16 results
dsh-passwords: a server-grade gateway that turns DeepSeek Harness into a multi-tenant platform — remote access + automatic HTTPS, per-subuser permissions & quotas, sandbox enforcement, first-run setup, SQLite auth with at-rest encryption, rate-limit and audit log (bilingual zh/en UI)
DSH tool-call compatibility: strips sandbox_permissions/justification from tool-call arguments for third-party models (GPT etc.), and lets the user skip possibly-stuck tool calls with an LLM-facing notice.
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
DeepSeek Harness plugin: real-time Feishu/Lark notifications when a DSH session pauses for user interaction (permission asks, questions, fatal errors).
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.
DeepSeek Harness config sync: export/import DSH settings, API credentials, profile plugin patches and user agent presets as portable local bundles or a single password-encrypted file (AES-256-GCM + PBKDF2-SHA256).
Password gate for dsh-web: opening the web port requires a username/password login; account credentials are stored salted+scrypt-hashed and AES-256-GCM encrypted in a local config file under $DSH_HOME. Host-only cordis plugin, no dsh source changes.
DSH profile plugin: unconfined (GPU-capable) session sandbox plus per-operation user approval for writes outside the workspace or to protected files.
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.
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.
Single-process multi-user workspace view partitioning for DeepSeek Harness: JWT-in-cookie login wall, per-user workspace/session filtering, and admin user management.
DSH plugin: anonymize workspace-external file paths before model requests with user confirmation
Static security audit for dynamic Cordis plugins in DeepSeek Harness (DSH): rule-based source scanning, risk reports injected into tool results, and user-approval escalation before activating high-risk plugin packages.
A fourth permission option for DeepSeek Harness sessions: selected-workspace-write, where the user opens the workspace directory tree and toggles which directories the agent may write to.
Enforce recycle-bin-only deletion on Windows: block del/rm/Remove-Item and other disk-erase commands, forbid automatically emptying the recycle bin, and stop + ask the user when the recycle bin or disk is full.