Build an isolated execution context for a single todo. Passes only final results from completed dependencies — never execution traces

Build the LLM-facing description, including the current per-call cap. Args: max_seconds: The per-call cap advertised to the model. R

Build the execution prompt, stop words, and RPM limit function. Args: raw_tools: The raw tools available to the agent. R

Build context by reading file once. Args: file: The file to build context for. Returns: FileContext with cac

Build fingerprint metadata as a config dict for tool invocation. Returns the fingerprint data in a config dict rather than injecting it

Build a multi-turn conversation that produces multiple chunks at max_tokens=200. Each non-system message is ~100-140 estimated tokens (400-560 ch

Inner builder shared by the public entry point and recursive nested-object creation. Preprocessing via ``jsonref.replace_refs`` and the sanitizat

Build a LiteAgentOutput from an executor result dict. Shared logic used by both sync and async execution paths. Args: re

Build a timestamped checkpoint file path under a branch subdirectory. Filename format: ``{ts}_{uuid8}_p-{parent_id}.json`` Args: dir

Mimic a litellm ModelResponse that contains both content and tool_calls.

Cache key for a provider's resolved model list. Keyed by the exact API key (via a short, non-reversible digest — never the key itself), so sw

Call provided synchronous handlers. Args: source: The emitting object event: The event instance handlers:

Calls the LLM with the planning prompt. Args: prompt: The prompt to send to the LLM. plan_type: The type of plan bein

Call OpenAI Responses API.

Check if an execution error should be re-raised immediately. Args: e: The exception that occurred. task: The task bei

Warn when the lockfile pins a crewai release older than 1.13.0, which is where ``_load_response_format`` was introduced.

Utility method to split text into chunks.

Utility method to split text into chunks.

Utility method to split text into chunks.

Utility method to split text into chunks.

Utility method to split text into chunks.

Utility method to split text into chunks.

Three-chunk stream mirroring LiteLLM's include_usage behavior: two content chunks where the second carries finish_reason="stop", then a final

Classify a Gemini exception as transient or permanent upload error. Checks Gemini-specific error message patterns first, then falls back to g

Classify an S3 exception as transient or permanent upload error. Args: e: The exception to classify. filename: The filename for e

Clean up batch data after successful finalization to free memory

Cleanup MCP client connections after task execution.

Drop the header's active method once it ends. Caller holds the lock. Falls back to another still-active step (methods can overlap) so the

Validate an LLM response into the configured Pydantic model. Pure post-processing — performs no I/O. Shared by ``to_pydantic`` and ``

Collect CEL root identifiers, excluding receiver macro local variables.

Append a single line with soft JSON syntax highlighting.

Combine agent and crew knowledge contexts into a single string. Args: agent: The agent with knowledge contexts. Returns: Com

Shared strict sanitization: inline refs, close objects, require all properties.

Fire-and-forget: compact the table in a daemon background thread.

Mark the final reviewed answer as the completed executor state.

Compute exponential backoff delay with jitter. Args: attempt: The current attempt number (0-indexed). Returns: Delay in seco

Determine output format and schema from task requirements. This is a helper method that examines the task's output requirements and r

Prompt before ZIP upload unless confirmation was already supplied.

Check if any message content contains a file_id reference. Anthropic's Files API is in beta and requires a special header when file_id refere

Convert CrewAI tool format to OpenAI function calling format.

Convert CrewAI tools to Responses API format. Responses API uses internally-tagged format (flat structure): { "type": "fu

Copy method metadata to a wrapper object. Args: wrapper: The wrapper object to update. meth: The method to copy metadata from.

Create Pydantic field definition based on type and requirement.

Create an instructor.

Create a mock agent card with proper model_dump behavior.

Creates the planner task using the given agent and tasks summary. Args: planning_agent: The agent responsible for planning.

Creates the planning agent for the crew planning. Returns: An Agent instance configured for planning tasks.

Create a PointStruct from a document and its embedding. Args: doc: Document dictionary containing content, metadata, and optional doc_id.

Create a new table with the given vector dimension. Caller must already hold ``store_lock(self._lock_name)``.

Create git tag, push it, and create a GitHub release.

Helper to write raw content to a temporary file and return its path.

Create a trace event with ordering information.

Create a fresh transport instance from an MCP server config. Returns a ``(transport, server_name)`` tuple. Each call produces an inde

Read ``AZURE_CREDENTIAL_SCOPES`` (comma-separated) into a list.

Return the validated path of a custom tool inside ``tools/``. Rejects names that aren't plain identifiers and (belt-and-suspenders) any resol

Return the best available identifier for a deployment show URL.

Return the first write command inside a CTE body, or None. Instead of tokenizing the whole statement (which falsely matches column names like

Dispatch EXECUTION_END with status="failed" for a kickoff that raised. No-op when EXECUTION_START never dispatched (pairing invariant) or whe

Dispatch EXECUTION_END with status="failed" for an execution that raised. Callers enforce the pairing invariant (EXECUTION_START dispatched,

Print and open the verification URL the user must visit.

Display success message after crew creation. Args: json_response (Dict[str, Any]): The response containing crew informat

Explain that ZIP deployment will be used without an origin remote.

Display log messages. Args: log_messages (List[Dict[str, Any]]): The log messages to display.

Write a checkpoint and prune old ones if configured.

Run parallel search across (embeddings x scopes) with filters. Populates ``state.chunk_findings`` and ``state.confidence``. Returns t