Version Packages

[github-actions]

This PR was opened by the Changesets release GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated.

Releases

@browserbasehq/stagehand@3.3.1

Patch Changes

• #2047 a87c1fc Thanks @tkattkat! - Set default agent mode to hybrid with auto routing to dom for non compatible models

• #2065 9ff70dd Thanks @miguelg719! - Add support for CUA models: openai/gpt-5.4-mini, openai/gpt-5.5, and anthropic/claude-haiku-4-5

@browserbasehq/stagehand-evals@2.0.1

Patch Changes

• Updated dependencies [a87c1fc, 9ff70dd]:
  • @browserbasehq/stagehand@3.3.1

@browserbasehq/stagehand-server-v3@3.6.4

Patch Changes

• Updated dependencies [a87c1fc, 9ff70dd]:
  • @browserbasehq/stagehand@3.3.1

@browserbasehq/stagehand-server-v4@3.6.4

Patch Changes

• Updated dependencies [a87c1fc, 9ff70dd]:
  • @browserbasehq/stagehand@3.3.1

[cubic-dev-ai]

No issues found across 9 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 / Client
    participant Server as Stagehand Server (v3/v4)
    participant Core as Stagehand Core (v3.3.1)
    participant LLM as LLM Provider (OpenAI/Anthropic)

    Note over Client, LLM: Request Flow with New Model Support

    Client->>Server: Request browser action (params: model)
    
    alt Model Selection
        Server->>Core: CHANGED: Initialize with v3.3.1
        Note right of Core: NEW: Validates CUA models:<br/>openai/gpt-5.5, openai/gpt-5.4-mini,<br/>anthropic/claude-haiku-4-5
    end

    Core->>Core: Process browsing instructions

    Core->>LLM: NEW: API Request to specific CUA model
    
    alt Successful Inference
        LLM-->>Core: Model reasoning & action steps
        Core->>Core: Execute browser automation
        Core-->>Server: Result / Page State
        Server-->>Client: 200 OK (Response)
    else Model Error / Unsupported
        LLM-->>Core: Error (Rate limit / Invalid model)
        Core-->>Server: Execution Failure
        Server-->>Client: Error Response
    end

    Note over Core: Evals package (v1.1.12) runs against<br/>these models to verify performance.

Loading