Dark-Alex-17/coyote
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add model catalog source adapters and merge engine

Browse Source
This commit is contained in:
Dark-Alex-17 committed 2026-09-03 11:17:58 -06:00
1 parent 078e5c757d
commit 2d7a759fc0
3 files changed
+2100 -6
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/client/catalog.rs
+1105 -6
View File
File diff suppressed because it is too large. Load diff
src/client/testdata/modelsdev_fixture.json
Vendored
+457
View File
@@ -0,0 +1,457 @@
{
"openai": {
"id": "openai",
"env": [
"OPENAI_API_KEY"
],
"npm": "@ai-sdk/openai",
"name": "OpenAI",
"doc": "https://platform.openai.com/docs/models",
"models": {
"gpt-5.6": {
"id": "gpt-5.6",
"name": "GPT-5.6",
"description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
"family": "gpt-sol",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"temperature": false,
"knowledge": "2026-02-16",
"release_date": "2026-07-09",
"last_updated": "2026-07-09",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"open_weights": false,
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"experimental": {
"modes": {
"fast": {
"cost": {
"input": 8,
"output": 40,
"cache_read": 0.8,
"cache_write": 10
},
"provider": {
"body": {
"service_tier": "priority"
}
}
},
"pro": {
"provider": {
"body": {
"reasoning": {
"mode": "pro"
}
}
}
}
}
},
"cost": {
"input": 4,
"output": 20,
"cache_read": 0.4,
"cache_write": 5,
"tiers": [
{
"input": 8,
"output": 30,
"cache_read": 0.8,
"cache_write": 10,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 8,
"output": 30,
"cache_read": 0.8,
"cache_write": 10
}
}
},
"gpt-4.1": {
"id": "gpt-4.1",
"name": "GPT-4.1",
"description": "Long-lived GPT workhorse for coding, instruction following, and production apps",
"family": "gpt",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"temperature": true,
"knowledge": "2024-04",
"release_date": "2025-04-14",
"last_updated": "2025-04-14",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"open_weights": false,
"limit": {
"context": 1047576,
"output": 32768
},
"cost": {
"input": 2,
"output": 8,
"cache_read": 0.5
}
},
"gpt-4o": {
"id": "gpt-4o",
"name": "GPT-4o",
"description": "Omni-era GPT for multimodal chat, practical coding, and general assistants",
"family": "gpt",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"temperature": true,
"knowledge": "2023-09",
"release_date": "2024-05-13",
"last_updated": "2024-08-06",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"open_weights": false,
"limit": {
"context": 128000,
"output": 16384
},
"cost": {
"input": 2.5,
"output": 10,
"cache_read": 1.25
}
}
}
},
"anthropic": {
"id": "anthropic",
"env": [
"ANTHROPIC_API_KEY"
],
"npm": "@ai-sdk/anthropic",
"name": "Anthropic",
"doc": "https://docs.anthropic.com/en/docs/about-claude/models",
"models": {
"claude-sonnet-4-6": {
"id": "claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"description": "Claude workhorse for coding agents, careful analysis, and production cost control",
"family": "claude-sonnet",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"max"
]
},
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"temperature": true,
"knowledge": "2025-08-31",
"release_date": "2026-02-17",
"last_updated": "2026-03-13",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"open_weights": false,
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3.75
}
},
"claude-opus-4-6": {
"id": "claude-opus-4-6",
"name": "Claude Opus 4.6",
"description": "High-end Claude for difficult coding, planning, and slower expert reasoning",
"family": "claude-opus",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"max"
]
},
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"temperature": true,
"knowledge": "2025-05-31",
"release_date": "2026-02-04",
"last_updated": "2026-03-13",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"open_weights": false,
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
}
}
},
"xai": {
"id": "xai",
"env": [
"XAI_API_KEY"
],
"npm": "@ai-sdk/xai",
"name": "xAI",
"doc": "https://docs.x.ai/docs/models",
"models": {
"grok-4.6": {
"id": "grok-4.6",
"name": "Grok 4.6",
"description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
"family": "grok",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"temperature": true,
"knowledge": "2026-02-01",
"release_date": "2026-08-12",
"last_updated": "2026-08-12",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"open_weights": false,
"limit": {
"context": 500000,
"output": 500000
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.5,
"tiers": [
{
"input": 4,
"output": 12,
"cache_read": 1,
"tier": {
"type": "context",
"size": 200000
}
}
],
"context_over_200k": {
"input": 4,
"output": 12,
"cache_read": 1
}
}
},
"grok-4.5": {
"id": "grok-4.5",
"name": "Grok 4.5",
"description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk",
"family": "grok",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"temperature": true,
"release_date": "2026-07-08",
"last_updated": "2026-07-08",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"open_weights": false,
"limit": {
"context": 500000,
"output": 500000
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.3,
"tiers": [
{
"input": 4,
"output": 12,
"cache_read": 0.6,
"tier": {
"type": "context",
"size": 200000
}
}
],
"context_over_200k": {
"input": 4,
"output": 12,
"cache_read": 0.6
}
}
}
}
},
"alibaba": {
"id": "alibaba",
"env": [
"DASHSCOPE_API_KEY"
],
"npm": "@ai-sdk/openai-compatible",
"name": "Alibaba",
"doc": "https://www.alibabacloud.com/help/en/model-studio/models",
"models": {
"qwen-max": {
"id": "qwen-max",
"name": "Qwen Max",
"description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows",
"family": "qwen",
"attachment": false,
"reasoning": false,
"tool_call": true,
"temperature": true,
"knowledge": "2024-04",
"release_date": "2024-04-03",
"last_updated": "2025-01-25",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"open_weights": false,
"limit": {
"context": 32768,
"output": 8192
},
"cost": {
"input": 1.6,
"output": 6.4
}
}
}
}
}
src/client/testdata/openrouter_fixture.json
Vendored
+538
View File
@@ -0,0 +1,538 @@
{
"data": [
{
"id": "x-ai/grok-4.6",
"canonical_slug": "x-ai/grok-4.6-20260810",
"hugging_face_id": null,
"name": "SpaceXAI: Grok 4.6",
"created": 1786548957,
"description": "Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.",
"context_length": 500000,
"architecture": {
"modality": "text+image+file->text",
"input_modalities": [
"text",
"image",
"file"
],
"output_modalities": [
"text"
],
"tokenizer": "Grok",
"instruct_type": null
},
"pricing": {
"prompt": "0.000002",
"completion": "0.000006",
"web_search": "0.005",
"input_cache_read": "0.0000005",
"overrides": [
{
"min_prompt_tokens": 200000,
"prompt": "0.000004",
"completion": "0.000012",
"input_cache_read": "0.000001"
}
]
},
"top_provider": {
"context_length": 500000,
"max_completion_tokens": 450000,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"include_reasoning",
"logprobs",
"max_tokens",
"reasoning",
"reasoning_effort",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
"top_logprobs",
"top_p"
],
"default_parameters": {},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/x-ai/grok-4.6-20260810/endpoints"
},
"reasoning": {
"mandatory": true,
"default_enabled": true,
"supported_efforts": [
"xhigh",
"high",
"medium",
"low"
],
"default_effort": "high"
}
},
{
"id": "qwen/qwen3.8-max",
"canonical_slug": "qwen/qwen3.8-max-20260803",
"hugging_face_id": null,
"name": "Qwen: Qwen3.8 Max",
"created": 1785731612,
"description": "Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding,...",
"context_length": 1000000,
"architecture": {
"modality": "text+image+video->text",
"input_modalities": [
"text",
"image",
"video"
],
"output_modalities": [
"text"
],
"tokenizer": "Qwen",
"instruct_type": null
},
"pricing": {
"prompt": "0.000002",
"completion": "0.000006",
"input_cache_read": "0.00000025",
"input_cache_write": "0.0000025"
},
"top_provider": {
"context_length": 1000000,
"max_completion_tokens": 131072,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
"logprobs",
"max_tokens",
"presence_penalty",
"reasoning",
"reasoning_effort",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
"top_logprobs",
"top_p"
],
"default_parameters": {},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/qwen/qwen3.8-max-20260803/endpoints"
},
"reasoning": {
"mandatory": true,
"default_enabled": true,
"supported_efforts": [
"xhigh",
"high",
"medium",
"low",
"minimal"
],
"default_effort": "xhigh"
}
},
{
"id": "x-ai/grok-4.5",
"canonical_slug": "x-ai/grok-4.5-20260708",
"hugging_face_id": null,
"name": "SpaceXAI: Grok 4.5",
"created": 1783523154,
"description": "Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.",
"context_length": 500000,
"architecture": {
"modality": "text+image+file->text",
"input_modalities": [
"text",
"image",
"file"
],
"output_modalities": [
"text"
],
"tokenizer": "Grok",
"instruct_type": null
},
"pricing": {
"prompt": "0.000002",
"completion": "0.000006",
"web_search": "0.005",
"input_cache_read": "0.0000003",
"overrides": [
{
"min_prompt_tokens": 200000,
"prompt": "0.000004",
"completion": "0.000012",
"input_cache_read": "0.0000006"
}
]
},
"top_provider": {
"context_length": 500000,
"max_completion_tokens": 450000,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"include_reasoning",
"logprobs",
"max_tokens",
"reasoning",
"reasoning_effort",
"response_format",
"seed",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_logprobs",
"top_p"
],
"default_parameters": {},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/x-ai/grok-4.5-20260708/endpoints"
},
"reasoning": {
"mandatory": true,
"default_enabled": true,
"supported_efforts": [
"high",
"medium",
"low"
],
"default_effort": "high"
}
},
{
"id": "anthropic/claude-sonnet-4.6",
"canonical_slug": "anthropic/claude-4.6-sonnet-20260217",
"hugging_face_id": "",
"name": "Anthropic: Claude Sonnet 4.6",
"created": 1771342990,
"description": "Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...",
"context_length": 1000000,
"architecture": {
"modality": "text+image+file->text",
"input_modalities": [
"text",
"image",
"file"
],
"output_modalities": [
"text"
],
"tokenizer": "Claude",
"instruct_type": null
},
"pricing": {
"prompt": "0.000003",
"completion": "0.000015",
"web_search": "0.01",
"input_cache_read": "0.0000003",
"input_cache_write": "0.00000375",
"input_cache_write_1h": "0.000006"
},
"top_provider": {
"context_length": 1000000,
"max_completion_tokens": 128000,
"is_moderated": true
},
"per_request_limits": null,
"supported_parameters": [
"include_reasoning",
"max_completion_tokens",
"max_tokens",
"reasoning",
"reasoning_effort",
"response_format",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
"top_p",
"verbosity"
],
"default_parameters": {},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/anthropic/claude-4.6-sonnet-20260217/endpoints"
},
"reasoning": {
"mandatory": false,
"supported_efforts": [
"max",
"high",
"medium",
"low"
],
"default_effort": "medium"
}
},
{
"id": "openrouter/free",
"canonical_slug": "openrouter/free",
"hugging_face_id": "",
"name": "Free Models Router",
"created": 1769917427,
"description": "The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...",
"context_length": 200000,
"architecture": {
"modality": "text+image->text",
"input_modalities": [
"text",
"image"
],
"output_modalities": [
"text"
],
"tokenizer": "Router",
"instruct_type": null
},
"pricing": {
"prompt": "0",
"completion": "0"
},
"top_provider": {
"context_length": null,
"max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
"logprobs",
"max_completion_tokens",
"max_tokens",
"min_p",
"presence_penalty",
"reasoning",
"reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
"top_logprobs",
"top_p"
],
"default_parameters": {
"temperature": null,
"top_p": null,
"frequency_penalty": null
},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/openrouter/free/endpoints"
}
},
{
"id": "openai/gpt-4.1",
"canonical_slug": "openai/gpt-4.1-2025-04-14",
"hugging_face_id": "",
"name": "OpenAI: GPT-4.1",
"created": 1744651385,
"description": "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...",
"context_length": 1047576,
"architecture": {
"modality": "text+image+file->text",
"input_modalities": [
"image",
"text",
"file"
],
"output_modalities": [
"text"
],
"tokenizer": "GPT",
"instruct_type": null
},
"pricing": {
"prompt": "0.000002",
"completion": "0.000008",
"web_search": "0.01",
"input_cache_read": "0.0000005"
},
"top_provider": {
"context_length": 1047576,
"max_completion_tokens": 32768,
"is_moderated": true
},
"per_request_limits": null,
"supported_parameters": [
"max_completion_tokens",
"max_tokens",
"response_format",
"seed",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_p"
],
"default_parameters": {},
"supported_voices": null,
"knowledge_cutoff": "2024-06-30",
"expiration_date": null,
"links": {
"details": "/api/v1/models/openai/gpt-4.1-2025-04-14/endpoints"
}
},
{
"id": "openai/gpt-4o",
"canonical_slug": "openai/gpt-4o",
"hugging_face_id": null,
"name": "OpenAI: GPT-4o",
"created": 1715558400,
"description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...",
"context_length": 128000,
"architecture": {
"modality": "text+image+file->text",
"input_modalities": [
"text",
"image",
"file"
],
"output_modalities": [
"text"
],
"tokenizer": "GPT",
"instruct_type": null
},
"pricing": {
"prompt": "0.0000025",
"completion": "0.00001",
"input_cache_read": "0.00000125"
},
"top_provider": {
"context_length": 128000,
"max_completion_tokens": 16384,
"is_moderated": true
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"logit_bias",
"logprobs",
"max_completion_tokens",
"max_tokens",
"prediction",
"presence_penalty",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_logprobs",
"top_p",
"web_search_options"
],
"default_parameters": {},
"supported_voices": null,
"knowledge_cutoff": "2023-10-31",
"expiration_date": null,
"links": {
"details": "/api/v1/models/openai/gpt-4o/endpoints"
}
},
{
"id": "openrouter/auto",
"canonical_slug": "openrouter/auto",
"hugging_face_id": null,
"name": "Auto Router",
"created": 1699401600,
"description": "The Auto Router automatically selects the best model for your prompt, powered by the wisdom of the market. It routes you based on what the OpenRouter community collectively spends on...",
"context_length": 2000000,
"architecture": {
"modality": "text+image+file+audio+video->text+image",
"input_modalities": [
"text",
"image",
"audio",
"file",
"video"
],
"output_modalities": [
"text",
"image"
],
"tokenizer": "Router",
"instruct_type": null
},
"pricing": {
"prompt": "-1",
"completion": "-1"
},
"top_provider": {
"context_length": null,
"max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
"logit_bias",
"logprobs",
"max_tokens",
"min_p",
"prediction",
"presence_penalty",
"reasoning",
"reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_a",
"top_k",
"top_logprobs",
"top_p",
"web_search_options"
],
"default_parameters": {},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/openrouter/auto/endpoints"
}
}
]
}