Plugins

Whale girl desktop pet for DeepSeek Harness: browser floating mascot plus Windows desktop pet sharing one data backend, with real-time balance board, task notices, head-pat interaction, 19 pre-synthesized voiced lines with per-line emotion, and presence-aware idle speech.

Fully local vector memory for DSH: local embeddings, SQLite storage, automatic recall injection, dedup with conflict detection, soft-delete recycle bin, online backup, and optional LLM extraction.

Compaction fix for NInfer-hosted qwen3.8-27b gateways: disables thinking on dsh context-compaction and session-title calls so xhigh reasoning stops burning the whole output budget; the same idea applies to other launch methods, this package targets NInfer only.

DeepSeek account balance, this session's billed spend, and today's total spend in the session-header badge; a turn-cost row in the message actions strip, a detail panel with per-model pricing and a today session-spend ranking. Official peak/off-peak pricing; balance from the real /user/balance API.

Read-only Gitea and Forgejo tools over the REST API both projects share: instance info, repository listing, issue and pull request search and read, PR diffs and changed files, and Actions runs, jobs and job logs. Tool metadata is available in English, Traditional Chinese, Simplified Chinese and Japanese.

Liquid Glass refraction input card for the DSH web GUI, with coupled-spring press animation. Published on npm: dsh plugin --profile web add dsh-liquid-glass-input.

Genuine Liquid Glass theme for DSH Web UI: SVG feDisplacementMap edge refraction on input card, send button, bubbles, view tabs, queue dock and sidebar. Built-in animated demo wallpaper, customizable background blur & brightness, redesigned model selector popup, glass-styled buttons throughout, and a unique water-drop settings icon.

Adds a red permanent-delete action with a confirmation dialog to the native session menu.

Session handoff & context management: structured handoff documents (export/resume/status) so a fresh session can continue seamlessly, plus active context pruning (acp_* tools via the official compaction API with model-authored summaries).

Merged plugin: wallpaper customization (original-resolution uploads, crop editor, per-area opacity, MP4/WebM dynamic wallpapers) + Steam Workshop wallpaper extraction (parses scene.pkg/.tex via a bundled Python script, preview/download) + DeepSeek balance & usage widget + OpenCode Go plan usage (rolling/weekly/monthly percents in a top header pill; expand for progress bars & reset countdowns). API keys are read from DSH's credential store by the host — never stored in source or the browser.

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.

Specialized in Git branch and status handling: a Git status drawer on the right edge of the DSH web UI with a commit DAG lane graph, uncommitted changes and stash rows, inline diffs, right-click branch/tag actions, and one-click fetch from all remotes.

Local toolbox for the DSH web GUI: 35 pure-client tools (text, encoding, hashing, extraction, conversion, reference tables) in a sidebar view, plus the /toolbox command and config-driven agent tool exposure.

Enhanced auto-compaction defaults for DeepSeek Harness agent presets: apply tuned threshold/retention budgets and per-model policies with one command, idempotent with backups and rollback.

**DeepSeek Chat (chat.deepseek.com) same-style attachments**: paperclip upload button, 240×64 DS-style file cards with official colored doc icons (PDF/DOCX/XLSX/PPT/IMG extracted from the DS frontend bundle), drag-and-drop, text extraction (PDF/DOCX/XLSX/TXT) injected into the message, and real attachment cards rendered in the transcript (custom user renderer) with the model reading full content.

Content-addressed artifact, fact, action and report lineage for DeepSeek Harness

Session execution analytics: steps, tool calls, failures, repeated actions, token usage and verification signals, rendered as text/Markdown/JSON reports.

Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.

The generic New Session action opens a default-directory workspace instead of requiring a folder pick, and the workspace picker lists that workspace as a no-folder choice.

Web reading tools for text-only agents. Five read-only tools: web_fetch (any URL rendered as clean Markdown or plain text), web_links (inventory of a page's links), web_feed (RSS 2.0 / Atom entries), web_headers (HTTP status, response headers and redirect chain without downloading the body, HEAD with automatic GET fallback), and web_table (HTML tables extracted as structured rows with header detection and colspan/rowspan grid expansion). Transport is Node fetch plus a zero-dependency HTTP proxy implementation (CONNECT tunnelling, absolute-URI requests, NO_PROXY with suffix/wildcard/IPv4-CIDR matching, Proxy-Authorization). Zero runtime dependencies.

Stages exact DSH tool calls without dispatch, presents complete canonical arguments in a durable Batch Review Inbox, invalidates approvals after edits or restarts, and commits only a matching SHA-256 digest plus single-use nonce through the normal DSH tool pipeline.

Splits New Session in the DSH web sidebar into two modes: a 日常聊天 row opens a session on the `daily` agent preset the plugin installs into the harness home (persona, web search and fetch, ask-user and compaction — no files, shell, plan mode or subagents), inside its own daily-chat workspace whose sidebar region lists only those chats, while 开始工作 keeps the shipped coding agent; the built-in New Session button is hidden and every other New Session entry point follows the active mode, which is remembered in localStorage.

Merges other sessions' context into the current turn: evidence-weighted conflict resolution, retraction of claims whose premises were retracted, trust labelling that resists cross-session prompt injection, and budget-bounded packing. Ships a benchmark.

GLM Mode agent preset for zhipuai/glm-5.3-flash: PTC/Code Mode tool presentation, a reasoning loop guard and a tool spin guard (live-incident driven), and GLM-specific auto-compaction at 75%/22%.