mcp-server/src/legal_mcp/services/digest_library.py

@@ -213,7 +213,23 @@ async def enrich_digest(digest_id: UUID | str, progress: ProgressCb | None = Non
         fields["subject_tags"] = extracted["subject_tags"]
 
     if fields:
-        await db.update_digest(digest_id, **fields)
+        try:
+            await db.update_digest(digest_id, **fields)
+        except Exception as e:
+            # The same yomon issue can arrive as two different PDFs (re-sent /
+            # forwarded twice → different bytes → content_hash dedup misses it),
+            # but the yomon_number is unique. The extracted number then collides
+            # on uq_digests_yomon_number. This row is a duplicate of an already-
+            # ingested yomon → drop it so it isn't retried forever by the cron.
+            if "uq_digests_yomon_number" in str(e):
+                await db.delete_digest(digest_id)
+                logger.info(
+                    "digest %s is a duplicate yomon (%s) — deleted",
+                    digest_id, fields.get("yomon_number"),
+                )
+                return {"status": "duplicate", "digest_id": str(digest_id),
+                        "yomon_number": fields.get("yomon_number")}
+            raise
     merged = await db.get_digest(digest_id)
 
     await progress("embedding", 75, "מחשב embedding")