Manmohan Sharma 5bd773ef13 feat: double default and max generation budget ... Default inference_default_max_tokens 512->1024 in chat-api and in modal/serve.py default. Hard cap in modal raised 2048->4096. Fixes mid-sentence cutoffs on longer (esp. thinking-mode) answers. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>		2026-04-22 22:20:05 -07:00
..
auth	Merge pull request #26 from manmohan659/fix/missing-models	2026-04-16 16:50:22 -04:00
chat-api	feat: double default and max generation budget	2026-04-22 22:20:05 -07:00
frontend	feat(ui): cleaner input layout + sanitize model-output artifacts	2026-04-22 15:31:00 -07:00
inference	fix(inference): regenerate uv.lock after structlog/prometheus deps added	2026-04-16 12:49:05 -07:00