Skip to content

Add gemini-3.8-flash to Gemini CUA, HyperAgent, and Browser Use LLM types - #120

Merged
NikhilShahi merged 1 commit into
mainfrom
devin/1788398018-gemini-3-8-flash
Sep 3, 2026
Merged

Add gemini-3.8-flash to Gemini CUA, HyperAgent, and Browser Use LLM types#120
NikhilShahi merged 1 commit into
mainfrom
devin/1788398018-gemini-3-8-flash

Conversation

@shrisukhani

@shrisukhani shrisukhani commented Sep 3, 2026

Copy link
Copy Markdown
Contributor

Summary

Adds "gemini-3.8-flash" to GeminiComputerUseLlm, HyperAgentLlm, and BrowserUseLlm literals. Server support: hyperbrowserai/browserctrl#1385 (it is now the server-side default for Gemini Computer Use).

Changes

  • hyperbrowser/models/consts.py: new "gemini-3.8-flash" entry in the three LLM Literals.

Validation

  • Syntax-checked; ruff not installed in this environment (constants-only change).

Link to Devin session: https://app.devin.ai/sessions/7dccc05e05b04c63bd5760859b161275
Open in Devin Desktop: https://app.devin.ai/desktop/session/7dccc05e05b04c63bd5760859b161275?variant=devin
Requested by: @shrisukhani


Note

Low Risk
Constants-only expansion of allowed model strings; no runtime logic changes.

Overview
Adds gemini-3.8-flash to three LLM Literal types in hyperbrowser/models/consts.py: BrowserUseLlm, HyperAgentLlm, and GeminiComputerUseLlm.

This lets the Python SDK accept and type-check that model id on Browser Use, HyperAgent, and Gemini Computer Use agent options (e.g. llm fields), matching server support where it is now the default for Gemini Computer Use.

Reviewed by Cursor Bugbot for commit 48a7ec1. Bugbot is set up for automated code reviews on this repo. Configure here.

@devin-ai-integration

Copy link
Copy Markdown

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

  • Address comments on this PR. Add '(aside)' to your comment to have me ignore it.
  • Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

  • Disable automatic comment, CI, and merge conflict monitoring

@greptile-apps

greptile-apps Bot commented Sep 3, 2026

Copy link
Copy Markdown

Greptile Summary

Adds gemini-3.8-flash to the SDK’s supported model type literals.

  • Extends BrowserUseLlm, HyperAgentLlm, and GeminiComputerUseLlm.
  • Enables typed request models to accept the new Gemini model identifier.

Confidence Score: 5/5

The PR appears safe to merge, with no concrete changed-code failure identified.

The constants-only change consistently extends the intended request type literals, and no repository contract establishes that another SDK allowlist must be updated with them.

Important Files Changed

Filename Overview
hyperbrowser/models/consts.py Adds the new model identifier consistently to the three intended LLM literal aliases without an established defect.

Reviews (1): Last reviewed commit: "Add gemini-3.8-flash to Gemini CUA, Hype..." | Re-trigger Greptile

@NikhilShahi
NikhilShahi added this pull request to the merge queue Sep 3, 2026
@NikhilShahi
NikhilShahi removed this pull request from the merge queue due to a manual request Sep 3, 2026
@NikhilShahi
NikhilShahi merged commit 4a2c00a into main Sep 3, 2026
14 checks passed
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.

2 participants