ci(pr-agent): update configuration

[xmfcx]

User description

Description

Reference:

• https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml
• https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#github-action
• https://pr-agent-docs.codium.ai/usage-guide/additional_configurations/?h=model#changing-a-model

Tests performed

Not applicable.

Effects on system behavior

Interface changes

Pre-review checklist for the PR author

The PR author must check the checkboxes below when creating the PR.

• I've confirmed the contribution guidelines.
• The PR follows the pull request guidelines.

In-review checklist for the PR reviewers

The PR reviewers must check the checkboxes below before approval.

• The PR follows the pull request guidelines.

Post-review checklist for the PR author

The PR author must check the checkboxes below before merging.

• There are no open discussions or they are tracked via tickets.

After all checkboxes are checked, anyone who has write access can merge the PR.

---

PR Type

configuration changes, enhancement

---

Description

• Added new configuration settings for the PR agent in .github/workflows/pr-agent.yaml.
• Set pr_description.publish_labels to false.
• Configured models to gpt-4o and gpt-4o for turbo.
• Adjusted pr_code_suggestions settings, including max_context_tokens to 12000 and enabling commitable_code_suggestions.

---

Changes walkthrough 📝

	Relevant files
Configuration changes	pr-agent.yaml Update PR agent configuration settings                                      .github/workflows/pr-agent.yaml Added new configuration settings for PR agent. Set pr_description.publish_labels to false. Configured models to gpt-4o. Adjusted pr_code_suggestions settings. +6/-0

---

💡 PR-Agent usage:
Comment /help on the PR to get a list of all available PR-Agent tools and their descriptions

[xmfcx]

/describe

[github-actions]

PR Description updated to latest commit (adb19ae)

[xmfcx]

/ask what model are you?

[github-actions]

Ask❓

what model are you?

Answer:

The new configuration in the PR specifies the models as follows:

config.model: gpt-4o
config.model_turbo: gpt-4o

This indicates that the model being used is gpt-4o.

[xmfcx]

/improve

[github-actions]

PR Code Suggestions ✨

Category	Suggestion	Score
Best practice	Change the string "true" to a boolean true for the commitable_code_suggestions setting The pr_code_suggestions.commitable_code_suggestions setting is set to "true" as a string rather than a boolean. YAML supports boolean values directly, which can help avoid type mismatches during parsing. Consider changing the setting to a boolean. .github/workflows/pr-agent.yaml [38] -pr_code_suggestions.commitable_code_suggestions: "true" +pr_code_suggestions.commitable_code_suggestions: true Suggestion importance[1-10]: 9 Why: Changing the string "true" to a boolean true is a best practice in YAML to avoid type mismatches and ensure consistency. This is a significant improvement for maintainability and correctness.	9
	Use a boolean value for publish_labels to maintain consistency and avoid parsing issues The setting pr_description.publish_labels is set to "false" as a string. For consistency with other boolean settings in YAML, consider using a boolean value directly. .github/workflows/pr-agent.yaml [33] -pr_description.publish_labels: "false" +pr_description.publish_labels: false Suggestion importance[1-10]: 9 Why: Using a boolean value for publish_labels enhances consistency and avoids potential parsing issues, making it a significant improvement for code quality and maintainability.	9
Possible issue	Adjust the model configuration settings to use distinct values if they serve different purposes It seems that the configuration for config.model and config.model_turbo are both set to gpt-4o. If these settings are meant to specify different model configurations or operational modes, consider using distinct values for each to avoid redundancy and potential confusion. .github/workflows/pr-agent.yaml [34-35] config.model: gpt-4o -config.model_turbo: gpt-4o +config.model_turbo: gpt-4o-turbo # Example of a distinct setting if applicable Suggestion importance[1-10]: 7 Why: The suggestion addresses potential redundancy and confusion by recommending distinct values for config.model and config.model_turbo. However, it may not be crucial if the same model is intended for both settings.	7
Performance	Evaluate and possibly reduce the max model tokens to optimize performance and cost The config.max_model_tokens is set to 64000 which might be too high depending on the use case. Consider evaluating the necessity of such a high limit as it can impact performance and costs. .github/workflows/pr-agent.yaml [36] -config.max_model_tokens: 64000 +config.max_model_tokens: 32000 # Adjusted to a lower value based on performance evaluation Suggestion importance[1-10]: 6 Why: While reducing the max model tokens could optimize performance and cost, the necessity of this change depends on specific use case requirements. It is a valid suggestion but may not be universally applicable.	6