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/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"