fix(api): forward real LLM usage in /v1/chat/completions response (#4310)

* fix(api): forward real LLM usage in /v1/chat/completions response

_chat_completion_response() hardcoded prompt_tokens/completion_tokens
to zero.  Now reads agent_loop._last_usage (set by process_direct
after every LLM call) and forwards the actual prompt/completion counts.

Streaming path is unchanged; usage is only surfaced in non-streaming
responses for now.

Fixes #4309

* fix: use defensive getattr for _last_usage and add it to all test mock agents

- Use getattr(agent_loop, '_last_usage', None) in server.py for safety
- Add _last_usage = {} to mock agents in test_api_attachment.py and test_api_stream.py
- Prevents AttributeError/500 when mock agents don't have the attribute

* fix(api): preserve provider total usage

---------

Co-authored-by: michaelxer <michaelxer@users.noreply.github.com>
Co-authored-by: Xubin Ren <52506698+Re-bin@users.noreply.github.com>

tests/test_api_attachment.py

@@ -32,6 +32,7 @@ def _make_mock_agent(response_text: str = "mock response") -> MagicMock:
     agent.process_direct = AsyncMock(return_value=response_text)
     agent._connect_mcp = AsyncMock()
     agent.close_mcp = AsyncMock()
+    agent._last_usage = {}
     return agent