dsh-auto-review
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent decides allow/deny on the approval answerer chain, with fail-closed fallback and full session-log audit.
76 results
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent decides allow/deny on the approval answerer chain, with fail-closed fallback and full session-log audit.
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
Role-based Codex / Claude Code / ACP subagent providers for the DeepSeek Harness: continuable children, durable session recovery, per-role product permissions, delegation with a permission ceiling, and a declarative role library.
A read-only mirror for installed DeepSeek Harness plugins: capability inventory with evidence, cross-plugin conflicts, a diff of what changed since the last scan, and an upgrade preflight that tells you which profiles still boot on a newer DSH
Plugin Hub for DeepSeek Harness (DSH): a graphical app-store inside the Harness Web UI — browse, search, and one-click install GitHub dsh-plugins, with local ratings, dependency impact graphs, audit logging, and a development scaffold
Private, zero-trust gateway for DeepSeek Harness Web: loopback-only proxy, exact principal allowlists, and provider-agnostic onboarding
Security scanner for DSH plugins: static and semantic passes over plugin source, DSH-specific attack-surface rules, npm audit, batch scanning, and an HTML report with per-finding severity and evidence.
Tensorlake sandbox execution providers for DeepSeek Harness
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。
Net Access permission preset for DeepSeek Harness (Windows): HTTPS works inside the sandbox while file writes stay confined like workspace-write.
Run the DeepSeek Harness agent's filesystem, bash and PTY terminals inside a Docker container, so execution state survives a harness restart.
Observe-only hash-chained evidence receipts for DeepSeek Harness
Fail-closed microsandbox microVM provider and model-facing guest tools
DSH bundle: grok-geo GEO brand audit agent skill — AI-search visibility, recommendations, citations, competitor presence and content-gap diagnosis across 17+ AI engines (ChatGPT/Perplexity/Claude/Gemini/豆包/DeepSeek/Kimi/文心一言...), shipped as a bundled skill provider. Zero-dependency.
Security for DeepSeek Harness in two layers: source-backed pre-install vetting plus fail-closed runtime guardrails and HMAC-chained audit logs. Zero runtime dependencies.
DSH plugin: strip GPT-family tool-call sandbox_permissions that are not strictly wider than the current session.
OMV Audit Desk: an evidence-first vulnerability audit workbench for DeepSeek Harness
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.
Retrieved ≠ injected: CBDC-gated memory for DeepSeek Harness — decides how memory is USED (use/verify/ignore decisions, feedback learning, full audit); local SQLite + FTS5, bounded, no extra model call
Find and audit DeepSeek Harness (DSH) plugins inside the agent — live `dsh-plugin` topic search + source audit with trial-to-production install plans.
Content-addressed, value-redacted policy drift evidence for DeepSeek Harness
Register models, assist with portraits, and select the Agent model from a secret-free catalog for DeepSeek Harness.
Content-addressed audit indexes across independent DeepSeek Harness evidence producers