@dsh-external/dsh-thinking-counter
DSH「蓝色大肥鱼·智商鉴定中心」:从放鱼时刻起对全部运行中会话的 thinking(reasoning)内容做短语检测统计,含思考块数、思考字符数、偷吃/头脑大开词/吃瓜词命中与梁圣/梁子判定;侧边栏按钮 + 可拖拽悬浮窗,检测词可自由增删
201 results
DSH「蓝色大肥鱼·智商鉴定中心」:从放鱼时刻起对全部运行中会话的 thinking(reasoning)内容做短语检测统计,含思考块数、思考字符数、偷吃/头脑大开词/吃瓜词命中与梁圣/梁子判定;侧边栏按钮 + 可拖拽悬浮窗,检测词可自由增删
DeepSeek Harness 统一推理等级插件:一个 llm-reasoning 设置项动态配置 DSH 所有模型的默认推理等级(思考等级)——自动为手写声明的模型补齐推理能力、按路由设置默认等级(仅当全部模型支持)、同步 DeepSeek 官方路由,改设置即生效。
DeepSeek Harness plugin: a General-settings selector that chooses which language the model reasons in, via a system-prompt section.
DeepSeek Harness 插件:一键配置任意 OpenAI 兼容 API 并自动带思考模式,同时规避 developer 角色被第三方端点拒绝(content_filter)的问题。
DSH web plugin: 为自定义模型(OpenAI-compatible pi-ai provider)增加思考强度(reasoning effort)配置 —— 设置页新增「思考强度」分区,按模型配置思考级别与线格式、按 provider 配置默认思考强度,直接写入 llm-pi-ai 设置,composer 模型选择器随即生效。
Native interactive visual-reasoning plugin for DeepSeek Harness: precise pixel grounding (SOM grid, zoom, annotate, measure, diff, color, OCR) + MiMo V2.5 multimodal backend, with zero external MCP servers.
Windows Git Bash fix for DeepSeek Harness (dsh): MSYS sandbox conflict + terminal inspector, plus the minimal-win collective-thinking preset (we/let's reasoning chain).
Unified ModelID routing for DeepSeek Harness: one logical model id over multiple providers, first-token failover with cooldown, health-aware ranking, fallback reasoning efforts, purpose-based simple/complex task split, per-tier reasoning effort, and a settings-page management panel.
DeepSeek Harness plugin with two default model-and-reasoning shortcuts above the composer and optional Settings customization.
DSH plugin (NInfer engine only): fixes compaction failure on local qwen3.8-27b gateways served by NInfer — xhigh thinking burns the entire output token budget, so thinking is off for compaction-only, with the model's non-thinking sampling parameters; the same idea applies to other launch methods
Declare per-model reasoning efforts, image input, and openai-completions dialect on hand-declared llm-pi-ai routes. Writes the official namespace; does not intercept llm/stream or replace the Models page.
Keep Think reasoning rows visible and auto-expanded, and always force Chinese thinking and replies. 保持 Think 思考行可见并自动展开,并始终强制中文思考与回复。
使用仓库内新版 mcp-bridge.js 连接已有的本地 Chrome MCP 服务;默认对接 /mcp-new 无会话 Streamable HTTP,也兼容旧 /mcp Session 端点
Vision-augmented DeepSeek adapter plugin for DeepSeek Harness: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description
Reasonix-style cache-aware compaction backend for DeepSeek Harness (DSH). Replaces/enhances compaction-basic with compact_ratio, one structured summary checkpoint, and a stable recent tail.
DevTools for DeepSeek Harness web: read-only Agent Runtime Trace — turn/step execution timeline, model latency (TTFT/decode), tool-call durations, retries, hook and turn end reasons. Metadata-first, durable events only, zero behavior modification.
项目文档体系初始化 skill(DeepSeek Harness 插件包 / Reasonix 技能):提问驱动落实文档规范 + 固化 AI 协作工作流,以「存量完善」为核心场景,跨平台可用(DSH / Reasonix / Claude Code / Codex)。
DeepSeek Harness 实用工具箱:便签、API 余额与费用、推理等级、删除会话、对话节点导航条、轻拟物皮肤(monorepo,可一键安装全家桶)
Message edit / regenerate for DSH Web: inline edit of assistant replies (text + reasoning), regenerate replies, and user-message edit — a Cordis host plugin serving /api/msg-edit/* plus a dsh.client UI plugin contributing to the assistant action strip.
Shows the selected model provider's account balance next to the composer model seat once a model and reasoning effort are selected.
A calmer reading view for DeepSeek Harness: native process details, live reasoning, and clean final answers.
DeepSeek Harness 插件:让模型的思考(reasoning)与最终回答默认使用简体中文。A Chinese-first plugin that makes DeepSeek Harness reason and answer in Simplified Chinese by default.
Limit the expanded thinking block to a bounded scroll window in the DSH web conversation.
在 Settings 面板中为自定义 pi-ai 模型编辑推理等级(reasoningEfforts),支持多选、拖拽、复制粘贴,自动保存。