dsh-quality-review
AI response quality review for DeepSeek Harness: audits each finished assistant turn with an independent reviewer model and steers the agent to fix unreasonable output (up to 2 review rounds).
119 results
AI response quality review for DeepSeek Harness: audits each finished assistant turn with an independent reviewer model and steers the agent to fix unreasonable output (up to 2 review rounds).
Event-driven development automation, offline standards, CI adapters, and quality gates for Cordis plugins in DeepSeek Harness.
DeepSeek Harness 实时 AI 自审插件:报错/警告连同时间、错误码、会话、用户原话、AI 动作与工作区写入日志目录,并主动通知 AI
Privacy-minimal provenance receipts for DeepSeek Harness workspace instructions
DSH hot-plug execution engine: a reliable install/enable/disable/rollback/audit service for plugin marketplaces, agents, and host plugins (execution layer, not a marketplace).
Static DSH plugin compatibility audit before installation, plus bounded Loader lifecycle observation
Non-intrusive safety belt for DeepSeek Harness: blocks API keys pasted to the agent, blocks secret writes, tracks leak events, and offers a workspace health scan. 非侵入式安全护栏:拦截粘贴给 Agent 的 API 密钥、写入拦截、泄露追踪与工作区安全体检。
Fail-closed DSH compatibility guard for redundant GPT/Codex sandbox escalation arguments
拒绝 AI 味的 UI 设计:21 主题 + 四动词(构建/audit 审计/redesign 重构/study 提取 DNA)+ 57 个 slop 测试门 + 预输出自我批评——拒绝所有 LLM 训练成的分布默认值。受 Nutlope/hallmark(25.8k★ MIT)启发。
DSH LLM response-stream injection/pollution filter: hard-block rare Unicode scripts (Track A) and score-based disposal of control chars / protocol markers / script mixing / spam keywords (Track B) on the llm/stream waterfall.
Enterprise-grade Zero-Trust Authentication, LAN/Public Access Control & Security Gate Plugin for DeepSeek Harness (DSH).
Native Auto Review for DeepSeek Harness with automatic host compatibility selection
DeepSeek Harness plugin: a masked password input panel in the Web GUI. The agent calls the password_prompt tool, the browser pops an HTML password panel, and the typed value is returned to the agent — no interactive terminal needed.
Plugin insight center — one answer to '哪些值得装': requirement matching (plugin_guide), environment recipes (recipe), health scoring (plugin_rank), static security scanning (plugin_audit), and a single install verdict (plugin_verdict)
Structured, machine-readable CI output for DeepSeek Harness (dsh): session event capture with JSON/NDJSON reports, JUnit XML, semantic exit codes, artifact collection and privacy redaction. Ships as a dsh profile bundle and a standalone CLI.
Fifth DeepSeek Harness mode with configurable Codex, Claude Code, or DSH audits, user-approved remediation turns, progressive Cordis/skill elevation, safety pauses, and Web/TUI review controls.
Hawkeye Scan Workbench - AI-driven source-code security scanning for DeepSeek Harness (DSH): 5 model tools + /hawkeye web UI + JSON/Markdown/HTML vuln reports. Zero-dependency Cordis plugin.
Multi-workspace sandbox for DSH: automatically grant file-write access to ALL registered workspaces — add a workspace in the UI, write to it immediately, no config needed.
Maestro Guard — pre-execute safety gate: native DSH approval prompts, parsed command-surface rules, decision journal
DeepSeek Harness plugin: installs the 'wsl' agent preset — the Windows WSL variant of the standard preset that routes the bash tool through Windows Subsystem for Linux (WSL), with automatic shell discovery and sandbox-aware gating.
Pre-install supply-chain provenance checks for DeepSeek Harness plugins: verify the tarball you're about to install matches the source you read, before any code runs. Never executes the audited package.
X-ray for your DeepSeek Harness — diagnostics for what's actually loaded, why, and what it costs: per-plugin context-tax attribution, per-request token ledger, skill catalog pricing, dependency cascades.
Named user credentials for DeepSeek Harness: model-facing credential tools, secrets behind the ctx.credentials seam, DSH_CM_* shell variables, and a Settings → Credentials page
A safety harness plugin for DeepSeek Harness (DSH): protected-path enforcement, trash-based safe_delete with undo, last-known-good composition snapshots, pre-restart composition checks, and an audit journal.