On NixOS (and other non-FHS systems) /bin/bash does not exist, so
scripts with an absolute shebang fail to run. Switch the remaining
holdouts to /usr/bin/env bash: eleven scripts/*.sh,
test-infrastructure/run.sh, and the three Claude Code hook scripts
emitted by src/cli/cli.c (gate, session reminder, subagent reminder).
Distilled from PR #674, with parser-test coverage preserved: the
infra_parse_shell* fixtures in tests/test_pipeline.c intentionally keep
#!/bin/bash so absolute-path shebang extraction stays covered, and
tests/repro fixtures are untouched.
Also replace the GitHub-PAT-shaped fixture string flagged in the #674
thread with an obviously fake placeholder (ghp_FAKE...) that still
matches the ghp_ + 36-alnum secret detector.
Co-authored-by: Sandro Jäckel <sandro.jaeckel@gmail.com>
Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>
verify_compiler() in scripts/env.sh ran `file` on the clang path and
grepped for arm64/universal. Nix's clang is a bash wrapper script, so
`file` reports "ASCII text executable" and the check falsely concluded
"x86_64 only", aborting before any compile. Replace it with a capability
probe: compile + link a trivial program for the target -arch and trust
the result — correct for wrapper scripts (Nix, ccache) and cross-compilers.
Make arch targeting explicit and toolchain-agnostic: export
ARCHFLAGS="-arch <arch>" from env.sh and fold it into CC/CXX in
Makefile.cbm via `override`, so it reaches every compile and link
(including the vendored objects) and survives a command-line CC=
override. This replaces the `arch -<arch> make` prefix, which cannot
work with Nix's fixed-target clang. Drop the now-redundant ARCH_PREFIX
from build/test/lint/repro.
Refs #705.
Signed-off-by: Kris Williams <115474+kriswill@users.noreply.github.com>
A reproduction fails its assertion and returns before cleanup, so LeakSanitizer
flagged benign harness leaks on every red store-level test and _exit()'d,
swallowing the unflushed summary — repro.sh then misread it as a build failure
(Linux only; macOS/Windows have no LSan). Fixes:
- repro.sh: export ASAN_OPTIONS=detect_leaks=0 for the board run. Leak-cleanliness
is not the board's signal (the RED rows are); the #581 leak bug gets a dedicated
RSS-growth test. ASan's real checks (use-after-free, overflow) stay enabled.
- repro_main.c: setvbuf(stdout, _IONBF) so the summary + RED rows survive any
abnormal _exit (sanitizer or crash).
- add tests/repro/repro_harness.h: shared multi-file index + store-query + fork
crash-detector helpers (ported from the proven test_lang_contract.c harness)
for the cross-file / store-level / crash reproduction waves.
Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>
Stand up a separate, non-gating reproduce-first suite that holds one RED case
per open bug issue (the redness is the deliverable + the regression guard):
- tests/repro/ + repro_main.c -> `make test-repro` (its own runner with its own
main + counters; deliberately EXCLUDED from ALL_TEST_SRCS so the gating
`make test` / ci-ok required check stays green and PRs are not wedged)
- repro_extraction.c: first reproduction, #554 -- a C++ out-of-line method's
inner CALLS edge must attribute to the class-qualified Method QN, not the
Module; ties the call's enclosing_func_qn to the method definition's own
qualified_name so a class-qualifier drop (the live root cause) fails it
- scripts/repro.sh: build+run the board; a build/link failure fails the job,
while expected test redness is reported as the board state (job stays green)
- .github/workflows/bug-repro.yml: workflow_dispatch (platform filter) + qa/**
push; runs the board on linux x2 / macos x2 / windows so many bug vectors can
be reproduced on many platforms at once
Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>
Martin Vogel