Switch AI primary to qwen3.6:35b and raise timeout #9
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
gemma4:26b has been removed from fox, so the configured primary (AI_MODEL default gemma4:26b) now errors and every summary falls back to cube. Switch the primary to qwen3.6:35b, which produced richer, more accurate Norwegian summaries in a 4-article comparison.
qwen3.6:35b is a 35B reasoning model and is ~2.5x slower than gemma4 — it exceeded the 60s OpenAI client timeout on 2 of 4 test articles (up to 79s). So the switch must also raise the OpenAI client timeout (to ~120s); otherwise long articles would time out mid-generation and fall back to cube, paying the latency without getting qwen's output. The app is an async background summarizer, so the higher latency is acceptable.
Scope: change AIPrimary default model to qwen3.6:35b, raise OpenAIClient timeout, update tests/README. cube (qwen3:14b via OLLAMA_URL) stays as fallback.