# Claude Code Working Guide

## Project mission
- Maintain a reliable local-first dashboard for Claude Code session monitoring.
- Preserve real-time behavior (hooks -> API -> SQLite -> WebSocket -> UI).
- Keep MCP integration production-ready for local use (`mcp/`).

## Repo map
- `server/`: Express API, hook ingestion, SQLite access, websocket broadcast (includes optional git upstream checks and `routes/updates.js`, plus `lib/workflow-ingest.js` which ingests on-disk Workflow-tool run journals — fleets that emit no hooks).
- `client/`: React + Vite UI.
- `scripts/`: hook installer/handler, import, seed, cleanup utilities. (Update detection lives server-side in `server/lib/update-check.js`; the dashboard never restarts itself — users run the printed command, surfaced in the UI and by `ccam update-check`.)
- `mcp/`: local MCP server exposing dashboard operations as tools. **`mcp/build/` is committed on purpose** — plugin MCP servers start before any bootstrap could build them; `scripts/check-mcp-build.js` (content hash in `mcp/build/.srchash`, run by pre-commit and `/ccam-doctor`) keeps it honest. Rebuild with `npm run mcp:build`, never hand-edit `mcp/build/`.
- `.claude-plugin/`: the marketplace plus the root `ccam` plugin manifest (`"source": "./"` — the whole repo is the plugin). Its hooks are inline in `plugin.json`; its commands live in `plugins/ccam/commands/`, which is NOT a subdirectory plugin. `scripts/plugin-bootstrap.js` runs from `SessionStart` and owns the writable runtime under `~/.claude/agent-dashboard/runtime/` — it never writes into the plugin cache, which Claude Code replaces on every update. See `docs/PLUGINS.md`.

## Lanes

A **lane** is a durable unit of parallel agent work — one working directory, many Claude Code sessions over time. Lanes are keyed by `cwd`, not `session_id`, so they survive session restarts and allow the dashboard to show a pipeline that persists across runs.

**Key points:**
- Sessions are bound to lanes by longest path-boundary prefix match on their `cwd` (set in hook data from `claude` CLI).
- A lane's stage is **declared** by the driving Claude session (via `ccam stage <stage> [--evidence "..."]`), not inferred by the dashboard.
- **The console never writes a lane's stage.** Declared stages come from `ccam stage` (a skill calling the CLI command), and inferred stages come from tool-event detection only. The UI's run console and the Workspace page never call `POST /api/lanes/:id/stage` — that boundary exists because the console observes tool calls but cannot see their outcomes. A lane's stage is the session's truth about progress; the console's observation of tool execution would not be proof of completion.
- **A detection expires, an evidence rule does not.** `recordDetection` skips its forward-only comparison once `detected_at` is older than `DETECTION_TTL_MS` (default 5 min), so a lane can move backwards between work sessions. That window changes only WHICH detection is current — it never relaxes declared-wins (an agent's own claim has no expiry) and never lets an inferred node render `done`.
- **Working-copy facts live at `GET /api/lanes/:id/git`, never inside `GET /api/lanes`.** That endpoint shells out to git three times; the lane list is polled and re-broadcast on every hook. A cwd that is not a readable repo returns `{available:false}` with HTTP 200 — a normal state, not a fault. Cards fetch it themselves every 30s and fail silently.
- **The Workspace console collapses with CSS, never by unmounting.** Unmounting `RunConsole` disposes the run subscription and drops a live run's rendered history.
- **CCAM does not orchestrate:** no chaining, no queue, no retry logic, no gate evaluation. The session in control makes all decisions; the dashboard records the claimed stage and shows evidence. The runtime layer (`ccam lanes up|down|hook`) does not change this — it offers *primitives* a session calls; nothing in the dashboard sequences them.
- **The runtime never writes `stage`, `status` or `notes`** — only `slot` and `ports`. `status=running` means an AGENT is working, not that a server is listening; merging the two would corrupt `classifyLiveness`. Boot failures live in `LANES_ROOT/.state/lane<slot>/last-error.json` and surface via `GET /api/lanes/:id/runtime`. Same boundary as the console-never-writes-stage rule above.
- **A lane's stack is up or down as a computed fact, never a stored one.** `runtimeFacts` re-derives it from pid files and port probes on every read. A process dies to OOM, a stray `kill`, a reboot — caching a truth CCAM does not control buys ghost state. Slot allocation is the opposite (fully controlled, must be race-free), so that one does live in the DB, under `withLaneLock` plus a partial unique index.
- **A profile's `profile.env` is parsed, never sourced.** Hooks are executed deliberately; config is only read. Sourcing arbitrary shell from a user's repository into the dashboard process would be a code-execution path. Hook names always come from the fixed allowlist in `server/lib/lane-profile.js`, never from a request.
- Pipeline templates are JSON files (`server/data/pipelines/`) with node definitions; custom templates override built-ins when `DASHBOARD_PIPELINES_DIR` is set.
- Nodes render in five states: `failed` (rejected), `current` (now), `done` (with evidence), `passed-no-evidence` (claimed or skipped, amber), `pending` (not reached).
- Liveness: a silent **watcher** (stage matching `/watch|poll/`) is dead after `LANE_DEAD_SEC` seconds (default 300); a silent **idle** lane is at rest, not dead.
- **Never `rm -rf` a lane.** Destructive lane operations (`reset`, `remove`, `purge`) go through `server/lib/worktree.js`/`server/lib/lanes.js`, never a raw filesystem delete — that's what keeps the three-check destroy guard and the DB bookkeeping in lockstep.
- **Never build a git command as a shell string.** Lane git operations use `execFile("git", [...args])` with an explicit argument array (see `server/lib/worktree.js`'s `git()` helper), never a concatenated/interpolated string passed to a shell.
- **Adopted lanes are not destroyable.** A lane with `kind === "adopted"` may never have its worktree reset or removed; "removing" one only drops the dashboard's own record of it. This is enforced in code (`assertDestroyable`'s first check) — do not add a path that bypasses it.

See `docs/LANES.md` for full guide: stage reporting, custom templates, lane actions, and the five node states.

## Non-negotiable engineering rules
- Preserve existing behavior unless explicitly asked to change it.
- Prefer minimal, reversible diffs.
- Never silently weaken safety controls around destructive actions.
- Keep docs updated when behavior, commands, file locations, or workflows change — apply the `update-project-docs` skill automatically at the end of every change-set that alters behavior, config, interfaces, events, schema, CLI commands, or features (do not wait to be asked).
- Every applicable source file you create or update (`.js/.ts/.tsx/.cjs/.mjs/.py/.sh/.css`) must start with the copyright/authorship header — file overview + the exact line `@author Nguyễn Ngọc Trí Vĩ <vinnt@smartgift.vn>`. Formats and audit script: `.claude/skills/file-headers/` (verify with `bash .claude/skills/file-headers/scripts/check-headers.sh`). This binds every coding agent (Claude Code, Codex, or others).

## Commands you should know
- Setup: `npm run setup`
- Dev: `npm run dev`
- Prod build/start: `npm run build` then `npm start`
- Server tests: `npm run test:server`
- Client tests: `npm run test:client`
- MCP install/build/start: `npm run mcp:install`, `npm run mcp:build`, `npm run mcp:start`
- MCP build freshness: `npm run mcp:check-build` (must pass whenever `mcp/src` changes)
- MCP typecheck: `npm run mcp:typecheck`
- CLI (after setup): `ccam <command>` — terminal access to the full dashboard surface (`bin/ccam.js`; `ccam help` lists commands)

## Testing and verification policy
- Backend changes: run `npm run test:server` before finishing.
- Frontend changes: run `npm run test:client` when relevant. This includes per-screen render snapshots (`client/src/pages/__tests__/screens.snapshot.test.tsx`). If a UI change is intentional, review the snapshot diff and regenerate baselines with `cd client && npx vitest run -u`; never blindly update snapshots to make tests pass.
- MCP changes: run `npm run mcp:typecheck` and `npm run mcp:build`.
- If you cannot run a verification step, state exactly what was not run and why.

## Change guidelines by area
- API routes: preserve response shapes unless change is requested and documented.
- Database: avoid schema changes without migration-safe logic.
- Hooks: keep fail-safe and non-blocking behavior.
- WebSocket: keep message types stable and backward-compatible.
- Documentation: include exact commands and paths; keep markdown examples runnable.

## Agent behavior
- Explore first, then implement.
- For larger tasks, propose/check a short plan before broad edits.
- Use file-specific rules in `.claude/rules/` when working in scoped areas.
- Use project skills from `.claude/skills/` for repeatable workflows.
- Use `.claude/agents/` subagents for focused review or investigation passes.
- **Declare lane stage even in plain chat, not just inside skills.** `ccam stage` (see `docs/LANES.md` § Reporting a stage) is a reporting command, not a skill-only ritual — any Claude session working inside an adopted lane's cwd should call it on real stage transitions (starting to plan, starting to implement, running tests, opening the PR, etc.), whether or not a skill is driving. Tool-event detection (`server/lib/stage-detect.js`) only ever paints the amber "detected" badge, never the blue `current` ring — a lane worked entirely through plain chat with no `ccam stage` calls will show a stale `current` stage no matter how much real work happens. Skip it only when `ccam stage` reports no lane owns the cwd (not adopted).