Repository Issue Activity (beta)

#663 Docker fails to work (sh: vite: not found)

#662 master notes

#661 Rationale for using Llama-3.1-Nemotron-70B-Reward as the Puppeteer state encoder

#656 test

#657 Add REFUTE scientific critique + calibration benchmark

#592 Integration: Clarvia AEO scoring for agent tool quality validation

#653 Non-streaming chat completions fail against Anthropic-backed OpenAI-compatible endpoints on long-running turns (HTTP 400 "Streaming is required")

#652 Research tool idea: BGPT for scientific evidence in ChatDev agents

#650 CodeReviewModification never shows the programmer the six review regulations, so fixes are made blind to the checklist they are re-reviewed against

#646 Feature: Persistent cross-project memory via Dakera — agents recall prior related work

#645 Test

#644 SuperCompress: Cut LLM token costs by ~65% with open-source prompt compression

#631 [Help Wanted] Design review: spec-to-epic decomposition workflow with subgraphs, custom Python tools and local LLM

#638 Arbitrary file write and delete via unsanitized upload filename in the ChatDev workflow server

#640 Puppeteer seems to always produce identical selection and highly simlar workflow

#571 Launch聊天界面，如果页面刷新之后内容就丢失了，这个能改成在执行中的任务页面刷新也能恢复当前聊天内容，然后继续完成任务吗

#642 Dependency hardening: pin minimum safe dependency versions

#637 [Security] Arbitrary File Loading and Logical Hijacking via Unvalidated --path Parameter

#636 Federation Partnership — Runtime Open Federation (open task market + USDC on-chain rewards)

#633 Add HVTracker trust badge to README

#626 刷新页面Bug

#616 选择function tool的时候不能滚轮或者鼠标下滑

#622 Caching Issue with subgraphs

#621 Cannot select "literal", "loop_counter" and "loop_timer" due to scroll bug in node-type dropdown.

#569 Workflow appears to trigger the server to restart leaving the webui waiting indefinitely