Add project-aware boost to raw query

src/atocore/retrieval/retriever.py

@@ -6,6 +6,7 @@ from dataclasses import dataclass
 import atocore.config as _config
 from atocore.models.database import get_connection
 from atocore.observability.logger import get_logger
+from atocore.projects.registry import get_registered_project
 from atocore.retrieval.embeddings import embed_query
 from atocore.retrieval.vector_store import get_vector_store
 
@@ -28,6 +29,7 @@ def retrieve(
     query: str,
     top_k: int | None = None,
     filter_tags: list[str] | None = None,
+    project_hint: str | None = None,
 ) -> list[ChunkResult]:
     """Retrieve the most relevant chunks for a query."""
     top_k = top_k or _config.settings.context_top_k
@@ -71,6 +73,9 @@ def retrieve(
             meta = results["metadatas"][0][i] if results["metadatas"] else {}
             content = results["documents"][0][i] if results["documents"] else ""
 
+            if project_hint:
+                score *= _project_match_boost(project_hint, meta)
+
             chunks.append(
                 ChunkResult(
                     chunk_id=chunk_id,
@@ -85,6 +90,8 @@ def retrieve(
             )
 
     duration_ms = int((time.time() - start) * 1000)
+    chunks.sort(key=lambda chunk: chunk.score, reverse=True)
+
     log.info(
         "retrieval_done",
         query=query[:100],
@@ -96,6 +103,35 @@ def retrieve(
     return chunks
 
 
+def _project_match_boost(project_hint: str, metadata: dict) -> float:
+    """Return a project-aware relevance multiplier for raw retrieval."""
+    hint_lower = project_hint.strip().lower()
+    if not hint_lower:
+        return 1.0
+
+    source_file = str(metadata.get("source_file", "")).lower()
+    title = str(metadata.get("title", "")).lower()
+    tags = str(metadata.get("tags", "")).lower()
+    searchable = " ".join([source_file, title, tags])
+
+    project = get_registered_project(project_hint)
+    candidate_names = {hint_lower}
+    if project is not None:
+        candidate_names.add(project.project_id.lower())
+        candidate_names.update(alias.lower() for alias in project.aliases)
+        candidate_names.update(
+            source_ref.subpath.replace("\\", "/").strip("/").split("/")[-1].lower()
+            for source_ref in project.ingest_roots
+            if source_ref.subpath.strip("/\\")
+        )
+
+    for candidate in candidate_names:
+        if candidate and candidate in searchable:
+            return 2.0
+
+    return 1.0
+
+
 def _existing_chunk_ids(chunk_ids: list[str]) -> set[str]:
     """Filter out stale vector entries whose chunk rows no longer exist."""
     if not chunk_ids: