Plugins

Connects DeepSeek Harness to a local SolidWorks install through an MCP server, with a read-only default mode and per-call confirmation for high-risk operations. Windows 10/11 x64 only; needs Python 3.10+ with mcp, pydantic and jsonschema (plus pywin32 and comtypes on Windows) and a local SolidWorks 2023-2026 installed and started at least once.

Local-first experience library for DeepSeek Harness: indexed markdown knowledge with error-signature retrieval, failure capture, gap-to-entry closure, and a sidebar panel. Ships a sanitized starter library. No network access.

Long-conversation memory for DeepSeek Harness (DSH): keeps settled decisions, user corrections and exact numbers, with their conditions and sources, available across compaction and restarts in 100-1000+ turn sessions; one small budgeted evidence block per model step, with enabled skill rules re-applied in the same block.

Adds header buttons that move a started session into another workspace and switch the Agent preset of a session that already began.

Adds a Continue button to the composer dock and resumes automatically when a turn is cut off by a network drop or an upstream output-limit cut. A resident link monitor asks every 10 seconds whether the network is back, because the link returning fires no event, and a turn that completes normally counts as proof the link works. The click goes through the host submission pipeline — beginSubmission plus session.prompt — so the message carries real user attribution instead of faking one, and a genuine refusal is reported rather than retried. On startup it also scans recent session logs for both fingerprints of a host that left mid-turn: an unclosed turn, and a turn closed as disposed, which is what a normal shutdown writes. A turn the user stopped by hand is never resumed.

Set the startup window size of DeepSeek Harness Desktop from a settings page, with 4:3, 16:9 and 16:10 presets and up to 12 custom presets.

Adds a button to the composer that restates your draft, then asks a few questions with clickable options — every question offers an "I don't know, you decide" escape — and only then rewrites the draft into a request an agent can start on. The whole flow can be finished without typing, and it never sends for you.

Turns real DSH crash logs into a short hard-constraint list: static preflight before a plugin installs, conflict check afterwards, controlled self-heal when the harness will not start — plus handing a huge session over to a fresh one, the brief written by a model that reads the original transcript.

Windows only: a night-and-moon themed floating button (a sleepy DeepSeek-chan whale mascot, awake/sleeping artwork) in the bottom-right corner arms the plugin — click it to power the machine off once every root Agent session has gone idle, and click it again to disarm. The button is draggable (position remembered in localStorage), automatically dodges other plugins' corner popups, and survives the frontend re-rendering it away. When the batch finishes a 60 s cancellable countdown starts (configurable 10–600 s) with the remaining seconds on the button and a matching banner: clicking Cancel runs shutdown /a and disarms the mode, and any new session starting during the countdown aborts it. A right-click menu on the button switches the shutdown condition between only-on-success and shutdown-regardless, persisted across restarts in $DSH_HOME/deepseek-chan-sleep-shutdown.json. Zero runtime dependencies.

Static-context audit for a DSH home: a six-layer baseline (rules, memory, skills, tool surface, sessions, KB), broken-path checks for a markdown capability map, memory duplicate/stale/over-limit reports, SKILL.md description compression, and tool-surface plus cold-start static-context estimates recovered from session logs. Four read-only DSH tools; writes require --apply and are backed up first. Requires Python 3.10+ on the host (stdlib only; all four tools shell out to the bundled CLI).

Per-workspace session defaults for DeepSeek Harness: save the Agent preset, permission preset, model, reasoning effort, Chat work-details level and collapse timing per workspace; new or reused blank sessions in that workspace start from them.

EVA armor HUD theme skin for DSH, with startup animation and sequential UI entrance animation.

A transparent always-on-top desktop pet for DSH on Linux (X11 / XWayland), driven by the session state. The pet lives outside the browser as its own window, follows the pointer with a distance and per-display limit, shows a live session-status bubble that lists each session task and state, and auto-starts with your session. Linux only (X11/XWayland); needs Python 3 with PyGObject, GTK3, GdkPixbuf and xdotool. Its sprite sheets come from @michengai/dsh-codex-pet (MichengAI/dsh-codex-pet in this list).

Three things for DSH plugin development: reload the plugins whose files changed, restart the client when a reload cannot apply a change, and let the model trigger a reload itself. Reload uses DSH's own path, so untouched plugins keep running. Restart starts outside the client, so it completes even when the client is what gets replaced, and refuses while a session or job runs. Lightweight: no parameters, no added context, buttons off by default.

Progressive disclosure agent preset and call directory tool that starts from a minimal baseline and unlocks tools, skills, and MCP servers on demand.

Command DeepSeek Harness from Telegram and Feishu (Lark): one live progress message per turn, approvals and questions as buttons, files and voice, delivery that survives outages and restarts, QR setup for Feishu, and per-person roles.

Adds a Restart card to the harness settings: one click hands the restart to the DeepSeek Harness launcher (`Launch-DeepSeekHarness.ps1`), which replaces the running web process, and the page reconnects itself once the new instance answers. Windows only; without that launcher the button reports an error instead of restarting.

Colored status marks on DeepSeek Harness sidebar workspace rows — waiting for you, running, or recently finished — aggregated per workspace, plus a pinned-conversations section above the list and pinned-only notifications, persisted across restarts.

Folders for the DSH Plugins page: group installed plugins, toggle a whole group, batch move with undo, search across groups, long-press drag to reorder, reinstall removed plugins from their record, and restart Harness with one click.

Restart button for the Harness desktop app: one sidebar entry that closes every Harness process and starts the application again, launched without a console window and without a close-confirmation dialog. Windows only.

Restart control for the DeepSeek Harness desktop app on Windows. A session header button or a tray icon stops the app and its host process, waits for both to exit, clears a stale profile lock, and relaunches, so a newly installed plugin loads without quitting the app by hand.

Three literature-research skills packaged as one DSH plugin: academic-web-research (lightweight proxy fetch), academic-literature-research (Scholar/IEEE/CNKI/Wanfang/Sci-Hub pipeline), off-campus-literature (campus WebVPN/CARSI access). Installing drops the three SKILL.md folders into ~/.dsh/skills/, so the agent can invoke them by name after a restart. The bundled web-research skill assumes a local HTTP proxy at 127.0.0.1:7897; edit it if your setup differs.

Agent Settings: manage reusable sub-agent profiles in the sidebar, each with a when-to-use description and its own provider/model route, and let the agent start the matching one as a subagent.

Task timing for DSH agents: a task_clock tool that measures elapsed time on the host monotonic clock, resumes across DSH or system restarts with the gap estimated, and returns unknown rather than inventing a number; it does not touch presets.