Plugins

Secure remote access for the DeepSeek Harness Web UI: a login gate, MFA/TOTP, signed session cookies, optional admin/user/guest roles, in-browser workspace selection, and allowlisted remote file previews.

Access the dsh web UI over LAN: HTTP/HTTPS/WS forwarding plus TLS (self-signed or custom certificates); adaptive Brotli/gzip compression for HTTP and permessage-deflate for WebSocket; half-open WebSocket probing keeps mobile clients from going stale after backgrounding; launch-token auto-injection lets LAN devices connect without copying the token; DNS-rebinding protection + loopback-only upstream allowlist.

Private loopback DSH Web gateway for Tailscale Serve, Cloudflare Access, and Headscale TCP Serve, with exact principal allowlists and guided fail-closed setup.

Private Tailscale access for DeepSeek Harness Web that allowlists users from the trusted Tailscale-User-Login header that Serve injects, with a loopback-only gateway and guarded Serve setup.

Two-way iMessage channel for DeepSeek Harness over Photon: sender allowlisting, session commands, in-chat approvals and questions, and a Settings page for device authorization and hosted-line setup.

MySQL connector for DeepSeek Harness: configure multiple connections in the settings page with per-connection table allowlist and write permission, switch the active connection from the composer, and expose mysql_query / mysql_tables / mysql_execute tools to every agent preset.

Identity-gated Tailscale access to the Web GUI with dsh still bound to loopback: a 127.0.0.1 proxy published by `tailscale serve` admits a request only when the Tailscale login it stamps is allowed, with an optional per-device allowlist, so the privileged /api methods behind the loopback check — Settings, Models, Plugins — answer without dsh being told to trust a remote host.

A guarded local fetch provider for the ctx.web seam — the backend dsh does not ship for its own web_fetch tool. Every redirect hop is re-resolved and checked against the non-routable ranges, with a streamed size cap and a content-type allowlist.

Feishu/Lark IM channel for DeepSeek Harness agents with native thinking-process messages, approval cards, live goal and todo cards, workflow fan-out lines, session text search, and background job and subagent settlement notices. Access is bounded by the Feishu app's own visibility scope by design — anyone the app admits can drive the agent and answer its approvals unless the optional sender, group and approver allowlists are filled in.

Deterministic keyword routing, allowlisted model switching, and an isolated image_gen channel for DeepSeek Harness.

Fail-closed Feishu (Lark) channel bridge: chat with a bot, get dsh agent turns back — with opt-in human-in-the-loop tool approval (Allow/Deny cards before every bash call, fail-closed timeout). Official-Python-SDK-only integration (exact-pinned); deny-by-default allowlist, webhook signature/timestamp/replay verification, per-chat sticky sessions; daily latest-SDK compatibility canary; bilingual docs.

Feishu/Lark gateway for DeepSeek Harness with topic-persistent conversations, live execution cards, image and file inputs, in-chat approvals and questions, source allowlists, and durable one-time or recurring agent tasks created in natural language.

Adds subagent_route and subagent_fork_route delegation tools where the model itself picks the provider/model route for each child; the deployment only sets the spawn/fork backend, background policy and allowedProviders allowlist, while continuable children and background jobs reuse the official send_message / job_output tools.

Windows desktop automation for DeepSeek Harness: accessibility-first observe/act loop with 30 standard tools (element/coordinate targets, auto/a11y/event strategy routing), superseded-observations and no-replay safety semantics, persistent kill switch, RuntimeId/rect-drift stale protection, chat cards and a floating panel (live ops, frame wall, env auto-detect settings), tiled vision describe for low-res models, JSONL audit trail and a pid allowlist. Requires Windows 10+ and Python 3.9+ with uiautomation and pillow (installable from the settings page).

Archived-session management, task-stop notifications, an update checker, model routing (keyword rules + allowlist-gated model_route), multi-task scheduled triggers (heartbeats and fixed-time tasks), and a DeepSeek-style message scroll nav for the dsh web GUI.

Bridges Feishu, WeCom aibot, DingTalk Stream and QQ Gateway chats into dsh agents over outbound long connections, with an im_status tool. Ships with an empty user allowlist, which means EVERYONE can drive your agent — set allowedUserIds before exposing a bot; IM input can run tools on the host.

WeChat Official Account channel for DSH — WeChat messages run agent turns and the answers are pushed back through the customer-service message API, with signature-checked callbacks and an openid allowlist.

Advises or applies allowlisted Windows portproxy for a WSL listen port, preferring the kit :3081 relay and launch token for local dsh UI.

Launches allowlisted Windows apps such as VS Code, Explorer, and browsers from WSL.

Read and search bounded log output from allowlisted SSH servers and log roots without exposing arbitrary remote commands.

Security-focused Feishu (Lark) channel for DeepSeek Harness: allowlisted remote-agent access with workspace-scoped paths, symlink checks, risk-based approvals, session isolation, redacted logs, and bounded message queues.

Translates visible Chinese UI and content in DeepSeek Harness Web, using a browser-local OPUS-MT model for session titles, workspace names, messages, search results, and opted-in plugin prose while keeping remote translation limited to allowlisted UI labels.

Mobile pairing remote for DeepSeek Harness: E2EE companion over dual-plane allowlisted RPC (LAN, Tailscale, optional Cloudflare Quick Tunnel or self-hosted rendezvous).

Runtime security gate on the tool pipeline: denies calls naming hosts outside an egress allowlist, redacts credentials from results at the canonical value rather than only the rendered content, and appends every decision to a JSONL audit log; ships in monitor-only mode.