feat(core): extended retry logic for RunnableRetry #9446
Closed
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Outdated suggestions cannot be applied.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 extends the
RunnableRetryclass with granular retry control options, enabling fine-grained retry policies for base chat models and other runnables. This addresses the limitation where using.withRetry()on LLMs was incompatible withcreate_agentdue to type changes, and provides production-ready retry capabilities similar toToolRetryMiddleware.Note: this change is fully backwards compatible and only makes additive changes.
Changes
Extended
RunnableRetryClassAdded support for advanced retry configuration options:
retryOn: Filter which exceptions trigger retries (function or array of error constructors)backoffFactor: Control exponential backoff multiplier (default: 2.0)initialDelayMs: Set initial delay before first retry (default: 1000ms)maxDelayMs: Cap maximum delay between retries (default: 60000ms)jitter: Enable/disable random jitter to avoid thundering herd (default: true)Usage Examples
Basic Usage (Backward Compatible)
Advanced Retry Options
Retry Specific Error Types