fix(ci): preserve full precision and guard malformed resolution artifacts (#1167)

- scripts/resolution-benchmark.ts: stop rounding precision/recall to 3
  decimals before writing the artifact. The rounding let a near-miss like
  0.8497 round up to 0.850 and silently clear a 0.85 threshold in CI
  artifact mode while failing in fixture mode.
- tests/benchmarks/resolution/resolution-benchmark.test.ts: validate
  numeric fields in metricsFromArtifact so a stale or malformed artifact
  surfaces a clear 'regenerate' error instead of a confusing TypeError at
  the threshold assertions.
- tests/benchmarks/resolution/resolution-benchmark.test.ts: reject an
  empty artifact in loadArtifact. Without this guard, an empty {} would
  register zero describe blocks and vitest would exit 0 with '0 tests',
  silently passing the gate.

Author: carlos-alm

scripts/resolution-benchmark.ts

@@ -127,9 +127,12 @@ function computeMetrics(resolvedEdges: ResolvedEdge[], expectedEdges: ExpectedEd
 		m.recall = m.expected > 0 ? m.resolved / m.expected : 0;
 	}
 
+	// Keep full precision so the artifact-mode gate compares the exact same
+	// values the fixture-mode gate would compute. Rounding here let a near-miss
+	// like 0.8497 round up to 0.850 and silently clear a 0.85 threshold.
 	return {
-		precision: Math.round(precision * 1000) / 1000,
-		recall: Math.round(recall * 1000) / 1000,
+		precision,
+		recall,
 		truePositives: truePositives.size,
 		falsePositives: falsePositives.size,
 		falseNegatives: falseNegatives.size,

tests/benchmarks/resolution/resolution-benchmark.test.ts

@@ -291,10 +291,37 @@ function loadArtifact(artifactPath: string): Record<string, ArtifactLangResult>
       `RESOLUTION_RESULT_JSON=${artifactPath} not found — run scripts/resolution-benchmark.ts first.`,
     );
   }
-  return JSON.parse(fs.readFileSync(artifactPath, 'utf-8'));
+  const parsed = JSON.parse(fs.readFileSync(artifactPath, 'utf-8')) as Record<
+    string,
+    ArtifactLangResult
+  >;
+  // Refuse to proceed on an empty artifact: with zero languages, vitest would
+  // register no describe blocks and exit 0, silently passing the gate without
+  // evaluating a single threshold.
+  if (!parsed || typeof parsed !== 'object' || Object.keys(parsed).length === 0) {
+    throw new Error(
+      `RESOLUTION_RESULT_JSON=${artifactPath} contains no language results — regenerate with scripts/resolution-benchmark.ts.`,
+    );
+  }
+  return parsed;
 }
 
 function metricsFromArtifact(lang: string, raw: ArtifactLangResult): BenchmarkMetrics {
+  if (
+    typeof raw.precision !== 'number' ||
+    typeof raw.recall !== 'number' ||
+    typeof raw.truePositives !== 'number' ||
+    typeof raw.falsePositives !== 'number' ||
+    typeof raw.falseNegatives !== 'number' ||
+    typeof raw.totalResolved !== 'number' ||
+    typeof raw.totalExpected !== 'number' ||
+    !raw.byMode ||
+    typeof raw.byMode !== 'object'
+  ) {
+    throw new Error(
+      `Resolution artifact for ${lang} is missing required numeric fields — regenerate with the current resolution-benchmark.ts.`,
+    );
+  }
   if (!Array.isArray(raw.falsePositiveEdges) || !Array.isArray(raw.falseNegativeEdges)) {
     throw new Error(
       `Resolution artifact for ${lang} is missing falsePositiveEdges/falseNegativeEdges — regenerate with the current resolution-benchmark.ts.`,