Plugins

Vision toolkit for text-only DeepSeek: model-invokable `vision` tool, wrapper adapters for deepseek/opencode-go (v4 flash/pro), Antigravity IDE quota (default, flash/pro) / any OpenAI-compatible VLM / Gemini / local Ollama channels, evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

Model-facing `vision` tool for DeepSeek Harness: describe and OCR image files by calling the free Zhipu GLM vision API directly (glm-4v-flash fallback chain), no external CLI required.

Routes chat images to a fixed OpenAI-compatible vision model, returns factual observations to the selected main model, and reuses session-scoped observations across replay, compaction, and restarts.

Jira Cloud issue-tracker integration exposing eight model tools for issue search, project and transition lookup, creation, updates, comments, and transitions; writes are opt-in and support dry-run.

MuApi media-generation tool: a muapi_generate tool that submits and polls jobs against any of MuApi's 100+ image, video, audio, and 3D models through one x-api-key.

A slim port of Headroom: compresses tool output, cuts up to 20% of context, without affecting the model's context cache or agent performance.

Stage-gate governance tools: model-callable gate_open / gate_check / gate_list / gate_close for in-memory, per-session acceptance checks with PASS/BLOCK conclusions.

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.

Brings your existing Claude / ChatGPT history into DSH: instant zero-token import of the memories.json inside a Claude export, local Claude Code transcripts with no export needed, and conversations distilled through the model you already configured in DSH. Every memory carries verbatim evidence checked against the source by code — a paraphrase is dropped and counted, and evidence found only in the assistant turns is always routed to review rather than stored.

Layered memory pipeline for DSH: auto-distills conversations into atomic facts, scene summaries and a persona profile (L0–L3), with hybrid BM25 + vector retrieval, chat/work family separation, and context injection before each model step.

Model-authored context pruning for DeepSeek Harness through the official compaction API.

Message review and quote chips for conversations: multi-model cross review (code/reply) with severity grading and summaries, review history, and host-persisted preferences.

Sub-agent matrix swarm that routes heterogeneous tasks to the most suitable model from an OpenRouter-like gateway plus cfgpu.com/llm/square, dispatches each via in-process subagents or direct LLM calls, and tracks per-model token consumption with a feedback-driven ranking.

Ollama Cloud native chat adapter: direct NDJSON translation of the Ollama /api/chat wire format, model discovery with context windows and capabilities, and web search/fetch providers under the ollama-cloud id, plus a Web settings card.

Writes live provider model lists into DSH settings and shows 5h/7d plan windows or metered balance for the current session model.

Warm light and dark theme for DSH Web with responsive layout, bilingual settings, safe Markdown preview, per-block copy controls, and no telemetry.

Use wallpapers downloaded in Wallpaper Engine as the DeepSeek Harness web background: video wallpapers play in place, image wallpapers use the highest-resolution standalone artwork, with cover/contain fit modes and a 0-100 panel dimmer.

Look & theme plugin for the DSH Web UI: built-in palettes, light/dark/follow-system appearance modes, Open VSX theme search & install, and VS Code theme import with a persisted theme library.

Real-time DeepSeek API usage: account balance with low-balance alerts (browser notification on threshold crossing), token & request stats (total/today/last-60s windows, per-model and per-session), estimated cost — a composer dock plus a settings-page usage panel.

Persistent provider-reported token usage for DSH Web, with a sidebar summary and settings-page breakdowns by range, token type, provider, and model.

Persistent provider-reported token usage totals with per-session, per-model, and daily activity statistics.

Sidebar billing dashboard: real usage aggregated from session logs (per-model and per-day calls/tokens/cache), cost estimated in CNY from a current multi-provider pricing catalog, subscription-plan (coding/token/agent) routes exempt, and per-provider health dots.

Adds a "用量" section to the DSH Settings page that shows your MiniMax Token Plan usage (5h and weekly windows with reset countdowns), per-model breakdown, and video bonus credits; fetches `/v1/token_plan/remains` via a trusted plugin that holds the API key, auto-hides when no key is configured. MIT.

Model sampling sliders (temperature / maxTokens) in the composer: override every model request for all providers via the agent/request hook, with hot/persist modes.