fix: switch default AI model to gemini-2.5-flash to avoid quota limits by omsherikar · Pull Request #288 · bubblelabai/BubbleLab

omsherikar · 2026-02-06T19:38:05Z

Update RECOMMENDED_MODELS (BEST/PRO/FAST) from gemini-3-pro-preview to gemini-2.5-flash
Update COFFEE_DEFAULT_MODEL from gemini-3-pro-preview to gemini-2.5-flash
Update BubbleFlowGeneratorWorkflow model from gemini-3-flash-preview to gemini-2.5-flash
Fix documentation references and comments to reflect new default

This resolves quota limit errors on fresh installations while maintaining quality and reducing costs. Users can still explicitly select other models.

Summary

Related Issues

Type of Change

Checklist

My code follows the code style of this project
I have added appropriate tests for my changes
I have run pnpm check and all tests pass
I have tested my changes locally
I have linked relevant issues

Screenshots (Required)

For New Bubble Integrations

📋 Integration Flow Tests: When creating a new bubble, you must write an integration flow test that exercises all operations end-to-end in realistic scenarios—including edge cases. This flow should be runnable in bubble studio and return structured results tracking each operation's success/failure with details. See packages/bubble-core/src/bubbles/service-bubble/google-sheets/google-sheets.integration.flow.ts for a complete reference implementation.

⚠️ If your integration requires API credits for testing, please reach out to the team for test credentials.

Integration flow test (.integration.flow.ts) covers all operations
Screenshots showing full test results in Bubble Studio attached above

Additional Context

Summary by CodeRabbit

Chores
- Updated AI model configurations for BubbleFlow generation and Coffee planning workflows to align with current model provider versions.
- Updated default AI models across all generation tiers (BEST, PRO, FAST) to ensure consistent performance and optimal generation quality.

- Update RECOMMENDED_MODELS (BEST/PRO/FAST) from gemini-3-pro-preview to gemini-2.5-flash - Update COFFEE_DEFAULT_MODEL from gemini-3-pro-preview to gemini-2.5-flash - Update BubbleFlowGeneratorWorkflow model from gemini-3-flash-preview to gemini-2.5-flash - Fix documentation references and comments to reflect new default This resolves quota limit errors on fresh installations while maintaining quality and reducing costs. Users can still explicitly select other models.

coderabbitai · 2026-02-06T19:38:35Z

📝 Walkthrough

Walkthrough

Configuration updates swapping default AI model references from Gemini 3 variants to Gemini 2.5-flash across BubbleFlow generation prompts, workflow configurations, and shared schemas. These changes standardize the default model selection for the generation system without altering control flow or logic.

Changes

Cohort / File(s)	Summary
BubbleFlow Generation Configuration `apps/bubblelab-api/src/config/bubbleflow-generation-prompts.ts`, `packages/bubble-shared-schemas/src/bubbleflow-generation-prompts.ts`	Updated model references from gemini-3-pro-preview and gemini-3-flash-preview to gemini-2.5-flash across BEST, PRO, and FAST tier definitions; added notes indicating gemini-2.5-flash as the current default.
AI Workflow Model Configuration `apps/bubblelab-api/src/services/ai/bubbleflow-generator.workflow.ts`	Replaced primary and backup model configurations from gemini-3-flash-preview/claude-sonnet-4-5 to gemini-2.5-flash and gemini-2.5-flash-lite respectively.
Default Model Constants `packages/bubble-shared-schemas/src/coffee.ts`	Updated COFFEE_DEFAULT_MODEL constant from gemini-3-pro-preview to gemini-2.5-flash.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~10 minutes

Possibly related issues

Issue #287: Changes directly address default model configuration updates from Gemini 3 variants to Gemini 2.5-flash across the generation system.

Possibly related PRs

PR #230: Modifies the same workflow file (bubbleflow-generator.workflow.ts) for AI agent setup, though with different changes (retry flow enhancements versus model configuration swaps).

Poem

🐰 With whiskers twitching, models shift and change,
From Gemini's third tier to 2.5's range,
The configs hop and skip with grace,
New defaults settle in their place, ✨
Faster, brighter, BubbleFlow's new face!

🚥 Pre-merge checks | ✅ 3

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately summarizes the main change: switching the default AI model to gemini-2.5-flash to avoid quota limits, which is reflected across all modified files.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing touches

📝 Generate docstrings

🧪 Generate unit tests (beta)

Create PR with unit tests
Post copyable unit tests in a comment

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

Copilot

Pull request overview

This PR updates the project’s default/recommended Gemini model selections to google/gemini-2.5-flash to reduce quota-limit errors on fresh installs while keeping acceptable quality/cost.

Changes:

Switch COFFEE_DEFAULT_MODEL to google/gemini-2.5-flash.
Update RECOMMENDED_MODELS (BEST/PRO/FAST) to google/gemini-2.5-flash.
Update BubbleFlowGeneratorWorkflow to use google/gemini-2.5-flash and adjust related prompt/documentation text.

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 3 comments.

File	Description
packages/bubble-shared-schemas/src/coffee.ts	Updates Coffee agent’s default model constant.
packages/bubble-shared-schemas/src/bubbleflow-generation-prompts.ts	Updates shared recommended model constants used in instructions/config.
apps/bubblelab-api/src/services/ai/bubbleflow-generator.workflow.ts	Switches BubbleFlow generator agent model to `gemini-2.5-flash` and changes backup model.
apps/bubblelab-api/src/config/bubbleflow-generation-prompts.ts	Updates embedded prompt documentation/examples to reflect the new default model.

Copilot · 2026-02-06T19:40:47Z

apps/bubblelab-api/src/services/ai/bubbleflow-generator.workflow.ts

+            model: 'google/gemini-2.5-flash',
            temperature: 0.3,
            backupModel: {
-              model: 'anthropic/claude-sonnet-4-5',
+              model: 'google/gemini-2.5-flash-lite',
              temperature: 0.3,
            },


The generator agent’s backupModel was changed to another Google Gemini variant. If the primary model fails due to provider-wide issues or quota/rate limits, falling back to the same provider is unlikely to recover. Consider keeping a cross-provider backup (e.g., the previous Anthropic model) or making the backup configurable so fallback can still succeed when Gemini is unavailable.

Copilot · 2026-02-06T19:40:47Z

apps/bubblelab-api/src/config/bubbleflow-generation-prompts.ts

+// add date ranges, or filter by publication type. Currently using gemini-2.5-flash for thorough
+// multi-step research; current default is gemini-2.5-flash for balanced speed and cost.


The updated example comment repeats the same model name twice and still describes gemini-2.5-flash as being used for “thorough multi-step research”, which can be confusing for readers. Suggest rewriting this to state a single clear rationale for the chosen model (e.g., default/balanced) without repetition.

Suggested change

// add date ranges, or filter by publication type. Currently using gemini-2.5-flash for thorough

// multi-step research; current default is gemini-2.5-flash for balanced speed and cost.

// add date ranges, or filter by publication type. Uses gemini-2.5-flash as the default model for

// balanced speed and cost.

Copilot · 2026-02-06T19:40:47Z

apps/bubblelab-api/src/config/bubbleflow-generation-prompts.ts

+  task: \`Find research papers about \${ topic }...\`,
+  model: 'google/gemini-2.5-flash',


In the TypeScript example snippet, the template literal interpolation is written as \${ topic } instead of the usual \${topic} used elsewhere. Even though it’s in a documentation snippet, this odd formatting may confuse users—consider normalizing it.

Copilot AI review requested due to automatic review settings February 6, 2026 19:38

Copilot started reviewing on behalf of omsherikar February 6, 2026 19:38 View session

Copilot AI reviewed Feb 6, 2026

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

fix: switch default AI model to gemini-2.5-flash to avoid quota limits#288

fix: switch default AI model to gemini-2.5-flash to avoid quota limits#288
omsherikar wants to merge 1 commit intobubblelabai:mainfrom
omsherikar:fix/switch-default-model-to-gemini-2.5-flash

omsherikar commented Feb 6, 2026 •

edited by coderabbitai bot

Loading

Uh oh!

coderabbitai bot commented Feb 6, 2026 •

edited

Loading

Walkthrough

Changes

Estimated code review effort

Possibly related issues

Possibly related PRs

Poem

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Feb 6, 2026

Uh oh!

Copilot AI Feb 6, 2026

Uh oh!

Copilot AI Feb 6, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

		// add date ranges, or filter by publication type. Currently using gemini-2.5-flash for thorough
		// multi-step research; current default is gemini-2.5-flash for balanced speed and cost.

		task: \`Find research papers about \${ topic }...\`,
		model: 'google/gemini-2.5-flash',

Conversation

omsherikar commented Feb 6, 2026 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Related Issues

Type of Change

Checklist

Screenshots (Required)

For New Bubble Integrations

Additional Context

Summary by CodeRabbit

Uh oh!

coderabbitai bot commented Feb 6, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Possibly related issues

Possibly related PRs

Poem

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Feb 6, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 6, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 6, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

omsherikar commented Feb 6, 2026 •

edited by coderabbitai bot

Loading

coderabbitai bot commented Feb 6, 2026 •

edited

Loading