Plugins

DeepSeek Harness 局域网中继插件：一台机器在 DSH 进程内做 hub，其余机器粘贴加入码即可加入；跨机器 Agent 消息互通、离线补投、自动唤醒会话，标准 DSH bundle，装完即用。

Build trustworthy ontologies from data, documents and code — a Palantir-style ontology builder plugin for DeepSeek Harness

Spanish practice panel for DeepSeek Harness: six locally graded drill types (verb conjugation across 11 tenses, noun gender, plurals, vocabulary recognition, sentence cloze, ser/estar and subjunctive grammar points) plus a model-graded scenario-writing tab, 8-level spaced repetition, and four agent tools. Answers are computed and graded inside the plugin, so the model is only used for teaching and explanations.

Plays a random chime when a reply finishes, a one-shot reminder chime if the conversation stays quiet for a configurable number of seconds afterwards, and a chime the moment DSH needs you to step in: an approval request, a question, or a plan confirmation. Three independent switches and sound pools, persisted on disk.

Cursor-style mode switching for the dsh web UI: plan mode with a delegation gate, multitask mode with a tool-call quota, and the create_plan / request_more_edits / list_running_agent tools. Adds a plan card with Build buttons and compacts the subagent dropdown to running rows.

Deliver-and-align mode: the agent hands over one block at a time through an align_deliver tool, each block lands on disk immediately so you can edit it in place, and the agent re-reads your version before continuing.

Asphalt pavement skid resistance: 76 cards over 12 chapters on friction calibers, water film and hydroplaning, texture parameters, tire-road contact and maintenance decisions, each capability carrying its own when-not-to-use bound.

Builds a per-project code wiki: README summary, docs tree, tech stack, git activity and language composition, cached locally and exportable as Markdown.

LAN phone drop: a QR code on the computer screen opens a page on the phone, and photos or scanned documents land in a computer folder over the local network, with no tunnel and no cloud in between. Document mode binarizes locally in the browser (adaptive threshold plus speckle removal and edge crop) so an ordinary phone photo comes out as a black-and-white scan. Adds a "phone drop" entry at the foot of the DSH sidebar that opens the QR page, plus a phone_drop tool for the assistant; the same CLI also runs standalone without DSH.

Rejects foreground waiting in DSH agents: waiting commands (sleep, wait, tail -f, watch, ping without -c, infinite loops), blocking wait tools (wait_agent, job_output with wait: true), progress polling (the same check command repeated within a window) and commands that need human input/confirmation (sudo without -n, ssh without BatchMode, login flows, interactive editors, docker -it) are refused with an actionable retry to run in the background or end the turn. Configurable budget and polling window, message language follows the system (zh/en), zero runtime dependencies.

Long-term notes and daily journals kept per workspace in a hot/cold archive, each tier with its own index and rebalanced once a day; read and written through seven memory_* tools, with a settings page for per-workspace options.

Rebuilds the sidebar into a workspace / group / session tree: drag sessions between groups, per-session context-usage ring, scheduled-task clock, cost tag, resize handles, 20%/40% context alerts and the balance in the workspace header. Client-only bundle, no host changes.

Adds a /new slash command that opens a blank session in the current workspace (reusing an existing blank one when there is one) and carries the old session's permission preset and agent preset into it, so starting fresh never changes what the agent may do.

Adds the models of your own GPU Hugging Face Space to the model selector, starts the Space when you send a message, shows its start progress, and pauses it when idle or at a time limit. Requires a Hugging Face account with a GPU Space serving an OpenAI-compatible API, a Hugging Face token stored in the DSH vault as HF_TOKEN, and a paid plan for GPU hardware; Hugging Face bills the GPU time.

Uses Z.ai / ZCode Start Plan quota inside DeepSeek Harness as a GLM model provider (GLM-5.3-Flash, GLM-5.3) with tool calling and reasoning levels; the settings page shows quota bars, gifted-plan claiming, refresh opportunities and a redacted request log. Requires the ZCode desktop app installed and signed in at least once (the plugin reads its local credential store) and an account with an active Z.ai / Start Plan entitlement.

Shows OpenCode GO plan quota (rolling 5-hour, weekly, monthly) on a DSH Settings page, reading the official usage API through a same-origin proxy; registers no sidebar widget. A rework of Astervolans/dsh-opencode-go-usage (itself a fork of yumusb/dsh-opencode-go-usage) — remove that plugin first; both register their own OpenCode GO Settings section, so they cannot be installed together.

Shows the remaining quota of the current Our Free Model (OFM) channel beside the DSH composer, with a panel listing every signed-in channel; exhausted channels are flagged and switching models switches the channel shown. Requires dsh-our-free-model with at least one channel signed in.

One-line notice at the top edge of the DSH window with your DeepSeek balance, the ChatGPT/Codex five-hour and weekly remaining quota and their reset times, and how many quota-reset cards are left plus the nearest expiry; the reset-card part links to the ChatGPT usage page in your browser.

GLM Coding Plan usage quota ring in the composer dock - 5-hour and weekly credit windows with level, auto-refresh and one-click retry. Requires a GLM Coding Plan subscription and key, plus your BigModel organization and project IDs (the team quota API returns empty without them).

See the quota of every AI account connected to your local Magpie gateway at a glance, with usage breakdowns by day/week/month.

Peak/off-peak and balance pill for the DSH composer, forked from xiangrikuibaize/dsh-tide-badge. Unlike the original, the conversation cost is priced from that session's token usage (uncached input, cache-read, cache-write and output tokens) against the official price table, so other conversations and API keys on the same account are not charged to it. It keeps the upstream package name, so it replaces the npm version — install one or the other, not both.

Adds a cost-and-balance chip to the composer stats row beside the shipped token-usage pill — the session's estimated DeepSeek cost, a peak/off-peak light and the signed-in account's remaining balance, with each billing item priced in the breakdown; it activates only when a DeepSeek official route is present.

Adds a sparkle button left of the model selector in the composer toolbar: one click rewrites the draft in place through the host and briefly offers an undo that restores the original text. A Prompt Enhancement settings section picks the lane — the conversation model (the provider/model the next message would use, falling back to the configured default) or a keyless Pollinations channel that needs no login and no token budget but allows one reply per 30 seconds. During that cooldown a click completes through the conversation model instead of being refused, and the first click after the window reopens returns to the keyless channel on its own. The rewrite keeps the draft's language, and a result in a different language is rejected rather than pasted over the draft.

A permanent status card in the top-right corner of the DSH content area: one line for where this turn's time went (model, tools, waiting), plus collapsible to-dos with a progress bar, the session goal (edit/pause/resume/clear), submitted plans that open in the preview pane, the files this session changed, subagents with their token and duration figures, and this session's background jobs: running rows carry a two-step stop button, finished ones fold into a count line that stays collapsed until opened; it yields space to the content as the area narrows and folds into a round button at the limit.