Files
BrowserOS/.github/workflows/eval-weekly.yml
shivammittal274 0babc05077 feat(eval): NopeCHA CAPTCHA solver integration (#537)
* feat(eval): show mean score instead of pass/fail in report and viewer

* feat(eval): integrate NopeCHA CAPTCHA solver into eval pipeline

Add CAPTCHA detection and waiting so screenshots capture post-solve state.
Run headed with xvfb on CI since headless breaks extension content scripts.

- Add CaptchaWaiter module (detect reCAPTCHA/hCaptcha/Turnstile, poll until solved)
- Add optional `captcha` config block to EvalConfigSchema
- Wait for CAPTCHA solve before screenshot in single-agent and orchestrator-executor
- Patch NopeCHA manifest with API key before launching workers
- Fix CAPTCHA_EXT_DIR path (was pointing one level too high)
- Remove --incognito (extensions don't run in incognito; fresh user-data-dir isolates)
- CI: install xvfb, run headed via xvfb-run, pass NOPECHA_API_KEY secret
2026-03-24 00:14:16 +05:30

99 lines
3.6 KiB
YAML

name: Weekly Eval
on:
schedule:
# Every Saturday at 06:00 UTC
- cron: '0 6 * * 6'
push:
branches: [main]
paths:
- 'packages/browseros-agent/apps/server/src/agent/**'
- 'packages/browseros-agent/apps/server/src/tools/**'
workflow_dispatch:
inputs:
config:
description: 'Eval config file (relative to apps/eval/)'
required: false
default: 'configs/browseros-agent-weekly.json'
permissions:
contents: read
jobs:
eval:
runs-on: ubuntu-latest
timeout-minutes: 360
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Install BrowserOS
run: |
wget -q https://github.com/browseros-ai/BrowserOS/releases/download/v0.44.0.1/BrowserOS_v0.44.0.1_amd64.deb
sudo dpkg -i BrowserOS_v0.44.0.1_amd64.deb
browseros --version || echo "BrowserOS installed at $(which browseros)"
- name: Install Bun
uses: oven-sh/setup-bun@v2
with:
bun-version: latest
- name: Install dependencies
working-directory: packages/browseros-agent
run: bun install --ignore-scripts && bun run build:agent-sdk
- name: Install xvfb
run: sudo apt-get update && sudo apt-get install -y xvfb
- name: Install captcha solver extension
working-directory: packages/browseros-agent/apps/eval
run: |
mkdir -p extensions
curl -sL -o /tmp/nopecha.zip https://github.com/NopeCHALLC/nopecha-extension/releases/latest/download/chromium_automation.zip
unzip -qo /tmp/nopecha.zip -d extensions/nopecha
- name: Run eval
working-directory: packages/browseros-agent/apps/eval
env:
FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
CLAUDE_CODE_OAUTH_TOKEN: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
NOPECHA_API_KEY: ${{ secrets.NOPECHA_API_KEY }}
BROWSEROS_BINARY: /usr/bin/browseros
EVAL_CONFIG: ${{ github.event.inputs.config || 'configs/browseros-agent-weekly.json' }}
run: |
echo "Running eval with config: $EVAL_CONFIG"
xvfb-run --auto-servernum --server-args="-screen 0 1440x900x24" bun run src/index.ts -c "$EVAL_CONFIG"
- name: Upload runs to R2
if: success()
working-directory: packages/browseros-agent/apps/eval
env:
EVAL_R2_ACCOUNT_ID: ${{ secrets.EVAL_R2_ACCOUNT_ID }}
EVAL_R2_ACCESS_KEY_ID: ${{ secrets.EVAL_R2_ACCESS_KEY_ID }}
EVAL_R2_SECRET_ACCESS_KEY: ${{ secrets.EVAL_R2_SECRET_ACCESS_KEY }}
EVAL_R2_BUCKET: ${{ secrets.EVAL_R2_BUCKET }}
EVAL_R2_CDN_BASE_URL: ${{ secrets.EVAL_R2_CDN_BASE_URL }}
EVAL_CONFIG: ${{ github.event.inputs.config || 'configs/browseros-agent-weekly.json' }}
run: |
CONFIG_NAME=$(basename "$EVAL_CONFIG" .json)
bun scripts/upload-run.ts "results/$CONFIG_NAME"
- name: Generate trend report
if: success()
working-directory: packages/browseros-agent
env:
EVAL_R2_ACCOUNT_ID: ${{ secrets.EVAL_R2_ACCOUNT_ID }}
EVAL_R2_ACCESS_KEY_ID: ${{ secrets.EVAL_R2_ACCESS_KEY_ID }}
EVAL_R2_SECRET_ACCESS_KEY: ${{ secrets.EVAL_R2_SECRET_ACCESS_KEY }}
EVAL_R2_BUCKET: ${{ secrets.EVAL_R2_BUCKET }}
EVAL_R2_CDN_BASE_URL: ${{ secrets.EVAL_R2_CDN_BASE_URL }}
run: bun apps/eval/scripts/weekly-report.ts /tmp/eval-report.html
- name: Upload report as artifact
if: success()
uses: actions/upload-artifact@v4
with:
name: eval-report-${{ github.run_id }}
path: /tmp/eval-report.html