dsh-plugin-question-navigator
Navigate to the latest and previous user questions in long DeepSeek Harness conversations.
304 results
Navigate to the latest and previous user questions in long DeepSeek Harness conversations.
DSH web plugin: play a notification chime when the agent asks the user a question (ask_user_question / plan review) or requests approval (sandbox escalation, tool approval).
Trigger only when the user explicitly invokes $dsh-deliver or clearly asks to hand implementation to DSH. Do not trigger for ordinary implementation, read-only review, commit/push/MR/deploy, or image-only tasks.
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.
dsh web client plugin: a floating right-side navigator that jumps to prior user inputs in the conversation
Notify me when DSH needs me: desktop notification (with tab-title fallback) when an approval prompt or an ask-user-question card appears while the page is in the background.
Configurable user-confirmed lessons that help DeepSeek Harness avoid repeating mistakes.
DeepSeek Harness plugin: widens the conversation column, sets the user-bubble width and composer max height, and right-aligns the session stats strip, with a settings-row UI to tune all four. Built for the DSH client plugin slot `settings.general.item`.
A native DSH Bundle that installs a user-owned, plain-language pure PTC preset for GPT-5.6 Sol, Terra, and Luna.
DSH web plugin: a floating bubble at the top of the conversation showing the last user instruction that scrolled out of view.
DSH plugin: scheduled sending (⏰ composer button, dock list of pending tasks, sidebar 定时任务 panel with cross-session cancel, due-time delivery as a normal user bubble)
DSH-native multi-AI group chat: the host (user) runs a chatroom of configurable AI agents with per-agent models, role cards, mute controls, and passive/active speaking modes — pure Node.js/Cordis, no Tauri/Rust
Codex-style per-session memory draft for DeepSeek Harness: one session one draft (rollout_summaries), restrained & passive (write only on explicit user request), layered disclosure (summary + registry), idempotent integration watermark. / 一会话一草稿记忆插件。
DSH 插件:GitHub MCP 示例提示面板(设置→插件,随机 4/30 条可复制 + 公开仓库星/fork 可视化)+ gh_repo_stats / gh_current_user 模型工具(星数/近14天克隆量/当前账号)。前端直连公开 API 但带本地缓存降频与容错,避免触发 403。
Detect Claude Code and Codex CLI updates, prompt the user, and run the right channel-specific upgrade
Codex-style user-message navigation sidebar for DeepSeek Harness Web
Hybrid memory plugin for DeepSeek Harness: L1 frozen-snapshot memory (MEMORY.md/USER.md, prefix-cache friendly) + L2 searchable knowledge base (one-fact-per-file, FTS5) + L3 multi-tool import. Data lives on D drive, never C.
DSH web plugin: a per-session question index on the right edge. Lists every user question (with time) of the main session and its branch/subagent sessions, click to jump & highlight; a thin rail with scrubber expands into a chain (tree) view.
DSH plugin: Feishu (飞书) custom-bot notifications when an agent session settles (idle) or asks for input (ask_user_question). Adapted for DSH 0.1.0-rc.7 (@deepseek-ai/cordis line).
My Habits for DeepSeek Harness: edit the user-global AGENTS.md from the Web settings — injected into every session by the built-in agent-instructions loader.
Publish a validated DSH plugin package (`@deepseek-ai/dsh-*` or `@lovstudio/dsh-*`) to npm, git, or tarball channels and verify it loads in the DeepSeek Harness. Use when the user asks to publish, release, or ship a plugin. 触发:发布插件 / 上架插件 / release dsh 插件。
In-GUI skill manager for the dsh web GUI: a top-level Skills entry in Settings (movable into the Plugins section) that lists every installed skill (name, description, model/user invocation type, source root), with search. Read-only browser of the local skill catalog (user roots: $DSH_HOME/skills, ~/.agents/skills).
Manage user-installed DeepSeek Harness plugins from the DSH Web settings page
Long-term memory for DeepSeek Harness agents: user preferences, project facts, session summaries, and knowledge entries, with auto-injection at session start.