Plugins

Adds a configurable vision model to text-only main models: a vision_read_image tool, a composer-bar vision-model selector, and automatic image-to-text conversion for text-only routes.

DSH 模型 Pro:为 DSH WebUI 提供将 pi-ai 预设或任意已配置提供商的模型上下文、输出上限、推理档位与兼容开关一键应用到目标提供商,并集中查看、新建、编辑、复制与删除各提供商模型条目的能力。

MCP bridge that lets ChatGPT Web create, view, continue, and supervise DeepSeek Harness agent sessions and goals while preserving DSH's native approval, sandbox, and workspace security model.

Gives text-only models vision: forwards user images to an OpenAI-compatible vision model and shows the descriptions in a Web UI right panel.

DeepSeek Harness plugin that shows API balances and available models in Settings

HUD status panel: Git status, MCP servers, skills, model and token usage in a floating side panel.

Extensible animated response pet with blue-whale, orange-cat, and silver-shaded-cat themes, per-session progress, model and tool-call traces, token counts, output speed, elapsed time, and collapsible multi-session status cards.

Unified anchored agent preset for DeepSeek V4 Pro/Flash on the official API and opencode-go: Minimal-exact two-tool first-request bootstrap, model-aware Pro/Flash paths, and epoch-aware catalog management for long-session stability.

Bottom info bar for the DSH Web UI: provider/model, live balance, peak/off-peak pricing with countdown, and real persisted per-session spend in a single line.

模型路由与成本优化器：简单问题 flash 直答、故障自动降级、会话 token/缓存/成本实时面板 | Model router & cost optimizer for DeepSeek Harness: flash quick-answers for simple questions, failure fallback, live token/cache/cost panel

A second brain for your DeepSeek Harness agent — strong-model review before risky tool calls, plus 67 models from one wallet. No accounts, no API keys.

Claude Code-style declarative permission rules: ordered allow/deny/ask YAML rules matching tool names, arguments, workspace paths, and agent identity on the tools/pre-execute waterfall, with full session-log audit, dry-run mode, and hot reload.

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

Model high-availability failover (quarantine, circuit breaking, probe recovery) and subagent orchestration (fanout/pipeline/supervisor) with bilingual settings UI.

Reads assistant replies aloud via free Edge TTS or your own RVC voice models: read-aloud buttons + auto-read, adaptive chunked progressive playback (gapless long reads), one-click voice-pack installs from a registry, and a portable RVC runtime.

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.

Telegram mobile remote that attaches the phone to a live DeepSeek Harness Web session: workspace-then-session picker (/sessions), /last for the previous Q/A, /model switch, and native Rich Message replies.

Hook DeepSeek Harness into a Hermes pipeline: dispatch-spec template, model-tier routing, orchestrator-run quality gates, git single-writer rule, as a SKILL.md pack (bundle installable).

Fifteen curated theme families plus custom CSS-only themes with import, preview, apply, delete, and restore-default flows that follow the native Light, Dark, and Follow system modes.

dsh client bundle: a sidebar usage & cost dashboard — token stats, peak/off-peak aware per-model pricing, membership ladder, achievements and a daily heatmap.

Multi-character Galgame conversation view with separate character and reply-model selection, per-character affection, memory, dialogue history, and CG galleries, plus responses informed by task events across Harness sessions.

Composer mic for the Web UI: tap-to-monitor live transcription and hold-to-talk, with host Edge TTS reply reading that streams while the model generates, echo-pause during reading, and tap-to-stop.

A vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.

Local OCR for attached images via the built-in Windows engine (Windows.Media.Ocr): only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.