Prevent active chat streams from being cancelled after 60 seconds #68

Merged
ryan merged 1 commits from fix/stream-stall-timeout into main 2026-10-12 19:38:23 -04:00
Owner

Quart applies a 60-second response deadline to the chat SSE endpoint, cancelling active generation even when the model continues producing output. Disable the response deadline for this endpoint while preserving the existing silent-model stall timeout.

Add a regression test that streams beyond a shortened Quart response deadline and still completes successfully.

Validation: all 6 tests in tests/unit/test_stream_stall.py pass; Ruff and formatting hooks pass.

Quart applies a 60-second response deadline to the chat SSE endpoint, cancelling active generation even when the model continues producing output. Disable the response deadline for this endpoint while preserving the existing silent-model stall timeout. Add a regression test that streams beyond a shortened Quart response deadline and still completes successfully. Validation: all 6 tests in tests/unit/test_stream_stall.py pass; Ruff and formatting hooks pass.
ryan added 1 commit 2026-10-12 19:38:20 -04:00
ryan merged commit 78259855c8 into main 2026-10-12 19:38:23 -04:00
Sign in to join this conversation.
No Reviewers
No Label
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: ryan/simbarag#68