Update model references from o3-mini to o4-mini and add Gemini models

[mrT23]

PR Type

Enhancement, Documentation, Bug fix

---

Description

• Updated model references from o3-mini to o4-mini.

• Added support for new Gemini models (gemini-2.5-pro and gemini-2.5-flash).

• Enhanced error handling for undefined models in MAX_TOKENS.

• Updated documentation to reflect new model options and configurations.

---

Changes walkthrough 📝

	Relevant files
Enhancement	__init__.py Added new Gemini models to `MAX_TOKENS`                                    pr_agent/algo/init.py Added new Gemini models (gemini-2.5-pro-preview-03-25 and gemini-2.5-flash-preview-04-17) to MAX_TOKENS. +2/-0
Error handling	utils.py Enhanced error handling for undefined models                          pr_agent/algo/utils.py Improved error handling for undefined models in MAX_TOKENS. Added a logger error message for better debugging. +1/-0
Documentation	pr_agent_pro.md Updated model references and improved formatting                  docs/docs/overview/pr_agent_pro.md Updated model references from o3-mini to o4-mini. Improved formatting and descriptions for model selection. +10/-10  qodo_merge_models.md Updated model references and added Gemini configurations  docs/docs/usage-guide/qodo_merge_models.md Replaced o3-mini with o4-mini in model references. Added configuration examples for new Gemini models. +23/-6
Configuration changes	configuration.toml Updated default and fallback model configurations                pr_agent/settings/configuration.toml Updated default model to o4-mini. Adjusted fallback model to gpt-4.1. +2/-2

---

Need help?

Type /help how to ... in the comments thread for any questions about Qodo Merge usage.

Check out the documentation for more information.

[qodo-merge-pro-for-open-source]

PR Reviewer Guide 🔍

Here are some key observations to aid the review process:

⏱️ Estimated effort to review: 2 🔵🔵⚪⚪⚪

🧪 No relevant tests

🔒 No security concerns identified

⚡ Recommended focus areas for review Model Inconsistency The default model is set to o4-mini but the PR description mentions updating from o3-mini to o4-mini. The file already had o4-mini as the default model before the change, which is inconsistent with the PR description. model="o4-mini" fallback_models=["gpt-4.1"] Error Message Clarity The added error message is helpful but could be more specific about what action is needed. Consider suggesting how to add the model to MAX_TOKENS or where to set custom_model_max_tokens. get_logger().error(f"Model {model} is not defined in MAX_TOKENS in ./pr_agent/algo/__init__.py and no custom_model_max_tokens is set") raise Exception(f"Ensure {model} is defined in MAX_TOKENS in ./pr_agent/algo/__init__.py or set a positive value for it in config.custom_model_max_tokens")

[qodo-merge-pro-for-open-source]

PR Code Suggestions ✨

Explore these optional code suggestions:

Category	Suggestion	Impact
General	Remove hardcoded file path The error message is too specific about the file path. Use a relative import path that matches the actual module structure rather than hardcoding the file path with "./pr_agent/algo/init.py", which might not be accurate in all deployment environments. pr_agent/algo/utils.py [881] -get_logger().error(f"Model {model} is not defined in MAX_TOKENS in ./pr_agent/algo/__init__.py and no custom_model_max_tokens is set") +get_logger().error(f"Model {model} is not defined in MAX_TOKENS and no custom_model_max_tokens is set") Apply this suggestion Suggestion importance[1-10]: 7 __ Why: The suggestion correctly identifies that hardcoded file paths can cause issues in different deployment environments. Removing the specific path reference makes the error message more maintainable and less likely to become outdated if the file structure changes.	Medium
More

• Author self-review: I have reviewed the PR code suggestions, and addressed the relevant ones.