Answers 'how much do you actually use these tools' with a real number that updates while someone watches, not a static claim. Zero-dependency stdlib Python, real-fixture test suite (no mocks), graceful degradation on every malformed-input path since it reads files another process is actively writing.

Reads two live sources per session (the session registry and each session's own transcript JSONL) for a real-time board of what's running, and separately scans every transcript on disk plus kimi CLI session logs for a day-by-day usage history, independent of which sessions are still alive. A short server-side cache keeps the expensive historical scan fast on repeat loads without going stale for more than 15 minutes.

Built and hardened the same way any production change here goes out: full existing test suite green before touching the live systemd service, a throwaway-port smoke test against real data first, then a restart and a live re-verify after deploy, never the reverse.

• > 216 tests, zero skips
• > Live at call-monitor.ecbtx.com behind Cloudflare Access