fix(sse): correct UTF-8 handling and chunking in SSE streaming\n\n- Updated splitContentIntoSegments to handle runes instead of bytes\n- Fixed buildWebUIStreamForwarder to send delta chunks instead of cumulative content\n- Ensures proper handling of multi-byte characters in SSE streams

README.md

@@ -27,6 +27,7 @@ Now supports mutually exclusive message channels:
 	- If `telegram`: set `TELEGRAM_BOT_TOKEN`, keep `FEISHU_*` empty.
 	- If `feishu`: set `FEISHU_APP_ID` and `FEISHU_APP_SECRET`, keep `TELEGRAM_BOT_TOKEN` empty.
 	- If `webui`: set `WEBUI_LISTEN_ADDR` (default `:8090`).
+	- Optional for `webui`: set `WEBUI_EXPOSE_REASONING=true` to expose `thought/tool_call/tool_result` events to frontend.
 3. Set log level with `LOG_LEVEL=debug|info|warn|error`.
 	- To inspect full skill/tool execution content and detailed ReAct step traces, use `LOG_LEVEL=debug`.
 4. Configure knowledge and reasoning:
@@ -95,6 +96,7 @@ Minimum env config in `workspace/agent_runtime/configs/env`:
 ```env
 MESSAGE_CHANNEL=webui
 WEBUI_LISTEN_ADDR=:8090
+WEBUI_EXPOSE_REASONING=false
 LLM_API_KEY=your_api_key
 ```
 
@@ -115,6 +117,7 @@ docker run --rm -d \
 	--env-file ./workspace/agent_runtime/configs/env \
 	-e MESSAGE_CHANNEL=webui \
 	-e WEBUI_LISTEN_ADDR=:8090 \
+	-e WEBUI_EXPOSE_REASONING=false \
 	-e AGENT_WORKSPACE_DIR=/app/workspace/agent_runtime \
 	-v "$(pwd)/workspace/agent_runtime:/app/workspace/agent_runtime" \
 	laodingbot:latest