Plugins

Per-model reasoning effort (off/minimal/low/medium/high/xhigh) for GPT, Codex, Gemini and OpenAI-compatible models. Installs a helper, not a runtime adapter: run enable-capabilities.ps1 once per profile (Windows) and restart — it declares the levels in ~/.dsh/settings.yaml, with a disable script and a backup to revert.

Display companion for dsh-vision-router: keep Auto Vision routing, and put a square picture button on each original model row. Does nothing unless dsh-vision-router is installed.

Ghost-text completion for the composer: FIM suggestions stream in inline after a typing pause (SSE, first token rendered immediately), Tab accepts one word at a time and Shift+Tab takes all, in-flight requests are truly cancelled on retyping or Esc. Plus two-layer typo checking: a browser-local dictionary scan (Chinese wrong phrases, English misspellings and proper-noun capitalization, user-defined per-browser entries) with a debounced LLM context pass, underlined in red in the text with per-item navigation and click-to-fix.

DeepPilot companion plugin for DeepSeek Harness: use DSH from a native iPhone app over an authenticated, direct connection to your own Mac.

DSH web plugin: a green/red status dot left of the composer model select showing whether DeepSeek API is currently in official peak time (red) or off-peak (green). Click for a live dashboard: countdown, 24h day track, stat tiles.

ego lite for DeepSeek Harness, with a memory it keeps: the agent recalls what it learned about a site before it acts, promotes a script that worked into a reusable site tool, and hands you the keyboard through a real dsh prompt when a page needs a human.

Chat branch tree plugin for DeepSeek Harness: mind-map of conversation branches, group folders, archiving and compaction preview.

One-click silent DSH restart button in the composer input bar. DeepSeek Harness plugin (dsh-plugin).

All-in-one UI enhancement layer for DeepSeek Harness web: prompt library with quick-insert and management, two-step AI polish, predicted-reply dock with click-to-send, MCP tool management, scheduled automation, smart session titles, adjustable chat width, full-width AI messages without gray background, auto-collapse for long user messages with smooth expand/collapse animations, and scene-specific entrance animations across all plugin surfaces.

Adds a 'file' row to the DSH web GUI composer plus menu: pick images (native composer thumbnails) or arbitrary files (video/audio/Office/PDF, up to 50MB), stored in the DSH home and inserted into the draft as native file reference chips the agent can read

DeepSeek balance & token-cost plugin for DeepSeek Harness (dual-face): query official balances of every DeepSeek provider (multi API key), compute costs (last question / session / today-project / today-all) from token usage with a user-editable price tabl

High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness — a drop-in upgrade over dsh-compaction-basic.

Edit an earlier question and run again from that point in the DeepSeek Harness web GUI: forks a child session whose history ends before the edited turn and prefills the composer, leaving the original conversation untouched

AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.

把长文本渲染成图片发送，利用每图 384 token 封顶压缩 LLM 输入 token，专为DeepSeek Harness设计的插件；Pack long text into images to cut LLM input tokens (384/image cap) — a DeepSeek Harness plugin.

Periodic prompt injection for the DeepSeek Harness Web GUI: every N model invocations (conversation turns and tool-call steps both count) the plugin injects a user-configured prompt as a model-visible user message; the first injection happens at conversat

Firefox browser control for DeepSeek Harness: token-authenticated WebSocket bridge + text-first browser_* tools driving the user's own Firefox via the companion AMO extension

Linux crontab-style scheduled tasks for DeepSeek Harness: the LLM can schedule recurring workflow runs and prompt-driven tasks with cron expressions, plus proactive task suggestions inferred from the chat.

LLM compatibility auto-healer: detects 400 errors from incorrectly declared model capabilities (thinking/reasoning) on transit/gateway providers, then idempotently patches `llm-pi-ai` config and suppresses thinking on the next request — no restart needed. Full settings UI for every pi-ai compat field.

Fork any session into a different agent preset from the conversation header: a preset picker creates a new child session mounted on the chosen preset, inheriting the source session's completed turns.

修复在DSH中使用自定义提供方模型时会遇到的toolcall json schema被错误解析后不断产生错误toolcall的问题，同时提供长时间等待toolcall跳过的功能。

Reusable prompt presets for DeepSeek Harness: manage a preset library in Settings and inject any preset at the start of the composer draft with one click. / DeepSeek Harness 提示词预设库：设置页管理、对话框一键注入。

Aemeath theme for the dsh web GUI — sakura pink × icy cyan × pearl white × deep navy, dual light/dark, animated pulsing composer border, and wallpaper backdrops

OpenAI-compatible gateway adapter and dialect fixes for DeepSeek Harness