feat: Claude Code Monitor — lanes, pipelines and a merged workspace

Internal SmartGift build of a Claude Code monitoring dashboard.

Lanes: a durable unit of parallel agent work, one per working directory,
tracked across session restarts. Managed lanes are git worktrees the
dashboard provisions and can reset or remove behind a three-check destroy
guard and a counted preflight; adopted lanes are directories you already
own and are never destroyable.

Pipelines: a lane moves through pipeline stages. A stage the agent declares
with evidence renders green; a stage inferred from the tool-event stream
renders dashed amber and never counts as done. Detection is forward-only
within a 30-minute window, and never writes the declared stage.

Workspace: one page at /run with a lane grid, the selected lane's pipeline,
and a full Claude console behind a disclosure.
This commit is contained in:
2026-07-29 17:07:45 +07:00
commit 57dc91585d
783 changed files with 221743 additions and 0 deletions
@@ -0,0 +1,19 @@
---
description: One-screen focus snapshot — avg turn duration, thinking-block usage, and longest sessions.
argument-hint: "[limit]"
---
Print a one-screen focus snapshot from Agent Monitor data at `http://localhost:4820`. If the dashboard is unreachable, tell the user to start it with `npm start` from the repo root.
Optional **$ARGUMENTS**: a session count to inspect (default 100).
1. Fetch sessions: `curl -s 'http://localhost:4820/api/sessions?limit=100'` (use the $ARGUMENTS limit if given). Parse each `metadata` JSON for `turn_count`, `total_turn_duration_ms`, and `thinking_blocks`.
2. Fetch baselines: `curl -s http://localhost:4820/api/analytics` for `avg_events_per_session` and `sessions_by_status`.
Compute and print (over sessions that have the focus metadata):
- **Avg turn duration** = `total_turn_duration_ms / turn_count`, reported in seconds (averaged across sessions).
- **Thinking-block usage** = average `thinking_blocks` per session and per turn (`thinking_blocks / turn_count`).
- **Longest sessions**: top 35 by `total_turn_duration_ms`, each with project (`cwd`), duration in minutes, turn count, and thinking blocks.
Show the three metrics as a compact table plus the longest-sessions list. State how many sessions had usable metadata. Durations from ms; cite only numbers returned by the API. Keep it to one screen.