feat(documents): snapshot boundary and corpus models on process

Co-authored-by: Cursor <cursoragent@cursor.com>

src/documents/models.py

@@ -16,6 +16,8 @@ class DocumentResponse(BaseModel):
     paragraph_count: int = 0
     chunk_counts: dict[str, int] = Field(default_factory=dict)
     created_at: str
+    last_corpus_embedding_model_id: Optional[str] = None
+    last_boundary_embedding_model_id: Optional[str] = None
 
 
 class DocumentDetailResponse(DocumentResponse):
@@ -37,6 +39,14 @@ class ProcessRequest(BaseModel):
         description="Which chunking strategies to run (defaults to all 5)",
         min_length=1,
     )
+    boundary_model_id: Optional[str] = Field(
+        default=None,
+        description="Boundary Embedding Model id (semantic cuts); default = Admin Boundary",
+    )
+    corpus_model_id: Optional[str] = Field(
+        default=None,
+        description="Corpus Embedding Model id (storage); default = Admin Corpus",
+    )
 
 
 class StrategyResult(BaseModel):
@@ -52,6 +62,8 @@ class ProcessResponse(BaseModel):
     document_id: str
     strategies_completed: list[StrategyResult]
     strategies_failed: list[StrategyResult]
+    corpus_embedding_model_id: Optional[str] = None
+    boundary_embedding_model_id: Optional[str] = None
 
 
 class DeleteResponse(BaseModel):

src/documents/service.py

@@ -101,7 +101,12 @@ def process_document(
     # Import here to avoid circular imports at module level
     from src.chunking.service import run_strategies
 
-    completed_raw, failed_raw = run_strategies(doc_id, request.strategies)
+    completed_raw, failed_raw = run_strategies(
+        doc_id,
+        request.strategies,
+        boundary_model_id=request.boundary_model_id,
+        corpus_model_id=request.corpus_model_id,
+    )
 
     completed = [
         StrategyResult(
@@ -120,17 +125,28 @@ def process_document(
         for r in failed_raw
     ]
 
+    corpus_id = None
+    boundary_id = None
+    for r in completed_raw:
+        corpus_id = r.get("corpus_embedding_model_id") or corpus_id
+        if r.get("boundary_embedding_model_id"):
+            boundary_id = r["boundary_embedding_model_id"]
+
     return ProcessResponse(
         document_id=doc_id,
         strategies_completed=completed,
         strategies_failed=failed,
+        corpus_embedding_model_id=corpus_id,
+        boundary_embedding_model_id=boundary_id,
     )
 
 
 # ── Delete ─────────────────────────────────────────────────────────
 
 def delete_document(doc_id: str) -> bool:
-    """Delete a document and all its Qdrant vectors."""
+    """Delete a document and all its Qdrant vectors across Model Corpora."""
+    from src.chunking.embedding_models import list_models
+
     doc = db.get_document(doc_id)
     if doc is None:
         return False
@@ -139,7 +155,20 @@ def delete_document(doc_id: str) -> bool:
         if count > 0:
             try:
                 strategy = StrategyName(strategy_name)
-                qdr.delete_document_chunks(strategy, doc["filename"])
+                for model in list_models():
+                    try:
+                        qdr.delete_document_chunks(
+                            strategy,
+                            doc["filename"],
+                            model_id=model.id,
+                        )
+                    except Exception as exc:
+                        logger.warning(
+                            "Failed to delete Qdrant vectors for %s/%s: %s",
+                            strategy_name,
+                            model.id,
+                            exc,
+                        )
             except Exception as exc:
                 logger.warning("Failed to delete Qdrant vectors for %s: %s", strategy_name, exc)