Skip to content

Conversation

@miguelg719
Copy link
Collaborator

@miguelg719 miguelg719 commented Dec 23, 2025

why

This setting improves the performance of gemini 3 models for computer use applications (recommended by Deepmind)

what changed

Added a providerOption to google models (specifically filtered by gemini-3) to include MEDIA_RESOLUTION_HIGH (nit: ULTRA_HIGH not supported by aisdk yet)

test plan


Summary by cubic

Set the Google provider option mediaResolution to MEDIA_RESOLUTION_HIGH for Gemini 3 models in the hybrid agent to improve computer-use performance.
Applied conditionally when the modelId includes "gemini-3" for both step execution and streaming paths.

Written for commit 5e00581. Summary will update automatically on new commits.

@changeset-bot
Copy link

changeset-bot bot commented Dec 23, 2025

🦋 Changeset detected

Latest commit: 5e00581

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 3 packages
Name Type
@browserbasehq/stagehand Patch
@browserbasehq/stagehand-evals Patch
@browserbasehq/stagehand-server Patch

Not sure what this means? Click here to learn what changesets are.

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

@miguelg719 miguelg719 marked this pull request as ready for review December 23, 2025 15:29
Copy link
Contributor

@cubic-dev-ai cubic-dev-ai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No issues found across 2 files

@greptile-apps
Copy link
Contributor

greptile-apps bot commented Dec 23, 2025

Greptile Summary

Added providerOptions to both execute() and stream() methods in V3AgentHandler to include MEDIA_RESOLUTION_HIGH for Google Gemini models, following Deepmind's recommendation for computer use applications.

Critical Issue Found:

  • The condition wrappedModel.modelId.includes("gemini-3") doesn't match any existing Gemini models in the codebase (all are gemini-1.5-x, gemini-2.0-x, or gemini-2.5-x), so this feature will never activate

Changes:

  • Added conditional providerOptions for both generateText (line 276) and streamText (line 417) calls
  • Updated changeset file to document the patch

Confidence Score: 1/5

  • This PR contains a critical logic error that prevents the intended functionality from working
  • The string match condition includes("gemini-3") will never match any existing Gemini models in the codebase (gemini-1.5, gemini-2.0, gemini-2.5), making this change completely non-functional. The PR description mentions improving Gemini 3 models, but no Gemini 3 models exist in the codebase.
  • packages/core/lib/v3/handlers/v3AgentHandler.ts requires immediate attention - both occurrences of the model check need to be corrected

Important Files Changed

Filename Overview
packages/core/lib/v3/handlers/v3AgentHandler.ts Adds providerOptions with media resolution for Gemini models, but the condition wrappedModel.modelId.includes("gemini-3") doesn't match any existing Gemini models (1.5, 2.0, 2.5)
.changeset/quiet-needles-fetch.md Standard changeset file for patch release, properly formatted

Sequence Diagram

sequenceDiagram
    participant Client
    participant V3AgentHandler
    participant LLMClient
    participant GoogleAPI

    Client->>V3AgentHandler: execute() or stream()
    V3AgentHandler->>V3AgentHandler: prepareAgent()
    V3AgentHandler->>LLMClient: getLanguageModel()
    LLMClient-->>V3AgentHandler: wrappedModel
    V3AgentHandler->>V3AgentHandler: Check modelId.includes("gemini-3")
    
    alt Model is gemini-3
        V3AgentHandler->>LLMClient: generateText/streamText with providerOptions
        Note over V3AgentHandler,LLMClient: providerOptions: { google: { mediaResolution: "MEDIA_RESOLUTION_HIGH" } }
        LLMClient->>GoogleAPI: Request with MEDIA_RESOLUTION_HIGH
        GoogleAPI-->>LLMClient: Response
    else Model is not gemini-3
        V3AgentHandler->>LLMClient: generateText/streamText without providerOptions
        LLMClient->>GoogleAPI: Standard request
        GoogleAPI-->>LLMClient: Response
    end
    
    LLMClient-->>V3AgentHandler: Result
    V3AgentHandler-->>Client: AgentResult/AgentStreamResult
Loading

Copy link
Contributor

@greptile-apps greptile-apps bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

1 file reviewed, 2 comments

Edit Code Review Agent Settings | Greptile

@miguelg719 miguelg719 merged commit 51e0170 into main Dec 23, 2025
28 checks passed
miguelg719 pushed a commit that referenced this pull request Dec 27, 2025
This PR was opened by the [Changesets
release](https://github.com/changesets/action) 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/[email protected]

### Patch Changes

- [#1461](#1461)
[`0f3991e`](0f3991e)
Thanks [@tkattkat](https://github.com/tkattkat)! - Move hybrid mode out
of experimental

- [#1433](#1433)
[`e0e22e0`](e0e22e0)
Thanks [@tkattkat](https://github.com/tkattkat)! - Put hybrid mode
behind experimental

- [#1456](#1456)
[`f261051`](f261051)
Thanks [@shrey150](https://github.com/shrey150)! - Invoke page.hover for
agent move action

- [#1473](#1473)
[`e021674`](e021674)
Thanks [@shrey150](https://github.com/shrey150)! - Add safety
confirmation support for OpenAI + Google CUA

- [#1399](#1399)
[`6a5496f`](6a5496f)
Thanks [@tkattkat](https://github.com/tkattkat)! - Ensure cua agent is
killed when stagehand.close is called

- [#1436](#1436)
[`fea1700`](fea1700)
Thanks [@miguelg719](https://github.com/miguelg719)! - Fix auto-load key
for act/extract/observe parametrized models on api

- [#1439](#1439)
[`5b288d9`](5b288d9)
Thanks [@tkattkat](https://github.com/tkattkat)! - Remove base64 from
agent actions array ( still present in messages object )

- [#1408](#1408)
[`e822f5a`](e822f5a)
Thanks [@seanmcguire12](https://github.com/seanmcguire12)! - allow for
act() cache hit when variable values change

- [#1472](#1472)
[`638efc7`](638efc7)
Thanks [@seanmcguire12](https://github.com/seanmcguire12)! - fix: agent
cache not refreshed on action failure

- [#1424](#1424)
[`a890f16`](a890f16)
Thanks [@seanmcguire12](https://github.com/seanmcguire12)! - fix:
"Error: -32000 Failed to convert response to JSON: CBOR: stack limit
exceeded"

- [#1418](#1418)
[`934f492`](934f492)
Thanks [@miguelg719](https://github.com/miguelg719)! - Cleanup handlers
and bus listeners on close

- [#1430](#1430)
[`bd2db92`](bd2db92)
Thanks [@shrey150](https://github.com/shrey150)! - Fix CUA model
coordinate translation

- [#1465](#1465)
[`51e0170`](51e0170)
Thanks [@miguelg719](https://github.com/miguelg719)! - Add media
resolution high provider option to gemini 3 hybrid agent

- [#1431](#1431)
[`05f5580`](05f5580)
Thanks [@tkattkat](https://github.com/tkattkat)! - Update the cache
handling for agent

- [#1432](#1432)
[`f56a9c2`](f56a9c2)
Thanks [@tkattkat](https://github.com/tkattkat)! - Deprecate cua: true
in favor of mode: "cua"

- [#1406](#1406)
[`b40ae11`](b40ae11)
Thanks [@tkattkat](https://github.com/tkattkat)! - Add support for
hovering with coordinates ( page.hover )

- [#1407](#1407)
[`0d2b398`](0d2b398)
Thanks [@tkattkat](https://github.com/tkattkat)! - Clean up page methods

- [#1412](#1412)
[`cd01f29`](cd01f29)
Thanks [@seanmcguire12](https://github.com/seanmcguire12)! - fix: load
GOOGLE_API_KEY from .env

- [#1462](#1462)
[`a734fca`](a734fca)
Thanks [@shrey150](https://github.com/shrey150)! - fix: correctly pass
userDataDir to chrome launcher

- [#1466](#1466)
[`b342acf`](b342acf)
Thanks [@seanmcguire12](https://github.com/seanmcguire12)! - move
playwright to optional dependencies

- [#1440](#1440)
[`2987cd1`](2987cd1)
Thanks [@tkattkat](https://github.com/tkattkat)! - [Feature] support
excluding tools from agent

- [#1455](#1455)
[`dfab1d5`](dfab1d5)
Thanks [@seanmcguire12](https://github.com/seanmcguire12)! - update
aisdk client to better enforce structured output with deepseek models

- [#1428](#1428)
[`4d71162`](4d71162)
Thanks [@tkattkat](https://github.com/tkattkat)! - Add "hybrid" mode to
stagehand agent

## @browserbasehq/[email protected]

### Minor Changes

- [#1459](#1459)
[`abb3469`](abb3469)
Thanks [@monadoid](https://github.com/monadoid)! - Added building of
binaries

- [#1457](#1457)
[`5fc1281`](5fc1281)
Thanks [@monadoid](https://github.com/monadoid)! - First changeset for
stagehand-server

- [#1469](#1469)
[`d634d45`](d634d45)
Thanks [@monadoid](https://github.com/monadoid)! - Bump to test binary
builds

### Patch Changes

- Updated dependencies
\[[`0f3991e`](0f3991e),
[`e0e22e0`](e0e22e0),
[`f261051`](f261051),
[`e021674`](e021674),
[`6a5496f`](6a5496f),
[`fea1700`](fea1700),
[`5b288d9`](5b288d9),
[`e822f5a`](e822f5a),
[`638efc7`](638efc7),
[`a890f16`](a890f16),
[`934f492`](934f492),
[`bd2db92`](bd2db92),
[`51e0170`](51e0170),
[`05f5580`](05f5580),
[`f56a9c2`](f56a9c2),
[`b40ae11`](b40ae11),
[`0d2b398`](0d2b398),
[`cd01f29`](cd01f29),
[`a734fca`](a734fca),
[`b342acf`](b342acf),
[`2987cd1`](2987cd1),
[`dfab1d5`](dfab1d5),
[`4d71162`](4d71162)]:
    -   @browserbasehq/[email protected]

## @browserbasehq/[email protected]

### Patch Changes

- [#1373](#1373)
[`cadd192`](cadd192)
Thanks [@tkattkat](https://github.com/tkattkat)! - Update screenshot
collector in agent evals cli

- Updated dependencies
\[[`0f3991e`](0f3991e),
[`e0e22e0`](e0e22e0),
[`f261051`](f261051),
[`e021674`](e021674),
[`6a5496f`](6a5496f),
[`fea1700`](fea1700),
[`5b288d9`](5b288d9),
[`e822f5a`](e822f5a),
[`638efc7`](638efc7),
[`a890f16`](a890f16),
[`934f492`](934f492),
[`bd2db92`](bd2db92),
[`51e0170`](51e0170),
[`05f5580`](05f5580),
[`f56a9c2`](f56a9c2),
[`b40ae11`](b40ae11),
[`0d2b398`](0d2b398),
[`cd01f29`](cd01f29),
[`a734fca`](a734fca),
[`b342acf`](b342acf),
[`2987cd1`](2987cd1),
[`dfab1d5`](dfab1d5),
[`4d71162`](4d71162)]:
    -   @browserbasehq/[email protected]

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants