feat(langchain/createAgent): implement retry model request hook in middleware #9128
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR implements the
retryModelRequest
middleware hook andModelFallbackMiddleware
, mirroring the Python implementation.Changes
1. New
retryModelRequest
Middleware HookAdded a new optional hook to the
AgentMiddleware
interface that allows middleware to intercept model invocation errors and optionally retry with modified requests:Parameters:
error
: The exception that occurred during model invocationrequest
: The original model request that failedstate
: The current agent stateruntime
: The runtime contextattempt
: The current attempt number (1-indexed)Return value:
ModelRequest
: Modified request to retry withvoid
: Propagate the error (no retry)2. ModelFallbackMiddleware
New middleware that provides automatic model fallback on errors:
Features:
3. AgentNode Retry Logic
Modified
AgentNode#invokeModel
to implement retry loop:retryModelRequest
hooks