插件

A DeepSeek Harness plugin: model-facing reload_plugin tool that restarts one Cordis Loader entry (by entry id, module name, or MCP serverName) without touching sibling entries — respawns mcp-client server processes

DeepSeek Harness plugin bundle: qwen_vision (Qwen-VL image understanding) and qwen_generate (Qwen-Image text-to-image) tools for text-only models

检查并管理当前 dsh 会话生效的指令链与项目技能，支持就地创建与编辑——所见即模型所得。

Request Context Profiler for DeepSeek Harness — see what changed between model requests, and how cache reuse changed with it.

DeepSee: DeepSeek Harness vision, multi-model routing, and Gemini visual self-checks before delivery

为纯文本 DeepSeek Harness 模型补上视觉：vision 工具内置免费 VLM 预设，支持多图批量分析、粘贴图片与热重载设置页。

浏览器 Web Speech API 语音输入：零服务端、零密钥、零模型下载（Edge=Azure 语音、Chrome=Google 语音）。

可自修改的 DeepSeek Harness 桌面工作台：完整 dsh web 副本 + 编辑模式，agent 在对话中实时修改工作台（补丁层、插件、UI）并热更新生效。

DeepSeek Harness 可复用 Markdown Prompt Profile，支持单轮模型选择、参数替换和状态恢复。

遥测后端：把 turns、model steps、tool calls 导出到 yiTrace。

跨会话记忆：全文检索所有历史会话（复用 ctx.sessionQuery 的 SQLite FTS5 索引），把最强匹配片段带回当前上下文。

Model-facing library_search tool: free cross-ecosystem (npm/crates.io/Maven/Go/PyPI/RubyGems + GitHub) 'has this already been built?' search — exact-name ranked, stars/downloads as fitness signals, no API key required

Model-facing codebase-memory CLI tools (codebase_list_projects/index_repository/index_status/search_graph/query_graph/trace_path/get_code_snippet/get_graph_schema/get_architecture/search_code/detect_changes/manage_adr/ingest_traces/delete_project) that ru

A session recap plugin for DeepSeek Harness with /recap, automatic idle summaries, and configurable models.

Infix rerun for DeepSeek Harness: re-run any earlier turn in place - the reply is regenerated from the same prompt while every later turn survives, so subsequent model calls read A B C1 D E F G. Implemented with the official surface-replace contract plus

Per-session LLM cost meter for the DeepSeek Harness Web UI: folds provider usage into uncached input / cache read / cache write / output per model and prices it against DeepSeek and Xiaomi MiMo pay-as-you-go rates (DeepSeek peak-idle tiering included).

OpenCode Go model provider and settings UI for DeepSeek Harness

Lets the model trigger compaction itself at a safe point via a compact_now tool (works mid-turn), plus a context_status tool reporting real token usage against the session's actual context window.

fal.ai native image generation for DSH: a FAL_KEY settings card that follows DSH's language (zh/en, English default) plus Agent tools (fal_generate_image async / fal_edit_image / fal_get_image_task / fal_list_image_models) that call queue.fal.run directly

SenseNova connect family bundle for the Harness Web UI: Token Plan credit panel (per-pool quota windows, per-model consumption, self-renewing console token) plus optional provider registration that brings SenseNova models into DSH conversation, with host-

Codex-aligned Auto-review and Approve for me mode for DeepSeek Harness

LMM browser OAuth and account-scoped model provider for DeepSeek Harness

编程学习悬浮面板：编辑并运行 Python/JavaScript/TypeScript/PowerShell（含退出码与耗时），JSON 课程包关卡自动评判并可导出进度，提供 Markdown 笔记与代码片段库；代码分析以用户消息直投当前对话，由对话主模型直接输出。

A grouped, searchable replacement for the DSH composer model selector.