跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
AI 与知识库

pinme-llm

Use this skill when a PinMe project (Worker TypeScript) needs to call OpenRouter-backed LLM APIs, including models, chat/completions, streaming, or OpenRouter web search. Guides AI to generate correct Worker TS code.

glitternetwork · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add glitternetwork/pinme --skill pinme-llm

技能说明


name: pinme-llm description: Use this skill when a PinMe project (Worker TypeScript) needs to call OpenRouter-backed LLM APIs, including models, chat/completions, streaming, or OpenRouter web search. Guides AI to generate correct Worker TS code.

PinMe Worker OpenRouter API Integration

Guides how to call PinMe platform's OpenRouter proxy APIs in a PinMe Worker (TypeScript). Workers use the PinMe project API key; they never hold the real OpenRouter API key.

Environment Variables

The following environment variables are automatically injected when the Worker is created — no manual configuration needed:

// backend/src/worker.ts
export interface Env {
  DB: D1Database;
  API_KEY: string;       // Project API Key from create_worker
  PROJECT_NAME: string;  // Actual project_name from create_worker; must match API_KEY
  BASE_URL?: string;     // Optional override for PinMe API base URL, defaults to https://pinme.cloud
}

API_KEY authenticates the Worker to PinMe. PROJECT_NAME is required for chat/completions and must belong to the same project as API_KEY. When BASE_URL is not set, use https://pinme.cloud.


Models API

Endpoint: GET {BASE_URL}/api/v1/models Authentication: X-API-Key header (using env.API_KEY) Request Body: none

Use this when the Worker needs to list available OpenRouter models. The response body, status, and headers are passed through from OpenRouter /models.

async function listModels(env: Env): Promise<unknown> {
  const baseUrl = env.BASE_URL ?? 'https://pinme.cloud';
  const resp = await fetch(`${baseUrl}/api/v1/models`, {
    headers: { 'X-API-Key': env.API_KEY },
  });

  if (!resp.ok) {
    throw new Error(await extractPinmeOpenRouterError(resp));
  }

  return await resp.json();
}

Chat Completions API

Endpoint: POST {BASE_URL}/api/v1/chat/completions?project_name={project_name} Authentication: X-API-Key header (using env.API_KEY) Request Body: OpenRouter chat/completions format, passed through as-is after a 1MB size check Streaming: Supports SSE (stream: true) Web Search: Supports OpenRouter openrouter:web_search server tool via the tools array

Request Format

{
  "model": "openai/gpt-4o-mini",
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "Hello!" }
  ],
  "stream": true
}

Use env.PROJECT_NAME from create_worker; always URL-encode it in the query string. For available models, call GET /api/v1/models or refer to OpenRouter model IDs.

OpenRouter Web Search

PinMe does not provide a raw search endpoint. To search the web, pass OpenRouter's openrouter:web_search server tool to chat/completions; the model decides whether and when to search.

Always set max_results and max_total_results to keep search volume and cost bounded.

async function searchWithLLM(env: Env, query: string): Promise<string> {
  const baseUrl = env.BASE_URL ?? 'https://pinme.cloud';
  const resp = await fetch(
    `${baseUrl}/api/v1/chat/completions?project_name=${encodeURIComponent(env.PROJECT_NAME)}`,
    {
      method: 'POST',
      headers: {
        'Content-Type': 'application/json',
        'X-API-Key': env.API_KEY,
      },
      body: JSON.stringify({
        model: 'openai/gpt-5.2',
        messages: [{ role: 'user', content: query }],
        tools: [
          {
            type: 'openrouter:web_search',
            parameters: {
              engine: 'auto',
              max_results: 5,
              max_total_results: 10,
            },
          },
        ],
      }),
    },
  );

  if (!resp.ok) {
    throw new Error(await extractPinmeOpenRouterError(resp));
  }

  const data = await resp.json() as { choices: Array<{ message?: { content?: string } }> };
  return data.choices[0]?.message?.content ?? '';
}

Response Format

Successful requests return OpenRouter's raw response body.

Non-streaming Success (200):

{
  "id": "chatcmpl-...",
  "choices": [{ "message": { "role": "assistant", "content": "Hello!" }, "finish_reason": "stop" }],
  "usage": { "prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15 }
}

Streaming Success (200): SSE format

data: {"choices":[{"delta":{"content":"Hello"}}]}
data: {"choices":[{"delta":{"content":" there"}}]}
data: [DONE]

Errors:

HTTP StatusMeaningdata.error Example
401API Key missing, invalid, or mismatched with project_name"X-API-Key header is required" / "Invalid API key" / "Invalid API key or project name"
400project_name missing or OpenRouter key not configured"project_name is required" / "LLM service not configured for this project"
403LLM balance insufficient or disabled"Insufficient balance, please recharge to continue using LLM service"
413Request body exceeds 1MB"Request body too large (max 1MB)"
500Proxy failed before upstream request"Failed to build request"
502LLM service unavailable"LLM service unavailable"

If OpenRouter receives the request and returns a 4xx/5xx, PinMe passes through OpenRouter's status, headers, and response body instead of wrapping it.

Worker Example Code — Non-streaming

async function callLLM(
  env: Env,
  messages: Array<{ role: string; content: string }>,
  model = 'openai/gpt-4o-mini',
): Promise<{ content: string; error?: string }> {
  const baseUrl = env.BASE_URL ?? 'https://pinme.cloud';
  const resp = await fetch(
    `${baseUrl}/api/v1/chat/completions?project_name=${encodeURIComponent(env.PROJECT_NAME)}`,
    {
      method: 'POST',
      headers: {
        'Content-Type': 'application/json',
        'X-API-Key': env.API_KEY,
      },
      body: JSON.stringify({ model, messages }),
    },
  );

  if (!resp.ok) {
    return { content: '', error: await
阅读完整来源 ↗