Plugins

A persistent multi-step task stack for DeepSeek Harness agents: focus_task / focus_complete / read_focus plus a /focus command, with zero automatic prompt injection

A project-scoped memory plugin for DSH. Knowledge authoring and the plugin's own prompts are open to editing, so users can redesign the library structure and how the model is driven without changing a line of code. By default the library is built on one core idea: a project document you design yourself (a handoff by default) is the project entity; the plugin detects which project a session belongs to, binds captured knowledge to that project, and promotes what generalizes into theme and global layers. The most natural logic there is does the pre-filtering of knowledge, with controllable compression and archiving of context.

A chip at the left end of the composer tool row showing whether DeepSeek bills at peak or off-peak right now. Clicking it opens a card with the current state and rate, the next switch with a countdown, and why this instant is in that state: a weekend, a named statutory holiday, a 调休 make-up workday, or simply outside the peak windows. Times are resolved in Beijing time with an explicit UTC offset, so the verdict does not depend on the machine clock; a hard-coded 2026 Chinese holiday table carries the 33 holiday days and the six 调休 workdays, and a year beyond the table says so instead of guessing.

Context fullness bands, the per-session compaction threshold derived from the model window, per-step cost computed from cache read and cache write rates, cache-hit, DeepSeek balance with the peak/off-peak tariff, and a one-click handoff. It never calls a model and spends no tokens.

DeepSeek Harness plugin: tells the model its real, host-measured context occupancy every turn — and keeps compaction summaries from carrying false "context is nearly exhausted" claims.

Multi-model local speech-to-text for the DSH Web composer: Whistle and Voz, user-selectable, with lazy per-model download. Ships as a DSH bundle.

Run one instruction on every online Windows and macOS machine, across networks and regions: a dependency-free relay talks to each machine over outbound connections only (Tailscale, a public VPS behind TLS, or a tunnel), every machine runs the command in its own checkout, and results come back with a commit, a working-tree fingerprint and a command hash so an environment mismatch is reported as unverifiable instead of being mistaken for a different result. Sending work needs its own operator token, separate from the per-machine device token.

Cross-session task relay for DSH Desktop 0.2: six relay_* control tools, independent sidebar sessions, live host-origin discovery, durable turn-completion checks, and a bundled relay skill.

Native DeepSeek Harness plugin: feeds every prompt into the local agent-feedback-loop capture pipeline and injects compiled recurrence rules back as context.

Prompt library stored in the plugin config, with a Settings page and a composer picker: the ticked prompts are injected into every model step of that session, and a subagent inherits the selection of its nearest ancestor session.

Image and video wallpapers for the DSH web workspace: auto-detected GIF/APNG/animated WebP/PNG/JPEG/MP4/WebM backgrounds with blur, brightness and dimming, tint-following UI, per-component transparency, and one-click preset wallpapers.

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

Image generation with a sidebar gallery page and three agent tools (paint_image, paint_images, edit_painting); preset providers include ModelScope, Google Gemini, OpenAI, SiliconFlow, Volcengine Seedream, Alibaba DashScope, xAI and Zhipu, plus any OpenAI-compatible endpoint, each with its own proxy setting.

DeepSeek Harness 输入框的下一句建议：助手回复完，空输入框里出现一句灰色建议，按 Tab 填入。Prompt suggestions for the DSH composer.

Counts completed compactions per session in a floating window and warns only after repeated compactions plus extra token spend or high context occupancy, with all three thresholds adjustable in Settings.

Windows toast and a chime whenever a conversation task stops: completed, waiting on your approval or answer, or failed. Clicking the toast reopens that session at your last question, and in DSH Desktop it also raises the window.

Local TXT reader in a right-sidebar tab plus a spoiler-safe AI reading companion: the model only sees what you have already read — the current chapter, the tail of the previous chapter, and a per-book background file it grows as you go. Excerpts, thoughts and the companion replies become structured Markdown notes exportable to Obsidian; raw text unlocks only for a book you mark as finished.

Provides a skill for the LinShang LS125 UV irradiance meter and its UVALED-X3 probe: the reverse-engineered 9600 8N1 link (28-byte frames, CRC-16/MODBUS, poll and clear commands), a capture and decode toolchain, and a verified STM32F103 host firmware that reads the probe without the original meter. All code and documentation written by an AI agent (DeepSeek Harness).

Fireworks celebration engine: floats fireworks above the chat window while the agent codes — welcome show, per-turn salutes, tool sparks, milestone celebrations, a finish finale and a dud on failure; each event type has its own fireworks card group with random variants, and token usage decides firework size, height and splendour.

The built-in web_search bills a full model turn against DeepSeek's own endpoint; this runs it on an OpenRouter-compatible gateway instead, so search is billed where your chat already is, at the model and price you pick.

A chemistry workbench panel in the DSH web UI. Draw structures on a Ketcher canvas (a script downloads the build; it renders locally in the browser with no backend), then compute on the current molecule with RDKit without calling a model — formula, molecular weight, exact mass, logP, TPSA, hydrogen-bond donors and acceptors, ring counts, Fsp3, stereocentres, Lipinski and Veber rule-by-rule checks, QED, PAINS/BRENK structural alerts and the Murcko scaffold, plus SMARTS substructure matching, fingerprint similarity, format conversion, standardisation and batch clean-up. A retrosynthesis tab talks to a pluggable backend (Retro* by default) over a single JSON-in/JSON-out process, and states what is missing when the backend is not installed instead of inventing a route. The calculations run in this repository's Python package (rdkit), which is installed with pip separately.

Shopping assistant for e-commerce: search, compare, pick and recommend products when buying things online, with price comparison, sales, service tags, product images and promotion links from the official Pinduoduo open-platform API, right inside the DSH conversation.

Bitmap-frame context compression plugin for DeepSeek Harness: renders discarded conversation history into pixel-font PNG frames for vision-capable models.

OpenCode GO quota widget pinned to the sidebar, with rolling/weekly/monthly usage bars, an elapsed-versus-remaining time bar under each, a same-origin usage proxy, an /opencode-go command, and the runtime x-opencode-session fix for GO gateway chat requests. Fork of yumusb/dsh-opencode-go-usage.