feat(lighthouse): filter out non-compatible OpenAI models

[Chan9390]

Context

OpenAI provides lot of non-compatible LLM models. For a model to work with Lighthouse it must support text input, text output and tool calls.

Description

This PR filters out non-compatible models at the Django task level. The filtering is based on the model names.

Steps to review

1. Add OpenAI key to Lighthouse
2. In the models section, you'll not find models that don't support text input, text output or tool calling (ex: tts-1, sora-2, etc)

Checklist

• Are there new checks included in this PR? Yes / No
  • If so, do we need to update permissions for the provider? Please review this carefully.
• Review if the code is being covered by tests.
• Review if code is being documented following this specification https://github.com/google/styleguide/blob/gh-pages/pyguide.md#38-comments-and-docstrings
• Review if backport is needed.
• Review if is needed to change the Readme.md
• Ensure new entries are added to CHANGELOG.md, if applicable.

UI

• All issue/task requirements work as expected on the UI
• Screenshots/Video of the functionality flow (if applicable) - Mobile (X < 640px)
• Screenshots/Video of the functionality flow (if applicable) - Table (640px > X < 1024px)
• Screenshots/Video of the functionality flow (if applicable) - Desktop (X > 1024px)
• Ensure new entries are added to CHANGELOG.md, if applicable.

API

• Verify if API specs need to be regenerated.
• Check if version updates are required (e.g., specs, Poetry, etc.).
• Ensure new entries are added to CHANGELOG.md, if applicable.

License

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.

[github-actions]

✅ All necessary CHANGELOG.md files have been updated.

[github-actions]

✅ Conflict Markers Resolved

All conflict markers have been successfully resolved in this pull request.

[github-actions]

🔒 Container Security Scan

Image: prowler-api:d9d8cf5
Last scan: 2025-12-15 09:34:58 UTC

📊 Vulnerability Summary

Severity	Count
🔴 Critical	4
Total	4

3 package(s) affected

⚠️ Action Required

Critical severity vulnerabilities detected. These should be addressed before merging:

• Review the detailed scan results
• Update affected packages to patched versions
• Consider using a different base image if updates are unavailable

---

📋 Resources:

• Download full report (see artifacts)
• View in Security tab
• Scanned with Trivy

[codecov]

Codecov Report

❌ Patch coverage is 18.18182% with 9 lines in your changes missing coverage. Please review.
✅ Project coverage is 92.43%. Comparing base (6158c16) to head (a377c35).
⚠️ Report is 5 commits behind head on master.

Additional details and impacted files

@@             Coverage Diff             @@
##           master    #9523       +/-   ##
===========================================
+ Coverage   43.35%   92.43%   +49.07%     
===========================================
  Files         832      159      -673     
  Lines       23490    22675      -815     
===========================================
+ Hits        10184    20959    +10775     
+ Misses      13306     1716    -11590     

Flag	Coverage Δ
api	92.43% <18.18%> (?)
prowler-py3.10-aws	?
prowler-py3.11-aws	?
prowler-py3.12-aws	?
prowler-py3.9-aws	?

Flags with carried forward coverage won't be shown. Click here to find out more.

Components	Coverage Δ
prowler	∅ <ø> (∅)
api	92.43% <18.18%> (∅)

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[josemazo]

When returning a dictionary with the key equals to the value instead of a list?

[Chan9390]

@josemazo OpenAI is the only provider that returns model ID and not model name. They take care of having shorter model ID. But comparing this to other providers (like Bedrock and OpenRouter, etc), they have model IDs that are not very straightforward (has versions, region info, etc) but have model names that can be displayed for the end user.

So because we use : dict for other providers, for OpenAI we just pass :.