Qwen-Agent · Issues· 538 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #962
[DeepPlanning] LLM report→JSON conversion silently drops drafts and copies the few-shot budget (2400/…/6700), inflating travelplanning scores
Updated Sep 14, 2026 - #936
RFC: Optional tool lifecycle hooks for auditable execution receipts
Updated Sep 9, 2026 - #783
coder.qwen.ai "Publish to GitHub" fail,s
Updated Sep 8, 2026 - #889
MCPManager: Missing timeout on future.result(), no thread-safety on clients dict, fragile shutdown
Updated Sep 4, 2026 - #622
关于Router实现多Agent的bug
Updated Sep 4, 2026 - #954
MCP: no OAuth 2.0 support for remote MCP servers (SSE/streamable-http), static headers only
Updated Sep 2, 2026 - #949
NameError / ImportError with streamable-http MCP server (Incompatible with MCP SDK v2.0.0)
Updated Aug 25, 2026 - #941
Docs: DashScope thinking mode requires thinking_budget, docs only mention enable_thinking
Updated Aug 23, 2026 - #945
EvalPort: portable tool-call test suites for Assistant/FnCallAgent
Updated Aug 23, 2026 - #938
long chats not loading
Updated Aug 16, 2026 - #767
Tool fetch does not exists
Updated Aug 16, 2026 - #904
Avoid persisting or logging API keys from run_server.py
Updated Aug 16, 2026 - #939
Feature Request: Artifacts / Live Preview Panel for Code & Document Generation
Updated Aug 15, 2026 - #558
使用工具调用时，有概率传输的json结构不全
Updated Aug 8, 2026 - #935
[Feature Request] Optional verified-answer mode for local Qwen models
Updated Aug 6, 2026