Create an AzureCompletion(api='responses'). Must be called inside a context where OpenAICompletion is already mocked (i.e. via the ``mock_ope

A 200 body holding only an upstream error, as gateways send it.

Return the latest non-prerelease, non-yanked version from PyPI releases.

Format messages for Anthropic API. Anthropic has specific requirements: - System messages are separate from conversation messages

Kill the cached persistent sandbox if one exists.

Create a deployable ZIP archive for a CrewAI project. Raises: ArchiveError: Nothing deployable was found, or the project could not be

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

Format a message for the LLM. Args: prompt: The message content. role: The role of the message sender, either 'user' or 'assist

Create a tool from a function. Args: func: The function to create a tool from name: The name of the tool. Defaults to

Asynchronous kickoff method to start the crew execution. Args: inputs: Optional input dictionary for task interpolation.

Load all task output records from the database. Returns: List of dictionaries containing task output records, ordered by task_ind

Load an existing ``Agent`` from a ``.json`` / ``.jsonc`` definition file.

Retrieve a cached tool result. Args: tool: Name of the tool. input: Input string used for the tool. Returns:

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

Resolve the effective policy for one call. Most specific wins: tool, task, agent, crew, then :attr:`ToolFailurePolicy.WARN`. Callers pass eit

Unpack an archive into the cache and write metadata. Uses tarfile with filter='data' for path-traversal protection. Args:

Check if the model supports function calling.

Convert to JSON-RPC error object format.

Verify a JWT's signature and claims using PyJWT. Args: jwt_token: The JWT (JWS) string to validate. jwks_url: The URL of the JWKS

Factory function that returns crewai platform tools. Args: apps: List of platform apps to get tools that are available on the platform.

Send batch initialization to backend

Resolve tool specs into tool instances or serialized BaseTool dicts. Strings keep the existing shorthand behavior. Dicts are passed through so

Add documents with their embeddings to a collection. Keyword Args: collection_name: The name of the collection to add documents t

Scan a directory for skill directories containing SKILL.md. Loads each discovered skill at METADATA disclosure level. Args: search_p

Block until all pending background saves have completed. Called automatically by ``recall()`` and should be called by the crew at shu

Generate conversion instructions based on the model and LLM capabilities. Args: model: A Pydantic model class. llm: The language

Load a skill at METADATA disclosure level. Parses SKILL.md frontmatter only and validates directory name. Args: skill_dir: Path to t

Return the message content as text. Used wherever a message has to collapse to a string -- token estimation, memory, and the one turn promote

Pause Live session updates to allow for human input without interference. This stops any active streaming Live session to prevent console ref

Context manager to temporarily set the platform integration token. Args: integration_token: The integration token to set within the context

Sanitize a name for use in hierarchical scope paths. Converts to lowercase, replaces non-alphanumeric chars (except underscore and hyphen) wi

Estimate token count using a conservative cross-provider heuristic. Args: text: The text to estimate tokens for. Returns: Es

Invoke after_llm_call hooks for an LLM call that reached the provider. This method should be called by native provider implementations after

Return ``(yanked, reason)`` for ``version_str`` against PyPI releases.

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

Convert a provider usage object to a plain dict and flatten the cache/reasoning sub-counts that LiteLLM nests under provider-specific

Handle and display error messages from API responses. Args: response: The response from the Plus API.

Delete memories matching the given criteria. Args: scope_prefix: Optional scope path prefix. categories: Optional lis

Format log record as JSON string.

Create a Fingerprint from a dictionary representation. Args: data: Dictionary representation of a fingerprint Returns:

Get constraints for a provider by name or return if already ProviderConstraints. Args: provider: Provider name string or ProviderConstrai

Split SKILL.md content into frontmatter dict and body text. Args: content: Raw SKILL.md file content. Returns: Tuple of (fro

Parse a TOML string and return its parsed contents.

Parse tool call arguments from a JSON string or dict. Returns: ``(args_dict, None)`` on success, or ``(None, error_result)`` on J

Stop the MCP server.

Report a hook deny as a deny rather than as a provider failure. The call still owes its started event a terminal one, so the failed event

Build an in-memory .tar.gz containing the given filename → content mapping.

Normalize an Ollama base URL into a full OpenAI-compatible endpoint. ``OLLAMA_HOST`` follows Ollama's own convention and may be a bare host (

Replace crewai dependency version pins in a pyproject.toml string. Handles both pinned (==) and minimum (>=) version specifiers, as well as e

Run a void telemetry procedure, swallowing failures.

Whether this kickoff should defer final flow trace finalization.

Fail unless every effective canary CrewAI requirement has the exact pin.

Add documents with their embeddings to a collection asynchronously. Keyword Args: collection_name: The name of the collection to

Add a new task output record to the database. Args: task: The Task object containing task details. output: Dictionary

Start an execution context unless one is already active. The outermost crew or flow receives a new uuid by default. Nested executions inherit

Download a skill from the registry and store it in the cache. Args: org: Organisation slug. name: Skill name. source: Opt

Search exceptions for an HTTP status reported by an MCP server. Args: *errors: Exceptions to search, in order of preference. Returns

Return the cached skill directory path if usable, else None. Args: org: Organisation slug. name: Skill name.

Returns the context window size, using 75% of the maximum to avoid cutting off messages mid-thread. Raises: Valu

Get current call_id from context

Handle unknown errors by informing the user. Args: printer: Printer instance for output exception: The exception that occurred

List all CLI configuration parameters.

Context manager that establishes an LLM call scope with a unique call_id.

Load and process all files from a directory recursively. Args: source_content: Directory path or URL to a directory listing

Fetch content from URL (for providers that don't support URL references).

Resolve a registry reference to a Skill object. Resolution order: 1. ./skills/{name}/ in the current working directory (project-local) 2.