feat(collection): scoped query mode and experimental multi-doc warning

- get_agent_tools branches on doc_ids:
  - scoped (doc_ids=[...]): drops list_documents and hard-enforces a
    whitelist on the remaining tools; system prompt switches to
    SCOPED_SYSTEM_PROMPT (no list_documents instruction); doc list +
    summaries are prepended to the user message via wrap_with_doc_context.
  - open (doc_ids=None): unchanged 4-tool agent loop.
- list_documents now exposes doc_description (sqlite + cloud).
- Collection.query emits UserWarning when doc_ids is None and the
  collection holds >1 documents; PAGEINDEX_EXPERIMENTAL_MULTIDOC=1
  silences it. Single-doc collections skip the warning; empty
  collections raise ValueError.
- Agents SDK tracing upload disabled by default (avoids SSL timeouts);
  PAGEINDEX_AGENTS_TRACING=1 re-enables it.
- README: new SDK Usage section covering local/cloud quick start,
  streaming, multi-doc as experimental, and runnable examples.

pageindex/storage/sqlite.py

@@ -125,10 +125,10 @@ class SQLiteStorage:
     def list_documents(self, collection: str) -> list[dict]:
         conn = self._get_conn()
         rows = conn.execute(
-            "SELECT doc_id, doc_name, doc_type FROM documents WHERE collection_name = ? ORDER BY created_at",
+            "SELECT doc_id, doc_name, doc_description, doc_type FROM documents WHERE collection_name = ? ORDER BY created_at",
             (collection,),
         ).fetchall()
-        return [{"doc_id": r[0], "doc_name": r[1], "doc_type": r[2]} for r in rows]
+        return [{"doc_id": r[0], "doc_name": r[1], "doc_description": r[2] or "", "doc_type": r[3]} for r in rows]
 
     def delete_document(self, collection: str, doc_id: str) -> None:
         conn = self._get_conn()