feat: cache failed ffprobe scans with scanner_version and exclude downloading items from scan queue to prevent incomplete metadata

Store failed ffprobe attempts in media_cache with scanner_version/audio_languages/subtitle_languages/external_subtitle_files/video_codec/size/error fields. Add comment explaining mtime-based invalidation triggers automatic retry. Filter out downloading items from radarr/sonarr/missing scan paths using not row.get("downloading") check to prevent scanning incomplete files

app.py

@@ -913,8 +913,18 @@ def scan_one(path):
     p = Path(path)
     if not p.exists(): data = {"error": f"Datei nicht gefunden: {p}"}
     else:
-        try: data = run_ffprobe(str(p)); log.info("Gescannt: %s", p)
+        try:
-        except Exception as exc: data = {"error": str(exc)}; log.error("Scanfehler für %s: %s", p, error_summary(exc))
+            data = run_ffprobe(str(p)); log.info("Gescannt: %s", p)
+        except Exception as exc:
+            # Cache failed probes as completed attempts. A changed mtime will
+            # invalidate this entry automatically and trigger a retry later.
+            data = {
+                "scanner_version": SCANNER_VERSION,
+                "audio_languages": [], "subtitle_languages": [],
+                "external_subtitle_files": [str(file) for file in external_subtitle_files(str(p))],
+                "video_codec": "—", "size": 0, "error": error_summary(exc),
+            }
+            log.error("Scanfehler für %s: %s", p, error_summary(exc))
         mtime = p.stat().st_mtime
         con = db(); con.execute("INSERT INTO media_cache(path,mtime,data,scanned_at) VALUES(?,?,?,?) ON CONFLICT(path) DO UPDATE SET mtime=excluded.mtime,data=excluded.data,scanned_at=excluded.scanned_at", (str(p), mtime, json.dumps(data), datetime.utcnow().isoformat())); con.commit(); con.close()
     return data
@@ -1005,16 +1015,16 @@ def start_scan(source, force=False, rows_snapshot=None, series_snapshot=None):
             paths = []
             if source == "radarr":
                 for row in rows_snapshot if rows_snapshot is not None else radarr_rows():
-                    if row["local_path"] != "—" and row["pending"]: paths.append(row["local_path"])
+                    if row["local_path"] != "—" and row["pending"] and not row.get("downloading"): paths.append(row["local_path"])
             elif source == "sonarr":
                 for group in series_snapshot if series_snapshot is not None else sonarr_groups():
-                    paths.extend(r["local_path"] for r in group["episodes"] if r["local_path"] != "—" and r["pending"])
+                    paths.extend(r["local_path"] for r in group["episodes"] if r["local_path"] != "—" and r["pending"] and not r.get("downloading"))
             else:
                 for row in rows_snapshot if rows_snapshot is not None else radarr_rows():
-                    if row["local_path"] != "—" and is_german_review_candidate(row) and not has_german_track(row): paths.append(row["local_path"])
+                    if row["local_path"] != "—" and is_german_review_candidate(row) and not row.get("downloading") and not has_german_track(row): paths.append(row["local_path"])
                 if SONARR_URL and SONARR_API_KEY:
                     for group in series_snapshot if series_snapshot is not None else sonarr_groups():
-                        paths.extend(r["local_path"] for r in group["episodes"] if r["local_path"] != "—" and is_german_review_candidate(r) and not has_german_track(r))
+                        paths.extend(r["local_path"] for r in group["episodes"] if r["local_path"] != "—" and is_german_review_candidate(r) and not r.get("downloading") and not has_german_track(r))
             with job_lock: jobs[source]["total"] = len(paths)
             futures = [scan_executor.submit(scan_one, path) for path in paths]
             for future in as_completed(futures):