mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-04-25 11:18:22 +00:00
- Move time.sleep() -> asyncio.sleep() from Planned to Completed Features - Clean up duplicate entries in TODO.md Ensures completed async optimizations are properly tracked.
1.7 KiB
1.7 KiB
TODO List
Completed Features
- Launch the sandbox only after the first file system or bash tool is called
- Add Clarification Process for the whole process
- Implement Context Summarization Mechanism to avoid context explosion
- Integrate MCP (Model Context Protocol) for extensible tools
- Add file upload support with automatic document conversion
- Implement automatic thread title generation
- Add Plan Mode with TodoList middleware
- Add vision model support with ViewImageMiddleware
- Skills system with SKILL.md format
- Replace
time.sleep(5)withasyncio.sleep()inpackages/harness/deerflow/tools/builtins/task_tool.py(subagent polling)
Planned Features
- Pooling the sandbox resources to reduce the number of sandbox containers
- Add authentication/authorization layer
- Implement rate limiting
- Add metrics and monitoring
- Support for more document formats in upload
- Skill marketplace / remote skill installation
- Optimize async concurrency in agent hot path (IM channels multi-task scenario)
- Replace
subprocess.run()withasyncio.create_subprocess_shell()inpackages/harness/deerflow/sandbox/local/local_sandbox.py- Replace sync
requestswithhttpx.AsyncClientin community tools (tavily, jina_ai, firecrawl, infoquest, image_search) - Replace sync
model.invoke()with asyncmodel.ainvoke()in title_middleware and memory updater - Consider
asyncio.to_thread()wrapper for remaining blocking file I/O - For production: use
langgraph up(multi-worker) instead oflanggraph dev(single-worker)
- Replace sync
Resolved Issues
- Make sure that no duplicated files in
state.artifacts - Long thinking but with empty content (answer inside thinking process)