Feature: run pending LLM index migrations automatically on startup

Add document_llmindex migrate, a cheap check-only path (no reindex) safe
to run unconditionally: has_pending_migration() short-circuits to a
metadata-only read once the store is current, so a healthy install pays
almost nothing. If a pending migration would require re-embedding, it
only logs a warning and leaves the index as-is -- re-embedding can be
slow and, for a metered embedding backend, cost money, so it stays a
deliberate manual action (document_llmindex rebuild), never automatic.

Wire it into the Docker image as a new init-llmindex-migrate oneshot
(modeled on init-search-index, gated on init-migrations), and document
the equivalent manual step for bare-metal upgrades.

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

src/documents/management/commands/document_llmindex.py

@@ -3,6 +3,7 @@ from typing import Any
 from documents.management.commands.base import PaperlessCommand
 from documents.tasks import llmindex_index
 from paperless_ai.indexing import llm_index_compact
+from paperless_ai.indexing import llm_index_migrate
 
 
 class Command(PaperlessCommand):
@@ -13,12 +14,18 @@ class Command(PaperlessCommand):
 
     def add_arguments(self, parser: Any) -> None:
         super().add_arguments(parser)
-        parser.add_argument("command", choices=["rebuild", "update", "compact"])
+        parser.add_argument(
+            "command",
+            choices=["rebuild", "update", "compact", "migrate"],
+        )
 
     def handle(self, *args: Any, **options: Any) -> None:
         if options["command"] == "compact":
             llm_index_compact()
             return
+        if options["command"] == "migrate":
+            llm_index_migrate()
+            return
         llmindex_index(
             rebuild=options["command"] == "rebuild",
             iter_wrapper=lambda docs: self.track(

src/documents/tests/management/test_management_document_llmindex.py

@@ -8,6 +8,7 @@ if TYPE_CHECKING:
     from pytest_mock import MockerFixture
 
 _COMPACT = "documents.management.commands.document_llmindex.llm_index_compact"
+_MIGRATE = "documents.management.commands.document_llmindex.llm_index_migrate"
 _INDEX = "documents.management.commands.document_llmindex.llmindex_index"
 
 
@@ -17,6 +18,11 @@ class TestDocumentLlmindexCommand:
         call_command("document_llmindex", "compact")
         mock_compact.assert_called_once_with()
 
+    def test_migrate_calls_llm_index_migrate(self, mocker: MockerFixture) -> None:
+        mock_migrate = mocker.patch(_MIGRATE)
+        call_command("document_llmindex", "migrate")
+        mock_migrate.assert_called_once_with()
+
     def test_rebuild_calls_llmindex_index_with_rebuild_true(
         self,
         mocker: MockerFixture,

src/paperless_ai/indexing.py

@@ -461,6 +461,31 @@ def llm_index_add_or_update_document(document: Document):
         store.upsert_document(str(document.id), new_nodes)
 
 
+def llm_index_migrate() -> None:
+    """Apply any pending LLM index schema migrations, with no reindex.
+
+    Intended to run unconditionally on every startup (see the
+    init-llmindex-migrate container step and the bare-metal upgrade docs):
+    has_pending_migration() short-circuits to a metadata-only read once the
+    store is current, so a healthy install pays almost nothing here. Only
+    ever applies structural migrations -- a pending re-embed migration is
+    left for the explicit, deliberate rebuild path (``document_llmindex
+    update``/``rebuild``) to resolve, since re-embedding can be slow and,
+    for a metered embedding backend, cost money.
+    """
+    if not AIConfig().llm_index_enabled:
+        return
+    with write_store() as store:
+        needs_reembed = _check_and_run_migrations(store)
+    if needs_reembed:
+        logger.warning(
+            "LLM index requires re-embedding, which this automatic migration "
+            "check will not do on its own -- it can be slow and, for a "
+            "metered embedding backend, cost money. Run "
+            "'document_llmindex rebuild' manually when ready.",
+        )
+
+
 def llm_index_compact() -> None:
     """Compact the index immediately, rebuilding the table to reclaim space."""
     with write_store() as store:

src/paperless_ai/tests/test_ai_indexing.py

@@ -722,6 +722,110 @@ def test_llm_index_compact_uses_force(
     mock_store.compact.assert_called_once_with(force=True)
 
 
+@pytest.mark.django_db
+class TestLlmIndexMigrate:
+    """llm_index_migrate() is the cheap, startup-safe migration check -- see
+    the init-llmindex-migrate container step and the bare-metal upgrade docs.
+    """
+
+    def test_skips_when_llm_index_disabled(
+        self,
+        temp_llm_index_dir: Path,
+        mocker: pytest_mock.MockerFixture,
+    ) -> None:
+        """
+        GIVEN:
+            - The LLM index is disabled
+        WHEN:
+            - llm_index_migrate() is called
+        THEN:
+            - The store is never opened (no stray db file for users who
+              never enabled AI features)
+        """
+        mock_config = mocker.MagicMock()
+        mock_config.llm_index_enabled = False
+        mocker.patch("paperless_ai.indexing.AIConfig", return_value=mock_config)
+        mock_write_store = mocker.patch("paperless_ai.indexing.write_store")
+
+        indexing.llm_index_migrate()
+
+        mock_write_store.assert_not_called()
+
+    def test_runs_pending_structural_migration(
+        self,
+        temp_llm_index_dir: Path,
+        mocker: pytest_mock.MockerFixture,
+        caplog: pytest.LogCaptureFixture,
+    ) -> None:
+        """
+        GIVEN:
+            - The LLM index is enabled and a structural migration is pending
+        WHEN:
+            - llm_index_migrate() is called
+        THEN:
+            - check_and_run_migrations() runs, and no re-embed warning is
+              logged (the pending migration was structural, not re-embed)
+        """
+        mock_config = mocker.MagicMock()
+        mock_config.llm_index_enabled = True
+        mocker.patch("paperless_ai.indexing.AIConfig", return_value=mock_config)
+        mock_store = mocker.MagicMock()
+        mock_store.has_pending_migration.return_value = True
+        mock_store.check_and_run_migrations.return_value = False
+        mocker.patch(
+            "paperless_ai.indexing.write_store",
+            return_value=mocker.MagicMock(
+                __enter__=mocker.MagicMock(return_value=mock_store),
+                __exit__=mocker.MagicMock(return_value=False),
+            ),
+        )
+
+        with caplog.at_level("WARNING"):
+            indexing.llm_index_migrate()
+
+        mock_store.check_and_run_migrations.assert_called_once()
+        assert "re-embedding" not in caplog.text
+
+    def test_warns_without_rebuilding_when_reembed_pending(
+        self,
+        temp_llm_index_dir: Path,
+        mocker: pytest_mock.MockerFixture,
+        caplog: pytest.LogCaptureFixture,
+    ) -> None:
+        """
+        GIVEN:
+            - The LLM index is enabled and a pending migration requires
+              re-embedding
+        WHEN:
+            - llm_index_migrate() is called
+        THEN:
+            - A warning is logged telling the admin to rebuild manually, but
+              no rebuild is triggered automatically -- re-embedding can be
+              slow and, for a metered embedding backend, cost money, so it
+              must be a deliberate user action, never an automatic one
+        """
+        mock_config = mocker.MagicMock()
+        mock_config.llm_index_enabled = True
+        mocker.patch("paperless_ai.indexing.AIConfig", return_value=mock_config)
+        mock_store = mocker.MagicMock()
+        mock_store.has_pending_migration.return_value = True
+        mock_store.check_and_run_migrations.return_value = True
+        mocker.patch(
+            "paperless_ai.indexing.write_store",
+            return_value=mocker.MagicMock(
+                __enter__=mocker.MagicMock(return_value=mock_store),
+                __exit__=mocker.MagicMock(return_value=False),
+            ),
+        )
+
+        with caplog.at_level("WARNING"):
+            indexing.llm_index_migrate()
+
+        assert "re-embedding" in caplog.text
+        mock_store.drop_table.assert_not_called()
+        mock_store.add.assert_not_called()
+
+
 @pytest.mark.django_db
 class TestLlmIndexLocking:
     """Index mutation functions must go through write_store(), which holds the lock.

src/paperless_ai/vector_store.py

@@ -671,7 +671,7 @@ class PaperlessSqliteVecVectorStore(BasePydanticVectorStore):
             if migration.kind == "re-embed":
                 logger.warning(
                     "LLM index schema v%d -> v%d requires re-embedding (%s); "
-                    "forcing full rebuild.",
+                    "the caller must force a rebuild.",
                     migration.from_version,
                     migration.to_version,
                     migration.description,