fix(agent): drop whitespace-only thinking events from the steps tree
Some LLMs (e.g. qwen3 series) emit blank lines like "\n\n" before tool calls. The backend faithfully forwards these as thought_chunk events because streamThinkingToEventBus only filters chunk.Content == "" and treats whitespace as content. The frontend then merges them into a thinking event whose content is non-empty in JS truthiness terms but visually empty, producing a "思考" card with a chevron and no text. Filter such events out at the end of buildFullEventList so neither the intermediate-steps tree nor the displayEvents fallback path renders them.
This commit is contained in:
@@ -1057,7 +1057,17 @@ const buildFullEventList = (stream: any[]) => {
|
||||
|
||||
result.push(event);
|
||||
}
|
||||
return result;
|
||||
|
||||
// Drop thinking events whose content is whitespace-only. Some models emit
|
||||
// "\n\n" before a tool call (see e.g. qwen3 emitting blank lines between
|
||||
// [assistant] and tool_calls), which the backend faithfully forwards as
|
||||
// thought_chunk events. Without this filter the tree shows an empty
|
||||
// "思考" card with no text — confusing to the user.
|
||||
return result.filter((e: any) => {
|
||||
if (e.type !== 'thinking') return true;
|
||||
const content = typeof e.content === 'string' ? e.content : '';
|
||||
return content.trim().length > 0;
|
||||
});
|
||||
};
|
||||
|
||||
// IDs of thinking events that should NOT be rendered in the intermediate-
|
||||
|
||||
Reference in New Issue
Block a user