Plugins

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.

Persistent conversation outline: per-turn questions and final replies, keyword filter, one-click jump, light/full history modes, and Ctrl/Shift+click to open the same position in the Trajectory view.

Export sessions to Markdown/JSON for review, replay, and per-session cost summaries.

Session timeline down the left of the conversation: every user message at a glance, current-message tracking, hover preview of the message and its reply, click to jump, collapsible.

Replace dsh's built-in web search with search MCP servers (Tavily/Brave/Exa/Perplexity/DuckDuckGo/custom), configured from the web Settings page. Disables the built-in DeepSeek search provider while enabled.

Two-way Slack messaging (notify/channels/inbox/reply) over Socket Mode, no public callback needed.

Short-video sidebar: native player, series navigation, precise history replay.

Multi-channel IM gateway plugin for DeepSeek Harness (dsh): DingTalk / QQ / WeChat(iLink) with QR-scan binding, streaming replies, and a unified ctx.imGateway service. 为 DeepSeek Harness 提供钉钉/QQ/个人微信多 IM 通道接入。

Voice-announce the final reply on Windows (SAPI5 natural voices) and macOS (system voice); skips reasoning and tool calls, one-line npm install.

Git Bash shell tool for Windows: runs commands through the bash bundled with Git for Windows, with timeout, sandbox, output truncation, and background jobs, replacing the slow pwsh tool and the WSL-only bash tool.

Customizable brand area for the Web UI: replace the whale logo and DeepSeek wordmark with local images, and edit the HARNESS badge text (double-click to change, right-click to reset).

Per-host personalization for DSH: custom instructions, local long-term memory, and reply-tone presets.

Test/extract/safe-replace/statically explain regexes without executing code.

Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.

Render local image paths from assistant replies inline in the message body (9 formats, click-to-zoom lightbox, adjustable size).

A Chrome-dino-style runner for the DeepSeek Harness Web UI: play while the agent replies, score from 梁子 to 梁圣 on a persistent progress strip.

XiaoTangYuan, an in-game AI companion for single-player games: understands the game screen, chats by text or push-to-talk, and speaks replies aloud; Stardew Valley is supported, with Don't Starve Together and Oxygen Not Included integrations in progress.

IM channel bridge: WeChat (ilinkai) / QQ / Feishu with proactive push — wake the channel bot from scheduled tasks and deliver AI replies to your phone.

GPT Image 2 `image_gen` with Codex subscription OAuth by default or explicit API-key mode: developing card, up to three live API partials, durable attachment replay/lightbox/download, text-only model output, and bounded credential-safe requests.

Faithful port of the hermes-agent MEMORY.md / USER.md mechanism for DSH: bounded dual-bank memory (2200/1375 chars), a single `memory` tool (add/replace/remove/batch), frozen-snapshot injection per session, nudge reminders, DSH-native JSON storage — zero external dependencies, zero LLM cost.

Dialog-style model picker for the DSH Web UI: fuzzy search, collapsible provider groups, favorites with a favorites-only filter, and a thinking-level dropdown, replacing the built-in model selector with official UI primitives and DSW tokens.

Replay-aware per-turn model usage and session cost for DeepSeek Harness

Self-editing desktop workbench for DeepSeek Harness: a full dsh web replica with an edit mode in which the agent modifies the workbench (patch layers, plugins, UI) with hot reload.

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.