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

@@ -5,11 +5,26 @@
"id": "mistral-medium-3.5",
"displayName": "Mistral Medium 3.5",
"family": "mistral-medium",
"match": { "exact": ["mistral-medium-3.5"], "patterns": ["mistral-medium-3.5*"] },
"match": {
"exact": [
"mistral-medium-3.5"
],
"patterns": [
"mistral-medium-3.5*"
]
},
"spec": {
"contextWindow": 262144,
"capabilities": ["chat", "reasoning", "code", "vision", "tool_use"],
"serviceType": ["chat"],
"capabilities": [
"chat",
"reasoning",
"code",
"vision",
"tool_use"
],
"serviceType": [
"chat"
],
"defaultTemperature": 1,
"supportsReasoning": true,
"description": "Mistral Medium 3.5128B 指令模型"
@@ -19,12 +34,25 @@
"id": "mistral-large-latest",
"displayName": "Mistral Large",
"family": "mistral-large",
"match": { "patterns": ["mistral-large*"] },
"match": {
"patterns": [
"mistral-large*"
]
},
"spec": {
"contextWindow": 256000,
"maxOutputTokens": 262144,
"capabilities": ["chat", "reasoning", "code", "vision", "tool_use", "long_context"],
"serviceType": ["chat"],
"capabilities": [
"chat",
"reasoning",
"code",
"vision",
"tool_use",
"long_context"
],
"serviceType": [
"chat"
],
"defaultTemperature": 0.7
}
},
@@ -32,12 +60,25 @@
"id": "mistral-small-latest",
"displayName": "Mistral Small",
"family": "mistral-small",
"match": { "patterns": ["mistral-small*"] },
"match": {
"patterns": [
"mistral-small*"
]
},
"spec": {
"contextWindow": 128000,
"maxOutputTokens": 8192,
"capabilities": ["chat", "code", "vision", "reasoning", "fast", "tool_use"],
"serviceType": ["fast"],
"capabilities": [
"chat",
"code",
"vision",
"reasoning",
"fast",
"tool_use"
],
"serviceType": [
"fast"
],
"defaultTemperature": 0.7
}
},
@@ -45,12 +86,21 @@
"id": "codestral-latest",
"displayName": "Codestral",
"family": "codestral",
"match": { "patterns": ["codestral*"] },
"match": {
"patterns": [
"codestral*"
]
},
"spec": {
"contextWindow": 128000,
"maxOutputTokens": 32768,
"capabilities": ["code", "fill_in_the_middle"],
"serviceType": ["chat"],
"capabilities": [
"code",
"fill_in_the_middle"
],
"serviceType": [
"chat"
],
"defaultTemperature": 0.7
}
}