mirror of
https://github.com/browseros-ai/BrowserOS.git
synced 2026-05-13 15:46:22 +00:00
feat(eval): switch to Linux GitHub-hosted runner (#519)
* feat(eval): switch to ubuntu-latest runner, add OE-Clado config - Switch workflow from self-hosted Mac Studio to ubuntu-latest - Install BrowserOS Linux .deb in CI (no self-hosted runner needed) - Add browseros-oe-clado-weekly.json config for orchestrator-executor - Fix report chart to show date+time (not just date) - Make BROWSEROS_BINARY configurable via env var * feat(eval): add NopeCHA captcha solver extension to eval runs - Auto-load NopeCHA extension in eval Chrome instances - Works in incognito + headless mode - CI workflow downloads NopeCHA before eval - extensions/ directory gitignored (downloaded at runtime) * feat(eval): per-config concurrency — different configs run in parallel * feat(eval): remove concurrency limit — all runs execute in parallel
This commit is contained in:
23
.github/workflows/eval-weekly.yml
vendored
23
.github/workflows/eval-weekly.yml
vendored
@@ -11,22 +11,24 @@ on:
|
||||
required: false
|
||||
default: 'configs/browseros-agent-weekly.json'
|
||||
|
||||
concurrency:
|
||||
group: eval-runner
|
||||
cancel-in-progress: false
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
eval:
|
||||
runs-on: self-hosted
|
||||
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:
|
||||
@@ -34,7 +36,14 @@ jobs:
|
||||
|
||||
- name: Install dependencies
|
||||
working-directory: packages/browseros-agent
|
||||
run: bun install
|
||||
run: bun install --ignore-scripts && bun run build:agent-sdk
|
||||
|
||||
- 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
|
||||
@@ -43,7 +52,7 @@ jobs:
|
||||
OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
|
||||
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
|
||||
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
|
||||
BROWSEROS_BINARY: ${{ secrets.BROWSEROS_BINARY }}
|
||||
BROWSEROS_BINARY: /usr/bin/browseros
|
||||
EVAL_CONFIG: ${{ github.event.inputs.config || 'configs/browseros-agent-weekly.json' }}
|
||||
run: |
|
||||
echo "Running eval with config: $EVAL_CONFIG"
|
||||
|
||||
Reference in New Issue
Block a user