Update bot user ID and model name in configuration files; enhance outage recovery reporting

This commit is contained in:
2026-06-23 21:25:07 +12:00
parent e14c21fab5
commit 9df86ead20
4 changed files with 147 additions and 7 deletions
+6 -3
View File
@@ -32,11 +32,14 @@ Claude Code, then relays/acts on the agent's JSON result.
re-probe. Kuma's root-owned `kuma.db` is read via a throwaway `keinos/sqlite3`
container mounting the `uptime-kuma-data` volume read-only.
- **Health loop** (5 min): down services confirmed over `down_confirmations`
cycles → invoke stack-support agent to remediate → report to Matrix.
cycles → invoke stack-support agent to remediate → report to Matrix. Also
reads Kuma's `important=1` heartbeat transitions since the last cycle (tracked
by heartbeat id) to catch services that blipped DOWN→UP on their own, and
hands those self-recovered windows to the agent for a log post-mortem.
- **Upgrade loop** (7 days): resolve containers behind tracked services → agent
researches + applies safe upgrades (test, pin, rollback); escalates
major/breaking ones to Matrix.
- **Matrix**: bot `@maintainer:semprini.me` DMs `@paul:semprini.me`. Escalations
- **Matrix**: bot `@maintainer-bot:semprini.me` DMs `@paul:semprini.me`. Escalations
are numbered questions; the reply is fed back to the agent to carry out.
- **Autonomy** (`config.json``autonomy`): `full` (default) | `fix-only` |
`notify`.
@@ -56,7 +59,7 @@ Claude Code, then relays/acts on the agent's JSON result.
|---|---|
| `maintainer.py` | The daemon (stdlib only). |
| `config.example.json` | Template — copy to `config.json`. |
| `register-matrix-bot.sh` | Creates `@maintainer` account + DM room; writes token to config. |
| `register-matrix-bot.sh` | Creates `@maintainer-bot` account + DM room; writes token to config. |
| `install.sh` | Syntax-check, install unit, enable + start. |
| `semprini-maintainer.service` | systemd unit (runs as `paul`). |
| `docs/architecture.md` | Architecture decision record. |