Plugins

Cross-agent monitoring board for local AI agent sessions (cursor-ide, claude, codex, copilot, kimi and dsh itself) with session timelines, and message injection behind a default-off two-phase confirmation gate.

Single-model disable gate: hides denied models from DSH catalogs, blocks direct dispatch with an in-protocol error chunk, and exposes a settings UI for the denylist.

Feishu/Lark channel that drives DeepSeek Harness agents from chats: streaming rich cards with live thinking and tool steps, per-turn cost metering at DeepSeek peak/off-peak rates, one-tap approval cards, model-gated image intake, and QR onboarding without a public endpoint.

Command-triggered red/blue adversarial review for ANY plan (not quant-specific). /plan-adversarial <plan>: arms a gate that requires the agent to derive two independent subagents (red=attack, blue=defend), have them converge on a consensus plan with NO th

Connect a stock DeepSeek Harness install to DSH Cloud: device login plus a 20-model gateway provider. Commercial hosted service by AgentsDance AI — new accounts include 500 free credits.

Bidirectional RPC between DSH Host and Client through the native Connection and Typert Gateway, with targeted peer calls, cancellation, and connection lifecycle handling.

macOS desktop shell for the DSH web UI: a plugin plus a small Tauri/WKWebView window over the loopback web surface — real macOS fullscreen, single instance, external links delegated to the system browser, and browser-style zoom.

DeepSeek Harness (DSH) plugin that delegates coding tasks to the Claude Code and Codex agent CLIs and streams the whole run live — autonomous control, multi-account, automatic install, git worktrees, and any Anthropic-compatible endpoint.

Forge quality gates for DeepSeek Harness (dsh): task gates, read-before-edit, bash hazard interception and quality scoring, driven by the forge CLI through DSH's typed interception points.

DeepSeek Harness compatibility plugin for third-party OpenAI-style gateways: tolerates SSE streams that close without the [DONE] sentinel after a complete reply.

Mobile access gateway for the Web GUI: isolated child-process reverse proxy with a first-visit PC approval gate (admin-token auth, DNS-rebinding defense), LAN/VPN/WAN auto-detection with network-mode switching, QR-code entry, WebSocket forwarding, and narrow-screen UI adaptations (composer reflow, third-party plugin overlays, crypto.randomUUID polyfill).

Forwards a local dsh web UI to the public internet under a *.ds.hn subdomain (or your own self-hosted relay), gated by a login, with optional end-to-end encryption (PBKDF2 to AES-256-GCM).

Infrastructure as code: gated plan/apply, state and output inspection, and configuration validation via the terraform CLI.

Minecraft-survival game mode as a DSH agent preset: hard-settled HP/hunger/day-night/mobs, vanilla crafting gates and anvil repair, plus a browser status bar; built on the official preset plugin spec.

Langfuse observability for DeepSeek Harness (DSH): per-turn trace trees aggregated by session id, with prompt versioning and evaluation.

DeepSeek Harness (dsh) approval answerer backed by the agent-governance sidecar — every approval/request is decided by the deny-by-default gate, L0–L4 rules and the organizational audit chain.

DSH Web Usage Center with local SQLite history, HUD and dashboard, Hub account/quota snapshots, custom pricing and fee ledger, and CSV/JSON export, plus coding-plan OAuth and an optional loopback OpenAI/Anthropic gateway.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

Bridges the LiuHe MCP code toolkit (44 tools) into dsh web: repo_map, symbol search, edit_batch with tolerant matching, transactional edits with undo journal, and deterministic quality gates — backed by a crash-isolated Rust tree-sitter parse daemon and SQLite index.

Falsification-driven correction loop for agent sessions: risky work commits an evidence-checkable claim first, deterministic gates verify it, falsified claims force mutually exclusive replacement hypotheses with discriminating experiments, and every event lands in an append-only evidence ledger.

Commitment write-gate: operator-authored rules enforced before a tool call runs — a deterministic guard tier plus an LLM-judge tier, fail-closed by default, every block written to a contradictions log.

Multi-root workspace plugin for the dsh web GUI: attach several independent folders to one project workspace, manage them in a sidebar panel, and let agents read, list, write, and glob across every registered root through gated host-side tools. Hot-plugga

Self-learning habit engine for the DeepSeek Harness — detects user-correction signals, judges habits with a low-cost model on threshold, settles candidates behind a two-level human gate

DSH plugin: password gate for remote (non-loopback) /api access (passwordless by default), unblock the loopback-pinned privileged endpoints, restore everything on uninstall, and give the local 127.0.0.1 user the native OS folder picker for workspace selec