stagehand

v@browserbasehq/[email protected] Feature

This release adds 4 notable features for engineering teams evaluating rollout.

Published 4h AI Agents & Assistants

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agents ai llms playwright puppeteer selenium

Summary

AI summary

Updates Patch Changes, https://github.com/miguelg719, and Minor Changes across a mixed release.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Medium	Adds a `screenshot` option to `extract()` sending viewport screenshot with the a11y tree. Adds a `screenshot` option to `extract()` sending viewport screenshot with the a11y tree. Source: llm_adapter@2026-06-03 Confidence: high	—
Feature	Medium	Adds `ignoreDefaultArgs` option to selectively remove chrome-launcher's built-in default flags. Adds `ignoreDefaultArgs` option to selectively remove chrome-launcher's built-in default flags. Source: llm_adapter@2026-06-03 Confidence: high	—
Feature	Medium	Adds native clipboard API. Adds native clipboard API. Source: llm_adapter@2026-06-03 Confidence: high	—
Feature	Medium	Adds Claude Opus 4.8 to the supported CUA model whitelist. Adds Claude Opus 4.8 to the supported CUA model whitelist. Source: llm_adapter@2026-06-03 Confidence: high	—
Feature	Medium	Includes "[selected]" or "[checked]" state in snapshot. Includes "[selected]" or "[checked]" state in snapshot. Source: llm_adapter@2026-06-03 Confidence: high	—
Feature	Medium	Adds a backend‑selectable v3 evaluator facade while preserving the legacy evaluator path. Adds a backend‑selectable v3 evaluator facade while preserving the legacy evaluator path. Source: llm_adapter@2026-06-03 Confidence: high	—
Feature	Medium	Adds verifier trajectory, rubric, and evaluation‑result types with normalized public naming. Adds verifier trajectory, rubric, and evaluation‑result types with normalized public naming. Source: llm_adapter@2026-06-03 Confidence: high	—
Feature	Medium	Captures verifier trajectory evidence from agent evidence callbacks for offline scoring. Captures verifier trajectory evidence from agent evidence callbacks for offline scoring. Source: llm_adapter@2026-06-03 Confidence: high	—
Bugfix	Medium	Fixes Anthropic CUA `triple_click` action mapping. Fixes Anthropic CUA `triple_click` action mapping. Source: llm_adapter@2026-06-03 Confidence: high	—
Bugfix	Medium	Fixes structuredOutputMode for newer Anthropic models. Fixes structuredOutputMode for newer Anthropic models. Source: llm_adapter@2026-06-03 Confidence: high	—

Full changelog

Minor Changes

#2149 6e75725 Thanks @miguelg719! - Added a screenshot option to extract() that sends the current viewport screenshot with the a11y tree for extraction.
#2127 78bcde8 Thanks @seanmcguire12! - Add ignoreDefaultArgs option to selectively remove chrome-launcher's built-in default flags (e.g. --disable-extensions) when running locally
#2160 49575d6 Thanks @monadoid! - Forward constructor and request model configuration when initializing API-backed sessions.
#2171 dc1445d Thanks @seanmcguire12! - add native clipboard API

Patch Changes

#2146 3a53ed4 Thanks @shriyatheunicorn! - Pass local browser launch options through when attaching over CDP so explicit viewport settings are respected.
#2107 8fc16d2 Thanks @miguelg719! - Fix Anthropic CUA triple_click action mapping.
#2118 3e95a87 Thanks @monadoid! - Add Vertex auth parameters to the core and server API schemas.
#2126 ebbdcd3 Thanks @seanmcguire12! - fix(core): import ToolSet from ai public export
#2120 12703a6 Thanks @miguelg719! - Fix structuredOutputMode for newer Anthropic models
#2170 1db5f1c Thanks @Kylejeong2! - Add Claude Opus 4.8 to the supported CUA model whitelist.
#2116 cb586a1 Thanks @seanmcguire12! - include "[selected]" or "[checked]" state in snapshot
#2129 765861c Thanks @miguelg719! - Add a backend-selectable v3 evaluator facade while preserving the legacy evaluator path.
#2157 2cd60a3 Thanks @miguelg719! - Add verifier trajectory, rubric, and evaluation-result types with normalized public naming.
#2131 e102a89 Thanks @miguelg719! - Capture verifier trajectory evidence from agent evidence callbacks for offline scoring.

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track stagehand

Get notified when new releases ship.

About stagehand

The SDK For Browser Agents

All releases →

Related context

Related tools

Earlier breaking changes

vstagehand-server-v3/v3.7.0 Delete packages/server-v4 entirely.
vstagehand-server-v3/v3.6.10 Remove cli release workflow
vstagehand-server-v3/v3.6.9 Integration libraries moved to peer dependencies.
v@browserbasehq/[email protected] move playwright-core, puppeteer-core, patchright-core from optional dependencies to peer dependencies