Plugins

Edit and regenerate: adds an edit action to user message bubbles, regenerating from that message with images and files carried over and the original model inherited.

Ollama provider for language models and embeddings, with model discovery, loading, and unloading in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.

Alibaba Cloud DashScope provider for Qwen language models, embeddings, reranking, speech, and image generation through native APIs in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.

A possibly useful DSH token usage plugin: cross-session stats on where your tokens went - four headline figures, context length distribution, a 12-week heatmap and weekly trend, plus workspace and model rankings; it also ships a next-turn token forecast and a draft-optimization feature.

White kitten accountant on the window sill: shows the tokens and money for each answer and for the whole session, the money the prompt cache saved, the context size against the model window, the next peak/off-peak price change and the live DeepSeek balance; it purrs when stroked, reacts while the agent works and synthesizes all of its sounds.

Registers /daily, which sends the model to read the newest bili-scroll report and say what it understood instead of repeating the text; a sidebar panel runs the same command. Needs the dsh-bili-scroll plugin to have written reports into ~/.dsh/bili-duty/out, otherwise /daily finds none.

Reasoning-effort slider for the DeepSeek Harness composer: drag through the thinking levels the current model declares and release to write the chosen level into the session. An auto band escalates one level after a tool error and another after two or more, and optional model routing picks a provider/model per task type.

Groups the composer model picker into customizable official, plugin and relay sources, with hierarchical navigation, an Our Free Model four-category view, and a dedicated settings page. The Our Free Model view needs dsh-our-free-model installed.

Effort slider in the model menu, a live tokens-per-second and turn-total readout beside the running status, a per-answer input/output/cached report, and a completion notification when a turn finishes, for the DeepSeek Harness Web GUI.

Adds a draggable off / low / high / max reasoning-effort slider to the composer model row and applies the selected level to the current DSH session. The slider only appears for models that offer all four effort levels.

A plugin for dsh: once ask_user_question times out, the content you entered will remain in the UI or model context.

Computer Use enhancement plugin for DeepSeek Harness (DSH). 纯 JS 视觉差分、网格位置编码、长程任务闭环与人机共驾授权。

A dsh plugin: after a timeout, the time distribution from the previous iteration is fed to the model, enabling the model to autonomously identify and adjust its behavior; if the introspection cost becomes too high, the plugin enters a dormant state, allowing the model to be restarted at any time.

Sync one sub2api instance's groups, keys, and models into dsh-llm-pi-ai provider routes: panel-driven login (password / OAuth), one relay key one provider.

模型故障转移队列：P1 限额/限流/不可用时自动切到队列下一个模型继续，全部图形界面配置 | Model fallback queue for DeepSeek Harness: auto-switch to the next model when the current one hits quota or rate limits

Install Desert Ant Labs on-device models as DSH tools and skills, with per-platform capability gating

Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.

Appends a tiny ice marker to the end of every sentence the model writes, chain of thought included, and plays a short synthesized sound for each one.

Adds a draggable lucky-block button to the DeepSeek Harness web UI. Single-click plays zero-cost little performances (popups, a fake blue screen, daily fortune, trivia, cold jokes, music, and a set of visual stunts); a 1.4-second long-press mines the block open and starts a new session to write a random paper, read the news, invent something, or spin a short story. It also appends a "lucky block" choice to the model's multiple-choice questions and rolls a random pick, reversible by saying "rollback". Block appearance and event weights are adjustable in settings.

Union IM bridge for DSH — an independent implementation uniting the capability sets of community peer plugins (xmanrui/dsh-im, MichengAI/dsh-im-connect). Drive your agent session from 15 channel adapters across 12 platforms (including email; WeCom/DingTalk/QQ each contribute two: bot + self-built app or notify tier) — WeChat (official iLink QR bind), Feishu/Lark (long-connection + streaming cards; the voice tier requires system ffmpeg), Telegram, Discord, WeCom intelligent bot & self-built app (signed callback), DingTalk (stream + AI Card and custom-robot notify), QQ official bot (plus notify tier), Slack (Socket Mode), WhatsApp (Baileys QR pairing; the dependency ships as an optionalDependency of the plugin package), Matrix, iMessage (macOS only), Email (IMAP/SMTP thread routing). The cross-version narrow waist auto-adapts settings gen1/gen2/gen3 across hosts 0.1.2-rc.1→0.2.1-rc.2 (12-tag enum; rc.2 verified by a real desktop-profile install with double read-back) using capability probing only, never version branches. In chat: a 25-command panel, tool-approval and question loops answered in the originating chat (deny-by-default, initiator-only, 5-min expiry), image/file input gated on host model metadata, deliverable file return, a delivery log with bounded retry (uncertain is never re-sent), proactive delivery and fragment composition. It also splits the native sidebar into self-owned Tasks / Channels tabs (standing down entirely when another plugin already owns the slot), registers an `im-concise` agent preset plus reply sanitisation that keeps GenUI fences and raw HTML out of text-only chats, renders `svg` fences to PNG images, guards model choice with an allowlist, and mirrors each turn's final answer to notify channels via `/relay` (addressed by account ID or alias, never guessed on ambiguity). Secrets are one-way into the vault and never echoed back. npm: `dsh-im-union`.

Pre-execution guard: a `tools.guard` predicate decides allow, ask or refuse per permission preset for dangerous shell commands (git hook bypass, catastrophic `rm`, download-and-run, git history rewrites) and for edits to credential paths or to files the turn never read, and hands the model the reason plus a working alternative.

Rewrites the model-visible copy of system, developer, user, assistant and tool messages into stable HMAC placeholders before a request leaves the machine, while local session logs, the chat transcript and restored tool calls keep real values.

Replaces detected secrets (OpenAI, AWS, GitHub, PEM, Bearer) with deterministic, structurally valid honey tokens before they reach the model or the session file; adds manual marking for values the detectors miss, explicit user-visible restore, a cross-session canary alarm, and an opt-in JSONL log of substitution counts that never records the underlying values.

Outbound route pool for DeepSeek Harness. Ships 15 seed routes plus a 20-entry candidate pool covering 7 target kinds (GitHub raw/codeload/main, npm registry, PyPI index, HuggingFace, general). Routes are verified before use: upstream IP lists go through a TLS handshake with full certificate-chain validation (a bare TCP check can be answered locally and report dead IPs as healthy), and failures advance a cooldown ladder of 2/5/15 minutes with the fastest healthy route picked per target kind. Routes are applied by rewriting the URL with one of four rules (prefix, registry, index, host-replace), reaching git, pip, npm, pnpm, gh, curl and wget through three paths: the shell seam (download commands the model runs through the bash tool are intercepted and rewritten automatically; commands wrapped by the pwsh tool, and fetches made by the host itself or the renderer, are not covered), two registered tools the model can call directly (line_pool_status, line_pool_run), and child-process spawn. Multi-line commands keep their line breaks and only the download segment is touched. URLs carrying credentials (user:token@host) are never rewritten, so tokens are not forwarded to third-party mirrors. No global config is modified. A sidebar panel lists every route with latency, failure reason and cooldown countdown, supports per-route retest and enable/disable, and shows live TUN/proxy status from network-adapter and loopback port checks. The candidate pool is re-verified every 24 hours so newly usable routes are added and dead ones dropped. 570 tests, 87% line coverage.