mirror of
https://github.com/sipeed/picoclaw.git
synced 2026-06-12 18:08:54 +00:00
838a69085b
- Fix DingTalk section referencing "QQ numbers" instead of DingTalk user IDs - Fix Anthropic example showing OAuth when code uses paste-token auth - Replace OpenClaw references in ANTIGRAVITY_AUTH.md with actual PicoClaw paths and Go patterns - Fix auth file path from auth-profiles.json to auth.json in ANTIGRAVITY_USAGE.md - Remove non-existent approval tool from tools_configuration.md, add skills tool docs - Update Quick Start configs in fr/pt-br/vi/ja translations to use model_list format - Fix allowFrom camelCase to allow_from in fr/pt-br translations - Fix camelCase config keys in ja translation - Update zh/ja web search config from old flat format to brave/duckduckgo - Fix broken ClawdChat link and trailing commas in zh translation - Add missing qwen/cerebras providers to fr/pt-br/vi translation tables - Add missing protocol prefixes to migration guide - Fix typos in community roadmap
2.5 KiB
2.5 KiB
Using Antigravity Provider in PicoClaw
This guide explains how to set up and use the Antigravity (Google Cloud Code Assist) provider in PicoClaw.
Prerequisites
- A Google account.
- Google Cloud Code Assist enabled (usually available via the "Gemini for Google Cloud" onboarding).
1. Authentication
To authenticate with Antigravity, run the following command:
picoclaw auth login --provider antigravity
Manual Authentication (Headless/VPS)
If you are running on a server (Coolify/Docker) and cannot reach localhost, follow these steps:
- Run the command above.
- Copy the URL provided and open it in your local browser.
- Complete the login.
- Your browser will redirect to a
localhost:51121URL (which will fail to load). - Copy that final URL from your browser's address bar.
- Paste it back into the terminal where PicoClaw is waiting.
PicoClaw will extract the authorization code and complete the process automatically.
2. Managing Models
List Available Models
To see which models your project has access to and check their quotas:
picoclaw auth models
Switch Models
You can change the default model in ~/.picoclaw/config.json or override it via the CLI:
# Override for a single command
picoclaw agent -m "Hello" --model claude-opus-4-6-thinking
3. Real-world Usage (Coolify/Docker)
If you are deploying via Coolify or Docker, follow these steps to test:
- Environment Variables:
PICOCLAW_AGENTS_DEFAULTS_MODEL=gemini-flash
- Authentication persistence:
If you've logged in locally, you can copy your credentials to the server:
Alternatively, run the
scp ~/.picoclaw/auth.json user@your-server:~/.picoclaw/auth logincommand once on the server if you have terminal access.
4. Troubleshooting
- Empty Response: If a model returns an empty reply, it may be restricted for your project. Try
gemini-3-flashorclaude-opus-4-6-thinking. - 429 Rate Limit: Antigravity has strict quotas. PicoClaw will display the "reset time" in the error message if you hit a limit.
- 404 Not Found: Ensure you are using a model ID from the
picoclaw auth modelslist. Use the short ID (e.g.,gemini-3-flash) not the full path.
5. Summary of Working Models
Based on testing, the following models are most reliable:
gemini-3-flash(Fast, highly available)gemini-2.5-flash-lite(Lightweight)claude-opus-4-6-thinking(Powerful, includes reasoning)