ton/pi_harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(ai): provider factories, per-provider catalogs, createProvider (phase 3)

Browse Source 
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
2026-06-10 20:33:20 +02:00
parent afc2bd370e
commit fec0c3d12f
83 changed files with 18409 additions and 17094 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/ai/src/providers/nvidia.models.ts
+387
View File
@@ -0,0 +1,387 @@
// 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 NVIDIA_MODELS = {
"meta/llama-3.1-70b-instruct": {
id: "meta/llama-3.1-70b-instruct",
name: "Llama 3.1 70b Instruct",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"meta/llama-3.1-8b-instruct": {
id: "meta/llama-3.1-8b-instruct",
name: "Llama 3.1 8B Instruct",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 16000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"meta/llama-3.2-11b-vision-instruct": {
id: "meta/llama-3.2-11b-vision-instruct",
name: "Llama 3.2 11b Vision Instruct",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"meta/llama-3.2-90b-vision-instruct": {
id: "meta/llama-3.2-90b-vision-instruct",
name: "Llama-3.2-90B-Vision-Instruct",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 8192,
} satisfies Model<"openai-completions">,
"meta/llama-3.3-70b-instruct": {
id: "meta/llama-3.3-70b-instruct",
name: "Llama 3.3 70b Instruct",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"mistralai/mistral-large-3-675b-instruct-2512": {
id: "mistralai/mistral-large-3-675b-instruct-2512",
name: "Mistral Large 3 675B Instruct 2512",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"mistralai/mistral-small-4-119b-2603": {
id: "mistralai/mistral-small-4-119b-2603",
name: "mistral-small-4-119b-2603",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 8192,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2.6": {
id: "moonshotai/kimi-k2.6",
name: "Kimi K2.6",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-nano-30b-a3b": {
id: "nvidia/nemotron-3-nano-30b-a3b",
name: "nemotron-3-nano-30b-a3b",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
name: "Nemotron 3 Nano Omni",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-super-120b-a12b": {
id: "nvidia/nemotron-3-super-120b-a12b",
name: "Nemotron 3 Super",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
input: 0.2,
output: 0.8,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-ultra-550b-a55b": {
id: "nvidia/nemotron-3-ultra-550b-a55b",
name: "Nemotron 3 Ultra 550B A55B",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
input: 0.5,
output: 2.5,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"nvidia/nvidia-nemotron-nano-9b-v2": {
id: "nvidia/nvidia-nemotron-nano-9b-v2",
name: "nvidia-nemotron-nano-9b-v2",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"openai/gpt-oss-120b": {
id: "openai/gpt-oss-120b",
name: "GPT-OSS-120B",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 8192,
} satisfies Model<"openai-completions">,
"openai/gpt-oss-20b": {
id: "openai/gpt-oss-20b",
name: "GPT OSS 20B",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 32768,
} 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: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 66536,
} satisfies Model<"openai-completions">,
"qwen/qwen3.5-122b-a10b": {
id: "qwen/qwen3.5-122b-a10b",
name: "Qwen3.5 122B-A10B",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"stepfun-ai/step-3.5-flash": {
id: "stepfun-ai/step-3.5-flash",
name: "Step 3.5 Flash",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"stepfun-ai/step-3.7-flash": {
id: "stepfun-ai/step-3.7-flash",
name: "Step 3.7 Flash",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"z-ai/glm-5.1": {
id: "z-ai/glm-5.1",
name: "GLM-5.1",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
} as const;