@zoria-lind/dsh-behavior-enhancer
行为管理插件:系统提示词行为约束 / 失败收敛并行度 / 连续失败用户介入 / 写后检查与 .bak 回滚,基于 DSH 真实插件 API
624 results
行为管理插件:系统提示词行为约束 / 失败收敛并行度 / 连续失败用户介入 / 写后检查与 .bak 回滚,基于 DSH 真实插件 API
Privacy-minimal heuristic per-turn execution summaries for DeepSeek Harness
Hook DeepSeek Harness into your Hermes pipeline: dispatch-spec template, model-tier routing, quality gates, git single-writer rule — as an installable skill pack.
DSH plugin: auto-fill metadata (context length, output cap, display name, input modalities) for custom-provider models from the Model Metadata Registry (models.dev).
Skin manager for the DeepSeek Harness (DSH) web GUI: a floating 🐋 button — left-click restores the default look, right-click lists every installed skin and switches between them (mutually exclusive). Pure client-side presentation utility.
能力库 (Capability) — one-stop visual management of DSH Skills & MCP: on-demand MCP loading, in-session hot reload, and SKILL/MCP descriptions viewable in the plugin.
Page capability kit for DeepSeek Harness (dsh): composer-docked file tree / source control / terminal panels for the current session workspace, plus free multi-source web search (merged from dsh-free-search)
Task-aware native capability manager for DeepSeek Harness — use, prepare, and verify built-in DSH tools before adding another plugin.
DeepSeek Harness bundle for the Academic Research Graph Skill
Durable dependency-graph task factory for DeepSeek Harness
Global model request headers plus image input, reasoning, and DeepSeek system-role compatibility for custom providers
Desktop computer use for DeepSeek Harness (DSH): macOS app listing, accessibility-tree window capture, screenshots, and synthesized input — the seam, the local Swift-daemon provider, the computer_use_* tools, the approval policy, and a standalone MCP server in one installable plugin package
Wang Hong-inspired Notability academic handwritten PPT skill for DeepSeek Harness
A DeepSeek Harness research workspace with archived PDF reading, optional OCR, human review, cited reports, and recoverable research tasks.
行为管理插件:系统提示词行为约束 / 失败收敛并行度 / 连续失败用户介入 / 写后检查与 .bak 回滚,基于 DSH 真实插件 API
Generic LLM gateway model provider plugin for DeepSeek Harness: mounts newapi / LiteLLM / Higress / any OpenAI-compatible gateway as provider routes, auto-discovers the model list, enriches every model with models.dev parameters, and dispatches each model over its native wire protocol (OpenAI / Anthropic / Gemini) via the pi-ai SDK
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.
Agent trajectory governance & anomaly diagnosis for DeepSeek Harness: rebuild structured multi-branch trajectory trees from the session/event feed, keep observation-layer snapshots, and run three temporal anomaly strategies (loop deadlock / invalid retry / goal drift).
DSH 测试沙盒插件:把开发/测试任务路由到进程级隔离的沙盒实例(独立进程 + 独立 DSH_HOME + 独立端口),提供创建/注入/运行/健康检查/停止/销毁/清理与门禁式合回等原生工具,全程零影响本体(3080)。
Security review gate for DeepSeek Harness (dsh) plugins: static pre-install vetting of malicious code, vulnerabilities and supply-chain risks (with deobfuscation decoding), runtime audit, optional tool-call guard, and a one-click web review/install/uninstall panel.
Runtime compatibility shim for dsh (DeepSeek Harness) cordis bundle plugins: decouples third-party plugins from real dsh internal service names, module paths, and RPC details via a version-aware adapter registry.
Route-aware Codex environment simulation for DeepSeek Harness, improving tool-call reliability for GPT and other Codex-adapted models
Playwright/CDP web-fetch provider for DeepSeek Harness: renders pages in a real browser, denoises them (Readability + DOMPurify), and returns markdown.
Codex-style context visibility for DeepSeek Harness: live context-window occupancy, composition breakdown, KV-cache hit rate, and a GitHub-style 53-week usage heatmap