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.
23 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.
为 DeepSeek Harness 增加介于 Workspace Write 与 Full access 之间的自动批准权限档:例行沙箱升级由分类模型一次性放行,危险或不确定的操作仍转人工审批。An auto-approval permission preset for DeepSeek Harness between workspace-write and full access: routine sandbox escalations are granted once by a classifier, while dangerous or uncertain requests still go to a human.
Password login gateway plugin for dsh web: auto-generated initial password with forced onboarding, login, password change with real request interception, and OTP two-factor authentication.
Model-based permission approval (approve-for-me) for DeepSeek Harness: an approval/request answerer backed by a separate reviewer model
WebUI-managed encrypted credentials for DeepSeek Harness: one file, plaintext until a password is set, then AES-256-GCM ciphertext under an Argon2id-derived key with SHA3-256 fingerprints; per-request decryption, unlock lockout, leak-guard output redaction, and shipped-code integrity self-checks.
DeepSeek Harness desktop popup plugin: shows AI thinking status in a bottom-right always-on-top card, alerts on permission requests and completion, with a DeepSeek-style UI
Gitee/GitHub AI 员工:issue 里 @ 机器人自动开发并提 PR;v1.2 新增代码安全扫描——配置仓库地址后按内置/自定义提示词扫描漏洞,去重后提交 issue。An issue-driven AI developer for DeepSeek Harness (Gitee & GitHub) with optional static security scanning (dedup + issue reporting).
Real-time attention alerts for DeepSeek Harness: a global banner plus flashing workspace entries when the agent is blocked (approval request / sandbox denial), with an audible chime and OS-level notifications for new blockers.
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.
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.
Access-password gateway plugin for DeepSeek Harness Web: every request on the gateway port requires authentication (no unauthenticated surface besides the login/setup page), first visit sets the password, and it can be rotated from the dedicated Security settings page.
Approval timeout for DeepSeek Harness: when a sandbox/escalation approval is not answered within a configurable period, the request is automatically rejected instead of waiting forever.
DSH web plugin: play a notification chime when the agent asks the user a question (ask_user_question / plan review) or requests approval (sandbox escalation, tool approval).
LLM pre-review for sandbox-escalation approvals: an independent-context LLM gate answers sandbox escalation requests before they reach the user, falling back to the user on any failure.
DSH task chime: play local sounds for approval/permission requests and task completion, fully configurable from the Web GUI settings. DSH 任务提示音:审批/权限请求与任务完成提示音,可在 GUI 设置中自定义声音、音量与冷却时间。
Secret-scrubbing guard plugin: irreversible regex redaction of secrets before session-log persistence and model requests
DSH plugin: anonymize workspace-external file paths before model requests with user confirmation
Corner approval popup: answer pending permission requests from any session while the agent window is away
Configurable auto-approval for DeepSeek Harness: intercepts approval/request and answers allowed-once/rejected by policy (allow-all / allowlist / deny-always), with a full audit log — so the human is only asked when the policy says so.
A DeepSeek Harness Web plugin for inspecting redacted LLM HTTP request and response traces.
Local, zero-network, fail-closed secret preflight for DeepSeek Harness model requests.
Tolerate redundant sandbox_permissions requests: a tool call asking to escalate to a mode that is not strictly wider than the session's standing mode runs as-is at the standing mode instead of failing with "not strictly wider". Genuine escalations still route through the approval flow.
Auto-reject unanswered permission requests with a model-visible timeout notice