arne/news
0
0
Fork 1
Code Issues Pull requests Projects Releases Packages Wiki Activity

Switch AI primary to qwen3.6:35b and raise timeout #10

Merged
arne merged 1 commit from orbit-9-qwen35-primary into main 2026-06-07 21:14:20 +02:00
Conversation 0 Commits 1 Files changed 5 +14 -12
arne commented 2026-06-07 21:14:18 +02:00
Owner
Copy link

gemma4:26b was removed from fox, so the configured primary (AI_MODEL default gemma4:26b) now errors and every summary falls back to cube. This switches the primary to qwen3.6:35b, which produced richer, more accurate Norwegian summaries than gemma4 in a 4-article comparison (concrete scores, names, and nuance gemma left out).

Why the timeout bump

qwen3.6:35b is a 35B reasoning model — ~2.5× slower than gemma4, and it exceeded the 60s OpenAI client timeout on 2 of 4 test articles (up to ~79s). Left at 60s, long articles would time out mid-generation and fall back to cube — paying qwen's latency without getting its output. The client timeout is raised to 120s. The app is an async background summarizer, so the higher latency is acceptable.

cube (qwen3:14b via OLLAMA_URL) stays as the per-request fallback.

Verification

Build + vet clean; AI/config tests pass. The 4 failing tests (snapshot/desk OIDC) are pre-existing on main, unchanged. qwen3.6:35b was validated live against fox during the comparison.

Closes #9

gemma4:26b was removed from fox, so the configured primary (`AI_MODEL` default `gemma4:26b`) now errors and every summary falls back to cube. This switches the primary to **qwen3.6:35b**, which produced richer, more accurate Norwegian summaries than gemma4 in a 4-article comparison (concrete scores, names, and nuance gemma left out). ## Why the timeout bump qwen3.6:35b is a 35B reasoning model — ~2.5× slower than gemma4, and it exceeded the 60s OpenAI client timeout on 2 of 4 test articles (up to ~79s). Left at 60s, long articles would time out mid-generation and fall back to cube — paying qwen's latency without getting its output. The client timeout is raised to 120s. The app is an async background summarizer, so the higher latency is acceptable. cube (qwen3:14b via `OLLAMA_URL`) stays as the per-request fallback. ## Verification Build + vet clean; AI/config tests pass. The 4 failing tests (snapshot/desk OIDC) are pre-existing on `main`, unchanged. qwen3.6:35b was validated live against fox during the comparison. Closes #9
gemma4:26b was removed from fox, so the configured primary errored and every
summary fell back to cube. Make qwen3.6:35b the primary — it produced richer,
more accurate Norwegian summaries in a 4-article comparison. Raise the OpenAI
client timeout 60s→120s because qwen3.6:35b is a reasoning model that can take
~80s on longer articles, which would otherwise time out and fall back.

cube (qwen3:14b via OLLAMA_URL) stays as the fallback.

Closes #9

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
arne merged commit b0fc41b31b into main 2026-06-07 21:14:20 +02:00
Sign in to join this conversation.
Reviewers
No reviewers
Labels
Clear labels
No items
No labels
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
arne/news!10
No description provided.