mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 08:03:15 +00:00
eb98ff4c30
* Add 10 Fireworks models to selectable set Surface additional Fireworks-served models in the profile editor so they can be chosen per-thread, per-profile, and as team defaults. Each entry carries its recommended efforts and image support; only MiniMax M3 is multimodal. Refs: #78 * Suppress reasoning_effort on non-reasoning models Instruct-only Fireworks ids (kimi-k2-instruct-0905, mistral-large-3-fp8, qwen3-30b-a3b-instruct-2507) don't reason, so sending reasoning_effort either 400s (unusable at default effort) or is a silent no-op. Add a per-model reasoning flag (default True) and omit the param entirely for ids marked non-reasoning. Refs: #78 * Gate out 7 undeployed Fireworks models Account serverless probe returned 404 for 7 of the 10 proposed ids, so only minimax-m3, gpt-oss-120b, and deepseek-v4-flash are callable. Keep those 3 and drop the rest. All 3 survivors are reasoning-capable, so the per-model reasoning-effort suppression added earlier is no longer needed and is reverted. Refs: #78 --------- Co-authored-by: amoussa1229 <166072409+amoussa1229@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| dashboard | ||
| integrations | ||
| middleware | ||
| skills | ||
| tools | ||
| utils | ||
| analyzer.py | ||
| chat.py | ||
| ci_autofix.py | ||
| ci_monitor.py | ||
| encryption.py | ||
| prompt.py | ||
| review_style_collector.py | ||
| review_style_guidance.py | ||
| reviewer.py | ||
| reviewer_diff.py | ||
| reviewer_eval_store.py | ||
| reviewer_findings.py | ||
| reviewer_groups.py | ||
| reviewer_publish.py | ||
| reviewer_reconcile.py | ||
| scheduler.py | ||
| server.py | ||
| webapp.py | ||