679 results
Graceful restart + client auto-reconnect + cross-restart goal continuation for DeepSeek Harness (dsh). After a plugin update dsh-phoenix restarts dsh at a safe idle boundary, keeps the browser page connected, and resumes a running goal so a task can keep evolving across restarts.
Native CloakBrowser tools for DeepSeek Harness with per-agent browser sessions and snapshot references.
DSH (DeepSeek Harness) 自动化小说写作发布流水线插件：项目管理 + Agent 预设 + 可视化工作台 + 多平台发布配置与数据闭环
DSH plugin: auto-fill metadata (context length, output cap, display name, input modalities) for custom-provider models from the Model Metadata Registry (models.dev).
DeepSeek Harness (DSH) plugin: mount the nuphus-mcp desktop automation MCP server as native tools (mcp__nuphus-mcp__*).
自主智能多模型协同调度系统 — 主动感知、自主决策、多模型并行、质量反思自愈、经验沉淀进化
为 DeepSeek Harness 极简模式增加自动上下文压缩、/compact、/context 和模型主动压缩，解决极简模式长任务无法持续工作的问题。
A DeepSeek Harness (dsh) bundle: when `dsh web` is ready, print the full GUI URL and open it in your default browser. Cross-platform, dependency-free, fail-safe.
Zero-dependency MCP client bridge for DeepSeek Harness: connects stdio/HTTP MCP servers and auto-registers their tools for the agent.
Agent negative-knowledge ledger for DeepSeek Harness: records failed paths with evidence hashes and retry conditions, auto-invalidates on evidence change.
VocoType voice input bridge for DSH Web: mic button + recording panel in the composer, auto-insert recognized text (dedupe, auto-launch/deploy, mtime-optimized polling)
Approval mode control for DeepSeek Harness: default approval (ask) or bypass approval (auto-approve every tool call), next to the permission selector. DSH 审批模式插件。
Task planning with experience muscle-memory for DeepSeek Harness: condition-reflex recall of past solutions + LLM-driven capability matching + auto-persisted lessons. Zero keys, zero hard-coded paths.
Skin switcher for DeepSeek Harness web UI: one-click theme switching with auto-discovery of community skins
DeepSeek Harness plugin: direct multimodal image transfer declarations + per-session image clearing, reasoning-effort auto-fill, and progressive Figma MCP bridging (design-to-code + AI-driven design).
Application-level Vision-Language-Model (VLM) analyzer for DeepSeek Harness: analyze_image tool with primary/backup OpenAI-compatible endpoints, automatic failover, and an auto-saving web settings page.
DSH client plugin: 检测回合被中断/出错/超长时, 自动发送「继续」重试, 不做模型/provider 切换。带设置卡片。
Version management for the dsh Web GUI settings panel: inspect the installed @deepseek-ai/dsh against every npm channel or version line, install or downgrade with one click, roll back instantly from local snapshots, automate the whole cycle with a policy engine (silent auto-update, execution windows, daily checks), and restart the host seamlessly.
Matter-aware legal workspace dashboard and document agent tools for DeepSeek Harness
Auto-healing, argument normalization, Code-Mode bridging and execution diagnostics for DeepSeek Harness
Accurate cache-hit rate, token usage, and cost estimates for the DeepSeek Harness Web UI: one-decimal hit rate, bucket breakdown, peak/off-peak pricing with auto price-switch, and a session usage panel.
Context compression tool (context_compact): the agent writes the replacement checkpoint itself and hands it to the host compaction engine, which skips the LLM summarizer call; automatic compaction stays on the official engine.
Self-evolving plugin for DeepSeek Harness: observes agent behavior, proposes improvements to its own skills/policies via LLM, validates them in a sandboxed trial agent, and applies versioned mutations with rollback.
Automatic Web image-to-text bridge plus vision and OCR tools for DeepSeek Harness