Plugins

Auto mode for DeepSeek Harness (dsh): an Auto entry in the Permissions selector whose approval prompts are answered by OpenGuardrails policy instead of a human — plus the full OGR guard engine underneath. No core changes.

IM webhook and local notifications on turn completion, errors, or approval (Feishu/WeCom/DingTalk/Slack/Discord/custom).

Lark/Feishu IM bot channel for DeepSeek Harness: chats drive agents, replies and approvals return as messages and cards

Bridge DeepSeek Harness (dsh) into Feishu / Lark with streaming cards, project workspaces, approvals and scheduling

Bidirectional Lark/Feishu controller for DeepSeek Harness with project and session routing, interactive cards, approvals, attachments, and task controls.

Android GUI Agent with ADB screenshots, compact UI hierarchy grounding, verified iterative actions, approvals, and a Mobile Web view.

Conservative auto-approval preset for DeepSeek Harness sandbox escalations

Rings your phone over CallKit: `call_me` and `text_me` tools, plus optional turn-end and approval calls whose spoken answer is transcribed back into the session.

Adds an Auto Approve permission preset to the Web UI, using a fresh restricted Reviewer Agent to allow or deny each approval request.

Bounded, layered, approval-gated, auditable cross-session memory: a typed `ctx.memory` seam with a zero-dependency SQLite provider, a `memory` tool, and frozen snapshot injection; every write passes the approval gate and stays reconstructable from the session log.

GitHub integration for DeepSeek Harness: create pull requests, review PRs with background jobs, and read issues — every write gated by human approval

Declarative Claude Code-style permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, full session-log audit, and HMR rule reload.

Adds approval-gated Git status, diff, log, commit, branch, and optional checkpoint tools.

Turn-scoped “Allow for this task” approvals: automatically allow matching `danger-full-access` escalations only for the current task, then expire.

Two-way WeChat (iLink) bridge: turn-end and approval-request push, in-chat approve/reject and message injection, persistent dedup and convergent long-reply chunking; channel layer extensible to other IMs.

Model-based permission approval: an approval-request answerer backed by a separate reviewer model.

Pi TUI (differential-rendering terminal framework) front end: streaming markdown, thinking collapse, tool cards, slash commands, approval/question overlays, shared dsh session store.

DSHWeb 审批增强插件：无感替代内置审批窗口，支持「拒绝并附言」，并在拒绝后终止当前回合、让模型重新结合附言思考

A middle permission tier for DeepSeek Harness between workspace-write and danger-full-access: auto-approves harmless commands and operations targeting configured trusted areas, beyond the current workspace.

Manual approval mode ("Manual Mode" / "Ask Mode").

Native OS notifications for approval and question/plan prompts: the toast names the workspace, click jumps to it, bilingual (zh-CN/zh-TW/en), with chime.

Per-workspace completion ringtones plus attention sounds for approval, question, plan-review, goal-blocked, and task-failure events, with built-in synth, voice (TTS), and custom audio.

Bark push notifications to iPhone: turn completion, waiting-for-input, and approval events sent from the DSH Host.

Chat with, monitor, and approve your DSH agents from WeChat via the iLink gateway: text both ways, session targeting, digest heartbeats, and numbered approval prompts.