Plugins

Adds lasting bots with their own name, photo, persona, memory, voice and model, a Bots panel in the sidebar, and a hidden helper subagent per bot that follows the conversation, searches ahead and leaves notes the bot reads; voice uses your own ElevenLabs, OpenAI, Groq, Mistral or Deepgram key. Interface and prompts in Brazilian Portuguese.

Give your agent an external emotion state machine: several axes (0-100) that drift over time and move when you speak to it. Each turn the plugin injects which band you are in plus which tags you may use. The numbers belong to the plugin: the model reads them from the injected prompt and can change them only through the plugin's own emotion tools, never by asserting a mood.

Remembers the model used before quitting and restores it as the startup default.

Connect DeepSeek Harness to the local Codex CLI with dynamic model discovery, image input, Harness-owned tools, and read-only ChatGPT plan and quota display.

After user setup, guides native subagents toward model preferences by task type, using native model-selection permissions with no extra routing-model calls.

Adds MiniMax open-platform models to the DSH model picker: paste the API key in Settings and MiniMax models become selectable, with the M Plan quota windows shown beside the composer.

Signs in to ima.qq.com (Tencent IMA) with a WeChat QR code and runs a localhost OpenAI-compatible relay in front of its SSE chat endpoint, so the four models behind it appear in the picker.

TeleAgent (China Telecom TeleAI "Stellar" agent) model provider for DeepSeek Harness: corrects the cloud gateway request signing to two-round HMAC-SHA256 keyed by the login JWT signature segment, which fixes the 40104 failures the older local-v1 signing produced, and adds points balance, daily check-in, and an in-composer account chip. Reuses the existing local login credential. Cannot be installed alongside anye-99/dsh-codearts-auth — both register the same teleagent provider, and this plugin reuses its credentials and derives its SSE/tool-call parsing from it.

Per-turn cost in CNY, with 本轮 / 今日 / 会话 totals shown above the composer. Tokens are priced by model and by the moment they were spent (peak hours and holidays); native DeepSeek search spend can be folded in when the optional audit plugin is installed.

Read-only observer of native DeepSeek search model calls: appends each call token usage to a JSONL file so accounting plugins can price it. Requests and responses are not modified.

Usage panel for the provider account behind the current model: quota windows, credit balance and token usage, following the model automatically. It renders as a full page, plus a sidebar entry and a per-session usage chip in the conversation header.

Speaks the estimated spend of each turn aloud with an Alipay-style voice clip or a bundled meme voice; amounts come from dsh-cost-meter when installed, otherwise from per-model token prices. All audio is bundled, so nothing is fetched at runtime.

Cross-session per-model token usage replayed from the harness's own session logs, with a usage panel tab (requires dsh-better-sidebar) and a per-conversation model popover.

One Settings page for OpenCode Go: an account pool that rotates A-to-B when a key runs out or stops authenticating, per-account 5-hour/weekly/monthly allowance, per-model spend with remaining quota, capability tags (image, video, text-only, tools, reasoning), a live OpenCode-vs-official-API cost comparison, and 10 UI languages.

Right-click any selected assistant reply and add it to the composer as a removable quote chip. The selected text is delivered to the model as hidden context, so your message bubble keeps only your own words.

A DSH workbench for picking photos from local folders on macOS and Windows: local dedupe, filtering and grouping, AI grid triage and scoring with an image-capable model you supply (the plugin bundles no model, credentials or quota), then human review, calibration and export.

Replaces the composer's model selector with a starfield popup that sets the model and its reasoning effort in one control, and remaps the current effort to the nearest level the new model declares instead of failing the switch.

MCP server panel for the DeepSeek Harness Web GUI: the sidebar lists every @deepseek-ai/dsh-mcp-client row — including rows inserted by other plugins — with a connection state derived from the loader fiber plus the mcp__<server>__* tool count, shows that row's configuration, enables or disables it by editing only that row of the patch file, and reconnects once after a failed attempt.

A collapsible column beside the conversation that organises conversations into a workspace/topic tree, opens the real sessions in place, and exposes the tree to the assistant through 9 model tools.

Quote selected text from a DSH message into the composer as a blue chip, hover to read the full quote, and remove it with X or Backspace; sent quotes reach the model as a blockquote.

A personal life workbench as a sidebar panel: sleep, meals, workouts, spending, weight, schedule and to-dos share one page of cards that react to one another, and one sentence typed at the top is turned into structured records by the model configured in DSH. Records and card layout stay in local browser storage.

Model brand marks in the composer model selector; vendor and model marks across Settings → Models (provider rows, model rows, the add-provider dropdown); and a per provider/model icon picker that stores overrides in the DSH user settings document.

Selection comments on assistant output plus an independent side-chat window in the DSH Web GUI: annotate model output with floating comments, send those comments with the next message, and continue a question in a separate forked conversation that stays out of the sidebar.

Counts the assistant rounds that call tools without writing anything to the user, then inserts a short progress reminder as a visible user message at the next model-request boundary, so a long silent tool loop reports what it has done before continuing. A Settings page adjusts the silence threshold (default 10), the reminder wording, the language (en / zh-CN / zh-TW), whether the reminder repeats every further threshold of silent rounds, whether subagent sessions are counted, and whether Agent Teams nudges the lead only or every member.