fix: six P2 correctness/robustness cleanups from the SDK review

- legacy call_llm: open AsyncOpenAI via `async with` so the client (and
  its HTTP connection pool) is closed instead of leaked.
- LocalBackend.add_document: fail fast with CollectionNotFoundError when
  the collection doesn't exist, before the expensive parse + LLM index
  (previously the missing FK only tripped at save time, after paying for
  the LLM work). Also raise builtin FileNotFoundError for a missing path
  instead of FileTypeError (which now means only "unsupported extension").
- Collection.query(doc_ids=None): the empty-collection guard now always
  runs — previously it was skipped once PAGEINDEX_EXPERIMENTAL_MULTIDOC
  was set. A single list_documents call serves both the guard and the
  multi-doc warning (no separate call just to decide whether to warn).
- CloudBackend.query_stream: on early consumer break / GeneratorExit,
  signal the background SSE thread to stop and force-close the response,
  so it no longer drains the whole stream in the background.

Adds regression tests for each (client closed, fail-fast on unknown
collection, FileNotFoundError, empty-check under the multidoc env flag,
single list call, early-break thread stop).

Claude-Session: https://claude.ai/code/session_01Kx5DgKbhK1N8autqXH8SmS

tests/test_local_backend.py

@@ -165,3 +165,18 @@ def test_delete_collection_rejects_path_traversal(backend, tmp_path):
     with pytest.raises(PageIndexError, match="Invalid collection name"):
         backend.delete_collection("../..")
     assert canary.exists()
+
+
+def test_add_document_missing_file_raises_file_not_found(backend, tmp_path):
+    backend.get_or_create_collection("papers")
+    with pytest.raises(FileNotFoundError):
+        backend.add_document("papers", str(tmp_path / "nope.pdf"))
+
+
+def test_add_document_unknown_collection_fails_fast(backend, tmp_path):
+    from pageindex.errors import CollectionNotFoundError
+    pdf = tmp_path / "doc.pdf"
+    pdf.write_bytes(b"%PDF-1.4")
+    # Collection never created -> must raise before any parse/LLM work.
+    with pytest.raises(CollectionNotFoundError, match="does not exist"):
+        backend.add_document("ghost-collection", str(pdf))