diff --git a/.github/docker/Dockerfile.ci b/.github/docker/Dockerfile.ci index 9f499f68..b507200b 100644 --- a/.github/docker/Dockerfile.ci +++ b/.github/docker/Dockerfile.ci @@ -30,7 +30,6 @@ RUN curl -fsSL https://bun.sh/install | bash RUN npm i -g @anthropic-ai/claude-code # Playwright system deps (Chromium) — needed for browse E2E tests -# Install deps first (large layer, changes rarely), then Playwright + browser RUN npx playwright install-deps chromium # Pre-install dependencies (cached layer — only rebuilds when package.json changes) @@ -38,8 +37,10 @@ COPY package.json /workspace/ WORKDIR /workspace RUN bun install && rm -rf /tmp/* -# Install Playwright Chromium browser (uses deps installed above) -RUN npx playwright install chromium +# Install Playwright Chromium to a shared location accessible by all users +ENV PLAYWRIGHT_BROWSERS_PATH=/opt/playwright-browsers +RUN npx playwright install chromium \ + && chmod -R a+rX /opt/playwright-browsers # Verify everything works RUN bun --version && node --version && claude --version && jq --version && gh --version \ @@ -55,4 +56,5 @@ RUN mv /workspace/node_modules /opt/node_modules_cache \ # Create a non-root user for eval runs (GH Actions overrides USER, so # the workflow must set options.user or use gosu/su-exec at runtime). RUN useradd -m -s /bin/bash runner \ - && chmod -R a+rX /opt/node_modules_cache + && chmod -R a+rX /opt/node_modules_cache \ + && mkdir -p /home/runner/.gstack && chown -R runner:runner /home/runner/.gstack diff --git a/.github/workflows/evals.yml b/.github/workflows/evals.yml index a09834d1..61b8b5cf 100644 --- a/.github/workflows/evals.yml +++ b/.github/workflows/evals.yml @@ -116,6 +116,7 @@ jobs: OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }} GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }} EVALS_CONCURRENCY: "40" + PLAYWRIGHT_BROWSERS_PATH: /opt/playwright-browsers run: EVALS=1 bun test --retry 2 --concurrent --max-concurrency 40 ${{ matrix.suite.file }} - name: Upload eval results