Plugins

A read-only Cordis Inspect provider that lets an agent see the interface it is driving: outline() reports which UI regions the running shell actually rendered, with occupancy, geometry and current or past failure state; snapshot() returns one region's rendered node tree (tag, role, aria-label, own text, geometry, computed styles) addressed by slot key or CSS selector; failures() keeps a history of regions that failed to render and whether they recovered. Regions are addressed by the anchor the shell already writes for every slot, so it needs no region list and covers regions added later or contributed by other plugins. No UI, no tools, no dependencies, no network access.

Auto-hide a sidebar workspace the moment its last unarchived session is archived, and add a "隐藏工作区" entry to each workspace row's own "..." menu. The restore entry sits at the bottom of the sidebar. It only toggles display and never archives, deletes or rewrites a workspace.

Composer prompt polisher: a button in the input tool row rewrites the current draft through the session model (workflow engine, enabled automatically) or an OpenAI-compatible standalone API with host-side key storage, backfills the rewritten text with a replace/give-up dialog when the draft changed mid-run, and ships concise/structured style presets, custom templates with a {draft} placeholder, one-click restore from the status dock and reference-chip protection.

Rewrites your composer draft in the voice of a chosen character card before it is sent, using the model the current session is already on, with an optional review panel and a local check that reports any identifier or path the rewrite dropped.

Task-list staleness guard for DeepSeek Harness: watches the session event stream and counts tool calls since the last todo_write; past a configurable threshold it appends one short notice before the next step, quoting the current list, so the model writes it back to the real progress instead of leaving a stale snapshot on screen. Pure prompt injection, no blocking and no data mutation.

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.

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.

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.

Zotero library tools for DeepSeek Harness over the localhost local API (read) and the connector saveItems endpoint (write). No cloud, no API key.

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).

A planner board as a third tab beside chat and trajectory: a Monday-first month calendar above per-day cards holding title, note, times, three importance levels and a completion checkbox. Plans repeat daily, weekly or on weekdays with an optional end date; editing or deleting asks this occurrence versus the whole series; completion is tracked per day; one button clears a day while only skipping recurrent series. Five model tools let the agent read, write, delete, clear and undo plans in conversation.

Windows-only process control for the harness: a sidebar button that shuts DSH down through the host's own graceful exit path, an app-window / normal-tab switch on the Plugins card that rewrites the desktop shortcut and restarts, and advanced settings for the wait before exit, the process exit code and a force-quit option.

Audit DSH skills automatically: a host-layer tools/post-execute plugin that ships both the skill body and the audit engine, runs the engine after skill files change (write/edit/shell) or after a bulk restore/backup (any tool invoked with mode: restore|bac

Windows desktop control through UI Automation: nine tools that read a window control tree and drive elements by id through their own UI Automation patterns, with every write gated by an approval policy, an append-only action log and a settings panel.

Brings the Codex (ChatGPT Plus/Pro) subscription already signed in on this machine into DSH. It (1) shows the 5-hour and weekly windows with their reset times and the remaining reset credits in a sidebar panel, with one-click reset that consumes a credit; (2) registers the subscription route in llm-pi-ai (openai-codex) when the quota is read, so the Codex models appear in the model picker; (3) refreshes the OAuth access token before expiry and writes it back atomically, so no key has to be replaced by hand; and (4) adds a codex tool that delegates a task to the local Codex agent. No API key has to be entered.

Session change-review for DeepSeek Harness: tracks write/edit tool calls and renders VS Code-style side-by-side diffs via diff2html, auto-following the theme, with subagent aggregation and one-click revert.

Host- and agent-layer DeepSeek Harness plugin that prices every automatic context rewrite before it lands, asks the human by default, and reports what the provider had to re-read cold.

Workspace checkpoints per tool call: records every file mutation inside the workspace (excluding .git and node_modules by default), including changes made by shell commands rather than by write/edit, and stores the previous content of each changed path in a content-addressed store kept outside the workspace. Restores have two modes — undo one record, or return to a point in time — with a line-level diff preview, a dry run by default, and a rescue record written before every restore so the restore itself can be undone.

Adds a sparkle button left of the model selector in the composer: it rewrites the draft into a clearer, more complete task brief, replaces it in place with one-click undo, offers five rewrite styles, and greys out while the draft carries file/command chips.

Session evidence reports: /transcript writes styled HTML / Markdown / JSON reports from canonical logs, /stats prints a terminal stats card, /archive writes per-session ZIPs.

Redraws line-level diffs on edit, write, insert and str_replace_editor tool cards — unchanged lines render once and changed characters are underlined — covers run_code (PTC) sub-calls, adds a per-turn changed-files card, and opens or copies any of those paths from the card rows and the tool rows through a host route the plugin serves itself.

Zero-intervention permission gate for DeepSeek Harness (DSH) agents on macOS — active on install. Writes that can be undone via a local git baseline or macOS Time Machine are auto-approved and automatically snapshotted; network access, package installs, process/system management, and reads of sensitive credential paths are blocked; every decision is audited — the audit log keeps everything by default, with optional automatic cleanup of the oldest records.

Local relationship-memory workbench with a confirmation gate: every AI write — extracted memories and newly created contacts alike — lands in a pending queue until the user confirms it in the GUI; materials are archived verbatim with quote-level provenance checks on AI extraction, and confirmed memories aggregate into per-contact timelines, gift occasions and reciprocity views. Ships a native relationship agent preset for conversation capture; JSON storage by default with an optional SQLite backend, zero production dependencies.

A full-page console panel opened from the sidebar, with eight tabs: an overview; a session list read from the sessions service (title, directory, running state, updated time, with filters); installed bundles and Loader entries from pluginInventory and pluginManager, with per-bundle enable switches; a plugin market listing public topic:dsh-plugin repositories from the GitHub search API; a model and provider editor that writes the llm-pi-ai settings namespace through remote.settings.mutate (switch a session model, add or edit providers and their model lists, and store API keys via remote.credentials, merging over the stored profile so fields the form does not expose survive an edit); MCP and skills tabs; and a usage tab that reads the host's loopback /api/dsh-usage/overview document. Services are declared through ctx.inject, so a deployment that omits one mounts without the console rather than crashing.