Plugins

Volcengine Ark Coding Plan LLM provider for DeepSeek Harness: provider-scoped PDF and image input, with Responses API streaming support.

Explicit model routing for Main, Subagents, web_search, and image generation, plus a catalog-driven Composer and Plan Review picker with Model, Effort, Context, Fast, and Thinking variants.

iPhone-style agent phone: dual-panel calls & SMS, RCS group chat with trust gates, cross-device agent messaging via the registry inbox bridge, L0–L4 trust badges and evidence audit. Experimental: trust summaries are not a security guarantee, and SMS/signalling is relayed through the operator's inbox (visible to them); E2E encryption is planned.

Explain failed DeepSeek Harness agent runs locally, then produce a redacted recovery plan. No model required.

Daily cost card for your local LLM gateway: /usage reads gateway_usage.jsonl and itemizes spend per model and per hour, covering official direct, OpenRouter relay, and in-plan metered pools.

Windows system-level notifications when the agent finishes a task or needs your input: task-done, question, approval and plan-review alerts via the browser Notification API, click-to-open the session, background-only mode, and a first-level settings page (Settings → 任务提示).

DSH workspace hub: organize workspaces into color-coded folders in the sidebar (three-level drag reorder for folders/workspaces/sessions, inline edit, one-click expand/collapse, dual-channel search) with per-workspace and per-session token usage and cost stats from real session logs (official DeepSeek peak/off-peak pricing for any deepseek model, three spend calibers, hover detail cards, overview panel) plus OpenCode Go plan usage; data persists to host disk and refreshes live every 30 s.

Panel hotkeys for the web UI: Enter presses the confirm action and Esc presses the cancel action on every interaction panel (approval, question, plan review).

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.

OpenCode Go plan usage monitor for DeepSeek Harness: real-time 5h-rolling / weekly / monthly quota in a floating web dock

team-task for DeepSeek Harness: long-horizon multi-agent tasks — a lead plans a reviewed DAG, durable members execute, an event log is the single truth, and a resident reconciler survives crashes and restarts.

A full-screen terminal workbench for DeepSeek Harness with a durable assistant, workspace-grouped project sessions, transcript-only scrolling, and structured thinking, tool, diff, plan, and subagent views.

Long-task orchestration loop: Codex plans/scores/reviews, DeepSeek executes, Kimi supplements (vision acceptance, summarization, cross-check).

Turns the iterate skill into an autonomous closed-loop harness — plan, parallel review, atomic fixes, validate, loop, auto-stop — plus a dry-run review-only mode and a meta-review that audits the report and emits a final review report.

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.

Agentic Control Plane for DeepSeek Harness — check every tool call against your policies before it runs, and keep a durable record of what was allowed and why.

Command Code Go provider adapter for dsh: scan the Go-plan model catalog dynamically and serve /alpha/generate through the harness LLM seam

Evidence-first operating kit: six read-only tools (capability catalog, staged workflow plans, packaged skill reader, bounded local memory search, repository release audit, release checklist) and five packaged skills - plans and audits, never remote writes.

Model failover and turn keep-alive for DeepSeek Harness: a request that fails with a model error before any visible output falls through the models of the configured provider groups (then the next provider) until one streams; transient failures retry with backoff under a liveness watchdog, a dead turn self-resumes with templated 「继续」 wake-ups, and an optional full-auto mode auto-answers permission, question and plan approvals with every decision appended to an AUTO-MODE.md audit log.

Adversarial review for DeepSeek Harness: put one settled plan on the stand, send read-only red-team experts at it by dimension, then split their findings into single defects you endorse or reject one by one. It never rewrites the plan and never fixes code.

Composer Plus for DeepSeek Harness (dsh): git Changes panel, ↑/↓ input history, Shift+Tab /plan, one-click Continue, queue drag-and-drop, deeplinks, Auto Review allow-for-chat, notifications, 11 UI languages, auto-update

Adds subscription OAuth and provider Plan API-key logins through Pi adapters, using a DSH-owned credential store.

Checks each step of a plan before you approve it, using command rules plus Jev or an OpenAI-compatible endpoint with logprobs, and marks steps that can't be undone, affect things outside the workspace, weren't asked for or are too vague on the plan review card.

Find and compose DSH plugins from a task description, then open an independent chat environment or install the plan into the current profile.