Skip to content

Conversation

PeterDaveHello
Copy link
Contributor

@PeterDaveHello PeterDaveHello commented Jun 5, 2025

User description

Reference:


PR Type

enhancement


Description

  • Added support for Google Gemini 2.5 Pro Preview 06-05 model

  • Updated token limit mappings for new Gemini model variant


Changes diagram

flowchart LR
  A["Add Gemini 2.5 Pro Preview 06-05"] -- "Update token limits" --> B["Update model-token mapping in __init__.py"]
Loading

Changes walkthrough 📝

Relevant files
Enhancement
__init__.py
Add Gemini 2.5 Pro Preview 06-05 to model-token mappings 

pr_agent/algo/init.py

  • Added 'vertex_ai/gemini-2.5-pro-preview-06-05' with token limit
    1048576
  • Added 'gemini/gemini-2.5-pro-preview-06-05' with token limit 1048576
  • Ensured new Gemini model variant is recognized in both Vertex AI and
    Gemini mappings
  • +2/-0     

    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

    PR Code Suggestions ✨

    No code suggestions found for the PR.

    @mrT23
    Copy link
    Collaborator

    mrT23 commented Jun 5, 2025

    Great, thanks.

    will be cool to add in the future support for thinking budget. i think this is the main advantage of this release.
    old model was good, but thought too much (latency)

    image

    @mrT23 mrT23 merged commit ee4b847 into qodo-ai:main Jun 5, 2025
    2 checks passed
    @PeterDaveHello PeterDaveHello deleted the Gemini-2.5-Pro-Preview-06-05 branch June 5, 2025 17:49
    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