Plugins

Context Transparency Manager: the model context as a visible, editable, effectiveness-scored surface (self-contained dsh bundle plugin)

Compaction ledger for the DeepSeek Harness: audit every context compaction (what was shadowed, when, at what token cost) and let the model recall pruned content on demand

DSH plugin: configure per-model reasoning effort levels for custom pi-ai providers in the Models settings page, with presets for GPT, Claude, Grok, GLM and MiMo models.

Session Fleet: model-facing tools that let one DeepSeek Harness agent discover, read, create, and message other DSH sessions.

Per-conversation toggle that makes the model answer in classical Chinese (文言 above a —— line, a modern-Chinese translation below) and speak as a blue classical-style fish that eats plain rice; each conversation keeps its own switch, and turning it off restores plain modern Chinese.

Cross-device conversation and task sync for DSH: one machine generates a relay station and the others join with its invite link; every frame is end-to-end encrypted, so the relay routes a hashed channel it cannot read. Peers read each other's full transcripts and task boards, interject into a turn that is running on the owning machine, send a work command that runs in a workspace of the target machine with the model strength chosen by the sender, and can copy a conversation into a new local session and keep working on it here. Ships a token-gated phone page for listing devices, reading tasks and sending a command.

Diagnostic evaluation plugin for DeepSeek Harness: freezes the confirmed Harness configuration, runs a benchmark, keeps the full session trace, and attributes failures to model, Harness, benchmark or environment.

Prove that a local image edit left every pixel outside its mask untouched. Original, generated and mask PNGs go in; a greppable `MASK_PIXEL_LOCK=PASS|FAIL|EMPTY` verdict, a difference heatmap, per-channel statistics, a bounding box and the largest changed pixels come out, plus a self-contained HTML report and `report.json` with a SHA-256 file hash, a canonical protected-pixel digest and a proof digest binding both to the policy. Supports edit and lock mask polarities, a mask threshold, tolerance and alpha-ignoring; PNG color types 0/2/3/4/6, bit depths 1-16, all five filters and Adam7. Zero dependencies, local only — no model call, no network, no upload.

Fills in the vision capability that DSH's "fetch models" step drops, so image-capable models stop being declared text-only, and marks them in the model name.

This project aims to bridge the Blender MCP Add-on, so that models on DSH can conveniently connect to the current user's working Blender to assist creation, while meeting basic security requirements.

Search BOOTH for VRChat avatar assets — clothing, shaders, base models, accessories, textures, animations and props — from a dedicated BOOTH tab beside the conversation or via two read-only tools, with Chinese keywords translated to Japanese before the request.

Study companion for your materials with guided practice, evidence-grounded feedback, Leitner spaced review, 18 teacher tools, and a Chinese/English student panel using the current DSH session model; requires DSH >=0.2.1-rc.2 <0.3.0-0, Python 3.11+, and Python runtime dependencies.

Mounts the pen.dev desktop app MCP server in a DSH session so the model can read and edit the .pen document open in Pen through the get_app_state, read_skill, execute, get_style and browser tools; finds the server binary by probing the usual install paths, and adds a pen-dev skill plus a listener that turns pen.dev plan-limit failures into a short bilingual notice. Unofficial, and ships no pen.dev binaries.

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.

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.

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.

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.

Composer status bar for GLM Coding Plan quota: 5-hour and weekly limits with reset times, MCP tool usage, and today's model usage, plus a glm_balance query tool.

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.

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.

/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.