Add schema migrations and scope uniqueness to the owner

Step 0 of the roadmap: everything from the moderation queue onward adds
columns, and init_db could only ever run CREATE TABLE IF NOT EXISTS, so
it could not alter a live deployment.

- Track schema state in PRAGMA user_version and run ordered migrations.
  Fresh installs create the v1 table and migrate forward, so the upgrade
  path runs on every new deployment rather than only on old ones.
- Rebuild media with UNIQUE(owner_id, file_unique_id). The old global
  unique constraint stopped two users from each saving the same file,
  which blocks public mode.
- Replace INSERT OR REPLACE with an upsert. Replacing deleted and
  reinserted the row, giving it a new id and silently invalidating any
  id the user had noted from /list.
- Give search_media an optional owner_id scope, defaulting to the
  current shared-library behaviour.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

db.py

@@ -3,58 +3,155 @@ import os
 
 DB_PATH = os.getenv("DB_PATH", "/data/media.db")
 
+# Bump this and add a matching _migrate_to_vN() when the schema changes.
+SCHEMA_VERSION = 2
+
+
+# ── schema / migrations ──────────────────────────────────────────────────────
+
+async def _table_exists(db, name: str) -> bool:
+    cursor = await db.execute(
+        "SELECT 1 FROM sqlite_master WHERE type='table' AND name=?", (name,)
+    )
+    return await cursor.fetchone() is not None
+
+
+async def _create_v1(db) -> None:
+    """The original schema. Fresh installs start here and migrate forward, so
+    the migration path is exercised on every new deployment, not just old ones."""
+    await db.execute("""
+        CREATE TABLE media (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            owner_id INTEGER NOT NULL,
+            file_id TEXT NOT NULL,
+            file_unique_id TEXT NOT NULL UNIQUE,
+            media_type TEXT NOT NULL,
+            keywords TEXT NOT NULL,
+            added_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
+        )
+    """)
+    await db.execute("CREATE INDEX IF NOT EXISTS idx_owner ON media(owner_id)")
+
+
+async def _migrate_to_v2(db) -> None:
+    """Scope uniqueness to the owner so two users can each save the same file.
+
+    SQLite cannot drop a column constraint in place, so the table is rebuilt.
+    Row ids are carried over, which keeps any /delete <id> the user noted valid.
+    """
+    await db.execute("""
+        CREATE TABLE media_v2 (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            owner_id INTEGER NOT NULL,
+            file_id TEXT NOT NULL,
+            file_unique_id TEXT NOT NULL,
+            media_type TEXT NOT NULL,
+            keywords TEXT NOT NULL,
+            added_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+            UNIQUE(owner_id, file_unique_id)
+        )
+    """)
+    await db.execute("""
+        INSERT INTO media_v2 (id, owner_id, file_id, file_unique_id, media_type, keywords, added_at)
+        SELECT id, owner_id, file_id, file_unique_id, media_type, keywords, added_at FROM media
+    """)
+    await db.execute("DROP TABLE media")
+    await db.execute("ALTER TABLE media_v2 RENAME TO media")
+    await db.execute("CREATE INDEX IF NOT EXISTS idx_owner ON media(owner_id)")
+
+
+MIGRATIONS = {
+    2: _migrate_to_v2,
+}
+
 
 async def init_db():
     async with aiosqlite.connect(DB_PATH) as db:
-        await db.execute("""
+        cursor = await db.execute("PRAGMA user_version")
-            CREATE TABLE IF NOT EXISTS media (
+        version = (await cursor.fetchone())[0]
-                id INTEGER PRIMARY KEY AUTOINCREMENT,
+
-                owner_id INTEGER NOT NULL,
+        # A pre-versioning deployment also reports 0, so tell the two apart by
-                file_id TEXT NOT NULL,
+        # whether the table is already there.
-                file_unique_id TEXT NOT NULL UNIQUE,
+        if version == 0:
-                media_type TEXT NOT NULL,
+            if not await _table_exists(db, "media"):
-                keywords TEXT NOT NULL,
+                await _create_v1(db)
-                added_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
+            version = 1
-            )
+            await db.execute(f"PRAGMA user_version = {version}")
-        """)
+
-        await db.execute("CREATE INDEX IF NOT EXISTS idx_owner ON media(owner_id)")
+        for target in range(version + 1, SCHEMA_VERSION + 1):
+            migrate = MIGRATIONS.get(target)
+            if migrate is None:
+                continue
+            await migrate(db)
+            await db.execute(f"PRAGMA user_version = {target}")
+
         await db.commit()
 
 
+# ── writes ───────────────────────────────────────────────────────────────────
+
 async def add_media(owner_id: int, file_id: str, file_unique_id: str, media_type: str, keywords: list[str]):
     kw = ",".join(k.strip().lower() for k in keywords if k.strip())
     async with aiosqlite.connect(DB_PATH) as db:
+        # Upsert rather than INSERT OR REPLACE: replacing would delete and
+        # reinsert the row, handing it a new id and breaking /delete <id>.
         await db.execute(
-            "INSERT OR REPLACE INTO media (owner_id, file_id, file_unique_id, media_type, keywords) VALUES (?,?,?,?,?)",
+            """
+            INSERT INTO media (owner_id, file_id, file_unique_id, media_type, keywords)
+            VALUES (?,?,?,?,?)
+            ON CONFLICT(owner_id, file_unique_id) DO UPDATE SET
+                file_id = excluded.file_id,
+                media_type = excluded.media_type,
+                keywords = excluded.keywords
+            """,
             (owner_id, file_id, file_unique_id, media_type, kw),
         )
         await db.commit()
 
 
-async def search_media(query: str) -> list[dict]:
+async def update_media_keywords(media_id: int, keywords: list[str]) -> bool:
+    kw = ",".join(k.strip().lower() for k in keywords if k.strip())
+    async with aiosqlite.connect(DB_PATH) as db:
+        cur = await db.execute(
+            "UPDATE media SET keywords = ? WHERE id = ?",
+            (kw, media_id),
+        )
+        await db.commit()
+        return cur.rowcount > 0
+
+
+async def delete_media(media_id: int) -> bool:
+    async with aiosqlite.connect(DB_PATH) as db:
+        cur = await db.execute("DELETE FROM media WHERE id = ?", (media_id,))
+        await db.commit()
+        return cur.rowcount > 0
+
+
+# ── reads ────────────────────────────────────────────────────────────────────
+
+COLUMNS = "id, file_id, file_unique_id, media_type, keywords"
+
+
+async def search_media(query: str, owner_id: int | None = None) -> list[dict]:
+    """Search by keyword prefix. owner_id=None searches every owner, which is
+    the current shared-library behaviour; public mode will pass a scope."""
     query = query.strip().lower()
+    where = []
+    params: list = []
+    if query:
+        where.append("(',' || keywords || ',') LIKE ?")
+        params.append(f"%,{query}%")
+    if owner_id is not None:
+        where.append("owner_id = ?")
+        params.append(owner_id)
+    clause = f"WHERE {' AND '.join(where)}" if where else ""
+
     async with aiosqlite.connect(DB_PATH) as db:
         db.row_factory = aiosqlite.Row
-        if query:
+        cursor = await db.execute(
-            cursor = await db.execute(
+            f"SELECT {COLUMNS} FROM media {clause} ORDER BY added_at DESC LIMIT 50",
-                """
+            params,
-                SELECT id, file_id, file_unique_id, media_type, keywords
+        )
-                FROM media
-                WHERE (',' || keywords || ',') LIKE ?
-                ORDER BY added_at DESC
-                LIMIT 50
-                """,
-                (f"%,{query}%",),
-            )
-        else:
-            cursor = await db.execute(
-                """
-                SELECT id, file_id, file_unique_id, media_type, keywords
-                FROM media
-                ORDER BY added_at DESC
-                LIMIT 50
-                """,
-            )
         rows = await cursor.fetchall()
         return [dict(r) for r in rows]
 
@@ -65,8 +162,8 @@ async def list_media(page: int, page_size: int) -> list[dict]:
     async with aiosqlite.connect(DB_PATH) as db:
         db.row_factory = aiosqlite.Row
         cursor = await db.execute(
-            """
+            f"""
-            SELECT id, file_id, file_unique_id, media_type, keywords
+            SELECT {COLUMNS}
             FROM media
             ORDER BY added_at DESC, id DESC
             LIMIT ? OFFSET ?
@@ -88,26 +185,8 @@ async def get_media_by_id(media_id: int) -> dict | None:
     async with aiosqlite.connect(DB_PATH) as db:
         db.row_factory = aiosqlite.Row
         cursor = await db.execute(
-            "SELECT id, file_id, file_unique_id, media_type, keywords FROM media WHERE id = ?",
+            f"SELECT {COLUMNS} FROM media WHERE id = ?",
             (media_id,),
         )
         row = await cursor.fetchone()
         return dict(row) if row else None
-
-
-async def update_media_keywords(media_id: int, keywords: list[str]) -> bool:
-    kw = ",".join(k.strip().lower() for k in keywords if k.strip())
-    async with aiosqlite.connect(DB_PATH) as db:
-        cur = await db.execute(
-            "UPDATE media SET keywords = ? WHERE id = ?",
-            (kw, media_id),
-        )
-        await db.commit()
-        return cur.rowcount > 0
-
-
-async def delete_media(media_id: int) -> bool:
-    async with aiosqlite.connect(DB_PATH) as db:
-        cur = await db.execute("DELETE FROM media WHERE id = ?", (media_id,))
-        await db.commit()
-        return cur.rowcount > 0

test_db.py

@@ -0,0 +1,108 @@
+"""Migration tests. Run with: python test_db.py
+
+The v1->v2 migration rebuilds the media table, so it drops the original.
+These cases cover the paths that rebuild touches before it ever runs against
+a real bot_db/media.db.
+"""
+import asyncio
+import importlib
+import os
+import sqlite3
+import sys
+import tempfile
+
+V1_SCHEMA = """
+    CREATE TABLE media (
+        id INTEGER PRIMARY KEY AUTOINCREMENT,
+        owner_id INTEGER NOT NULL,
+        file_id TEXT NOT NULL,
+        file_unique_id TEXT NOT NULL UNIQUE,
+        media_type TEXT NOT NULL,
+        keywords TEXT NOT NULL,
+        added_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
+    );
+"""
+
+
+def user_version(path: str) -> int:
+    with sqlite3.connect(path) as c:
+        return c.execute("PRAGMA user_version").fetchone()[0]
+
+
+def load_db(path: str):
+    os.environ["DB_PATH"] = path
+    import db
+    return importlib.reload(db)
+
+
+async def test_legacy_upgrade(tmp: str):
+    path = os.path.join(tmp, "legacy.db")
+    with sqlite3.connect(path) as c:
+        c.executescript(V1_SCHEMA)
+        c.execute("INSERT INTO media (id,owner_id,file_id,file_unique_id,media_type,keywords)"
+                  " VALUES (7,111,'FID_A','UNI_A','photo','cat,funny')")
+        c.execute("INSERT INTO media (id,owner_id,file_id,file_unique_id,media_type,keywords)"
+                  " VALUES (9,111,'FID_B','UNI_B','gif','dog')")
+
+    db = load_db(path)
+    await db.init_db()
+
+    assert user_version(path) == 2
+    rows = sorted((r["id"], r["keywords"]) for r in await db.search_media(""))
+    assert rows == [(7, "cat,funny"), (9, "dog")], f"rows not preserved: {rows}"
+    print("  legacy v1 database upgrades to v2 with ids and keywords intact")
+
+
+async def test_per_owner_uniqueness(tmp: str):
+    path = os.path.join(tmp, "owners.db")
+    db = load_db(path)
+    await db.init_db()
+
+    await db.add_media(111, "FID_A", "UNI_A", "photo", ["cat"])
+    await db.add_media(222, "FID_A2", "UNI_A", "photo", ["cat"])
+    assert len(await db.search_media("cat")) == 2, "two owners must each keep their own row"
+    assert len(await db.search_media("", owner_id=222)) == 1, "owner scoping failed"
+    print("  two owners can save the same file; owner scoping filters correctly")
+
+
+async def test_readd_keeps_id(tmp: str):
+    path = os.path.join(tmp, "readd.db")
+    db = load_db(path)
+    await db.init_db()
+
+    await db.add_media(111, "FID_A", "UNI_A", "photo", ["cat"])
+    original = (await db.search_media("cat"))[0]["id"]
+    await db.add_media(111, "FID_NEW", "UNI_A", "photo", ["kitten"])
+    row = await db.get_media_by_id(original)
+
+    assert row is not None, "re-adding the same file orphaned its id"
+    assert row["keywords"] == "kitten" and row["file_id"] == "FID_NEW"
+    print("  re-adding a file updates in place and keeps its id")
+
+
+async def test_fresh_and_idempotent(tmp: str):
+    path = os.path.join(tmp, "fresh.db")
+    db = load_db(path)
+    await db.init_db()
+
+    with sqlite3.connect(path) as c:
+        sql = c.execute("SELECT sql FROM sqlite_master WHERE name='media'").fetchone()[0]
+    assert "UNIQUE(owner_id, file_unique_id)" in sql
+    assert user_version(path) == 2
+
+    await db.init_db()
+    await db.init_db()
+    print("  fresh install lands on v2; init_db is idempotent")
+
+
+async def main():
+    sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+    with tempfile.TemporaryDirectory() as tmp:
+        for test in (test_legacy_upgrade, test_per_owner_uniqueness,
+                     test_readd_keeps_id, test_fresh_and_idempotent):
+            await test(tmp)
+    print("\nAll database tests passed.")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())