fix: prime server conversation tracker in streaming path to prevent message duplication

When resuming a streaming run from RunState, the server conversation tracker
was not being primed with previously sent model responses. This caused
`prepare_input` to treat all previously generated items as unsent and
resubmit them to the server, breaking conversation threading.

**Issue**: Missing `track_server_items` call in streaming resumption path

**Fix**: Added server conversation tracker priming logic in `_start_streaming`
method (lines 1076-1079) to match the non-streaming path implementation
(lines 553-556).

The fix iterates through `run_state._model_responses` and calls
`track_server_items(response)` to mark them as already sent to the server.

**Impact**: Resolves message duplication when resuming interrupted streaming
runs, ensuring proper conversation threading with server-side sessions.

Fixes code review feedback from PR openai#2021

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <[email protected]>

Author: mjschock

src/agents/run.py

@@ -1073,6 +1073,11 @@ async def _start_streaming(
         else:
             server_conversation_tracker = None
 
+        # Prime the server conversation tracker from state if resuming
+        if server_conversation_tracker is not None and run_state is not None:
+            for response in run_state._model_responses:
+                server_conversation_tracker.track_server_items(response)
+
         streamed_result._event_queue.put_nowait(AgentUpdatedStreamEvent(new_agent=current_agent))
 
         try: