Check if settings are compatible when loading a db

src/haiku/rag/store/engine.py

@@ -13,6 +13,12 @@ class Store:
         self.db_path: Path | Literal[":memory:"] = db_path
         self._connection = self.create_db()
 
+        # Validate config compatibility after connection is established
+        from haiku.rag.store.repositories.settings import SettingsRepository
+
+        settings_repo = SettingsRepository(self)
+        settings_repo.validate_config_compatibility()
+
     def create_db(self) -> sqlite3.Connection:
         """Create the database and tables with sqlite-vec support for embeddings."""
         db = sqlite3.connect(self.db_path)

src/haiku/rag/store/repositories/settings.py

@@ -4,6 +4,12 @@ from typing import Any
 from haiku.rag.store.engine import Store
 
 
+class ConfigMismatchError(Exception):
+    """Raised when current config doesn't match stored settings."""
+
+    pass
+
+
 class SettingsRepository:
     def __init__(self, store: Store):
         self.store = store
@@ -34,3 +40,39 @@ class SettingsRepository:
         )
 
         self.store._connection.commit()
+
+    def validate_config_compatibility(self) -> None:
+        """Check if current config is compatible with stored settings.
+
+        Raises ConfigMismatchError if there are incompatible differences.
+        If no settings exist, saves current config.
+        """
+        db_settings = self.get()
+        if not db_settings:
+            # No settings in DB, save current config
+            self.save()
+            return
+
+        from haiku.rag.config import Config
+
+        current_config = Config.model_dump(mode="json")
+
+        # Critical settings that must match
+        critical_settings = [
+            "EMBEDDINGS_PROVIDER",
+            "EMBEDDINGS_MODEL",
+            "EMBEDDINGS_VECTOR_DIM",
+            "CHUNK_SIZE",
+            "CHUNK_OVERLAP",
+        ]
+
+        errors = []
+        for setting in critical_settings:
+            if db_settings.get(setting) != current_config.get(setting):
+                errors.append(
+                    f"{setting}: current={current_config.get(setting)}, stored={db_settings.get(setting)}"
+                )
+
+        if errors:
+            error_msg = f"Config mismatch detected: {'; '.join(errors)}. Consider rebuilding the database with the current configuration."
+            raise ConfigMismatchError(error_msg)

tests/test_settings.py

@@ -1,6 +1,14 @@
+import tempfile
+from pathlib import Path
+
+import pytest
+
 from haiku.rag.config import Config
 from haiku.rag.store.engine import Store
-from haiku.rag.store.repositories.settings import SettingsRepository
+from haiku.rag.store.repositories.settings import (
+    ConfigMismatchError,
+    SettingsRepository,
+)
 
 
 def test_settings_table_populated_on_store_init():
@@ -31,3 +39,35 @@ def test_settings_save_and_retrieve():
 
     Config.CHUNK_SIZE = original_chunk_size
     store.close()
+
+
+def test_config_validation_on_db_load():
+    """Test that config validation fails when loading db with mismatched settings."""
+    # Create a temporary database file
+    with tempfile.NamedTemporaryFile(suffix=".sqlite", delete=False) as tmp:
+        db_path = Path(tmp.name)
+
+    try:
+        # Create store and save settings
+        store1 = Store(db_path)
+        SettingsRepository(store1)
+        store1.close()
+
+        # Change config
+        original_chunk_size = Config.CHUNK_SIZE
+        Config.CHUNK_SIZE = 999
+
+        # Loading the database should raise ConfigMismatchError
+        with pytest.raises(ConfigMismatchError) as exc_info:
+            Store(db_path)
+
+        assert "CHUNK_SIZE" in str(exc_info.value)
+        assert "Consider rebuilding" in str(exc_info.value)
+
+        # Restore original config
+        Config.CHUNK_SIZE = original_chunk_size
+
+    finally:
+        # Cleanup
+        if db_path.exists():
+            db_path.unlink()