Prepare scanner branch for merge

src/eval/ocrEval.test.ts

@@ -1,24 +1,24 @@
 import { describe, expect, it } from "vitest";
 import { formatReport, runOcrEval } from "./ocrEvalHarness";
-import { seedCorpus } from "./corpus/seedCorpus";
+import { ocrEvalCorpus } from "./corpus";
 
-// Regression gate: the seed corpus is verified ground truth, so the parser must
-// read every labeled field correctly. A drop here means an OCR/parser change
-// regressed a previously-correct read - look at the printed failures. If a
-// change intentionally alters a correct output, update the corpus label in the
-// same commit (the label is the source of truth, not the code).
+// Regression gate: every case in the combined corpus is verified ground truth,
+// so the parser must read every labeled field correctly. A drop here means an
+// OCR/parser change regressed a previously-correct read - look at the printed
+// failures. If a change intentionally alters a correct output, update the corpus
+// label in the same commit (the label is the source of truth, not the code).
 
 describe("OCR eval harness", () => {
-  const report = runOcrEval(seedCorpus);
+  const report = runOcrEval(ocrEvalCorpus);
 
   it("prints the accuracy report", () => {
     // Surfaced in test output for humans; not an assertion.
     // eslint-disable-next-line no-console
     console.log("\n" + formatReport(report) + "\n");
-    expect(report.totalCases).toBe(seedCorpus.length);
+    expect(report.totalCases).toBe(ocrEvalCorpus.length);
   });
 
-  it("reads every labeled field on the seed corpus correctly", () => {
+  it("reads every labeled field on the eval corpus correctly", () => {
     const failureSummary = report.failures
       .map((failure) => {
         const wrong = failure.fields