feat(collection): doc_ids accepts str|list, design cleanups

- Collection.query and Backend.query/query_stream accept doc_ids as
  str, list[str] or None. Single str is normalized to [str] inside each
  backend; bare [] is rejected with ValueError at both layers.
- wrap_with_doc_context wraps the scoped doc list in <docs>...</docs>
  and SCOPED_SYSTEM_PROMPT instructs the agent to treat that block as
  data, not instructions (defense against prompt injection via
  auto-generated doc_description).
- _require_cloud_api now distinguishes api_key="" from api_key=None;
  the former gives a targeted error pointing at the empty-string vs
  fall-back-to-local situation when legacy SDK methods are called.
- Legacy PageIndexClient.list_documents docstring spells out the
  return-shape difference vs collection.list_documents() to flag a
  silent migration footgun (paginated dict with id/name keys vs plain
  list[dict] with doc_id/doc_name keys).
- Remove dead CloudBackend.get_agent_tools stub (not on the Backend
  protocol; only ever returned an empty AgentTools()) and the
  SYSTEM_PROMPT alias (OPEN_/SCOPED_SYSTEM_PROMPT are the explicit
  names now).
- README quick start and streaming example now pass doc_ids; new
  multi-document section shows both str and list forms.
- examples/demo_query_modes.py exercises all five query-mode cases
  (single-doc, multi-doc with/without env var, scoped single, scoped
  multi) for manual verification.

pageindex/backend/protocol.py

@@ -28,7 +28,9 @@ class Backend(Protocol):
     def list_documents(self, collection: str) -> list[dict]: ...
     def delete_document(self, collection: str, doc_id: str) -> None: ...
 
-    # Query
-    def query(self, collection: str, question: str, doc_ids: list[str] | None = None) -> str: ...
+    # Query — doc_ids accepts a single id or a list; implementations should
+    # normalize internally (a bare str is treated as a single-element list).
+    def query(self, collection: str, question: str,
+              doc_ids: str | list[str] | None = None) -> str: ...
     async def query_stream(self, collection: str, question: str,
-                           doc_ids: list[str] | None = None) -> AsyncIterator[QueryEvent]: ...
+                           doc_ids: str | list[str] | None = None) -> AsyncIterator[QueryEvent]: ...