agentscope-ai / agentscope-ai/QwenPaw
[Bug]: Reasoning and Tool Usage Should Appear Before Final Reply
Open
bug
- Dominant language
- Python
- Stars
- 34.9k
- Forks
- 3.1k
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 225
Description
## CoPaw Version
1.0.0.post2, but issue persists since early versions
## Description
The current display logic for AI responses is inverted. Actually, final reply appear before reasoning and tool usage, always
## Component(s) Affected
- [ ] Core / Backend (app, agents, config, providers, utils, local_models)
- [ ] Console (frontend web UI)
- [x] Channels (DingTalk, Feishu, QQ, Discord, iMessage, etc.)
- [ ] Skills
- [ ] CLI
- [ ] Documentation (website)
- [ ] Tests
- [ ] CI/CD
- [ ] Scripts / Deploy
## Environment
- **CoPaw version:** v1.0.0 post2
- **OS:** Debian GNU/Linux 12
Contributor guide
Assessment
This issue has not been assessed yet.