Compares stock and incoming orders against supplier lead times and real demand — and speaks only when someone must order something by a date.
Daily check, but it only messages when action is needed: “order X by <date>” with the evidence. No news is genuinely good news here (the dead-man's switch still proves it ran).
Because almost no items had lead times on record, nobody could compute “will we run out before a new order arrives?” As INV-2's approved coverage grows, this loop's answers sharpen from provisional to firm.
After the overnight data sync
On-hand + on-order per item
Days of cover vs lead time + demand rate
“Order by <date>” list, evidence attached
Healthchecks ping on clean runs
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 |
|---|---|
| NetSuite warehousePostgres on our server | Our nightly read-only copy of NetSuite (ERP) data — items, stock, transactions — refreshed by the ETL sync every morning. The loop queries this copy, never NetSuite itself. |
| Metabasebi.huxapps.com | The BI layer over the warehouse. The loop runs its SQL through Metabase's API, and every number in the digest links to a live, clickable Metabase list so you can drill into the exact records. |
| Postgres “loops” schemareporting database | A small dedicated schema where loops keep snapshots and history that need SQL (week-over-week diffs, mirrors for drill-down links). Scoped role; Metabase can read it for the clickable aggregate links. |
| 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. |
| Claude Opusthe judgment model | Reviews alert wording, thresholds, and anything a human will read and act on. Post-Fable, Opus owns everything that ships. |
Yesterday's risk list — the loop reports newly-at-risk and resolved items, not the same list every day.
Email only when action is needed; every item links to its ERP record and the aggregate links to a live list.
Read-only; PROVISIONAL label until lead-time coverage is real; never touches purchasing.