Fix OpenAI timeout settings not being applied #10036
Open
+1
−0
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Outdated suggestions cannot be applied.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.
Description
This PR fixes an issue where timeout settings were not being applied when using OpenAI-compatible backends in a local environment.
Previously, even when custom timeout values were configured, requests would still terminate based on the default timeout behavior of the OpenAI Node SDK. This change ensures that the configured timeout values are correctly propagated and respected by the backend.
AI Code Review
@continue-reviewChecklist
Screen recording or screenshot
Before
After
Tests
Before this change, requests were terminated after 10 minutes, which matches the default timeout behavior described in the OpenAI Node SDK documentation:
https://github.com/openai/openai-node?tab=readme-ov-file#timeouts
This was observed when the downstream client (Continue CLI) exited due to the timeout, even though custom timeout values were configured.
After applying this patch, running the same configuration confirms that the custom timeout settings are correctly applied and requests are no longer terminated at the default 10-minute limit.
Continue Tasks:▶️ 1 queued — View all
Summary by cubic
Ensure configured request timeouts are applied to OpenAI-compatible backends, preventing requests from being cut off at the SDK’s 10-minute default. This makes local runs honor custom timeout settings.
Written for commit bc206b0. Summary will update on new commits.