mirror of
https://github.com/openclaw/openclaw.git
synced 2026-06-25 04:19:30 +00:00
57e0bdaabe
Summary: - Add a shared live provider catalog runtime for SDK-backed providers. - Route OpenAI, xAI, OpenCode Go, Chutes, DeepInfra, Venice, NVIDIA, and Vercel AI Gateway live model discovery through the shared helper. - Remove duplicated provider-local live catalog caching and harden auth marker stripping, empty live-result retries, and OpenAI custom-base-url handling. Verification: - node scripts/run-vitest.mjs extensions/openai/openai-provider.test.ts src/plugin-sdk/provider-catalog-live-runtime.test.ts src/commands/models/list.source-plan.test.ts extensions/opencode-go/index.test.ts extensions/nvidia/provider-catalog.test.ts - pnpm plugin-sdk:api:check - pnpm lint --threads=8 - pnpm run lint:extensions:bundled - pnpm run test:extensions:package-boundary:compile - pnpm check:import-cycles - pnpm exec oxfmt --check extensions/openai/openai-provider.ts extensions/openai/openai-provider.test.ts - git diff --check origin/main...HEAD - autoreview clean: no accepted/actionable findings reported - AWS Crabbox focused remote proof: run_364680d1bff8 / cbx_2456fffafe01 - Earlier same-PR AWS Crabbox live proof: run_1f05ccab368e / cbx_7375c79fcf9b Known proof gap: - Final current-code true live-provider smoke was blocked by Crabbox secret hydration, documented in the PR proof comment.
591 lines
17 KiB
TypeScript
591 lines
17 KiB
TypeScript
/**
|
|
* Chutes model catalog, static model definitions, and dynamic model discovery.
|
|
*/
|
|
import {
|
|
clearLiveCatalogCacheForTests,
|
|
getCachedLiveProviderModelRows,
|
|
LiveModelCatalogHttpError,
|
|
} from "openclaw/plugin-sdk/provider-catalog-live-runtime";
|
|
import type { ModelDefinitionConfig } from "openclaw/plugin-sdk/provider-model-shared";
|
|
import { createSubsystemLogger } from "openclaw/plugin-sdk/runtime-env";
|
|
import { ssrfPolicyFromHttpBaseUrlAllowedHostname } from "openclaw/plugin-sdk/ssrf-runtime";
|
|
import {
|
|
asPositiveSafeInteger,
|
|
normalizeLowercaseStringOrEmpty,
|
|
normalizeOptionalString,
|
|
} from "openclaw/plugin-sdk/string-coerce-runtime";
|
|
import { isChutesModelDiscoveryTestEnvironment } from "./model-discovery-env.js";
|
|
|
|
const log = createSubsystemLogger("chutes-models");
|
|
|
|
/** Base URL for Chutes OpenAI-compatible inference. */
|
|
export const CHUTES_BASE_URL = "https://llm.chutes.ai/v1";
|
|
/** Default Chutes model id used for onboarding. */
|
|
export const CHUTES_DEFAULT_MODEL_ID = "zai-org/GLM-4.7-TEE";
|
|
/** Default Chutes model ref used for onboarding. */
|
|
export const CHUTES_DEFAULT_MODEL_REF = `chutes/${CHUTES_DEFAULT_MODEL_ID}`;
|
|
|
|
const CHUTES_DEFAULT_CONTEXT_WINDOW = 128000;
|
|
const CHUTES_DEFAULT_MAX_TOKENS = 4096;
|
|
|
|
/** Bundled fallback Chutes model catalog. */
|
|
export const CHUTES_MODEL_CATALOG: ModelDefinitionConfig[] = [
|
|
{
|
|
id: "Qwen/Qwen3-32B",
|
|
name: "Qwen/Qwen3-32B",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 40960,
|
|
maxTokens: 40960,
|
|
cost: { input: 0.08, output: 0.24, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "unsloth/Mistral-Nemo-Instruct-2407",
|
|
name: "unsloth/Mistral-Nemo-Instruct-2407",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
cost: { input: 0.02, output: 0.04, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "deepseek-ai/DeepSeek-V3-0324-TEE",
|
|
name: "deepseek-ai/DeepSeek-V3-0324-TEE",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 163840,
|
|
maxTokens: 65536,
|
|
cost: { input: 0.25, output: 1, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "Qwen/Qwen3-235B-A22B-Instruct-2507-TEE",
|
|
name: "Qwen/Qwen3-235B-A22B-Instruct-2507-TEE",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
cost: { input: 0.08, output: 0.55, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "openai/gpt-oss-120b-TEE",
|
|
name: "openai/gpt-oss-120b-TEE",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 131072,
|
|
maxTokens: 65536,
|
|
cost: { input: 0.05, output: 0.45, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "chutesai/Mistral-Small-3.1-24B-Instruct-2503",
|
|
name: "chutesai/Mistral-Small-3.1-24B-Instruct-2503",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
cost: { input: 0.03, output: 0.11, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "deepseek-ai/DeepSeek-V3.2-TEE",
|
|
name: "deepseek-ai/DeepSeek-V3.2-TEE",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 131072,
|
|
maxTokens: 65536,
|
|
cost: { input: 0.28, output: 0.42, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "zai-org/GLM-4.7-TEE",
|
|
name: "zai-org/GLM-4.7-TEE",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 202752,
|
|
maxTokens: 65535,
|
|
cost: { input: 0.4, output: 2, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "moonshotai/Kimi-K2.5-TEE",
|
|
name: "moonshotai/Kimi-K2.5-TEE",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
contextWindow: 262144,
|
|
maxTokens: 65535,
|
|
cost: { input: 0.45, output: 2.2, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "unsloth/gemma-3-27b-it",
|
|
name: "unsloth/gemma-3-27b-it",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
contextWindow: 128000,
|
|
maxTokens: 65536,
|
|
cost: { input: 0.04, output: 0.15, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "XiaomiMiMo/MiMo-V2-Flash-TEE",
|
|
name: "XiaomiMiMo/MiMo-V2-Flash-TEE",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
cost: { input: 0.09, output: 0.29, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "chutesai/Mistral-Small-3.2-24B-Instruct-2506",
|
|
name: "chutesai/Mistral-Small-3.2-24B-Instruct-2506",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
cost: { input: 0.06, output: 0.18, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "deepseek-ai/DeepSeek-R1-0528-TEE",
|
|
name: "deepseek-ai/DeepSeek-R1-0528-TEE",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 163840,
|
|
maxTokens: 65536,
|
|
cost: { input: 0.45, output: 2.15, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "zai-org/GLM-5-TEE",
|
|
name: "zai-org/GLM-5-TEE",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 202752,
|
|
maxTokens: 65535,
|
|
cost: { input: 0.95, output: 3.15, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "deepseek-ai/DeepSeek-V3.1-TEE",
|
|
name: "deepseek-ai/DeepSeek-V3.1-TEE",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 163840,
|
|
maxTokens: 65536,
|
|
cost: { input: 0.2, output: 0.8, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "deepseek-ai/DeepSeek-V3.1-Terminus-TEE",
|
|
name: "deepseek-ai/DeepSeek-V3.1-Terminus-TEE",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 163840,
|
|
maxTokens: 65536,
|
|
cost: { input: 0.23, output: 0.9, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "unsloth/gemma-3-4b-it",
|
|
name: "unsloth/gemma-3-4b-it",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
contextWindow: 96000,
|
|
maxTokens: 96000,
|
|
cost: { input: 0.01, output: 0.03, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "MiniMaxAI/MiniMax-M2.5-TEE",
|
|
name: "MiniMaxAI/MiniMax-M2.5-TEE",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 196608,
|
|
maxTokens: 65536,
|
|
cost: { input: 0.3, output: 1.1, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "tngtech/DeepSeek-TNG-R1T2-Chimera",
|
|
name: "tngtech/DeepSeek-TNG-R1T2-Chimera",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 163840,
|
|
maxTokens: 163840,
|
|
cost: { input: 0.25, output: 0.85, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "Qwen/Qwen3-Coder-Next-TEE",
|
|
name: "Qwen/Qwen3-Coder-Next-TEE",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
cost: { input: 0.12, output: 0.75, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "NousResearch/Hermes-4-405B-FP8-TEE",
|
|
name: "NousResearch/Hermes-4-405B-FP8-TEE",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 131072,
|
|
maxTokens: 65536,
|
|
cost: { input: 0.3, output: 1.2, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "deepseek-ai/DeepSeek-V3",
|
|
name: "deepseek-ai/DeepSeek-V3",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
contextWindow: 163840,
|
|
maxTokens: 163840,
|
|
cost: { input: 0.3, output: 1.2, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "openai/gpt-oss-20b",
|
|
name: "openai/gpt-oss-20b",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
cost: { input: 0.04, output: 0.15, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "unsloth/Llama-3.2-3B-Instruct",
|
|
name: "unsloth/Llama-3.2-3B-Instruct",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
cost: { input: 0.01, output: 0.01, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "unsloth/Mistral-Small-24B-Instruct-2501",
|
|
name: "unsloth/Mistral-Small-24B-Instruct-2501",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
contextWindow: 32768,
|
|
maxTokens: 32768,
|
|
cost: { input: 0.07, output: 0.3, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "zai-org/GLM-4.7-FP8",
|
|
name: "zai-org/GLM-4.7-FP8",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 202752,
|
|
maxTokens: 65535,
|
|
cost: { input: 0.3, output: 1.2, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "zai-org/GLM-4.6-TEE",
|
|
name: "zai-org/GLM-4.6-TEE",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 202752,
|
|
maxTokens: 65536,
|
|
cost: { input: 0.4, output: 1.7, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "Qwen/Qwen3.5-397B-A17B-TEE",
|
|
name: "Qwen/Qwen3.5-397B-A17B-TEE",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
cost: { input: 0.55, output: 3.5, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "Qwen/Qwen2.5-72B-Instruct",
|
|
name: "Qwen/Qwen2.5-72B-Instruct",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
contextWindow: 32768,
|
|
maxTokens: 32768,
|
|
cost: { input: 0.3, output: 1.2, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "NousResearch/DeepHermes-3-Mistral-24B-Preview",
|
|
name: "NousResearch/DeepHermes-3-Mistral-24B-Preview",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
contextWindow: 32768,
|
|
maxTokens: 32768,
|
|
cost: { input: 0.02, output: 0.1, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "Qwen/Qwen3-Next-80B-A3B-Instruct",
|
|
name: "Qwen/Qwen3-Next-80B-A3B-Instruct",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
cost: { input: 0.1, output: 0.8, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "zai-org/GLM-4.6-FP8",
|
|
name: "zai-org/GLM-4.6-FP8",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 202752,
|
|
maxTokens: 65535,
|
|
cost: { input: 0.3, output: 1.2, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "Qwen/Qwen3-235B-A22B-Thinking-2507",
|
|
name: "Qwen/Qwen3-235B-A22B-Thinking-2507",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
cost: { input: 0.11, output: 0.6, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
|
|
name: "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
cost: { input: 0.03, output: 0.11, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "tngtech/R1T2-Chimera-Speed",
|
|
name: "tngtech/R1T2-Chimera-Speed",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 131072,
|
|
maxTokens: 65536,
|
|
cost: { input: 0.22, output: 0.6, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "zai-org/GLM-4.6V",
|
|
name: "zai-org/GLM-4.6V",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
contextWindow: 131072,
|
|
maxTokens: 65536,
|
|
cost: { input: 0.3, output: 0.9, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "Qwen/Qwen2.5-VL-32B-Instruct",
|
|
name: "Qwen/Qwen2.5-VL-32B-Instruct",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
mediaInput: {
|
|
image: { maxPixels: 12845056, preferredSidePx: 2048, tokenMode: "provider" },
|
|
},
|
|
contextWindow: 16384,
|
|
maxTokens: 16384,
|
|
cost: { input: 0.05, output: 0.22, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "Qwen/Qwen3-VL-235B-A22B-Instruct",
|
|
name: "Qwen/Qwen3-VL-235B-A22B-Instruct",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
mediaInput: {
|
|
image: { maxPixels: 12845056, preferredSidePx: 2048, tokenMode: "provider" },
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
cost: { input: 0.3, output: 1.2, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "Qwen/Qwen3-14B",
|
|
name: "Qwen/Qwen3-14B",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 40960,
|
|
maxTokens: 40960,
|
|
cost: { input: 0.05, output: 0.22, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "Qwen/Qwen2.5-Coder-32B-Instruct",
|
|
name: "Qwen/Qwen2.5-Coder-32B-Instruct",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
contextWindow: 32768,
|
|
maxTokens: 32768,
|
|
cost: { input: 0.03, output: 0.11, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "Qwen/Qwen3-30B-A3B",
|
|
name: "Qwen/Qwen3-30B-A3B",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 40960,
|
|
maxTokens: 40960,
|
|
cost: { input: 0.06, output: 0.22, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "unsloth/gemma-3-12b-it",
|
|
name: "unsloth/gemma-3-12b-it",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
cost: { input: 0.03, output: 0.1, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "unsloth/Llama-3.2-1B-Instruct",
|
|
name: "unsloth/Llama-3.2-1B-Instruct",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
cost: { input: 0.01, output: 0.01, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-TEE",
|
|
name: "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-TEE",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
cost: { input: 0.3, output: 1.2, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "NousResearch/Hermes-4-14B",
|
|
name: "NousResearch/Hermes-4-14B",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
contextWindow: 40960,
|
|
maxTokens: 40960,
|
|
cost: { input: 0.01, output: 0.05, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "Qwen/Qwen3Guard-Gen-0.6B",
|
|
name: "Qwen/Qwen3Guard-Gen-0.6B",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
cost: { input: 0.01, output: 0.01, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
{
|
|
id: "rednote-hilab/dots.ocr",
|
|
name: "rednote-hilab/dots.ocr",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
cost: { input: 0.01, output: 0.01, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
];
|
|
|
|
/** Adds Chutes provider compat metadata to one model catalog entry. */
|
|
export function buildChutesModelDefinition(
|
|
model: (typeof CHUTES_MODEL_CATALOG)[number],
|
|
): ModelDefinitionConfig {
|
|
return {
|
|
...model,
|
|
compat: {
|
|
supportsUsageInStreaming: false,
|
|
},
|
|
};
|
|
}
|
|
|
|
interface ChutesModelEntry {
|
|
id: string;
|
|
name?: string;
|
|
supported_features?: string[];
|
|
input_modalities?: string[];
|
|
context_length?: number;
|
|
max_output_length?: number;
|
|
pricing?: {
|
|
prompt?: number;
|
|
completion?: number;
|
|
};
|
|
[key: string]: unknown;
|
|
}
|
|
|
|
const CACHE_TTL = 5 * 60 * 1000;
|
|
|
|
/** Clears the dynamic Chutes model discovery cache for tests. */
|
|
export function clearChutesModelCacheForTests(): void {
|
|
clearLiveCatalogCacheForTests();
|
|
}
|
|
|
|
async function fetchChutesModelRows(accessToken?: string): Promise<readonly unknown[]> {
|
|
return await getCachedLiveProviderModelRows({
|
|
providerId: "chutes",
|
|
endpoint: `${CHUTES_BASE_URL}/models`,
|
|
discoveryApiKey: accessToken,
|
|
timeoutMs: 10_000,
|
|
ttlMs: CACHE_TTL,
|
|
buildRequestHeaders: ({ discoveryApiKey }) => ({
|
|
Accept: "application/json",
|
|
...(discoveryApiKey ? { Authorization: `Bearer ${discoveryApiKey}` } : {}),
|
|
}),
|
|
policy: ssrfPolicyFromHttpBaseUrlAllowedHostname(CHUTES_BASE_URL),
|
|
auditContext: "chutes-model-discovery",
|
|
});
|
|
}
|
|
|
|
/** Discovers Chutes models dynamically, falling back to the bundled static catalog. */
|
|
export async function discoverChutesModels(accessToken?: string): Promise<ModelDefinitionConfig[]> {
|
|
const trimmedKey = normalizeOptionalString(accessToken) ?? "";
|
|
|
|
if (isChutesModelDiscoveryTestEnvironment()) {
|
|
return CHUTES_MODEL_CATALOG.map(buildChutesModelDefinition);
|
|
}
|
|
|
|
const staticCatalog = () => CHUTES_MODEL_CATALOG.map(buildChutesModelDefinition);
|
|
|
|
try {
|
|
const data = await fetchChutesModelRows(trimmedKey || undefined);
|
|
if (data.length === 0) {
|
|
log.warn("No models in response, using static catalog");
|
|
return staticCatalog();
|
|
}
|
|
|
|
const seen = new Set<string>();
|
|
const models: ModelDefinitionConfig[] = [];
|
|
|
|
for (const entry of data as ChutesModelEntry[]) {
|
|
const id = normalizeOptionalString(entry?.id) ?? "";
|
|
if (!id || seen.has(id)) {
|
|
continue;
|
|
}
|
|
seen.add(id);
|
|
|
|
const lowerId = normalizeLowercaseStringOrEmpty(id);
|
|
const isReasoning =
|
|
entry.supported_features?.includes("reasoning") ||
|
|
lowerId.includes("r1") ||
|
|
lowerId.includes("thinking") ||
|
|
lowerId.includes("reason") ||
|
|
lowerId.includes("tee");
|
|
|
|
const input: Array<"text" | "image"> = (entry.input_modalities || ["text"]).filter(
|
|
(i): i is "text" | "image" => i === "text" || i === "image",
|
|
);
|
|
|
|
models.push({
|
|
id,
|
|
name: id,
|
|
reasoning: isReasoning,
|
|
input,
|
|
cost: {
|
|
input: entry.pricing?.prompt || 0,
|
|
output: entry.pricing?.completion || 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: asPositiveSafeInteger(entry.context_length) ?? CHUTES_DEFAULT_CONTEXT_WINDOW,
|
|
maxTokens: asPositiveSafeInteger(entry.max_output_length) ?? CHUTES_DEFAULT_MAX_TOKENS,
|
|
compat: {
|
|
supportsUsageInStreaming: false,
|
|
},
|
|
});
|
|
}
|
|
|
|
if (models.length === 0) {
|
|
return staticCatalog();
|
|
}
|
|
return models;
|
|
} catch (error) {
|
|
if (error instanceof LiveModelCatalogHttpError && error.status === 401 && trimmedKey) {
|
|
return await discoverChutesModels(undefined);
|
|
}
|
|
if (
|
|
error instanceof LiveModelCatalogHttpError &&
|
|
error.status !== 401 &&
|
|
error.status !== 503
|
|
) {
|
|
log.warn(`GET /v1/models failed: HTTP ${error.status}, using static catalog`);
|
|
return staticCatalog();
|
|
}
|
|
log.warn(`Discovery failed: ${String(error)}, using static catalog`);
|
|
return staticCatalog();
|
|
}
|
|
}
|