Plugins

Tripo 3D skills for DeepSeek Harness — generate engine-ready 3D assets from a text prompt or a reference image via tripo-cli, with texturing, rigging, retopology and format conversion in one pass.

A DeepSeek Harness Skill built on the official command-line tool maa-cli for MaaAssistantArknights (MAA), enabling direct control of MaaCore to automate daily tasks in Arknights.

Switch the language of the agent's thinking/reasoning process (chain-of-thought): 简体中文, English, Русский, Français, Deutsch, Español, 日本語, 한국어 and more, or auto-follow the system locale. Adds a Settings → General row, a system-prompt instruction (per-prompt assembly, applies to new sessions), and the /thinking-language command.

Concurrency guard and monitor for DeepSeek Harness: FIFO queue when concurrent model requests reach the limit, per-day persisted stats with error-kind classification, and interruption detection for abandoned streams.

Unified Godot asset and project-goal management for DSH: godot_* model tools, a /gap REST surface, and a better-sidebar UI with asset manager, scene-tree viewer, and Git panel.

Technical documentation agent preset for DeepSeek Harness: template-driven writing with a self-learning template library, AI-flavor removal for tech docs, and a quality-assurance toolkit (document audit, cross-document consistency, numbering resequencing, version sync, PDF and Word export, screenshot automation).

Message-level full-text search across DSH sessions via an FTS5 trigram index (user / assistant / steering / tool with per-kind filters), deduplicated results across fork/continued sessions, read-only context preview with auto-scroll to the focused message, one-click jump to the real session, and incremental/full index rebuild with health check; zh/en i18n follows the Host locale service.

RLM mode for dsh: recursive sub-agents via a unified rlm() function — spawn, await, and chain child agents as first-class Python calls. Adds a persistent IPython kernel with tools.* bindings and context-as-variable.

Enhanced vision toolbox: 14 pixel-level vision tools (describe, ground, detect, crop, pixel-diff, OCR, long-screenshot OCR, vectorize, colors, cutout, screenshot, present, materialize, html-screenshot) driven by one OpenAI-compatible endpoint, with clean \[图片: path] bridge markers, content-safety classification and rate-limit auto-retry.

Requires DSH >= 0.2.0-rc.1. Annotate selected text in assistant messages and official file/Diff views, then submit drafts with official composer text and attachments as one Session user message; the model answers each annotation in order with hoverable reply chips.

Passcode marketplace inside DeepSeek Harness: enter a six-character code to unlock and install plugins shared by creators, plus themes, backup, updates and diagnostics.

Copy selections from assistant messages as Markdown, preserving links, LaTeX sources, and code-fence language info.

Password-gated public access for the DSH Web GUI through quick or named Cloudflare Tunnels, with HTTP/WebSocket proxying and an in-app directory picker.

Free voice closed loop for the Web UI: browser SpeechRecognition mic input with live interim results plus read-aloud speaker buttons and auto-read for assistant replies, zero configuration and no API key.

Fully-local image understanding & OCR via macOS Vision Framework: `ocr_image` (text, table layout + coordinates) and `view_image` (scene, faces, QR) — paste multiple images into the web input box or pass path/URL/base64; images never leave your Mac.

Cross-session archive: overview workbench, folded timeline, subagent lineage, full-text search, rule+LLM summaries, ZIP export, live tracking. Native session-page embeds: turn rail, docked right panel (live mode, pinned to original session on switch), rename (official-synced), conclusion digest, health monitoring + persistent header chip (idle / active / tool-wait / stalled). dsh v0.1.2+: fuses with the official TurnNavigatorRail — vector-icon info chips (duration, tool calls, errors, thinking) plus lazy tool distribution inside the official preview card, right-click opens the workbench; the classic piano-key strip is on by default and delegates unloaded-turn jumps to the official auto-load engine; the official rail can be hidden entirely. Settings dialog section with 10 tunable behavior params.

Import Claude Code sessions, skills and plugin assets into DSH as native resumable sessions, and export or sync DSH sessions back to Claude Code JSONL.

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

Multi-provider quota & balance glass card for the DSH sidebar footer (11 providers incl. StepFun / Xiaomi MiMo / Claude with one-click browser login; Step Plan credit). Installable from the dsh-plugin marketplace (GitHub topic "dsh-plugin") or via file: l

A liquid glass UI plugin for the DSH desktop app. Works alongside most wallpaper plugins. Currently supports dark mode only.

Paper reading workbench: a paper library, the PDF beside Markdown notes and one dedicated AI session per paper. Highlights and region screenshots go straight into notes; select-to-ask sends the passage with its page; notes are editable in place with autosave; sessions can be combined into a Summary.

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.

See which provider really serves your requests behind the Cline gateway, and how much of your Cline Pass quota is spent — a DeepSeek Harness plugin and a pi extension in one repository.

Circuit breaker for idle agent turns: watches agent/assistant-stream and cancels a turn that produces only reasoning — no text and no tool call — after 45s, after 80000 reasoning characters, or on a degenerate repetition pattern (exact repeat unit, sentence-template repeat, sparse repeat, or 6-gram density). On trip it injects a continue instruction that requires the next action to be a tool call, and ships 11 regression cases plus per-gate tuning.