mirror of
https://github.com/openai/codex.git
synced 2026-05-18 02:02:30 +00:00
30de54da36
## Why Bazel CI was not actually exercising some sharded Rust integration-test targets on macOS. The `rules_rust` sharding wrapper expects a symlink runfiles tree, but this repo runs Bazel with `--noenable_runfiles`. In that configuration the wrapper could fail to find the generated test binary, produce an empty test list, and exit successfully. That made targets such as `//codex-rs/core:core-all-test` look green even when Cargo CI could still catch failures in the same Rust tests. The coverage gap appears to have been introduced by [#18082](https://github.com/openai/codex/pull/18082), which enabled rules_rust native sharding on `//codex-rs/core:core-all-test` and the other large Rust test labels. The manifest-runfiles setup itself predates that change in [#10098](https://github.com/openai/codex/pull/10098), but #18082 is where the affected integration tests started running through the incompatible rules_rust sharding wrapper. [#18913](https://github.com/openai/codex/pull/18913) fixed the same class of issue for wrapped unit-test shards, but integration-test shards were still going through the rules_rust wrapper until this PR. We still do not have the V8/code-mode pieces stable under the Bazel CI cross-compile setup, so this keeps those tests out of Bazel while restoring coverage for the rest of the sharded Rust integration suites. Cargo CI remains responsible for V8/code-mode coverage for now. This change did uncover a real failing core test on `main`: `approved_folder_write_request_permissions_unblocks_later_apply_patch`. That fix is split into [#21060](https://github.com/openai/codex/pull/21060), which enables the `apply_patch` tool in the test, teaches the aggregate core test binary to dispatch the sandboxed filesystem helper, canonicalizes the macOS temp patch target, and isolates the core test harness from managed local/enterprise config. Keeping that fix separate lets this PR stay focused on restoring Bazel coverage while documenting the first failure it exposed. ## What changed - Build sharded Rust integration tests as manual `*-bin` binaries and run them through the existing manifest-aware `workspace_root_test` launcher. - Keep Bazel sharding on the launcher target so Rust test cases are still distributed by stable test-name hashing. - Configure Bazel CI to skip Rust tests whose names contain `suite::code_mode::`. - Exclude the standalone `codex-rs/code-mode` and `codex-rs/v8-poc` unit-test targets from `bazel.yml`. ## Verification - `bazel query --output=build //codex-rs/core:core-all-test` now shows `workspace_root_test` wrapping `//codex-rs/core:core-all-test-bin`. - `bazel test --test_output=all --nocache_test_results --test_sharding_strategy=disabled //codex-rs/core:core-all-test --test_filter=suite::request_permissions_tool::approved_folder_write_request_permissions_unblocks_later_apply_patch` runs the actual Rust test body and passes. - `bazel test --test_output=errors --nocache_test_results --test_env=CODEX_BAZEL_TEST_SKIP_FILTERS=suite::code_mode:: //codex-rs/core:core-all-test` runs the sharded target with code-mode skipped and passes overall locally, with one flaky attempt retried by the existing `flaky = True` setting.
188 lines
10 KiB
Plaintext
188 lines
10 KiB
Plaintext
common --repo_env=BAZEL_DO_NOT_DETECT_CPP_TOOLCHAIN=1
|
|
common --repo_env=BAZEL_NO_APPLE_CPP_TOOLCHAIN=1
|
|
# Dummy xcode config so we don't need to build xcode_locator in repo rule.
|
|
common --xcode_version_config=//:disable_xcode
|
|
|
|
common --disk_cache=~/.cache/bazel-disk-cache
|
|
common --repo_contents_cache=~/.cache/bazel-repo-contents-cache
|
|
common --repository_cache=~/.cache/bazel-repo-cache
|
|
common --remote_cache_compression
|
|
startup --experimental_remote_repo_contents_cache
|
|
|
|
common --experimental_platform_in_output_dir
|
|
|
|
# Runfiles strategy rationale: codex-rs/utils/cargo-bin/README.md
|
|
common --noenable_runfiles
|
|
|
|
common --enable_platform_specific_config
|
|
common:linux --host_platform=//:local_linux
|
|
common:windows --host_platform=//:local_windows
|
|
common --@rules_cc//cc/toolchains/args/archiver_flags:use_libtool_on_macos=False
|
|
common --@llvm//config:experimental_stub_libgcc_s
|
|
|
|
# TODO(zbarsky): rules_rust doesn't implement this flag properly with remote exec...
|
|
# common --@rules_rust//rust/settings:pipelined_compilation
|
|
|
|
common --incompatible_strict_action_env
|
|
# Not ideal, but We need to allow dotslash to be found
|
|
common:linux --test_env=PATH=/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin
|
|
common:macos --test_env=PATH=/opt/homebrew/bin:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin
|
|
|
|
# Pass through some env vars Windows needs to use powershell?
|
|
common:windows --test_env=SYSTEMROOT
|
|
common:windows --test_env=COMSPEC
|
|
common:windows --test_env=WINDIR
|
|
# Rust's libtest harness runs test bodies on std-spawned threads. The default
|
|
# 2 MiB stack can be too small for large async test futures on Windows CI; see
|
|
# https://github.com/openai/codex/pull/19067 for the motivating failure.
|
|
common --test_env=RUST_MIN_STACK=8388608 # 8 MiB
|
|
|
|
common --test_output=errors
|
|
common --bes_results_url=https://app.buildbuddy.io/invocation/
|
|
common --bes_backend=grpcs://remote.buildbuddy.io
|
|
common --remote_cache=grpcs://remote.buildbuddy.io
|
|
common --remote_download_toplevel
|
|
common --nobuild_runfile_links
|
|
common --remote_timeout=3600
|
|
common --noexperimental_throttle_remote_action_building
|
|
common --experimental_remote_execution_keepalive
|
|
common --grpc_keepalive_time=30s
|
|
common --experimental_remote_downloader=grpcs://remote.buildbuddy.io
|
|
|
|
# This limits both in-flight executions and concurrent downloads. Even with high number
|
|
# of jobs execution will still be limited by CPU cores, so this just pays a bit of
|
|
# memory in exchange for higher download concurrency.
|
|
common --jobs=30
|
|
|
|
common:remote --extra_execution_platforms=//:rbe
|
|
common:remote --remote_executor=grpcs://remote.buildbuddy.io
|
|
common:remote --jobs=800
|
|
# TODO(team): Evaluate if this actually helps, zbarsky is not sure, everything seems bottlenecked on `core` either way.
|
|
# Enable pipelined compilation since we are not bound by local CPU count.
|
|
#common:remote --@rules_rust//rust/settings:pipelined_compilation
|
|
|
|
# GitHub Actions CI configs.
|
|
common:ci --remote_download_minimal
|
|
common:ci --keep_going
|
|
common:ci --verbose_failures
|
|
common:ci --build_metadata=REPO_URL=https://github.com/openai/codex.git
|
|
common:ci --build_metadata=ROLE=CI
|
|
common:ci --build_metadata=VISIBILITY=PUBLIC
|
|
# rules_rust derives debug level from Bazel toolchain/compilation-mode settings,
|
|
# not Cargo profiles. Keep CI Rust actions explicit and lean.
|
|
common:ci --@rules_rust//rust/settings:extra_rustc_flag=-Cdebuginfo=0
|
|
common:ci --@rules_rust//rust/settings:extra_exec_rustc_flag=-Cdebuginfo=0
|
|
|
|
# Disable disk cache in CI since we have a remote one and aren't using persistent workers.
|
|
common:ci --disk_cache=
|
|
|
|
# Shared config for the main Bazel CI workflow.
|
|
common:ci-bazel --config=ci
|
|
common:ci-bazel --build_metadata=TAG_workflow=bazel
|
|
# Bazel CI cross-compiles in several legs, and the V8-backed code-mode tests
|
|
# are not stable in that setup yet. Keep running the rest of the Rust
|
|
# integration suites through the workspace-root launcher.
|
|
common:ci-bazel --test_env=CODEX_BAZEL_TEST_SKIP_FILTERS=suite::code_mode::
|
|
|
|
# Shared config for Bazel-backed Rust linting.
|
|
build:clippy --aspects=@rules_rust//rust:defs.bzl%rust_clippy_aspect
|
|
build:clippy --output_groups=+clippy_checks
|
|
build:clippy --@rules_rust//rust/settings:clippy.toml=//codex-rs:clippy.toml
|
|
# Keep this deny-list in sync with `codex-rs/Cargo.toml` `[workspace.lints.clippy]`.
|
|
# Cargo applies those lint levels to member crates that opt into `[lints] workspace = true`
|
|
# in their own `Cargo.toml`, but `rules_rust` Bazel clippy does not read Cargo lint levels.
|
|
# `clippy.toml` can configure lint behavior, but it cannot set allow/warn/deny/forbid levels.
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=-Dwarnings
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::await_holding_invalid_type
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::await_holding_lock
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::expect_used
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::identity_op
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::manual_clamp
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::manual_filter
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::manual_find
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::manual_flatten
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::manual_map
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::manual_memcpy
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::manual_non_exhaustive
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::manual_ok_or
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::manual_range_contains
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::manual_retain
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::manual_strip
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::manual_try_fold
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::manual_unwrap_or
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::needless_borrow
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::needless_borrowed_reference
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::needless_collect
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::needless_late_init
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::needless_option_as_deref
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::needless_question_mark
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::needless_update
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::redundant_clone
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::redundant_closure
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::redundant_closure_for_method_calls
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::redundant_static_lifetimes
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::trivially_copy_pass_by_ref
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::uninlined_format_args
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::unnecessary_filter_map
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::unnecessary_lazy_evaluations
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::unnecessary_sort_by
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::unnecessary_to_owned
|
|
build:clippy --@rules_rust//rust/settings:clippy_flag=--deny=clippy::unwrap_used
|
|
|
|
# Shared config for Bazel-backed argument-comment-lint.
|
|
build:argument-comment-lint --aspects=//tools/argument-comment-lint:lint_aspect.bzl%rust_argument_comment_lint_aspect
|
|
build:argument-comment-lint --output_groups=argument_comment_lint_checks
|
|
build:argument-comment-lint --@rules_rust//rust/toolchain/channel=nightly
|
|
|
|
# Rearrange caches on Windows so they're on the same volume as the checkout.
|
|
common:ci-windows --config=ci-bazel
|
|
common:ci-windows --build_metadata=TAG_os=windows
|
|
common:ci-windows --repo_contents_cache=D:/a/.cache/bazel-repo-contents-cache
|
|
|
|
# We prefer to run the build actions entirely remotely so we can dial up the concurrency.
|
|
# We have platform-specific tests, so we want to execute the tests on all platforms using the strongest sandboxing available on each platform.
|
|
|
|
# On linux, we can do a full remote build/test, by targeting the right (x86/arm) runners, so we have coverage of both.
|
|
# Linux crossbuilds don't work until we untangle the libc constraint mess.
|
|
common:ci-linux --config=ci-bazel
|
|
common:ci-linux --build_metadata=TAG_os=linux
|
|
common:ci-linux --config=remote
|
|
common:ci-linux --strategy=remote
|
|
common:ci-linux --platforms=//:rbe
|
|
|
|
# On mac, we can run all the build actions remotely but test actions locally.
|
|
common:ci-macos --config=ci-bazel
|
|
common:ci-macos --build_metadata=TAG_os=macos
|
|
common:ci-macos --config=remote
|
|
common:ci-macos --strategy=remote
|
|
common:ci-macos --strategy=TestRunner=darwin-sandbox,local
|
|
|
|
# On Windows, use Linux remote execution for build actions but keep test actions
|
|
# on the Windows runner so Bazel's normal test sharding and flaky-test retries
|
|
# still run against Windows binaries.
|
|
common:ci-windows-cross --config=ci-windows
|
|
common:ci-windows-cross --build_metadata=TAG_windows_cross_compile=true
|
|
common:ci-windows-cross --config=remote
|
|
common:ci-windows-cross --host_platform=//:rbe
|
|
common:ci-windows-cross --strategy=remote
|
|
common:ci-windows-cross --strategy=TestRunner=local
|
|
common:ci-windows-cross --local_test_jobs=4
|
|
common:ci-windows-cross --test_env=RUST_TEST_THREADS=1
|
|
# Native Windows CI still covers the PowerShell tests. The cross-built gnullvm
|
|
# binaries currently hang in PowerShell AST parser tests when those binaries are
|
|
# run on the Windows runner.
|
|
common:ci-windows-cross --test_env=CODEX_BAZEL_TEST_SKIP_FILTERS=suite::code_mode::,powershell
|
|
common:ci-windows-cross --platforms=//:windows_x86_64_gnullvm
|
|
common:ci-windows-cross --extra_execution_platforms=//:rbe,//:windows_x86_64_msvc
|
|
common:ci-windows-cross --extra_toolchains=//:windows_gnullvm_tests_on_msvc_host_toolchain
|
|
|
|
# Linux-only V8 CI config.
|
|
common:ci-v8 --config=ci
|
|
common:ci-v8 --build_metadata=TAG_workflow=v8
|
|
common:ci-v8 --build_metadata=TAG_os=linux
|
|
common:ci-v8 --config=remote
|
|
common:ci-v8 --strategy=remote
|
|
|
|
# Optional per-user local overrides.
|
|
try-import %workspace%/user.bazelrc
|