feat(routing): every eval case names its event; the P10 eval gate is exempted with its reason (A1)

P10's model-free part (wave 4, order A1, decision 63). The routing test now
checks every case in evals/ for from=, not only the skill-tagged ones (R1):
a case with no skill tag is not routed, only checked, and the report gives
both counts ("45 cases checked for from=, 37 routed"). The eight test-set
cases get from=proevesett-eval-suite (d311f3b) or
from=proevesett-intent-gate (3892a83), the commits that added them.

The release gate that reads the last test-set run is written into the
runbook as exempted with its reason (it waits for the fixed test set to run
again) and still says where it goes (scripts/release-check.mjs).

review-630's prototype-tag stub gets from=test: under R1 an unrouted case is
still checked for from=, and the stub tests that a prototype name is never
routed, which stands.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/lib/p10-model-free.test.mjs

@@ -0,0 +1,82 @@
+// tests/lib/p10-model-free.test.mjs
+// P10's model-free part (wave 4, order A1). Every case in evals/ names the
+// event it came from (`from=`), not only the skill cases; the routing check
+// covers every case and says how many it checked for `from=` and how many it
+// routed; and the release gate that would read the last test-set run is
+// written down as exempted with a reason, not built.
+
+import { test } from 'node:test';
+import { strict as assert } from 'node:assert';
+import { spawnSync } from 'node:child_process';
+import { mkdtempSync, mkdirSync, writeFileSync, readdirSync, readFileSync, existsSync, rmSync } from 'node:fs';
+import { tmpdir } from 'node:os';
+import { dirname, join } from 'node:path';
+import { fileURLToPath } from 'node:url';
+import { readFrontmatterFields } from '../../lib/skills/skill-frontmatter.mjs';
+import { checkRouting } from '../../lib/skills/routing.mjs';
+
+const ROOT = join(dirname(fileURLToPath(import.meta.url)), '..', '..');
+const CLI = join(ROOT, 'lib', 'skills', 'routing.mjs');
+
+const tagsOf = (file) => {
+  const f = readFrontmatterFields(readFileSync(file, 'utf8')).fields.tags;
+  return f && Array.isArray(f.value) ? f.value.map(String) : [];
+};
+
+test('P10: every case in evals/ names the event it came from (from=)', () => {
+  const dirs = readdirSync(join(ROOT, 'evals')).filter((d) => existsSync(join(ROOT, 'evals', d, 'prompt.md'))).sort();
+  assert.ok(dirs.length >= 45, `${dirs.length} cases`);
+  const missing = dirs.filter((d) => !tagsOf(join(ROOT, 'evals', d, 'prompt.md')).some((t) => /^from=\S+$/.test(t)));
+  assert.deepEqual(missing, [], `${missing.length} of ${dirs.length} cases have no from=: ${missing.join(', ')}`);
+});
+
+/** A plugin root with one skill, its 3/2/1 cases, and the extra cases given. */
+function stubRoot(extra) {
+  const root = mkdtempSync(join(tmpdir(), 'p10-model-free-'));
+  mkdirSync(join(root, 'skills', 'tidy-imports'), { recursive: true });
+  writeFileSync(join(root, 'skills', 'tidy-imports', 'SKILL.md'),
+    '---\nname: tidy-imports\ndescription: Sorts the import lines of a source file. Use when imports are out of order.\n---\n');
+  mkdirSync(join(root, 'commands'), { recursive: true });
+  writeFileSync(join(root, 'commands', 'rotate-logs.md'), '---\nname: rotate-logs\ndescription: Compresses and deletes old log files on disk.\n---\n');
+  const cases = {
+    p1: ['skill-trigger, skill=tidy-imports, from=test', 'sort the import lines'],
+    p2: ['skill-trigger, skill=tidy-imports, from=test', 'import lines are out of order'],
+    p3: ['skill-trigger, skill=tidy-imports, from=test', 'sort imports in the source file'],
+    n1: ['skill-no-trigger, skill=tidy-imports, owner=rotate-logs, from=test', 'delete old log files'],
+    n2: ['skill-no-trigger, skill=tidy-imports, owner=rotate-logs, from=test', 'compress the logs on disk'],
+    e1: ['skill-effect, skill=tidy-imports, from=test', 'x'],
+    ...extra,
+  };
+  for (const [n, [tags, prompt]] of Object.entries(cases)) {
+    mkdirSync(join(root, 'evals', n), { recursive: true });
+    writeFileSync(join(root, 'evals', n, 'prompt.md'), `---\ndescription: "case ${n}"\ntags: [${tags}]\nruns: 1\n---\n\n${prompt}\n`);
+  }
+  return root;
+}
+
+test('P10 (R1): a case with no skill tag and no from= is a finding of the routing check', () => {
+  const root = stubRoot({ 'plain-gate': ['proevesett', '/voyage:trekplan'], 'plain-sourced': ['proevesett, from=test', '/voyage:trekplan'] });
+  try {
+    const r = checkRouting(root);
+    const src = r.errors.filter((e) => e.code === 'ROUTING_CASE_NO_SOURCE').map((e) => e.case);
+    assert.deepEqual(src, ['plain-gate'], JSON.stringify(r.errors));
+    assert.ok(!r.errors.some((e) => e.case === 'plain-sourced'), 'a sourced case with no skill tag is not routed');
+  } finally { rmSync(root, { recursive: true, force: true }); }
+});
+
+test('P10 (R1): the report shows the denominators: cases checked for from= and cases routed', () => {
+  const root = stubRoot({ 'plain-sourced': ['proevesett, from=test', '/voyage:trekplan'] });
+  try {
+    const r = checkRouting(root);
+    assert.deepEqual([r.stats.sourced, r.stats.cases], [7, 6], JSON.stringify(r.stats));
+    const out = spawnSync('node', [CLI, '--root', root], { encoding: 'utf8' });
+    assert.match(out.stdout, /7 cases checked for from=, 6 routed/, out.stdout + out.stderr);
+  } finally { rmSync(root, { recursive: true, force: true }); }
+});
+
+// Found by its words, not its heading: the section title is set at the release.
+test('P10: the CHANGELOG says the eval gate is exempted, with the reason', () => {
+  const md = readFileSync(join(ROOT, 'CHANGELOG.md'), 'utf8');
+  assert.ok(/^- [^\n]*eval gate \(P10\)[^\n]*exempted[^\n]*test set runs again/m.test(md),
+    'a CHANGELOG line must say the eval gate (P10) is exempted until the test set runs again');
+});

tests/lib/release-prose-pins.test.mjs

@@ -118,8 +118,9 @@ test('runbook: the release check exits as the script does — 0 ready, 1 not rea
   assert.match(before, /0 = ready, 1 = not ready[^.]*, 2 = could not run — never green/);
 });
 
-test('runbook: the eval gate (P10) is named as not built, with where it goes', () => {
-  const p10 = part(read(RUNBOOK), 'Not built yet: the eval gate (P10)');
+test('runbook: the eval gate (P10) is exempted with its reason, and says where it goes', () => {
+  const p10 = part(read(RUNBOOK), 'Exempted: the eval gate (P10)').replace(/\s+/g, ' ');
+  assert.match(p10, /waits for the fixed test set to run again/, 'P10 must say why the gate is exempted');
   assert.ok(p10.includes('scripts/release-check.mjs'), 'P10 must say which file the gate goes into');
 });
 

tests/lib/review-630.test.mjs

@@ -384,7 +384,7 @@ test('review 630 r3: routing reads a kind tag only from its own table, never Obj
     for (const d of ['skills', 'commands', 'agents', 'evals']) cpSync(join(ROOT, d), join(dir, d), { recursive: true });
     const c = join(dir, 'evals', 'zz-proto');
     cpSync(join(ROOT, 'evals', 'skill-test-first-quiet-1'), c, { recursive: true });
-    writeFileSync(join(c, 'prompt.md'), '---\ntags: [constructor, owner=nobody]\n---\n\nWhat time is it?\n');
+    writeFileSync(join(c, 'prompt.md'), '---\ntags: [constructor, owner=nobody, from=test]\n---\n\nWhat time is it?\n');
     const { checkRouting } = awaitImportSync();
     const r = checkRouting(dir);
     assert.ok(!r.errors.some((e) => String(e.message ?? '').includes('zz-proto') || e.case === 'zz-proto'), JSON.stringify(r.errors));