Raise provider HTTP timeouts for longer generations#111
Closed
adambalogh wants to merge 1 commit into
Closed
Conversation
The provider-side httpx read/write timeouts (60s) and the Anthropic client timeout (120s) bound the full generation on non-streaming paths — the plain invoke() completion path and Anthropic json_schema structured output, which returns a single buffered chunk. With max_tokens raised to 12k, a long structured or non-streaming response can exceed those ceilings and fail with a read timeout. Raise read/write and the Anthropic timeout to 300s. On the streaming path this only widens the per-chunk ceiling, with no downside. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_013UUr2FRtYx6JJHShAqKPDj
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The provider-side httpx read/write timeouts (60s) and the Anthropic client timeout (120s) bound the full generation on non-streaming paths — the plain invoke() completion path and Anthropic json_schema structured output, which returns a single buffered chunk. With max_tokens raised to 12k, a long structured or non-streaming response can exceed those ceilings and fail with a read timeout. Raise read/write and the Anthropic timeout to 300s. On the streaming path this only widens the per-chunk ceiling, with no downside.
Claude-Session: https://claude.ai/code/session_013UUr2FRtYx6JJHShAqKPDj