dsh-thinking-effort
多功能 DSH 插件:① 为 OpenAI 兼容第三方模型声明 Codex 风格推理档位并钉住默认档位;② 引用目录(附加文件夹)——为会话添加可读写的白名单文件夹,注册 refdir_list/read/write/edit/grep 工具。安装一次,按模块持续扩展。
116 results
多功能 DSH 插件:① 为 OpenAI 兼容第三方模型声明 Codex 风格推理档位并钉住默认档位;② 引用目录(附加文件夹)——为会话添加可读写的白名单文件夹,注册 refdir_list/read/write/edit/grep 工具。安装一次,按模块持续扩展。
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。
LLM 自动重试设置卡片:在 设置 → General 里修改重试次数(maxRetries)与退避时间(initialDelayMs/maxDelayMs/jitterRatio),并可勾选额外可重试错误码 retryableCodes(默认补入 INVALID_REQUEST,OpenAI thinking 模式 HTTP 400 报错自动重试),宿主 dsh-llm-retry 实时生效
DSH 中转站模型思考强度配置与自动识别插件
A local-only Texas Hold'em table for DeepSeek Harness — play while your agent thinks.
Fold mis-rendered thinking content into collapsible blocks, render mermaid inline, show file-edit diff counts, rewrite composer drafts with the current model, and resume interrupted turns from the send button.
DSH Web client plugin: collapse every expanded collapsible section in the conversation (Think / tool cards / command cards...) in one click, with a customizable hotkey.
过程精简:把 DSH Web GUI 里的 Think / 工具调用等技术过程行折叠成友好摘要,面向文字工作者的非技术呈现。Collapses technical process rows in the DeepSeek Harness Web GUI into a friendly summary pill.
Display-layer translation for the DSH web app: thinking chain, task cards, and optional answer text, in 8 target languages (local Ollama / Google / Bing, fail-open)
Reasoning-wait thinking indicator for the DeepSeek Harness web composer
DSH plugin: switch the language of the agent's thinking/reasoning process (简体中文, English, Русский, Français, Deutsch, Español, 日本語, 한국어 and more)
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 plugin: a General-settings selector that chooses which language the model reasons in, via a system-prompt section.
Water ball pet plugin for the dsh web GUI: a floating sky-blue water ball with white eyes that reacts to agent activity (idle / thinking / tool) and ships an enable toggle plus size in the settings plugin section. Adapted to dsh 0.1.2-alpha.1 (dissolved dsh-client-runtime).
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。
Chinese-thinking system-prompt section for DeepSeek Harness: make your dsh agent think and answer in simplified Chinese (code/commands stay verbatim).
DSH plugin: start/stop a local llama.cpp llama-server from the settings → plugins page — two model slots (A/B) with per-slot model-file selection, eight editable launch-parameter groups (text/vision × fast/long × 2 slots), and one shared DSH provider carrying both slots' models with four thinking-effort levels.
DeepSeek Harness plugin that enhances custom provider setup by auto-discovering models and auto-populating contextWindow, maxTokens, vision, and reasoning capabilities from models.dev
DeepSeek Harness plugin that autonomously overrides and adjusts third-party model thinking levels, fixing missing or mismatched built-in presets
Volcengine Ark Agent Plan & Coding Plan providers for DeepSeek Harness (DSH), with verified thinking-effort compatibility
Read another session's content (messages, tool calls/results, thinking) from within a DSH session
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).
Codex-inspired planning, evidence, goal, and anti-loop policy plugin for DeepSeek Harness.
A swimming, spouting whale progress indicator for the DeepSeek Harness Web UI while the agent is thinking or running tools.