agentscope-ai / agentscope-ai/QwenPaw

[Bug]: Reasoning and Tool Usage Should Appear Before Final Reply

Open
#2,758 3 comments 0 reactions 0 assignees View on GitHub
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

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.