6vision 458b1a1d88 fix(wechatmp): merge cached text segments in passive reply ...

In subscription account passive reply mode, WeChat allows only one reply per request. Multi-turn agent output was cached as separate entries, forcing the user to send an extra message to fetch each one. Now drain and merge all consecutive cached text segments into a single reply; media still returns one at a time.

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-05-30 14:41:51 +08:00

..

dingtalk

feat(voice): enable TTS on Weixin / DingTalk / WeCom Bot with text-then-voice delivery

2026-05-21 17:29:26 +08:00

feishu

feat(agent): support user-initiated cancel for in-flight agent runs

2026-05-26 23:36:09 +08:00

qq

fix(wecom_bot): compat with old websocket-client

2026-03-21 14:03:17 +08:00

telegram

feat(channel): support telegram bot

2026-05-28 15:07:09 +08:00

terminal

fix terminal channel

2024-06-15 16:34:32 +08:00

web

feat(models): support claude-opus-4-8

2026-05-29 10:19:45 +08:00

wechatcom

feat: support channel start in sub thread

2026-02-13 12:38:52 +08:00

wechatmp

fix(wechatmp): merge cached text segments in passive reply

2026-05-30 14:41:51 +08:00

wecom_bot

feat(agent): support user-initiated cancel for in-flight agent runs

2026-05-26 23:36:09 +08:00

weixin

fix(scheduler): make cron pushes survive restart on weixin channel

2026-05-25 12:15:57 +08:00

channel_factory.py

feat(channel): telegram first version

2026-05-28 12:10:00 +08:00

channel.py

fix: default agent mode to enabled

2026-05-21 11:14:19 +08:00

chat_channel.py

feat(agent): support user-initiated cancel for in-flight agent runs

2026-05-26 23:36:09 +08:00

chat_message.py

refactor: remove unavailable channels

2026-03-16 11:05:45 +08:00

file_cache.py

feat: optimize agent configuration and memory

2026-02-02 11:48:53 +08:00