Skip to content

Replace default o3-mini with o4-mini #1710

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 19, 2025

Conversation

PeterDaveHello
Copy link
Contributor

@PeterDaveHello PeterDaveHello commented Apr 18, 2025

User description

We should change the default setting from o3-mini to o4-mini to take advantage of the same price while benefiting from improved performance and capability.


PR Type

Enhancement, Documentation


Description

  • Updated default model from o3-mini to o4-mini across documentation and configuration.

  • Adjusted references to reflect the new default model in usage guides and examples.

  • Ensured consistency in model naming in all relevant files.


Changes walkthrough 📝

Relevant files
Documentation
index.md
Updated model reference in Chrome extension documentation

docs/docs/chrome-extension/index.md

  • Replaced o3-mini with o4-mini in extension description.
  • Updated model reference for improved clarity.
  • +1/-1     
    locally.md
    Updated model reference in local installation guide           

    docs/docs/installation/locally.md

  • Changed model reference from o3-mini to o4-mini.
  • Updated instructions for acquiring keys with the new model.
  • +1/-1     
    pr_agent_pro.md
    Updated model references in PR-Agent Pro overview               

    docs/docs/overview/pr_agent_pro.md

  • Replaced o3-mini with o4-mini in model selection section.
  • Updated supported languages section to reflect the new model.
  • +2/-2     
    changing_a_model.md
    Updated default model in model-changing guide                       

    docs/docs/usage-guide/changing_a_model.md

  • Updated default model reference from o3-mini to o4-mini.
  • Adjusted examples and reasoning effort descriptions.
  • +2/-2     
    qodo_merge_models.md
    Updated supported models and configuration examples           

    docs/docs/usage-guide/qodo_merge_models.md

  • Replaced o3-mini with o4-mini in supported models list.
  • Updated configuration examples to reflect the new model.
  • +3/-3     
    Configuration changes
    configuration.toml
    Updated default model in configuration file                           

    pr_agent/settings/configuration.toml

  • Changed default model from o3-mini to o4-mini.
  • Ensured fallback models remain consistent.
  • +1/-1     

    Need help?
  • Type /help how to ... in the comments thread for any questions about Qodo Merge usage.
  • Check out the documentation for more information.
  • Copy link
    Contributor

    PR Reviewer Guide 🔍

    Here are some key observations to aid the review process:

    ⏱️ Estimated effort to review: 1 🔵⚪⚪⚪⚪
    🧪 No relevant tests
    🔒 No security concerns identified
    ⚡ No major issues detected

    Copy link
    Contributor

    qodo-merge-pro-for-open-source bot commented Apr 18, 2025

    PR Code Suggestions ✨

    No code suggestions found for the PR.

    @PeterDaveHello
    Copy link
    Contributor Author

    Maybe this one should wait for #1708

    cc @mrT23

    @PeterDaveHello PeterDaveHello force-pushed the SwitchDefaultTo-o4-mini branch from ea5c9b2 to e465682 Compare April 18, 2025 18:31
    Comment on lines -9 to 10
    model="o3-mini"
    model="o4-mini"
    fallback_models=["gpt-4o-2024-11-20"]
    Copy link
    Collaborator

    Choose a reason for hiding this comment

    The reason will be displayed to describe this comment to others. Learn more.

    /implement change fallback model to 'gpt-4.1'

    Copy link
    Contributor

    Choose a reason for hiding this comment

    The reason will be displayed to describe this comment to others. Learn more.

    Code Implementation 🛠️

    Implementation: Update the fallback model from "gpt-4o-2024-11-20" to "gpt-4.1" as requested.

    Suggested change
    model="o3-mini"
    model="o4-mini"
    fallback_models=["gpt-4o-2024-11-20"]
    model="o4-mini"
    fallback_models=["gpt-4.1"]

    See review comment here

    Copy link
    Contributor Author

    Choose a reason for hiding this comment

    The reason will be displayed to describe this comment to others. Learn more.

    Maybe leave it in another change will be cleaner 😆

    Copy link
    Collaborator

    @mrT23 mrT23 Apr 18, 2025

    Choose a reason for hiding this comment

    The reason will be displayed to describe this comment to others. Learn more.

    if we are updating to more modern models, I do want to remove the 'gpt-4o' from the config.
    it looks outdated and unmaintained.
    And its just the fallback model (that should not be called in normal usage)

    Copy link
    Contributor Author

    Choose a reason for hiding this comment

    The reason will be displayed to describe this comment to others. Learn more.

    Thanks for the suggestion. I see the importance of updating to modern models. Would you mind if I submit a separate PR for this change? It would help keep the commits cleaner and make it easier for maintainers to track changes. What do you think?

    @mrT23
    Copy link
    Collaborator

    mrT23 commented Apr 18, 2025

    Thanks for the PR.
    i will soon publish some benchmarks on o4-mini for PR code analysis - and indeed its very good (better than sonnet-3.7)

    Please address the comments above, and we can merge

    @PeterDaveHello
    Copy link
    Contributor Author

    Sure, I will be back with the updates soon.

    @PeterDaveHello PeterDaveHello force-pushed the SwitchDefaultTo-o4-mini branch from e465682 to e854383 Compare April 18, 2025 19:52
    @mrT23 mrT23 merged commit ca88ec9 into qodo-ai:main Apr 19, 2025
    2 checks passed
    @PeterDaveHello PeterDaveHello deleted the SwitchDefaultTo-o4-mini branch April 19, 2025 06:53
    Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
    Projects
    None yet
    Development

    Successfully merging this pull request may close these issues.

    2 participants