Add Dalidou storage foundation and deployment prep

src/atocore/ingestion/pipeline.py

@@ -6,6 +6,7 @@ import time
 import uuid
 from pathlib import Path
 
+import atocore.config as _config
 from atocore.ingestion.chunker import chunk_markdown
 from atocore.ingestion.parser import parse_markdown
 from atocore.models.database import get_connection
@@ -189,6 +190,52 @@ def ingest_folder(folder_path: Path, purge_deleted: bool = True) -> list[dict]:
     return results
 
 
+def get_source_status() -> list[dict]:
+    """Describe configured source directories and their readiness."""
+    sources = []
+    for spec in _config.settings.source_specs:
+        path = spec["path"]
+        assert isinstance(path, Path)
+        sources.append(
+            {
+                "name": spec["name"],
+                "enabled": spec["enabled"],
+                "path": str(path),
+                "exists": path.exists(),
+                "is_dir": path.is_dir(),
+                "read_only": spec["read_only"],
+            }
+        )
+    return sources
+
+
+def ingest_configured_sources(purge_deleted: bool = False) -> list[dict]:
+    """Ingest enabled source directories declared in config.
+
+    Purge is disabled by default here because sources are intended to be
+    read-only inputs and should not be treated as the primary writable state.
+    """
+    results = []
+    for source in get_source_status():
+        if not source["enabled"]:
+            results.append({"source": source["name"], "status": "disabled", "path": source["path"]})
+            continue
+        if not source["exists"] or not source["is_dir"]:
+            results.append({"source": source["name"], "status": "missing", "path": source["path"]})
+            continue
+
+        folder_results = ingest_folder(Path(source["path"]), purge_deleted=purge_deleted)
+        results.append(
+            {
+                "source": source["name"],
+                "status": "ingested",
+                "path": source["path"],
+                "results": folder_results,
+            }
+        )
+    return results
+
+
 def get_ingestion_stats() -> dict:
     """Return ingestion statistics."""
     with get_connection() as conn: