feat(models): add gpt-5.5 models

[waleedlatif1]

Summary

• Add GPT-5.5 and GPT-5.5 Pro to the OpenAI model catalog
• Include documented pricing, context windows, output limits, and capability flags

Type of Change

• Feature

Testing

Tested manually

Checklist

• Code follows project style guidelines
• Self-reviewed my changes
• Tests added/updated and passing
• No new warnings introduced
• I confirm that I have read and agree to the terms outlined in the Contributor License Agreement (CLA)

[vercel]

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

1 Skipped Deployment

Project	Deployment	Actions	Updated (UTC)
docs	Skipped		Apr 25, 2026 8:41am

[cursor]

PR Summary

Low Risk
Low risk: this is a catalog/configuration update that adds new model IDs and metadata plus a small test adjustment, with no changes to runtime logic or security-sensitive code paths.

Overview
Adds gpt-5.5 and gpt-5.5-pro to the OpenAI model catalog with pricing, context window, max output tokens, and capability flags (including structured outputs; gpt-5.5 also adds verbosity and becomes the new recommended GPT-5.* model).

Updates the model-capability tests to account for gpt-5.5-pro supporting reasoningEffort but not verbosity, and removes recommended from gpt-5.4 accordingly.

^{Reviewed by Cursor Bugbot for commit e56142f. Configure here.}

[greptile-apps]

Greptile Summary

This PR adds gpt-5.5-pro and gpt-5.5 to the OpenAI model catalog, correctly migrating the recommended flag from gpt-5.4, and updates the provider constants tests to reflect the new Pro-model exclusion pattern. The implementation is consistent with the existing GPT-5.x family conventions (capability flags, pricing shape, context windows).

Confidence Score: 5/5

Safe to merge — all changes are additive model catalog entries with no runtime logic touched.

No P0 or P1 findings. The only feedback is a P2 suggestion to add an explicit per-value test for gpt-5.5; the existing cross-model assertion already provides implicit coverage.

No files require special attention.

Important Files Changed

Filename	Overview
apps/sim/providers/models.ts	Adds gpt-5.5-pro and gpt-5.5 model entries following the established pattern; recommended flag correctly moved from gpt-5.4 to gpt-5.5; capabilities are consistent with the GPT-5.4 family convention.
apps/sim/providers/utils.test.ts	Updates the GPT-5 reasoning-effort/verbosity cross-check to exclude gpt-5.5-pro and adds explicit assertions for it; no explicit per-value tests added for gpt-5.5.

Flowchart

%%{init: {'theme': 'neutral'}}%%
flowchart TD
    A[PROVIDER_DEFINITIONS / openai] --> B[gpt-5.5-pro\nreasoning only, no verbosity\nrecommended: false]
    A --> C[gpt-5.5\nreasoning + verbosity\nrecommended: true]
    A --> D[gpt-5.4-pro\nreasoning only\nrecommended: false ← removed]
    A --> E[gpt-5.4\nreasoning + verbosity]
    A --> F[gpt-5.4-mini / nano\nreasoning + verbosity]

    style C fill:#d4edda,stroke:#28a745
    style D fill:#fff3cd,stroke:#ffc107

Loading

_{Reviews (2): Last reviewed commit: "fix(models): address gpt-5.5 review feed..." | Re-trigger Greptile}

[waleedlatif1]

@greptile

[waleedlatif1]

@cursor review

[cursor]

✅ Bugbot reviewed your changes and found no new issues!

Comment @cursor review or bugbot run to trigger another review on this PR

^{Reviewed by Cursor Bugbot for commit e56142f. Configure here.}