nesquena-hermes 765d8520d4 fix(streaming): quota error detection, error persistence, stream_end session_id fix (#767) ...

- quota_exhausted error type: distinguishes credit exhaustion from rate limits
- Streaming errors persisted to session file so they survive page reload
- _error flag excludes persisted errors from subsequent LLM API calls
- stream_end and title SSE events use original session_id (not s.session_id which rotates during context compaction)

Fixes #739, #652, #653

2026-04-20 22:48:19 +00:00

16 KiB

Raw Permalink Blame History

View Raw