Plugins

The composer predicts what you are about to type. Inline ghost text sits on the caret, measured against the editor's own font and line box, and Tab turns it into real text (Esc ignores it). The prediction is one short call through the session's own model router, seeded with your draft and the last few turns of the conversation, so an empty composer also gets a next-prompt guess written in the user's voice; suggestions that merely restate the assistant are dropped. Host side is one HTTP route with sub-path endpoints (loopback-only, 64 KB body cap, 2-minute result cache, 20-second miss cache, one in-flight call per session); client side is one 0-height overlay registered on conversation.input.overlay, with insertion guarded by the composer's draftRev CAS and a setDraft fallback. IME composition and slash commands are skipped. 16 node:test cases, zero runtime dependencies, real screenshots in docs/.

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.

English port of Windows Computer Use for DeepSeek Harness: 10 desktop tools (computer, computer_batch, open_application, windows, ui_elements, clipboard, switch_display, app_skill, request_access, list_granted_applications) with UI Automation, per-app access control, English settings UI and mini progress card overlay, Esc pause/resume, and DSH 0.2.1 unpacked koffi.node auto-discovery. Fork of copylee711/dsh-computer-use; it reuses the same plugin id and tool names, so the two cannot be installed together.

Distills long sessions into background observations and reflections, injects them as a system-prompt section, and renders compaction summaries from prepared memory; includes a Settings page and source-backed recall.

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.

A friend system for DeepSeek Harness: two DSH users see whether the other is online and whether their model is running a task, with an editable signature, mood emoji, pokes, and AES-GCM end-to-end encryption over a public relay.

Standalone QQ-bot extension pack for DeepSeek Harness — fully independent, no other plugin required. Two-layer SQLite memory with hippocampal recall, a persona that keeps learning from daily chats, group tiers, local-model quick replies with a single-brain arbiter, TTS outbox, sticker library, an approval-gated video studio, and a four-form desktop pet (three custom characters plus the stock fish) playable over a public invite link with access-code login, single seat and brute-force protection. Chat bridging is deny-by-default: c2c/group access defaults to a care mode that only responds to the special-cared people and groups of the owner (shared with the persona system, zero extra config); allowlist, open and disabled modes remain available. Requires QQBOT_APPID and QQBOT_SECRET, and Node.js 22.5 or newer.

Character persona summaries for DeepSeek Harness: collects moegirl-first public sources, distills them into a reusable persona document through the csp workflow, and keeps a per-character asset library with quality checks, manual source attachment, version snapshots and a settings page.

Per-Session OpenRouter routing: a loopback relay writes `service_tier`, `provider.sort` and the `:floor` variant into each request from one of nine presets picked on the composer chip, with a pinned base URL per preset for route-level defaults.

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.

Photo wallpaper for the DSH Web UI, with local image uploads and live mask, blur, saturation and panel translucency controls.

Keeps DeepSeek usage and account balance in a bar at the bottom of the window.

Composer-dock billing panel: DeepSeek account balance, official per-model usage and spend with cost per 100M tokens, plus cost estimates for this run and the whole conversation. Clicking opens a popover that matches the composer's width and position; balance comes from /user/balance, usage and spend from platform's usage endpoints, and the whole-conversation total is folded read-only from the local session log. Zero dependencies (node:https + node:zlib), writes nothing to disk.

Per-call token meter for the DSH composer: a colour-coded pill under the input and a dashboard above it showing every model call (total versus billable input+output), sub-agent spend, tool overhead and cache-versus-fresh input, read only from local session logs.

Always-visible account topped-up balance pill in the sidebar header, refreshed automatically and showing the same number as Settings → Account.

A composer-dock wallet pill for DeepSeek Harness that shows the account balance behind DEEPSEEK_API_KEY and opens a panel with the peak/off-peak billing window, a live switch countdown, and per-model token prices.

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.

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.