Evan
4f8dd2404d
* feat(providers): expand ollama model catalog with thinking-capable models Add commonly used local models with accurate capability flags: - gemma4, gemma3: supports_thinking, supports_vision - deepseek-r1: supports_thinking (fix missing flag) - deepseek-v3: supports_tools - qwen3, qwq: supports_thinking - llama4: supports_vision - llama3.3: supports_tools - phi4: supports_tools Previously only 6 models were listed and none had supports_thinking (except deepseek-r1), causing the dashboard to hide thinking toggles for models that actually support it. * chore(providers): major cleanup — remove defunct providers and old models Delete 21 defunct/obscure providers: aion-labs, arcee-ai, deepcogito, eleutherai, essentialai, ibm-granite, inception, inflection, kwaipilot, lemonade, liquid, morph, nex-agi, nousresearch, prime-intellect, reka, relace, switchpoint, tngtech, upstage, writer Clean up 10 major providers — keep only latest generation models: - anthropic: remove claude-3.5-sonnet (superseded by 4.x) - openai: remove gpt-4o/4-turbo/3.5/o1/o3-mini (superseded by gpt-5/4.1/o3/o4-mini) - gemini: remove 1.5-*/2.0-flash (superseded by 2.5/3.x) - deepseek: remove coder/chat-v3-0324 (superseded by r1/v3) - qwen: remove turbo/2.5-coder (superseded by qwen3) - groq: remove old llama/mixtral/gemma (keep latest only) - mistral: remove medium/nemo/pixtral-large (keep large/small/codestral) - xai: remove grok-2 (superseded by grok-3/4) - meta-llama: remove 3.x/guard (keep llama-4 + 3.3) - ollama: rewrite with current models (gemma4, qwen3, qwq, llama4, etc) Total: 90 → 48 models across major providers. All thinking-capable models now have supports_thinking = true. * chore: add pre-commit hook for automatic TOML formatting - .githooks/pre-commit: runs taplo fmt on staged .toml files - Makefile: add setup target + auto-configure hooks on first make - .gitignore: add .make-setup-done and .sync_marker
Providers
LLM provider and model metadata for LibreFang. Each provider file defines the provider's API configuration and all available models with pricing, context windows, and capability flags.
Structure
providers/
├── anthropic.toml
├── openai.toml
├── groq.toml
└── ... (46 providers, 220+ models)
Provider TOML Format
[provider]
id = "provider-id" # Unique identifier (lowercase, hyphenated)
display_name = "Provider Name"
api_key_env = "PROVIDER_API_KEY" # Env var for API key
base_url = "https://api.example.com"
key_required = true
[[models]]
id = "model-id" # Exact API model ID
display_name = "Model Name"
tier = "smart" # frontier | smart | balanced | fast | local
context_window = 128000
max_output_tokens = 16384
input_cost_per_m = 2.50 # USD per million input tokens
output_cost_per_m = 10.0 # USD per million output tokens
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["short-name"]
Tier Definitions
| Tier | Description | Examples |
|---|---|---|
frontier |
Most capable, cutting-edge | Claude Opus, GPT-4.1 |
smart |
Smart, cost-effective | Claude Sonnet, Gemini 2.5 Flash |
balanced |
Balanced speed/cost | GPT-4.1 Mini, Llama 3.3 70B |
fast |
Fastest, cheapest | GPT-4o Mini, Claude Haiku |
local |
Local models, zero cost | Ollama, vLLM, LM Studio |
Validation
python scripts/validate.py
Checks: required fields, valid tiers, non-negative costs, no duplicate model IDs.
Adding or Updating a Model
- Edit or create the provider file in
providers/ - Use exact API model IDs and verify pricing from official sources
- Run
python scripts/validate.py - Submit a PR
See CONTRIBUTING.md for the full guide and pricing source links.