refactor: consolidate smart routing into model specs (#75)

This commit is contained in:
2026-08-10 19:13:08 +08:00
committed by GitHub
parent ed0aeccf29
commit ad8c515938
32 changed files with 3907 additions and 2021 deletions

View File

@@ -5,12 +5,31 @@
"id": "gemini-3.5-flash",
"displayName": "Gemini 3.5 Flash",
"family": "gemini-3.5",
"match": { "exact": ["gemini-3.5-flash"], "patterns": ["gemini-3.5-flash*"] },
"match": {
"exact": [
"gemini-3.5-flash"
],
"patterns": [
"gemini-3.5-flash*"
]
},
"spec": {
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"capabilities": ["chat", "reasoning", "code", "vision", "video_understanding", "audio_understanding", "ultra_long_context", "tool_use", "fast"],
"serviceType": ["chat"],
"capabilities": [
"chat",
"reasoning",
"code",
"vision",
"video_understanding",
"audio_understanding",
"ultra_long_context",
"tool_use",
"fast"
],
"serviceType": [
"chat"
],
"defaultTemperature": 1,
"supportsReasoning": true,
"description": "Google Gemini 3.5 Flash全模态高性价比模型100 万上下文"
@@ -20,12 +39,25 @@
"id": "gemini-3.1-flash-image",
"displayName": "Gemini 3.1 Flash Image (Nano Banana 2)",
"family": "gemini-3.1",
"match": { "exact": ["gemini-3.1-flash-image"], "patterns": ["gemini-3.1-flash-image*"] },
"match": {
"exact": [
"gemini-3.1-flash-image"
],
"patterns": [
"gemini-3.1-flash-image*"
]
},
"spec": {
"contextWindow": 131072,
"maxOutputTokens": 32768,
"capabilities": ["image_generation", "image_editing", "text_rendering"],
"serviceType": ["image_gen"],
"capabilities": [
"image_generation",
"image_editing",
"text_rendering"
],
"serviceType": [
"image_gen"
],
"description": "Google Nano Banana 2最新文生图与编辑模型"
}
},
@@ -36,8 +68,17 @@
"spec": {
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"capabilities": ["chat", "reasoning", "code", "vision", "ultra_long_context", "tool_use"],
"serviceType": ["chat"],
"capabilities": [
"chat",
"reasoning",
"code",
"vision",
"ultra_long_context",
"tool_use"
],
"serviceType": [
"chat"
],
"defaultTemperature": 1,
"supportsReasoning": true
}
@@ -49,8 +90,18 @@
"spec": {
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"capabilities": ["chat", "reasoning", "code", "vision", "ultra_long_context", "tool_use", "fast"],
"serviceType": ["chat"],
"capabilities": [
"chat",
"reasoning",
"code",
"vision",
"ultra_long_context",
"tool_use",
"fast"
],
"serviceType": [
"chat"
],
"defaultTemperature": 1,
"supportsReasoning": true
}
@@ -59,12 +110,25 @@
"id": "gemini-2.5-pro",
"displayName": "Gemini 2.5 Pro",
"family": "gemini-2.5",
"match": { "patterns": ["gemini-2.5-pro*"] },
"match": {
"patterns": [
"gemini-2.5-pro*"
]
},
"spec": {
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"capabilities": ["chat", "reasoning", "code", "vision", "ultra_long_context", "tool_use"],
"serviceType": ["chat"],
"capabilities": [
"chat",
"reasoning",
"code",
"vision",
"ultra_long_context",
"tool_use"
],
"serviceType": [
"chat"
],
"defaultTemperature": 1,
"supportsReasoning": true
}
@@ -73,12 +137,26 @@
"id": "gemini-2.5-flash",
"displayName": "Gemini 2.5 Flash",
"family": "gemini-2.5",
"match": { "patterns": ["gemini-2.5-flash*"] },
"match": {
"patterns": [
"gemini-2.5-flash*"
]
},
"spec": {
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"capabilities": ["chat", "reasoning", "code", "vision", "ultra_long_context", "tool_use", "fast"],
"serviceType": ["chat"],
"capabilities": [
"chat",
"reasoning",
"code",
"vision",
"ultra_long_context",
"tool_use",
"fast"
],
"serviceType": [
"chat"
],
"defaultTemperature": 1,
"supportsReasoning": true
}
@@ -87,12 +165,29 @@
"id": "gemini-3.1-flash-lite-preview",
"displayName": "Gemini 3.1 Flash-Lite Preview",
"family": "gemini-3.1",
"match": { "exact": ["gemini-3.1-flash-lite-preview"], "patterns": ["gemini-3.1-flash-lite*"] },
"match": {
"exact": [
"gemini-3.1-flash-lite-preview"
],
"patterns": [
"gemini-3.1-flash-lite*"
]
},
"spec": {
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"capabilities": ["chat", "reasoning", "code", "vision", "ultra_long_context", "tool_use", "fast"],
"serviceType": ["fast"],
"capabilities": [
"chat",
"reasoning",
"code",
"vision",
"ultra_long_context",
"tool_use",
"fast"
],
"serviceType": [
"fast"
],
"defaultTemperature": 1,
"description": "Google Gemini 3.1 Flash-Lite Preview低成本高吞吐多模态模型"
}
@@ -101,11 +196,20 @@
"id": "text-embedding-005",
"displayName": "Text Embedding 005",
"family": "text-embedding",
"match": { "exact": ["text-embedding-005"] },
"match": {
"exact": [
"text-embedding-005"
]
},
"spec": {
"contextWindow": 2048,
"capabilities": ["text_embedding", "semantic_search"],
"serviceType": ["embedding"],
"capabilities": [
"text_embedding",
"semantic_search"
],
"serviceType": [
"embedding"
],
"description": "Google 文本嵌入模型768 维度"
}
}