Lark/Feishu bot channel for DeepSeek Harness: each chat drives its own agent, and tool approvals, model questions, and plan reviews return as cards answered by a button or a reply. Switch workspace and model from the chat (`/cd`, `/model`, `/new`), and run several bots that keep separate sessions and can hand turns to each other in one group.

Auto-memory for DSH: three-layer memory (user / project notes / daily logs) with automatic injection, per-turn auto-consolidation, AI greetings, smart search, a calendar view and a settings page, plus inheritance of other AI tools' memories.

Plugin health checks: manifest protocol / patch format / build traps, zero-dependency and read-only.

Multi-provider wallet chip: official DeepSeek balance, per-session cost & tokens, third-party token totals, recharge shortcut, low-balance alerts.

Accessibility-first macOS computer use: fresh observations, stale-state rejection, scoped permissions, and safe input.

Sidebar usage panel that attributes tokens to the relay site that served each request, read from your existing provider config: today/month/all-time totals, per-site and per-model breakdowns, a year activity heatmap, and New API / Sub2API / DeepSeek balances.

Share your conversations with one click.

Automatically add emojis to AI replies.

Complete reverse-skill pack (85 SKILL.md) as a DeepSeek Harness Cordis plugin: reverse engineering, authorized pentesting and security-research skill router.

Zero-dependency toolkit: time / encoding / json / calculator / csv / regex / markdown / diff / stat / schema — ten deterministic tools in one install.

Mobile-adaptive layout for the DSH Web UI: the sidebar becomes a content-hugging overlay drawer, the conversation gets the full width, and the settings panel becomes a near-full-width sheet.

Delete DSH sessions from the web UI and desktop client: header danger button and session-row menu item with a risk-consent dialog; host endpoint and agent tool remove the session log, projection cache, and workspace accounting.

Side-panel arcade: 18 offline mini-games to play while the model thinks.

Automatic conversation distillation: background subagent reflection + skill create/update.

Auto-resumes interrupted DSH Web requests: sends a queued 「继续」 after network, timeout or host-crash failures, with error classification, adaptive backoff, templated continue text and browser notifications.

Bidirectional sticker reactions between user and agent.

A "focus chat" minimal view that shows only final outputs.

Model-driven context compression (Active Context Pruning) for DeepSeek Harness: the model decides when and what to compress.

Finds potential UX issues in your project: automatically reviews React/TypeScript code, pinpoints each problem, and gives concrete suggestions.

Structured memory engine for DeepSeek Harness. Offline semantic search, entity-attribute-timeline, autoDream self-consolidation, and human-editable Markdown storage.

Academic assistant plugin.

Desktop notification reminders.

Transparent rankings and recommendations for the DSH plugin ecosystem: daily auto-fetched topic data, an open scoring model, and rank/search/recommend tools with a settings-page leaderboard.

Connect IM bots to DeepSeek Harness by scanning QR codes (supports Feishu, Weixin, DingTalk, and more).