fix(llm): Retry proxy upstream failures as transient#843
Merged
Conversation
Some proxy and gateway errors between the client and the provider report failures in bodies that don't match any provider's error envelope, so they land in the catch-all `StreamErrorKind::Other` bucket and were treated as non-retryable. Retrying these usually succeeds since the failure is on the network path, not the request itself. `StreamError::is_retryable` now also checks `Other`-kind errors for transient network patterns in the error message, such as "upstream unreachable", "no healthy upstream", "upstream connect error" (envoy-style proxies), and "network is unreachable" / "host unreachable" (transport errors). Errors matching these patterns are now retried automatically instead of surfacing as a hard failure. Signed-off-by: Jean Mertz <git@jeanmertz.com>
Signed-off-by: Jean Mertz <git@jeanmertz.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Some proxy and gateway errors between the client and the provider report failures in bodies that don't match any provider's error envelope, so they land in the catch-all
StreamErrorKind::Otherbucket and were treated as non-retryable. Retrying these usually succeeds since the failure is on the network path, not the request itself.StreamError::is_retryablenow also checksOther-kind errors for transient network patterns in the error message, such as "upstream unreachable", "no healthy upstream", "upstream connect error" (envoy-style proxies), and "network is unreachable" / "host unreachable" (transport errors). Errors matching these patterns are now retried automatically instead of surfacing as a hard failure.