How to use dsh-trajectory-governor
专为 pro 模型使用 Closed-loop trajectory policy plane for DeepSeek Harness
This article is auto-derived from indexed fields (wiki / faq / compatibility_json), not freshly AI-generated.
This article is derived from the plugin's already-indexed fields (wiki / faq / compatibility_json / readme), not freshly generated by AI. Source field is noted at the end of each section.
Quick start
专为 pro 模型使用 Closed-loop trajectory policy plane for DeepSeek Harness
— source: plugins.ai_summary
Install & verify
dsh plugin --profile web add @chunsi-m/dsh-trajectory-governor
Run the command above in your DSH Web Profile. Then enable the plugin in the plugin list.
— source: plugins.install
Key points
- Task Episode 与连续性关系;
- workspace revision 与完整 benchmark 证据;
- 同规格、带容差的性能回归判断;
- 重复调用与无新信息轨迹;
- scoped 工具能力面;
— source: plugin_wiki.readme_en (fallback readme_raw)
Pitfalls
Review the upstream repo before installing. This guide is auto-derived from indexed fields and may lag the latest release. If anything contradicts the official docs, treat the upstream source as authoritative.
— source: general rule