309 results
Multi-session split view for the DeepSeek Harness web GUI: the top window shadows the root slot with a resizable split container; each pane is an iframe running a full DSH client pinned to its own session, with per-pane title bars, LRU hibernation and a dual-loopback origin pool.
AI response quality review for DeepSeek Harness: audits each finished assistant turn with an independent reviewer model and steers the agent to fix unreasonable output (up to 2 review rounds).
Fold each DSH Web turn's thinking, tool calls and context into compact expandable process boxes cut at every piece of model text, and reuse the shipped turn-process disclosure row as the toggle whenever it exists.
Codex-compatible desktop pet for the DeepSeek Harness web GUI: animated pets that follow the agent state
Hierarchical long-form writing for DeepSeek Harness — WriteHERE as an agent driver, not extra ReAct tools.
DSH Feishu self-built app integration: receives text messages over the official Feishu WebSocket long connection, routes them to a DSH agent session, streams safe assistant text deltas through a Feishu CardKit card, and falls back to ordinary text when card streaming is unavailable. Acknowledges with an OK reaction (text fallback). Standalone Cordis bundle — no dsh source changes.
DeepSeek Harness 纯插件：思考状态行文案轮换。把内置 UI 的 "Deep diving..." 扩展为 73 个 deep 系短语的英/中双语池（deep seeking / 深度求索中 / deep breaching / 跃出海面中 ...，含 Claude Code spinner 词表扩充），回合开场随机一条，回合内随新思考段/工具调用切换（最短间隔 3 秒），点击状态行可切换中英文，不改 DSH 源码。
Git-graph style conversation fork topology for DeepSeek Harness (dsh): see which session forked from which, and jump between branches.
Graph Monitor plugin for DeepSeek Harness: define and customize GRAPH workflows, then visualize each node live as it executes — Waku-agent style topology chart with animated node/edge status, clickable node details, and a desktop trajectory-like monitor view.
Trace DAG visualizer for the dsh web GUI: a conversation view tab that projects the official trajectory snapshot into a ReactFlow trace graph with dagre / d3-force layouts, hover highlighting, and a slide-out detail panel.
A collapsible in-conversation interactive terminal: each tab is a live host PTY (xterm.js over WebSocket) with per-project persistent quick commands
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.
A public agent skill for faithful integration of canvas, WebGL, shader, scroll-driven, pointer-reactive, and third-party animated components.
Codex-style turn folding: collapse each group of reasoning + tool-call nodes (between visible outputs) into a single disclosure unit
DeepSeek Harness plugin: use your own Claude and ChatGPT/Codex subscriptions as model providers, over each vendor OAuth flow
对话锚点面板：会话列左侧悬浮，列出已加载窗口内的用户消息锚点（时间 + 单行预览），点击瞬时定位到对应消息
DSH Web GUI prompt-based conversation minimap: a vertical navigation rail on the left of long conversations, each anchor = one user prompt; hover shows the prompt preview, click jumps to that message.
Remotion video creation and verified rendering plugin for DeepSeek Harness
DeepSeek Harness plugin: provider account balance inside each Models settings row, queried through a loopback-pinned RPC channel with the stored API key kept on the host
Weekly hot DSH plugins ranking panel: trending (7/30/90-day star-growth) and curated topic leaderboards, rendered as a self-healing sidebar entry below the New Session button in the dsh web GUI.
A floating right-side table of contents (TOC) for the DeepSeek Harness Web UI: one entry per user question, click to scroll to that message.
DSH plugin: turn an agent's execution trajectory into a readable post-mortem report.
浠诲姟瀹屾垚鎻愮ず闊?for the dsh web GUI: a ding-dong chime when the current session's agent turn completes, a floating volume control, and a Plugins-settings page (volume, mute, built-in sounds, custom-audio upload). Zero runtime dependencies 鈥?host half is plain Node, browser half is plain React.
DeepSeek Harness plugin: aligns markdown tables in assistant replies right after each turn (surface-replace, replay-safe) and adds a /clear-history command that empties the model-visible conversation while keeping the append-only log.