Plugins

OpenCode Go provider that verifies a model against the gateway rather than treating a recommendation as a measurement: the models.dev protocol suggestion is probed before it is used, reasoning levels follow a measured contract, and requests run through an ordered protocol fallback chain. Context window, max output and image-input numbers are declared by a runtime-refreshed models.dev layer rather than probed, with operator overrides above both. Several OpenCode Go credentials can be stored and switched from the settings page.

OAuth sign-in for 9 subscription LLM providers (Claude, Codex, Grok, Antigravity, OpenRouter, Agnes AI, Qwen, Spark, ERNIE) with zero-config login and usage dashboards.

Brings the Codex (ChatGPT Plus/Pro) subscription already signed in on this machine into DSH. It (1) shows the 5-hour and weekly windows with their reset times and the remaining reset credits in a sidebar panel, with one-click reset that consumes a credit; (2) registers the subscription route in llm-pi-ai (openai-codex) when the quota is read, so the Codex models appear in the model picker; (3) refreshes the OAuth access token before expiry and writes it back atomically, so no key has to be replaced by hand; and (4) adds a codex tool that delegates a task to the local Codex agent. No API key has to be entered.

Declares the wire protocol for the opencode-go route so models the installed catalog does not describe resolve, adds the DeepSeek V4.1 models to that route when they are missing, and attaches a per-conversation x-opencode-session header to OpenCode requests.

Maintained fork of feibi-mochi/deepseek-harness-control-center, which has not been updated since 2026-09-09. Pricing follows the official model pool instead of a hardcoded model prefix, so DeepSeek V4.1 Flash (`deepseek-flash`) is billed and shows its peak/off-peak clock, and the official price page is parsed structurally so a renamed or retired model no longer stops price sync. Adds an English interface beside the original Chinese. Otherwise the same plugin: balance, per-session cost and token breakdown, a 24-hour peak/off-peak clock, Z.ai plan quota, and a local usage ledger, following the host light/dark theme.

Holds DeepSeek model calls for the rest of each peak-hour window you configure instead of sending them, so they are billed at off-peak rates; also pauses active goals while it waits and shows the account balance with an 8-hour spend chart.

Tracks API token usage and estimated costs with per-route model pricing, optional billing groups, synchronized CNY/USD display, session reports, composer totals and a clickable daily sidebar total.

Shows the active model's usage and remaining balance in the session header: OpenCode Go plan usage (rolling, weekly, monthly) with the selected model's monthly cap, Command Code 5-hour and weekly window usage with remaining credits, and DeepSeek account balance.

Floating phone-pairing QR button for the DSH WebUI. One click opens the dsh-remote-link pairing QR (image + 6-digit code + TTL) in an in-app overlay — works in both browser and DSH Desktop (same-origin img, no iframe).

AI-native expressions for two-way chat: people see images, while text-only models read fixed meanings; includes a picker, custom expressions, import/export, and two visual styles.

Agnes AI image/video generation tools (agnes_image / agnes_video) for DSH (DeepSeek Harness). Built-in cross-process RPM rate limiting, 429 backoff and local ffmpeg GIF conversion.

Session-local scheduled tasks: inject a prompt into the current session after a delay, at a fixed time, or on a repeating interval, so the model wakes up and runs it on time. Manage them from a panel above the composer, the /schedule command, or seven model-facing tools. Timers freeze while DSH is closed and never auto-resume; pause keeps the remaining time, so resuming continues from where it stopped.

Context compaction that keeps its receipts: a five-section handoff summary, a durable segment index, review tools that read compacted text back, optional working notes, and a read-only extraction exit. Mounts as the compaction-basic row's replacement; cha

Event-driven Hypatia memory for DSH: automatic conversation logging via session events, queued background consolidation (span summaries + work-unit extraction) with a dedicated model route, and recall injection — zero per-call model work in the main sessi

DeepSeek Harness plugin for Xiaohe Canvas: AI-powered e-commerce content creation (images, videos, workflows).

DeepSeek Harness 插件：AI 聚合网关可视化控制台——集成 Google Antigravity 与 OpenAI Codex 反代、多账号轮换池、5h/周额度看板与故障转移。

Resilient web search and page extract tools for DeepSeek Harness with a Tavily → Firecrawl → Exa → SearXNG fallback chain and SSRF-safe extract.

Motor-design AI assistant plugin: requirement parsing → parameter identification → candidate matrix → Top10 verification. L0 is a millisecond-level broad filter (pure JS, zero solver dependency) that ranks candidates and emits the handoff payload for the L1/L2 precision tools; usable as a local agent preset and Cordis plugin. L1 (RMxprt) and L2 (Motor-CAD) are reserved in this version — the level gate fails fast above l0.

Maintained fork of dsh-approval-gate. A neutral operation whose confirmation count has reached the threshold auto-approves when the judge is unavailable, instead of prompting a human again; approver-facing explanations are generated in Chinese from the real sandbox mode, command and paths. Also carries deterministic hard-deny for credential exfiltration and system-path destruction, judge-input redaction, a judge model candidate chain, fingerprint-scoped allow rules, and an approval view with unified diff and one-click revert.

Wire-level LLM inspector: captures the raw HTTP request and response bodies of model provider calls and attributes each capture to the session that caused it through the llm/stream waterfall. The request pane renders the body as a collapsible tree with per-node sizes — one measured request was 98.6% a single 973-entry array — and the response pane reassembles the OpenAI-style SSE chunk stream into reasoning, content, tool calls and usage. Shown in a Conversation View tab and a loopback viewer page.

Speaks a short status line when DSH changes state — turn done, turn error, job done, job failed, goal complete, goal blocked, an approval waiting, or the agent needs your answer — using eight pre-recorded clips in Chinese (default) and English. The audio is played by the host process through ffplay, or through the Windows PowerShell player that ships with the OS, so it does not depend on a Web Audio tab. Windows only.

Multi-instance ComfyUI orchestration: probes every configured ComfyUI endpoint for its GPU, free VRAM and queue depth, then dispatches a generation job to the idlest eligible instance. Ships three tools (comfyui_farm_status, comfyui_farm_pick, comfyui_farm_run). An instance is eligible only if it is reachable, has at least the requested free VRAM, and its queue is no deeper than the configured ceiling; eligible instances are ranked by free VRAM minus queue depth times a weight, so an idle shallow queue wins over a busy large one. Zero runtime dependencies. Optional retry on probe failure, because a single timeout across an SSH tunnel is not proof that an instance is down.

Long-term memory for DeepSeek Harness, read-only as of 0.1.0: a scribe_recall tool that reads a plain-markdown memory room, path rules that refuse directory traversal, Unicode smuggling and NTFS alternate data streams, and a bounded index whose truncation is always reported rather than silent.

Gives the agent four session tools: start a new session, send a message into another one, list sessions with their state, and wait for another session's turn to finish so its answer can be read back.