Stagehand agent improvements #1094
Draft
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# why solves #1060 patch regression of playwright arguments being removed from agent execute response # what changed agent.execute now returns playwright arguments in its response # test plan tested locally
…ms to docs (#1065) # why reflect project id changes in docs # what changed advanced configuration comments # test plan reviewed via mintlify on localhost
# why Easier to use for Custom LLM Clients and keep users up to date with our aisdk file # what changed added export of aisdk to lib/index.ts # test plan build local stagehand, import local AISdkClient, run Azure Stagehand session
…onfigu… (#1073) …ration settings # why Updated docs to match the new fingerprint params in the Browserbase docs here: https://docs.browserbase.com/guides/stealth-customization#customization-options # what changed Update browser configuration docs to reflect the docs changes. # test plan
# why Updating docs to reflect aisdk can be imported directly # what changed The model page # test plan Reviewed page with mintlify dev locally
# why # what changed # test plan
# why Currently, we do not support stagehand agent within the api # what changed When api is enabled, stagehand agent now routes through the api # test plan Tested locally
# why Currently, using playwright screenshot command is not available when the execution environment is Stagehand. A customer has indicated they would prefer to use Playwright's native screenshot command instead of CDP when using Browserbase as CDP screenshot causes unexpected behavior for their target site. # what changed - added a StagehandScreenshotOptions type with useCDP argument added - extended page type to accept custom stagehand screeenshot options - update screenshot proxy to default useCDP to true if the env is browserbase and use playwright screenshot if false - added eval for screenshot with and without cdp # test plan - tested and confirmed functionality with eval and external example script (not committed)
…1057) # why We want to build a best in class agent in stagehand. Therefore, we need more eval benchmarks. # what changed - Added Web-bench evals dataset - Added a subset of OS World evals - those that can be run in a chrome browser (desktop-based tasks omitted) - added LICENSE noticed to the copied evals tasks - Added ground truth / expected result to some WebVoyager tasks using reference_answer.json from Browser Use public evals repo. Improvements to `pnpm run evals -man` to better describe how to run evals. # test plan Evals should run locally and bb for these new benchmarks.
# why Initial instructions didn't mention uv or pip prerequisites and also didn't mention venv. Fix reduces friction on first timers. # what changed - added link to install uv - added details for initializing venv - adjusted code example respectively # test plan docs change
# why - webpage structure changed, needed to update the xpath in the expected locator
… with LanguageModelV1 + LiteLLM works for python (#1086) # why 1. aisdk not yet available through npm package 2. customLLM provider only works with LanguageModelV1 3. LiteLLM compatible providers are supported in python # what changed 1. change docs to install stagehand from git repo 2. pin versions that use LanguageModelV1 # test plan local test
# why currently we pass stagehand page to agent, this results in our page management having issues when facing new tabs # what changed the stagehand object is now passed instead of stagehandPage # test plan tested locally
# why Our existing screenshot service is a dummy time-based triggered service. It also does not trigger based on any actions of the agent. # what changed Added img hash diff algo (quick check with MSE, verify with SSIM algo) to see if there was an actual UI change and only store ss in the buffer if that is so. Added ss interceptor which copies each screenshot the agent is taking to a buffer (if different enough from the previous ss) to be later used for evals. - There's also a small refactor of the agent initialization config to enable the screenshot collector service to be attached # test plan Tests pass locally --------- Co-authored-by: Miguel <[email protected]> Co-authored-by: miguel <[email protected]>
# why # what changed # test plan
# why anthropic released a new sota computer use model # what changed added claude-sonnet-4-5-20250929 as a model to the list # test plan ran evals
Why
Custom AI SDK tools and MCP integrations weren't working properly with
Anthropic CUA - parameters were empty {} and tools weren't tracked.
What Changed
- Convert Zod schemas to JSON Schema before sending to Anthropic (using
zodToJsonSchema)
- Track custom tool calls in the actions array
- Silence "Unknown tool name" warnings for custom tools
Test Plan
Tested with examples file.
Parameters passed correctly ({"city":"San Francisco"} instead of {})
Custom tools execute and appear in actions array
No warnings
# why To improve context # what changed Added current page and url to the system prompt # test plan
# why To inform the user throughout the agent execution process # what changed Added logs to tool calls, and on the stagehand agent handler # test plan - [x] tested locally
PR to make clearer the dependencies for `extract` (for those who haven't used zod or pydantic before) --------- Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
# why
- before this change, when we convert `z.string().url()` to an ID, if it
was inside a `z.array()`, it was not getting converted back into a URL
- this meant that if you defined a schema like this:
```ts
schema: z.object({
records: z.array(z.string().url()),
})
```
you would receive an array like this:
```
{
records: [
'0-302', '0-309',
'0-316', '0-323',
'0-330', '0-337',
'0-344', '0-351',
'0-358', '0-365'
]
}
```
- with this change, you will now receive the actual URLs, ie:
```
{
records: [
'https://www.archives.gov/files/research/jfk/releases/2025/0318/104-10003-10041.pdf',
'https://www.archives.gov/files/research/jfk/releases/2025/0318/104-10004-10143%20(C06932208).pdf',
'https://www.archives.gov/files/research/jfk/releases/2025/0318/104-10004-10143.pdf',
'https://www.archives.gov/files/research/jfk/releases/2025/0318/104-10004-10156.pdf',
'https://www.archives.gov/files/research/jfk/releases/2025/0318/104-10004-10213.pdf',
'https://www.archives.gov/files/research/jfk/releases/2025/0318/104-10005-10321.pdf',
'https://www.archives.gov/files/research/jfk/releases/2025/0318/104-10006-10247.pdf',
'https://www.archives.gov/files/research/jfk/releases/2025/0318/104-10007-10345.pdf',
'https://www.archives.gov/files/research/jfk/releases/2025/0318/104-10009-10021.pdf',
'https://www.archives.gov/files/research/jfk/releases/2025/0318/104-10009-10222.pdf'
]
}
```
# what changed
- updated the `injectUrls` function so that when it hits an array and
there is not deeper path, it loops through the array and injects the
URLs
# test plan
- evals
# why Adding support for Gemini's new Computer Use model # what changed We partnered with Google Deepmind to help integrate and test their new Computer Use models. <img width="1238" height="655" alt="Screenshot 2025-10-07 at 1 14 44 PM" src="https://github.com/user-attachments/assets/af0d854a-8e55-4937-a071-10335497f686" /> The new model tag `gemini-2.5-pro-computer-use-preview-10-2025` is available for Stagehand Agent. You can try it today with the example `cua-example.ts` To learn more, check out the blog post [https://www.browserbase.com/blog/evaluating-browser-agents](https://www.browserbase.com/blog/evaluating-browser-agents) --------- Co-authored-by: tkattkat <[email protected]> Co-authored-by: Kylejeong2 <[email protected]> Co-authored-by: Sameel <[email protected]>
# why # what changed # test plan
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 - [#1082](#1082) [`8c0fd01`](8c0fd01) Thanks [@tkattkat](https://github.com/tkattkat)! - Pass stagehand object to agent instead of stagehand page - [#1104](#1104) [`a1ad06c`](a1ad06c) Thanks [@miguelg719](https://github.com/miguelg719)! - Fix logging for stagehand agent - [#1066](#1066) [`9daa584`](9daa584) Thanks [@tkattkat](https://github.com/tkattkat)! - Add playwright arguments to agent execute response - [#1077](#1077) [`7f38b3a`](7f38b3a) Thanks [@tkattkat](https://github.com/tkattkat)! - adds support for stagehand agent in the api - [#1032](#1032) [`bf2d0e7`](bf2d0e7) Thanks [@miguelg719](https://github.com/miguelg719)! - Fix for zod peer dependency support - [#1014](#1014) [`6966201`](6966201) Thanks [@tkattkat](https://github.com/tkattkat)! - Replace operator handler with base of new agent - [#1089](#1089) [`536f366`](536f366) Thanks [@miguelg719](https://github.com/miguelg719)! - Fixed info logs on api session create - [#1103](#1103) [`889cb6c`](889cb6c) Thanks [@tkattkat](https://github.com/tkattkat)! - patch custom tool support in anthropic cua client - [#1056](#1056) [`6a002b2`](6a002b2) Thanks [@chrisreadsf](https://github.com/chrisreadsf)! - remove need for duplicate project id if already passed to Stagehand - [#1090](#1090) [`8ff5c5a`](8ff5c5a) Thanks [@miguelg719](https://github.com/miguelg719)! - Improve failed act error logs - [#1014](#1014) [`6966201`](6966201) Thanks [@tkattkat](https://github.com/tkattkat)! - replace operator agent with scaffold for new stagehand agent - [#1107](#1107) [`3ccf335`](3ccf335) Thanks [@seanmcguire12](https://github.com/seanmcguire12)! - fix: url extraction not working inside an array - [#1102](#1102) [`a99aa48`](a99aa48) Thanks [@miguelg719](https://github.com/miguelg719)! - Add current page and date context to agent - [#1110](#1110) [`dda52f1`](dda52f1) Thanks [@miguelg719](https://github.com/miguelg719)! - Add support for new Gemini Computer Use models ## @browserbasehq/[email protected] ### Minor Changes - [#1057](#1057) [`b7be89e`](b7be89e) Thanks [@filip-michalsky](https://github.com/filip-michalsky)! - added web voyager ground truth (optional), added web bench, and subset of OSWorld evals which run on a browser ### Patch Changes - [#1072](#1072) [`dc2d420`](dc2d420) Thanks [@filip-michalsky](https://github.com/filip-michalsky)! - improve evals screenshot service - add img hashing diff to add screenshots and change to screenshot intercepts from the agent - Updated dependencies \[[`8c0fd01`](8c0fd01), [`a1ad06c`](a1ad06c), [`9daa584`](9daa584), [`7f38b3a`](7f38b3a), [`bf2d0e7`](bf2d0e7), [`6966201`](6966201), [`536f366`](536f366), [`889cb6c`](889cb6c), [`6a002b2`](6a002b2), [`8ff5c5a`](8ff5c5a), [`6966201`](6966201), [`3ccf335`](3ccf335), [`a99aa48`](a99aa48), [`dda52f1`](dda52f1)]: - @browserbasehq/[email protected] ## @browserbasehq/[email protected] ### Patch Changes - Updated dependencies \[[`8c0fd01`](8c0fd01), [`a1ad06c`](a1ad06c), [`9daa584`](9daa584), [`7f38b3a`](7f38b3a), [`bf2d0e7`](bf2d0e7), [`6966201`](6966201), [`536f366`](536f366), [`889cb6c`](889cb6c), [`6a002b2`](6a002b2), [`8ff5c5a`](8ff5c5a), [`6966201`](6966201), [`3ccf335`](3ccf335), [`a99aa48`](a99aa48), [`dda52f1`](dda52f1)]: - @browserbasehq/[email protected] Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
# why The original example used JavaScript destructuring syntax [table] which doesn't work in Python. Fixed to use proper Python array indexing. # what changed fixed example to proper python syntax # test plan Co-authored-by: Steven Bryan <[email protected]>
# why - need to set default viewport when running on browserbase. previously, we only defined the default inside the exported `StagehandConfig` # what changed - set default viewport to 1288 * 711 when running on browserbase # test plan - tested locally, - regression evals
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 - [#1114](#1114) [`c0fbc51`](c0fbc51) Thanks [@seanmcguire12](https://github.com/seanmcguire12)! - configure default viewport when running on browserbase ## @browserbasehq/[email protected] ### Patch Changes - Updated dependencies \[[`c0fbc51`](c0fbc51)]: - @browserbasehq/[email protected] ## @browserbasehq/[email protected] ### Patch Changes - Updated dependencies \[[`c0fbc51`](c0fbc51)]: - @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
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
why
This PR enhances the Stagehand agent with model routing, expanded toolset, and more robust context management to improve performance and reliability across different LLM providers.
what changed
Model Routing
New Tools Added
Anthropic-Specific Tools (enabled when storeActions: false)
Model-Agnostic Tools
Enhanced Context Management
Enhanced Type Safety
test plan