Evan
65cb852632
feat(openai): add GPT-5.5 and GPT-5.5 Pro ( #70 )
...
Source: https://openai.com/index/introducing-gpt-5-5/ (announcement 2026-04-23)
Adds 4 new model entries across 3 provider files:
- providers/openai.toml:
gpt-5.5 — 1M context, $5/$30 per 1M tokens (input/output)
gpt-5.5-pro — 1M context, $30/$180 per 1M tokens
- providers/codex-cli.toml:
codex-cli/gpt-5.5 — 400K context (Codex subscription limit),
$0/$0 (covered by subscription)
- providers/chatgpt.toml:
gpt-5.5-codex — 400K context, session-auth (subscription)
Notes:
- API availability announced as 'very soon'; pricing confirmed in the
announcement. tools/vision/streaming flags match GPT-5.4 family.
- max_output_tokens retained at 128000 (openai/codex-cli) and 65536
(chatgpt) — matches sibling 5.4 entries; announcement does not
specify a new output cap.
- Header comment in openai.toml updated (15 → 17 models).
2026-04-25 00:08:46 +09:00
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
2f4f94b45b
fix(codex-cli): refresh model list to match upstream ( #2347 ) ( #50 )
...
The prior entries (o4-mini, o3, gpt-4.1) no longer appear in
upstream openai/codex's codex-rs/models-manager/models.json and the
Codex CLI actively migrates users away from the old gpt-5 /
gpt-5-codex slugs via tui/src/model_migration.rs.
Replace with the currently-visible ("visibility": "list") slugs:
- gpt-5.4
- gpt-5.3-codex
- gpt-5.2
- gpt-5.2-codex
- gpt-5.1-codex-max
- gpt-5.1-codex-mini
All six share a 272k context window per upstream models.json.
Marking supports_tools / supports_vision / supports_streaming = true
to match the gpt-5-family capability envelope.
Closes librefang/librefang#2347
2026-04-14 19:40:56 +09:00
Evan
078218c70f
feat: add Gemini CLI, Codex CLI, and Aider provider catalogs ( #7 )
...
- gemini-cli: Google Gemini CLI (gemini-2.5-pro, gemini-2.5-flash)
- codex-cli: OpenAI Codex CLI (o4-mini, o3, gpt-4.1)
- aider: Aider AI coding assistant (sonnet, gpt-4o)
2026-03-21 07:14:18 +09:00
Evan