27 results
Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness — a capability seam (ctx.memory service + local SQLite provider + memory tool + frozen snapshot injection), not another memory warehouse
DSH local security audit tool: read-only scans of config, credential metadata, plugin provenance, session structure and network exposure; redacted, reproducible, locatable risk reports
唯稳律（Weiwen's Law）通用因果引擎（白箱呈现）—— DeepSeek Harness (Cordis) 插件实现
DSH sandbox extension: configurable trusted writable roots outside the workspace, read restrictions, and capability-based command allow-listing for sandboxed CLI commands. 为 DSH 默认沙箱增加「沙箱授权目录」「禁读规则」与按能力类判定的「命令放行」规则。
Audit the DeepSeek Harness plugin list by origin (official vs self-installed): a /plugin-audit command plus a Source tab in Web Settings
Native memory for DeepSeek Harness — auditable facts with evidence chains, powered by StateCore
Agent-decided approvals for DeepSeek Harness: a workspace-write base permission mode where an independent approval subagent judges every sandbox escalation (risky operations are rejected), with a configurable approval model and a per-session audit trail in the conversation window's 审批 tab.
自然语言查询 + 商业智能报表插件 for DeepSeek Harness：在 dsh-mysql 连接底座之上，提供 Text2SQL 自然语言查库、15+ 图表类型、Dashboard 仪表盘、指标/维度管理、多维分析、自助分析、报表导出、审计日志与数据权限。Natural-language data queries + enterprise BI reports for DeepSeek Harness: Text2SQL, 15+ chart types, dashboards, metric management, multi-dimensional analysis, self-service analysis, export, audit log and data permissions.
KISS's Law (Weiwen's Law) universal causal engine (white-box presentation). DeepSeek Harness (Cordis) plugin implementation.
Autonomous (auto) mode permission classifier for DeepSeek Harness: a Claude-Code-auto-mode-like classifier over tools/pre-execute and approval/request, a selectable 'auto' permission preset, LLM semantic judge, git checkpointing, agent discipline guidance, and a web control page in Settings → Plugins.
Out-of-tree DeepSeek Harness bundle: an executable implementation of the Harness Engineering Methodology (HARNESS-METHODOLOGY-SPEC v1.0) — agent-discipline prompt section + artifact scaffolding tool + compliance audit tool.
Bridges vendor agent SDKs into DeepSeek Harness as selectable LLM providers. Works in any DSH mode; DSH keeps its own prompt, tools, sandbox and approvals.
Solve the AI goldfish brain: a personal memory layer for DeepSeek Harness — preferences, project conventions, workflows, and error lessons, stored locally as auditable, evidence-backed Markdown/JSON. 解决 AI 金鱼脑：偏好、项目约定、工作方式与纠错教训的本地可审计记忆层。
Database connector bundle for DeepSeek Harness (dsh): SQLite/PostgreSQL/MySQL connections, schema introspection, read-only safety, write approval gate, and a JSONL SQL audit trail.
DSH sandbox extension: protect declared workspace subpaths (e.g. .git) from writes, and optionally grant extra writable roots under workspace-write, enforced for sandboxed CLI commands and the write/edit tools. 为 DSH 沙箱增加工作区子路径只读保护, 并支持在 workspace-write 下声明额外可写根.
Portable DSH WebUI skill security inspection with local rules and optional model review
Security and connection-stability overlay for DeepSeek Harness SSH workspaces
Scan installed DeepSeek Harness plugins and grade stability risk (hook surface, startup work, preflight health, packaging, dependencies). 扫描已安装插件的稳定性风险（钩子面/启动任务/预检/打包/依赖）。
DeepSeek Harness plugin: a citable append-only JSONL of filesystem touches — path, op, sha256 before and after — carrying no file contents
Cloud-backed cross-session memory for DeepSeek Harness: structured entries + vector retrieval persisted to S3-compatible object storage (AWS S3 / MinIO / R2 / OSS), with local cache projection, approval-gated writes and auditable trails
A fail-closed, auditable approval policy plugin for DeepSeek Harness
DeepSeek Harness (dsh) plugin: real AST-based scan of installed plugins for malicious-intent patterns, with an optional periodic schedule and auto-quarantine on critical findings. Advisory-by-default, not an antivirus signature database.
Permission matrix for DeepSeek Harness: 3 sandbox modes x 4 approval strategies = 9 selectable presets, with a global default, a separate LLM-robot default, four-tier risk policies, password-gated approval for high-risk operations, audit log and git checkpoint.
Audit a DeepSeek Harness session against the 14 consciousness indicator properties of Butlin, Long, Elmoznino, Bengio et al. (2023) and report an L1-L5 level