fix: audit fixes — 5 bugs found and resolved

Thorough code review found 5 issues across run_agent.py, cli.py, and gateway/:

1. CRITICAL — Gateway stream consumer task never started: stream_consumer_holder
   was checked BEFORE run_sync populated it. Fixed with async polling pattern
   (same as track_agent).

2. MEDIUM-HIGH — Streaming fallback after partial delivery caused double-response:
   if streaming failed after some tokens were delivered, the fallback would
   re-deliver the full response. Now tracks deltas_were_sent and only falls
   back when no tokens reached consumers yet.

3. MEDIUM — Codex mode lost on_first_delta spinner callback: _run_codex_stream
   now accepts on_first_delta parameter, fires it on first text delta. Passed
   through from _interruptible_streaming_api_call via _codex_on_first_delta
   instance attribute.

4. MEDIUM — CLI close-tag after-text bypassed tag filtering: text after a
   reasoning close tag was sent directly to _emit_stream_text, skipping
   open-tag detection. Now routes through _stream_delta for full filtering.

5. LOW — Removed 140 lines of dead code: old _streaming_api_call method
   (superseded by _interruptible_streaming_api_call). Updated 13 tests in
   test_run_agent.py and test_openai_client_lifecycle.py to use the new
   method name and signature.

4573 tests passing.

gateway/run.py

@@ -4371,10 +4371,19 @@ class GatewayRunner:
         if tool_progress_enabled:
             progress_task = asyncio.create_task(send_progress_messages())
 
-        # Start stream consumer task if configured
+        # Start stream consumer task — polls for consumer creation since it
+        # happens inside run_sync (thread pool) after the agent is constructed.
         stream_task = None
-        if stream_consumer_holder[0] is not None:
-            stream_task = asyncio.create_task(stream_consumer_holder[0].run())
+
+        async def _start_stream_consumer():
+            """Wait for the stream consumer to be created, then run it."""
+            for _ in range(200):  # Up to 10s wait
+                if stream_consumer_holder[0] is not None:
+                    await stream_consumer_holder[0].run()
+                    return
+                await asyncio.sleep(0.05)
+
+        stream_task = asyncio.create_task(_start_stream_consumer())
         
         # Track this agent as running for this session (for interrupt support)
         # We do this in a callback after the agent is created