Teknium 915df02bbf fix(streaming): stale stream detector race causing spurious RemoteProtocolError ...

The stale stream detector (90s timeout) was killing healthy connections
during the model's thinking phase, producing self-inflicted
RemoteProtocolError ("peer closed connection without sending complete
message body"). Three issues:

1. last_chunk_time was never reset between inner stream retries, so
   subsequent attempts inherited the previous attempt's stale budget
2. The non-streaming fallback path didn't reset the timer either
3. 90s base timeout was too aggressive for large-context Opus sessions
   where thinking time before first token routinely exceeds 90s

Fix: reset last_chunk_time at the start of each streaming attempt and
before the non-streaming fallback. Increase base timeout to 180s and
scale to 300s for >100K token contexts.

Made-with: Cursor

2026-03-27 04:05:51 -07:00

384 KiB

Raw Blame History

View Raw