Raise first-chunk timeout to 90s and retry same server+model before fallback

Fork: 0

root / navi-1

Browse code Raise first-chunk timeout to 90s and retry same server+model before fallback - config.py: llm_stream_first_chunk_timeout 180s → 90s - fallback.py stream_complete: wrap gen.__anext__() in asyncio.wait_for() with llm_stream_first_chunk_timeout; on TimeoutError or LLMConnectionError sleep 2s and retry once on the same server+model before blacklisting/fallback Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> feature/navi-code master vmkdemo
1 parent 80ba2f5 commit 4f780995bb41b217874bcfdfa3497505f3b060e2 Eugene Sukhodolskiy authored on 24 May

Browse code

- config.py: llm_stream_first_chunk_timeout 180s → 90s
- fallback.py stream_complete: wrap gen.__anext__() in asyncio.wait_for()
  with llm_stream_first_chunk_timeout; on TimeoutError or LLMConnectionError
  sleep 2s and retry once on the same server+model before blacklisting/fallback

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

feature/navi-code master vmkdemo

1 parent 80ba2f5 commit 4f780995bb41b217874bcfdfa3497505f3b060e2

Eugene Sukhodolskiy authored on 24 May

Patch

Unified Split

Showing 2 changed files

Ignore Space Show notes View navi/config.py

Ignore Space Show notes View navi/llm/fallback.py

Show line notes below