feat(llm): index_state.fingerprint + index_docket_state migrations (refs #615)

src/llm/migrate.py

@@ -21,10 +21,27 @@ CREATE TABLE IF NOT EXISTS index_state (
     content_hash TEXT        NOT NULL,
     chunk_count  INTEGER     NOT NULL DEFAULT 0,
     indexed_at   TIMESTAMPTZ NOT NULL DEFAULT now(),
+    fingerprint  TEXT        NOT NULL DEFAULT '',
     PRIMARY KEY (item_key, collection)
 )
 """
 
+# Existing databases predate the column.
+INDEX_STATE_ALTER = "ALTER TABLE index_state ADD COLUMN IF NOT EXISTS fingerprint TEXT NOT NULL DEFAULT ''"
+
+# A sealed docket that was fully indexed under a given seal: the iterator
+# does not even list its items until the seal changes (unseal/reseal
+# writes a new sealed_at in bib, which no longer matches).
+INDEX_DOCKET_STATE_DDL = """
+CREATE TABLE IF NOT EXISTS index_docket_state (
+    collection TEXT        NOT NULL,
+    docket     TEXT        NOT NULL,
+    sealed_at  TEXT        NOT NULL,
+    indexed_at TIMESTAMPTZ NOT NULL DEFAULT now(),
+    PRIMARY KEY (collection, docket)
+)
+"""
+
 # langchain-postgres creates langchain_pg_embedding with an untyped vector
 # column; HNSW needs a typed one. ALTER is a no-op when already typed.
 _HNSW_DDL = [
@@ -35,9 +52,11 @@ _HNSW_DDL = [
 
 
 def migrate(engine: Engine) -> None:
-    """Create llm-owned tables. Safe to run on every start."""
+    """Create llm-owned tables/columns. Safe to run on every start."""
     with engine.begin() as conn:
         conn.execute(text(INDEX_STATE_DDL))
+        conn.execute(text(INDEX_STATE_ALTER))
+        conn.execute(text(INDEX_DOCKET_STATE_DDL))
 
 
 def ensure_hnsw(engine: Engine, dim: int) -> None:

tests/llm/test_migrate.py

@@ -24,3 +24,20 @@ class TestDdl:
         executed = " ".join(str(call.args[0]) for call in conn.execute.call_args_list)
         assert "vector(768)" in executed
         assert "USING hnsw" in executed
+
+    def test_fingerprint_column_and_docket_state(self):
+        assert "fingerprint" in migrate.INDEX_STATE_DDL
+        assert "ADD COLUMN IF NOT EXISTS fingerprint" in migrate.INDEX_STATE_ALTER
+        assert (
+            "CREATE TABLE IF NOT EXISTS index_docket_state"
+            in migrate.INDEX_DOCKET_STATE_DDL
+        )
+        assert "PRIMARY KEY (collection, docket)" in migrate.INDEX_DOCKET_STATE_DDL
+
+    def test_migrate_runs_alter_and_docket_state(self):
+        engine = MagicMock()
+        conn = engine.begin.return_value.__enter__.return_value
+        migrate.migrate(engine)
+        executed = " ".join(str(call.args[0]) for call in conn.execute.call_args_list)
+        assert "ADD COLUMN IF NOT EXISTS fingerprint" in executed
+        assert "index_docket_state" in executed