feat(carwash): advisory vehicle category from the entry camera — mapping, pre-select, downgrade flag

The app plumbing for venue-modules.md §"Vehicle category from vision"; the model is the
open half (no bundled recognizer emits body_type yet, so the desk shows nothing until
phase A lands in the vision service).

- Shared: VEHICLE_CLASSES vocabulary, VehicleRead, CARWASH_VISION_THRESHOLD_DEFAULT,
  reason code carwash.categoryDowngrade; settings/order/lookup views carry the read.
- Vision contract: /analyze vehicle.body_type + confidence (service schema); the Node
  client normalises to the vocabulary and drops the rest.
- Record: snapshot.ts stores the read in the plate's device_events row (or its own when
  the plate was unreadable); vehicleForIdentity() resolves it like the plate.
- Car wash: carwash_categories.vision_classes (site mapping "car, sedan → Vetura"),
  carwash_config.vision_threshold (signed config_change when it moves), four vision
  columns on orders — migration 0030. Lookup returns vision + suggestedCategoryId.
- Desk pre-selects the mapped category and shows the read + snapshot thumbnail; Setup
  offers class chips per category and the threshold. Operator decides.
- Flag: a read at/above the threshold whose mapped category prices HIGHER than the chosen
  one signs one `anomaly` (both categories/prices, operator, snapshot) and stores its id on
  the order. Equal/upgrade/unsure/unmapped → nothing. Recorded only, never blocks, no
  reason prompt (user, 2026-09-06).

Tests in carwash.test.ts; wiki venue-modules (As built), opencv-anpr-service, log.

Claude-Session: https://claude.ai/code/session_01FWncR69HgGPuei1dLrW3cU
This commit is contained in:
2026-09-06 13:37:34 +02:00
parent 50c18405b6
commit 5e1395db18
19 changed files with 511 additions and 32 deletions
+25
View File
@@ -170,6 +170,31 @@ vehicle. The Hikvision push's `detectionTarget` only says `vehicle`/`human` on t
and the flagged-category set are **site config** (a minivan-heavy site tunes the noise down).
- CPU: a second model per frame on the i5-8500 — analyse one frame per vehicle, not every push.
**As built (2026-09-06) — the app plumbing; the model is the open half.** Decisions from the user:
a flagged downgrade is *recorded only* (no reason prompt), and Setup maps the vision vocabulary
onto the site's own categories ("car, sedan, hatchback → Vetura").
- **Vocabulary.** `VEHICLE_CLASSES` in `@parking/shared` (car, sedan, hatchback, suv, minivan,
pickup, van, truck, bus, motorcycle). The service's `/analyze` `vehicle.body_type` +
`confidence` carry it; the Node client normalises and drops anything outside the list.
- **Record.** `snapshot.ts` writes the read into the same unsigned `device_events` row as the plate
(or a row of its own when the plate was unreadable); `vehicleForIdentity()` resolves it like the
plate (entry over exit, newest first). Never on the ledger by itself.
- **Mapping + threshold.** `carwash_categories.vision_classes` (JSON list) and
`carwash_config.vision_threshold` (default 0.8; signed `config_change carwash.visionThreshold`
when it moves). Migration 0030.
- **Desk.** The ticket lookup returns `vision` + `suggestedCategoryId`; the intake pre-selects it
and shows "Camera saw SUV 91% → SUV" with the snapshot thumbnail; the operator may change it.
- **Flag.** On intake, if the mapped category prices HIGHER than the chosen one for that service
and the read is at or above the threshold → one `anomaly` (`carwash.categoryDowngrade`, both
categories, both prices, operator, snapshotId) and `downgrade_event_id` on the order. Equal,
upgrade, unsure or unmapped reads flag nothing. The order is always created.
- **Model — NOT built.** No bundled recognizer produces `body_type` yet, so today the desk shows
nothing and nothing is flagged. Phase A = a COCO detector on Apache-2.0 ONNX weights (car /
truck / bus / motorcycle, plus the vehicle crop); Phase B = the body-type classifier trained on
the pilot's own frames — every wash order is a labelled frame (entry snapshot + the category a
person chose), so the dataset builds itself on park-2. Reports (discrepancies per operator per
shift) wait for the first real reads.
## Car Wash — the pilot module (settled 2026-09-05)
- **Car Wash is the pilot for the registry (settled).** It is built *as* the first module, and