zeabur

Use when debugging services on a user's dedicated server via SSH. Use when needing to inspect pods, check container logs, view k8s resources, or run kubectl commands on the server. Use when "service exec" is insufficient and you need server-level access. Use when user says "check my server", "debug pod", "kubectl", "SSH into server", "check k8s", or "inspect cluster".

Use when deploying a local project or codebase to Zeabur. Use when the user says "deploy this", "deploy to Zeabur", "deploy from GitHub", "search my repos", or "find my repository". Default to direct deploy unless the user explicitly asks for Git-based deployment.

Use when the user uploads a project file and you see `<UploadedFile>` in the message. Use when user says "看看這個專案", "分析程式碼", "check this project", "what's in this upload", or asks about the structure of an uploaded file.

Use when modifying service config without full redeploy. Use when updating env vars and restarting single service. Use when user says "change env var", "update config", "fix variable without redeploying", "upgrade service version", "update image tag", or "change service tag".

Use when deploying a database to Zeabur. Use when user needs MySQL, PostgreSQL, MongoDB, or Redis. Use when user says "I need a database", "add database", "deploy postgres", "set up MySQL", "add Redis", "add MongoDB", or "connect to database". Also use when user mentions data persistence issues like "data lost after restart", "data not saved", "data disappears", "need persistent storage for data", or "how to persist data". Also use when integrating a database with an existing service.

Use when deploying object storage (S3-compatible) to Zeabur. Use when user needs MinIO, RustFS, or S3-compatible storage. Use when user says "object storage", "file storage", "S3", "MinIO", "RustFS", "upload files", "store files", "blob storage", or "OSS". Also use when integrating object storage with an existing service.

Use for ALL Zeabur environment variable operations — create, list, update, delete, or troubleshoot. Use when user says "set env var", "add variable", "create variable", "update variable", "delete variable", "change env var", or "why is my variable empty". Also use when variables are empty or SERVICE_NOT_FOUND errors.

Use when viewing service runtime or build logs. Use when user says "show logs", "why did deploy fail", "check build output", or "debug runtime error".

Contribute new verified knowledge to the RAG knowledge base. Use after you've solved a concrete problem, debugged a non-obvious issue, or discovered undocumented behavior that would help future agents — but only after calling zeabur-rag-search first to confirm the knowledge isn't already covered. Only contribute verified facts, not guesses or workarounds. The new chunk is marked unverified until an admin reviews it.

Interactive knowledge base curation loop — reviews pending items (reports, unverified chunks, failed queries, negative feedback) and walks through fixes one by one. Use when asked to "maintain the knowledge base", "review pending items", "run a curation round", "process reports", "clean up the KB", or any request to improve KB quality. This is the main entry point for the expand → organize → reflect cycle, and requires admin scope.

Send feedback on RAG search results — thumbs-up (+1) or thumbs-down (-1) to indicate whether the answer was helpful. Use after calling zeabur-rag-search when you can evaluate the quality of the results. Positive feedback reinforces good results; negative feedback flags poor matches for review. Requires write:feedback scope.

View a single chunk's full content plus related reports, search signals, and edit history. Use when you need to understand a chunk's context before editing, when investigating why a search result appeared, or when reviewing a reported issue. Triggers on "inspect chunk SUP-1234", "show chunk DOC-xxx", "chunk history", "why did this result appear", "look at this chunk". Requires admin scope.

Search the RAG knowledge base via hybrid search (semantic + BM25). Use whenever answering technical questions that may be covered in your knowledge base — even if the user doesn't explicitly ask you to search. Also use when you need to verify claims or find up-to-date information.

List pending knowledge base maintenance items — open reports, unverified learned chunks, low-score queries, and negative feedback. Use when checking KB health, reviewing the maintenance queue, or starting a curation session. Triggers on "review queue", "what needs attention in the KB", "pending reports", "unverified chunks", "failed queries", "KB health check". Requires admin scope.

Edit the content of an existing chunk in the RAG knowledge base. Use when a chunk has a typo, outdated info, wrong tags, wrong visibility, or needs its title/question/answer rewritten — and you want the fix to take effect immediately. Requires admin scope. Prefer zeabur-rag-report for surfacing issues without write access.

Report knowledge issues (outdated, incorrect, or missing content) in the RAG knowledge base. Use when search results seem outdated or wrong, when a topic should be covered but isn't found, or when a chunk contains incorrect information. This helps maintain knowledge base quality.

Translate documentation pages to all missing locales. Use when a document exists in one locale but needs to be translated to others. Supports --dry-run, single-locale targeting, and incremental updates.

Look up Zeabur platform UI term translations from the dashboard i18n files. Use when writing or reviewing docs that reference UI elements (button labels, tab names, menu items) to ensure docs match the actual platform translations.