Plugins

Ollama Cloud provider for DeepSeek Harness: adds the chat route on install, publishes each model's own thinking levels for the composer effort control, keeps the model list current from the endpoint (/api/tags and /api/show, cached for offline boots), shows the account allowance with an API-key field in the Models page and sidebar, and offers Ollama's web search and fetch as selectable DSH web providers.

Codex-style appearance for the DSH Web interface: window edge hairlines and shadows, sidebar colours and row alignment, a model picker with a reasoning-effort power rail, composer and right-panel geometry, a full-page settings-modal pass, a Trajectory view exit, and a settings card for theme, accent, background, foreground, fonts, sidebar translucency and contrast.

A fake-ip-aware ctx.web fetch provider that takes over the stock http provider id: a hostname is accepted when every DNS answer is a placeholder inside the proxy's fake-ip block (198.18.0.0/15 by default), so web_fetch works under mihomo/Clash TUN mode without disabling fake-ip or setting proxy environment variables. IP literals and private, loopback and reserved destinations stay blocked.

本地生图工作台,零订阅费:开自己的 API 生图(任意 OpenAI 兼容接口,零订阅),画布排版+修图/擦除/去背景/OCR/转矢量,可编辑 PSD/AI 交付,Photoshop/Illustrator 图层级双向桥接

Multi-threaded downloader plugin for DeepSeek Harness with bundled aria2: probes the target for Range support, then picks aria2 (4 or 8 connections by file size) or falls back to curl.

Worktree Space: puts a workspace task that spans one or more Git repositories in its own task space directory - each repository in it gets its own worktree on one shared task branch; the space is registered as a DSH Workspace so sessions start right there, and multiple tasks run side by side without interfering. Finishing a task can merge the work back into each repository's target branch, remove the worktrees, and file whatever Git does not track in an archive directory you choose.

Gaokao countdown blackboard: counts down the days to the gaokao on a desktop blackboard widget that collapses into a slim bar on double-click, and quizzes random knowledge cards while the agent works; open Markdown knowledge-card framework — drop .md files under subject/category folders and they load automatically, with cross-links, favorites, priority subjects and importing your own knowledge base.

Universal Model Context Protocol (MCP) bridge for DeepSeek Harness: connects agents to stdio/sse/websocket MCP servers with a 10k dormant scale engine, sub-millisecond BM25 tool search, dynamic token budgeting, and a real-time web UI dashboard.

Grok-compatible web search with retained source pagination, Context7 and Exa documentation lookup, bounded page extraction, site mapping, offline research planning, and read-only diagnostics.

A judgment core for DeepSeek Harness: a cognition loop that gives every decision a source and attribution and drives planning to a close, hippocampus memory that condenses running experience into knowledge (journal ledger, episodic archive, low-confidence decay), judgment identity responsibilities in the architecture (consistent rubric, judgment bound to its source), and an A2A memory-management team via dsh-linghun-assembler. Requires DSH ^0.1.0-rc.7 (rc.2 supported).

Wallpaper skin for the DSH Web UI: image background with opacity, mask and blur controls.

Visual goal lifecycle for the DSH web UI: a composer dock to create, multiline-edit, pause, resume, complete and clear session goals with live round progress, plus a phase-dot composer entry and a settings-page goal overview.

RainbowSpeak — a flowing rainbow marquee border around the chat composer card, driven by a conic-gradient ring. Live settings for speed, width, seven color schemes, direction, sides and breathing, plus session-state awareness that reacts to running, attention, error and celebration moments.

Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.

Sign in to DeepSeek Harness with a Claude Pro/Max membership (no API key), downscale Anthropic request images to a 2000px long edge, slim /compact summarizer payloads, and show 5-hour/weekly plan usage plus DSH message counts.

Proxies the loopback-only dsh web onto a LAN port so phones and other machines can reach it, with an optional access password that browsers type in and the bundled Android client unlocks with biometrics. Adds a LAN-access settings page with QR codes, inlines dsh-web-mobile (MIT, attribution kept) for the mobile layout, and the Android client in the same repository adds finish/approval notifications, voice input and a home-screen widget.

Run several DeepSeek Harness sessions side by side, hand work from one to another, and watch the whole collaboration on one read-only canvas.

Genshin Impact Yoimiya theme: two hand-tuned palettes, a procedural fireworks particle layer, and a local music player that reads your own files — songs and covers are never uploaded. Warm syntax colors and a hand-drawn goldfish brand mark; apart from the wallpaper every pixel is CSS gradients and hand-written SVG.

Calls your own chat.deepseek.com account as a second model from DSH: ask a question, analyze a file's line range, and check login state, plus a runtime skill and a settings-page login panel.

The Mayfly terminal UI bundle for DeepSeek Harness

Runs PowerShell scripts through base64 encoding, so quotes, $, backslashes and CJK survive as written. Same sandbox channel as the built-in pwsh tool.

Cross-session TODO board as a draggable floating panel: tasks are grouped by working directory and reorderable by drag, each one carries a run mode (remind only, continue in the current session, or open a new session in the same directory), up to four attached images sent to the model as real image attachments, and an optional local time it may run at; two checkboxes track AI-done and user-verified, and the agent picks up the next unfinished task in that directory when it finishes one.

Shipped with cc-safety-net-style mechanical safety-net rules appended; supports both no-model and model-assisted security review, in modes such as 自动审查 (auto-review) and 机械直通 (mechanical pass-through). P0–P4 deterministic-first permission gate with permissive tier, learning sedimentation and approval-history UI; hard-deny credentials and protected paths, auto-allow internal read-only tools.

Graceful restart + client auto-reconnect + cross-restart goal continuation for DeepSeek Harness (dsh). After a plugin update dsh-phoenix restarts dsh at a safe idle boundary, keeps the browser page connected, and resumes a running goal so a task can keep