tewip-ai 0.28.0 → 0.29.0

package/README.md

@@ -632,8 +632,12 @@ Two things it refuses to do, which is why the list is worth reading:
   test that compiles a TypeScript fixture and runs it asserts nothing *on purpose*. Those are reported
   separately as "compares no value", not as broken, and they do not trip `--strict`.
 
-Honest limit, also printed at the bottom of every report: its **recall is unmeasured**. A clean report
-means nothing it found was wrong, not that every test in the file is worth something.
+**Recall, measured by execution** (`eval/vouch-recall.ts`): mutate a source file, record which tests
+catch which mutation, remove the last statement of the ones that provably caught something, and run it
+all again. A test that caught a mutation before and catches nothing now has provably lost its check -
+a label that owes nothing to vouch's own patterns. On 17 such cases across seven source/test pairs in
+two projects, **vouch named 12 (70.6%)**, and the five it did not name still hold a real assertion, so
+it is right about those too. Nothing that still caught a mutation was wrongly accused.
 
 ## A goal instead of a verb (Phases 19 and 21)
 

package/dist/engine/vouch/vouch.js

@@ -59,7 +59,12 @@ function judge(file, test, helpers) {
     const at = { file, name: test.name, line: test.line };
     if (test.skipped)
         return { ...at, verdict: 'never-runs', evidence: test.name, why: MEANS['never-runs'] };
-    const body = withoutComments(test.body);
+    // Strings are blanked as well as comments. A fixture that quotes `expect(true).toBe(true)` is not a
+    // tautology, it is a test *about* tautologies - and before this, Tewip accused its own suite of
+    // exactly that. The extractor learned this lesson in Phase 22; the verdicts had not, and it took a
+    // recall measurement judging by execution to notice, because no ordinary project quotes test code in
+    // its tests. Any checker's own tests do, and so does any test asserting on generated code.
+    const body = withoutText(withoutComments(test.body));
     const tautology = tautologies(body);
     const unfinished = unfinishedExpectations(body);
     const checks = checksSomething(body);
@@ -98,6 +103,21 @@ function judge(file, test, helpers) {
         return { ...at, verdict: 'crash-only', evidence: '(the body is empty)', why: 'the test has no body at all, so nothing can fail it' };
     return { ...at, verdict: 'crash-only', evidence: firstRealLine(body), why: MEANS['crash-only'] };
 }
+/**
+ * The body with the *contents* of strings and template literals blanked, keeping the quotes and
+ * everything around them. `expect(x).toBe(1)` still reads as a call; `"expect(true).toBe(true)"` reads
+ * as an empty string.
+ */
+function withoutText(body) {
+    let out = body;
+    for (const [from, to] of textRanges(body).slice().reverse()) {
+        const span = out.slice(from, to + 1);
+        if (span.length < 3)
+            continue;
+        out = out.slice(0, from + 1) + ' '.repeat(span.length - 2) + out.slice(to);
+    }
+    return out;
+}
 /**
  * Everything inside a `try` whose `catch` discards what it caught. An assertion failure is an
  * exception, so a test shaped this way reports success however the code behaves - and a `catch` that

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "tewip-ai",
-  "version": "0.28.0",
+  "version": "0.29.0",
   "description": "Tewip finds why each failing test failed - real bug, flaky test, environment, test data or changed selector - for any stack, from the command line, CI, or your editor.",
   "keywords": [
     "test-failures",