feat(trainer): phase-B body-type classifier — trainer job on the collector host + the classifier stage on the booth

apps/trainer (parking-trainer): inspect / train / evaluate / publish. Reads the wash
collector's SQLite + crops read-only off its volume; time split (validation = newest
slice); thin classes dropped; damped class weights; `features` mode (frozen ImageNet
backbone, on-disk feature cache, seconds to retrain) and `finetune` mode (light
augmentation). CPU-only torch from PyTorch's wheel index. ONNX export checked against
the torch model; NO model file below the validation floor (exit 3, report still written);
exit 2 = not enough labels. `evaluate` scores a shipped model on labels reviewed after
training + the unlabelled pile; `publish` PUTs a version folder to a Gitea generic package.
Light core deps; the `train` extra is heavy — CI syncs without it, torch tests skip.

apps/vision: BodyTypeClassifier (bodytype.onnx + sidecar = the preprocessing contract:
crop margin, input size, RGB 0-255, normalisation inside the graph) and
RefinedVehicleDetector over YOLOX — refines only `car` or a class the classifier trained
on, min-confidence, `detector_class` on the result; path set but no file = phase B off
without an error; a broken file is a health detail. models/bodytype.version (tracked,
empty) pins the published version the Dockerfile fetches at build (BuildKit secret;
a pin that cannot be fetched fails the build). Verified: a trainer model gives identical
probabilities inside the vision service; both images built and smoke-tested.

Delivery: parking-trainer image in build-images.yml, the `trainer` compose profile on the
collector stack (CPU, read-only data, TRAINER_OUT), commented TRAINER_OUT/PUBLISH_TOKEN in
the wash-collector stack, .dockerignore for both Python contexts, trainer deps synced in CI.

Wiki: bodytype-classifier-training rewritten as built (+ one fleet model not per site,
secrets/access, where the crops live), opencv-anpr-service §Phase B, vision-review-outbox,
vision-service-packaging, fleet-deployment-komodo, index, log.

Claude-Session: https://claude.ai/code/session_01FWncR69HgGPuei1dLrW3cU

apps/trainer/tests/conftest.py

@@ -0,0 +1,102 @@
+"""A synthetic collector volume: the collector's `items` table (same DDL as apps/collector
+src/db.ts) + JPEG crops. Classes are told apart by COLOUR so even a random-init backbone's
+features separate them — the tests check the plumbing (split, floor, export, sidecar),
+not accuracy on real cars."""
+
+from __future__ import annotations
+
+import sqlite3
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
+
+import numpy as np
+import pytest
+
+DDL = """
+CREATE TABLE IF NOT EXISTS items (
+  id TEXT PRIMARY KEY, booth TEXT NOT NULL, kind TEXT NOT NULL DEFAULT 'wash',
+  order_ref TEXT NOT NULL, at TEXT NOT NULL, operator_ref TEXT NOT NULL DEFAULT '',
+  operator_category_id TEXT NOT NULL DEFAULT '', operator_category_name TEXT NOT NULL DEFAULT '',
+  operator_classes TEXT NOT NULL DEFAULT '[]', service TEXT NOT NULL, vision_class TEXT NOT NULL,
+  vision_confidence REAL NOT NULL, vision_category_id TEXT, downgraded INTEGER NOT NULL DEFAULT 0,
+  image_width INTEGER NOT NULL, image_height INTEGER NOT NULL, plate_blurred INTEGER NOT NULL,
+  image_path TEXT NOT NULL, received_at TEXT NOT NULL, review_label TEXT, reviewed_at TEXT, reviewer TEXT
+);
+"""
+
+COLOURS = {"sedan": (200, 40, 40), "suv": (40, 200, 40), "van": (40, 40, 200), "truck": (200, 200, 40)}
+
+
+def write_jpeg(path: Path, colour: tuple[int, int, int], rng: np.random.Generator) -> None:
+    import cv2
+
+    path.parent.mkdir(parents=True, exist_ok=True)
+    h, w = int(rng.integers(120, 200)), int(rng.integers(160, 260))
+    img = np.empty((h, w, 3), np.uint8)
+    img[:] = colour[::-1]  # BGR
+    noise = rng.integers(-20, 20, size=img.shape, dtype=np.int16)
+    img = np.clip(img.astype(np.int16) + noise, 0, 255).astype(np.uint8)
+    cv2.imwrite(str(path), img, [cv2.IMWRITE_JPEG_QUALITY, 85])
+
+
+@pytest.fixture
+def collector_dir(tmp_path: Path) -> Path:
+    """40 labelled crops per class for sedan/suv/van, 5 for truck (below the minimum), a few
+    unusable, a few pending, one labelled row whose file is missing."""
+    rng = np.random.default_rng(1)
+    con = sqlite3.connect(tmp_path / "collector.sqlite")
+    con.executescript(DDL)
+    t0 = datetime(2026, 9, 1, tzinfo=timezone.utc)
+    n = 0
+
+    def add(label: str | None, reviewed: bool, kind: str = "wash", missing: bool = False) -> None:
+        nonlocal n
+        n += 1
+        item = f"item-{n:04d}"
+        rel = f"crops/booth-2/{item}.jpg"
+        colour = COLOURS.get(label or "sedan", (128, 128, 128))
+        if not missing:
+            write_jpeg(tmp_path / rel, colour, rng)
+        at = (t0 + timedelta(minutes=10 * n)).isoformat().replace("+00:00", "Z")
+        reviewed_at = (
+            (t0 + timedelta(days=1, minutes=n)).isoformat().replace("+00:00", "Z") if reviewed else None
+        )
+        con.execute(
+            "INSERT INTO items (id, booth, kind, order_ref, at, service, vision_class, vision_confidence, "
+            "image_width, image_height, plate_blurred, image_path, received_at, review_label, "
+            "reviewed_at, reviewer) "
+            "VALUES (?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?)",
+            (
+                item,
+                "booth-2",
+                kind,
+                "o",
+                at,
+                "wash",
+                "car" if label != "truck" else "truck",
+                0.9,
+                200,
+                150,
+                1,
+                rel,
+                at,
+                label if reviewed else None,
+                reviewed_at,
+                "reviewer" if reviewed else None,
+            ),
+        )
+
+    # Interleaved in time so every class exists on both sides of the time split.
+    for i in range(40):
+        for label in ("sedan", "suv", "van"):
+            add(label, True)
+        if i % 8 == 0:
+            add("truck", True)
+    add("unusable", True)
+    add("unusable", True)
+    add("sedan", True, missing=True)
+    for _ in range(6):
+        add(None, False, kind="entry")
+    con.commit()
+    con.close()
+    return tmp_path

apps/trainer/tests/test_data.py

@@ -0,0 +1,98 @@
+"""Data rules, torch-free: labels, the time split, thin classes, weights, the report."""
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+
+from trainer.cli import main
+from trainer.data import (
+    class_weights,
+    load_labelled,
+    load_reviewed_since,
+    load_unlabelled,
+    make_split,
+    summarise,
+)
+from trainer.preprocess import CROP_MARGIN, Sidecar, load_input
+from trainer.report import compute_metrics, render_report
+
+
+def test_loads_only_reviewed_usable_rows_with_a_crop_on_disk(collector_dir: Path) -> None:
+    samples, missing = load_labelled(collector_dir)
+    assert missing == 1  # the labelled row whose file is gone
+    assert len(samples) == 125  # 3×40 + 5 trucks; unusable and pending excluded
+    assert all(s.path.is_file() for s in samples)
+    assert {s.label for s in samples} == {"sedan", "suv", "van", "truck"}
+    assert summarise(samples)["byClass"] == {"sedan": 40, "suv": 40, "van": 40, "truck": 5}
+    assert len(load_unlabelled(collector_dir)) == 6
+    assert len(load_reviewed_since(collector_dir, "2026-09-02T00:00:00Z")) == 125
+    assert load_reviewed_since(collector_dir, "2030-01-01T00:00:00Z") == []
+
+
+def test_split_is_by_time_and_drops_thin_classes(collector_dir: Path) -> None:
+    samples, _ = load_labelled(collector_dir)
+    split = make_split(samples, val_fraction=0.2, min_per_class=20)
+    assert split.classes == ("sedan", "suv", "van")  # canonical order, truck dropped
+    assert split.dropped == {"truck": 5}
+    assert len(split.train) + len(split.val) == 120
+    assert len(split.val) == 24
+    assert max(s.at for s in split.train) < min(s.at for s in split.val)  # newest = validation
+    assert all(v > 0 for v in split.counts("val").values())
+
+
+def test_class_weights_lean_against_imbalance_but_gently(collector_dir: Path) -> None:
+    samples, _ = load_labelled(collector_dir)
+    vans = [s for s in samples if s.label == "van"]
+    keep = set(vans[::10])  # 4 of 40 vans survive
+    split = make_split([s for s in samples if s.label != "van" or s in keep], 0.2, 3)
+    w = dict(zip(split.classes, class_weights(split), strict=True))
+    assert w["van"] > w["sedan"] > 0  # the rare class weighs more
+    assert w["van"] / w["sedan"] < 4  # but not the full inverse ratio (damped)
+    assert abs(sum(w.values()) / len(w) - 1.0) < 1e-9
+
+
+def test_metrics_and_report() -> None:
+    classes = ("sedan", "suv")
+    m = compute_metrics(classes, [0, 0, 1, 1], [0, 1, 1, 1], camera=["car"] * 4)
+    assert m.accuracy == 0.75
+    assert m.per_class["sedan"].recall == 0.5 and m.per_class["suv"].precision == 2 / 3
+    assert m.confusion == [[1, 1], [0, 2]]
+    assert m.camera_agreement == 0.0
+    text = render_report(
+        version="v1",
+        trained_at="t",
+        mode="features",
+        backbone="resnet18",
+        epochs=3,
+        classes=classes,
+        train_counts={"sedan": 10, "suv": 8},
+        val_counts={"sedan": 2, "suv": 2},
+        dropped={"truck": 2},
+        missing_files=1,
+        weights=[0.9, 1.1],
+        metrics=m,
+        min_accuracy=0.85,
+        written=False,
+    )
+    assert "MODEL NOT WRITTEN" in text and "| **sedan** | 1 | 1 |" in text and "truck (2)" in text
+
+
+def test_preprocess_contract(tmp_path: Path, collector_dir: Path) -> None:
+    samples, _ = load_labelled(collector_dir)
+    x = load_input(samples[0].path, 32)
+    assert x.shape == (3, 32, 32) and x.dtype.name == "float32" and 0 <= x.min() and x.max() <= 255
+    assert x[0].mean() > x[2].mean()  # a sedan crop is red: RGB order, not BGR
+    assert load_input(tmp_path / "nope.jpg", 32) is None
+    side = Sidecar(version="v1", classes=["sedan", "suv"])
+    side.write(tmp_path / "s.json")
+    back = Sidecar.read(tmp_path / "s.json")
+    assert back == side and back.crop_margin == CROP_MARGIN == 0.08 and back.normalization == "in-graph"
+
+
+def test_inspect_prints_the_run_shape(collector_dir: Path, capsys) -> None:  # type: ignore[no-untyped-def]
+    assert main(["inspect", "--data", str(collector_dir)]) == 0
+    out = json.loads(capsys.readouterr().out)
+    assert out["ready"] is True and out["run"]["classes"] == ["sedan", "suv", "van"]
+    assert out["run"]["dropped"] == {"truck": 5} and out["missingCrops"] == 1
+    assert main(["inspect", "--data", str(collector_dir), "--min-per-class", "100"]) == 2

apps/trainer/tests/test_train.py

@@ -0,0 +1,155 @@
+"""The training job end to end on the synthetic volume — needs the `train` extra (torch);
+skipped where it is not installed (CI syncs without it, like the vision service)."""
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+
+import numpy as np
+import pytest
+
+torch = pytest.importorskip("torch")
+
+from trainer.cli import main  # noqa: E402
+from trainer.infer import OnnxClassifier  # noqa: E402
+from trainer.preprocess import Sidecar  # noqa: E402
+
+COMMON = ["--no-pretrained", "--input-size", "64", "--no-cache", "--seed", "3"]
+
+
+def test_features_run_writes_model_sidecar_report_and_evaluates(
+    collector_dir: Path, tmp_path: Path, capsys
+) -> None:  # type: ignore[no-untyped-def]
+    out = tmp_path / "out"
+    rc = main(
+        [
+            "train",
+            "--data",
+            str(collector_dir),
+            "--out",
+            str(out),
+            "--version",
+            "vtest",
+            "--mode",
+            "features",
+            "--epochs",
+            "150",
+            "--min-accuracy",
+            "0.0",
+            *COMMON,
+        ]
+    )
+    assert rc == 0
+    d = out / "vtest"
+    assert {p.name for p in d.iterdir()} == {"bodytype.onnx", "bodytype.json", "report.md", "metrics.json"}
+    side = Sidecar.read(d / "bodytype.json")
+    assert side.classes == ["sedan", "suv", "van"] and side.input_size == 64 and side.mode == "features"
+    assert side.labels == {"train": 96, "val": 24} and side.metrics["floor"] == 0.0
+    metrics = json.loads((d / "metrics.json").read_text())
+    assert metrics["n"] == 24 and metrics["onnx_agreement"] == 1.0
+    # Colour-coded classes: even a random backbone's pooled features separate them.
+    assert metrics["accuracy"] >= 0.9
+    report = (d / "report.md").read_text()
+    assert (
+        "MODEL WRITTEN" in report
+        and "truck (5)" in report
+        and "crop is missing on disk (skipped): 1" in report
+    )
+
+    # The exported graph takes raw 0–255 RGB and answers by itself.
+    clf = OnnxClassifier(d / "bodytype.onnx")
+    probs, kept = clf.predict_files(
+        [s for s in sorted((collector_dir / "crops" / "booth-2").glob("*.jpg"))][:6]
+    )
+    assert probs.shape == (6, 3) and kept == [0, 1, 2, 3, 4, 5]
+    assert np.allclose(probs.sum(axis=1), 1.0, atol=1e-4)
+
+    # evaluate: labels reviewed after training (none — the fixture's reviews predate it) and the
+    # unlabelled pile (6 entry samples).
+    capsys.readouterr()
+    assert main(["evaluate", "--data", str(collector_dir), "--model", str(d / "bodytype.onnx")]) == 0
+    res = json.loads(capsys.readouterr().out)
+    assert res["model"] == "vtest" and res["reviewedSince"] is None
+    assert res["unlabelled"]["n"] == 6 and sum(res["unlabelled"]["predicted"].values()) == 6
+    assert (
+        main(
+            [
+                "evaluate",
+                "--data",
+                str(collector_dir),
+                "--model",
+                str(d / "bodytype.onnx"),
+                "--since",
+                "2026-09-01T00:00:00Z",
+            ]
+        )
+        == 0
+    )
+    res2 = json.loads(capsys.readouterr().out)
+    assert res2["reviewedSince"]["n"] == 125 - 5  # trucks are not a class the model knows
+
+
+def test_below_the_floor_writes_the_report_but_no_model(collector_dir: Path, tmp_path: Path) -> None:
+    out = tmp_path / "out"
+    rc = main(
+        [
+            "train",
+            "--data",
+            str(collector_dir),
+            "--out",
+            str(out),
+            "--version",
+            "vlow",
+            "--mode",
+            "features",
+            "--epochs",
+            "5",
+            "--min-accuracy",
+            "1.01",
+            *COMMON,
+        ]
+    )
+    assert rc == 3
+    d = out / "vlow"
+    assert {p.name for p in d.iterdir()} == {"report.md", "metrics.json"}
+    assert "MODEL NOT WRITTEN" in (d / "report.md").read_text()
+
+
+def test_not_enough_labels_is_exit_2(collector_dir: Path, tmp_path: Path) -> None:
+    out = tmp_path / "out"
+    rc = main(["train", "--data", str(collector_dir), "--out", str(out), "--min-per-class", "100", *COMMON])
+    assert rc == 2
+    assert not out.exists()
+
+
+def test_finetune_runs_and_uses_the_feature_cache(collector_dir: Path, tmp_path: Path) -> None:
+    out = tmp_path / "out"
+    args = [
+        "train",
+        "--data",
+        str(collector_dir),
+        "--out",
+        str(out),
+        "--mode",
+        "finetune",
+        "--backbone",
+        "mobilenet_v3_small",
+        "--epochs",
+        "1",
+        "--batch",
+        "16",
+        "--min-accuracy",
+        "0.0",
+        "--no-pretrained",
+        "--input-size",
+        "64",
+        "--seed",
+        "3",
+    ]
+    assert main([*args, "--version", "vft"]) == 0
+    cache = out / "cache" / "features-mobilenet_v3_small-64.npz"
+    assert cache.exists()
+    z = np.load(cache)
+    assert len(z["ids"]) == 96 and z["feats"].shape == (96, 576)
+    assert Sidecar.read(out / "vft" / "bodytype.json").mode == "finetune"