fix(dingtalk): use voice recognition text instead of raw audio binary

When DingTalk sends a voice message to the bot, the callback JSON contains
a 'recognition' field with the speech-to-text result (powered by Qwen).

Previously, LangBot only extracted the 'downloadCode' to download the raw
audio binary and passed it as 'file_base64' to LLM APIs, which caused
400 errors since most models don't support this content type.

This patch:
- Extracts the 'recognition' field from DingTalk audio message content
- Uses it as plain text input to the LLM instead of raw audio
- Falls back to audio binary only when no recognition text is available
- Fixes duplicate text issue for audio messages with recognition

Fixes voice messages returning 'Request failed' on all LLM models.
This commit is contained in:
haiyangbg
2026-04-08 23:23:27 +08:00
parent b894842736
commit de4d14fee3
2 changed files with 26 additions and 3 deletions

View File

@@ -71,7 +71,8 @@ class DingTalkMessageConverter(abstract_platform_adapter.AbstractMessageConverte
yiri_msg_list.append(platform_message.Image(base64=element['Picture']))
else:
# 回退到原有简单逻辑
if event.content:
# 对于音频消息content 来自 recognition 转写文字,在下方音频处理块中统一处理
if event.content and event.type != 'audio':
text_content = event.content.replace('@' + bot_name, '')
yiri_msg_list.append(platform_message.Plain(text=text_content))
if event.picture:
@@ -81,7 +82,11 @@ class DingTalkMessageConverter(abstract_platform_adapter.AbstractMessageConverte
if event.file:
yiri_msg_list.append(platform_message.File(url=event.file, name=event.name))
if event.audio:
yiri_msg_list.append(platform_message.Voice(base64=event.audio))
# 优先使用钉钉自带的语音转写文字recognition字段
if event.content and event.type == 'audio':
yiri_msg_list.append(platform_message.Plain(text=event.content))
else:
yiri_msg_list.append(platform_message.Voice(base64=event.audio))
chain = platform_message.MessageChain(yiri_msg_list)