Plugins

Windowseat bridge for DeepSeek Harness: a local host plugin exposing a loopback HTTP/SSE endpoint so the bundled Microsoft Edge side-panel extension can read the current page, search local files and talk to DSH; the Edge extension lives in the same repo and must be loaded separately. Windows 10/11 with desktop Edge required.

Bilibili-style danmaku overlay for the DSH Web chat area: scroll, top and bottom tracks driven by agent events, three preset packs, optional LLM-generated comments, a draggable control ball, per-session pools with replay, and a settings card.

Agentic answer reviewer for DeepSeek Harness: each final assistant turn is re-reviewed by a separate LLM graded 1-100; below-threshold scores steer the agent back with concrete feedback. The score is shown as a chip on the answer's action row (green pass / red needs-work, with retry count and reason on hover). Live gate config from the Reviewer 配置 tab in the conversation view ring above the composer (对话 / 轨迹 / 记忆系统 / Reviewer 配置), from a 127.0.0.1 HTTP server, or from an optional right-sidebar tab via dsh-better-sidebar.

Mixture-of-Agents plugin for DeepSeek Harness: a /moa slash command fans a prompt out to multiple models in parallel, merges their responses in a file workspace, and integrates with Live Canvas for visual output.

Fifteen curated theme families and nine complete dsh-web-ui skin replicas in one plugin behind a single settings entry, with CSS-only custom theme JSON, controlled custom skin-pack import via folder picker, preview, apply, delete and restore-default. Ships on npm as `dsh-appearance-gallery`.

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.

Curated research plugin market: adds a Research plugins page to Settings with hand-reviewed plugins for literature search, reference management, writing and workbenches — one-click install, update and remove pinned to the reviewed version, restart from the panel, and exactly one network request (its own catalog).

OpenCode Go usage bar in the composer dock: rolling/weekly/monthly quota rings, DSH-session token & cost stats priced with live official rates, per-model and current-session scope breakdowns with live per-session updates, one-click API key copy.

Registers Qoder CN and international language models into DSH, fetching each model's rate automatically as it shifts with off-peak hours. It also provides a daily check-in, a usage pill and a credit lookup. Needs the Qoder login state on this machine, or one browser login.

Git worktree panel for DSH Web: replaces the workspace sidebar with project → main/linked worktree → session groups, creates and removes worktrees, switches the main branch, and migrates configurable project-local or global storage with dirty-tree and active-session safeguards.

Auto-resume for interrupted agent sessions: an ordered rule table routes by failure type (rate limit, quota, auth, context overflow, crashed orphan) to automatic backoff retry, model switch, resume after context compaction, or a stop-loss notification, with a visual rule editor and a full activity log.

Experience memory and reflection for DSH agents: automatically extracts candidate lessons after tasks and recalls user-reviewed lessons in relevant later tasks. Supports source provenance, project-scoped retrieval, conflict handling, usage feedback and expiry review; capture and recall have separate controls, and writing lessons to AGENTS.md requires preview and explicit application. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

A self-healing layer for tool calls: missing params, wrong fields and out-of-range paths are fixed before they reach the model. Measured visible error rate fell from 7.95% to 2.20%.

Automatically generates and displays images in the DSH chat via API channels or local CLIs (mmx / codex / agy), and can also recognize images using the corresponding CLI.

Usage and cost statistics with peak/off-peak pricing after the 2026-08-17 rate change, a floating summary panel, per-session breakdowns, and a day/week/month/year/all usage heatmap.

MCP server installer and verifier for DeepSeek Harness: interactive init writes real patch entries into a profile, list and validate inspect them, and a CI-enforced verifier connects to every curated server.

Pops up a mini-game menu (wordle, match-3, extensible) while the model generates.

A whale-maid with a jar, sitting in the corner of your DSH window. She goes exploring on Bilibili for whatever you are into, ranks by like, coin and favourite rate rather than view count, and brings back pickled snacks that suit your taste. When a term runs dry she takes another route. Five picks go into the jar, and she tells you what each video is about. News-type axes keep only the last two weeks; game guides and music have no limit, and each axis decides for itself.

Bring the WorkBuddy accounts signed in on this machine into DSH, managing CN and international accounts separately. Supports automatic failover between accounts, one-click refresh of model catalogs and credits, the CN daily check-in, and a togglable OpenAI-compatible endpoint.

ClineBot and ClinePass integration for DeepSeek Harness: dedicated settings page, live quota dashboard, in-UI key saving, curated and custom model selection, and a /cline command.

DSH plugin bundling the kimi-ppt skill: create, edit and export presentations as a locally generated .pptx with Pillow-rendered previews. Derived from the MIT open-kimi-ppt-skill.

During Beijing working-day peak hours (default 09:00-12:00 and 14:00-18:00) it blocks official DeepSeek requests or reroutes them to a configured target provider; off-peak traffic flows to official as usual.

Git-style conversation branching that mirrors how real programmers collaborate: a secretary root branch dispatches tasks to child branches with their own contexts, merging back only compressed summaries via squash or rebase; ships /branch commands, a branch tab, branch-to-branch messaging, and a governance baseline pairing each session branch with a git worktree.

Lifecycle management UI for the llm-pi-ai model provider: create, edit, delete, enable and disable providers with custom headers and AES-GCM-encrypted API keys; uninstall-safe restore of parked providers, remote model discovery with batch write, smart routing with five strategies, union/intersection composites, per-model connectivity tests, and request observability.