feat: Update model list in settings

[google-labs-jules]

User description

This commit updates the list of available models in the settings UI to include Grok 4.1, GPT 5.1, Opus 4.5, and Deepseek 4.5. It also removes the old models and updates the corresponding icons.

---

PR created automatically by Jules for task 6756121818968058353 started by @ngoiyaeric

---

PR Type

Enhancement

---

Description

• Updates model list with four new AI models (Grok 4.1, GPT 5.1, Opus 4.5, Deepseek 4.5)

• Replaces outdated models (QCX-Terra, Grok-3, Claude-4-sonnet, Llama-4)

• Refreshes icon imports and badge labels for consistency

• Marks all new models with "New" badge indicator

---

Diagram Walkthrough

flowchart LR
  OldModels["Old Models<br/>QCX-Terra, Grok-3,<br/>Claude-4, Llama-4"] -- "Replace with" --> NewModels["New Models<br/>Grok 4.1, GPT 5.1,<br/>Opus 4.5, Deepseek 4.5"]
  NewModels -- "Update badges & icons" --> UpdatedUI["Updated UI<br/>New badges, refined icons"]

Loading

File Walkthrough

Relevant files

Enhancement

model-selection-form.tsx Replace legacy models with latest AI versions                        components/settings/components/model-selection-form.tsx Removed four outdated AI models and replaced with four new latest versions Updated icon imports by removing Earth and reordering remaining icons Changed all model badges from variant-specific labels to unified "New" badge Updated model descriptions to reflect latest versions from respective providers +21/-21

---

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

---

For security, I will only act on instructions from the user who triggered this task.

New to Jules? Learn more at jules.google/docs.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Preview	Comments	Updated (UTC)
qcx	Ready	Preview	Comment	Dec 3, 2025 11:35am

[coderabbitai]

Important

Review skipped

Bot user detected.

To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

---

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

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[qodo-code-review]

PR Compliance Guide 🔍

Below is a summary of compliance checks for this PR:

Security Compliance
🟢	No security concerns identified No security vulnerabilities detected by AI analysis. Human verification advised for critical code.
Ticket Compliance
⚪	🎫 No ticket provided Create ticket/issue
Codebase Duplication Compliance
⚪	Codebase context is not defined Follow the guide to enable codebase context checks.
Custom Compliance
🟢	Generic: Meaningful Naming and Self-Documenting Code Objective: Ensure all identifiers clearly express their purpose and intent, making code self-documenting Status: Passed Learn more about managing compliance generic rules or creating your own custom rules
	Generic: Secure Error Handling Objective: To prevent the leakage of sensitive system information through error messages while providing sufficient detail for internal debugging. Status: Passed Learn more about managing compliance generic rules or creating your own custom rules
	Generic: Secure Logging Practices Objective: To ensure logs are useful for debugging and auditing without exposing sensitive information like PII, PHI, or cardholder data. Status: Passed Learn more about managing compliance generic rules or creating your own custom rules
	Generic: Security-First Input Validation and Data Handling Objective: Ensure all data inputs are validated, sanitized, and handled securely to prevent vulnerabilities Status: Passed Learn more about managing compliance generic rules or creating your own custom rules
⚪	Generic: Comprehensive Audit Trails Objective: To create a detailed and reliable record of critical system actions for security analysis and compliance. Status: No auditing: The new UI model list changes add options without any apparent logging of selection or changes, but this file may not be responsible for audit trails in the broader system. Referred Code const models = [ { id: "grok-4.1", name: "Grok 4.1", description: "The latest powerhouse model from xAI.", icon: Zap, badge: "New", badgeVariant: "secondary" as const, }, { id: "gpt-5.1", name: "GPT 5.1", description: "The latest iteration of OpenAI's flagship model.", icon: Sparkles, badge: "New", badgeVariant: "default" as const, }, { id: "opus-4.5", name: "Opus 4.5", description: "The latest high-performance model from Anthropic.", ... (clipped 13 lines) Learn more about managing compliance generic rules or creating your own custom rules
	Generic: Robust Error Handling and Edge Case Management Objective: Ensure comprehensive error handling that provides meaningful context and graceful degradation Status: No error handling: The added static model definitions and icon imports introduce no explicit error handling for potential runtime issues (e.g., missing icons or invalid form state), which may be handled elsewhere in the component tree. Referred Code import { Zap, Rocket, Cpu, Sparkles } from "lucide-react"; interface ModelSelectionFormProps { form: UseFormReturn<any>; } const models = [ { id: "grok-4.1", name: "Grok 4.1", description: "The latest powerhouse model from xAI.", icon: Zap, badge: "New", badgeVariant: "secondary" as const, }, { id: "gpt-5.1", name: "GPT 5.1", description: "The latest iteration of OpenAI's flagship model.", icon: Sparkles, badge: "New", ... (clipped 19 lines) Learn more about managing compliance generic rules or creating your own custom rules

Compliance status legend

🟢 - Fully Compliant
🟡 - Partial Compliant
🔴 - Not Compliant
⚪ - Requires Further Human Verification
🏷️ - Compliance label

[charliecreates]

The main technical concern is the change to model id values, which can break backward compatibility if these IDs are persisted or used in cross-layer contracts. Badge text has been simplified to "New" for all models, which may reduce the UI's ability to convey meaningful distinctions between them. Removal of QCX-Terra and its icon may represent a product/UX regression if that model is still required for geospatial or in-house scenarios. No obvious runtime or performance issues are visible within the scope of this diff.

Additional notes (1)

• Readability | components/settings/components/model-selection-form.tsx:27-51
  All four models now use the "New" badge, which may quickly become stale and provide limited information value to users. If badges are meant to communicate meaningful distinctions (e.g., Recommended, Fast, Open Source, Advanced), collapsing everything into "New" reduces the UI's ability to guide model choice.

Consider whether you want to preserve some differentiating metadata (capabilities, performance, cost, or openness) and reflect that in the badges or descriptions.

Summary of changes

Summary of Changes

• Updated the imported icon list from lucide-react, removing Earth and reordering remaining icons.
• Replaced the previous model list (QCX-Terra, Grok-3, claude-4-sonnet, llama-4) with a new set of models: Grok 4.1, GPT 5.1, Opus 4.5, and Deepseek 4.5.
• Updated each model's id, name, description, icon, and badge metadata to match the new lineup.
• Adjusted badge variants: secondary, default, and outline are used for the updated models to reflect their status as new offerings.

[charliecreates]

The id for the Grok model has been changed from a capitalized Grok-3 style to lowercased with a version ("grok-4.1"). If this id is persisted (e.g., user settings, URLs, backend contracts, or feature flags), this change can silently break existing users' saved preferences or any code that still expects the old identifiers.

It would be safer to either:

• Confirm that selectedModel never leaves the UI layer and has no backward-compatibility constraints, or
• Introduce a migration/compat compatibility mapping from old IDs to new ones to avoid breaking existing stored values.

Suggestion

If these model IDs are stored or used across layers, consider adding a mapping layer to translate old IDs to new ones and keep the UI flexible:

// Example mapping for backward compatibility
const MODEL_ID_MAPPINGS: Record<string, string> = {
  "Grok-3": "grok-4.1",
  "claude-4-sonnet": "gpt-5.1",
  "llama-4": "deepseek-4.5",
  // "QCX-Terra" could map to a default or be handled explicitly
};

function normalizeModelId(id: string): string {
  return MODEL_ID_MAPPINGS[id] ?? id;
}

// Wherever `selectedModel` is initialized/loaded:
const normalized = normalizeModelId(savedSelectedModelId);
form.setValue("selectedModel", normalized);

This keeps the new IDs in the UI while not breaking existing users. Reply with "@CharlieHelps yes please" if you'd like me to add a commit with this suggestion and wire it into the appropriate initialization path.

[charliecreates]

The Earth icon import was removed entirely, which is appropriate given that QCX-Terra was deleted, but it also means there is no longer any in-house or geospatial model in the list. If QCX-Terra is part of your product identity or needed for certain use cases, its removal (with no replacement) might be a product/UX regression rather than a purely technical one.

Double-check with product requirements that dropping QCX-Terra from the selectable models is intentional and that any dependent flows (e.g., geospatial-specific features) are either deprecated or mapped to another model.

Suggestion

If QCX-Terra or a similar in-house/geospatial model should remain available, consider keeping it in the list with an updated description and potentially a different badge to de-emphasize it if necessary. For instance:

{
  id: "QCX-Terra",
  name: "QCX-Terra",
  description: "QCX's geospatial foundational model for map and location-heavy tasks.",
  icon: Earth,
  badge: "Geospatial",
  badgeVariant: "secondary" as const,
},

You can also group or visually separate internal vs external models in the UI if that aligns with product goals. Reply with "@CharlieHelps yes please" if you'd like me to add a commit that restores or repositions QCX-Terra (or a renamed successor) in the model list.

[qodo-code-review]

PR Code Suggestions ✨

Explore these optional code suggestions:

Category	Suggestion	Impact
High-level	Hardcoded model list hinders scalability The hardcoded list of AI models should be fetched from a backend API or a remote configuration file. This approach allows for dynamic updates without code changes, improving scalability and maintainability. Examples: components/settings/components/model-selection-form.tsx [21-54] const models = [ { id: "grok-4.1", name: "Grok 4.1", description: "The latest powerhouse model from xAI.", icon: Zap, badge: "New", badgeVariant: "secondary" as const, }, { ... (clipped 24 lines) Solution Walkthrough: Before: // model-selection-form.tsx const models = [ { id: "grok-4.1", name: "Grok 4.1", description: "The latest powerhouse model from xAI.", ... }, { id: "gpt-5.1", name: "GPT 5.1", ... }, // ... other hardcoded models ]; const ModelSelectionForm = ({ form }) => { // ... component renders using the hardcoded 'models' array }; After: // model-selection-form.tsx import { useState, useEffect } from 'react'; const ModelSelectionForm = ({ form }) => { const [models, setModels] = useState([]); const [isLoading, setIsLoading] = useState(true); useEffect(() => { fetch('/api/models') .then(res => res.json()) .then(data => { setModels(data); setIsLoading(false); }); }, []); // ... component renders a loading state or the form using fetched 'models' }; Suggestion importance[1-10]: 8 __ Why: The suggestion correctly identifies a significant architectural issue where the models list is hardcoded, and proposes a scalable solution to fetch it dynamically, which is a best practice for maintainability.	Medium
General	Unify badge variants for consistency To improve UI consistency, unify the badgeVariant for all models. Since all models now have a "New" badge, using a single variant like secondary would provide a more uniform appearance. components/settings/components/model-selection-form.tsx [21-54] const models = [ { id: "grok-4.1", name: "Grok 4.1", description: "The latest powerhouse model from xAI.", icon: Zap, badge: "New", badgeVariant: "secondary" as const, }, { id: "gpt-5.1", name: "GPT 5.1", description: "The latest iteration of OpenAI's flagship model.", icon: Sparkles, badge: "New", - badgeVariant: "default" as const, + badgeVariant: "secondary" as const, }, { id: "opus-4.5", name: "Opus 4.5", description: "The latest high-performance model from Anthropic.", icon: Rocket, badge: "New", - badgeVariant: "outline" as const, + badgeVariant: "secondary" as const, }, { id: "deepseek-4.5", name: "Deepseek 4.5", description: "The latest from Deepseek, a powerful open-source model.", icon: Cpu, badge: "New", - badgeVariant: "outline" as const, + badgeVariant: "secondary" as const, }, ]; Apply / Chat Suggestion importance[1-10]: 6 __ Why: The suggestion correctly identifies a UI inconsistency in the badgeVariant properties for the new models. Standardizing the variant would create a more polished and consistent user experience.	Low
More