Skip to content

Conversation

@uinstinct
Copy link
Contributor

@uinstinct uinstinct commented Nov 25, 2025

Description

https://hub.continue.dev/continuedev/gemini-3-pro-preview

resolves CON-4933

AI Code Review

  • Team members only: AI review runs automatically when PR is opened or marked ready for review
  • Team members can also trigger a review by commenting @continue-review

Checklist

  • [] I've read the contributing guide
  • [] The relevant docs, if any, have been updated or created
  • [] The relevant tests, if any, have been updated or created

Screen recording or screenshot

[ When applicable, please include a short screen recording or screenshot - this makes it much easier for us as contributors to review and understand your changes. See this PR as a good example. ]

Tests

[ What tests were added or updated to ensure the changes work as expected? ]


Summary by cubic

Adds support for Google Gemini 3 Pro Preview so users can configure and run gemini-3-pro-preview for chat and agent workflows. Addresses Linear CON-4933.

  • New Features
    • Registered gemini-3-pro-preview in Gemini and CometAPI providers with context/token limits and chat recommendation.
    • Added Gemini 3 Pro to the Add New Model flow (model card and provider list).
    • Updated agent model recommendations to include Gemini 3 Pro.
    • Updated docs to recommend Gemini 3 Pro with a YAML example.

Written for commit e13c68d. Summary will update automatically on new commits.

@uinstinct uinstinct requested a review from a team as a code owner November 25, 2025 13:01
@uinstinct uinstinct requested review from RomneyDa and removed request for a team November 25, 2025 13:01
@dosubot dosubot bot added the size:M This PR changes 30-99 lines, ignoring generated files. label Nov 25, 2025
@continue
Copy link
Contributor

continue bot commented Nov 25, 2025

Added documentation updates to include Gemini 3 Pro in:

  • Model recommendations table for agent_plan and chat_edit roles
  • Model capabilities reference table

These changes maintain consistency with the new Gemini 3 Pro support added in this PR.

@continue
Copy link
Contributor

continue bot commented Nov 25, 2025

Updated seed scripts in remote-config-server to include Gemini 3 Pro Preview for local testing: https://github.com/continuedev/remote-config-server/pull/1811

Added tests for Gemini 3 Pro model recognition and other agent models.
Tests cover:
- OpenAI o1/o3/o4 models
- DeepSeek R1/Reasoner models
- Gemini 2.5 and 3.x Pro models (including new gemini-3-pro-preview)
- Claude Sonnet 3.7+ and Opus 4 models
- xAI Grok Code models
- Case insensitivity and edge cases

Co-authored-by: nate <[email protected]>
Copy link
Contributor

@cubic-dev-ai cubic-dev-ai bot left a comment

Choose a reason for hiding this comment

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

No issues found across 7 files

@dosubot dosubot bot added size:L This PR changes 100-499 lines, ignoring generated files. and removed size:M This PR changes 30-99 lines, ignoring generated files. labels Nov 25, 2025
@github-actions
Copy link

github-actions bot commented Nov 25, 2025


Thank you for your submission, we really appreciate it. Like many open-source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution. You can sign the CLA by just posting a Pull Request Comment same as the below format.


I have read the CLA Document and I hereby sign the CLA


2 out of 3 committers have signed the CLA.
✅ (uinstinct)[https://github.com/uinstinct]
✅ (RomneyDa)[https://github.com/RomneyDa]
@continue
Continue seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
You can retrigger this bot by commenting recheck in this Pull Request. Posted by the CLA Assistant Lite bot.

@continue
Copy link
Contributor

continue bot commented Nov 25, 2025

Added comprehensive test coverage for the isRecommendedAgentModel function to ensure the Gemini 3 Pro model recognition works correctly.

The tests cover:

  • ✅ Gemini 3 Pro models (including the new gemini-3-pro-preview)
  • ✅ Existing model families (OpenAI o1/o3/o4, DeepSeek R1, Claude 3.7+, etc.)
  • ✅ Case insensitivity handling
  • ✅ Edge cases (empty strings, partial matches, invalid models)
  • ✅ Verification that only Pro models are recommended (not Flash)

The regex change from /2\.5/ to /2\.5|3/ now correctly matches both Gemini 2.5 and 3.x versions.

@github-project-automation github-project-automation bot moved this from Todo to In Progress in Issues and PRs Nov 25, 2025
@dosubot dosubot bot added the lgtm This PR has been approved by a maintainer label Nov 25, 2025
@RomneyDa RomneyDa closed this Nov 26, 2025
@github-project-automation github-project-automation bot moved this from In Progress to Done in Issues and PRs Nov 26, 2025
@RomneyDa RomneyDa reopened this Nov 26, 2025
@github-project-automation github-project-automation bot moved this from Done to In Progress in Issues and PRs Nov 26, 2025
@github-actions github-actions bot locked and limited conversation to collaborators Nov 26, 2025
@RomneyDa RomneyDa merged commit 827ca72 into continuedev:main Nov 26, 2025
103 of 110 checks passed
@github-project-automation github-project-automation bot moved this from In Progress to Done in Issues and PRs Nov 26, 2025
@sestinj
Copy link
Contributor

sestinj commented Nov 26, 2025

🎉 This PR is included in version 1.7.1 🎉

The release is available on:

Your semantic-release bot 📦🚀

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

lgtm This PR has been approved by a maintainer released size:L This PR changes 100-499 lines, ignoring generated files.

Projects

Status: Done

Development

Successfully merging this pull request may close these issues.

4 participants