Studio: add RAG with hybrid search, reranker, chat integration

Backend (studio/backend/):
- core/rag/: parsers (PDF/TXT/MD/DOCX/HTML via pypdf/python-docx/bs4),
  recursive token-aware chunker, embeddings singleton via
  FastSentenceTransformer.from_pretrained(for_inference=True), Qdrant
  local vector store, bm25s lexical index, RRF hybrid retrieval,
  spawn-subprocess ingestion job with SSE progress, optional
  CrossEncoder reranker (off-by-default).
- routes/rag.py: KB CRUD, doc upload (KB + per-thread), doc list/delete,
  ingestion SSE, hybrid+rerank search, thread-index list/clear.
- routes/chat_history.py: purge thread RAG artifacts on thread delete
  and clear-all (rag_documents has no FK cascade to chat_threads so
  uploads work on un-persisted threads).
- studio.db gains 4 RAG tables; storage_roots gains rag_*() helpers.
- auth/authentication.py: get_current_subject_sse accepts ?token=... so
  EventSource can stream ingestion progress.

Frontend (studio/frontend/):
- features/rag/: api client, Zustand store, hooks, dropzone, KB list,
  doc rows, ingestion-progress, thread-index list components.
- Settings dialog gains a Knowledge Bases tab (master/detail + thread
  documents list); /knowledge-bases deep-links to it.
- features/chat/: per-thread ragSource/enableRerank/ragTopK state in
  chat-runtime-store; Retrieval section in chat-settings-sheet with KB
  DropdownMenu (active highlight + per-row trash), thread doc list with
  Clear-thread-index button, RAG Top K slider, reranker toggle;
  chat-adapter retrieves before /v1/chat/completions and injects hits
  as a system block; shared-composer + button routes documents into
  pendingDocs (auto-uploads, send blocked while indexing).

tests/python/test_rag_vector_store.py

@@ -0,0 +1,84 @@
+"""Qdrant local-mode vector store tests (skipped if qdrant-client is unavailable)."""
+
+import sys
+from pathlib import Path
+
+import pytest
+
+REPO_ROOT = Path(__file__).resolve().parents[2]
+STUDIO_BACKEND = REPO_ROOT / "studio" / "backend"
+if str(STUDIO_BACKEND) not in sys.path:
+    sys.path.insert(0, str(STUDIO_BACKEND))
+
+pytest.importorskip("qdrant_client")
+
+
+@pytest.fixture
+def isolated_qdrant(tmp_path, monkeypatch):
+    monkeypatch.setenv("UNSLOTH_STUDIO_HOME", str(tmp_path))
+    from core.rag import vector_store
+
+    # Reset client cache so the fixture's tmp path is used.
+    vector_store._client = None
+    yield tmp_path
+    vector_store._client = None
+
+
+def test_ensure_and_upsert_and_search(isolated_qdrant):
+    from core.rag import vector_store
+
+    scope = "kb_test"
+    vector_store.ensure_collection(scope, dim = 4)
+    points = [
+        {
+            "id": "p1",
+            "vector": [1.0, 0.0, 0.0, 0.0],
+            "payload": {"document_id": "doc1", "chunk_index": 0, "text": "first"},
+        },
+        {
+            "id": "p2",
+            "vector": [0.0, 1.0, 0.0, 0.0],
+            "payload": {"document_id": "doc1", "chunk_index": 1, "text": "second"},
+        },
+    ]
+    vector_store.upsert_chunks(scope, points)
+    results = vector_store.search(scope, [1.0, 0.0, 0.0, 0.0], top_k = 2)
+    assert results
+    assert results[0]["chunk_id"] == "p1"
+
+
+def test_delete_scope_removes_collection(isolated_qdrant):
+    from core.rag import vector_store
+
+    scope = "kb_to_delete"
+    vector_store.ensure_collection(scope, dim = 3)
+    assert vector_store.collection_exists(scope)
+    vector_store.delete_scope(scope)
+    assert not vector_store.collection_exists(scope)
+
+
+def test_delete_document_removes_only_its_points(isolated_qdrant):
+    from core.rag import vector_store
+
+    scope = "kb_doc_del"
+    vector_store.ensure_collection(scope, dim = 3)
+    vector_store.upsert_chunks(
+        scope,
+        [
+            {
+                "id": "a",
+                "vector": [1.0, 0.0, 0.0],
+                "payload": {"document_id": "keep", "chunk_index": 0},
+            },
+            {
+                "id": "b",
+                "vector": [0.0, 1.0, 0.0],
+                "payload": {"document_id": "drop", "chunk_index": 0},
+            },
+        ],
+    )
+    vector_store.delete_document(scope, "drop")
+    results = vector_store.search(scope, [0.0, 1.0, 0.0], top_k = 5)
+    doc_ids = {r["payload"]["document_id"] for r in results}
+    assert "drop" not in doc_ids
+    assert "keep" in doc_ids