fix: resolve five P1 defects from the SDK review

- AgentRunner.run: offload to a worker-thread event loop when called
  from inside a running loop (Jupyter, FastAPI handlers) — mirrors
  pipeline._run_async; Runner.run_sync raised RuntimeError there.

- SQLiteStorage: create connections with check_same_thread=False so
  close() can actually close connections created by worker threads.
  Each thread still gets its own connection via threading.local; with
  the default True those closes raised ProgrammingError (silently
  swallowed) and leaked every worker connection.

- CloudBackend.query: non-streaming chat completions now use a 300s
  timeout and a single attempt. The default 30s ReadTimeout fired
  before generation finished and the retry loop re-billed the full
  server-side retrieval + generation up to three times. _request gains
  retries/timeout overrides; the exhausted-retry path also no longer
  sleeps before raising.

- MarkdownParser: content before the first heading (abstract/preamble)
  becomes a node instead of being silently dropped and unretrievable;
  a file with no headings at all yields a single document node instead
  of zero nodes (which pushed an empty page list into the pipeline).

- LegacyCloudAPI.is_retrieval_ready: API failures (revoked key, network
  down) now propagate as PageIndexAPIError instead of reading as
  "not ready", which turned polling loops into infinite loops.

Adds regression tests for each fix.

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

tests/test_sqlite_storage.py

@@ -59,3 +59,23 @@ def test_delete_collection_cascades_documents(storage):
     storage.save_document("papers", "doc-1", {"doc_name": "test.pdf", "doc_type": "pdf", "file_path": "/tmp/test.pdf", "structure": []})
     storage.delete_collection("papers")
     assert "papers" not in storage.list_collections()
+
+
+def test_close_closes_connections_created_in_other_threads(storage):
+    """Regression: with check_same_thread=True, close() from another thread
+    raised ProgrammingError (swallowed) and leaked every worker connection."""
+    import sqlite3
+    import threading
+
+    conns = {}
+
+    def worker():
+        conns["worker"] = storage._get_conn()
+
+    t = threading.Thread(target=worker)
+    t.start()
+    t.join()
+
+    storage.close()  # main thread closes the worker's connection too
+    with pytest.raises(sqlite3.ProgrammingError):
+        conns["worker"].execute("SELECT 1")