fix(collector,trainer): migrate an existing collector DB on open; trainer handlers answer 500 JSON

The reviewer host's collector.sqlite was created by an earlier build, before the
`kind` column. CREATE TABLE IF NOT EXISTS shapes only a new database, so every query
naming the column failed: the collector's /health (container unhealthy), every
booth ingest, and the trainer's readiness — whose stdlib server printed the
traceback and dropped the socket, which the collector could only render as
"trainer not reachable: fetch failed". Nine days like that.

- CollectorDb.#migrate(): PRAGMA table_info against the list of columns added
  since the first deploy; ALTER TABLE ADD COLUMN for each missing one (all
  nullable or defaulted). Append to that list whenever a column joins the CREATE.
  Test replays the original schema: health, ingest, stats, a legacy row reads
  back with the defaults.
- Trainer Handler._guarded(): any unexpected exception → 500 JSON naming it,
  never a dropped connection; /health keeps answering. Test drives readiness
  against an old-schema DB.
- The collector's training status proxy includes the trainer's error text.

Wiki: the incident and the schema rule (vision-review-outbox), what the message
means (bodytype-classifier-training), log. Deploy: the new collector migrates on
start; nothing manual.

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

apps/collector/src/app.test.ts

@@ -151,3 +151,46 @@ describe("config", () => {
     expect(() => parseBoothTokens("nocolon")).toThrow(/bad pair/);
   });
 });
+
+describe("schema migration", () => {
+  it("opens a database created before the `kind` column and adds the missing columns, so ingest and stats work", async () => {
+    // art-docker-station, 2026-09-16: the volume's DB predated `kind`; CREATE TABLE IF NOT
+    // EXISTS left it alone, and /health, every ingest and the trainer's readiness failed
+    // with "no such column: kind". Replay: a file with the ORIGINAL column set.
+    const { default: Database } = await import("better-sqlite3");
+    const file = path.join(dir, "old.sqlite");
+    const old = new Database(file);
+    old.exec(`CREATE TABLE items (
+      id TEXT PRIMARY KEY, booth TEXT NOT NULL, order_ref TEXT NOT NULL, at TEXT NOT NULL,
+      service TEXT NOT NULL, vision_class TEXT NOT NULL, vision_confidence REAL NOT NULL,
+      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)`);
+    old.prepare(
+      "INSERT INTO items (id, booth, order_ref, at, service, vision_class, vision_confidence, image_width, image_height, plate_blurred, image_path, received_at) VALUES (?,?,?,?,?,?,?,?,?,?,?,?)",
+    ).run("legacy-1", "booth-7", "o-0", "2026-09-01T00:00:00.000Z", "Standard", "suv", 0.8, 100, 100, 1, "crops/legacy-1.jpg", "2026-09-01T00:00:00.000Z");
+    old.close();
+
+    const legacy = await buildCollector({ host: "127.0.0.1", port: 0, dataDir: dir, boothTokens: TOKENS, reviewer: REVIEWER, trainerUrl: null }, { dbFile: file });
+    await legacy.ready();
+    try {
+      const health = await legacy.inject({ method: "GET", url: "/health" });
+      expect(health.statusCode).toBe(200);
+      expect(health.json()).toMatchObject({ ok: true, booths: 1, pending: 1 });
+
+      const { body, type } = multipart({ meta: JSON.stringify(meta({ item: "item-new" })) }, JPEG);
+      const r = await legacy.inject({ method: "POST", url: "/ingest", headers: { authorization: `Bearer ${TOKENS.get("booth-7")!}`, "content-type": type }, payload: body });
+      expect(r.statusCode).toBe(201);
+
+      const stats = await legacy.inject({ method: "GET", url: "/api/stats", headers: { authorization: basic } });
+      expect(stats.statusCode).toBe(200);
+
+      // The legacy row reads back with the defaults the new columns carry.
+      const cols = new Database(file, { readonly: true }).prepare("PRAGMA table_info(items)").all() as { name: string }[];
+      expect(cols.map((c) => c.name)).toEqual(expect.arrayContaining(["kind", "operator_ref", "operator_classes", "vision_category_id", "downgraded"]));
+      const legacyRow = new Database(file, { readonly: true }).prepare("SELECT kind, operator_classes, downgraded FROM items WHERE id = 'legacy-1'").get() as Record<string, unknown>;
+      expect(legacyRow).toEqual({ kind: "wash", operator_classes: "[]", downgraded: 0 });
+    } finally {
+      await legacy.close();
+    }
+  });
+});

apps/collector/src/app.ts

@@ -253,7 +253,18 @@ export async function buildCollector(cfg: CollectorConfig, opts: { dbFile?: stri
     try {
       const get = async (p: string) => {
         const r = await fetch(trainer + p, { signal: AbortSignal.timeout(15_000) });
-        if (!r.ok) throw new Error(`${p} → HTTP ${r.status}`);
+        if (!r.ok) {
+          // Surface the trainer's own error text (its handlers answer 500 JSON), so the
+          // reviewer reads "no such column: kind", not just a status code.
+          const detail = await r.text().then((t) => {
+            try {
+              return String((JSON.parse(t) as { error?: unknown }).error ?? t);
+            } catch {
+              return t;
+            }
+          }, () => "");
+          throw new Error(`${p} → HTTP ${r.status}${detail ? `: ${detail.slice(0, 300)}` : ""}`);
+        }
         return r.json() as Promise<Record<string, unknown>>;
       };
       const [health, readiness, versions, jobs] = await Promise.all([get("/health"), get("/readiness"), get("/versions"), get("/jobs")]);

apps/collector/src/db.ts

@@ -71,6 +71,39 @@ export class CollectorDb {
       CREATE INDEX IF NOT EXISTS items_pending ON items (reviewed_at, received_at);
       CREATE INDEX IF NOT EXISTS items_booth ON items (booth, received_at);
     `);
+    this.#migrate();
+  }
+
+  /** Columns added after the first deploy, with the DDL that adds them to an EXISTING
+   *  table. `CREATE TABLE IF NOT EXISTS` above only shapes a NEW database; a volume that
+   *  was created by an earlier build keeps its old columns, and every query naming a new
+   *  one then fails ("no such column: kind" — art-docker-station, 2026-09-16: the
+   *  collector's /health, every ingest, and the trainer's readiness all broke on a DB
+   *  from before `kind`). Each entry must be addable to a populated table, i.e. nullable
+   *  or carrying a DEFAULT. Append here whenever a column joins the CREATE above. */
+  static readonly #ADDED_COLUMNS: ReadonlyArray<readonly [name: string, ddl: string]> = [
+    ["kind", "TEXT NOT NULL DEFAULT 'wash'"],
+    ["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 '[]'"],
+    ["vision_category_id", "TEXT"],
+    ["downgraded", "INTEGER NOT NULL DEFAULT 0"],
+  ];
+
+  /** Bring an existing `items` table up to the current column set (idempotent). */
+  #migrate(): void {
+    const present = new Set(
+      (this.#db.prepare("PRAGMA table_info(items)").all() as { name: string }[]).map((c) => c.name),
+    );
+    for (const [name, ddl] of CollectorDb.#ADDED_COLUMNS) {
+      if (!present.has(name)) this.#db.exec(`ALTER TABLE items ADD COLUMN ${name} ${ddl}`);
+    }
+  }
+
+  /** The current column names of `items` (for tests and diagnostics). */
+  columns(): string[] {
+    return (this.#db.prepare("PRAGMA table_info(items)").all() as { name: string }[]).map((c) => c.name);
   }
 
   close(): void {