fix(config): use flash-lite for utility model configs to preserve quota

[kazukinakai]

Fixes #23397
Fixes #18059
Related to #24937 (capacity/429 tracking issue)

Problem

When gemini-3-flash-preview quota is exhausted (100%), the CLI becomes completely unusable even if the user explicitly switches to gemini-3.1-flash-lite-preview. The "Usage limit reached for gemini-3-flash-preview" error keeps firing regardless of the selected model.

Root cause: all six internal utility configs are hardcoded to gemini-3-flash-base → gemini-3-flash-preview, so they consume Flash quota independently of the user's model selection:

Config key	Role	Before	After
loop-detection	UTILITY_LOOP_DETECTOR	Flash	Flash Lite ✓
llm-edit-fixer	UTILITY_EDIT_CORRECTOR	Flash	Flash Lite ✓
next-speaker-checker	UTILITY_NEXT_SPEAKER	Flash	Flash Lite ✓
web-fetch-fallback	fallback path (no tools)	Flash	Flash Lite ✓
web-search	Grounding with Google Search	Flash	Flash Lite ✓
web-fetch	URL context tool	Flash	Flash Lite ✓

Fix

Add gemini-3-flash-lite-base targeting gemini-3.1-flash-lite-preview and switch all six configs to use it.

Why Flash Lite is safe:

• Utility tasks (loop detection, edit fixing, next-speaker routing): lightweight reasoning — same pattern as edit-corrector, fast-ack-helper, summarizer-*, classifier which already use Flash Lite variants
• web-search and web-fetch: gemini-3.1-flash-lite-preview officially supports both googleSearch (Grounding) and urlContext tools per Gemini API docs

Impact

• Users with exhausted Flash but available Flash Lite quota can keep working
• Reduces Flash consumption for all utility calls, preserving quota for the main model
• No functional regression

Reproduction (from #23397)

# Set Flash Lite as main model explicitly:
gemini -m 'gemini-3.1-flash-lite-preview'

# Still gets:
Usage limit reached for gemini-3-flash-preview.
/model to switch models.

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request addresses a critical usability issue where internal utility tasks were hardcoded to use the standard Flash model, causing failures when that specific quota was exhausted. By migrating these lightweight utility tasks to a Flash Lite base configuration, the system now effectively manages quota consumption and prevents unnecessary service interruptions for users.

Highlights

• New Base Configuration: Introduced 'gemini-3-flash-lite-base' to target the 'gemini-3.1-flash-lite-preview' model.
• Utility Model Migration: Updated 'loop-detection', 'llm-edit-fixer', and 'next-speaker-checker' to use the new Flash Lite base configuration.
• Quota Management: Ensures utility tasks continue to function even when the primary Flash quota is exhausted by leveraging available Flash Lite capacity.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[gemini-code-assist]

Code Review

This pull request introduces a new model configuration, gemini-3-flash-lite-base, which utilizes the gemini-3.1-flash-lite-preview model. Additionally, it updates the loop-detection, llm-edit-fixer, and next-speaker-checker configurations to extend this new base instead of gemini-3-flash-base. I have no feedback to provide.

[kazukinakai]

Ran npm run preflight locally (Node 20, per .nvmrc): all checks passed (clean → npm ci → format → build → lint → typecheck → test).