Plugins

VS Code-style local workbench for DSH with a file explorer, Monaco editor, full-text search and a Git panel.

Template-driven code review skill: five-step review flow, critical/medium/minor severity grading, four-dimension scoring (quality, security, performance, maintainability), dual text and HTML report output, and an on-demand reference knowledge base.

China A-share financial data MCP server for the harness: 11 fin_data__* tools (quotes/K-lines/financials/calendar/special-data/announcements/EDB/reconcile/funds/indices) over THS free official REST (primary) + AKShare (fallback) + Wind (exclusive domains), with observable degradation, context-budget compression (result-side -72.2% measured), and an offline 10-year market-data lake; BYOK.

Better streaming text animation for DeepSeek Harness.

One upload button plus drag-and-drop files into the conversation as local paths: save to the project's uploads/, path text into the input box, works with any vision tool.

A right-side floating panel and /context command for DeepSeek Harness — a live donut chart of context token usage, allocation, and estimated cost.

Auto thinking-effort routing for dsh: a locally fine-tuned 7-question classifier (ModernBERT, 842MB, <1s CPU inference) picks low/high/max for no-intent messages; in-session retries escalate the tier (low to high to max) under exclusion constraints; the judge service fails safe to low if unreachable. A tier chip in the input bar shows the live tier and the last 20 judgments. All inference is local - task text never leaves the machine.

Multi-engine web search for coding agents — one SearchBoost core (fused search, fetch, X) with MCP (Cursor, Codex, Claude Code, Grok Build, Antigravity), pi extension, and DeepSeek Harness bundle adapters

Real mouse and keyboard for a DeepSeek Harness agent: describe what to click in words, a vision model finds it, a USB HID device clicks it.

Bridges WeChat private chats into DeepSeek Harness as an in-process plugin over Tencent's iLink bot protocol, with two-way text, image, file and voice messaging, in-WeChat slash commands resolved through the native command registry, WeChat-side handling of approvals and agent questions, and proactive push through a send_wechat tool.

Forces context compression when running low-context llama.cpp models such as Qwen3.8-27B, improving model efficiency and usage smoothness, together with well-refined compaction prompts.

FormatForge: forge 30+ file formats (PDF, DOCX, PPTX, XLSX, EML, EPUB, TOML, archives) into AI-readable text via a drag-and-drop inbox, ff_translate/ff_formats/ff_result tools and a CLI; scanned PDFs fall back to local OCR or an enhance hint for the session model.

Archived-session manager for DSH Web: workspace-grouped list, FTS5 full-text search over session content with per-session snippets, restore-and-open, and hard delete.

One-level session folders for the web sidebar - group sessions per workspace, move them by drag-and-drop or context menu, archive and restore, server-side persistence.

Android real-device debugging workbench for the DSH Web GUI: auto-attached logcat with severity/keyword filters and crash snapshots, live on-device screen casting with remote tap/swipe/text control, memory/proc/frida reverse-engineering toolset, 30 agent tools.

Content-aware tool-result reducer: 13 reducers cut oversized output by meaning at tools/post-execute (failing tests kept, diff context dropped, JSON and CSV sampled, lint problems grouped by rule, dependency stack frames collapsed, crowded directories counted), with full originals spilled to disk behind a locator.

Multi-engine text-to-image generation (OpenAI Images and Zhipu CogView presets) with per-session quota tracking, engine failover, credential-safe config, and a result card with regenerate.

An ikun (basketball meme) pet that fills the dock under the "Deep diving..." status row during replies: a sprite-sheet pet walks a 0→100% progress bar, switching animation and text every 20%, and plays a system-level "nǐ gàn ma~" voice cue at completion.

Adds /btw for one-off, context-aware side questions without tool execution, with independent answer bubbles that can be copied, collapsed, or closed without adding answers to the main conversation.

On-demand second opinions through ask_advisor, with editable requests, per-call human approval, and text advice from a model configured in DSH.

An opencode-inspired terminal UI for DeepSeek Harness that boots as a dsh profile app plugin, with a session sidebar, streaming chat, markdown tool cards, todo lists, slash-command suggestions, a telemetry footer with a context meter and inline approval prompts.

Deterministic context compression for dsh — zero LLM calls, rule-based pruning that preserves paths, commands, error traces, and open todos verbatim. Compresses ~80k tokens to a few hundred.

XiaoTangYuan, an in-game AI companion for single-player games: understands the game screen, chats by text or push-to-talk, and speaks replies aloud; Stardew Valley is supported, with Don't Starve Together and Oxygen Not Included integrations in progress.

Overleaf-style LaTeX paper workbench: annotate any text in the rendered PDF and let a dsh agent revise the sources with compile checks and git history.