Skip to content

Gemini authentication with browser-based OAuth login and model selection dropdowns #449

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
reikernodd wants to merge 5 commits into
base: main
Choose a base branch
from
Open

Gemini authentication with browser-based OAuth login and model selection dropdowns #449

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
ddc1071
feat: add support for local LLM provider and integrate Google OAuth flow
reikernodd May 8, 2026
98fb5d3
feat: implement Gemini OAuth 2.0 flow with automated credential loadi…
reikernodd May 9, 2026
b732ae4
chore: update hello-agent language to English and refine .gitignore p…
reikernodd May 9, 2026
ae7e1fa
test: add useLayoutEffect mock to ConsoleOAuthFlow tests
reikernodd May 10, 2026
0195760
Merge branch 'main' into main
reikernodd May 10, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,10 +12,10 @@ coverage
src/utils/vendor/

# AI tool runtime directories
.agents/
.claude/
.omx/
.docs/task/
.agents/*
.claude/*
.omx/*
.docs/task/*
# Binary / screenshot files (root only)
/*.png
*.bmp
Expand Down
33 changes: 21 additions & 12 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
| **Poor Mode** | 穷鬼模式，关闭记忆提取和键入建议,大幅度减少并发请求 | /poor 可以开关 |
| **Channels 频道通知** | MCP 服务器推送外部消息到会话（飞书/Slack/Discord/微信等），`--channels plugin:name@marketplace` 启用 | [文档](https://ccb.agent-aura.top/docs/features/channels) |
| **自定义模型供应商** | OpenAI/Anthropic/Gemini/Grok 兼容 (`/login`) | [文档](https://ccb.agent-aura.top/docs/features/all-features-guide) |
| **本地 LLM (Ollama/Local)** | 支持 Ollama, LM Studio, Jan.ai, LocalAI。支持在 `/login` 中一键拉取模型、检查硬件状态、本地优先运行。 | /login 选择 Local LLM |
| Voice Mode | 语音输入，支持豆包语言输入（`/voice doubao`） | [文档](https://ccb.agent-aura.top/docs/features/voice-mode) |
| Computer Use | 屏幕截图、键鼠控制 | [文档](https://ccb.agent-aura.top/docs/features/computer-use) |
| Chrome Use | 浏览器自动化、表单填写、数据抓取 | [自托管](https://ccb.agent-aura.top/docs/features/chrome-use-mcp) [原生版](https://ccb.agent-aura.top/docs/features/claude-in-chrome-mcp) |
Expand Down Expand Up @@ -145,23 +146,31 @@ bun run build

### 👤 新人配置 /login

首次运行后，在 REPL 中输入 `/login` 命令进入登录配置界面，选择 **Anthropic Compatible** 即可对接第三方 API 兼容服务（无需 Anthropic 官方账号）。
选择 OpenAI 和 Gemini 对应的栏目都是支持相应协议的
首次运行后，在 REPL 中输入 `/login` 命令进入登录配置界面：

需要填写的字段：
1. **Anthropic Compatible**: 对接第三方 API 兼容服务（OpenRouter、AWS Bedrock 代理等）。
2. **OpenAI / Gemini / Grok**: 对应各自协议的云端服务。
- **Gemini (Google Auth)**: 支持交互式浏览器登录。
1. 在 Google Cloud Console 的 **APIs & Services > OAuth consent screen** 中配置 OAuth 客户端（User Type 设为 External）。
2. 下载 credentials JSON 文件并保存到项目根目录的 `/.files/OAuth.json`。
3. 在 `/login` 配置界面中留空 API Key 并按 Enter，程序将自动拉起浏览器完成授权并自动拉取模型列表。
Comment on lines +154 to +156
Copy link
Copy Markdown
Contributor

@coderabbitai coderabbitai Bot May 10, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
# Find the Gemini google-oauth implementation and inspect what file path it expects for the credentials JSON.
fd -t f 'google-oauth' src/services/api/gemini 2>/dev/null
fd -t f 'gemini' src/services/api 2>/dev/null | head -50

# Search for credential path references inside the gemini auth code
rg -n -C3 'OAuth\.json|\.files|credentials' --type=ts --type=tsx -g '*gemini*'

# Also search for any mention of the documented path verbatim
rg -nF '.files/OAuth.json'

Repository: claude-code-best/claude-code

Length of output: 354

🏁 Script executed:

cat -n src/services/api/gemini/google-oauth.ts

Repository: claude-code-best/claude-code

Length of output: 5809

Remove the leading slash from the OAuth.json path in the README.

The code loads credentials from .files/OAuth.json (line 15 of src/services/api/gemini/google-oauth.ts uses path.join(process.cwd(), '.files', 'OAuth.json')), but the README documents it as /.files/OAuth.json. The leading slash is incorrect and may confuse users into placing the file at the filesystem root instead of the project root. Update lines 155 (and the corresponding line in README_EN.md:152) to remove the leading slash:

2. 下载 credentials JSON 文件并保存到项目根目录的 `.files/OAuth.json`。
🤖 Prompt for AI Agents 
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@README.md` around lines 154 - 156, Update the README entries that incorrectly
show the OAuth credentials path with a leading slash; change any occurrences of
"/.files/OAuth.json" to ".files/OAuth.json" in README.md (around the current
lines referencing the OAuth.json path) and the corresponding entry in
README_EN.md so they match how the code in
src/services/api/gemini/google-oauth.ts (which uses path.join(process.cwd(),
'.files', 'OAuth.json')) expects the file to be located in the project root.

3. **Local LLM**: **(推荐)** 使用本地运行的模型。
- 支持 **Ollama**, **LM Studio**, **Jan.ai**, **LocalAI**。
- **Ollama 深度集成**: 可直接在 CLI 中查看已安装模型，或输入模型名（如 `llama3.1`）一键拉取（Pull）。支持模型列表交互切换和硬件状态自动检测。
- 自动检测本地运行状态和默认端口。

#### /login 字段说明 (云端模式)：

| 📌 字段 | 📝 说明 | 💡 示例 |
| ------------ | ------------- | ---------------------------- |
| Base URL | API 服务地址 | `https://api.example.com/v1` |
| API Key | 认证密钥 | `sk-xxx` |
| Haiku Model | 快速模型 ID | `claude-haiku-4-5-20251001` |
| Sonnet Model | 均衡模型 ID | `claude-sonnet-4-6` |
| Opus Model | 高性能模型 ID | `claude-opus-4-6` |
> ℹ️ 支持所有 Anthropic API 兼容服务（如 OpenRouter、AWS Bedrock 代理等），只要接口兼容 Messages API 即可。

- ⌨️ **Tab / Shift+Tab** 切换字段，**Enter** 确认并跳到下一个，最后一个字段按 Enter 保存
### 🩺 系统诊断 /doctor

> ℹ️ 支持所有 Anthropic API 兼容服务（如 OpenRouter、AWS Bedrock 代理等），只要接口兼容 Messages API 即可。
如果你在使用过程中遇到环境问题（尤其是本地模型运行缓慢或无法连接），可以使用 `/doctor` 命令进行全方位诊断：

- **硬件负载**: 自动显示当前 CPU 型号、核心数、剩余内存 (RAM) 以及系统架构。
- **本地环境**: 检查 Ollama 等本地 Runner 是否正在运行，并列出所有可用模型。
- **配置校验**: 检查环境变量（如 `LOCAL_BASE_URL`）和权限设置。
- **故障排查**: 识别多个重复安装的版本、过期的版本锁或权限不足的更新。

## Feature Flags

Expand Down
Loading