feat(llm): support incremental Responses WebSocket transport

artemis/llm/diagnostics.py

@@ -390,7 +390,12 @@ async def observe_response_headers(response):
     """Correlate allowlisted headers and passively observe bounded SSE frames."""
     attempt = ACTIVE_ATTEMPT.get()
     if attempt is not None:
-        attempt.headers(response)
+        websocket = response.extensions.get("artemis_websocket", False)
+        if websocket:
+            # 200/SSE is an in-process SDK facade, not a wire HTTP response.
+            attempt.data.update(headers_at=time.time(), phase="waiting_output")
+        else:
+            attempt.headers(response)
         content_type = response.headers.get("content-type", "").split(";", 1)[0].lower()
         if (
             response.status_code == 200
@@ -407,5 +412,7 @@ async def observe_response_headers(response):
                 )
                 response.stream = stream
                 attempt.wire_streams.append(stream)
+                if websocket:
+                    stream.observation.data["observation_boundary"] = "websocket_event_sse_adapter"
             else:
                 attempt.data["wire_streams_truncated"] = True