Files
msd-core/tests
Tom Boucher b780cd2dc6 test(#2933): prove one fragment edit reaches every emitted artifact (#3046)
Epic #1671 Phase 6 "Done when" required a maintainer-reachable proof that a
single-fragment edit propagates to every emitted per-runtime artifact with no
second source surface needing an edit. No test referenced that surface at all.

Adds tests/fragment-single-edit-propagation.install.test.cjs (20 rows): a
hard-linked overlay repo overrides exactly ONE steps/ fragment, real installers
are spawned per runtime, and the emitted artifacts are asserted directly.
Expected runtime sets derive from RUNTIME_META at run time, never a hardcoded
count, so a new runtime cannot be silently under-covered.

Six negative controls keep it from being pass-always theater. An
identity-stubbed composer must make marker bytes LEAK, proving the
marker-absence assertion can fail. Each derived generator whose --check is used
as evidence has its own red-path control driven by an override-only edit, each
asserting the generator's own typed reason enum rather than matching prose.

Coverage is disclosed, not implied. REGEN_STEPS_WITHOUT_CHECK_MODE names the
regen:derived steps with no read-only mode; CONTENT_EDIT_INSENSITIVE_CHECKS
names gen-inventory-manifest, whose --check derives from directory listings and
is structurally blind to content edits. Both constants are pinned by a test so
the disclosure cannot silently rot.

Assertions check sentinel PRESENCE, not whole-file byte identity: partial-wave.md
embeds the runtime-launcher snippet, so emitted fragments are legitimately
rewritten per runtime (windsurf -> .windsurf, qwen -> .qwen, claude -> its
absolute config dir). A dedicated row now locks that behavior in.

The overlay tree-diff is labelled a harness self-check, not the no-cascade
proof it cannot be: the overlay is built from the checkout with the override
map applied, so that diff can only ever restate the test's own fixture.

Extracts buildOverlayRepo into tests/helpers/overlay-repo.cjs so both install
suites share one implementation instead of diverging copies, converts that
sibling's six try/finally test bodies to t.after() per CONTRIBUTING.md, and
frees each per-runtime temp install eagerly so peak disk stays bounded.

Refs #2933

Co-authored-by: sim <sim@local>
2026-08-04 13:37:03 -04:00
..