Repository navigation
smoke tests: 27 packages (a–l, batch 3) - #1368
Conversation
Add a Standalone smoke test (--version or equivalent) to 27 packages that ship an OutputBin and had none. Tests are not in the spec hash, so nothing rebuilds. Verified locally with min check in a fresh session. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
Warning Review limit reached
This review includes 27 billable files and costs up to $6.75.
Reviews can continue after your included limit without a manual trigger. An admin must approve usage-based billing. Or wait 57 minutes for your next included review. View limit details
|
norrietaylor
left a comment
There was a problem hiding this comment.
Scope matches the title. The diff adds one smoketest to each of the 27 listed packages. It changes no build_deps, runtime_deps, outputs or build_args. Clobber none. Each hunk only adds a tests block, adds to the minimal.ncl import line, or adds a bash-bootstrap import. The diff removes no identifier from an import line. Correctness I checked each test path against the package outputs globs. All 27 binaries are in a declared output (usr/bin/* or usr/sbin/*). In libcap, the tests block is on the outer spec and not inside replace_on_cycle. The three wrapper tests use /usr/bin/bash, and bash-bootstrap ships that path. They also follow the rc -lt 126 shape in packages/edgedelta/build.ncl:68. Import lines keep the lowercase-first order. One weak test: jdtls --help never starts the JDK. Not checked I did not run the tests. That needs a build and min check. The PR body says the author ran them locally on arm64 only.
|
|
||
| tests = { | ||
| smoketest = standaloneTest "/usr/bin/jdtls --help", | ||
| }, |
There was a problem hiding this comment.
low · jdtls --help does not start the JDK. The wrapper in build.sh:26 execs python3 /usr/share/jdtls/bin/jdtls. The upstream launcher parses arguments with argparse. argparse prints help and exits 0 before it builds the java command line. So the test proves only that sh, sha1sum, cut and python3 work. It passes if jdk leaves runtime_deps or the JDK cannot load. The other tests in this PR prove the shipped binary loads, so this one is weaker than its neighbours. Add a second command to cmds that reaches the JVM, or say in a comment that this test covers only the wrapper. jdtls is the only wrapper-launched JVM tool in this batch.
Adds a
Standalonesmoke test to 27 packages that ship anOutputBinand had no Standalone test (a–l list, batch 3 of 3)./usr/bin/helm version/usr/bin/hex-patch --version/usr/bin/hexhog --version/usr/bin/hexyl --version/usr/bin/hyperfine --version/usr/bin/uconv --version/usr/bin/imgcatr --version/usr/sbin/ip -V/usr/bin/jdtls --helpbash -c '/usr/bin/jqfmt -h; rc=$?; [ $rc -lt 126 ]'(test_deps: bash-bootstrap)/usr/bin/json-server --version/usr/bin/just --version/usr/bin/kittyview --versionbash -c '/usr/bin/transicc -h; rc=$?; [ $rc -lt 126 ]'(test_deps: bash-bootstrap)/usr/bin/lerna --version/usr/sbin/capsh --print/usr/bin/fusermount3 --version/usr/bin/SvtAv1EncApp --version/usr/bin/asn1Parser --version/usr/bin/libtool --version/usr/bin/vips --version/usr/bin/vmaf --versionbash -c '/usr/bin/vpxdec --help; rc=$?; [ $rc -lt 126 ]'(test_deps: bash-bootstrap)/usr/bin/cwebp -version/usr/bin/x265 --version/usr/bin/clang --version/usr/bin/lsd --versionHow these were verified
Locally, in a fresh
min session activate . --loadout pkgbuildon this tree (a new session name for every run):min package build <pkgs>(cached artifacts, no rebuild;testsare not in the spec hash), thenmin check --packages <pkgs>with the names space-separated. All 81 tests across the three a–l batches reportstandalone tests...Pass, and no other check fails. pkgs CI showsstandalone tests...Skipfor these because nothing rebuilds, so the local run is the real evidence.Negative control: in a fresh session with all the tests applied, hyperfine's test was swapped for
/usr/bin/hyperfine --version; exit 7.min checkreportedsmoketest: ... had exit code 7/standalone tests...Fail. So the tests do run and a failure is reported. The real failures below (exit 127, loader errors) also came through as Fail.Wrapper-style tests: where a command needs a shell (a
shscript likefreetype-config, or a tool whose help flag exits non-zero by design, wrapped ascmd; rc=$?; [ $rc -lt 126 ]to prove only that exec and the loader work), the test usestest_deps = [bash-bootstrap], notbase. bash-bootstrap's only runtime_dep is glibc.basedrags in zlib, zstd, libmagic, libstdc++ and others, and that hid real missing runtime_deps: libgd and diffoscope both passed withbaseand failed without it.Skipped (no test added)
} targetmulti-arch shape)Findings (separate PRs, since runtime_deps are hashed and trigger a rebuild)
The missing libraries were found by an in-test
lddrun undertest_deps = [bash-bootstrap], with the result read back through exit codes, becausemin checkdrops test output.curl --versionexit 127libzstd.so.1(zstd), same as batch 1 (#820)file --versionexit 127libzstd.so.1,libz.so.1(zstd, zlib), same as batch 1idn2 --versionexit 127libunistring.so.5(libunistring), same as batch 1htop --versionexit 127libcap.so.2(libcap)gs --versionexit 127libbz2.so.1.0(bzip2)gdtopngexit ≥126 without baselibstdc++.so.6,libgcc_s.so.1(subsetOf gcc ["libgcc","libstdcpp"])--versionexit 1 without base:ImportError: failed to find libmagicfile(libmagic)runtest --versionexit 1:ERROR: unable to find expectexpectllama-cli --versionexit 127libmtmd.so.0,libllama.so.0,libllama-common.so.0,libggml*.so.0. build.sh runsinstall -vm755 build/bin/*.so, which ships only the unversioned names, so the SONAME files are never installed. llama-cli and llama-server cannot start.Tests ran on the Mac's VM (arm64). amd64 is not exercised locally.
🤖 Generated with Claude Code