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_chunking.py

@@ -0,0 +1,84 @@
+"""Unit tests for RAG chunking — pure-python, no external deps."""
+
+import sys
+from pathlib import Path
+
+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))
+
+from core.rag.chunking import Chunk, chunk_pages
+from core.rag.parsers import ParsedPage
+
+
+def _wc_counter(text: str) -> int:
+    return max(1, len(text.split()))
+
+
+def test_chunk_pages_splits_long_text():
+    text = "Lorem ipsum dolor sit amet. " * 200
+    chunks = chunk_pages(
+        [ParsedPage(text = text)],
+        max_tokens = 50,
+        overlap_tokens = 5,
+        token_counter = _wc_counter,
+    )
+    assert len(chunks) > 1
+    for chunk in chunks:
+        assert _wc_counter(chunk.text) <= 55  # max + small slack from atomic split granularity
+
+
+def test_chunk_pages_short_text_is_one_chunk():
+    text = "Just a short sentence."
+    chunks = chunk_pages(
+        [ParsedPage(text = text)],
+        max_tokens = 50,
+        overlap_tokens = 5,
+        token_counter = _wc_counter,
+    )
+    assert len(chunks) == 1
+    assert chunks[0].text == text
+
+
+def test_chunk_pages_preserves_page_numbers():
+    chunks = chunk_pages(
+        [
+            ParsedPage(text = "Page one content here.", page_number = 1),
+            ParsedPage(text = "Page two content here.", page_number = 2),
+        ],
+        max_tokens = 50,
+        overlap_tokens = 0,
+        token_counter = _wc_counter,
+    )
+    page_numbers = {c.page_number for c in chunks}
+    assert page_numbers == {1, 2}
+
+
+def test_chunk_pages_no_empty_chunks():
+    text = "\n\n\n\n\nReal content\n\n\n\n\n"
+    chunks = chunk_pages(
+        [ParsedPage(text = text)],
+        max_tokens = 50,
+        overlap_tokens = 0,
+        token_counter = _wc_counter,
+    )
+    for chunk in chunks:
+        assert chunk.text.strip()
+
+
+def test_chunk_pages_overlap_produces_repeated_tokens():
+    # Build a list of unique numbered sentences so we can detect overlap.
+    sentences = [f"sentence-{i}" for i in range(40)]
+    text = " ".join(sentences)
+    chunks = chunk_pages(
+        [ParsedPage(text = text)],
+        max_tokens = 10,
+        overlap_tokens = 4,
+        token_counter = _wc_counter,
+    )
+    if len(chunks) >= 2:
+        first_tail_words = set(chunks[0].text.split()[-4:])
+        second_head_words = set(chunks[1].text.split()[:4])
+        # At least one word should appear in both
+        assert first_tail_words & second_head_words