บริการโมเดลภายในเครื่อง

{
  models: {
    providers: {
      local: {
        baseUrl: "http://127.0.0.1:8000/v1",
        apiKey: "local-model",
        api: "openai-completions",
        timeoutSeconds: 300,
        localService: {
          command: "/absolute/path/to/server",
          args: ["--host", "127.0.0.1", "--port", "8000"],
          cwd: "/absolute/path/to/working-dir",
          env: { LOCAL_MODEL_CACHE: "/absolute/path/to/cache" },
          healthUrl: "http://127.0.0.1:8000/v1/models",
          readyTimeoutMs: 180000,
          idleStopMs: 0,
        },
        models: [
          {
            id: "my-local-model",
            name: "My Local Model",
            reasoning: false,
            input: ["text"],
            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
            contextWindow: 131072,
            maxTokens: 8192,
          },
        ],
      },
    },
  },
}

{
  agents: {
    defaults: {
      model: { primary: "inferrs/google/gemma-4-E2B-it" },
    },
  },
  models: {
    mode: "merge",
    providers: {
      inferrs: {
        baseUrl: "http://127.0.0.1:8080/v1",
        apiKey: "inferrs-local",
        api: "openai-completions",
        timeoutSeconds: 300,
        localService: {
          command: "/opt/homebrew/bin/inferrs",
          args: [
            "serve",
            "google/gemma-4-E2B-it",
            "--host",
            "127.0.0.1",
            "--port",
            "8080",
            "--device",
            "metal",
          ],
          healthUrl: "http://127.0.0.1:8080/v1/models",
          readyTimeoutMs: 180000,
          idleStopMs: 0,
        },
        models: [
          {
            id: "google/gemma-4-E2B-it",
            name: "Gemma 4 E2B (inferrs)",
            reasoning: false,
            input: ["text"],
            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
            contextWindow: 131072,
            maxTokens: 4096,
            compat: {
              requiresStringContent: true,
            },
          },
        ],
      },
    },
  },
}

{
  models: {
    providers: {
      ds4: {
        baseUrl: "http://127.0.0.1:18000/v1",
        apiKey: "ds4-local",
        api: "openai-completions",
        timeoutSeconds: 300,
        localService: {
          command: "/Users/you/Projects/oss/ds4/ds4-server",
          args: [
            "--model",
            "/Users/you/Projects/oss/ds4/ds4flash.gguf",
            "--host",
            "127.0.0.1",
            "--port",
            "18000",
            "--ctx",
            "393216",
          ],
          cwd: "/Users/you/Projects/oss/ds4",
          healthUrl: "http://127.0.0.1:18000/v1/models",
          readyTimeoutMs: 300000,
          idleStopMs: 0,
        },
        models: [],
      },
    },
  },
}