From 717549bc852cc921926993fc58f3fd35be691194 Mon Sep 17 00:00:00 2001 From: ekko Date: Sun, 19 Apr 2026 23:36:28 +0800 Subject: [PATCH] docs: update README with multi-profile, gateway, provider management and star history - Add active session indicator and latest-message sorting to AI Chat - Expand Model Management with provider CRUD and Codex OAuth - Add Multi-Profile & Gateway section - Add Model Settings to Settings section - Add Star History chart to both EN and ZH READMEs Co-Authored-By: Claude Opus 4.6 --- README.md | 21 +++++++++++++++++++-- README_zh.md | 21 +++++++++++++++++++-- 2 files changed, 38 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 70fd03b..3347e71 100644 --- a/README.md +++ b/README.md @@ -39,6 +39,8 @@ - Real-time streaming via SSE with async run support - Multi-session management — create, rename, delete, switch between sessions - Session grouping by source (Telegram, Discord, Slack, etc.) with collapsible accordion +- Active session indicator — live sessions pin to top with spinner icon +- Sessions sorted by latest message time - Markdown rendering with syntax highlighting and code copy - Tool call detail expansion (arguments / result) - File upload support @@ -83,8 +85,18 @@ Unified configuration for **8 platforms** in one page: - Auto-discover models from credential pool (`~/.hermes/auth.json`) - Fetch available models from each provider endpoint (`/v1/models`) -- Add custom OpenAI-compatible providers -- Provider-level model grouping +- Add, update, and delete providers (preset & custom OpenAI-compatible) +- OpenAI Codex OAuth login for Codex models +- Provider-level model grouping with default model switching + +### Multi-Profile & Gateway + +- Create, rename, delete, and switch between Hermes profiles +- Clone existing profile or import from archive (`.tar.gz`) +- Export profile for backup or sharing +- Multi-gateway management — start, stop, and monitor gateway per profile +- Auto port conflict resolution +- Profile-scoped configuration and cache isolation ### Skills & Memory @@ -105,6 +117,7 @@ Unified configuration for **8 platforms** in one page: - Memory (enable/disable, char limits) - Session reset (idle timeout, scheduled reset) - Privacy (PII redaction) +- Model settings (default model & provider) - API server configuration ### Web Terminal @@ -233,6 +246,10 @@ The BFF layer handles API proxy (with path rewriting), SSE streaming, file uploa **Backend:** Koa 2 (BFF server) + node-pty (web terminal) +## Star History + +[![Star History Chart](https://api.star-history.com/svg?repos=EKKOLearnAI/hermes-web-ui&type=Date)](https://star-history.com/#EKKOLearnAI/hermes-web-ui&Date) + ## License [MIT](./LICENSE) diff --git a/README_zh.md b/README_zh.md index 4906580..901cb0f 100644 --- a/README_zh.md +++ b/README_zh.md @@ -40,6 +40,8 @@ - 通过 SSE 实时流式输出，支持异步 Run - 多会话管理 — 创建、重命名、删除、切换会话 - 按来源分组会话（Telegram、Discord、Slack 等），可折叠手风琴面板 +- 活跃会话实时指示器 — 正在进行的会话置顶并显示旋转图标 +- 按最新消息时间排序会话列表 - Markdown 渲染，支持语法高亮和代码复制 - 工具调用详情展开（参数 / 结果） - 文件上传支持 @@ -84,8 +86,18 @@ - 从凭证池自动发现模型（`~/.hermes/auth.json`） - 从每个 Provider 端点获取可用模型（`/v1/models`） -- 添加自定义 OpenAI 兼容 Provider -- Provider 级别模型分组 +- 添加、更新、删除 Provider（预设 & 自定义 OpenAI 兼容） +- OpenAI Codex OAuth 登录，使用 Codex 模型 +- Provider 级别模型分组，支持切换默认模型 + +### 多配置文件与网关 + +- 创建、重命名、删除、切换 Hermes 配置文件（Profile） +- 克隆现有配置文件或从归档导入（`.tar.gz`） +- 导出配置文件用于备份或分享 +- 多网关管理 — 按 Profile 启动、停止、监控网关 +- 自动端口冲突解决 +- 配置文件级别的配置和缓存隔离 ### 技能与记忆 @@ -106,6 +118,7 @@ - 记忆（启用/禁用、字符限制） - 会话重置（空闲超时、定时重置） - 隐私（PII 脱敏） +- 模型设置（默认模型 & Provider） - API 服务器配置 ### Web 终端 @@ -234,6 +247,10 @@ BFF 层负责：API 代理（含路径重写）、SSE 流式推送、文件上 **后端：** Koa 2（BFF 服务器）+ node-pty（Web 终端） +## Star 历史 + +[![Star 历史图表](https://api.star-history.com/svg?repos=EKKOLearnAI/hermes-web-ui&type=Date)](https://star-history.com/#EKKOLearnAI/hermes-web-ui&Date) + ## 许可证 [MIT](./LICENSE)