fix(retrieval): preserve project ids across unscoped ingest

src/atocore/ingestion/pipeline.py

@@ -37,6 +37,13 @@ def ingest_file(file_path: Path, project_id: str = "") -> dict:
     start = time.time()
     file_path = file_path.resolve()
     project_id = (project_id or "").strip()
+    if not project_id:
+        try:
+            from atocore.projects.registry import derive_project_id_for_path
+
+            project_id = derive_project_id_for_path(file_path)
+        except Exception:
+            project_id = ""
 
     if not file_path.exists():
         raise FileNotFoundError(f"File not found: {file_path}")

src/atocore/projects/registry.py

@@ -8,7 +8,6 @@ from dataclasses import asdict, dataclass
 from pathlib import Path
 
 import atocore.config as _config
-from atocore.ingestion.pipeline import ingest_project_folder
 
 
 # Reserved pseudo-projects. `inbox` holds pre-project / lead / quote
@@ -260,6 +259,7 @@ def load_project_registry() -> list[RegisteredProject]:
         )
 
     _validate_unique_project_names(projects)
+    _validate_ingest_root_overlaps(projects)
     return projects
 
 
@@ -307,6 +307,28 @@ def resolve_project_name(name: str | None) -> str:
     return name
 
 
+def derive_project_id_for_path(file_path: str | Path) -> str:
+    """Return the registered project that owns a source path, if any."""
+    if not file_path:
+        return ""
+    doc_path = Path(file_path).resolve(strict=False)
+    matches: list[tuple[int, int, str]] = []
+
+    for project in load_project_registry():
+        for source_ref in project.ingest_roots:
+            root_path = _resolve_ingest_root(source_ref)
+            try:
+                doc_path.relative_to(root_path)
+            except ValueError:
+                continue
+            matches.append((len(root_path.parts), len(str(root_path)), project.project_id))
+
+    if not matches:
+        return ""
+    matches.sort(reverse=True)
+    return matches[0][2]
+
+
 def refresh_registered_project(project_name: str, purge_deleted: bool = False) -> dict:
     """Ingest all configured source roots for a registered project.
 
@@ -322,6 +344,8 @@ def refresh_registered_project(project_name: str, purge_deleted: bool = False) -
     if project is None:
         raise ValueError(f"Unknown project: {project_name}")
 
+    from atocore.ingestion.pipeline import ingest_project_folder
+
     roots = []
     ingested_count = 0
     skipped_count = 0
@@ -447,6 +471,33 @@ def _validate_unique_project_names(projects: list[RegisteredProject]) -> None:
             seen[key] = project.project_id
 
 
+def _validate_ingest_root_overlaps(projects: list[RegisteredProject]) -> None:
+    roots: list[tuple[str, Path]] = []
+    for project in projects:
+        for source_ref in project.ingest_roots:
+            roots.append((project.project_id, _resolve_ingest_root(source_ref)))
+
+    for i, (left_project, left_root) in enumerate(roots):
+        for right_project, right_root in roots[i + 1:]:
+            if left_project == right_project:
+                continue
+            try:
+                left_root.relative_to(right_root)
+                overlaps = True
+            except ValueError:
+                try:
+                    right_root.relative_to(left_root)
+                    overlaps = True
+                except ValueError:
+                    overlaps = False
+            if overlaps:
+                raise ValueError(
+                    "Project registry ingest root overlap: "
+                    f"'{left_root}' ({left_project}) and "
+                    f"'{right_root}' ({right_project})"
+                )
+
+
 def _find_name_collisions(
     project_id: str,
     aliases: list[str],

src/atocore/retrieval/retriever.py

@@ -209,8 +209,9 @@ def _is_allowed_for_project_scope(
 
 
 def _metadata_matches_project(project: RegisteredProject, metadata: dict) -> bool:
-    if "project_id" in metadata:
-        return str(metadata.get("project_id", "")).strip().lower() == project.project_id.lower()
+    stored_project_id = str(metadata.get("project_id", "")).strip().lower()
+    if stored_project_id:
+        return stored_project_id == project.project_id.lower()
 
     path = _metadata_source_path(metadata)
     tags = _metadata_tags(metadata)