This release adds 2 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
Summary
AI summaryUpdates evals, fix, and feat across a mixed release.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Low |
Adds opt-out flag for browse CLI .env auto-loading with warning. Adds opt-out flag for browse CLI .env auto-loading with warning. Source: llm_adapter@2026-07-16 Confidence: high |
— |
| Feature | Low |
Adds OdysseysBench agent benchmark to evals. Adds OdysseysBench agent benchmark to evals. Source: llm_adapter@2026-07-16 Confidence: high |
— |
| Bugfix | Medium |
Silences AI SDK "system message in messages" warning in act/extract/observe. Silences AI SDK "system message in messages" warning in act/extract/observe. Source: llm_adapter@2026-07-16 Confidence: high |
— |
| Bugfix | Medium |
Fixes source eval browser skill loading from packages/cli browse SKILL.md. Fixes source eval browser skill loading from packages/cli browse SKILL.md. Source: llm_adapter@2026-07-16 Confidence: high |
— |
| Other | Low |
Updates braintrust UI publisher with sonnet-5, gpt-5.6, and grok pricing. Updates braintrust UI publisher with sonnet-5, gpt-5.6, and grok pricing. Source: llm_adapter@2026-07-16 Confidence: low |
— |
Full changelog
What's Changed
- [docs]: add docs for
setDomainPolicyby @seanmcguire12 in https://github.com/browserbase/stagehand/pull/2289 - fix: silence AI SDK "system message in messages" warning in act/extract/observe by @shrey150 in https://github.com/browserbase/stagehand/pull/2359
- [STG-2510] fix: source eval browser skill from packages/cli browse SKILL.md by @shrey150 in https://github.com/browserbase/stagehand/pull/2334
- chore(evals): add sonnet-5, gpt-5.6, and grok pricing to braintrust UI publisher by @miguelg719 in https://github.com/browserbase/stagehand/pull/2318
- feat: warn and add opt-out flag for browse CLI .env auto-loading by @shrey150 in https://github.com/browserbase/stagehand/pull/2361
- chore(docs): Replace “LLM model” wording in Stagehand docs by @Kylejeong2 in https://github.com/browserbase/stagehand/pull/2366
- feat(evals): add OdysseysBench agent benchmark by @miguelg719 in https://github.com/browserbase/stagehand/pull/2275
- chore: cut stagehand-server-v3 catchup release by @shrey150 in https://github.com/browserbase/stagehand/pull/2367
Full Changelog: https://github.com/browserbase/stagehand/compare/@browserbasehq/[email protected]/v3.7.3
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
Related context
Related tools
Earlier breaking changes
- v@browserbasehq/[email protected] Changes `setScreenshotProvider` callback to return `{ base64, mediaType }` instead of bare base64 string.
- 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
Beta — feedback welcome: [email protected]