# Scratchpad: @mosaic/brain Structured Data Service

**Issue:** #10
**Branch:** feat/brain-service
**PRD:** jarvis-brain/docs/planning/MOSAIC-BRAIN-MEMORY-PRD.md

## Objective

Implement @mosaic/brain as a Fastify service exposing structured data (tasks, projects, events, missions, etc.) via MCP + REST with JSON file backend.

## Plan

1. [x] Add brain data types to @mosaic/types
2. [ ] Scaffold packages/brain/ with Fastify + MCP SDK
3. [ ] Implement JSON file storage adapter with locking
4. [ ] Implement collections: tasks, projects, events, agents, tickets, appreciations, missions, mission_tasks
5. [ ] Implement MCP tools (query + mutation + mission)
6. [ ] Implement REST API (mirrors MCP)
7. [ ] Bearer token auth middleware
8. [ ] brain_today computed endpoint
9. [ ] brain_stale, brain_stats, brain_audit, brain_search, brain_graph
10. [ ] Dockerfile + docker-compose
11. [ ] Tests
12. [ ] Code review
13. [ ] Commit, push, PR, merge

## Progress

- 2026-03-10: Issue #10 created, branch created, starting implementation

## Risks

- Types package already has `Task`/`TaskStatus`/`TaskPriority` for queue — need namespacing
- Large implementation surface — focus on core CRUD first, computed endpoints second

## Decisions

- Brain types exported from `@mosaic/types` under `Brain` prefix to avoid queue type conflicts
- JSON storage uses one file per collection
- In-memory index rebuilt on startup