dsh-model-context-catalog
HOWILLMAKEIT
DeepSeek Harness 插件:一键匹配模型上下文窗口,展示容量来源,支持勾选批量配置、已有窗口管理和手动编辑。
GITHUB TOPIC
20个项目包含此标签
20 个项目
GitHub Topic 精确匹配
HOWILLMAKEIT
DeepSeek Harness 插件:一键匹配模型上下文窗口,展示容量来源,支持勾选批量配置、已有窗口管理和手动编辑。
PerryLink
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).
wall1234567
DSH 长期记忆插件:上下文超过阈值时把最早的一段对话归档到 memory/ 回忆文件夹,之后按关键词与重要度概率自动回忆。Host-only, zero-dependency memory engine for DeepSeek Harness.
HorusJiang
Jev judgment, not generation: prune long tool output, screen fetched pages for injected instructions, and gate completion claims inside DeepSeek Harness.
hoyyang
Context window auto-management for DeepSeek Harness: lossless zero-model rollover, budget reminders, notes.
yindf
Context folding for DeepSeek Harness (DSH): wrap work in named tasks, fold finished spans into short summaries, recall originals on demand.
helloxkk
Usage statistics for DeepSeek Harness (dsh) — lifetime token dashboard: 52-week activity heatmap (daily/weekly/cumulative), per-model trend + donut, streaks, plus a Codex-style /context lens
Toctsu
A biomimetic memory plugin for DeepSeek Harness. Folds context into token clues and reconstructs memories, enabling infinite conversations without overflow. (一个 DSH 的仿生记忆插件,将上下文折叠为 Token 线索并重建记忆,告别上下文溢出,给所有模型完整的一生。)
peach0x33a
DSH plugin: fill custom-provider model metadata from models.dev through an explicit, pre-declared mapping — no guessing, fail-closed. Includes a graphical settings page.
AiLi1337
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。
AllShadowAnan
User-set absolute context ceiling for DeepSeek Harness: auto-compacts a session once it reaches a configured token limit. External plugin with a dedicated Settings page.
catsenior507
Assembled context for DeepSeek Harness: a context tree over the session surface with per-node assemble modes (full / key / off), agent-authored presets, and a panel that decides what the model actually sees.
Dreverie
Cut the input-token cost of long DeepSeek Harness sessions: source-side tool-output compression on tools/post-execute plus per-agent tool-catalogue visibility, with a measurement script.
GuYou9799
Turn Sieve (回合筛) — DeepSeek Harness 插件:在对话里原位筛除低价值问答或单条消息,可随时撤销。Prune low-value parts of a DSH chat in place — whole turns, single messages or just your own prompt — and undo any time.
LuminariSoftwares
Too many MCP servers eating your context? tool-guardian sits in front of all of them and loads each tool’s schema only when needed. A 7-server setup went from 20,005 tokens to 1,084. Any MCP client.
Pasumao
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)
qiyuexue-xiyu
不告诉你花了多少钱,只告诉你每个工具往你的上下文里塞了多少东西。
xiamubumu
DSH 1.5 上下文治理:折叠工具结果、保持提示词缓存命中、接管宿主可写请求(不再需要 dsh-llm 文件补丁)。仅支持 DSH 1.5,后续会跟进更新。 / Context governance for DSH 1.5: folds tool results, keeps the prompt cache warm, takes over the writable-request path. DSH 1.5 only; newer releases will follow.
xlcg10086
Live context-compaction threshold control (20%-80%) for the DeepSeek Harness composer. | DSH ????????????????????
xunyyds
按模型自定义上下文窗口的 DSH 插件