dsh-failbook
失败账本 — DeepSeek Harness 工具失败记录、签名聚类与失败感知重试拦截(含 Web UI 面板)。Failure ledger for DeepSeek Harness: capture, cluster, persist and learn from failed tool calls, with a failure-aware retry guard and a Web UI panel.
223 results
失败账本 — DeepSeek Harness 工具失败记录、签名聚类与失败感知重试拦截(含 Web UI 面板)。Failure ledger for DeepSeek Harness: capture, cluster, persist and learn from failed tool calls, with a failure-aware retry guard and a Web UI panel.
DeepSeek Harness bundle that routes real sandbox escalation prompts through a dedicated approval reviewer
Independent Codex Guardian-style approval reviewer for DSH.
Tavily search provider for DSH with full search-control mapping, credential-backed key UI, and guarded rc.6 compatibility patches.
文档-代码一致性守护(Document-Code Consistency Guard):审计仓库的版本号/更新记录表/结构树/模块清单/测试计数/文档间交叉引用,检测漂移并按严重度输出修复建议。全程只读。
DeepSeek Harness guardrail that limits how many files an AI coding agent can edit per turn
Mingleng mcpguard for DeepSeek Harness 鈥?the first security plugin for DSH. Scans skills and MCP configs for prompt injection, homoglyphs, hidden Unicode, dangerous shell and credential leaks.
上下文治理一体化插件:/context 命令 + ctx.contextMeter 服务 + 剪枝工具(prune_candidates/apply/expand/guard/stats)+ 两条提醒通道(上下文提醒 / 压缩告警,状态落盘跨重启去重)
Pre-install supply-chain poison scanner for DeepSeek Harness plugins: AST analysis (NodeSecure JS-X-Ray) + deobfuscation decoder + regex heuristics to catch credential exfiltration, dynamic code execution, obfuscated imports, and install-time scripts.
Unofficial DSH context guard and SearXNG search adapter maintained by xoykor
Stop runaway agent loops in DeepSeek Harness: denies repeated identical tool calls and enforces a per-agent call cap, outside the model where instructions cannot reach.
Secret-scrubbing guard plugin: irreversible regex redaction of secrets before session-log persistence and model requests
dsh-chatroom kit plugin: dsh-weave Fix1-Fix4 patch guard + chatroom_* agent tools + /dsh-chatroom host RPC.
Research-first assistant for DeepSeek Harness: gently nudge the agent to investigate docs / code / community before edits, detect blocked research, and record every hint in the session log.
禁止在 edit/write 写入内容中使用匹配正则的字符,extraTools 可额外配置拦截更多工具。可在 cordis 配置文件里配置正则与报错文案。host 单半身。
Stavros RedTeam for DeepSeek Harness (DSH) — authorized red-team persona + scope-guarded pentest tooling (persona, 24 subagents, methodology and 78 zero-dependency guard tools).
Agent discipline guard for DeepSeek Harness: loop circuit-breaker, token-cost fuse, route-switch warning and plan approval — enforced at the harness boundary, so the model cannot talk its way past them. / DSH Agent 纪律卫士:循环熔断、成本熔断、路由警示、计划门四道硬闸门。
DSH web plugin: search and read an Outline knowledge base from conversations, with approved, whitelist-guarded document writes.
Static and runtime security guard for the DeepSeek Harness: scans plugins and workspaces for malicious code, context injection and token waste (block/warn/clean), intercepts dangerous runtime tool calls and prompt steps, and exposes /scan, plugin_scan, the scan web panel and a user-managed allowlist. Fully static analysis — never executes scanned code.
Real-time repetition guard for DeepSeek Harness (DSH): stops model generation when the same string repeats >=10 times in the streamed output. 实时检测 DSH 大模型流式输出中的重复内容,同一字符串重复十次以上立即停止生成。
Provider-backed automatic approval review for DeepSeek Harness.
A dsh policy plugin that gates kubectl writes by kubeconfig context: hard-deny irreversible verbs outside local clusters, ask for the rest.
保险区 Vault Wall — 让 DeepSeek Harness 无法感知、无法触碰用户指定敏感路径的隔离墙插件(隔离墙 + 人在回路审批 + 执行后验证 + 循环纠正 + 可回滚规则)
OpenViking memory & context bundle for DeepSeek Harness: auto-recall, session capture, threshold commit, offline outbox replay, self-contained MCP tool bridge, viking:// URI guard.