Append new training data for a specific agent and iteration. Args: train_iteration: The training iteration number. ag

Retrieve an auth scheme by key.

Execute the crew's workflow. Args: inputs: Optional input dictionary for task interpolation. input_files: Optional di

Emit an event to all registered handlers. If handlers have dependencies (registered with depends_on), they execute in dependency orde

Build a runnable declarative flow from contents or a file path.

Executes the tool synchronously. Args: *args: Positional arguments for the tool. **kwargs: Keyword arguments for the

Context manager for temporary event handling scope. Useful for testing or temporary event handling. All handlers registered within th

Main method for tool execution.

High-level LLM call method. Args: messages: Input messages for the LLM. Can be a string or list of message d

Store an auth scheme.

Print to console. Simplified to only handle panel-based output.

Update an existing memory record by ID. Args: record_id: ID of the record to update. content: New content; re-embedde

Read the file content as string.

Print ``content`` with optional color, honoring suppression context.

Execute the agent with the given messages using the AgentExecutor. This method provides standalone agent execution without requiring a Crew.

Return keys for dict unpacking.

Return scope info for path. Args: path: Scope path to get info for. If None and root_scope is set, defaults to ro

Append a user message, run one conversational turn, and return output. Available only when ``conversational = True`` is set on the subclass

Generic handler for action events (LLM calls, tool usage). Args: event_type: Type of the event. source: Source object

Sync wrapper for aget.

Create a Pydantic model from a JSON schema. This function takes a JSON schema as input and dynamically creates a Pydantic model class based o

Return a NL2SQLTool wired to an in-memory SQLite DB. Schema-introspection is patched out so we can create the tool without a real PostgreSQL

Print a panel with consistent formatting if verbose is enabled.

Sanitize tool name for LLM provider compatibility. Normalizes Unicode, splits camelCase, lowercases, replaces invalid characters with undersc

Async high-level LLM call method. Args: messages: Input messages for the LLM. Can be a string or list of mes

Native async kickoff method using async task execution throughout. Unlike kickoff_async which wraps sync kickoff in a thread, this method

Return the static Flow Definition built from this Flow class.

Add an event to the record and wire its edges. Args: event: The event to insert. Returns: The created node.

Remove all nodes from the record under the write lock.

Read the file content as bytes.

Count records in scope (and subscopes). Args: scope_prefix: Optional scope path (None = all). Returns: Numbe

Format this match as a human-readable string including metadata. Returns: A multi-line string with score, content, categories, an

Create an AgentExecutor without validation — for unit tests. Uses model_construct to skip Pydantic validators so plain Mock() objects are acc

Raise ValueError if *sql_query* is not permitted under the current config. Splits the query on semicolons and validates each statement

Build the (body, content_type, final_url) tuple safe_get_bounded returns.

Retrieve a prompt slice by key. Args: slice: The key of the prompt slice to retrieve. Returns: The prompt sl

Convert MCP server references/configs to CrewAI tools.

Log a message with timestamp if verbose mode is enabled. Args: level: The log level (e.g., 'info', 'warning', 'error').

Run all checks. Later checks are skipped when earlier ones make them impossible (e.g. no pyproject.toml → no lockfile check).

Call the LLM with the given messages. Args: messages: Input messages for the LLM. Can be a string or list of

Load the data from the specified file using pickle. Returns: The data loaded from the file.

Parse {% js 'script.js' %} tag. Args: parser: Jinja2 parser instance. Returns: Output node with rendered scr

Execute the update mechanism and return result. Args: client: A2A client instance. message: Message to send.

Records that a feature was used. One span = one count. Args: feature: Feature identifier, e.g. "planning:creation",

Prepare parameters for the completion call. Args: messages: Input messages for the LLM tools: Optional list of tool s

Connect to MCP server and initialize session. Returns: Self for method chaining. Raises: MCPAuthenticationEr

Return the project's id, minting and persisting one if absent. Writes ``project_id`` into the ``[tool.crewai]`` table so it is committed with

Mimic requests' error-status behavior.

Emit LLM call completed event.

Execute a task with the agent. Args: task: Task to execute. context: Context to execute the task in. tool

Execute telemetry operation safely, checking both readiness and environment variables. Args: operation: A callable that performs

Execute the task synchronously.

Return the active execution uuid, if any.

Load a ``Crew`` from a JSON/JSONC definition file. The definition file describes the crew's agents, tasks, process type, and default inputs.

Store a single item in memory (synchronous). Routes through the same serialized save pool as ``remember_many`` to prevent races, but

Build a provider whose SDK clients are pinned to a mock transport. Replaces the private clients rather than patching module globals so the test

Return a DB2VectorSearchTool with mocked ibm_db packages.

Retrieve an error message by key. Args: error: The key of the error message to retrieve. Returns: The error

Reset (delete all) memories in scope. Args: scope: Scope to reset. If None and root_scope is set, resets only wit

Validate that a URL is safe to fetch. Blocks ``file://`` scheme entirely. For ``http``/``https``, resolves DNS and checks that the target IP

Wait for all pending event handlers to complete. This helper ensures all sync and async handlers finish processing before proceeding. Useful

Save current settings to settings.json.

Register an extension. Args: extension: The extension to register.

Return the final result after stream exhaustion or completion.

Creates a deep copy of the Task while preserving its original class type. Args: agents: List of agents available for the task.

Creates or returns an LLM instance based on the given llm_value. Args: llm_value: LLM instance, model name string, config dict, None, or

Create a Flow instance from a pending feedback state. This classmethod is used to restore a flow that was paused waiting for async hu

Interpolate placeholders (e.g., {key}) in a string while leaving JSON untouched. Only interpolates placeholders that follow the pattern {variable_