What it does
DSH 升级后幂等重打的模型调优补丁:DeepSeek 推理拓宽为 7 档、workflow/ralph 子 agent 默认模型指向 deepseek-v4-flash。Idempotent DSH model-tuning patch: 7 reasoning levels & workflow/ralph default deepseek-v4-flash.
Installation
dsh plugin --profile web add github:TOBYCAI/dsh-patch-reasoningInstall 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.
——2735f4ed4a17The scan result is valid for the scanned commit. New commits within 7 days are tolerated (the rating still counts); after 7 days without a rescan the badge shows outdated.
`[](https://www.dsh.so/artifact/dsh-patch-reasoning/)`Disclaimer: automated static analysis, not a security guarantee. Always review what you install.
Risk details
• Static heuristic scan: pending
• Dependency vulnerabilities: —
• Hardcoded secrets: —
• Supply chain risks: —
Activity
Last commit 2026-08-21 · activity: Active
• Repo created: 2026-08-21
• Stars: ★ 0 · Forks: 0
• Health: Active — committed within last 30 days
