Skip to content

Conversation

@MagellaX
Copy link

Swapped out tsup for esbuild so the Stagehand build stays fast and maintained, and taught Playwright to run against precompiled JS instead of scrambling at runtime. We now bundle the library and CLI with tiny esbuild scripts, compile the deterministic suite ahead of time, rewrite its imports, and keep the helper that Playwright was missing. The net effect: pnpm run build and the local e2e suite run clean again, no more __name explosions, and the build pipeline feels a lot healthier.
covers #263

tkattkat and others added 18 commits September 10, 2025 13:40
# why

solves browserbase#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 (browserbase#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… (browserbase#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)
…rowserbase#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 (browserbase#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
To help make sense of eval test cases and results

# what changed
Added metadata to eval runs, cleaned deprecated code

# test plan
@changeset-bot
Copy link

changeset-bot bot commented Sep 24, 2025

⚠️ No Changeset found

Latest commit: af7dd0c

Merging this PR will not cause a version bump for any packages. If these changes should not result in a new version, you're good to go. If these changes should result in a version bump, you need to add a changeset.

Click here to learn what changesets are, and how to add one.

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

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.

Greptile Overview

Summary

This PR successfully migrates from tsup to esbuild for build tooling, addressing issue #263. The migration introduces dedicated build scripts for library, CLI, and end-to-end test compilation, replacing the previous tsup-based approach.

Key changes:

  • Removed tsup dependency and replaced with esbuild (already present)
  • Created modular build scripts: build-lib.mjs, build-cli.mjs, build-e2e.mjs, run-playwright.mjs
  • Updated package.json scripts to use new build scripts instead of tsup commands
  • Modified TypeScript config to only emit declaration files since esbuild handles JS compilation
  • Added sophisticated e2e test precompilation with import rewriting and import.meta compatibility

The new build system addresses the "no more __name explosions" mentioned in the PR description by adding explicit __name helpers in the esbuild banner. The e2e build script precompiles Playwright tests and rewrites Stagehand imports to use the local build, eliminating runtime compilation issues.

Confidence Score: 4/5

  • This PR is safe to merge with minimal risk
  • Score reflects well-structured migration with proper error handling and compatibility measures, but one minor hardcoded string replacement that could be more robust
  • Pay close attention to build-e2e.mjs for the string replacement logic

Important Files Changed

File Analysis

Filename        Score        Overview
package.json 4/5 Replaced tsup dependency with esbuild, updated build scripts to use new build scripts instead of tsup commands
scripts/build-lib.mjs 5/5 Clean esbuild script for library build with proper external dependency handling and __name helper for node compatibility
scripts/build-cli.mjs 4/5 Comprehensive CLI build script with proper executable permissions, config copying, and npm linking with error handling
scripts/build-e2e.mjs 4/5 Complex e2e build script that precompiles Playwright tests, rewrites imports, and handles import.meta compatibility
scripts/run-playwright.mjs 5/5 Simple pass-through script that runs precompiled Playwright tests, avoiding tsx/ts-node timing issues
tsconfig.build.json 5/5 Updated TypeScript config to only emit declaration files, since esbuild now handles JS compilation
pnpm-lock.yaml 5/5 Removed tsup and its dependencies from lockfile, esbuild already present as dependency

Sequence Diagram

sequenceDiagram
    participant Developer
    participant npm as npm/pnpm
    participant lib as build-lib.mjs
    participant cli as build-cli.mjs
    participant e2e as build-e2e.mjs
    participant tsc as TypeScript
    participant esbuild as esbuild
    participant dist as dist/

    Developer->>npm: pnpm run build
    npm->>npm: lint & gen-version & build-dom-scripts
    npm->>lib: node scripts/build-lib.mjs
    lib->>esbuild: bundle lib/index.ts
    esbuild->>dist: output dist/index.js (ESM)
    npm->>tsc: build-types (tsc --project tsconfig.build.json)
    tsc->>dist: emit .d.ts files only
    
    Developer->>cli: node scripts/build-cli.mjs
    cli->>esbuild: bundle evals/cli.ts
    esbuild->>dist: output dist/evals/cli.js (CJS)
    cli->>cli: copy config & set permissions
    cli->>npm: npm link (if enabled)
    
    Developer->>e2e: node scripts/build-e2e.mjs
    e2e->>e2e: collect .ts entry points
    e2e->>esbuild: bundle all deterministic tests
    esbuild->>dist: output to dist/playwright/
    e2e->>e2e: rewrite stagehand imports
    e2e->>e2e: patch import.meta compatibility
Loading

6 files reviewed, 1 comment

Edit Code Review Bot Settings | Greptile

MagellaX and others added 2 commits September 24, 2025 16:50
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
@MagellaX
Copy link
Author

Hey, i think u can merge this @seanmcguire12

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.

9 participants