플러그인

Route each WeChat group session to a different Agent preset by group name, reusing dsh-wechat-assistant without changing its code.

Rotate the outbound LLM session ID after each successful DSH compaction without creating a new DSH session.

Replaces the chat input model picker with a provider-grouped, collapsible list: groups models by provider, folds vision-bridge mirror providers back into their upstream, and carries the reasoning-effort options each model declares in settings. Tested on DSH Desktop only; the DSH web build is untested.

Audits a DSH profile for capabilities nothing consumes: inventories the declared composition rows, counts how often each registered tool and skill is actually called in the session logs, separates calls that were made from calls that returned a result, and reports the ones with no observed consumer. Ships a skill that fixes the evidence-chain format for completion claims.

Mirrors cc-switch providers and models into DeepSeek Harness the moment they are saved, and shows each provider's plan windows, account balance, or custom usage script in the composer and the settings card.

A continuation of simon300000/dsh-auto: the Auto Approve permission preset for the DSH Web UI reviews each approval with one single-shot model call instead of a reviewer subagent, auto-approves only the actions that pass and hands the rest to human approval, and remembers confirmed decisions as project- and global-scope allow/deny lists, with an approval timeline in the right sidebar.

Native DSH right-sidebar tab that lists the ports this machine is listening on together with the process behind each one, and offers per-port actions to open it, copy its address, reveal its working directory or end the process.

Runs git init in each newly registered DSH workspace, with an empty initial commit by default, so git-aware plugins have a repository to attach to; directories already inside a work tree are skipped.

Skill routing for DeepSeek Harness: embeds skills and each user task with a local model, keeps the clearly-relevant skills with a gap-based selection rule, and auto-injects their full bodies into the prompt.

Declare any number of LLM providers, each with its own endpoint, credential and per-model parameters (reasoning-effort vocabulary, image input, retry policy), across the OpenAI Chat, OpenAI Responses, Anthropic Messages and Google Gemini wire formats, configured from a settings page.

System-audio visualizer for the turn navigator rail: the rail reacts in real time to whatever the default playback device is rendering, with four motion modes (spectrum, pulse, sway, travelling wave), a 16-band logarithmic spectrum from a 2048-point FFT on the host, and live sensitivity, strength, bass-punch and wave-speed controls. Audio is captured host-side through WASAPI loopback, so there is no permission prompt, no microphone and no screen capture. The browser half adds one attribute, one stylesheet, some CSS variables and a sidebar control row, and never patches the official component; switching it off removes the attribute, the stylesheet and the variables, returning the rail to its default styling. Windows only.

Live change review for DeepSeek Harness: tracks write/edit tool calls per session, lists changed files above the composer and opens each file's line-level diff in a plugin-registered right-sidebar tab, with session-log / initial-version / Git comparison modes, per-change and per-file revert, subagent aggregation and SSE updates. A fork of cirelir/dsh-change-review rebuilt around the right sidebar.

Floating audio control panel in the Web GUI: play/pause/next/previous for Windows media sessions (SMTC) and the system master volume/mute, served by a Node route half that runs a PowerShell helper.

Maintained fork of godchen520/dsh-web-search-bing adapted to DSH 0.1.5-rc.1: Bing-backed provider for the built-in web_search tool, scraping the public cn.bing.com HTML results page with no API key, reachable from mainland China, and keeping searches off the model's own search quota. Endpoint and result count configurable.

Local file recall: indexes the folders you choose into one local SQLite database, so 'where did I put that file?' is one query instead of a disk walk. Caches, VCS and program folders are pruned per directory; each folder keeps its own incremental anchor, so a folder added later is backfilled in full. Read-only: it never modifies, moves or deletes your files.

Automatic tier-based model routing for DeepSeek Harness: a virtual `smart` model classifies each request by difficulty (hard / normal / easy) and by vision need, then delegates it to the models you already configured. 三级难度 + 视觉自动路由，虚拟 smart 模型零配置接入。

Composer add-assets plate for the DeepSeek Harness Web Client: an options menu on the composer's + button (files, folders, slash commands) and a Claude Code-style draft attachment preview

Reach local DeepSeek Harness web from the LAN, Cloudflare Tunnel, or an SSH reverse forward.

Colors each DSH sidebar session title by state: unread (blue while the model is running, green once it has finished) and pinned (yellow, read from DSH's own pinned set), composed into one left-to-right gradient. Pinning, archiving and ordering stay with DSH itself — the plugin reimplements no pinning and rewrites no official bundle — and a settings section lists every unread session.

DeepSeek Harness plugin bundle: grill_tree, a fixed-policy design-space search tool. Expands one decision per node, fans out independent proposers, has a separate judge prune the branches, beam-limits each depth, and ends with complete designs or an infea

Task management for the DeepSeek Harness: the session todo list, a project task board backed by a queryable SQLite database, and board cards dispatched to the agent as background jobs

Management center: link skill directories into the user skills root (enable/disable/unlink/delete) and manage MCP servers — add/edit/delete, import from other agents (Claude Code/Codex/Cursor/Gemini CLI), auto-load each project's own MCP servers via the l

DeepSeek Harness (DSH) web plugin: per-turn response window. Each turn's tool calls collapse into ONE always-expanded bounded slide (configurable N-line window, inner scroll, nothing hidden), and long assistant markdown gets a bounded scroll window too —

Context occupancy and account balance for the DeepSeek Harness Web Client: a session-header readout, a balance capability seam, and a DeepSeek provider