src/songtrace/web.py

@@ -77,7 +77,7 @@ def _cleanup_uploads(cfg: Config, job_id: str, video_path: Path | None) -> None:
     Covers are left behind: they are small, and a rebuild inherits cover_path, so
     removing one would silently strip #COVER from the rebuilt song. A rebuild can
     also inherit its parent's upload, so the directory is not always uploads/<job_id>.
-    Never raises — the caller has already marked the job done.
+    Never raises, so cleaning up cannot fail a job that otherwise succeeded.
     """
     uploads = (cfg.work_dir / "uploads").resolve()
     dirs = {uploads / job_id}
@@ -193,6 +193,7 @@ def create_app(cfg: Config, runner=run_pipeline) -> FastAPI:
                     if m := STAGE_LINE.match(msg):
                         job.stage = m[1]
 
+            status, error = "done", None
             try:
                 force_from = _prepare_rebuild(job, log)
                 _write_sidecar(job)
@@ -201,18 +202,15 @@ def create_app(cfg: Config, runner=run_pipeline) -> FastAPI:
                     job.output_dir = str(result.output_dir)
                     job.warnings = list(result.warnings)
                 _drop_superseded_output(job, log)
-                with lock:
-                    job.status = "done"
                 # uploads survive a failure so the job stays rerunnable; acquire
                 # has already copied the video into the work dir by now.
                 _cleanup_uploads(cfg, job_id, job.inp.video_path)
             except BaseException as e:
-                with lock:
-                    job.status = "failed"
-                    job.error = str(e)
-            finally:
-                with lock:
-                    job.finished_at = time.time()
+                status, error = "failed", str(e)
+            # last, and all at once: a client that sees the job finished must
+            # find everything finishing it does already done
+            with lock:
+                job.status, job.error, job.finished_at = status, error, time.time()
 
     threading.Thread(target=worker, daemon=True).start()
 

tests/test_web.py

@@ -1852,3 +1852,23 @@ def test_rebuild_all_reports_a_selected_job_that_was_since_rebuilt(tmp_path):
     body = client.post("/api/rebuild-all", data={"force_from": "pitch", "ids": [old]}).json()
     assert body == {"ids": [], "skipped": [
         {"id": old, "reason": "no longer the current job for its song"}]}
+
+
+def test_a_job_is_only_reported_finished_once_it_has_finished(tmp_path, monkeypatch):
+    """Done must mean done: a slow upload cleanup used to show a 'done' job
+    with its upload still there and no finished_at."""
+    from songtrace import web
+    real_cleanup = web._cleanup_uploads
+
+    def slow_cleanup(*args):
+        time.sleep(0.3)
+        real_cleanup(*args)
+
+    monkeypatch.setattr(web, "_cleanup_uploads", slow_cleanup)
+    client, cfg = make_client(tmp_path, ok_runner)
+    job_id = client.post("/api/jobs", data={"title": "T", "artist": "A", "lyrics": "x"},
+                         files={"video": ("v.mp4", io.BytesIO(b"data"), "video/mp4")}
+                         ).json()["id"]
+    job = wait_status(client, job_id, "done")
+    assert job["finished_at"] is not None
+    assert not (cfg.work_dir / "uploads" / job_id / "v.mp4").exists()