Conversation
The gateway's per-call OpenAI timeout for gpt-image-2 was raised to 180s server-side (it routinely takes ~120-180s at 1536x1024 and larger). The SDK's old 120s default was cutting the request before the server had a chance to return. New default leaves ~20s of buffer above the server's 180s cap. Existing users passing an explicit timeout option are unaffected. Bumps to 1.10.1.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
The gateway's per-call OpenAI timeout for
gpt-image-2was raised to 180s server-side (BlockRunAI/blockrun#4) because OpenAI routinely takes 120–180s at 1536×1024+. The SDK's old 120s default was cutting the request before the server had a chance to return.Change
DEFAULT_TIMEOUT = 200000(was120000)Compatibility
Pure default-value bump. Existing callers passing an explicit
timeoutoption are unaffected.Test plan
npx vitest run— 101 passed / 0 failed / 12 skippedtsc --noEmit— no type errors