Plugins

Automatically generates and displays images in the DSH chat via API channels or local CLIs (mmx / codex / agy), and can also recognize images using the corresponding CLI.

Kiro model provider with Builder ID, Identity Center, Google, GitHub and credential-import sign-in, automatic token and profile refresh, account usage, live model discovery, selectable reasoning efforts, streaming tool calls, provider stop-reason and context-overflow handling, and token accounting that uses Kiro's exact counters when it sends them and otherwise scales the context-usage percentage it does send by the model's advertised window.

Wakes the main agent after any DSH restart so interrupted work resumes automatically — adds a restart tool and an optional canary that validates the boot and aborts with an alert before a broken restart.

File-based cross-session memory: plain Markdown memory files with automatic retrieval injection, format-compatible with Claude Code's CLAUDE.md and memory files, so migrating is a manual file copy.

TencentDB Agent Memory integration with conversation capture, structured memory extraction, automatic recall, and memory and conversation search tools.

Automatic cross-session memory for DeepSeek Harness, backed by a local EverOS service.

Cristiano Ronaldo desktop pet for DeepSeek Harness: a chibi Portugal number 7 mascot in a bottom-right overlay whose animation follows the agent state — dribbling while tools run, thinking during a turn, waiting at approvals, diving on errors — and jumping in a SIU celebration with a host-process sound when a turn completes; it can be dragged, looks at the cursor on hover, dives on a triple click, and a settings panel manages several pets and imports custom spritesheets. It also runs as a borderless, always-on-top native Windows window that keeps living after the browser is closed: hovering shows the current workspace and conversation title, double-clicking opens the Harness page in Edge, and dragging, mouse-wheel resizing and a right-click menu work there too, sharing position, size and behaviour with the web panel. Pet sheets may use any cell resolution and scale preserving aspect ratio (atlas.scaling: smooth | pixelated). v2.2 adds a video route — feed it a clip (green screen or ordinary footage) and its real motion becomes the pet animations, via automatic backdrop sampling, chroma keying with spill suppression, motion-based segment splitting and union-bbox alignment; already-extracted PNG frames work too, with no video decoder installed, and the clip audio can be cut into per-action sounds. Pets can also be published to the community gallery under the DPSL-1.0 sharing declaration, and installed from it in one click.

Automatic session retrospective: after a conversation wraps up, distills useful experience into reusable skills stored in the skill library for the model to call, with signal-accelerated triggers, manual runs, an approval mode, and skill-library governance (archive/restore, never deletes directly).

Download-and-run Electron desktop build (macOS/Windows installers): no Node.js or terminal needed, tracks upstream `@deepseek-ai/dsh` releases automatically, with built-in web UI and auto-update.

Rewrites the Chinese copy of a market-installed plugin into English using a model already configured in the harness — automatically when the plugin is installed, then live-reloaded. Each file is translated in one whole-file pass, validated by a real parser where one exists (node --check for JavaScript, JSON and YAML parsers otherwise) and handed back to the model with the error for up to three repair attempts; files above 48 KB, or that never parse, fall back to a line-range pass that checks every returned line against the original for structure. Trigger phrases and locale tables can optionally be preserved rather than translated, and the untouched original is kept beside the file as a .zh.bak.

Network optimization for the DSH web UI: reduces transfer size with caching and compression to greatly speed up page loading, plus a connection-drop indicator and automatic reconnection. Ideal for users pursuing peak performance or using unstable networks.

Version management for dsh: inspect the installed version against every npm channel or version line, install or downgrade in one click, stream the install log live (rollback-snapshot copy progress, npm extraction progress, elapsed time), roll back instantly from local snapshots, and automate the cycle with a policy engine (silent auto-update, execution windows, daily checks). Never stops npm mid-install — a wedged run is only stopped after an hour, and a half-committed global tree is detected and repaired from the pre-install snapshot automatically. Confirms before installing a found update, auto-restarts the host after install, and falls back to a mirror when the primary registry is unreachable.

Per-model proxy routing for LLM requests: selected models go through a proxy (Clash etc.) while the rest stay direct, with automatic retry on transport errors, 429 and 5xx, configured live from the settings page.

Talk to Excel in DeepSeek Harness: create, edit, repair, and verify spreadsheets by conversation, with automatic formula health checks after every edit.

Adds a take screenshot tool plus two optional automatic capture points, putting the screen into the conversation as an image block; requires an image-capable model.

Inline preview for \[图片: path] image bridge markers: after the marker renders, the image shows in chat automatically, keeping long instructions out of the conversation.

Proactive multi-model scheduling plugin: multi-source signal intake with dedup and urgency ranking, a four-way execute/defer/dismiss/ask-user decision engine, DAG plan generation with parallel model execution, quality reflection with automatic retry and model switch, long-term memory for task patterns and lessons, and strategy evolution via genetic algorithms with sandboxed evaluation and canary rollout.

Long-term cross-session markdown memory with an LLM-Wiki structure and a SOUL.md persona, injected at session start (by default only after the first user message and only in the active session), plus remember/recall/consolidate/forget workflows, an embedded memory skill, pack/unpack migration tooling, and an idle-time first-person recall nudge that surfaces real memories in a companion voice. Also gives the store observability and upkeep it lacked: a per-file boot-block budget that keeps the index routing table from being truncated, automatic last_access stamping so salience decay actually works, a read-only memory health dashboard (size, freshness, lint-parity checks), a declarative index compiler (pages declare summary:, one command re-lines the index), an interactive memory graph (page links plus shared tags, draggable, wheel zoom), structured queries (tag/type/salience/hot/stale filters), cross-link suggestions for pages that have no relationship yet, and a `checkup` report that ends in a prioritised action list. The boot payload was also cut by ~23% by moving operational detail into the on-demand skill.

Routes agent requests to configurable default, planner, and subagent models, automatically using the planner role in plan mode, with per-role reasoning effort and Web UI configuration.

Wraps Python virtual environment management commands: reduces the network and permission problems agents hit when managing environments through terminal commands, works across operating systems, and routes installs automatically through mirrors and local proxies. The tools are strictly confined by the granted read/write permissions.

一个可以让ai自动调用VLM(多模态模型)进行视觉分析的dsh插件。A dsh plugin that allows AI to automatically invoke VLMs (multimodal models) for visual analysis.

Automatic approval and review for tool calls that need approval: keyword buckets match red lines without context, then a judge model classifies what was requested and sends it to allow, reject or a human according to the matching row and risk level; a judgment that never ran always goes to a human, and rejections tell the model why.

Auto-resume for interrupted agent sessions: an ordered rule table routes by failure type (rate limit, quota, auth, context overflow, crashed orphan) to automatic backoff retry, model switch, resume after context compaction, or a stop-loss notification, with a visual rule editor and a full activity log.

Voice assistant for dsh web: say the wake phrase (e.g. "小鲸") to activate hands-free dictation — what you say is transcribed and typed into the chat box automatically. Supports spoken edit commands (send, clear, new line, stop reading) and reads assistant replies aloud in Chinese. Speech recognition runs locally in-browser via sherpa-onnx WASM, so it works offline without an API key.