dsh-openrouter-free
OpenRouter 免费模型面板:自动拉取实时免费模型清单(综合能力 1-5★ 分级、最优优先排序),一键安装进 openrouter 路由并切换当前对话模型(全局默认 + 会话级双写,推理档自动选该模型支持的最高档),免手动配置。
168 results
OpenRouter 免费模型面板:自动拉取实时免费模型清单(综合能力 1-5★ 分级、最优优先排序),一键安装进 openrouter 路由并切换当前对话模型(全局默认 + 会话级双写,推理档自动选该模型支持的最高档),免手动配置。
DeepSeek Harness 项目组插件:在一个会话中跨多个项目文件夹工作——读写组内文件、运行命令、查看各项目 AGENTS.md;每个项目可带一句说明,AI 据此快速定位目录。项目组跟随工作区(每个工作区独立默认选择),组内文件路径默认允许读写。官方安装:dsh plugin --profile web add。
Skill bundles for DeepSeek Harness: a bundle box holds a root skill and sub-skills, loaded by metadata (loadSubskills) or by model decision from body text.
DSH 插件:给所有非官方(自定义)提供商的模型自动填充模型信息,包括:推理级别、最大上下文、输出上限与图片模态,数据来自 models.dev。
Text-to-image for DeepSeek Harness: a `draw_image` model tool, an input-bar 生图 button with a prompt popup (async generation, 4-grid results, download / keep / delete), an /imgdraw image route, and persisted history. Backends: DashScope wan2.7-image (free default) and SiliconFlow Qwen-Image.
DSH plugin: keyboard shortcuts to switch models and reasoning effort levels
DSH plugin: /init slash command that generates an AGENTS.md guide for the current project with a two-stage model call
Real-time repetition guard for DeepSeek Harness (DSH): stops model generation when the same string repeats >=10 times in the streamed output. 实时检测 DSH 大模型流式输出中的重复内容,同一字符串重复十次以上立即停止生成。
DeepSeek Harness plugin: matlab.run tool — run MATLAB code via matlab -batch and return output plus saved figures.
DSH 模型中心插件:免费模型目录 / 真免费实测 / 价格余额 / 一键切换 / 用量统计 — Model center plugin for DeepSeek Harness
DeepSeek Harness 插件:按工作阶段自动路由模型(对话/规划用 flash,实施用 pro)。
Call a new-api (one-api style) relay station's video model from the conversation, with @-referenced image/video materials plus a prompt.
Codex-style /reasoning command for DeepSeek Harness Web: select the reasoning effort of the current model from the slash menu
Explain failed DeepSeek Harness agent runs locally, then produce a redacted recovery plan. No model required.
Model-facing Everything search tool (es.exe) — blazing-fast file search on Windows via the Everything engine
DeepSeek Harness plugin: Grok Imagine image generation as a model tool (subscription)
Manual budget-targeted context compression for DeepSeek Harness: the conversation model picks ranges, a cheap flash-tier route writes the checkpoint summaries.
MCP 服务器管理器:在 DSH 设置页配置 MCP 服务器,宿主侧按配置热挂载/卸载 mcp-client 实例
DeepSeek Harness 峰谷定价自动模型路由插件:高峰时段自动使用 deepseek-v4-flash,空闲时段自动使用 deepseek-v4-pro;用户显式选择的模型始终优先。
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。
Read imported .txt novels in a draggable floating window while the model works.
DeepSeek Harness 本地模型插件:设置里独立的「本地模型」页,首条对话自动拉起 llama.cpp,空闲 5 分钟自动卸载释放资源。
DeepSeek Harness advisor plugin: pair a fast executor with a stronger reviewer model for plan / correction / stop guidance.
Show a hover hint with a model's full configuration (input types, context window, max tokens, protocol, base URL, credential env, …) over each model in the DeepSeek Harness web model picker, read from ~/.dsh/settings.yaml.