Evan
85db9c8d78
feat(providers): add supports_thinking to thinking-capable models ( #53 )
...
* feat(providers): add supports_thinking field to thinking-capable models
Mark models that support extended thinking / reasoning with
supports_thinking = true so the dashboard can conditionally show
thinking toggles.
Providers updated: anthropic (8), codex-cli (7), gemini (6),
openai (3), qwen (2), deepseek (1). Schema updated accordingly.
* feat(providers): add supports_thinking to remaining thinking-capable models
Cover 19 additional providers: alibaba-coding-plan, allenai, arcee-ai,
fireworks, gemini-cli, groq, liquid, nvidia-nim, ollama, openai (codex),
openrouter, perplexity, qwen-code, replicate, sambanova, tngtech,
venice, vertex-ai, xai.
Total: 62 models across 24 providers now have supports_thinking = true.
* feat(providers): add supports_thinking to chutes, huggingface, together
Missed in prior commits: DeepSeek-R1 on chutes/huggingface/together,
Qwen3-235B on chutes. Total now 66 models across 27 providers.
* feat(providers): add supports_thinking to bedrock, claude-code, aider, moonshot, stepfun
- bedrock: all 5 Claude models
- claude-code: all 3 models (opus/sonnet/haiku wrappers)
- aider: aider/sonnet (Claude-backed)
- moonshot: kimi-k2.5 (reasoning mode)
- stepfun: step-1o-turbo-vision (reasoning model)
Total: 77 models across 32 providers.
* feat(providers): add supports_thinking to alibaba kimi-k2.5, openrouter claude-sonnet-4
2026-04-15 00:46:51 +09:00
Evan
2fa48bfdcb
fix: clean up OpenRouter-generated provider configs ( #37 )
...
- Merge unique models from duplicate providers into their hand-written
counterparts and remove the duplicates:
- alibaba (tongyi-deepresearch) → qwen
- amazon (nova-2-lite, nova-micro, nova-premier) → bedrock
- bytedance (ui-tars) → volcengine
- nvidia (nemotron-3-nano, nemotron-3-super, etc.) → nvidia-nim
- rekaai (reka-flash-3) → reka
- Set correct official API base_url for providers with public APIs:
arcee-ai, inception, morph, reka, upstage
- Set key_required=false for 20 providers only accessible through
hosting platforms (no public API)
- Update sync-pricing.py with SKIP_DUPLICATES, PROVIDER_API mapping,
and default key_required=false for future auto-generated providers
2026-04-02 23:30:56 +08:00
Evan
a00e813bdf
feat: add 22 mainstream models to nvidia-nim provider catalog ( #26 )
...
Add model entries for the most popular models available on NVIDIA NIM:
- NVIDIA: Nemotron Ultra 253B, Super 49B, 70B, Mini 4B
- Meta: Llama 4 Maverick/Scout, Llama 3.3 70B, 3.1 405B/8B, 3.2 Vision
- Mistral: Large 3 675B, Small 3.1 24B, Mixtral 8x22B
- DeepSeek: V3.2, R1 Distill 32B
- Qwen: 3.5 397B, 2.5 Coder 32B, QWQ 32B
- Google: Gemma 3 27B
- Microsoft: Phi-4 Multimodal, Phi-4 Mini
Refs librefang/librefang#1621
2026-03-25 23:36:00 +09:00
Evan Hu and Claude Opus 4.6
3aa662bd6d
feat: add Z.AI chat models + 5 new providers ( #3 )
...
* feat: add Z.AI chat models (GLM-5, GLM-4.7)
Sync with librefang/librefang#409 — add the two Z.AI chat models
to the standalone model catalog.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
* feat: add 5 new providers (Stepfun, SiliconFlow, Baichuan, NVIDIA NIM, Writer)
- Stepfun (阶跃星辰): step-3.5-flash, step-3, step-2-mini, step-1o-turbo-vision
- SiliconFlow (硅基流动): inference platform, models discovered at runtime
- Baichuan (百川): Baichuan-4, Baichuan-3 Turbo 128K
- NVIDIA NIM: inference platform, models discovered at runtime
- Writer: Palmyra X5, X4, Med, Fin
- Add global aliases for stepfun, baichuan, writer
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com >
2026-03-16 18:07:07 +09:00
Evan