插件

Official OpenAI account model connector for DeepSeek Harness

Make the model believe it is inside the Z.ai Code (Zhipu ZCode) agent environment: replaces the harness identity opener and injects a ZCode rules skeleton with a dynamic project section. 让模型认为自己处于智谱 ZCode Agent 环境。

Codex-style /reasoning command for DeepSeek Harness Web: select the reasoning effort of the current model from the slash menu

Composer polish: the model-select button shows a per-provider brand icon and collapses to icon-only under a narrow composer row (same mechanism as the built-in access-mode button), with a generic fallback icon for unrecognized/new providers.

ESLint Security SAST bundle and model-facing scan tool for DeepSeek Harness.

DSH plugin: inject per-model sampling parameters (top_p, top_k, min_p, repeat_penalty, presence_penalty, frequency_penalty) into every chat-completions request sent to a local llama.cpp / llama-server gateway.

智能体选择器：像模型选择器一样在输入框旁勾选委派目标+具体模型，把对话任务派给外部智能体（Codex CLI / WorkBuddy 内置模型活动价 automation 桥 / WorkBuddy 自定义模型直连 / Claude Code）执行，结果流回 DSH 对话。含 agent_dispatch 工具 + composer 两步下拉 + 设置面板 + 桥健康探活 + 反冒充出处凭证。

DSH session-log repair plugin: scan every stored session, detect a seq collision in the committed region or a torn trailing record, and repair it from a one-click Web UI, model tools, or the /dsh-session-log-repair command. Installing it also registers it

Unified management and invocation of external Agent CLIs in DSH, fully isolated from the user's native installs; preset Provider, model, reasoning effort, and permissions per CLI, callable directly or like native subagents.

OpenRouter free-models browser plugin (dual-face): fetch OpenRouter models, filter the free ones (price 0 or :free), list them newest-first in a Settings tab with local search and full model info, and create a ready-to-use DSH model config (settings.yaml

A minimal reasoning-effort ruler for the DSH composer: one hairline, a sliding marker, per-model memory, optimistic switching — and a streamlined model picker.

Persistent, searchable, per-project memory for the DeepSeek Harness: decisions, rules, and sprint context in a queryable DuckDB file, rules enforced on every model request, with a full management UI in the Web Client

Intelligent sub-agent orchestration for DeepSeek Harness, with model discovery, routing, planning, and parallel delegation.

Native desktop notifications for DeepSeek Harness (dsh): run completion, model questions, and approval requests on macOS, Linux, and Windows. Includes a web settings card consistent with the dsh web UI.

让没做完的任务清单跨回合保留。DSH 在每个回合开始时清空 todos 投影，指望模型重写整份清单，于是回合一旦被中断，计划虽然durable 地留在会话日志里，界面上却永久消失——而 todo_write 只写不读，用户和模型都拿不回来。本插件只注册一个普通的 session/event 监听器，按会话记住最后一份清单；当 turn/start 到来而那份清单仍有未完成项时，把它补折回去，投影就不再显示空计划。不 fork tool-todo、不注册任何 waterfall：插件换不掉投影（注册表对 stateVersion 不一致直接抛错），追加折叠所反应的那条事件才是够得着的缝。刻意收得很窄——只管未完成的清单、每次回合开始最多补一条、失败即放行。已用真实会话上的受控 A/B 验证：两次运行内容相同，唯一差别是插件装没装，都用真实的投影定义折叠。零依赖。

Enforces your comment policy at write time, inside DeepSeek Harness. Reads the policy from your AGENTS.md or CLAUDE.md, blocks violating writes, and re-injects the policy verbatim so the model stops drifting from it.

在准入前把提示词里的图片换成视觉模型的文字分析，因此任何模型（包括纯文本模型）都能读图且会话不切换模型；另提供 describe_image 工具处理图片路径。

通过同源反向代理把外部 AI 对话站点嵌进 DSH 右侧面板（DOM 适配器写在配置里，站点改版无需改代码），并在输入框旁加一个按钮：要么用宿主模型改写草稿，要么跑一轮闭环——压缩对话、优化、发送到嵌入站点、捕获回复、整理成终稿写回输入框。

把你自己的 chat.deepseek.com 账号当作第二个模型接入 DSH：提问、按文件行区间分析、查看登录状态，附带运行时技能与设置页登录面板。

把模型选择菜单按来源（provider）分组：菜单先列出来源，点来源从右侧滑出子面板列出该来源的全部模型（默认），双击来源标题可切换为在列表内就地展开。

在 DeepSeek Harness WebUI 中通过原生设置卡搜索和选择模型。

模型渠道管理：多个供应商/模型候选共享一条虚拟路由（roundrobin/组），带失败转移、重试、超时与冷却；设置页签可编辑供应商与轮询组、跑测速与单模型真实请求测试，健康面板聚合七天延迟、失败与上游 token 用量（输入、输出、缓存、推理）。

在 llm-pi-ai 设置节为第三方模型提供商补齐推理档位（reasoning effort）声明，让 DSH 自带的思考强度选择器对 pi-ai 目录之外的模型真正可用。

为 DSH Web UI 的每个对话实时计算 token 费用：本对话、其子代理与整棵会话树，价格来自内置的 models.dev 快照：七家供应商、139 个有价模型，缓存读写费率按供应商实际公布的取值，DeepSeek 则使用其官方峰谷价格表。每个完成的回答都会在对话中显示自身费用，未打开的对话则按日志计价而不是整行消失。费用按区间计价，依据写入项目目录的只追加 JSONL 账本，因此已记录的工作保留当时的费率。此外还提供：按金额预算排布的工作计划、展示值得接入哪些模型的路由方案比较、以英语/中文/俄语生成的计划文档，以及当费用未归入任何计划单元时的提醒。