-cp313-cp313t-musllinux_1_2_s390x.whl", hash = "sha256:492534a0ab925d1db998defc3c302dae3616a2fc3fe2e08db1472348f096ddf2", size = 854753, upload-time = "2026-01-14T23:16:10.395Z" },
-    { url = "https://files.pythonhosted.org/packages/3b/67/dc8946ef3965e166f558ef3b47f492bc364e96a265eb4a2bb3ca765c8e46/regex-2026.1.15-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:c661fc820cfb33e166bf2450d3dadbda47c8d8981898adb9b6fe24e5e582ba60", size = 799559, upload-time = "2026-01-14T23:16:12.347Z" },
-    { url = "https://files.pythonhosted.org/packages/a5/61/1bba81ff6d50c86c65d9fd84ce9699dd106438ee4cdb105bf60374ee8412/regex-2026.1.15-cp313-cp313t-win32.whl", hash = "sha256:99ad739c3686085e614bf77a508e26954ff1b8f14da0e3765ff7abbf7799f952", size = 268879, upload-time = "2026-01-14T23:16:14.049Z" },
-    { url = "https://files.pythonhosted.org/packages/e9/5e/cef7d4c5fb0ea3ac5c775fd37db5747f7378b29526cc83f572198924ff47/regex-2026.1.15-cp313-cp313t-win_amd64.whl", hash = "sha256:32655d17905e7ff8ba5c764c43cb124e34a9245e45b83c22e81041e1071aee10", size = 280317, upload-time = "2026-01-14T23:16:15.718Z" },
-    { url = "https://files.pythonhosted.org/packages/b4/52/4317f7a5988544e34ab57b4bde0f04944c4786128c933fb09825924d3e82/regex-2026.1.15-cp313-cp313t-win_arm64.whl", hash = "sha256:b2a13dd6a95e95a489ca242319d18fc02e07ceb28fa9ad146385194d95b3c829", size = 271551, upload-time = "2026-01-14T23:16:17.533Z" },
+    { url = "https://files.pythonhosted.org/packages/63/12/497bd6599ce8a239ade68678132296aec5ee25ebea45fc8ba91aa60fceec/regex-2024.9.11-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:1494fa8725c285a81d01dc8c06b55287a1ee5e0e382d8413adc0a9197aac6408", size = 482488, upload-time = "2024-09-11T18:56:55.331Z" },
+    { url = "https://files.pythonhosted.org/packages/c1/24/595ddb9bec2a9b151cdaf9565b0c9f3da9f0cb1dca6c158bc5175332ddf8/regex-2024.9.11-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:0e12c481ad92d129c78f13a2a3662317e46ee7ef96c94fd332e1c29131875b7d", size = 287443, upload-time = "2024-09-11T18:56:58.531Z" },
+    { url = "https://files.pythonhosted.org/packages/69/a8/b2fb45d9715b1469383a0da7968f8cacc2f83e9fbbcd6b8713752dd980a6/regex-2024.9.11-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:16e13a7929791ac1216afde26f712802e3df7bf0360b32e4914dca3ab8baeea5", size = 284561, upload-time = "2024-09-11T18:57:00.655Z" },
+    { url = "https://files.pythonhosted.org/packages/88/87/1ce4a5357216b19b7055e7d3b0efc75a6e426133bf1e7d094321df514257/regex-2024.9.11-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:46989629904bad940bbec2106528140a218b4a36bb3042d8406980be1941429c", size = 783177, upload-time = "2024-09-11T18:57:01.958Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/65/b9f002ab32f7b68e7d1dcabb67926f3f47325b8dbc22cc50b6a043e1d07c/regex-2024.9.11-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a906ed5e47a0ce5f04b2c981af1c9acf9e8696066900bf03b9d7879a6f679fc8", size = 823193, upload-time = "2024-09-11T18:57:04.06Z" },
+    { url = "https://files.pythonhosted.org/packages/22/91/8339dd3abce101204d246e31bc26cdd7ec07c9f91598472459a3a902aa41/regex-2024.9.11-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e9a091b0550b3b0207784a7d6d0f1a00d1d1c8a11699c1a4d93db3fbefc3ad35", size = 809950, upload-time = "2024-09-11T18:57:05.805Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/19/556638aa11c2ec9968a1da998f07f27ec0abb9bf3c647d7c7985ca0b8eea/regex-2024.9.11-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5ddcd9a179c0a6fa8add279a4444015acddcd7f232a49071ae57fa6e278f1f71", size = 782661, upload-time = "2024-09-11T18:57:07.881Z" },
+    { url = "https://files.pythonhosted.org/packages/d1/e9/7a5bc4c6ef8d9cd2bdd83a667888fc35320da96a4cc4da5fa084330f53db/regex-2024.9.11-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6b41e1adc61fa347662b09398e31ad446afadff932a24807d3ceb955ed865cc8", size = 772348, upload-time = "2024-09-11T18:57:09.494Z" },
+    { url = "https://files.pythonhosted.org/packages/f1/0b/29f2105bfac3ed08e704914c38e93b07c784a6655f8a015297ee7173e95b/regex-2024.9.11-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:ced479f601cd2f8ca1fd7b23925a7e0ad512a56d6e9476f79b8f381d9d37090a", size = 697460, upload-time = "2024-09-11T18:57:11.595Z" },
+    { url = "https://files.pythonhosted.org/packages/71/3a/52ff61054d15a4722605f5872ad03962b319a04c1ebaebe570b8b9b7dde1/regex-2024.9.11-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:635a1d96665f84b292e401c3d62775851aedc31d4f8784117b3c68c4fcd4118d", size = 769151, upload-time = "2024-09-11T18:57:14.358Z" },
+    { url = "https://files.pythonhosted.org/packages/97/07/37e460ab5ca84be8e1e197c3b526c5c86993dcc9e13cbc805c35fc2463c1/regex-2024.9.11-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:c0256beda696edcf7d97ef16b2a33a8e5a875affd6fa6567b54f7c577b30a137", size = 777478, upload-time = "2024-09-11T18:57:16.397Z" },
+    { url = "https://files.pythonhosted.org/packages/65/7b/953075723dd5ab00780043ac2f9de667306ff9e2a85332975e9f19279174/regex-2024.9.11-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:3ce4f1185db3fbde8ed8aa223fc9620f276c58de8b0d4f8cc86fd1360829edb6", size = 845373, upload-time = "2024-09-11T18:57:17.938Z" },
+    { url = "https://files.pythonhosted.org/packages/40/b8/3e9484c6230b8b6e8f816ab7c9a080e631124991a4ae2c27a81631777db0/regex-2024.9.11-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:09d77559e80dcc9d24570da3745ab859a9cf91953062e4ab126ba9d5993688ca", size = 845369, upload-time = "2024-09-11T18:57:20.091Z" },
+    { url = "https://files.pythonhosted.org/packages/b7/99/38434984d912edbd2e1969d116257e869578f67461bd7462b894c45ed874/regex-2024.9.11-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:7a22ccefd4db3f12b526eccb129390942fe874a3a9fdbdd24cf55773a1faab1a", size = 773935, upload-time = "2024-09-11T18:57:21.652Z" },
+    { url = "https://files.pythonhosted.org/packages/ab/67/43174d2b46fa947b7b9dfe56b6c8a8a76d44223f35b1d64645a732fd1d6f/regex-2024.9.11-cp310-cp310-win32.whl", hash = "sha256:f745ec09bc1b0bd15cfc73df6fa4f726dcc26bb16c23a03f9e3367d357eeedd0", size = 261624, upload-time = "2024-09-11T18:57:23.777Z" },
+    { url = "https://files.pythonhosted.org/packages/c4/2a/4f9c47d9395b6aff24874c761d8d620c0232f97c43ef3cf668c8b355e7a7/regex-2024.9.11-cp310-cp310-win_amd64.whl", hash = "sha256:01c2acb51f8a7d6494c8c5eafe3d8e06d76563d8a8a4643b37e9b2dd8a2ff623", size = 274020, upload-time = "2024-09-11T18:57:25.27Z" },
+    { url = "https://files.pythonhosted.org/packages/86/a1/d526b7b6095a0019aa360948c143aacfeb029919c898701ce7763bbe4c15/regex-2024.9.11-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:2cce2449e5927a0bf084d346da6cd5eb016b2beca10d0013ab50e3c226ffc0df", size = 482483, upload-time = "2024-09-11T18:57:26.694Z" },
+    { url = "https://files.pythonhosted.org/packages/32/d9/bfdd153179867c275719e381e1e8e84a97bd186740456a0dcb3e7125c205/regex-2024.9.11-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:3b37fa423beefa44919e009745ccbf353d8c981516e807995b2bd11c2c77d268", size = 287442, upload-time = "2024-09-11T18:57:28.133Z" },
+    { url = "https://files.pythonhosted.org/packages/33/c4/60f3370735135e3a8d673ddcdb2507a8560d0e759e1398d366e43d000253/regex-2024.9.11-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:64ce2799bd75039b480cc0360907c4fb2f50022f030bf9e7a8705b636e408fad", size = 284561, upload-time = "2024-09-11T18:57:30.83Z" },
+    { url = "https://files.pythonhosted.org/packages/b1/51/91a5ebdff17f9ec4973cb0aa9d37635efec1c6868654bbc25d1543aca4ec/regex-2024.9.11-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a4cc92bb6db56ab0c1cbd17294e14f5e9224f0cc6521167ef388332604e92679", size = 791779, upload-time = "2024-09-11T18:57:32.461Z" },
+    { url = "https://files.pythonhosted.org/packages/07/4a/022c5e6f0891a90cd7eb3d664d6c58ce2aba48bff107b00013f3d6167069/regex-2024.9.11-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d05ac6fa06959c4172eccd99a222e1fbf17b5670c4d596cb1e5cde99600674c4", size = 832605, upload-time = "2024-09-11T18:57:34.01Z" },
+    { url = "https://files.pythonhosted.org/packages/ac/1c/3793990c8c83ca04e018151ddda83b83ecc41d89964f0f17749f027fc44d/regex-2024.9.11-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:040562757795eeea356394a7fb13076ad4f99d3c62ab0f8bdfb21f99a1f85664", size = 818556, upload-time = "2024-09-11T18:57:36.363Z" },
+    { url = "https://files.pythonhosted.org/packages/e9/5c/8b385afbfacb853730682c57be56225f9fe275c5bf02ac1fc88edbff316d/regex-2024.9.11-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6113c008a7780792efc80f9dfe10ba0cd043cbf8dc9a76ef757850f51b4edc50", size = 792808, upload-time = "2024-09-11T18:57:38.493Z" },
+    { url = "https://files.pythonhosted.org/packages/9b/8b/a4723a838b53c771e9240951adde6af58c829fb6a6a28f554e8131f53839/regex-2024.9.11-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8e5fb5f77c8745a60105403a774fe2c1759b71d3e7b4ca237a5e67ad066c7199", size = 781115, upload-time = "2024-09-11T18:57:41.4Z" },
+    { url = "https://files.pythonhosted.org/packages/83/5f/031a04b6017033d65b261259c09043c06f4ef2d4eac841d0649d76d69541/regex-2024.9.11-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:54d9ff35d4515debf14bc27f1e3b38bfc453eff3220f5bce159642fa762fe5d4", size = 778155, upload-time = "2024-09-11T18:57:43.608Z" },
+    { url = "https://files.pythonhosted.org/packages/fd/cd/4660756070b03ce4a66663a43f6c6e7ebc2266cc6b4c586c167917185eb4/regex-2024.9.11-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:df5cbb1fbc74a8305b6065d4ade43b993be03dbe0f8b30032cced0d7740994bd", size = 784614, upload-time = "2024-09-11T18:57:45.219Z" },
+    { url = "https://files.pythonhosted.org/packages/93/8d/65b9bea7df120a7be8337c415b6d256ba786cbc9107cebba3bf8ff09da99/regex-2024.9.11-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:7fb89ee5d106e4a7a51bce305ac4efb981536301895f7bdcf93ec92ae0d91c7f", size = 853744, upload-time = "2024-09-11T18:57:46.907Z" },
+    { url = "https://files.pythonhosted.org/packages/96/a7/fba1eae75eb53a704475baf11bd44b3e6ccb95b316955027eb7748f24ef8/regex-2024.9.11-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:a738b937d512b30bf75995c0159c0ddf9eec0775c9d72ac0202076c72f24aa96", size = 855890, upload-time = "2024-09-11T18:57:49.264Z" },
+    { url = "https://files.pythonhosted.org/packages/45/14/d864b2db80a1a3358534392373e8a281d95b28c29c87d8548aed58813910/regex-2024.9.11-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:e28f9faeb14b6f23ac55bfbbfd3643f5c7c18ede093977f1df249f73fd22c7b1", size = 781887, upload-time = "2024-09-11T18:57:51.619Z" },
+    { url = "https://files.pythonhosted.org/packages/4d/a9/bfb29b3de3eb11dc9b412603437023b8e6c02fb4e11311863d9bf62c403a/regex-2024.9.11-cp311-cp311-win32.whl", hash = "sha256:18e707ce6c92d7282dfce370cd205098384b8ee21544e7cb29b8aab955b66fa9", size = 261644, upload-time = "2024-09-11T18:57:53.334Z" },
+    { url = "https://files.pythonhosted.org/packages/c7/ab/1ad2511cf6a208fde57fafe49829cab8ca018128ab0d0b48973d8218634a/regex-2024.9.11-cp311-cp311-win_amd64.whl", hash = "sha256:313ea15e5ff2a8cbbad96ccef6be638393041b0a7863183c2d31e0c6116688cf", size = 274033, upload-time = "2024-09-11T18:57:55.605Z" },
+    { url = "https://files.pythonhosted.org/packages/6e/92/407531450762bed778eedbde04407f68cbd75d13cee96c6f8d6903d9c6c1/regex-2024.9.11-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:b0d0a6c64fcc4ef9c69bd5b3b3626cc3776520a1637d8abaa62b9edc147a58f7", size = 483590, upload-time = "2024-09-11T18:57:57.793Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/a2/048acbc5ae1f615adc6cba36cc45734e679b5f1e4e58c3c77f0ed611d4e2/regex-2024.9.11-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:49b0e06786ea663f933f3710a51e9385ce0cba0ea56b67107fd841a55d56a231", size = 288175, upload-time = "2024-09-11T18:57:59.671Z" },
+    { url = "https://files.pythonhosted.org/packages/8a/ea/909d8620329ab710dfaf7b4adee41242ab7c9b95ea8d838e9bfe76244259/regex-2024.9.11-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:5b513b6997a0b2f10e4fd3a1313568e373926e8c252bd76c960f96fd039cd28d", size = 284749, upload-time = "2024-09-11T18:58:01.855Z" },
+    { url = "https://files.pythonhosted.org/packages/ca/fa/521eb683b916389b4975337873e66954e0f6d8f91bd5774164a57b503185/regex-2024.9.11-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ee439691d8c23e76f9802c42a95cfeebf9d47cf4ffd06f18489122dbb0a7ad64", size = 795181, upload-time = "2024-09-11T18:58:03.985Z" },
+    { url = "https://files.pythonhosted.org/packages/28/db/63047feddc3280cc242f9c74f7aeddc6ee662b1835f00046f57d5630c827/regex-2024.9.11-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a8f877c89719d759e52783f7fe6e1c67121076b87b40542966c02de5503ace42", size = 835842, upload-time = "2024-09-11T18:58:05.74Z" },
+    { url = "https://files.pythonhosted.org/packages/e3/94/86adc259ff8ec26edf35fcca7e334566c1805c7493b192cb09679f9c3dee/regex-2024.9.11-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:23b30c62d0f16827f2ae9f2bb87619bc4fba2044911e2e6c2eb1af0161cdb766", size = 823533, upload-time = "2024-09-11T18:58:07.427Z" },
+    { url = "https://files.pythonhosted.org/packages/29/52/84662b6636061277cb857f658518aa7db6672bc6d1a3f503ccd5aefc581e/regex-2024.9.11-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:85ab7824093d8f10d44330fe1e6493f756f252d145323dd17ab6b48733ff6c0a", size = 797037, upload-time = "2024-09-11T18:58:09.879Z" },
+    { url = "https://files.pythonhosted.org/packages/c3/2a/cd4675dd987e4a7505f0364a958bc41f3b84942de9efaad0ef9a2646681c/regex-2024.9.11-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8dee5b4810a89447151999428fe096977346cf2f29f4d5e29609d2e19e0199c9", size = 784106, upload-time = "2024-09-11T18:58:11.55Z" },
+    { url = "https://files.pythonhosted.org/packages/6f/75/3ea7ec29de0bbf42f21f812f48781d41e627d57a634f3f23947c9a46e303/regex-2024.9.11-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:98eeee2f2e63edae2181c886d7911ce502e1292794f4c5ee71e60e23e8d26b5d", size = 782468, upload-time = "2024-09-11T18:58:13.552Z" },
+    { url = "https://files.pythonhosted.org/packages/d3/67/15519d69b52c252b270e679cb578e22e0c02b8dd4e361f2b04efcc7f2335/regex-2024.9.11-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:57fdd2e0b2694ce6fc2e5ccf189789c3e2962916fb38779d3e3521ff8fe7a822", size = 790324, upload-time = "2024-09-11T18:58:15.268Z" },
+    { url = "https://files.pythonhosted.org/packages/9c/71/eff77d3fe7ba08ab0672920059ec30d63fa7e41aa0fb61c562726e9bd721/regex-2024.9.11-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:d552c78411f60b1fdaafd117a1fca2f02e562e309223b9d44b7de8be451ec5e0", size = 860214, upload-time = "2024-09-11T18:58:17.583Z" },
+    { url = "https://files.pythonhosted.org/packages/81/11/e1bdf84a72372e56f1ea4b833dd583b822a23138a616ace7ab57a0e11556/regex-2024.9.11-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:a0b2b80321c2ed3fcf0385ec9e51a12253c50f146fddb2abbb10f033fe3d049a", size = 859420, upload-time = "2024-09-11T18:58:19.898Z" },
+    { url = "https://files.pythonhosted.org/packages/ea/75/9753e9dcebfa7c3645563ef5c8a58f3a47e799c872165f37c55737dadd3e/regex-2024.9.11-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:18406efb2f5a0e57e3a5881cd9354c1512d3bb4f5c45d96d110a66114d84d23a", size = 787333, upload-time = "2024-09-11T18:58:21.699Z" },
+    { url = "https://files.pythonhosted.org/packages/bc/4e/ba1cbca93141f7416624b3ae63573e785d4bc1834c8be44a8f0747919eca/regex-2024.9.11-cp312-cp312-win32.whl", hash = "sha256:e464b467f1588e2c42d26814231edecbcfe77f5ac414d92cbf4e7b55b2c2a776", size = 262058, upload-time = "2024-09-11T18:58:23.452Z" },
+    { url = "https://files.pythonhosted.org/packages/6e/16/efc5f194778bf43e5888209e5cec4b258005d37c613b67ae137df3b89c53/regex-2024.9.11-cp312-cp312-win_amd64.whl", hash = "sha256:9e8719792ca63c6b8340380352c24dcb8cd7ec49dae36e963742a275dfae6009", size = 273526, upload-time = "2024-09-11T18:58:25.191Z" },
+    { url = "https://files.pythonhosted.org/packages/93/0a/d1c6b9af1ff1e36832fe38d74d5c5bab913f2bdcbbd6bc0e7f3ce8b2f577/regex-2024.9.11-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:c157bb447303070f256e084668b702073db99bbb61d44f85d811025fcf38f784", size = 483376, upload-time = "2024-09-11T18:58:27.11Z" },
+    { url = "https://files.pythonhosted.org/packages/a4/42/5910a050c105d7f750a72dcb49c30220c3ae4e2654e54aaaa0e9bc0584cb/regex-2024.9.11-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:4db21ece84dfeefc5d8a3863f101995de646c6cb0536952c321a2650aa202c36", size = 288112, upload-time = "2024-09-11T18:58:28.78Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/56/0c262aff0e9224fa7ffce47b5458d373f4d3e3ff84e99b5ff0cb15e0b5b2/regex-2024.9.11-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:220e92a30b426daf23bb67a7962900ed4613589bab80382be09b48896d211e92", size = 284608, upload-time = "2024-09-11T18:58:30.498Z" },
+    { url = "https://files.pythonhosted.org/packages/b9/54/9fe8f9aec5007bbbbce28ba3d2e3eaca425f95387b7d1e84f0d137d25237/regex-2024.9.11-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:eb1ae19e64c14c7ec1995f40bd932448713d3c73509e82d8cd7744dc00e29e86", size = 795337, upload-time = "2024-09-11T18:58:32.665Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/e7/6b2f642c3cded271c4f16cc4daa7231be544d30fe2b168e0223724b49a61/regex-2024.9.11-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f47cd43a5bfa48f86925fe26fbdd0a488ff15b62468abb5d2a1e092a4fb10e85", size = 835848, upload-time = "2024-09-11T18:58:34.337Z" },
+    { url = "https://files.pythonhosted.org/packages/cd/9e/187363bdf5d8c0e4662117b92aa32bf52f8f09620ae93abc7537d96d3311/regex-2024.9.11-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9d4a76b96f398697fe01117093613166e6aa8195d63f1b4ec3f21ab637632963", size = 823503, upload-time = "2024-09-11T18:58:36.17Z" },
+    { url = "https://files.pythonhosted.org/packages/f8/10/601303b8ee93589f879664b0cfd3127949ff32b17f9b6c490fb201106c4d/regex-2024.9.11-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0ea51dcc0835eea2ea31d66456210a4e01a076d820e9039b04ae8d17ac11dee6", size = 797049, upload-time = "2024-09-11T18:58:38.225Z" },
+    { url = "https://files.pythonhosted.org/packages/ef/1c/ea200f61ce9f341763f2717ab4daebe4422d83e9fd4ac5e33435fd3a148d/regex-2024.9.11-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b7aaa315101c6567a9a45d2839322c51c8d6e81f67683d529512f5bcfb99c802", size = 784144, upload-time = "2024-09-11T18:58:40.605Z" },
+    { url = "https://files.pythonhosted.org/packages/d8/5c/d2429be49ef3292def7688401d3deb11702c13dcaecdc71d2b407421275b/regex-2024.9.11-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:c57d08ad67aba97af57a7263c2d9006d5c404d721c5f7542f077f109ec2a4a29", size = 782483, upload-time = "2024-09-11T18:58:42.58Z" },
+    { url = "https://files.pythonhosted.org/packages/12/d9/cbc30f2ff7164f3b26a7760f87c54bf8b2faed286f60efd80350a51c5b99/regex-2024.9.11-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:f8404bf61298bb6f8224bb9176c1424548ee1181130818fcd2cbffddc768bed8", size = 790320, upload-time = "2024-09-11T18:58:44.5Z" },
+    { url = "https://files.pythonhosted.org/packages/19/1d/43ed03a236313639da5a45e61bc553c8d41e925bcf29b0f8ecff0c2c3f25/regex-2024.9.11-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:dd4490a33eb909ef5078ab20f5f000087afa2a4daa27b4c072ccb3cb3050ad84", size = 860435, upload-time = "2024-09-11T18:58:47.014Z" },
+    { url = "https://files.pythonhosted.org/packages/34/4f/5d04da61c7c56e785058a46349f7285ae3ebc0726c6ea7c5c70600a52233/regex-2024.9.11-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:eee9130eaad130649fd73e5cd92f60e55708952260ede70da64de420cdcad554", size = 859571, upload-time = "2024-09-11T18:58:48.974Z" },
+    { url = "https://files.pythonhosted.org/packages/12/7f/8398c8155a3c70703a8e91c29532558186558e1aea44144b382faa2a6f7a/regex-2024.9.11-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6a2644a93da36c784e546de579ec1806bfd2763ef47babc1b03d765fe560c9f8", size = 787398, upload-time = "2024-09-11T18:58:51.05Z" },
+    { url = "https://files.pythonhosted.org/packages/58/3a/f5903977647a9a7e46d5535e9e96c194304aeeca7501240509bde2f9e17f/regex-2024.9.11-cp313-cp313-win32.whl", hash = "sha256:e997fd30430c57138adc06bba4c7c2968fb13d101e57dd5bb9355bf8ce3fa7e8", size = 262035, upload-time = "2024-09-11T18:58:53.526Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/80/51ba3a4b7482f6011095b3a036e07374f64de180b7d870b704ed22509002/regex-2024.9.11-cp313-cp313-win_amd64.whl", hash = "sha256:042c55879cfeb21a8adacc84ea347721d3d83a159da6acdf1116859e2427c43f", size = 273510, upload-time = "2024-09-11T18:58:55.263Z" },
 ]
 
 [[package]]