Files
codex/.github/workflows/bazel.yml
2026-03-27 01:38:58 -07:00

299 lines
12 KiB
YAML

name: Bazel (experimental)
# Note this workflow was originally derived from:
# https://github.com/cerisier/toolchains_llvm_bootstrapped/blob/main/.github/workflows/ci.yaml
on:
pull_request: {}
push:
branches:
- main
workflow_dispatch:
concurrency:
# Cancel previous actions from the same PR or branch except 'main' branch.
# See https://docs.github.com/en/actions/using-jobs/using-concurrency and https://docs.github.com/en/actions/learn-github-actions/contexts for more info.
group: concurrency-group::${{ github.workflow }}::${{ github.event.pull_request.number > 0 && format('pr-{0}', github.event.pull_request.number) || github.ref_name }}${{ github.ref_name == 'main' && format('::{0}', github.run_id) || ''}}
cancel-in-progress: ${{ github.ref_name != 'main' }}
jobs:
test:
timeout-minutes: 120
strategy:
fail-fast: false
matrix:
include:
# macOS
- os: macos-15-xlarge
target: aarch64-apple-darwin
- os: macos-15-xlarge
target: x86_64-apple-darwin
# Linux
- os: ubuntu-24.04
target: x86_64-unknown-linux-gnu
- os: ubuntu-24.04
target: x86_64-unknown-linux-musl
# 2026-02-27 Bazel tests have been flaky on arm in CI.
# Disable until we can investigate and stabilize them.
# - os: ubuntu-24.04-arm
# target: aarch64-unknown-linux-musl
# - os: ubuntu-24.04-arm
# target: aarch64-unknown-linux-gnu
# Windows
- os: windows-latest
target: x86_64-pc-windows-gnullvm
runs-on: ${{ matrix.os }}
# Configure a human readable name for each job
name: Local Bazel build on ${{ matrix.os }} for ${{ matrix.target }}
steps:
- uses: actions/checkout@v6
- name: Set up Node.js for js_repl tests
uses: actions/setup-node@v6
with:
node-version-file: codex-rs/node-version.txt
# Some integration tests rely on DotSlash being installed.
# See https://github.com/openai/codex/pull/7617.
- name: Install DotSlash
uses: facebook/install-dotslash@v2
- name: Make DotSlash available in PATH (Unix)
if: runner.os != 'Windows'
run: cp "$(which dotslash)" /usr/local/bin
- name: Make DotSlash available in PATH (Windows)
if: runner.os == 'Windows'
shell: pwsh
run: Copy-Item (Get-Command dotslash).Source -Destination "$env:LOCALAPPDATA\Microsoft\WindowsApps\dotslash.exe"
# Install Bazel via Bazelisk
- name: Set up Bazel
uses: bazelbuild/setup-bazelisk@v3
- name: Check MODULE.bazel.lock is up to date
if: matrix.os == 'ubuntu-24.04' && matrix.target == 'x86_64-unknown-linux-gnu'
shell: bash
run: ./scripts/check-module-bazel-lock.sh
# Restore bazel repository cache so we don't have to redownload all the external dependencies
# on every CI run.
- name: Restore bazel repository cache
id: cache_bazel_repository_restore
uses: actions/cache/restore@v5
with:
path: |
~/.cache/bazel-repo-cache
key: bazel-cache-${{ matrix.target }}-${{ hashFiles('MODULE.bazel', 'codex-rs/Cargo.lock', 'codex-rs/Cargo.toml') }}
restore-keys: |
bazel-cache-${{ matrix.target }}
- name: Configure Bazel startup args (Windows)
if: runner.os == 'Windows'
shell: pwsh
run: |
# Use a very short path to reduce argv/path length issues, but avoid the
# drive root because some Windows test launchers mis-handle MANIFEST paths there.
"BAZEL_STARTUP_ARGS=--output_user_root=D:\b" | Out-File -FilePath $env:GITHUB_ENV -Encoding utf8 -Append
- name: Enable Git long paths (Windows)
if: runner.os == 'Windows'
shell: pwsh
run: git config --global core.longpaths true
- name: bazel test //...
env:
BUILDBUDDY_API_KEY: ${{ secrets.BUILDBUDDY_API_KEY }}
shell: bash
run: |
set -o pipefail
bazel_console_log="$(mktemp)"
print_failed_bazel_test_logs() {
local console_log="$1"
local testlogs_dir
testlogs_dir="$(bazel $BAZEL_STARTUP_ARGS info bazel-testlogs 2>/dev/null || echo bazel-testlogs)"
local failed_targets=()
while IFS= read -r target; do
failed_targets+=("$target")
done < <(
grep -E '^FAIL: //' "$console_log" \
| sed -E 's#^FAIL: (//[^ ]+).*#\1#' \
| sort -u
)
if [[ ${#failed_targets[@]} -eq 0 ]]; then
echo "No failed Bazel test targets were found in console output."
return
fi
for target in "${failed_targets[@]}"; do
local rel_path="${target#//}"
rel_path="${rel_path/:/\/}"
local test_log="${testlogs_dir}/${rel_path}/test.log"
echo "::group::Bazel test log tail for ${target}"
if [[ -f "$test_log" ]]; then
tail -n 200 "$test_log"
else
echo "Missing test log: $test_log"
fi
echo "::endgroup::"
done
}
bazel_args=(
test
--test_verbose_timeout_warnings
--build_metadata=COMMIT_SHA=$(git rev-parse HEAD)
)
bazel_targets=(
//...
# Keep V8 out of the ordinary Bazel CI path. Only the dedicated
# canary and release workflows should build `third_party/v8`.
-//third_party/v8:all
)
if [[ "${RUNNER_OS:-}" == "Windows" ]]; then
# A `//...`-based query still loads `third_party/v8` on Windows even if
# we subtract the final labels, and Bazel 9 currently crashes during
# that analysis. Query within `//codex-rs/...` so the Windows smoke
# suite is discovered dynamically without touching the V8 packages.
#
# Match the common codex-rs Bazel test naming conventions here so the
# workflow keeps following the repo as new crates add `-unit-tests`
# or `-all-test` targets. Keep the exclusions package-scoped so
# every new test in an already-excluded package stays out
# automatically, while the rest of `//codex-rs/...` continues to
# grow dynamically.
#
# We intentionally avoid `rdeps(..., //codex-rs/code-mode:code-mode)`
# on Windows here. That query discovers the right set, but on a cold
# GitHub runner it materializes enough repos during analysis to fill
# the disk before the actual Bazel test run starts. The package list
# below is the current set whose tests still reach `code-mode`
# transitively. `v8-poc` contributes direct Windows targets, and
# `shell-command` still times out on the GitHub runner.
windows_target_query="
filter(
'(^|:).*(-all-test|-unit-tests|schema_fixtures-test)$',
tests(
//codex-rs/...
except //codex-rs/app-server/...
except //codex-rs/app-server-client/...
except //codex-rs/app-server-test-client/...
except //codex-rs/arg0/...
except //codex-rs/backend-client/...
except //codex-rs/chatgpt/...
except //codex-rs/cli/...
except //codex-rs/cloud-requirements/...
except //codex-rs/cloud-tasks/...
except //codex-rs/cloud-tasks-client/...
except //codex-rs/code-mode/...
except //codex-rs/core/...
except //codex-rs/exec/...
except //codex-rs/linux-sandbox/...
except //codex-rs/lmstudio/...
except //codex-rs/login/...
except //codex-rs/mcp-server/...
except //codex-rs/ollama/...
except //codex-rs/shell-command/...
except //codex-rs/tui/...
except //codex-rs/tui_app_server/...
except //codex-rs/utils/oss/...
except //codex-rs/utils/sandbox-summary/...
except //codex-rs/v8-poc/...
)
)
"
mapfile -t bazel_targets < <(
bazel $BAZEL_STARTUP_ARGS query "$windows_target_query" --keep_going \
| sort -u
)
echo "Windows smoke target count: ${#bazel_targets[@]}"
fi
if [[ "${RUNNER_OS:-}" != "Windows" ]]; then
# Bazel test sandboxes on macOS may resolve an older Homebrew `node`
# before the `actions/setup-node` runtime on PATH.
node_bin="$(which node)"
bazel_args+=("--test_env=CODEX_JS_REPL_NODE_PATH=${node_bin}")
fi
ci_config=ci-linux
if [[ "${RUNNER_OS:-}" == "macOS" ]]; then
ci_config=ci-macos
elif [[ "${RUNNER_OS:-}" == "Windows" ]]; then
ci_config=ci-windows
fi
if [[ -n "${BUILDBUDDY_API_KEY:-}" ]]; then
echo "BuildBuddy API key is available; using remote Bazel configuration."
# Work around Bazel 9 remote repo contents cache / overlay materialization failures
# seen in CI (for example "is not a symlink" or permission errors while
# materializing external repos such as rules_perl). We still use BuildBuddy for
# remote execution/cache; this only disables the startup-level repo contents cache.
set +e
bazel $BAZEL_STARTUP_ARGS \
--noexperimental_remote_repo_contents_cache \
"${bazel_args[@]}" \
"--config=${ci_config}" \
"--remote_header=x-buildbuddy-api-key=$BUILDBUDDY_API_KEY" \
-- \
"${bazel_targets[@]}" \
2>&1 | tee "$bazel_console_log"
bazel_status=${PIPESTATUS[0]}
set -e
else
echo "BuildBuddy API key is not available; using local Bazel configuration."
# Keep fork/community PRs on Bazel but disable remote services that are
# configured in .bazelrc and require auth.
#
# Flag docs:
# - Command-line reference: https://bazel.build/reference/command-line-reference
# - Remote caching overview: https://bazel.build/remote/caching
# - Remote execution overview: https://bazel.build/remote/rbe
# - Build Event Protocol overview: https://bazel.build/remote/bep
#
# --noexperimental_remote_repo_contents_cache:
# disable remote repo contents cache enabled in .bazelrc startup options.
# https://bazel.build/reference/command-line-reference#startup_options-flag--experimental_remote_repo_contents_cache
# --remote_cache= and --remote_executor=:
# clear remote cache/execution endpoints configured in .bazelrc.
# https://bazel.build/reference/command-line-reference#common_options-flag--remote_cache
# https://bazel.build/reference/command-line-reference#common_options-flag--remote_executor
set +e
bazel $BAZEL_STARTUP_ARGS \
--noexperimental_remote_repo_contents_cache \
"${bazel_args[@]}" \
--remote_cache= \
--remote_executor= \
-- \
"${bazel_targets[@]}" \
2>&1 | tee "$bazel_console_log"
bazel_status=${PIPESTATUS[0]}
set -e
fi
if [[ ${bazel_status:-0} -ne 0 ]]; then
print_failed_bazel_test_logs "$bazel_console_log"
exit "$bazel_status"
fi
# Save bazel repository cache explicitly; make non-fatal so cache uploading
# never fails the overall job. Only save when key wasn't hit.
- name: Save bazel repository cache
if: always() && !cancelled() && steps.cache_bazel_repository_restore.outputs.cache-hit != 'true'
continue-on-error: true
uses: actions/cache/save@v5
with:
path: |
~/.cache/bazel-repo-cache
key: bazel-cache-${{ matrix.target }}-${{ hashFiles('MODULE.bazel', 'codex-rs/Cargo.lock', 'codex-rs/Cargo.toml') }}