Files
picoclaw/docs/zh/ANTIGRAVITY_USAGE.md
T
BeaconCat 403ceb39be docs: fix inaccuracies, add translations, and expand channel docs (#1837)
## Config field fixes (cross-verified against Go source)
- MaixCam: server_address → host + port
- IRC: use_tls → tls, channels_to_join → channels (all 6 languages)
- WeCom AI Bot: callback port 18791 → 18790
- credential_encryption: base_url → api_base, add required model field,
  remove incorrect passphrase-only mode docs
- providers.md: agents.defaults.model → model_name (×4), remove
  non-existent session.backlog_limit
- migration guide, troubleshooting: agents.defaults.model → model_name
- ANTIGRAVITY_AUTH: fix file path, Go 1.21 → 1.25, model → model_name
- spawn-tasks: fix truncated file, add Heartbeat introduction
- tools_configuration: add Tavily/SearXNG/GLMSearch, exec allow_remote/
  timeout_seconds/custom_allow_patterns, cron allow_command, skills
  github/search_cache, clawhub timeout/max_zip_size/max_response_size
- configuration: fix builtin skills path (build-time embedded, not cwd),
  HEARTBEAT.md marked auto-generated

## Broken link fixes (15 total)
- chat-apps.md: WeCom/Matrix links with wrong relative paths
- providers.md: migration link with extra docs/ prefix
- hardware-compatibility.md: README links with wrong depth (all 5 langs)
- chat-apps.md: WhatsApp dead links → anchor links (zh/ja)

## Getting-started accuracy
- README (all 6 langs): add picoclaw.io as recommended download,
  add missing picoclaw model CLI command
- docker.md: clarify first-run trigger condition (all 6 langs)
- configuration.md: fix builtin skills path description (all 6 langs)

## QQ channel
- Add quick setup via q.qq.com/qqbot/openclaw (one-click bot creation)
- Add manual setup as fallback (all 6 languages)

## Feishu channel
- Update setup flow: WebSocket/SDK mode, no webhook URL needed
- Preserve Lark international domain note (all 6 languages)

## chat-apps.md
- Add Feishu, Slack, IRC, OneBot detail sections (all 6 languages)
- Add MaixCam section to ja/fr/pt-br/vi
- Fix all channel doc links to point to correct language version

## New translations (25 files, 5 docs × 5 languages)
debug.md, credential_encryption.md, hardware-compatibility.md,
ANTIGRAVITY_AUTH.md, ANTIGRAVITY_USAGE.md → zh/ja/fr/pt-br/vi

## Channel docs (6 languages each, 60 new files)
telegram, discord, qq, feishu, maixcam, dingtalk, line, slack, onebot,
wecom/wecom_aibot, wecom/wecom_app, wecom/wecom_bot

Co-authored-by: BeaconCat <BeaconCat@users.noreply.github.com>
2026-03-20 22:37:05 +08:00

73 lines
2.5 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
> 返回 [README](../../README.zh.md)
# 在 PicoClaw 中使用 Antigravity 提供商
本指南介绍如何在 PicoClaw 中设置和使用 **Antigravity**Google Cloud Code Assist)提供商。
## 前提条件
1. 一个 Google 账户。
2. 已启用 Google Cloud Code Assist(通常通过"Gemini for Google Cloud"引导流程获取)。
## 1. 身份验证
要使用 Antigravity 进行身份验证,请运行以下命令:
```bash
picoclaw auth login --provider antigravity
```
### 手动验证(无界面/VPS 环境)
如果你在服务器(Coolify/Docker)上运行且无法访问 `localhost`,请按照以下步骤操作:
1. 运行上述命令。
2. 复制提供的 URL 并在本地浏览器中打开。
3. 完成登录。
4. 浏览器将重定向到 `localhost:51121` URL(页面将无法加载)。
5. **从浏览器地址栏复制该最终 URL**
6. **将其粘贴回 PicoClaw 正在等待的终端中**
PicoClaw 将自动提取授权码并完成流程。
## 2. 管理模型
### 列出可用模型
查看你的项目可以访问哪些模型并检查其配额:
```bash
picoclaw auth models
```
### 切换模型
你可以在 `~/.picoclaw/config.json` 中更改默认模型,或通过 CLI 覆盖:
```bash
# 为单个命令覆盖
picoclaw agent -m "Hello" --model claude-opus-4-6-thinking
```
## 3. 实际使用(Coolify/Docker
如果你通过 Coolify 或 Docker 部署,请按照以下步骤进行测试:
1. **环境变量**
* `PICOCLAW_AGENTS_DEFAULTS_MODEL=gemini-flash`
2. **身份验证持久化**
如果你已在本地登录,可以将凭据复制到服务器:
```bash
scp ~/.picoclaw/auth.json user@your-server:~/.picoclaw/
```
*或者*,如果你有终端访问权限,可以在服务器上运行一次 `auth login` 命令。
## 4. 故障排除
* **空响应**:如果模型返回空回复,可能是该模型在你的项目中受到限制。请尝试 `gemini-3-flash` 或 `claude-opus-4-6-thinking`。
* **429 速率限制**Antigravity 有严格的配额限制。如果触发限制,PicoClaw 将在错误消息中显示"重置时间"。
* **404 未找到**:确保你使用的是 `picoclaw auth models` 列表中的模型 ID。请使用短 ID(例如 `gemini-3-flash`),而非完整路径。
## 5. 可用模型总结
根据测试,以下模型最为可靠:
* `gemini-3-flash`(快速,高可用性)
* `gemini-2.5-flash-lite`(轻量级)
* `claude-opus-4-6-thinking`(强大,包含推理能力)