ff9a07a37a
feat: Azure OpenAI / Azure AI Foundry support. Models should be defined in conf/azure_models.json (or a custom path). See .env.example for environment variables or see readme. https://github.com/BeehiveInnovations/zen-mcp-server/issues/265 feat: OpenRouter / Custom Models / Azure can separately also use custom config paths now (see .env.example ) refactor: Model registry class made abstract, OpenRouter / Custom Provider / Azure OpenAI now subclass these refactor: breaking change: `is_custom` property has been removed from model_capabilities.py (and thus custom_models.json) given each models are now read from separate configuration files
42 lines
2.2 KiB
JSON
42 lines
2.2 KiB
JSON
{
|
|
"_README": {
|
|
"description": "Model metadata for local/self-hosted OpenAI-compatible endpoints (Custom provider).",
|
|
"documentation": "https://github.com/BeehiveInnovations/zen-mcp-server/blob/main/docs/custom_models.md",
|
|
"usage": "Each entry will be advertised by the Custom provider. Aliases are case-insensitive.",
|
|
"field_notes": "Matches providers/shared/model_capabilities.py.",
|
|
"field_descriptions": {
|
|
"model_name": "The model identifier e.g., 'llama3.2'",
|
|
"aliases": "Array of short names users can type instead of the full model name",
|
|
"context_window": "Total number of tokens the model can process (input + output combined)",
|
|
"max_output_tokens": "Maximum number of tokens the model can generate in a single response",
|
|
"supports_extended_thinking": "Whether the model supports extended reasoning tokens",
|
|
"supports_json_mode": "Whether the model can guarantee valid JSON output",
|
|
"supports_function_calling": "Whether the model supports function/tool calling",
|
|
"supports_images": "Whether the model can process images/visual input",
|
|
"max_image_size_mb": "Maximum total size in MB for all images combined (capped at 40MB max for custom models)",
|
|
"supports_temperature": "Whether the model accepts temperature parameter in API calls (set to false for O3/O4 reasoning models)",
|
|
"temperature_constraint": "Type of temperature constraint: 'fixed' (fixed value), 'range' (continuous range), 'discrete' (specific values), or omit for default range",
|
|
"description": "Human-readable description of the model",
|
|
"intelligence_score": "1-20 human rating used as the primary signal for auto-mode model ordering"
|
|
}
|
|
},
|
|
"models": [
|
|
{
|
|
"model_name": "llama3.2",
|
|
"aliases": [
|
|
"local-llama",
|
|
"ollama-llama"
|
|
],
|
|
"context_window": 128000,
|
|
"max_output_tokens": 64000,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": false,
|
|
"supports_function_calling": false,
|
|
"supports_images": false,
|
|
"max_image_size_mb": 0.0,
|
|
"description": "Local Llama 3.2 model via custom endpoint (Ollama/vLLM) - 128K context window (text-only)",
|
|
"intelligence_score": 6
|
|
}
|
|
]
|
|
}
|