fix(core): add gpt-5.5 to CUA model support

[BABTUNA]

why

openai/gpt-5.5 was missing from the CUA model allowlist/mapping, so CUA mode rejected it even though gpt-5.4 was already supported.

Closes #2041.

what changed

• Added gpt-5.5 -> openai in modelToAgentProviderMap
• Added openai/gpt-5.5 to AVAILABLE_CUA_MODELS
• Updated public API unit test expected CUA model list

test plan

• node node_modules/vitest/vitest.mjs run --config .tmp-vitest-public-api-config.mjs
  • tests/unit/public-api/llm-and-agents.test.ts
• npm.cmd exec prettier -- --write on touched files

---

Summary by cubic

Adds CUA support for openai/gpt-5.5, which was missing and caused the model to be rejected in CUA mode.
Maps gpt-5.5 to openai in modelToAgentProviderMap, adds it to AVAILABLE_CUA_MODELS, and updates the public API test.

^{Written for commit 05fac0b. Summary will update on new commits. Review in cubic}

[changeset-bot]

⚠️ No Changeset found

Latest commit: 05fac0b

Merging this PR will not cause a version bump for any packages. If these changes should not result in a new version, you're good to go. If these changes should result in a version bump, you need to add a changeset.

This PR includes no changesets

When changesets are added to this PR, you'll see the packages that this PR includes changesets for and the associated semver types

Click here to learn what changesets are, and how to add one.

Click here if you're a maintainer who wants to add a changeset to this PR

[github-actions]

This PR is from an external contributor and must be approved by a stagehand team member with write access before CI can run.
Approving the latest commit mirrors it into an internal PR owned by the approver.
If new commits are pushed later, the internal PR stays open but is marked stale until someone approves the latest external commit and refreshes it.

[cubic-dev-ai]

No issues found across 3 files

Confidence score: 5/5

• Automated review surfaced no issues in the provided summaries.
• No files require special attention.

Architecture diagram

sequenceDiagram
    participant Client as User / Public API
    participant Validator as Type Validator
    participant Registry as AgentProvider Registry
    participant Provider as OpenAI Provider
    participant LLM as OpenAI API

    Note over Client,LLM: Request flow for Model "openai/gpt-5.5"

    Client->>Validator: Initialize Agent(model: "openai/gpt-5.5")
    
    rect rgb(240, 240, 240)
        Note right of Validator: Validates against AVAILABLE_CUA_MODELS
        Validator->>Validator: NEW: Check "openai/gpt-5.5" inclusion
    end
    
    Validator-->>Client: Validation Success
    
    Client->>Registry: getProvider("gpt-5.5")
    
    rect rgb(240, 240, 240)
        Note right of Registry: Lookup in modelToAgentProviderMap
        Registry->>Registry: NEW: Map "gpt-5.5" to "openai"
    end
    
    Registry-->>Client: Return OpenAI Agent Provider
    
    Client->>Provider: performTask(instruction)
    Provider->>LLM: POST /chat/completions (model: "gpt-5.5")
    
    alt Success
        LLM-->>Provider: Tool Call / Response
        Provider-->>Client: Task Result
    else Unsupported Model Error
        Note over LLM,Provider: Error if model is not yet active in API
        LLM-->>Provider: 404/400 Error
        Provider-->>Client: Provider Error
    end

Loading