dsh.so
EN
English中文
dsh-better-model-thinking-control avatar

dsh-better-model-thinking-control

DSH 插件：为 OpenAI 兼容中转站按模型管理思考强度，并自动识别公开能力

PluginAI Models
Verification
L2 · Structured
Security
Medium
Health
Active
Trust
Silver

What it doesAI

DSH plugin to control per-model thinking effort for OpenAI-compatible APIs, auto-detecting public reasoning capabilities.

  • Uses DSH native settings.plugin.item, no repo changes
  • Supports off, minimal, low, medium, high, xhigh, max effort
  • Auto-fetches /models and extension reasoning fields

AI-generated from the repo README — for reference only.

Installation

dsh plugin --profile web add github:Guyao146/dsh-better-model-thinking-control

Install method: GitHub · not yet tested in container (L3+)

Compatibility

DSH VersionStatus
not statedDeclared — not tested

Requirements

  • • Node.js: not stated
  • • DSH: declared "not stated"
  • • External credentials: none detected

Security Report

Automated static scan, not manual review.

DSH.SO AUDITWARNINGdd90a9
Security reviewAutomated review · daily
WARNING

No critical findings, but warning-level issues were detected (file writes, remote imports, base64 decoding, downloads).

0 critical·1 warning·3 info·4 files scanned
Version binding
plugin version0.1.4dsh manifest
scanned commitdd90a929d10c2026-08-20
latest commitdd90a929d10c

The 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 New commits within 7 days are tolerated (the rating still counts); after 7 days without a rescan the badge shows outdated.

Disclaimer: automated static analysis, not a security guarantee. Always review what you install.

Second-opinion scan (vet · parallel evaluation)
vet: clean

vet verdict: vet: clean · score 100

  • R9 · info [heuristic] — 无出口常驻循环（含 await，可能是合法服务循环；交由 LLM 审计复核上下文）
  • R9 · info [heuristic] — 循环内 += 累加（字符串拼接可能 O(n²)）
  • R2 · info [likely] — require()（客户端加载器 factory 形参注入，DSH bundle 标准写法）

vet is advisory and does not change dsh’s four-tier level.

Risk: Medium0 critical · 1 warning · 3 info

• Static heuristic scan: done (4 files)

• Dependency vulnerabilities: requires deep audit (L3+)

• Permission sandboxing: requires runtime testing (L4+)

High-risk findings · 1 / 1

  • warningHTTP request to a raw IP addresslib/index.js:223
    try { url = new URL(req.url, 'http://127.0.0.1') } catch { return sendJson(res, 400, { ok: false, error: 'bad url' }) }

Heuristic static scan — may produce false positives. Review the source yourself before trusting.

Activity

Last commit 2026-08-20 · activity: Active

• Repo created: 2026-08-20

• Stars: ★ 0 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/Guyao146/dsh-better-model-thinking-control

Was this page helpful?