xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-19 12:00:37 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs: update fallback model configuration and clarify self-hosted runner requirements

Browse Source
This commit is contained in:
Abhinav Kumar
2025-07-13 00:20:03 +05:30
parent 6108f96bff
commit 3aaa727e05
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docs/docs/installation/github.md
View File

@ -138,7 +138,7 @@ jobs:
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
config.model: "anthropic/claude-3-opus-20240229"
config.fallback_models: '["anthropic/claude-3-opus-20240229"]'
config.fallback_models: '["anthropic/claude-3-haiku-20240307"]'
ANTHROPIC.KEY: ${{ secrets.ANTHROPIC_KEY }}
github_action_config.auto_review: "true"
github_action_config.auto_describe: "true"
@ -212,7 +212,7 @@ To use Claude models:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Set the model to Claude
config.model: "anthropic/claude-3-opus-20240229"
config.fallback_models: '["anthropic/claude-3-opus-20240229"]'
config.fallback_models: '["anthropic/claude-3-haiku-20240307"]'
# Add your Anthropic API key
ANTHROPIC.KEY: ${{ secrets.ANTHROPIC_KEY }}
# Tool configuration
@ -273,7 +273,7 @@ To use local models via Ollama:
github_action_config.auto_improve: "true"
```
**Note:** For local models, you'll need to run Ollama on your GitHub Actions runner or use a self-hosted runner.
**Note:** For local models, you'll need to use a self-hosted runner with Ollama installed, as GitHub Actions hosted runners cannot access localhost services.
### Advanced Configuration Options
@ -439,8 +439,8 @@ If you encounter rate limiting:
```yaml
# Correct
config.fallback_models: '["model1", "model2"]'
# Incorrect
config.fallback_models: "[model1, model2]"
# Incorrect (interpreted as a YAML list, not a string)
config.fallback_models: ["model1", "model2"]
```
#### Debugging Tips