feat(ai): provider factories, per-provider catalogs, createProvider (phase 3)
Auth helpers in src/auth/helpers.ts: envApiKeyAuth() (stored key wins, then env vars in order, with secret-prompt login) and lazyOAuth() (flow loads on first use through bundler-opaque dynamic imports in utils/oauth/load.ts; the OAuthAuth flow exports land in phase 4). There is no OAuth factory toggle: providers that support OAuth always attach it, advertising costs nothing until login/refresh runs. createProvider() in models.ts builds providers from parts: single API implementation or a map dispatched on model.api (mixed-API providers like opencode and github-copilot); unknown api yields a stream error. generate-models.ts now emits one providers/<id>.models.ts catalog per provider (35 files, biome-excluded like models.generated.ts) and models.generated.ts becomes a generated aggregator, so importing one provider factory pulls one catalog. Typed getModel globals unchanged. One factory per built-in provider under src/providers/: envApiKeyAuth for standard providers, OAuth for anthropic/openai-codex/github-copilot, ambient ApiKeyAuth for amazon-bedrock (AWS env/profile/IAM) and google-vertex (explicit key or ADC+project+location). providers/all.ts: builtinProviders(), builtinModels(), getBuiltin* re-exports. fauxProvider() factory returns a real Provider for tests; legacy registerFauxProvider() unchanged.
This commit is contained in:
Mario Zechner
@@ -0,0 +1,403 @@
|
||||
// This file is auto-generated by scripts/generate-models.ts
|
||||
// Do not edit manually - run 'npm run generate-models' to update
|
||||
|
||||
import type { Model } from "../types.ts";
|
||||
|
||||
export const HUGGINGFACE_MODELS = {
|
||||
"MiniMaxAI/MiniMax-M2.1": {
|
||||
id: "MiniMaxAI/MiniMax-M2.1",
|
||||
name: "MiniMax-M2.1",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 1.2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"MiniMaxAI/MiniMax-M2.5": {
|
||||
id: "MiniMaxAI/MiniMax-M2.5",
|
||||
name: "MiniMax-M2.5",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 1.2,
|
||||
cacheRead: 0.03,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"MiniMaxAI/MiniMax-M2.7": {
|
||||
id: "MiniMaxAI/MiniMax-M2.7",
|
||||
name: "MiniMax-M2.7",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 1.2,
|
||||
cacheRead: 0.06,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"Qwen/Qwen3-235B-A22B-Thinking-2507": {
|
||||
id: "Qwen/Qwen3-235B-A22B-Thinking-2507",
|
||||
name: "Qwen3-235B-A22B-Thinking-2507",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 3,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"Qwen/Qwen3-Coder-480B-A35B-Instruct": {
|
||||
id: "Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
||||
name: "Qwen3-Coder-480B-A35B-Instruct",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 2,
|
||||
output: 2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 66536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"Qwen/Qwen3-Coder-Next": {
|
||||
id: "Qwen/Qwen3-Coder-Next",
|
||||
name: "Qwen3-Coder-Next",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.2,
|
||||
output: 1.5,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"Qwen/Qwen3-Next-80B-A3B-Instruct": {
|
||||
id: "Qwen/Qwen3-Next-80B-A3B-Instruct",
|
||||
name: "Qwen3-Next-80B-A3B-Instruct",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.25,
|
||||
output: 1,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 66536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"Qwen/Qwen3-Next-80B-A3B-Thinking": {
|
||||
id: "Qwen/Qwen3-Next-80B-A3B-Thinking",
|
||||
name: "Qwen3-Next-80B-A3B-Thinking",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"Qwen/Qwen3.5-397B-A17B": {
|
||||
id: "Qwen/Qwen3.5-397B-A17B",
|
||||
name: "Qwen3.5-397B-A17B",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.6,
|
||||
output: 3.6,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"XiaomiMiMo/MiMo-V2-Flash": {
|
||||
id: "XiaomiMiMo/MiMo-V2-Flash",
|
||||
name: "MiMo-V2-Flash",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.1,
|
||||
output: 0.3,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"deepseek-ai/DeepSeek-R1-0528": {
|
||||
id: "deepseek-ai/DeepSeek-R1-0528",
|
||||
name: "DeepSeek-R1-0528",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 3,
|
||||
output: 5,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 163840,
|
||||
maxTokens: 163840,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"deepseek-ai/DeepSeek-V3.2": {
|
||||
id: "deepseek-ai/DeepSeek-V3.2",
|
||||
name: "DeepSeek-V3.2",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.28,
|
||||
output: 0.4,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 163840,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"deepseek-ai/DeepSeek-V4-Pro": {
|
||||
id: "deepseek-ai/DeepSeek-V4-Pro",
|
||||
name: "DeepSeek V4 Pro",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.435,
|
||||
output: 0.87,
|
||||
cacheRead: 0.003625,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 1048576,
|
||||
maxTokens: 393216,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"moonshotai/Kimi-K2-Instruct": {
|
||||
id: "moonshotai/Kimi-K2-Instruct",
|
||||
name: "Kimi-K2-Instruct",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1,
|
||||
output: 3,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"moonshotai/Kimi-K2-Instruct-0905": {
|
||||
id: "moonshotai/Kimi-K2-Instruct-0905",
|
||||
name: "Kimi-K2-Instruct-0905",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1,
|
||||
output: 3,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"moonshotai/Kimi-K2-Thinking": {
|
||||
id: "moonshotai/Kimi-K2-Thinking",
|
||||
name: "Kimi-K2-Thinking",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.6,
|
||||
output: 2.5,
|
||||
cacheRead: 0.15,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 262144,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"moonshotai/Kimi-K2.5": {
|
||||
id: "moonshotai/Kimi-K2.5",
|
||||
name: "Kimi-K2.5",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.6,
|
||||
output: 3,
|
||||
cacheRead: 0.1,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 262144,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"moonshotai/Kimi-K2.6": {
|
||||
id: "moonshotai/Kimi-K2.6",
|
||||
name: "Kimi-K2.6",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.95,
|
||||
output: 4,
|
||||
cacheRead: 0.16,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 262144,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"zai-org/GLM-4.7": {
|
||||
id: "zai-org/GLM-4.7",
|
||||
name: "GLM-4.7",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.6,
|
||||
output: 2.2,
|
||||
cacheRead: 0.11,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"zai-org/GLM-4.7-Flash": {
|
||||
id: "zai-org/GLM-4.7-Flash",
|
||||
name: "GLM-4.7-Flash",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0,
|
||||
output: 0,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"zai-org/GLM-5": {
|
||||
id: "zai-org/GLM-5",
|
||||
name: "GLM-5",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1,
|
||||
output: 3.2,
|
||||
cacheRead: 0.2,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 202752,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"zai-org/GLM-5.1": {
|
||||
id: "zai-org/GLM-5.1",
|
||||
name: "GLM-5.1",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1,
|
||||
output: 3.2,
|
||||
cacheRead: 0.2,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 202752,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
} as const;
|
||||
Reference in New Issue
Block a user