Plugins

Cross-session lesson book (the agent wrong-answer notebook) for DeepSeek Harness: injects a memory index capped at 2 KB verbatim into every turn, adds mem_recall and mem_save model tools whose write gate demands four sections, a locatable reference and explicit human approval before anything reaches disk, registers the /memory command, and keeps every lesson as a zero-dependency Markdown entry in the .memory/ directory.

Route conversation-compaction calls to a chosen summarizer model in the Web settings page, and retry them on a configured fallback model when the primary ends in an error.

Token usage panel in DeepSeek Harness Settings: folds session logs into day, week and month totals per model or per provider, persisted in the plugin storage domain and served over a same-origin /token-usage-rpc route; SVG line chart with crosshair hover, ranking with share and optional cost, cache hit-rate and cache read/write cards, a user-supplied price table priced per million tokens, daily and monthly budget alerts, CSV or JSON export of the current range, auto-refresh while visible, preset and custom start/end date ranges, and a rebuild that asks for confirmation before dropping history whose session logs no longer exist.

Shows the linked COROS watch model and cumulative activity days in the Web UI, expanding to a one-line review and suggestion when clicked.

Session-context surfaces ported from T3 Code: a session-row hover card showing machine, git branch, model, agent preset, approval policy and token usage, a status pill covering pending approval, awaiting input, working, error and subagent work, a provider and model chip, a per-session header strip, a lineage breadcrumb, row-menu actions that copy the context or run DSH compaction, and a preference row in DSH Settings for choosing which facts appear. Nothing is added to the composer.

Shows the API balance of the provider behind the current model as a dsh Web sidebar card, with per-package progress bars, currency/credit-aware units, a settings tab, and subscription and credit quota monitoring.

Three-window workbench for dsh web: chat, construct, and a read-only review window side by side for each workspace, per-window hooks, and an anonymous multi-model review that asks before it runs, groups findings by issue, and reports in Markdown.

TOFU BOX 伞包：一条命令装齐 tofu-zyc 的全套 dsh 插件（model-search、model-tuning、read-image-preview、shell-selector、computer-use、mcp-ui）。本包不含代码，只做两件事：以 dependencies 拉入六个子包，以 patch 层注册它们的插件行——即 dsh-base 同款 bundle 模式。装本包或单装子包，二选一，不要混装。

Global on/off switch for injecting workspace instruction files (AGENTS.md / CLAUDE.md) into the model context · 全局开关：是否把工作区指令文件注入模型上下文

DeepSeek Harness plugin: attaches a stable per-conversation session header to model requests routed to configured providers. Header name is configurable, so one plugin serves SMG (X-SMG-Routing-Key), OpenCode (x-opencode-session), and any other header-bas

Speaker button left of the model selector in the composer tool row — one click scrolls to the start of your newest question, marks it with a blinking caret and reads from there through the newest agent reply (dsh-tts, browser voice as fallback); press-and-hold the icon and then click anywhere on the page to pick another reading start position; press-and-drag-up opens a vertical mixer for in-page media volume and system output volume.

Shows which backend model actually served each request when using the auto route.

Persistent memory for dsh in the style of Hermes Agent: a memory tool that keeps a user profile and the model's own notes, delivered to every chat as a logged context message — at the start, after a change and after compaction — and a session_search tool

DSH plugin: model-generated session titles that follow the latest task, remember manual renames, persist their settings, and never fail silently.

WorkBuddy console for DeepSeek Harness, in one plugin: the account/model pool (merged from dsh-workbuddy-xdpool), the skill market with an in-composer skill picker, batch check-in, pending tasks, session health, history and credit usage. Bilingual.

One-click restart for DeepSeek Harness via a sidebar button, a model tool, and a detached watchdog.

Maintained fork of dsh-prompt-enhance, brought up to DSH 0.1.7 — the plugin would not even load on current hosts (InputState.imageIds became attachmentIds, so the composer button crashed the input box; settings.get() was removed; /enhance read a session id the agent no longer exposes). Rewrites default to reasoningEffort off, which measured 252 output tokens for a draft where the model default spent 2897, and a Settings page for all 17 fields is bundled. Verified on a real 0.1.7-rc.2 host: activation, a live HTTP enhancement request, /enhance in the GUI, and the Settings page reading and persisting configuration. 204 tests.

Chain-of-thought panel for the DSH Web right sidebar: folds the live reasoning stream of each session into turn → step groups carrying the reasoning text and the tool calls made in that step. Only the newest turn is expanded by default and earlier turns collapse to one line; steps are grouped into activity phases by a local rule, the step waiting on a tool is marked, tool failures show their reason, full reasoning text is fetched per step on demand, an all-turn directory searches turn titles, user text and turn numbers locally, and a whole turn can be summarised into a Chinese title with one model call.

Agnes Token Plan quota panel rendered as a config card on the Harness Plugins page: account-wide quota windows (5-hour requests, weekly requests, daily images, daily video) plus cumulative usage with a daily chart and the public plan catalogue, all read from the Agnes console API, with in-panel sign-in and automatic re-login. Four opt-in switches, off by default, register the Agnes models as an LLM provider, connect the AgnesCode desktop-app login state as a second upstream provider, and expose image- and video-generation tools to the agent.

Model-facing library_search tool: free cross-ecosystem (npm/crates.io/Maven/Go/PyPI/RubyGems + GitHub) 'has this already been built?' search — exact-name ranked, stars/downloads as fitness signals, no API key required

Model-facing codebase-memory CLI tools (codebase_list_projects/index_repository/index_status/search_graph/query_graph/trace_path/get_code_snippet/get_graph_schema/get_architecture/search_code/detect_changes/manage_adr/ingest_traces/delete_project) that ru

A session recap plugin for DeepSeek Harness with /recap, automatic idle summaries, and configurable models.

Infix rerun for DeepSeek Harness: re-run any earlier turn in place - the reply is regenerated from the same prompt while every later turn survives, so subsequent model calls read A B C1 D E F G. Implemented with the official surface-replace contract plus

Per-session LLM cost meter for the DeepSeek Harness Web UI: folds provider usage into uncached input / cache read / cache write / output per model and prices it against DeepSeek and Xiaomi MiMo pay-as-you-go rates (DeepSeek peak-idle tiering included).