3e98314d7c
- Add `clang_tidy_deps` CMake target that only builds generated headers (protobuf, Arrow, glog, gflags, lz4) instead of full `zvec_db` - Run clang-tidy in parallel via `xargs -P $(nproc)` with per-file logs - Split actions/cache into restore/save to ensure cache is saved even when clang-tidy fails, without caching incomplete build artifacts - Shallow-clone submodules with `--depth 1` - Bump ccache size from 100M to 500M - Add `--quiet` to suppress noisy clang-tidy summary lines - Remove redundant concurrency block from reusable workflow Performance comparison (3 runs, same repo): | Step | Before | After (cold) | After (warm) | |-----------------|---------|--------------|--------------| | Submodule clone | 66s | 49s | 28s | | Build deps | 70s | 21s | 0s (skipped) | | Cache restore | 1s | 1s | 12s | | Total | 3m03s | 2m34s | 1m46s | Dominant win: reduced build target (~49s). Headers cache adds ~9s net. `--depth 1` contributes ~15s (with network variance). |
||
|---|---|---|
| .. | ||
| docker | ||
| scripts | ||
| 01-ci-pipeline.yml | ||
| 02-lint-check.yml | ||
| 03-macos-linux-build.yml | ||
| 04-android-build.yml | ||
| 05-windows-build.yml | ||
| 06-ios-build.yml | ||
| _build_wheel_job.yml | ||
| auto-assign.yml | ||
| build_test_wheel.yml | ||
| build_wheel.yml | ||
| build_wheel_on_windows.yml | ||
| clang_tidy.yml | ||
| community-pr-handler.yml | ||
| continuous_bench.yml | ||
| issue-auto-assign.yml | ||
| nightly_coverage.yml | ||