Plugins

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.

Sign in with a ChatGPT account and view Codex subscription usage directly in DSH Web's model settings, with browser or device-code OAuth.

Floating DeepSeek API balance capsule for the DSH Web GUI: a corner pill shows the remaining balance, clicking expands the total, granted and topped-up breakdown, double-clicking refreshes at once and the balance polls every 5 seconds; the host half proxies /user/balance so the key never reaches the browser.

Adds a sidebar panel to the DeepSeek Harness web UI that reports token usage and cost straight from DeepSeek's own usage API (today's spend, 7/30-day trends, today's hourly split, a history table, cost breakdown, peak/off-peak tier pricing), plus per-session detail from local logs. Zero-config: it reads the browser sign-in for the official figures, and falls back to local session logs with the source labelled.

Adds a Cmd/Ctrl+F find bar to the DSH desktop app, and it searches the whole conversation: when a match sits in history that is not on screen yet, the plugin pages that history in and searches again, so the match count and the highlights cover the entire session instead of only the rendered messages.

Conversation outline panel for the DSH web surface: user questions as root nodes (index, time, tool count and text volume per turn) with the Markdown headings of assistant replies hanging beneath them, plus level slider, search scope, bookmarks, copy and export as Markdown, section jump, keyboard navigation, a right-edge density rail and per-session reading-position memory. Read-only UI: it never touches prompts, tool results or provider traffic, and writes nothing outside its own localStorage keys.

loci second-brain sidebar tab: hybrid search, cited Q&A, day-grouped memory browsing and quick capture over a local loci knowledge base; proxies `loci serve-http` same-origin from dsh-better-sidebar, no core fork.