Use pathspec for monitor filtering

pyproject.toml

@@ -26,6 +26,7 @@ dependencies = [
     "fastmcp>=2.12.4",
     "httpx>=0.28.1",
     "lancedb>=0.25.2",
+    "pathspec>=0.12.1",
     "pydantic>=2.12.2",
     "pydantic-ai>=1.0.18",
     "pydantic-graph>=1.0.18",

src/haiku/rag/config/models.py

@@ -8,6 +8,8 @@ from haiku.rag.utils import get_default_data_dir
 class StorageConfig(BaseModel):
     data_dir: Path = Field(default_factory=get_default_data_dir)
     monitor_directories: list[Path] = []
+    monitor_ignore_patterns: list[str] = []
+    monitor_include_patterns: list[str] = []
     disable_autocreate: bool = False
     vacuum_retention_seconds: int = 60
 

tests/test_settings.py

@@ -82,3 +82,11 @@ async def test_config_validation_on_db_load(temp_db_path):
 
     finally:
         Config.processing.chunk_size = original_chunk_size
+
+
+def test_monitor_filter_patterns_config():
+    """Test that monitor filter patterns are available in config."""
+    assert hasattr(Config.storage, "monitor_ignore_patterns")
+    assert hasattr(Config.storage, "monitor_include_patterns")
+    assert isinstance(Config.storage.monitor_ignore_patterns, list)
+    assert isinstance(Config.storage.monitor_include_patterns, list)

uv.lock

@@ -1130,6 +1130,7 @@ dependencies = [
     { name = "fastmcp" },
     { name = "httpx" },
     { name = "lancedb" },
+    { name = "pathspec" },
     { name = "pydantic" },
     { name = "pydantic-ai" },
     { name = "pydantic-graph" },
@@ -1175,6 +1176,7 @@ requires-dist = [
     { name = "httpx", specifier = ">=0.28.1" },
     { name = "lancedb", specifier = ">=0.25.2" },
     { name = "mxbai-rerank", marker = "extra == 'mxbai'", specifier = ">=0.1.6" },
+    { name = "pathspec", specifier = ">=0.12.1" },
     { name = "pydantic", specifier = ">=2.12.2" },
     { name = "pydantic-ai", specifier = ">=1.0.18" },
     { name = "pydantic-graph", specifier = ">=1.0.18" },