Measures how long delivery and work inspections take per project against targets set with Yasar — the honest version: the timestamps mostly don't exist yet, so the loop ships in degraded mode and upgrades itself as data appears.
Weekly once real data flows; today it reports coverage honestly (“0 of 4 deliveries have inspection dates”) rather than pretending.
The investigation found the billing database has the right tables but they're empty — inspections and batch dates simply aren't captured. So this loop's first deliverable was a precise feature request (three capture fields), plus a monitor that switches itself from “coverage report” to “speed report” the day data lands.
Monday
Milestone tables, capture coverage
Data present? → speed report. Absent? → coverage report
Medians vs targets, or the coverage gap
Yasar sets what “fast enough” means
For implementers and the technically curious. The full build sheet — verified queries, thresholds, and build notes — lives on the specs page.
| System | Role in this loop |
|---|---|
| Joinery Billing appSQLite on our server | The construction billing system. The loop reads a snapshot copy of its database — never the live file. |
| Hermesagent runtime on our server | The scheduler that wakes the loop up. Each loop is a cron job under a Hermes profile; the planned bizops profile will host the business digests (IT loops run under vpsops). |
| Healthcheckshealthchecks.huxapps.com | The dead-man's switch. The loop pings it only after a clean run — if the loop dies or errors, the ping stops and Healthchecks raises the alarm independently. This is how 'never silent' is enforced by machinery, not promises. |
| Email renderer + gwsrender_email.py | All digests pass through one shared renderer: Huxberry-branded HTML, tables for repeated rows, a coral 'needs your response' box when the loop has questions, and an arrow link on every record. Sent from the loops mailbox via the Google Workspace CLI. |
| Loop chassisloop_common.py | Shared plumbing every loop reuses instead of reinventing: state files, run-over-run diffing, Metabase drill-down link building, quiet-on-green notify logic. |
| Model / brain | What it does here |
|---|---|
| None at run timedeterministic script | A normal cycle is a plain Python script — no AI tokens are spent unless a diagnosis or judgment step is actually needed. AI wrote the script; the script does the rounds. |
| GPT-5.5 via Codexthe bulk-work model | Wrote and maintains the mechanical parts — SQL, diffing, digest assembly. Effectively free on our existing subscription, so routine cycles cost almost nothing. |
Coverage history — so “capture is improving” is itself a visible trend while the feature request lands.
Weekly email to Yasar; deliberately short until there's something real to measure.
Snapshot reads only. Reports coverage honestly instead of inventing durations from absent data.