Dispatch a context to all hooks registered for a point. Resolves global then scoped hooks and runs them through :func:`run_hooks`. No-op fast

Generates the task prompt with optional markdown formatting. When the markdown attribute is True, instructions for formatting the res

Reset the last event ID to None. Should be called at the start of a new flow or when resetting event state.

Resume flow execution, optionally with human feedback. This method continues flow execution after a flow was paused for async human f

Request input from the user during flow execution. Blocks the current thread until the user provides input or the timeout expires. Wo

Build a visualization structure projection from a FlowDefinition.

Convert CrewAI tools to OpenAI function calling format. This function converts CrewAI BaseTool and CrewStructuredTool objects into the OpenAI

Generate JSON schema description of a Pydantic model. This function takes a Pydantic model class and returns its JSON schema, which includes

Sync wrapper for aremove.

A declaration naming the built-in methods explicitly. Synthesizing these entries from ``conversational.enabled`` is a follow-up; until then a

Create a simple analyst crew for file analysis.

Track token usage from Bedrock response.

Append a final user-visible assistant message.

Get all registered global before_llm_call hooks. Returns: List of registered before hooks

Converts a Python object into a JSON-compatible representation. Supports primitives, datetime objects, collections, dictionaries, dataclasses

Apply stop words to truncate response content. This method provides consistent stop word behavior across all native SDK providers. Na

Build a multimodal message with text and file content.

Build a ``requests.Response``-like mock with the attributes used by ``_make_request``.

Prepare parameters for OpenAI Responses API. The Responses API uses a different structure than Chat Completions: - `input` instead of

Look up a node by event ID. Args: event_id: The event's unique identifier. Returns: The node, or None if not

Choose how executions in this context ask permission to share traces. The callback runs once after a successful execution has finished. It re

Allow arbitrary attribute assignment for backward compat with plain class.

Store a span and apply any pending end that arrived before it was created. The event-bus thread pool can deliver completion-event handlers before

Create a deep copy of the Agent.

Block until all pending event handlers complete. This method waits for all futures from previously emitted events to finish executing

Get the platform integration token from the current context or environment. Returns: The integration token if set, otherwise None.

Return the tracing session owned by the active execution.

Reset the emission sequence counter to 1. Resets for the current context only.

Check if the model supports multimodal inputs. For litellm, check common vision-enabled model prefixes. Returns: True if

Return the call-scoped streaming mode for this instance.

Emit LLM call started event.

Run validation with the subprocess-based import check stubbed out; the classifier is exercised directly in its own tests below.

Return the installed crewAI version string. Falls back to ``"unknown"`` when neither crewai nor crewai-core are pip-installed (e.g. running d

Retrieve a prompt by kind and key. Args: kind: The kind of prompt. key: The key of the specific prompt to retrieve.

Save state with a pending feedback marker. This method stores both the flow state and the pending feedback context, allowing the flow

Summarize messages to fit within context window. Uses structured context compaction: preserves system messages, splits at message boundaries,

Create a simple analyst agent for file analysis.

Generic handler for context end events. Args: event_type: Type of the event. source: Source object that triggered the

Smart task factory that automatically assigns a mock agent when guardrails are present. This maintains backward compatibility while handling

Get summary of token usage for this LLM instance. The counters are cumulative for the lifetime of this instance: they grow across eve

Check if the exception is due to context length exceeding. Args: exception: The exception to check Returns: bool: True if th

Join a root scope with an inner scope, handling edge cases properly. Args: root: The root scope prefix (e.g. '/crew/research-crew').

Context manager for acquiring a read lock. Yields: None

Validate that a file path is safe to read. Resolves symlinks and ``..`` components, then checks that the resolved path falls within *base_dir

Call OpenAI Chat Completions API. Falls back to the Responses API when the model turns out not to be served by chat completions, whic

Sanitize a collection name to meet ChromaDB requirements. Requirements: 1. 3-63 characters long 2. Starts and ends with alphanumeric char

Best-effort detection of the AI coding assistant running this process. Uses the shared ``CODING_AGENT_ENV_MARKERS`` table, so this agrees with th

Format text and files as provider-specific multimodal content blocks. This is the main high-level API for converting files to content blocks

Register a global before_tool_call hook. Global hooks are added to all tool executions automatically. This is a convenience function for regi

Resolve a file to its delivery format for a provider. Args: file: The file to resolve. provider: Provider name (e.g.,

Run a shell command and return output. Args: cmd: Command to run as list of strings. cwd: Working directory for command. Ret

Sync wrapper for aset.

Invoke before_llm_call hooks for an LLM call reaching the provider. This method should be called by native provider implementations before

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

Register a global after_tool_call hook. Global hooks are added to all tool executions automatically. This is a convenience function for regis

Store multiple items in memory (non-blocking). The encoding pipeline runs in a background thread. This method returns immediately so

Convert text to pydantic. Args: current_attempt: The current attempt number for conversion retries. Returns:

Context manager for acquiring a write lock. Yields: None

Handle tool execution with proper event emission. Args: function_name: Name of the function to execute function_args:

Execute the task asynchronously using native async/await.

Drain pending saves, flush storage, and shut down the background thread pool.

Create standardized status content with consistent formatting.

Get a todo by its step number.

GET a URL while validating each redirect target before following it. On success the hops are attached to the returned response's ``history`` and

Emit LLM call failed event.

Create a SkillFrontmatter with the given name.

Call OpenAI API (Chat Completions or Responses based on api setting). Args: messages: Input messages for the completion.

Flush local shard to central and clean up.

Best-effort detection of where this process is running. Separate from :func:`detect_coding_agent` because the two answer different questions.

Generate a unique document id based on the source reference and content. If the source reference is not provided, the content is used as the s

Get all registered global before_tool_call hooks. Returns: List of registered before hooks

Return neighbor IDs for a given edge type. Args: edge_type: The relationship type to query. Returns: List of

Replay the crew execution from a specific task.