Convert MCP server references/configs to CrewAI tools. Delegates to :class:`~crewai.mcp.tool_resolver.MCPToolResolver`.

Increment the tools errors counter.

Executes the Crew's workflow for each input and aggregates results. Args: inputs: List of input dictionaries, one per execution.

Retrieve relevant memories. ``shallow`` embeds the query directly and runs a single vector search. ``deep`` (default) uses the Recall

Register a global after_llm_call hook. Global hooks are added to all executors automatically. This is a convenience function for registering

Reset specific or all memories for the crew. Args: command_type: Type of memory to reset. Valid options: 'memory'

GET a URL through :func:`safe_get`, refusing bodies over *max_bytes*. The body is streamed and abandoned as soon as it crosses the limit, so an

Search for similar documents using a query. Keyword Args: collection_name: Name of the collection to search in. query

Set available input files. Args: files: Dictionary mapping file names to file inputs.

Get the git status in porcelain format.

Generate a standard prompt for task execution. Returns: A dictionary containing the constructed prompt(s).

Allow arbitrary attribute assignment for backward compat with plain class.

Save the documents to the storage asynchronously. This method should be called after the chunks and embeddings are generated. Raises

Build a minimal docs/ tree with one previous snapshot + Edge + docs.json. The shape mirrors the real repo: an Edge directory with per-locale fold

Turn a raw import-time exception into a user-actionable finding.

Collapse free-form feedback to a predefined outcome using LLM. This method uses the specified LLM to interpret the human's feedback a

Extract token usage and response metadata from Anthropic response.

Format messages with role labels for summarization. Skips system messages. Handles None content, tool_calls, and multimodal content blocks.

Get or create a code interpreter for the specified thread. Args: thread_id: Thread ID for the code interpreter session R

Return ``True`` if *fn* cannot survive a serialize/deserialize round-trip. Built-in functions, plain module-level functions, and classes produce

Read the user-data JSON file, returning ``{}`` on missing/corrupt.

Prepare documents for ChromaDB by extracting IDs, texts, and metadata. Args: documents: List of BaseRecord documents to prepare. Ret

Run an async coroutine from sync context without blocking event loop.

Run a void telemetry procedure, swallowing failures.

Set status for an explicit plan step reported by the planner.

Promote a skill to INSTRUCTIONS disclosure level. Idempotent: returns the skill unchanged if already at or above INSTRUCTIONS. Args:

Add a tool result to the cache. Declared failures are never stored: replaying one would make a transient error permanent for the rest

Asynchronously emit an event to registered async handlers. Only processes async handlers. Use in async contexts. Args: s

Clean up Stagehand resources.

Return the configured declarative flow source for flow projects.

Create a new collection in Qdrant. Keyword Args: collection_name: Name of the collection to create. Must be unique. v

Extract output from code interpreter response stream. Args: response: Response from code interpreter execution Returns: Extr

Extract tool call ID, name, and arguments from various provider formats. Args: tool_call: The tool call object to extract info from.

Emit a final ``FlowFinishedEvent`` and finalize the trace batch. Pairs with ``flow.defer_trace_finalization = True`` (or ``Conversati

Restore a Crew from a checkpoint, ready to resume via kickoff(). Args: config: Checkpoint configuration with ``restore_from`` set

Normalize a provider's raw usage dict into a ``UsageMetrics``. Accepts the full set of key aliases CrewAI providers emit: ``prompt_to

Get all registered global after_tool_call hooks. Returns: List of registered after hooks

Get the current parent event ID from the stack.

Return ``[tool.crewai].project_id`` if the project has one. Read-only and safe to call from library code: it never creates or modifies anythi

Initialize a new trace batch (thread-safe)

Return ``(yanked, reason)`` for the currently installed version.

Check if tracing is enabled in current execution context. Returns: True if tracing is enabled in context, False otherwise. Return

Return ``message`` with the cache-breakpoint flag set. Returns a new dict so callers can safely pass literal dicts.

Mark a todo as completed by step number.

Push an event ID and type onto the scope stack.

Register a global hook for an interception point.

Save the data to the specified file using pickle. Args: data: The data to be saved to the file.

Convert a dotted path string to the callable it references. If *value* is already callable it is returned as-is, with a warning if it cannot

Validate an audio file against constraints. Args: file: The audio file to validate. constraints: Audio constraints to validate ag

Common payload refinement for all tools.

Helper to create a skill directory with SKILL.md.

Emit one fake ``LLMCallCompletedEvent`` with ``current_flow_id`` pinned to ``flow_id``. Runs in a freshly-copied context so the value the bus

Fetch action schemas from the platform API.

Format messages for OpenAI API.

Format messages for Converse API following AWS documentation. Note: Returns dict[str, Any] instead of LLMMessage because Bedrock uses

Get or create the Gemini client.

Get OpenAI client parameters.

Stable, privacy-preserving machine fingerprint (cross-platform).

Invoke before_llm_call hooks for direct LLM calls (no agent context). This method should be called by native provider implementations before

Invoke step callback if configured. Args: formatted_answer: Current agent response.

Return True if the cache is less than 24 hours old.

Make a JSON-RPC 2.0 MCP request to Agent Handler.

Whether a 400 is OpenAI refusing `reasoning_effort` alongside tools. GPT-5.6 applies a server-side `reasoning_effort` default and then reject

Import a module and walk attribute lookups to resolve a dotted path. Handles multi-level qualified names like ``"module.ClassName.method"`` b

Split messages into chunks at message boundaries. Excludes system messages from chunks. Each chunk stays under max_tokens based on estimated

Translate a chat-format message into Responses ``input`` items. Tool calling is expressed differently by the two APIs. Chat Completions

Track token usage internally in the LLM instance. Args: usage_data: Token usage data from the API response

Validate the search query to ensure it's safe to execute. Only SELECT and SHOW statements are allowed for security reasons. Args:

Cancel streaming and clean up resources.

Add content to the knowledge base.

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

Creates a deep copy of the Crew instance. Returns: Crew: A new instance with copied components

Delete a collection and all its data. Keyword Args: collection_name: Name of the collection to delete. Raises:

Detect MIME type from file content. Uses python-magic if available for accurate content-based detection, falls back to mimetypes module using

Force additionalProperties=false on all object-type dicts recursively. OpenAI strict mode requires all objects to have additionalProperties=false

Format skill information for agent prompt injection. At METADATA level: returns name and description only. At INSTRUCTIONS level or above: re

Build an expression with the standard Flow runtime context.

Generate a UUID-based filename with extension from content type. Args: content_type: MIME type to derive extension from. Returns:

Get merged crew and task files. Task files override crew files with the same name. Args: crew_id: Unique identifier for the crew exe