Plugins

Workspace drift awareness for DeepSeek Harness agents: detects external/user file changes and injects them into the agent context at step boundaries.

Rich Markdown notebook for the composer region: a tool-row toggle plus a CodeMirror editor card with Codex-style list editing, submitted through the conversation service.

Sanitizes leaked DeepSeek DSML closing tags from model text streams.

TRAE-style conversation rollback — per-turn checkpoints (10-turn sliding window) roll back touched files and truncate model context in place, keeping the same session id. Human-initiated only: a /rollback command or a per-turn Web button (works on interrupted turns too), with a preview listing each affected file and its action — restore, recover, delete, or skip.

Multi-language codebase intelligence for DeepSeek Harness and MCP-compatible IDEs: chat, search, audit, refactor, and board-ready reports from local code.

Workspace-wide sticky notes on an infinite canvas: notes are plain Markdown files, created manually, captured from conversations, or distilled by the AI, and can be handed back as context; ships 12 model tools and 5 bundled skills for creating, tagging, arranging, comparing and merging notes.

DeepSeek Harness adapter for Context Mode: in-process ctx_* tools for sandboxed code execution and an FTS5 knowledge base, plus context-window routing guidance.

人脑式上下文压缩逻辑，大幅减少长任务上下文占用以及token消耗

Compresses DSH time-context from ~280 chars to 46 chars by injecting a compact date line into the runtime-context snapshot; zero runtime dependencies.

Voice call assistant for the DSH Web GUI: a draggable floating call ball, browser-side VAD that sends each utterance after a pause, FunASR HTTP or streaming speech recognition, MiniMax or OpenAI-compatible TTS replies, an optional wake-word mode with auto-sleep, and task dispatch to separate subagent sessions with progress, stop, and spoken completion reports.

Side-ask drawer opened from a completed answer's action row: follow-up questions run in an independent, auto-archived session seeded with the prior conversation text (read-only, capped at 48,000 characters), leaving the main session untouched. The side session inherits the main session's model, switchable inside the drawer, with a context-usage ring.

Request-level one-time prompt injection without further context pollution. SillyTavern-style UI and data compatibility, keyword/regex/constant triggers, and a lore_lookup tool for on-demand searching.

Installs a Web-profile helper that diagnoses and writes MCP config so Codex, Cursor, or Claude Code can spawn dsh --profile codex.

Configurable image recognition for text-only DSH models: image messages are first transcribed by an OpenAI-compatible vision model (Base URL, model ID and API key set in a Settings section) and then passed to the main model as text, while image-input support is advertised. The API key auth scheme is selectable — OpenAI, Anthropic, Gemini or Azure style request headers — and a missing key is reported before any request is sent.

Vision bridge for text-only DeepSeek: send images (alone or mixed with text) and a fast tiny vision model describes them behind the scenes — the chat keeps the picture, DeepSeek sees only text. Pure plugin: uninstall restores everything.

Insurance company operations analyst — runs real solvency, profitability, embedded value (EV), investment risk and regulatory compliance calculations, not just text explanations.

Turns a Xiaohongshu, Douyin, TikTok, YouTube or X link into text: transcript with timecodes, on-screen text, a description and OCR of every image, caption and metadata. Mounts the hosted MCP server over streamable HTTP.

AST-based context compression, test log filtering, and token budget guard for DeepSeek Harness: strips redundant syntax, prunes noisy log lines, and enforces a token ceiling so the context window never overflows.

Parse Chinese e-invoice PDFs (XML attachment first, text-layer regex fallback) into structured JSON with amount cross-check, and generate expense reports (Markdown / xlsx).

Settings panel for global and per-workspace AGENTS.md, with identity and persona injection, runtime-context toggle, and result notifications.

MCP server that searches the Roblox DevForum and official creator docs so AI coding agents can debug Roblox games against real community and engine knowledge.

Competition math (IMO/Putnam/USAMO/AIME) solved with a pure-reasoning pass, an adversarial verifier in a fresh subagent context, and calibrated confidence output (high / medium / honest "no confident solution"); optional LaTeX-to-PDF rendering.

A Codex-style conversation navigator for the DeepSeek Harness Web GUI.

Per-message delete for DeepSeek Harness — a trash icon beside the copy button on every chat message that removes that message from the derived model context (and the visible transcript) via the official surface-replace contract