shinalok 6435af5837 Separate TTS text from metadata tokens in respond() ...

Filter __meta dict tokens from TTS accumulator so progress messages
([LangGraph], thinking blocks, source references) are displayed in chat
but not read aloud. Answer tokens continue to accumulate in tts_text.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-05-31 23:08:22 +09:00

.gitignore

Fix TTS to use pure response content without meta tokens

2026-05-31 23:05:28 +09:00

api_client.py

Add cross-platform TTS support and update dependencies

2026-05-30 23:54:41 +09:00

app.py

Separate TTS text from metadata tokens in respond()

2026-05-31 23:08:22 +09:00

requirements.txt

Add cross-platform TTS support and update dependencies

2026-05-30 23:54:41 +09:00

S

Description

No description provided

233 KiB

Languages

Python 100%