context-window

Terminal-style input history for the DeepSeek Harness web composer: edge-first arrows with exact draft/caret restore, browser-local persisted history, Ctrl+R reverse search, workspace recall - and sliding-context awareness (compaction summaries in recall/search, compaction notice with one-click /compact fill).

DeepSeek Harness 插件：维护 llm-pi-ai 模型的准确上下文窗口，避免长会话被误判为上下文溢出。

DeepSeek Harness MCP tool search for large catalogs: 1,000 MCP tools behind 2 MCP-facing schemas, exact-schema calls, allow/deny controls, and a local calculator.

Context visibility + GitHub-style usage heatmap for DeepSeek Harness (dsh) — Codex-style /context lens + 53-week contribution graph

dsh-context-length 是一个 DSH（DeepSeek Harness）设置页插件。它会在设置面板「模型」的正下方新增一个「上下文长度」页面：从已配置的渠道（提供方）中选一个，再选该渠道下的某个模型，填一个上下文窗口数值（支持 131072、256K、1M 等写法），点击「保存」后才会写入 settings.yaml 并立即生效。未配置的内置渠道不会出现在列表里；已自定义的模型会集中展示在页面底部，并支持一键「恢复默认」。整个页面完全走官方设置接口，宿主端始终是唯一事实源，安全且无副作用。

Model-driven context-window rollover bundle for the DeepSeek Harness: fresh working context, durable notes, verbatim recent tail, no summarization

会话注入门控：按会话裁剪注入模型的 skill / tool / 提示词段落 · Per-session injection gate for DeepSeek Harness (dsh)

该仓库暂未提供项目说明。

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。

DeepSeek Harness settings page: cap every configured model to a working context window, clamped to what it can actually hold.

Context occupancy and account balance for the DeepSeek Harness Web Client — a session-header readout with a swappable balance provider.