Updated all active documentation and code to point to Discord community instead of Slack. All community links now use https://stagehand.dev/discord for better SEO.
**Changes:**
- Replaced Slack badges with Discord in README files
- Updated community links in documentation pages and error messages
- Removed Slack footer link from docs config
- Excluded historical changelogs and changesets
๐ค Generated with [Claude Code](https://claude.com/claude-code)
<!-- This is an auto-generated description by cubic. -->
---
## Summary by cubic
Switched all community references from Slack to Discord, updating badges, links, docs, and messages to point to https://stagehand.dev/discord for better SEO.
- **Refactors**
- Replaced Slack badges with Discord (added dark/light Discord SVGs, removed Slack SVGs).
- Updated README files, docs pages, and cards to use https://stagehand.dev/discord.
- Updated example and SDK error messages to mention Discord.
- Removed Slack footer link; docs anchors now point to https://stagehand.dev/discord.
- Excluded historical changelogs and changesets.
- Updated license badges to 32px height to match Discord badges.
<sup>Written for commit 75e632a74b77bbdf0c0e4509c3719fbccd69f881. Summary will update on new commits.</sup>
<!-- End of auto-generated description by cubic. -->
# why
deepwiki is a great resource to help potential new contributors/users to
understand the repo quickly and deeply. adding the badge helps route
people there as well as get our repo auto refreshed for when we update.
# what changed
added badge to readme + also updated outdated slack invite link
# test plan
n/a
---------
Co-authored-by: Sean McGuire <seanmcguire1@outlook.com>
# why
Link points to the old docs route
# what changed
Fixed link to the
[Quickstart](https://docs.stagehand.dev/v3/first-steps/quickstart)
section of the docs on the readme
Shoutout to @JerryWu1234 for the contrib
# test plan
---------
Co-authored-by: Jerry_wu <409187100@qq.com>
โบ ## Why
Add WebVoyager and GAIA evaluation suites to benchmark Stagehand's web
navigation and
reasoning capabilities against industry-standard datasets.
## What Changed
- Added WebVoyager eval suite with 643 test cases for web navigation
tasks
- Added GAIA eval suite with 90 test cases for general AI assistant
tasks
- Refactored eval infrastructure to support sampling and filtering
- Created reusable utilities for JSONL parsing and test case generation
- Added configuration for new eval suites in `evals.config.json`
### Environment Variables
- `EVAL_WEBVOYAGER_SAMPLE`: Random sample size from WebVoyager dataset
- `EVAL_WEBVOYAGER_LIMIT`: Max cases to run (default: 25)
- `EVAL_GAIA_SAMPLE`: Random sample size from GAIA dataset
- `EVAL_GAIA_LIMIT`: Max cases to run (default: 25)
- `EVAL_GAIA_LEVEL`: Filter GAIA by difficulty level (1, 2, or 3)
### Sampling Strategy
The sampling implementation uses Fisher-Yates shuffle for unbiased
random selection
when `SAMPLE` is specified, otherwise takes the first `LIMIT` cases.
This allows for
both deterministic (first N) and randomized (sample N) test runs.
## Test Plan
```bash
# Test WebVoyager with OpenAI
EVAL_SUITE=webvoyager EVAL_WEBVOYAGER_SAMPLE=1
EVAL_MODEL=openai/gpt-4o-computer-use-preview pnpm run evals
# Test WebVoyager with Claude
EVAL_SUITE=webvoyager EVAL_WEBVOYAGER_SAMPLE=1
EVAL_MODEL=anthropic/claude-3-5-sonnet-20241022 pnpm run evals
# Test GAIA with OpenAI
EVAL_SUITE=gaia EVAL_GAIA_SAMPLE=1
EVAL_MODEL=openai/gpt-4o-computer-use-preview pnpm
run evals
# Test GAIA with Claude
EVAL_SUITE=gaia EVAL_GAIA_SAMPLE=1
EVAL_MODEL=anthropic/claude-3-5-sonnet-20241022
pnpm run evals
# Verify existing evals still work
pnpm run evals
```
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Miguel <36487034+miguelg719@users.noreply.github.com>
# why
To keep up with changes on client SDKs
# what changed
Added a workflow 'Feature Parity' that, given an added (specific) label
to a PR, will open an issue on the sibling repo describing the PR for
future implementation
# test plan
---------
Co-authored-by: Roaring <216452114+the-roaring@users.noreply.github.com>
* add branding to readme
* logo
* light/dark mode
* better light/dark mode
* logo
* changeset
* remove license link
* link to mit license
* add branding to readme
* logo
* light/dark mode
* better light/dark mode
* logo
* changeset
* remove license link
* link to mit license
* cleanup readme
* env vars
* more cleanup
* more cleanup
* don't fmt readme
* move prereqs
* available models
* fix note
* cleanup
* axe more
* axe even more
* contributors
* env vars
* need to add contributing guide
* contribution guide
* contributions
* installation
* rm stagehand v. playwright
* temp
* move note
* wording
* lindsay edits
* change interoperable
* allow llmClient to be optionally passed in (#352)
* feat: allow llmClient to be optionally passed in
* update: add ollama client example from pr: #349
* update: README and changeset
* lint
---------
Co-authored-by: Arihan Varanasi <63890951+arihanv@users.noreply.github.com>
* Use CI on v2 branch
* branch
* add docs, move scoring functions to scoring.ts, move experiment naming to utils.ts
* add initStagehand.ts
* break up index.evals.ts and utils into smaller files
* export LogLineEval
* typing
* follow StagehandConfig pattern
* choose api key based on model name
* stagehand.act -> page.act (#326)
* need to actually move to act to page now
* move act -> page
* fix e2e
* fix tests
* readme
* changeset
* package json and changeset
* don't fail on combo evals
* Add act evals on `stagehand.page` (#328)
* move act evals to stagehand.page
* add basic act and make act necessary in type
* move extract and observe to page (#329)
* move act evals to stagehand.page
* add basic act and make act necessary in type
* move extract and observe
* example
* changeset
* More playwright tests (#330)
* add docs, move scoring functions to scoring.ts, move experiment naming to utils.ts
* add initStagehand.ts
* break up index.evals.ts and utils into smaller files
* export LogLineEval
* typing
* follow StagehandConfig pattern
* choose api key based on model name
* Use CI on v2 branch
* branch
* stagehand.page tests
* dont run on BB
* prettier
* pls dont fail
* headless
---------
Co-authored-by: Anirudh Kamath <github@kamath.io>
* add extract evals for stagehand.page (#331)
* add extract evals for stagehand.page
* fix typign
* smh i didn't actually run extract
* add observe page evals (#332)
* change stagehand.observe to stagehand.page.observe in evals
* changeset
* Browsercontext playwright tests (#334)
* add docs, move scoring functions to scoring.ts, move experiment naming to utils.ts
* add initStagehand.ts
* break up index.evals.ts and utils into smaller files
* export LogLineEval
* typing
* follow StagehandConfig pattern
* choose api key based on model name
* Use CI on v2 branch
* branch
* BrowserContext tests
* file path
---------
Co-authored-by: Anirudh Kamath <github@kamath.io>
* changeset minor
* ci yml
---------
Co-authored-by: seanmcguire12 <seanmcguire1@outlook.com>
Co-authored-by: Sean McGuire <75873287+seanmcguire12@users.noreply.github.com>
* update readme
* add bounding box functions to use on the DOM
* add parameterized textExtract
* add formatText function and helpers
* ad TextAnnotation type
* changeset & prettier
* add useTextExtract as param for ExtractOptions
* use textExtract method in CI
* rm NotImplementedError
* indentation fix
* dont run domExtract and textExtract at the same time
* ๐ time limit
* โฌ๏ธ time limit & rm extract_partners
* add caching on the llm provider level
* fix the bug in prev commit
* add lock file for caching + clear actions that are unsuccesful at the end
* leftover from prev commit
* disable caching by default
* add cache option for evals + cleanup
* update readme