Extract raw finish_reason and response_id from an Anthropic ``Message`` / ``BetaMessage``. Anthropic exposes ``stop_reason`` (e.g. ``"

Extract token usage and response metadata from OpenAI ChatCompletion.

Extract token usage and response metadata from Responses API response.

Extract token usage and response metadata from Gemini response.

Fetch MCP server configurations via CrewAI+ API. Sends a GET request to the CrewAI+ mcps/configs endpoint with comma-separated slugs.

Format messages for Azure AI Inference API. Args: messages: Input messages Returns: List of dict objects wit

Get or create the OpenAI client.

Get the appropriate client - instance-specific or global.

Get the appropriate purpose for a file based on content type. OpenAI Files API requires different purposes for different file types: - Images

Platform-appropriate per-user credential directory (mode 0o700).

Handles the Crew planning.

Initialize backend batch and send collected events.

Type guard to check if the client is an asynchronous AsyncQdrantClient. Args: client: The client to check. Returns: True if

Type guard to check if the client is an asynchronous AsyncClientAPI. Args: client: The client to check. Returns: True if the

Whether a 404 means the model exists but isn't on chat completions. OpenAI distinguishes the two 404s it returns here: responses

Type guard to check if the client is a synchronous QdrantClient. Args: client: The client to check. Returns: True if the cli

Type guard to check if the client is a synchronous ClientAPI. Args: client: The client to check. Returns: True if the client

Return true for complete Anthropic tool-use blocks across SDK shapes. New/preview Anthropic models can return content blocks whose concrete SDK

Create a mock MCPClient that returns *tool_definitions*.

True when a crew runs inside a flow session (context or batch ownership).

Parse an AMP reference into *(slug, optional tool name)*. Accepts both bare slugs (``"notion"``, ``"notion#search"``) and the legacy

Parse the LLM response into a StepObservation. The LLM may return: - A StepObservation instance directly (streaming + litellm path)

Read raw bytes from a secure file, or None if absent.

Subclass must implement: transform validated params dict into API request params.

Return the bound ``Memory`` or raise a clear error if missing.

Coerce a checkpoint field value. Returns: CheckpointConfig — use this config. _SENTINEL — explicit opt-out (``False``), stop walk

Emit agent execution event. Args: formatted_answer: Agent's response to log.

Build an in-memory tar archive via `build(tf)` and return it for reading.

Extract timestamp from checkpoint ID or filename.

Use trained data for the agent task prompt to improve output.

Call the LLM asynchronously and return the response. Args: llm: The LLM instance to call. messages: The messages to send to the L

Get an existing collection or create it if it doesn't exist asynchronously. Keyword Args: collection_name: Name of the collection

Cancel an A2A task. Publishes a cancel event that the cancellable decorator listens for. Args: context: The A2A request context cont

Split a PDF into chunks of maximum page count. Yields chunks one at a time to minimize memory usage. Args: file: The PDF file to chu

Clear all registered global after_tool_call hooks. Returns: Number of hooks that were cleared Example: >>> register_after_to

Close the underlying stream.

Creates the Content Crew

Build the default flow persistence backend. Returns the result of the registered factory if one is set, otherwise a built-in :class:`~crewai.

Evaluate this value as a full CEL expression.

Execute a single native tool call with full lifecycle management. Handles: arg parsing, tool lookup, max-usage check, cache read/write, befor

Execute crew with trigger payload.

Create a gRPC channel for the given URL.

Return a path label that does not expose absolute directory prefixes.

Format text as a content block for the LLM. Default implementation uses OpenAI/Anthropic format. Subclasses should override for provi

Get A2A agent configs and response model. Args: a2a_config: A2A configuration (any type). Returns: Tuple of client A2A confi

Get the dimensions of an image file. Args: file: The image file to measure. Returns: Tuple of (width, height) in pixels, or

Return the latest non-yanked PyPI version of CrewAI, or ``None`` on failure.

Call the LLM and return the response, handling any invalid responses. Args: llm: The LLM instance to call. messages: The messages

Get all pending todos. Returns: List of pending TodoItem objects.

Get the current human input provider. Returns: The current provider, or a new SyncHumanInputProvider if none set.

Handle the completion flow as shown in your diagram.

Handles the case when the maximum number of iterations is exceeded. Performs one more LLM call to get the final answer. Args: formatted_a

Handle partial JSON in a result string and convert to Pydantic model or dict. Args: result: The result string to process. model:

Check if the maximum number of iterations has been reached. Args: iterations: Current number of iterations. max_iterations: Maxim

Return True if the user has explicitly declined trace collection.

Return True when the enterprise non-interactive mode is enabled.

Return True if the Git repository is fully synced with the remote, False otherwise.

Execute the agent asynchronously with the given messages. This is the async version of the kickoff method that uses native async exec

List immediate child scopes under path. Args: path: Scope path to list children of. If None and root_scope is set,

Load prompts from a JSON file. Returns: The I18N instance with loaded prompts. Raises: Exception: If the pro

Convert a list of file sources to a named dictionary of FileInputs. Args: input_files: List of file source inputs or File objects. R

Process a single file according to constraints and its mode mode. Args: file: The file to process. Returns:

Resize an image to fit within the specified dimensions. Args: file: The image file to resize. max_width: Maximum width in pixels.

Restore the event scope stack from a checkpoint.

Push the latest recorded ``task_started`` scope for a task. Args: task_id: The task identifier to look up in the active event record.

Run all ``post_tool_call`` hooks against a context. Returns: The (possibly modified) tool result carried on the context.

Run all ``pre_tool_call`` hooks against a context. Returns: True if a hook blocked execution (returned False or raised :class:`Ho

Safely extract and validate tool information. Combines extraction, validation, and logging for robust tool conversion. Args: tool: T

Set a CLI configuration parameter.

Set the cache handler for the agent. Args: cache_handler: An instance of the CacheHandler class.

Set the ID of the last emitted event. Args: event_id: The event_id to set as the last emitted event.

Set whether to suppress tracing-related console messages. Args: suppress: True to suppress messages, False to show them. Returns:

Setup event listeners - delegates to specific handlers. Args: crewai_event_bus: The event bus to register listeners on.

Start the MCP server and initialize the tools.

Run the LLM call and stream scoped public ``StreamFrame`` events.

Iterate over frames, optionally filtered by channel.