Pre-generate all thumbnails up-front, not on scroll

After every scan, automatically kick off a background thread that
generates a JPEG thumbnail for every file in a duplicate group and
caches it locally at /data/thumbs/. Idempotent — already-cached files
are skipped.

New endpoints:
  POST /api/thumbs/generate            — start pre-gen for all files
  POST /api/thumbs/generate?only_in_groups=true  — only dup-group files
  GET  /api/thumbs/status              — progress (total/done/skipped/failed)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

app/main.py

@@ -116,11 +116,16 @@ def scan_start(body: ScanStartBody):
         stats={},
     )
 
-    thread = threading.Thread(
-        target=sc.run_scan,
-        args=(body.folder_path, scan_id, mode),
-        daemon=True,
-    )
+    def _scan_then_thumbs():
+        try:
+            sc.run_scan(body.folder_path, scan_id, mode)
+        finally:
+            # Kick off thumbnail pre-generation immediately when scan ends.
+            # Limited to files actually in duplicate groups — that's the gallery
+            # view and the only place thumbs are looked at.
+            _start_thumb_thread(only_in_groups=True)
+
+    thread = threading.Thread(target=_scan_then_thumbs, daemon=True)
     thread.start()
 
     return {"scan_id": scan_id}
@@ -629,6 +634,106 @@ def clear_thumb_cache():
     return {"cleared": True}
 
 
+# ── Bulk thumbnail pre-generation ────────────────────────────────────────────
+
+thumb_state: dict = {
+    "status": "idle",       # idle | running | done | error
+    "total": 0,
+    "done": 0,
+    "skipped": 0,           # already cached
+    "failed": 0,
+    "current": "",
+    "started_at": None,
+    "completed_at": None,
+}
+_thumb_thread_lock = threading.Lock()
+
+
+def _generate_all_thumbs(only_in_groups: bool = False):
+    """Walk every file and generate any missing thumbnail.
+
+    Runs in a background thread. Idempotent — already-cached files are
+    counted as skipped, not regenerated.
+    """
+    import time
+    from datetime import datetime
+    thumb_state.update(
+        status="running", total=0, done=0, skipped=0, failed=0,
+        current="", started_at=datetime.utcnow().isoformat() + "Z",
+        completed_at=None,
+    )
+    try:
+        con = get_db()
+        cur = con.cursor()
+        if only_in_groups:
+            cur.execute("""
+                SELECT DISTINCT f.id, f.path, f.extension
+                FROM files f
+                JOIN duplicate_members dm ON dm.file_id = f.id
+            """)
+        else:
+            cur.execute("SELECT id, path, extension FROM files")
+        files = cur.fetchall()
+        con.close()
+        thumb_state["total"] = len(files)
+
+        for r in files:
+            fid = r["id"]
+            path = r["path"]
+            ext = (r["extension"] or "").lower()
+            cached = _thumb_cache_path(fid)
+
+            thumb_state["current"] = path or ""
+
+            if os.path.isfile(cached) and os.path.getsize(cached) > 0:
+                thumb_state["skipped"] += 1
+            elif not path or not os.path.isfile(path):
+                thumb_state["failed"] += 1
+            elif _generate_thumb(path, cached, ext):
+                thumb_state["done"] += 1
+            else:
+                thumb_state["failed"] += 1
+
+            # Yield occasionally so the API stays responsive
+            if (thumb_state["done"] + thumb_state["skipped"] + thumb_state["failed"]) % 50 == 0:
+                time.sleep(0)
+
+        from datetime import datetime as _dt
+        thumb_state["status"] = "done"
+        thumb_state["completed_at"] = _dt.utcnow().isoformat() + "Z"
+        thumb_state["current"] = ""
+    except Exception as e:
+        thumb_state["status"] = "error"
+        thumb_state["current"] = f"error: {e}"
+
+
+def _start_thumb_thread(only_in_groups: bool = False) -> bool:
+    """Start the background generator if not already running. Returns True if started."""
+    with _thumb_thread_lock:
+        if thumb_state["status"] == "running":
+            return False
+        t = threading.Thread(
+            target=_generate_all_thumbs,
+            args=(only_in_groups,),
+            daemon=True,
+        )
+        t.start()
+        return True
+
+
+@app.post("/api/thumbs/generate")
+def generate_thumbs(only_in_groups: bool = Query(False)):
+    """Pre-generate thumbnails for every file (or only files in a duplicate group)."""
+    if not _start_thumb_thread(only_in_groups):
+        raise HTTPException(409, "Thumbnail generation already in progress")
+    return {"status": "started"}
+
+
+@app.get("/api/thumbs/status")
+def thumbs_status():
+    return dict(thumb_state)
+
+
 @app.get("/api/files/{file_id}")
 def get_file_meta(file_id: int):
     con = get_db()

debian/build-deb.sh

@@ -13,7 +13,7 @@ BUILD_DIR="$REPO_ROOT/build/deb"
 
 # ── Config ────────────────────────────────────────────────────────────────────
 PKG_NAME="dupfinder"
-PKG_VERSION="1.0.8"
+PKG_VERSION="1.0.9"
 PKG_ARCH="amd64"
 DEB_FILE="${PKG_NAME}_${PKG_VERSION}_${PKG_ARCH}.deb"