cloudrun-development

Backend service development with long connections, multi-language support, and AI agent capabilities. If this environment only installed the current skill, start from the CloudBase main entry and use the published cloudbase/references/... paths for sibling skills. Keep local references/... paths for files that ship with the current skill directory. When this file points to a sibling skill such as auth-tool or web-development , use the standalone fallback URL shown next to that reference. Use CloudBase Run when the task needs a deployed backend service rather than a short-lived serverless function. Choose mode first Follow mandatory runtime rules Use the correct tools Follow the deployment sequence MinNum: 1 is the recommended default when you want to reduce cold-start latency. If the user explicitly prefers lower cost and accepts more cold starts, explain the tradeoff and let them reduce MinNum to 0 . - Supports two modes: Function mode (Node.js, built-in HTTP/WebSocket/SSE, fixed port 3000, local running) and Container mode (any language/runtime via Docker, no local tool support) - Requires stateless services that listen on the PORT environment variable and write data externally; resource constraints enforce Mem = 2 × CPU - Includes read tools ( queryCloudRun ) for listing services and templates, and write tools ( manageCloudRun ) for init, deploy, run, and agent creation...