{
  "id": "n8n",
  "name": "n8n and workflow automation",
  "category": "connector",
  "recipe": "n8n-http",
  "protocol": "chat-completions",
  "source": "https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatopenai/",
  "referenceDate": "2026-09-29",
  "verification": {
    "setup": "prepared",
    "session": "not_run"
  },
  "notes": "Use an OpenAI Chat Model custom Base URL, or the generated HTTP request descriptor in an existing authenticated workflow. Store keys in n8n credentials. Graph operations are available via the shared SDK and OpenAPI spec; this descriptor is not a full importable workflow.",
  "contractVersion": "1.0.0",
  "endpoint": "https://jesse.my/api/v1/chat/completions",
  "apiRoot": "https://jesse.my/api",
  "model": "jesse",
  "files": [
    {
      "name": "request.json",
      "format": "json",
      "content": "{\n  \"method\": \"POST\",\n  \"url\": \"https://jesse.my/api/v1/chat/completions\",\n  \"authentication\": \"Generic credential > Header Auth > Authorization: Bearer YOUR_JESSE_KEY (store in credentials)\",\n  \"sendBody\": true,\n  \"contentType\": \"json\",\n  \"body\": {\n    \"model\": \"jesse\",\n    \"messages\": [\n      {\n        \"role\": \"user\",\n        \"content\": \"What is 17 * 23?\"\n      }\n    ]\n  },\n  \"responseFormat\": \"json\",\n  \"retryOnFail\": false\n}\n"
    },
    {
      "name": "README.md",
      "format": "markdown",
      "content": "# n8n and workflow automation with Jesse\n\nUse an OpenAI Chat Model custom Base URL, or the generated HTTP request descriptor in an existing authenticated workflow. Store keys in n8n credentials. Graph operations are available via the shared SDK and OpenAPI spec; this descriptor is not a full importable workflow.\n\nAPI root: https://jesse.my/api\nOpenAI-compatible base URL: https://jesse.my/api/v1\nEndpoint: https://jesse.my/api/v1/chat/completions\nModel: jesse\nKey environment: JESSE_API_KEY\n\nKeep the key in the app's credential store or launch environment. These files are merge snippets; never overwrite existing providers or settings. GUI apps may not inherit shell environment variables.\n\nClient budgets: context 10000, output 4096. These are conservative defaults, not server capacity claims. Keep general vision, embeddings, audio, provider-hosted web tools and automatic retry of billable turns disabled.\n\nFull Jesse API access: shared/client_sdk.mjs supports 31 operations. The MCP bridge exposes the same operation list where the host supports MCP. Preserve the full Jesse receipt. Tool calls remain proposals and are not executed by the bridge.\n\nVerification: setup prepared; current full application session not_run. Run a chat, a streamed reply, a refused credential, a failing tool result and a file task with its actual tests before qualifying a coding-agent release.\n\nUpstream: https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatopenai/\n"
    }
  ]
}