init() — langchain Function Reference

Architecture documentation for the __init__() function in tool_retry.py from the langchain codebase.

Function python LangChainCore ApiManagement

Entity Profile

LangChainCore→ ApiManagement→ __init__() — langchain Function Reference

Dependency Diagram

graph TD
  eca8764c_16d4_7994_0b57_199409e3f389["__init__()"]
  33f83a05_ad1b_0c1c_e484_ac91455db157["ToolRetryMiddleware"]
  eca8764c_16d4_7994_0b57_199409e3f389 -->|defined in| 33f83a05_ad1b_0c1c_e484_ac91455db157
  style eca8764c_16d4_7994_0b57_199409e3f389 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain_v1/langchain/agents/middleware/tool_retry.py lines 128–221

    def __init__(
        self,
        *,
        max_retries: int = 2,
        tools: list[BaseTool | str] | None = None,
        retry_on: RetryOn = (Exception,),
        on_failure: OnFailure = "continue",
        backoff_factor: float = 2.0,
        initial_delay: float = 1.0,
        max_delay: float = 60.0,
        jitter: bool = True,
    ) -> None:
        """Initialize `ToolRetryMiddleware`.

        Args:
            max_retries: Maximum number of retry attempts after the initial call.

                Must be `>= 0`.
            tools: Optional list of tools or tool names to apply retry logic to.

                Can be a list of `BaseTool` instances or tool name strings.

                If `None`, applies to all tools.
            retry_on: Either a tuple of exception types to retry on, or a callable
                that takes an exception and returns `True` if it should be retried.

                Default is to retry on all exceptions.
            on_failure: Behavior when all retries are exhausted.

                Options:

                - `'continue'`: Return a `ToolMessage` with error details,
                    allowing the LLM to handle the failure and potentially recover.
                - `'error'`: Re-raise the exception, stopping agent execution.
                - **Custom callable:** Function that takes the exception and returns a
                    string for the `ToolMessage` content, allowing custom error
                    formatting.

                **Deprecated values** (for backwards compatibility):

                - `'return_message'`: Use `'continue'` instead.
                - `'raise'`: Use `'error'` instead.
            backoff_factor: Multiplier for exponential backoff.

                Each retry waits `initial_delay * (backoff_factor ** retry_number)`
                seconds.

                Set to `0.0` for constant delay.
            initial_delay: Initial delay in seconds before first retry.
            max_delay: Maximum delay in seconds between retries.

                Caps exponential backoff growth.
            jitter: Whether to add random jitter (`±25%`) to delay to avoid thundering herd.

        Raises:
            ValueError: If `max_retries < 0` or delays are negative.
        """
        super().__init__()

        # Validate parameters
        validate_retry_params(max_retries, initial_delay, max_delay, backoff_factor)

        # Handle backwards compatibility for deprecated on_failure values
        if on_failure == "raise":  # type: ignore[comparison-overlap]
            msg = (  # type: ignore[unreachable]
                "on_failure='raise' is deprecated and will be removed in a future version. "
                "Use on_failure='error' instead."
            )
            warnings.warn(msg, DeprecationWarning, stacklevel=2)
            on_failure = "error"
        elif on_failure == "return_message":  # type: ignore[comparison-overlap]
            msg = (  # type: ignore[unreachable]
                "on_failure='return_message' is deprecated and will be removed "
                "in a future version. Use on_failure='continue' instead."
            )
            warnings.warn(msg, DeprecationWarning, stacklevel=2)
            on_failure = "continue"

        self.max_retries = max_retries

        # Extract tool names from BaseTool instances or strings