dsh-lark-channel
Lark/Feishu IM bot channel for DeepSeek Harness: chats drive agents, replies and approvals return as messages and cards
21 results
Lark/Feishu IM bot channel for DeepSeek Harness: chats drive agents, replies and approvals return as messages and cards
The Feishu UI for DeepSeek Harness (dsh) — a dsh-native plugin: live streaming cards, in-card questions & approvals, one-QR setup.
Desktop notifications for DeepSeek Harness approvals, questions, and turn completion — so neither DSH nor you end up waiting while you browse another tab.
Secure mobile gateway for DeepSeek Harness with split realtime/control channels, editable queues, stop/resume, archive/rename sync, tasks, goals, commands, approvals, and file transfers
Codex conversation backend for DeepSeek Harness, powered by the Codex App Server with approvals and DSH tool support.
Bridge DeepSeek Harness (dsh) into Feishu / Lark with streaming cards, project workspaces, approvals and scheduling
Feishu/Lark bot bridge for DeepSeek Harness with approvals, progress updates, context, and file transfer.
Claude Code integration plugin for DeepSeek Harness, providing native Claude conversations powered by the Claude Agent SDK, with model selection, approvals, questions, tools, and session continuation.
Neovim-style TUI for DeepSeek Harness (dsh): nvim renders the terminal, a Node runner bridges DSH agent events over msgpack-RPC — sessions, tool cards, reasoning panel, approvals, markdown tables
DSH WebUI capability controls for skills, MCP servers, tools, prompt injections, approvals, and safety guards at session, project, and global levels.
Agent-decided approvals for DeepSeek Harness: a workspace-write base permission mode where an independent approval subagent judges every sandbox escalation (risky operations are rejected), with a configurable approval model and a per-session audit trail in the conversation window's 审批 tab.
DeepSeek Harness health and safety diagnostics for effective tool surfaces, approvals, and AgentFuse composition
LLM pre-review for sandbox-escalation approvals: an independent-context LLM gate answers sandbox escalation requests before they reach the user, falling back to the user on any failure.
Governed platform access for DeepSeek Harness — no credential on the machine
Approval attention plugin for the DSH Web GUI — audible + visual alerts (chime, tab badge, OS notification, dock) for pending approvals, session completions, job failures, and connection loss.
System notifications for the DeepSeek Harness web GUI — OS-level popups for finished turns and pending interactions (approvals, questions, plan reviews). · DSH Web 界面系统通知:回合结束、待处理授权/提问/计划审核时弹出系统级提醒。
A Claude Code-style coding agent for the terminal, composed on the DeepSeek Harness (dsh): interactive TTY surface, plan mode, approvals, custom commands, and session management over the dsh plugin runtime
Browser notifications for every DSH event that needs attention: completions, approvals, questions, plan reviews, and background jobs.
Desktop notifications for DeepSeek Harness approvals, questions, and turn completion — so neither DSH nor you end up waiting while you browse another tab.
Bridges vendor agent SDKs into DeepSeek Harness as selectable LLM providers. Works in any DSH mode; DSH keeps its own prompt, tools, sandbox and approvals.
Windows always-on-top task progress overlay for DeepSeek Harness (DSH): live phase, tool or command, real todo step progress, multi-task list, and approvals answered from the overlay.