What it does
0-LLM compaction for DeepSeek Harness (dsh): deterministic atomic reference-graph pruning of agent history — exact compression ratio, selective forgetting, recall instead of rewrite. 压缩阶段零 LLM 调用的确定性上下文压缩插件:原子引用图剪枝、选择性遗忘、压缩率精确兑现,即插即用 CompactionEngine。
Installation
dsh plugin --profile web add github:yoza10635/dsh-argpInstall method: GitHub · not yet tested in container (L3+)
Compatibility
| DSH Version | Status |
|---|---|
| not stated | Declared — not tested |
Requirements
- • Node.js: not stated
- • DSH: declared "not stated"
- • External credentials: none detected
Security Report
Automated static scan, not manual review.
No security scan record for this plugin yet. Newly indexed plugins are scanned by the daily pipeline.
——f17d54dbae5eThe scan result is only valid for the scanned commit. If the latest commit differs, the badge shows outdated until the daily pipeline rescans.
Disclaimer: automated static analysis, not a security guarantee. Always review what you install.
• Static heuristic scan: pending
• Dependency vulnerabilities: —
• Hardcoded secrets: —
• Supply chain risks: —
Activity
Last commit 2026-08-17 · activity: Active
• Repo created: 2026-08-18
• Stars: ★ 1 · Forks: 0
• Health: Active — committed within last 30 days
Source
GitHub: github.com/yoza10635/dsh-argp
