fix(agent-ui): reset streamed text at generation boundaries in agent chat (#10664)

One agent turn runs several internal LLM generations (tool selection,
reasoning, final answer) that all emit stream_event deltas over the same
per-agent SSE channel. The chat page accumulated every 'content' delta
into a single live bubble and ignored the 'done' boundary events, so the
internal generations' text (e.g. the English tool-selection rationale)
merged with — and visually corrupted — the streamed final answer.

Reset the accumulated content/reasoning on 'done': each generation gets
a clean live bubble, and the authoritative full answer still arrives via
the final json_message event as before.

Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de>

Author: walcz-de

core/http/react-ui/src/pages/AgentChat.jsx

@@ -221,7 +221,14 @@ export default function AgentChat() {
             return updated
           })
         } else if (data.type === 'done') {
-          // Content will be finalized by json_message event
+          // One agent turn runs several internal LLM generations (tool
+          // selection, reasoning, final answer) over the same SSE channel;
+          // 'done' marks the boundary between them. Reset the accumulated
+          // text so an internal generation's output doesn't merge into the
+          // next one's bubble — the final json_message carries the
+          // authoritative full answer anyway.
+          setStreamContent('')
+          setStreamReasoning('')
         }
       } catch (_err) {
         // ignore