taixf/backend/main/xiaozhi-server/core/providers
hailin 12b4994ac0 fix: extract content from ASR JSON before sending to Antaf
ASR wraps user speech as JSON {"content":"...", "language":"zh", "emotion":"..."},
extract only the content field instead of sending raw JSON to Antaf bridge.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-05 20:32:45 -07:00
..
asr add backend code 2026-04-05 19:01:15 +00:00
intent add backend code 2026-04-05 19:01:15 +00:00
llm fix: extract content from ASR JSON before sending to Antaf 2026-04-05 20:32:45 -07:00
memory add backend code 2026-04-05 19:01:15 +00:00
tools add backend code 2026-04-05 19:01:15 +00:00
tts add backend code 2026-04-05 19:01:15 +00:00
vad add backend code 2026-04-05 19:01:15 +00:00
vllm add backend code 2026-04-05 19:01:15 +00:00