rUv e111bfbd7f fix(memory,tests): restore memory search recall and green the CLI suite (69 → 0) (#3252) ...

* fix(memory,tests): restore `memory search` recall and green the CLI suite (69 → 0)

The CLI suite had 69 failing tests across 50 files. Root-causing each rather
than adjusting expectations turned up one real product regression, two real
bugs, and a set of tests asserting things about the machine instead of the code.

PRODUCT REGRESSION — `memory search` recalled nothing (re-break of #2558)

`memory search` returned zero results for content that matched word for word,
while store/list/retrieve worked. Bisected to the threshold default:

  * 2026-07-04 #2558 restored recall, designed around a 0.3 threshold. Its
    fusion scores a full-coverage keyword hit as
    0.6*max(0,semantic) + 0.4*lexical, so with a non-positive cosine — routine
    for a one-word query — a PERFECT keyword match tops out at exactly 0.40.
  * 2026-07-26 #2790 set the CLI default to 0.7. Above 0.4, keyword recall is
    mathematically unreachable, so #2558 silently regressed.

Instrumented the live path to confirm before changing anything:
  key=note/alpha terms=["connectivity"] cov=1 bm25=0.029 sem=-0.883
  lex=1.000 score=0.400 thr=0.7      → dropped
Default restored to 0.3 at both sites, with the ceiling documented so it is not
raised past 0.4 again. Verified end to end: a shared keyword recalls all three
entries, a unique keyword recalls only its own. This was broken on main too.

REAL BUG — anchor containment rejected any project under a symlink

containedPath() compared a realpath'd root against a NON-realpath'd candidate,
so on macOS (/tmp → /private/tmp) every project looked like an escape. Now
compares like with like. Both guarantees re-verified by probe: ../ traversal,
deep traversal, absolute-outside and symlink-escape all still rejected;
symlinked-root spelling now accepted.

REAL BUG — a test that could not fail

funnel.test.ts asserted `elapsed < 100ms` as a proxy for "no network call" —
its own comment conceded a future fetch() would still pass. It also failed
intermittently (118ms) under full-suite CPU contention. Replaced with an
actual assertion on fetch/http.request/https.request, patched via the CJS
copies (ESM namespaces are non-writable). Negative-controlled: the technique
observes a real call and restores cleanly.

TESTS THAT MEASURED THE MACHINE, NOT THE CODE

  * 51 wasm tests asserted `available === true` for optional packages that were
    simply not installed, gated only on `process.env.CI`. Now also gated on real
    availability. The 7 tests in those files that need no WASM were lifted into
    their own blocks so they keep running rather than being skipped along with
    the rest — no coverage traded away for a green tick.
  * 4 agenticow tests lacked the `skipIf(!havePkg)` guard their 4 siblings had;
    in degraded mode the verb is inert and returns before validation.
  * policy-runtime hashed the raw tmpdir path while the source hashes the
    CANONICAL one, so it looked for a trust anchor that is never written there —
    and its cleanup was deleting a nonexistent path, leaking real anchors into
    ~/.config on every run.
  * sona's provider allowlist predated the ruvector / wasm-embedder /
    @claude-flow/embeddings backends.
  * ruvector/index asserted vi.mock satisfies a *dynamic* import() of a bare
    specifier. It does not under vitest 4 — the specifier is rewritten to
    '/@id/@ruvector/core' and fails with ERR_MODULE_NOT_FOUND. Now pins the
    contract the try/catch actually provides: unloadable → false, never throws.

TIMEOUTS — the "flakiness" was a fixed 5s budget

Six memory/intelligence files failed with "Test timed out in 5000ms", never an
assertion. They initialise a real ONNX embedder and SQLite; alone they are
fast, but the full suite saturates every core (~440% CPU). Because it depended
on scheduling, a different file failed each run. Raised testTimeout/hookTimeout
to 30s. (Process-level isolation was tried first and ruled out — forks changed
nothing, which is what identified the cause as time, not shared state.)

Verified: 3 consecutive full runs at 0 failed / 3572 passed on the feature
base, and 0 failed / 3537 passed on this branch's base.

Co-Authored-By: RuFlo <ruv@ruv.net>
Claude-Session: https://claude.ai/code/session_013u4pmL9ZUAXb6usVQgNo67

* fix(tests): make ruvector availability assertion environment-independent

CI caught what my first pass missed. The rewritten test asserted
`isRuvectorAvailable()` resolves to `false`, but whether the dynamic
`import('@ruvector/core')` resolves is environment-dependent:

  - under vitest's module runner a bare-specifier dynamic import is
    rewritten to '/@id/@ruvector/core' and fails (ERR_MODULE_NOT_FOUND)
    → false → my `toBe(false)` passed locally
  - a normal install where the package resolves → true → `toBe(false)`
    fails, which is exactly what the CI test-ratchet flagged

The prior `toBe(true)` had the same defect in the other direction. Pin
the invariant that holds in BOTH environments instead — the only thing
the try/catch actually promises: it resolves to a boolean and never
throws. No specific resolution outcome is asserted.

Verified 33/33 locally; the sibling "should return boolean" test already
covers the type, so this now documents the no-throw contract distinctly.

Co-Authored-By: RuFlo <ruv@ruv.net>
Claude-Session: https://claude.ai/code/session_013u4pmL9ZUAXb6usVQgNo67

2026-09-09 23:07:32 +00:00

2.3 KiB

Raw Permalink Blame History

View Raw