Plugins

Pure JavaScript macOS Keychain credentials provider for DeepSeek Harness, replacing plaintext .credentials.yaml storage and fully supporting both refs and records without native builds, signing, or Xcode.

Shows a reminder card in the bottom-right corner of the DSH web GUI whenever the agent is waiting for your answer, and adds a desktop notification plus a flashing tab title when you are on another tab or window.

OpenCode Go provider that verifies a model against the gateway rather than treating a recommendation as a measurement: the models.dev protocol suggestion is probed before it is used, reasoning levels follow a measured contract, and requests run through an ordered protocol fallback chain. Context window, max output and image-input numbers are declared by a runtime-refreshed models.dev layer rather than probed, with operator overrides above both. Several OpenCode Go credentials can be stored and switched from the settings page.

Floating phone-pairing QR button for the DSH WebUI. One click opens the dsh-remote-link pairing QR (image + 6-digit code + TTL) in an in-app overlay — works in both browser and DSH Desktop (same-origin img, no iframe).

Webhook notifications for dsh sessions: a POST when an approval is requested or a turn ends, to ntfy, Bark, a Slack/DingTalk/WeCom bot URL, or any HTTPS endpoint.

Persona engine for DeepSeek Harness: one config.json drives the AI's self-name (per model, per tier), how it addresses you, relationship stance, character text, per-item work contracts with individual toggles, thinking-chain language, appearance and reply tone (both opt-in and per-model overridable), and long-term memory gated by human confirmation - the AI can only append proposed candidates, a human confirm line flips them into effect, and the log is physically append-only and replayable. Confirmed entries are injected as a quoted data-not-instructions block; entries tagged with a kind can instead be routed to arbitrary files on confirmation and never reach the prompt. Three prompt sections re-evaluate from disk on every assembly, so edits apply on the next step with no restart. Persona presets are shareable JSON snapshots (imports and exports SillyTavern character cards, v2/v3 read, v2 written) and deliberately never carry memory. Zero runtime dependencies, no network, no shell; any error degrades to an empty section rather than a broken session. Ships blank - installing changes nothing until you write something.

Telegram remote control for DeepSeek Harness: list conversations with titles and workspaces, resume paused persisted sessions on demand (preset remount), turn-tracked reply relay, first-line reasoning summaries, inline-button approve/reject with outcome edits, and a bot command menu.

Adds a Run button to shell code blocks in replies, executing the snippet through the host shell service and showing its output in a floating bottom-right dock, or in one bottom-panel tab per run.

Humanized fork of @xmanrui/dsh-im (base 4.21.2): humanized message delivery with send-delay and typing two-phase, message_break + streaming coexistence, status reactions, reply quotes, per-bot humanize overrides, and a no_reply reclaim tool — across WeChat, Feishu, DingTalk, WeCom, QQ, Telegram, Slack and WhatsApp channels.

WeChat bridge for DeepSeek Harness over Tencent's iLink bot channel: one session per contact, inbound text/images/files, and WeChat's native typing indicator while a turn runs.

Bridge a Feishu bot to a DSH session: open a real session in a workspace, run tasks with the existing model and plugins, and report results back.

Session usage statistics panel: token and request stats at day/hour/minute granularity, an activity heatmap, bottom-bar session info takeover with per-turn cost chips, and cost estimation under multi-condition time-segmented pricing. Re-implemented from HaoyueQin/dsh-usage-statistics-panel with extensions.

Feishu multi-agent robot console: start, stop and reconnect the daemon, view status and recent activity, and jump to the task workspace.

Engineering work-tools for DeepSeek Harness: registers two model-facing Host Tools — a scoped `git` runner, and a package-manager runner (`dev`) that detects npm/pnpm/yarn/bun from the workspace lockfile and picks the right verb per manager. Both run through dsh's sandboxed shell and return structured stdout/stderr/exitCode, so the agent gets focused, reviewable results instead of raw bash, and adding another tool is a copy-paste of one register block.

DSH cordis plugin: task dispatch, session wake-up and completion reporting through the AstrBot dsh gateway.

A Models settings companion page listing every model's input modalities in one place, editable for both LLM adapter families

Byte-faithful text editing tools (edit_text / write_text) for DeepSeek Harness. They fix what the built-in write/edit cannot do: both drop a UTF-8 BOM, neither restores the file's own line-ending style (writing LF content turns a CRLF file into an LF file

Smooth think-row experience for the DSH Web UI: think rows expand as a capped 24-line preview that glides to the bottom while reasoning streams, collapse with a short height animation on settle, and the main conversation view follows with a reader-safe smooth chase (no snaps, no yanks).

Visual web settings panel for the official @tencent-connect/dsh-qqbot plugin: manage the QQ Bot AppID/AppSecret, c2c & group access modes/allowlists, cwd and requireMention directly in the DSH web settings page (reads/writes the qqbot profile's cordis.pat

Interactive terminal drawer plugin (dual-face): bottom drawer with real PTY terminals (xterm.js), multi-tab, Windows shell picker (PowerShell default / pwsh / CMD / Git Bash / WSL + custom), docked (occupies page height) or overlay mode, keep-alive sessio

DeepSeek Harness global account-balance card: live session/job status plus GLM / KIMI quota windows and OpenRouter / DeepSeek balances, pinned to the shell overlay bottom-right

A DSH (DeepSeek Harness) client plugin that adds a GitHub info sidebar to the chat window's right details column: the top pane lists repositories under a GitHub topic (e.g. dsh-plugin) sorted by stars, the bottom pane lists a repository's discussions with

Project-based learning coach: a subject-agnostic teaching engine plus swappable domain packs (Unity/C# included), shipped both as a DSH skill and as an installable bundle. The skill protocol enforces attempt-first teaching and graded hints; a zero-dependency validator rejects ability claims their evidence does not support and blocks stage acceptance while blockers are open.

Session-row unread mark for DeepSeek Harness: the session menu gains Mark unread and Unmark, pinning a red dot before the session title that survives reload and opening until cleared, both entries disabled while the built-in green finished-unopened dot is present.