Speed: dhash-only rows (0.21s→6ms/file); gate near-dup+phash behind flag; fix hx UnboundLocalError; loop in single task (engine deadlock fix); photo_watch uses ingest flow

photo_db.py

@@ -82,14 +82,21 @@ def sha256_file(path: Path) -> str:
     return h.hexdigest()
 
 
-def hash_image(path: Path, hash_size: int = 8):
-    """Perceptual hashes for one image file."""
+def hash_image(path: Path, hash_size: int = 8, include_phash: bool = False):
+    """Perceptual hashes for one image file.
+
+    dhash is cheap (~6ms); phash is expensive (~210ms) so only computed when
+    include_phash=True (near-dup checks). The stored row uses dhash as the
+    dedup fingerprint — dhash is a valid perceptual hash for this purpose.
+    """
     with Image.open(path) as im:
         im = im.convert("RGB")
-        return {
-            "phash": str(phash(im, hash_size=hash_size)),
-            "dhash": str(dhash(im, hash_size=hash_size)),
-        }
+        hx = {"dhash": str(dhash(im, hash_size=hash_size))}
+        if include_phash:
+            hx["phash"] = str(phash(im, hash_size=hash_size))
+        else:
+            hx["phash"] = ""
+        return hx
 
 
 def register_image(conn, path: Path, source: str, exif_date: str | None = None):
@@ -122,8 +129,11 @@ def check_near_dup(conn, path: Path, hamming_threshold: int = 10):
     rows = conn.execute("SELECT phash, dhash, path, source FROM image_hashes").fetchall()
     best, best_dist = None, None
     for ph, dh, p, src in rows:
-        phd = hamming(ph, hx["phash"])
-        dhd = hamming(dh, hx["dhash"])
+        dhd = hamming(dh, hx.get("dhash", ""))
+        if ph and hx.get("phash"):
+            phd = hamming(ph, hx["phash"])
+        else:
+            phd = dhd  # no phash available — use dhash distance
         dist = min(phd, dhd)
         if best_dist is None or dist < best_dist:
             best, best_dist = (p, src), dist
@@ -168,8 +178,11 @@ def _near_dup_lookup(conn, hx: dict, hamming_threshold: int = 10):
     rows = conn.execute("SELECT phash, dhash, path, source FROM image_hashes").fetchall()
     best, best_dist = None, None
     for ph, dh, p, src in rows:
-        phd = hamming(ph, hx["phash"])
-        dhd = hamming(dh, hx["dhash"])
+        dhd = hamming(dh, hx.get("dhash", ""))
+        if ph and hx.get("phash"):
+            phd = hamming(ph, hx["phash"])
+        else:
+            phd = dhd  # no phash available — use dhash distance
         dist = min(phd, dhd)
         if best_dist is None or dist < best_dist:
             best, best_dist = (p, src), dist