fix: treat gateway-instant-408 responses as retryable timeouts - #35
Open
Michael J. Jabbour (michaeljabbour) wants to merge 1 commit into
Open
Conversation
The vLLM provider pins max_retries=0 and retries via its own backoff wrapper, but the OpenAI SDK maps a *received* HTTP 408 to a generic APIStatusError, so a gateway-fabricated 408 bypassed retry entirely and surfaced to the caller after ~0.2s. The LiteLLM gateway emits 408s with 'time taken=0.0 seconds' in the body when its own transport fails instantly; a genuine client inactivity 408 carries real elapsed time. Distinguish on that marker: instant 408 -> retryable LLMTimeoutError (handled by the existing retry_with_backoff path); genuine 408 -> non-retryable LLMError.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
408withtime taken=0.0 secondswhen its transport fails instantly) reaches this provider as a generic OpenAIAPIStatusError; because the provider setsmax_retries=0and retries via its own wrapper, these user-invisible infrastructure hiccups surfaced to callers after ~0.2s instead of being retried.time taken=0.0) → retryableLLMTimeoutErrorhandled by the existingretry_with_backoffpath; a genuine client-inactivity 408 (real elapsed time) → non-retryableLLMError, unchanged behavior.Tests
test_error_translation.py, 278/279 full suite — the one failure (test_behavioral.py::test_list_models_returns_list) pre-exists onmain.