karea_set_markdown
Write markdown documents for tasks to store research findings, technical docs, requirements, and design decisions. Overwrites existing content for a single source of truth.
Instructions
Write the markdown document for a task. Overwrites any existing content. Use this to persist: investigation findings and research, technical documentation (architecture, APIs, schemas), functional documentation (requirements, acceptance criteria, user flows), root cause analysis and debugging logs, solution design — planned or implemented, risks, trade-offs, and open questions. This is the single source of truth for everything learned about this task. Always append to existing content (read first with karea_get_markdown) rather than replacing it, unless restructuring.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | Task name, visual ID (C1, T2), or UUID | |
| markdown | Yes | The full markdown content to store on the task. Pass empty string to clear. | |
| toolType | No | Optional: your AI provider ("claude-code" / "opencode" / "codex" / "cursor" / "aider" / "other"). Required when aiSessionId is supplied. | |
| projectId | No | Project name or ID (needed for visual ID lookup) | |
| aiSessionId | No | Optional: your current AI CLI session ID. When paired with toolType, atomically links this session to the affected task (equivalent to calling karea_link_session, but saves the round-trip). For Claude Code use the id from `claude --resume`. | |
| sessionLabel | No | Optional short label for the linked session (e.g. "Feature draft"). |