All Plugins

Vision provider route that transcribes attached images to text through a configurable model (15+ OpenAI-compatible and Anthropic vendors) while DeepSeek keeps answering.

CDP bridge to an already-running Chrome/Edge for DSH: screenshots, pixel assertions, DOM/CSS checks, and page JS evaluation over HTTP + WebSocket, with zero child processes, zero npm dependencies, and zero per-use approval.

Bottom-right 余额 badge for the DSH Web UI: on expand it fetches the currently-selected provider's OpenCode Go plan limits or DeepSeek prepaid balance, plus local token usage and pricing-based spend estimates.

Session cost estimate in a status bar at the bottom of the conversation (per-model token pricing, CNY) plus the live DeepSeek account balance via the official balance API.

DeepSeek API quota panel collapsed into a left-edge handle for the Web UI: click to expand balance, official today's consumption (with platform token) and live conversation cost; fork of dsh-deepseek-quota.

MiniMax token-plan quota dock for the Web UI: a drop-shape 5h-usage % chip in the conversation input area, click for a detail panel listing every model's 5h & weekly usage and reset countdown, auto-hidden when the active default model is not a MiniMax model.

Connects DeepSeek Harness to AsimovBox for creating, updating, rendering, and finishing videos through API-key-authenticated tools.

Live per-task token cost widget: peak/valley pricing windows, projected post-hike costs, sortable per-task cost table, multi-currency (COP/USD/CNY + ~40 more) with FX rates, and one-click streamed LLM explain of expensive tasks.

Transparent image guard for text-only routes: paste images without the 400 session deadlock, plus a vision_analyze tool for OCR/PDF/docx/pptx/video.

Image-to-text input for the Web UI: paste or drag an image and it is transcribed into structured text and sent, giving text-only LLMs image-input takeover (OpenAI-compatible vision API).

Chain-of-thought leakage linter: zero-dependency CLI that finds AI-session residue in docs and comments (dead design citations, PR vantage, change narration, review choreography), shipping the cot-trim fixing skill as the installable bundle.

Ingestion-time tool-output curation: keeps error and warning lines plus head and tail, spills the full text to disk with a pointer the model can read back; covers every text tool, small results pass through untouched.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

Settings-page usage dashboard: per-provider/model token summary across all sessions, with today/7-day/30-day CSS-bar trends and a cache-hit rate.

Persistent model tool-call trace recorder: every tool call is durably written to a JSONL file that survives restarts, queryable via a structured call_trace tool and a callTraceHistory service, with size rotation and an optional floating canvas UI add-on.

Desktop and browser automation bridge (36 tools): window/screen/mouse/keyboard control with PaddleOCR element perception, Chrome CDP browsing with accessibility snapshots.

Code knowledge graph bridge for codebase-memory-mcp: semantic symbol search (BM25), source snippets, architecture overview with Leiden communities, call/data-flow/cross-service traces, graph-augmented grep.

Multi-engine reverse image search aggregator: Google Lens, Baidu, Yandex, TinEye, SauceNAO, IQDB, Ascii2d.

Recurring-habit scheduling from pure date math: next occurrence, range schedules, and overdue advice.