datadog-analysis

# Datadog Analysis Analyze production error logs from Packmind Datadog services, group them into patterns, cross-reference stack traces with the codebase, and produce a structured markdown report with root causes and Datadog search patterns. ## Prerequisites - The Datadog MCP server must be connected. If not connected, prompt the user to run `/mcp` first. - Read `references/datadog_mcp.md` before making any MCP tool calls for guidance on tool usage, gotchas, and known pitfalls. ## Services The analysis covers three production services. Each maps to a Datadog service name, a codebase location, and a Dockerfile: | Datadog service | App | Codebase | Dockerfile | Runtime | |----------------|-----|----------|------------|---------| | `api-proprietary` | API | `apps/api/` + all `packages/` | `dockerfile/Dockerfile.api` | Node.js (NestJS, TypeORM, Redis/ioredis, BullMQ) | | `mcp-proprietary` | MCP Server | `apps/mcp-server/` + all `packages/` | `dockerfile/Dockerfile.mcp` | Node.js (tree-sitter, SSE) | | `frontend-proprietary` | Frontend | `apps/frontend/` | `dockerfile/Dockerfile.frontend` | Nginx (static SPA serving) | Root cause analysis should trace errors back to source files in the monorepo. For Nginx (frontend), also check the Nginx configs in `dockerfile/nginx.*.conf` and the entrypoint `dockerfile/nginx-entrypoint.sh`. ## Parameters | Parameter | Default | Description | |-----------|---------|-------------| | Days to analyze | 7 | Number of past days to look at. Ov...