プラグイン

Reusable LLM configuration profile library exposed to browser consumers as a Remote

Provider-scoped HTTP/HTTPS forward proxy for DeepSeek Harness: configure independent proxy URLs and enable/disable switches per LLM provider, with environment-variable references for proxy credentials and model discovery routing.

Expose a local MCP server to remote agents through an outbound-only tunnel stack (mcp-proxy + cloudflared Quick Tunnel), then register the public URL into dsh-mcp-client streamable-http config.

Tiered compaction hub: replaces the single 80% compaction cliff with a configurable ladder (default 30/50/70/90) whose tiers escalate from gentle to maximum consolidation laws, folds a deterministic keyword index into every checkpoint so facts accumulate across cycles, and summarizes through a model chain — primary plus up to 3 fallbacks, each with its own reasoning effort. Adds a Compaction module sub-tab and a Settings card; toggling off always restores stock compaction.

OAuth sign-in for 9 subscription LLM providers (Claude, Codex, Grok, Antigravity, OpenRouter, Agnes AI, Qwen, Spark, ERNIE) with zero-config login and usage dashboards.

DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.

Per-model vision (image input) toggle for DeepSeek Harness (dsh): list every configured model and flip a switch to enable/disable image support without hand-editing settings.yaml. 为 DeepSeek Harness 提供按模型的「支持图片」开关：无需手改 settings.yaml。

Configurable non-public address allowlists for DeepSeek Harness web_fetch

Browse, sign in to, and safely install public or private team Skills from a configured Skill Base in DSH Web.

DSH web plugin: open .docx/.xlsx/.pptx in the better-sidebar editor through a self-hosted ONLYOFFICE Document Server (JWT-signed config, in-network document/callback routes, save-back to disk).

Zero-config per-turn git checkpoints: after every completed agent turn in a git workspace, stages all changes into one tagged \[turnsnap] commit (serialized queue, sandbox-policy aware), so any turn is a rollback point.

Display-layer text replacement for DSH chat messages: rewrite how any configured text appears on screen without touching the real conversation, with per-rule whole-word matching and code-block protection.

DSH web plugin: a better-sidebar tab that embeds the VS Code web workbench opened at the current session workspace, behind the gateway's /vscode subpath or any configured editor base URL. Editor selections land as atomic reference chips whose canonical me

Holds the OS wake lock while any agent, subagent, or background job runs, releases it after a configurable grace period, and provides a bilingual web settings page with live status, manual hold, and display-on options.

将 WorkBuddy 桌面 App 包含的模型自动接入 DeepSeek Harness — bring WorkBuddy desktop app models into DeepSeek Harness with zero configuration.

Bridges images into text for DeepSeek Harness: when the session's selected model cannot see images, a configured vision model describes them and the descriptions enter the durable session history as folded context rows — your message stays untouched.

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

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.

One-click Claude Code and Codex hooks for DeepSeek Harness: auto-discovers your existing hooks config and runs it on the official bridge plugins.

Multi-key Tavily search provider for DeepSeek Harness (ctx.web) with a live settings card in the web plugin configuration page

Browser Web Speech dictation for the Composer: recognition needs no dedicated ASR server, key, or model download; reuses Session text and a configured DSH model for contextual phrase hints and optional transcript polishing.

Runs one coding prompt across multiple configured models in isolated Git worktrees, streams side-by-side tool traces and results, and commits the candidate the user adopts for later rounds.

Organize DSH sidebar sessions by configurable last-updated activity groups with attention-first sorting and Focus mode.

OpenAI-compatible LLM adapter plugin for DeepSeek Harness with configurable default sampling parameters (temperature / topP / topK / penalties / seed) over a providers dict.