dsh-multi-workspace
Multi-workspace sandbox for DSH: automatically grant file-write access to ALL registered workspaces — add a workspace in the UI, write to it immediately, no config needed.
151 results
Multi-workspace sandbox for DSH: automatically grant file-write access to ALL registered workspaces — add a workspace in the UI, write to it immediately, no config needed.
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。
DeepSeek Harness (DSH) host-layer plugin: detects and auto-fixes Windows PowerShell command syntax mistakes — bash constructs, broken line continuations, pasted prompts, CRLF pollution — then executes the corrected command through the host shell seam under the normal sandbox/approval policy
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.
Seam-aligned background command execution for DeepSeek Harness — run_command via ctx.shell under the session sandbox policy, auto-promotion into ctx.jobs
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.
DeepSeek Harness plugin: installs the 'wsl' agent preset — the Windows WSL variant of the standard preset that routes the bash tool through Windows Subsystem for Linux (WSL), with automatic shell discovery and sandbox-aware gating.
What can this MCP server actually do? Inspect its real capability surface, seal it, and get told when it changes. Never invokes a tool; gives the server a minimal environment.
Stent MXC sandbox sidecar for the DeepSeek Harness
Localize leftover DSH UI chrome to Chinese (command palette descriptions, permission presets, reasoning effort) at the display layer, and detect when the official build adapts them
Pre-install supply-chain provenance checks for DeepSeek Harness plugins: verify the tarball you're about to install matches the source you read, before any code runs. Never executes the audited package.
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.
Transport-layer data masking for deepseek-harness (dsh): sensitive values never leave the process — the model sees placeholders, you see real values restored live in the stream.
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
Persistent credential vault for DeepSeek Harness (DSH): manage API tokens, server logins, and site credentials in one settings panel. Secrets live in the DSH credential store and are consumed by the model via vault_status / vault_get tools.
Don't hand over the whole machine, just the decision blocking it: unattended DeepSeek Harness approvals and ask_user_question prompts reach your phone as Feishu cards, desktop first, outbound only.
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)
Privacy protector for DeepSeek Harness: per-session toggle, syntactically pseudonymize PII before it reaches the model, restore after response.
Lock, verify and govern AI agent skills: a DSH plugin that makes the agent check what a skill can do before installing or updating it, and notice when it changes.
DSH plugin: a codex-style apply_patch tool (*** Begin Patch / *** Update File / *** Add File / *** Delete File) injected into the model toolset through DSH's built-in sandbox, with a settings card to choose injection scope (off / GPT models only / all models).
Pre-write reuse firewall for DeepSeek Harness: before the agent writes a new helper/service, surface the existing implementations that already cover that intent. Deterministic retrieval (no LLM) backed by the Auto_code_audit capability channel.
Audit an agent harness against the harness-evaluation criteria, with machine-enforced evidence validation.
Say the secret handshake: DSH subagents start on the Minimal two-tool condition to unlock DeepSeek's full RL-trained strength, then get the whole toolbox.
Governed platform access for DeepSeek Harness — no credential on the machine