Add Qwen3-VL 30B vision model support by AnthonyRonning · Pull Request #310 · OpenSecretCloud/Maple

AnthonyRonning · 2025-11-18T17:23:59Z

Adds support for the new Qwen3-VL 30B vision-language model with 256K context.

Changes:

Added qwen3-vl-30b model configuration to ModelSelector
- 256K token context limit (highest among vision models)
- Vision support enabled
- Pro plan requirement
- "New" badge
Updated UpgradePromptDialog to mention Qwen3-VL alongside Gemma 3
Updated pricingConfig to show both vision models in Starter plan features

Model Details:

A 30B-parameter vision-language model that understands images and videos
Excels at visual tasks including GUI interaction, generating code from screenshots, spatial understanding, video analysis, and OCR across 32 languages
Supports up to 256K context for processing long videos and documents

Note: Gemma 3 27B remains the default image analysis model. Qwen3-VL is available in the advanced model list for Pro users.

Summary by CodeRabbit

New Features
- Added Qwen3‑VL 30B model with advanced vision support and 256,000 token capacity.
UI Copy
- Upgrade prompt now lists Qwen3‑VL alongside other advanced vision models.
Display
- Improved pricing/plan display formatting for Gemini-related entry to ensure clearer presentation.

coderabbitai · 2025-11-18T17:24:09Z

Walkthrough

Adds a new model entry qwen3-vl-30b to the frontend model configuration, updates Image Upload UI copy to mention Qwen3-VL, and reformats a Starter plan pricing object in pricingConfig (no control-flow or runtime logic changes).

Changes

Cohort / File(s)	Summary
Model configuration `frontend/src/components/ModelSelector.tsx`	Adds `qwen3-vl-30b` to `MODEL_CONFIG` with displayName "Qwen3-VL 30B", shortName "Qwen3-VL", badges `["Pro","New"]`, `requiresPro: true`, `supportsVision: true`, and `tokenLimit: 256000`.
Pricing formatting `frontend/src/config/pricingConfig.tsx`	Reformats the Starter plan's Gemini entry into a multi-line object (no semantic change to data).
UI copy `frontend/src/components/UpgradePromptDialog.tsx`	Updates Image Upload benefits text to mention "and Qwen3-VL" alongside "Gemma 3".

Sequence Diagram(s)

No sequence diagram required — changes are configuration and copy only.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Check MODEL_CONFIG entry shape and consistency with nearby model entries.
Verify requiresPro, supportsVision, badges, and tokenLimit values match product intent.
Confirm the pricing object reformat did not introduce trailing commas or lint issues.
Confirm UI copy change is accurate and localized if applicable.

Possibly related PRs

feat: add Qwen3 Coder 480B model with 128K context #214 — Adds Qwen3 model entries and updates pricing UI; likely touches the same model/pricing UI areas.
feat: add Mistral Small 3.1 24B and Qwen 2.5 72B models for Pro/Team … #142 — Previously modified MODEL_CONFIG and pricing entries; similar code-level changes.
Handle unknown models #104 — Refactors MODEL_CONFIG and display handling; related to adding model metadata and badges.

Poem

🐰 A new model hops into view tonight,
Qwen3-VL joins Gemma in the light,
Badges gleam Pro and New so bright,
Tokens abundant for long prompt flight,
I nibble code and dance with delight.

Pre-merge checks and finishing touches

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	You can run `@coderabbitai generate docstrings` to improve docstring coverage.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately and concisely describes the main change: adding Qwen3-VL 30B vision model support, which is reflected across all three modified files.

✨ Finishing touches

📝 Generate docstrings

🧪 Generate unit tests (beta)

Create PR with unit tests
Post copyable unit tests in a comment
Commit unit tests in branch add-qwen3-vl-30b

📜 Recent review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 1e8b5ad and 679fc7c.

📒 Files selected for processing (3)

frontend/src/components/ModelSelector.tsx (1 hunks)
frontend/src/components/UpgradePromptDialog.tsx (1 hunks)
frontend/src/config/pricingConfig.tsx (1 hunks)

🚧 Files skipped from review as they are similar to previous changes (2)

frontend/src/components/ModelSelector.tsx
frontend/src/components/UpgradePromptDialog.tsx

🧰 Additional context used

📓 Path-based instructions (2)

**/*.{ts,tsx,js,jsx}

📄 CodeRabbit inference engine (CLAUDE.md)

**/*.{ts,tsx,js,jsx}: Use 2-space indentation, double quotes, and a 100-character line limit for formatting
Use camelCase for variable and function names
Use try/catch with specific error types for error handling

Files:

frontend/src/config/pricingConfig.tsx

**/*.{ts,tsx}

📄 CodeRabbit inference engine (CLAUDE.md)

Use strict TypeScript typing and avoid any when possible

Files:

frontend/src/config/pricingConfig.tsx

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (5)

GitHub Check: build-linux
GitHub Check: build-android
GitHub Check: build-macos (universal-apple-darwin)
GitHub Check: build-ios
GitHub Check: Cloudflare Pages

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

greptile-apps · 2025-11-18T17:26:43Z

Greptile Summary

Adds Qwen3-VL 30B vision model with 256K context support for Pro users
Updates UI references to mention both Gemma 3 and Qwen3-VL as available vision models

Confidence Score: 5/5

This PR is safe to merge with no issues.
Clean addition of a new model configuration with proper access controls, token limits, and vision support flags. All changes are consistent and follow existing patterns.
No files require special attention.

Important Files Changed

Filename	Overview
frontend/src/components/ModelSelector.tsx	Added Qwen3-VL 30B model configuration with Pro plan requirement, 256K token limit, and vision support

Sequence Diagram

sequenceDiagram
participant User
participant ModelSelector
participant MODEL_CONFIG
participant UpgradeDialog
User->>ModelSelector: "Select Qwen3-VL model"
ModelSelector->>MODEL_CONFIG: "Check model configuration"
MODEL_CONFIG-->>ModelSelector: "requiresPro: true, supportsVision: true, tokenLimit: 256000"
ModelSelector->>ModelSelector: "Check hasAccessToModel()"
alt User has Pro plan
ModelSelector->>ModelSelector: "setModel('qwen3-vl-30b')"
ModelSelector-->>User: "Model selected successfully"
else User does not have Pro plan
ModelSelector->>UpgradeDialog: "Open with modelName='Qwen3-VL 30B'"
UpgradeDialog-->>User: "Show upgrade prompt with benefits"
end

greptile-apps

_{3 files reviewed, no comments}

_{Edit Code Review Agent Settings | Greptile}
_{React with 👍 or 👎 to share your feedback on this new summary format}

coderabbitai

Actionable comments posted: 3

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 3a5cbcf and 1e8b5ad.

📒 Files selected for processing (3)

frontend/src/components/ModelSelector.tsx (1 hunks)
frontend/src/components/UpgradePromptDialog.tsx (1 hunks)
frontend/src/config/pricingConfig.tsx (1 hunks)

🧰 Additional context used

📓 Path-based instructions (2)

**/*.{ts,tsx,js,jsx}

📄 CodeRabbit inference engine (CLAUDE.md)

**/*.{ts,tsx,js,jsx}: Use 2-space indentation, double quotes, and a 100-character line limit for formatting
Use camelCase for variable and function names
Use try/catch with specific error types for error handling

Files:

frontend/src/components/UpgradePromptDialog.tsx
frontend/src/components/ModelSelector.tsx
frontend/src/config/pricingConfig.tsx

**/*.{ts,tsx}

📄 CodeRabbit inference engine (CLAUDE.md)

Use strict TypeScript typing and avoid any when possible

Files:

frontend/src/components/UpgradePromptDialog.tsx
frontend/src/components/ModelSelector.tsx
frontend/src/config/pricingConfig.tsx

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (5)

GitHub Check: build-ios
GitHub Check: build-macos (universal-apple-darwin)
GitHub Check: build-linux
GitHub Check: build-android
GitHub Check: Cloudflare Pages

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

cloudflare-workers-and-pages · 2025-11-18T17:29:24Z

Deploying maple with Cloudflare Pages

Latest commit:	`679fc7c`
Status:	✅ Deploy successful!
Preview URL:	https://80bd98cc.maple-ca8.pages.dev
Branch Preview URL:	https://add-qwen3-vl-30b.maple-ca8.pages.dev

View logs

greptile-apps

_{3 files reviewed, no comments}

_{Edit Code Review Agent Settings | Greptile}
_{React with 👍 or 👎 to share your feedback on this new summary format}

greptile-appsBot reviewed Nov 18, 2025
View reviewed changes

coderabbitaiBot reviewed Nov 18, 2025
View reviewed changes

Comment threadfrontend/src/components/ModelSelector.tsx
Comment threadfrontend/src/components/UpgradePromptDialog.tsx
Comment threadfrontend/src/config/pricingConfig.tsx

Add Qwen3-VL 30B vision model support
679fc7c
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

AnthonyRonning force-pushed the add-qwen3-vl-30b branch from 1e8b5ad to 679fc7cCompare November 18, 2025 17:29

greptile-appsBot reviewed Nov 18, 2025
View reviewed changes

AnthonyRonning merged commit 05c16c4 into masterNov 19, 2025
8 checks passed

AnthonyRonning deleted the add-qwen3-vl-30b branch November 19, 2025 17:46

coderabbitaiBot mentioned this pull request Dec 10, 2025
Upgrade vision model to Qwen3-VL 30B #342
Merged

coderabbitaiBot mentioned this pull request Dec 19, 2025
Add Kimi K2 Thinking model and re-enable brain toggle #346
Merged

Navigation Menu

Uh oh!

Add Qwen3-VL 30B vision model support - #310

Add Qwen3-VL 30B vision model support#310
AnthonyRonning merged 1 commit into
masterfrom
add-qwen3-vl-30b

AnthonyRonning commented Nov 18, 2025•
edited by coderabbitai Bot
Loading

Uh oh!

coderabbitaiBot commented Nov 18, 2025•
edited
Loading

Uh oh!

greptile-appsBot commented Nov 18, 2025•
edited
Loading

Uh oh!

greptile-appsBot left a comment

Uh oh!

coderabbitaiBot left a comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

cloudflare-workers-and-pagesBot commented Nov 18, 2025•
edited
Loading

Uh oh!

greptile-appsBot left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

AnthonyRonning commented Nov 18, 2025• edited by coderabbitai BotLoading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Uh oh!

coderabbitaiBot commented Nov 18, 2025• edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Sequence Diagram(s)

Estimated code review effort

Possibly related PRs

Poem

Pre-merge checks and finishing touches

Uh oh!

greptile-appsBot commented Nov 18, 2025• edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Greptile Summary

Confidence Score: 5/5

Important Files Changed

Sequence Diagram

Uh oh!

greptile-appsBot left a comment

Choose a reason for hiding this comment

Uh oh!

coderabbitaiBot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

cloudflare-workers-and-pagesBot commented Nov 18, 2025• edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Deploying maple with Cloudflare Pages

Uh oh!

greptile-appsBot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

AnthonyRonning commented Nov 18, 2025•
edited by coderabbitai Bot
Loading

coderabbitaiBot commented Nov 18, 2025•
edited
Loading

greptile-appsBot commented Nov 18, 2025•
edited
Loading

cloudflare-workers-and-pagesBot commented Nov 18, 2025•
edited
Loading