fix(fleet): correct operator documentation validation

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

packages/mosaic/src/fleet/fleet-documentation.spec.ts

@@ -49,23 +49,157 @@ async function markdownFiles(root: string): Promise<string[]> {
 }
 
 function localMarkdownTargets(source: string): string[] {
-  return [...source.matchAll(/\[[^\]]*\]\(([^)]+)\)/g)]
-    .map((match): string => match[1] ?? '')
+  const link =
+    /\[[^\]]*\]\(\s*(?:<([^>]+)>|((?:\\.|[^()\s]|\([^()]*\))+))(?:\s+(?:"[^"]*"|'[^']*'|\([^)]*\)))?\s*\)/g;
+  return [...source.matchAll(link)]
+    .map((match): string => match[1] ?? match[2] ?? '')
     .filter(
       (target): boolean =>
         target !== '' &&
-        !target.startsWith('#') &&
         !target.startsWith('http://') &&
         !target.startsWith('https://') &&
         !target.startsWith('mailto:'),
-    )
-    .map((target): string => decodeURIComponent(target.split('#', 1)[0] ?? ''));
+    );
+}
+
+function markdownHeadingAnchors(source: string): Set<string> {
+  const anchors = new Set<string>();
+  let fence: { readonly marker: string; readonly length: number } | undefined;
+
+  for (const line of source.split('\n')) {
+    const fenceMatch = line.match(/^\s{0,3}(`{3,}|~{3,})(.*)$/);
+    if (fence === undefined && fenceMatch !== null) {
+      const run = fenceMatch[1] ?? '';
+      fence = { marker: run[0] ?? '', length: run.length };
+      continue;
+    }
+    if (fence !== undefined) {
+      const closingRun = line.match(/^\s{0,3}(`{3,}|~{3,})\s*$/)?.[1];
+      if (
+        closingRun !== undefined &&
+        closingRun[0] === fence.marker &&
+        closingRun.length >= fence.length
+      ) {
+        fence = undefined;
+      }
+      continue;
+    }
+
+    const heading = line.match(/^\s{0,3}#{1,6}\s+(.+?)\s*#*\s*$/)?.[1];
+    if (heading === undefined) continue;
+    const base = heading
+      .replace(/!?\[([^\]]*)\]\([^)]*\)/g, '$1')
+      .replace(/<[^>]*>/g, '')
+      .replace(/[`*_~]/g, '')
+      .toLowerCase()
+      .trim()
+      .replace(/[^\p{L}\p{N}\s-]/gu, '')
+      .replace(/\s+/g, '-');
+    let anchor = base;
+    let duplicate = 0;
+    while (anchors.has(anchor)) {
+      duplicate += 1;
+      anchor = `${base}-${duplicate}`;
+    }
+    anchors.add(anchor);
+  }
+  return anchors;
+}
+
+function markdownLinkViolations(
+  sourcePath: string,
+  source: string,
+  documents: Readonly<Record<string, string>>,
+): string[] {
+  const violations: string[] = [];
+  for (const target of localMarkdownTargets(source)) {
+    const [encodedPath = '', encodedFragment] = target.split('#', 2);
+    const targetPath = decodeURIComponent(encodedPath);
+    const normalizedTarget = resolve('/', dirname(sourcePath), targetPath).slice(1);
+    const targetSource = documents[normalizedTarget];
+    if (targetSource === undefined) {
+      violations.push(`${sourcePath} -> ${target}: missing file`);
+      continue;
+    }
+    if (encodedFragment !== undefined) {
+      const fragment = decodeURIComponent(encodedFragment);
+      if (fragment === '' || !markdownHeadingAnchors(targetSource).has(fragment)) {
+        violations.push(`${sourcePath} -> ${target}: missing heading`);
+      }
+    }
+  }
+  return violations;
+}
+
+function exampleSafetyViolationKinds(source: string): string[] {
+  const kinds = new Set<string>();
+  const sensitiveKey = /(?:secret|token|password|credential|MOSAIC_AGENT_COMMAND)/i;
+  const credentialFormat =
+    /(?:\bAKIA[0-9A-Z]{16}\b|\bAIza[0-9A-Za-z_-]{35}\b|\bgh[pousr]_[A-Za-z0-9]{20,}\b|\bgithub_pat_[A-Za-z0-9_]{20,}\b|\bglpat-[A-Za-z0-9_-]{20,}\b|\bnpm_[A-Za-z0-9]{20,}\b|\bsk_live_[A-Za-z0-9]{16,}\b|\bxox[baprs]-[A-Za-z0-9-]{10,}\b|\bBearer\s+[A-Za-z0-9._~+/=-]{16,}\b|\beyJ[A-Za-z0-9_-]{8,}\.[A-Za-z0-9_-]{8,}\.[A-Za-z0-9_-]{8,}\b|-----BEGIN [A-Z ]*PRIVATE KEY-----|\b[A-Za-z][A-Za-z0-9+.-]*:\/\/[^\s/:]+:[^\s/@]+@)/;
+  const privilegedCommand =
+    /(?:^|[\n;&|])\s*(?:[$#>]\s*)?(?:env\s+(?:[A-Za-z_][A-Za-z0-9_]*=[^\s]+\s+)*|command\s+)*(?:(?:sudo|doas|pkexec)\s+|su\s+(?:-|--command\b|-c\b)|(?:systemctl|service|mount|umount|reboot|shutdown|poweroff|halt|chown|chmod|useradd|usermod|groupadd|visudo)\s+)/m;
+
+  if (sensitiveKey.test(source)) kinds.add('sensitive-key');
+  if (credentialFormat.test(source)) kinds.add('credential-format');
+  if (privilegedCommand.test(source)) kinds.add('privileged-command');
+  if (/\b(?:Tess|Ultron)\b/.test(source)) kinds.add('identity');
+  return [...kinds].sort();
 }
 
 function fencedCodeBlocks(source: string): string[] {
   return [...source.matchAll(/```[^\n]*\n(.*?)```/gs)].map((match): string => match[1] ?? '');
 }
 
+const UNSAFE_EXAMPLE_FIXTURES = [
+  {
+    expected: 'privileged-command',
+    source: ['cd /srv && su', 'do systemctl restart example'].join(''),
+  },
+  { expected: 'credential-format', source: ['ghp_', 'a'.repeat(36)].join('') },
+  {
+    expected: 'credential-format',
+    source: ['eyJ', 'a'.repeat(12), '.', 'b'.repeat(12), '.', 'c'.repeat(12)].join(''),
+  },
+] as const;
+
+describe('documentation validation regressions', (): void => {
+  it('rejects a local Markdown link whose heading fragment does not exist', (): void => {
+    expect(
+      markdownLinkViolations('docs/fleet/source.md', '[broken](target.md#missing)', {
+        'docs/fleet/target.md': '# Present',
+      }),
+    ).toEqual(['docs/fleet/source.md -> target.md#missing: missing heading']);
+  });
+
+  it('accepts balanced-parenthesis link destinations and visible-text heading anchors', (): void => {
+    expect(localMarkdownTargets('[guide](guide-(legacy).md#setup "Guide")')).toEqual([
+      'guide-(legacy).md#setup',
+    ]);
+    expect(markdownHeadingAnchors('# [Fleet API](cli.md) behavior')).toContain(
+      'fleet-api-behavior',
+    );
+  });
+
+  it('keeps longer fenced blocks closed only by an equal-or-longer fence', (): void => {
+    expect(markdownHeadingAnchors('````markdown\n```\n# Not a heading\n````\n# Present')).toEqual(
+      new Set(['present']),
+    );
+  });
+
+  it('assigns a free suffix when a prior heading already occupies the next duplicate anchor', (): void => {
+    expect(markdownHeadingAnchors('# Foo\n# Foo-1\n# Foo')).toEqual(
+      new Set(['foo', 'foo-1', 'foo-2']),
+    );
+  });
+
+  it.each(UNSAFE_EXAMPLE_FIXTURES)(
+    'classifies unsafe example fixture as $expected',
+    ({ expected, source }): void => {
+      expect(exampleSafetyViolationKinds(source)).toContain(expected);
+    },
+  );
+});
+
 describe('fleet operator documentation', (): void => {
   it('ships every accepted information-architecture page', async (): Promise<void> => {
     await expect(
@@ -73,20 +207,34 @@ describe('fleet operator documentation', (): void => {
     ).resolves.toHaveLength(REQUIRED_FLEET_PAGES.length);
   });
 
-  it('resolves every local Markdown link in the fleet book and sitemap', async (): Promise<void> => {
+  it('resolves every local Markdown link and heading fragment in the fleet book and sitemap', async (): Promise<void> => {
     const files = [...(await markdownFiles(fleetDocs)), join(repositoryRoot, 'docs', 'SITEMAP.md')];
-    const missing: string[] = [];
+    const documents: Record<string, string> = {};
     for (const file of files) {
-      const source = await readFile(file, 'utf8');
+      const relative = file.slice(repositoryRoot.length + 1);
+      documents[relative] = await readFile(file, 'utf8');
+    }
+
+    const violations: string[] = [];
+    for (const [sourcePath, source] of Object.entries(documents)) {
       for (const target of localMarkdownTargets(source)) {
-        try {
-          await readFile(resolve(dirname(file), target), 'utf8');
-        } catch {
-          missing.push(`${file.slice(repositoryRoot.length + 1)} -> ${target}`);
+        const encodedPath = target.split('#', 1)[0] ?? '';
+        const targetPath = resolve(
+          dirname(join(repositoryRoot, sourcePath)),
+          decodeURIComponent(encodedPath),
+        );
+        const relativeTarget = targetPath.slice(repositoryRoot.length + 1);
+        if (documents[relativeTarget] === undefined) {
+          try {
+            documents[relativeTarget] = await readFile(targetPath, 'utf8');
+          } catch {
+            // The deterministic validator below records the missing target without exposing content.
+          }
         }
       }
+      violations.push(...markdownLinkViolations(sourcePath, source, documents));
     }
-    expect(missing).toEqual([]);
+    expect(violations).toEqual([]);
   });
 
   it('validates the canonical documentation example through the production compiler and resolver', async (): Promise<void> => {
@@ -105,26 +253,20 @@ describe('fleet operator documentation', (): void => {
     ]);
   });
 
-  it('keeps every fenced fleet example free of sensitive values, arbitrary commands, and product-hardcoded identities', async (): Promise<void> => {
+  it('keeps every fenced fleet example free of sensitive values, privileged commands, arbitrary command overrides, and product-hardcoded identities', async (): Promise<void> => {
     const violations: string[] = [];
     for (const file of await markdownFiles(fleetDocs)) {
       const source = await readFile(file, 'utf8');
       for (const [index, block] of fencedCodeBlocks(source).entries()) {
-        if (/(?:secret|token|password|credential|MOSAIC_AGENT_COMMAND)/i.test(block)) {
-          violations.push(`${file.slice(repositoryRoot.length + 1)}#block-${index + 1}: sensitive`);
-        }
-        if (/\b(?:Tess|Ultron)\b/.test(block)) {
-          violations.push(`${file.slice(repositoryRoot.length + 1)}#block-${index + 1}: identity`);
+        for (const kind of exampleSafetyViolationKinds(block)) {
+          violations.push(`${file.slice(repositoryRoot.length + 1)}#block-${index + 1}: ${kind}`);
         }
       }
     }
 
     const rosterSource = await readFile(join(fleetDocs, 'examples', 'roster-v2.yaml'), 'utf8');
-    if (/(?:secret|token|password|credential|MOSAIC_AGENT_COMMAND)/i.test(rosterSource)) {
-      violations.push('docs/fleet/examples/roster-v2.yaml: sensitive');
-    }
-    if (/\b(?:Tess|Ultron)\b/.test(rosterSource)) {
-      violations.push('docs/fleet/examples/roster-v2.yaml: identity');
+    for (const kind of exampleSafetyViolationKinds(rosterSource)) {
+      violations.push(`docs/fleet/examples/roster-v2.yaml: ${kind}`);
     }
     expect(violations).toEqual([]);
   });