Plugins

Content-catalog guard for WeChat mini-programs: validates catalog.json so every activity price is an integer amountFen, every template renders prices through money(), required fields / duplicate copy / image paths are checked, and the result is an issue list plus a unified diff that can be applied with patch -p1. 29 rules over five groups (catalog shape, required fields and uniqueness, amounts, rendering, images). Three fixes are automatic (legacy yuan amount, string Fen, absolute image path) and preserve the file's own indent, EOL and trailing newline; everything else is reported with a hint instead of being guessed. Dry-run by default; apply re-checks the written file so the report describes what remains. One implementation serves a tool, a conversation panel and a CLI with exit codes 0/1/2. Zero runtime dependencies, no model call, no network.

Auditable token-cost ledger for DeepSeek Harness: wraps the llm/stream waterfall and records every call with provider, model, input/output/cache-hit/cache-write tokens, usage source and integer nano-CNY cost from an explicit price table. Aggregates by hour, day and session; exports JSON or CSV with a no-write dry-run preview; keeps a manually entered official platform bill in a parallel column with actual-minus-estimate diff. Unknown provider/model routes stay explicitly unpriced. Zero runtime dependencies; no balance query, notifications or animations.

Version-adaptive tooling for DeepSeek Harness: it reads the running DSH version from the plugin manager, mirrors app-boot plugin-compatibility rules (engines.dsh first, then @deepseek-ai/dsh* peers, prerelease-inclusive comparison, exact-version exemptions) to score every installed plugin, and statically flags source still using APIs renamed or deprecated between v0.1.6 and v0.2.1. Ships a conversation-view panel, an agent tool and HTTP state/scan/report routes. Read-only, offline.

Adds a writing console above the composer with four style tiers (T1-T4) and five rigor tiers (L1-L5), selectable by hand or left to automatic choice; keeps project terminology and banned phrasing in .mem/config.md with a read-only human section; and provides a whale_polish tool that rewrites expression without changing facts.

Explicit, project-scoped memory handoff: when you open a new conversation, one model call that you confirm curates the project's earlier conversations into a bounded brief and injects it into the conversation's first step. No silent background calls; a Memory panel shows the brief and lets you edit notes.

Codex-style drag-to-reference for DeepSeek Harness: drag a conversation row from the sidebar onto the chat area and it becomes a native session-reference chip in the composer draft, so you can keep typing around it before sending. The reference cap comes from the host (3 by default) and is read at runtime instead of being hard-coded, so it can be raised on the host side — a host patch you can hand to your own agent — and the plugin follows it without being changed. If the chip cannot be inserted, the plugin falls back to sending a reference-only message instead of failing silently.

Restart initiated by the agent itself, not by a button. The agent calls one tool, then the plugin takes over: it waits until every agent and background job on the host is idle, runs a visible ten-second countdown that a click, a scroll, or a key press cancels, then restarts DSH and wakes the original session so the agent carries on from its last sentence. No button, no manual entry: the tool is the only way in. Works on the official desktop app and the official web client; third-party shells are not supported out of the box. Windows only.

Prefixes every session title with the name of its workspace or project, so a flat session list shows which project each conversation belongs to; titles you renamed yourself are left unchanged.

Adds a Delete action to archived Session rows that permanently removes the Session log directory, the log directories of its subagent Sessions, its Workspace membership and archive mark, its projection-cache record and its spill directory; a Session the Host still holds is staged and finished at the next start or from a cleanup dialog. It also sweeps abandoned blank placeholders, leftover subagent Sessions and orphaned projection-cache records, and keeps blank placeholders out of the @ reference list.

Extension pack and patch set for the community @zaofan/dsh-qqbot plugin: a two-layer SQLite memory with a hippocampal-style recall and consolidation pass plus a persona drift guard, group tiers, persona/worldbook injection, local-model quick replies with a single-brain arbiter, a TTS outbox, a sticker library, and an approval-gated video studio that plans storyboards, quality-gates generated frames, renders a procedural 2D mascot and drafts Bilibili posts for the owner to review.

A simplified version of the Plan/Act feature in the RooCode and Cline VS Code extensions, binding one provider, model and reasoning effort to plan mode and another to act mode, with per-workspace overrides.

Signs in to ChatGPT by driving DSH's bundled pi-ai Codex OAuth flow from a settings page, revokes the session at OpenAI on sign-out, shows the signed-in account's five-hour and weekly quota, and limits the Codex route to seven GPT models with low, medium, high and xhigh reasoning (default low).

Retro CRT phosphor theme: pure-black Matrix green, 40K amber-green or TFEL amber screens with bold glowing text, a code-rain boot animation and a BIOS-style control panel.

Shows today's, this month's and cumulative spend in the sidebar footer, under the message box and in the session header. Spend is metered by the plugin itself from session usage events using official DeepSeek unit prices (peak/off-peak, weekends and holidays treated as off-peak), with local-day aggregation and currency conversion. Also adds a cost_today tool and a /cost command.

Token usage workbench for token-plan users: folds assistant/message usage from the session log into per-day call-level detail (cross-session responseId dedupe keeps fork/resume copies counted once), converts local volume into plan credits against terms you enter (default 1M tokens = 0.2 credits, caps 600/2500/6000 for day/week/month, optionally scoped to selected channels), and shows a composer-dock readout plus a settings page with per-provider cost table, 7/30d bar and line trends and a rolling six-month heatmap. No credentials are read: the remaining percentage a provider keeps behind its control-plane API is replaced by a clearly labelled local conversion, and reference costs come from the public DeepSeek pricing page.

Forked from j62268781-alt/dsh-skills-mcp-manager (MIT) at its 0.5.6 baseline and substantially reworked since; it registers the same plugin id, so it cannot be installed alongside the original. Adds lossless cordis.patch.yml writes (JS expression values preserved), save-gated per-tool filters, skills governance over the DSH roots plus 10 external agent directories with per-skill/per-source switches enforced through the agent-scope skills provider (disabling actually hides a skill from the model), categories and a restorable trash, GitHub-repository install/update/rollback, zip and SKILL.md import, skills.sh/ClawHub market, workspace view, sidebar panel, dark/light contrast fixes, and update checks against this repository GitHub Releases (npm publication carries OIDC provenance).

Delivery panel in the DSH sidebar: indexes every image and file sent to the harness (content-addressed attachments plus @-mentioned local paths), rebuilds Taildrop send history per target device from tailscale file cp calls in the session logs, lists incoming files (the Tailscale inbox plus unmarked files in ~/Downloads), and sends new files to a device from the panel with online status and upload progress.

Chat quotes for DSH: select text in any message to quote or comment; quotes wait above the composer and become jump-back quote cards in the sent message.

Read-only terminal view tab in the conversation header: aggregates bash output, background jobs and persistent terminal sessions from the current session, subagents and Agent Team teammates into one filterable panel, with type and session-scope filters, command/output search, auto-collapse, follow-scroll and a maximize dialog; foreground bash shows final output only. Requires DeepSeek Harness 0.2.1-rc.2 or later (0.2.x).

/cmd <command> in the composer runs that shell command in the session working directory, sends the command and its output to the model as a user message, and renders the input as a terminal card with exit status, expandable output and copy buttons; a bare /cmd opens an interactive terminal whose transcript is sent to the model with Ctrl+Enter. Runs with its own terminal permissions (danger-full-access) by default; set useSessionPolicy: true to use the session sandbox.

Quote any message of the current conversation into the composer: pick one from the @ menu, click the quote button on a user or assistant message, or select text and use Quote in the right-click menu. Quotes show as numbered chips in the composer and as summary bubbles above it; after sending, each quote becomes a fenced block so the model can tell quoted text from new text.

Review DeepSeek Harness responses with inline annotations, document reading, comment threads, and text revisions, then bring a reading summary back to the main conversation.

A 44x44 always-on-top desktop ball for DSH that reflects what the agent is actually doing (thinking, searching, web fetch, error, waiting for input) and shows an exclamation or question-mark badge when a task finishes or needs an answer while you are away. Windows only; it downloads its own Electron runtime on first use.

Fluid conversation width for the DSH web UI: the chat column follows the window minus a 64px margin, capped at 1560px and floored at 640px, while the built-in drag handles still override it.