Add voice state tags, SuperTTS configs, and demo WS log groups.

Parse leading <state> tags from LLM replies and emit response.state over the product websocket while stripping tags from TTS/text streams. Add FastGPT+Xfyun voice configs (including state-enabled preset), SuperTTS support, and context sync for interrupted turns. Refresh the voice demo with a state indicator and collapsible audio delta websocket log groups.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Xin Wang
2026-05-28 11:32:20 +08:00
parent b14ef64665
commit 9e2374f492
18 changed files with 1596 additions and 195 deletions

View File

@@ -118,6 +118,10 @@
<span class="indicator__dot indicator__dot--bot"></span>
<span class="indicator__label">Bot</span>
</span>
<span id="state-indicator" class="indicator indicator--state">
<span class="indicator__dot indicator__dot--state"></span>
<span id="state-label" class="indicator__label">State -</span>
</span>
</div>
<button id="clear-btn" class="btn btn--ghost" type="button">