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 +1,241 @@
|
||||
// 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 FIREWORKS_MODELS = {
|
||||
"accounts/fireworks/models/deepseek-v4-flash": {
|
||||
id: "accounts/fireworks/models/deepseek-v4-flash",
|
||||
name: "DeepSeek V4 Flash",
|
||||
api: "anthropic-messages",
|
||||
provider: "fireworks",
|
||||
baseUrl: "https://api.fireworks.ai/inference",
|
||||
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.14,
|
||||
output: 0.28,
|
||||
cacheRead: 0.03,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 1000000,
|
||||
maxTokens: 384000,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"accounts/fireworks/models/deepseek-v4-pro": {
|
||||
id: "accounts/fireworks/models/deepseek-v4-pro",
|
||||
name: "DeepSeek V4 Pro",
|
||||
api: "anthropic-messages",
|
||||
provider: "fireworks",
|
||||
baseUrl: "https://api.fireworks.ai/inference",
|
||||
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1.74,
|
||||
output: 3.48,
|
||||
cacheRead: 0.145,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 1000000,
|
||||
maxTokens: 384000,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"accounts/fireworks/models/glm-5p1": {
|
||||
id: "accounts/fireworks/models/glm-5p1",
|
||||
name: "GLM 5.1",
|
||||
api: "anthropic-messages",
|
||||
provider: "fireworks",
|
||||
baseUrl: "https://api.fireworks.ai/inference",
|
||||
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1.4,
|
||||
output: 4.4,
|
||||
cacheRead: 0.26,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 202800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"accounts/fireworks/models/gpt-oss-120b": {
|
||||
id: "accounts/fireworks/models/gpt-oss-120b",
|
||||
name: "GPT OSS 120B",
|
||||
api: "anthropic-messages",
|
||||
provider: "fireworks",
|
||||
baseUrl: "https://api.fireworks.ai/inference",
|
||||
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.15,
|
||||
output: 0.6,
|
||||
cacheRead: 0.015,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"accounts/fireworks/models/gpt-oss-20b": {
|
||||
id: "accounts/fireworks/models/gpt-oss-20b",
|
||||
name: "GPT OSS 20B",
|
||||
api: "anthropic-messages",
|
||||
provider: "fireworks",
|
||||
baseUrl: "https://api.fireworks.ai/inference",
|
||||
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.07,
|
||||
output: 0.3,
|
||||
cacheRead: 0.035,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"accounts/fireworks/models/kimi-k2p5": {
|
||||
id: "accounts/fireworks/models/kimi-k2p5",
|
||||
name: "Kimi K2.5",
|
||||
api: "anthropic-messages",
|
||||
provider: "fireworks",
|
||||
baseUrl: "https://api.fireworks.ai/inference",
|
||||
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.6,
|
||||
output: 3,
|
||||
cacheRead: 0.1,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 256000,
|
||||
maxTokens: 256000,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"accounts/fireworks/models/kimi-k2p6": {
|
||||
id: "accounts/fireworks/models/kimi-k2p6",
|
||||
name: "Kimi K2.6",
|
||||
api: "anthropic-messages",
|
||||
provider: "fireworks",
|
||||
baseUrl: "https://api.fireworks.ai/inference",
|
||||
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.95,
|
||||
output: 4,
|
||||
cacheRead: 0.16,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262000,
|
||||
maxTokens: 262000,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"accounts/fireworks/models/minimax-m2p5": {
|
||||
id: "accounts/fireworks/models/minimax-m2p5",
|
||||
name: "MiniMax-M2.5",
|
||||
api: "anthropic-messages",
|
||||
provider: "fireworks",
|
||||
baseUrl: "https://api.fireworks.ai/inference",
|
||||
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 1.2,
|
||||
cacheRead: 0.03,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 196608,
|
||||
maxTokens: 196608,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"accounts/fireworks/models/minimax-m2p7": {
|
||||
id: "accounts/fireworks/models/minimax-m2p7",
|
||||
name: "MiniMax-M2.7",
|
||||
api: "anthropic-messages",
|
||||
provider: "fireworks",
|
||||
baseUrl: "https://api.fireworks.ai/inference",
|
||||
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 1.2,
|
||||
cacheRead: 0.06,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 196608,
|
||||
maxTokens: 196608,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"accounts/fireworks/models/qwen3p6-plus": {
|
||||
id: "accounts/fireworks/models/qwen3p6-plus",
|
||||
name: "Qwen 3.6 Plus",
|
||||
api: "anthropic-messages",
|
||||
provider: "fireworks",
|
||||
baseUrl: "https://api.fireworks.ai/inference",
|
||||
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.5,
|
||||
output: 3,
|
||||
cacheRead: 0.1,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"accounts/fireworks/routers/glm-5p1-fast": {
|
||||
id: "accounts/fireworks/routers/glm-5p1-fast",
|
||||
name: "GLM 5.1 Fast",
|
||||
api: "anthropic-messages",
|
||||
provider: "fireworks",
|
||||
baseUrl: "https://api.fireworks.ai/inference",
|
||||
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 2.8,
|
||||
output: 8.8,
|
||||
cacheRead: 0.52,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 202800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"accounts/fireworks/routers/kimi-k2p6-fast": {
|
||||
id: "accounts/fireworks/routers/kimi-k2p6-fast",
|
||||
name: "Kimi K2.6 Fast",
|
||||
api: "anthropic-messages",
|
||||
provider: "fireworks",
|
||||
baseUrl: "https://api.fireworks.ai/inference",
|
||||
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 2,
|
||||
output: 8,
|
||||
cacheRead: 0.3,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262000,
|
||||
maxTokens: 262000,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"accounts/fireworks/routers/kimi-k2p6-turbo": {
|
||||
id: "accounts/fireworks/routers/kimi-k2p6-turbo",
|
||||
name: "Kimi K2.6 Turbo",
|
||||
api: "anthropic-messages",
|
||||
provider: "fireworks",
|
||||
baseUrl: "https://api.fireworks.ai/inference",
|
||||
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 2,
|
||||
output: 8,
|
||||
cacheRead: 0.3,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262000,
|
||||
maxTokens: 262000,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
} as const;
|
||||
Reference in New Issue
Block a user