Improve audit pipeline and outreach review

lib/ai/german-copy-guard.ts

@@ -1,3 +1,5 @@
+import { customerToneGuidelines } from "./customer-tone-guidelines";
+
 const GERMAN_MARKERS = new Set([
   "ich",
   "mich",
@@ -31,6 +33,12 @@ const GERMAN_MARKERS = new Set([
   "wenn",
   "für",
   "bei",
+  "kurz",
+  "kurzer",
+  "hinweis",
+  "zur",
+  "kontaktseite",
+  "webauftritt",
 ]);
 
 const ENGLISH_MARKERS = new Set([
@@ -120,6 +128,63 @@ const RAW_TECH_PATTERNS = [
   /\b[0-9a-f]{24}\b/i,
 ];
 
+const EMAIL_TEMPLATE_PATTERNS = [
+  /\bich habe beobachtet\b/i,
+  /\bmir ist aufgefallen\b/i,
+  /\bich schlage vor\b/i,
+  /\bich empfehle\b/i,
+];
+
+const EMAIL_BROCHURE_PATTERNS = [
+  /\bmaßnahmen umsetzen\b/i,
+  /\bconversion[- ]rate steigern\b/i,
+  /\branking positiv beeinflussen\b/i,
+  /\babsprungraten senken\b/i,
+  /\bnachhaltig verbessern\b/i,
+  /\bsignifikant\b/i,
+  /\boptimierungspotenzial(?:e)?\b/i,
+  /\bnutzerzufriedenheit\b/i,
+  /\bsuchmaschinenplatzierung\b/i,
+];
+
+const EMAIL_AUDIT_TOPIC_PATTERNS = [
+  /\bmeta[- ]beschreibung\b/i,
+  /\bpage[- ]?speed\b/i,
+  /\bladezeit(?:en)?\b/i,
+  /\bkontaktformular\b/i,
+  /\bcall[- ]to[- ]action\b/i,
+  /\bmobile(?:n|r|s)? gerät/i,
+  /\bdesktop\b/i,
+  /\bh1[- ]?überschrift(?:en)?\b/i,
+  /\bbewertung(?:en)?\b/i,
+  /\bvertrauenssignal(?:e)?\b/i,
+  /\bstrukturierte daten\b/i,
+];
+
+const EMAIL_MINI_AUDIT_TRANSITIONS = [
+  /\baußerdem\b/i,
+  /\bzudem\b/i,
+  /\bein weiterer punkt\b/i,
+  /\bschließlich\b/i,
+  /\bdurch die umsetzung\b/i,
+];
+
+const EMAIL_LOW_FRICTION_ASK_PATTERNS = [
+  /\bsoll ich ihnen\b/i,
+  /\bwäre (?:das|ein kurzer hinweis)\b/i,
+  /\bdarf ich ihnen\b/i,
+  /\bkann ich ihnen\b/i,
+  /\boffen für\b/i,
+];
+
+const INFORMAL_EMAIL_ADDRESS_PATTERNS = [
+  /\bdu\b/i,
+  /\bdir\b/i,
+  /\bdein(?:e[rmns]?)?\b/i,
+  /\beuch\b/i,
+  /\beuer(?:e[rmns]?)?\b/i,
+];
+
 export type GermanCopyGuardIssue = {
   field: string;
   rule: string;
@@ -256,6 +321,178 @@ function hasRawArtifact(value: string): boolean {
   return RAW_TECH_PATTERNS.some((pattern) => pattern.test(value));
 }
 
+function countMatches(value: string, patterns: readonly RegExp[]) {
+  return patterns.reduce(
+    (count, pattern) => count + (pattern.test(value) ? 1 : 0),
+    0,
+  );
+}
+
+function countRegexMatches(value: string, pattern: RegExp) {
+  return value.match(pattern)?.length ?? 0;
+}
+
+function countSentences(value: string) {
+  return value
+    .split(/[.!?]+/)
+    .map((sentence) => sentence.trim())
+    .filter(Boolean).length;
+}
+
+function countParagraphs(value: string) {
+  return value
+    .trim()
+    .split(/\n\s*\n/)
+    .map((paragraph) => paragraph.trim())
+    .filter(Boolean).length;
+}
+
+function startsWithTemplateEmailPhrase(value: string) {
+  return new RegExp(
+    String.raw`^\s*(?:(?:guten tag|hallo|sehr geehrte[^,.!?]*|moin)[,.!?\s]+)?(?:${EMAIL_TEMPLATE_PATTERNS.map(
+      (pattern) => pattern.source,
+    ).join("|")})`,
+    "i",
+  ).test(value);
+}
+
+function hasLowFrictionAsk(value: string) {
+  return (
+    value.includes("?") &&
+    EMAIL_LOW_FRICTION_ASK_PATTERNS.some((pattern) => pattern.test(value))
+  );
+}
+
+function validateEmailSubjectTone(
+  issues: GermanCopyGuardIssue[],
+  subject: string,
+) {
+  const trimmed = subject.trim();
+  if (!trimmed) {
+    return;
+  }
+
+  const words = tokenizeWords(trimmed);
+  const { subject: subjectRules } = customerToneGuidelines.email;
+  const hasInflatedSubject =
+    /optimierungspotenzial/i.test(trimmed) ||
+    /mehr sichtbarkeit/i.test(trimmed) ||
+    /bessere nutzererfahrung/i.test(trimmed) ||
+    /kundengewinnung/i.test(trimmed) ||
+    /conversion/i.test(trimmed) ||
+    /ranking/i.test(trimmed);
+
+  if (
+    trimmed.length > subjectRules.maxCharacters ||
+    words.length < subjectRules.minWords ||
+    words.length > subjectRules.maxWords ||
+    /:/.test(trimmed) ||
+    hasInflatedSubject
+  ) {
+    addIssue(
+      issues,
+      "emailSubject",
+      "unnatural_email_subject",
+      "Betreff wirkt zu pitchig, zu lang oder nicht wie eine kurze Erstmail.",
+    );
+  }
+}
+
+function validateEmailBodyTone(
+  issues: GermanCopyGuardIssue[],
+  body: string,
+) {
+  const trimmed = body.trim();
+  if (!trimmed) {
+    return;
+  }
+
+  const { email } = customerToneGuidelines;
+  const wordCount = tokenizeWords(trimmed).length;
+  if (wordCount < email.wordCount.min || wordCount > email.wordCount.max) {
+    addIssue(
+      issues,
+      "emailBody",
+      "unnatural_email_length",
+      "E-Mail sollte als Erstkontakt kurz bleiben: 60-130 Wörter.",
+    );
+  }
+
+  if (countSentences(trimmed) > email.maxSentences) {
+    addIssue(
+      issues,
+      "emailBody",
+      "too_many_email_sentences",
+      "E-Mail enthält zu viele Sätze für eine erste Kontaktaufnahme.",
+    );
+  }
+
+  if (countParagraphs(trimmed) > email.maxParagraphs) {
+    addIssue(
+      issues,
+      "emailBody",
+      "too_many_email_paragraphs",
+      "E-Mail sollte höchstens zwei kurze Absätze enthalten.",
+    );
+  }
+
+  const templatePhraseCount = EMAIL_TEMPLATE_PATTERNS.reduce(
+    (count, pattern) => count + countRegexMatches(trimmed, new RegExp(pattern.source, "gi")),
+    0,
+  );
+  const firstPersonCount = countRegexMatches(trimmed, /\bich\b/gi);
+  if (
+    startsWithTemplateEmailPhrase(trimmed) ||
+    templatePhraseCount >= 2 ||
+    firstPersonCount > 2
+  ) {
+    addIssue(
+      issues,
+      "emailBody",
+      "formulaic_email_tone",
+      "E-Mail wirkt formelhaft; vermeide wiederholte Ich-habe-/Ich-schlage-vor-Muster.",
+    );
+  }
+
+  if (EMAIL_BROCHURE_PATTERNS.some((pattern) => pattern.test(trimmed))) {
+    addIssue(
+      issues,
+      "emailBody",
+      "brochure_email_language",
+      "E-Mail klingt nach Broschüre statt nach natürlicher Erstansprache.",
+    );
+  }
+
+  const topicCount = countMatches(trimmed, EMAIL_AUDIT_TOPIC_PATTERNS);
+  const transitionCount = countMatches(trimmed, EMAIL_MINI_AUDIT_TRANSITIONS);
+  if (topicCount >= 4 || transitionCount >= 2) {
+    addIssue(
+      issues,
+      "emailBody",
+      "email_reads_like_mini_audit",
+      "E-Mail bündelt zu viele Audit-Punkte und sollte höchstens zwei Befunde anreißen.",
+    );
+  }
+
+  if (INFORMAL_EMAIL_ADDRESS_PATTERNS.some((pattern) => pattern.test(trimmed))) {
+    addIssue(
+      issues,
+      "emailBody",
+      "informal_email_address",
+      "E-Mail sollte unbekannte lokale Betriebe formal mit Sie/Ihnen ansprechen.",
+    );
+  }
+
+  if (!hasLowFrictionAsk(trimmed)) {
+    addIssue(
+      issues,
+      "emailBody",
+      "missing_low_friction_ask",
+      "E-Mail sollte mit einer kurzen, leicht beantwortbaren Frage enden.",
+    );
+  }
+}
+
 function validateTextField(
   issues: GermanCopyGuardIssue[],
   field: string,
@@ -372,10 +609,12 @@ export function validateEmailCopy(email: EmailCopy): GermanCopyGuardResult {
   const issues: GermanCopyGuardIssue[] = [];
 
   validateTextField(issues, "emailSubject", email.subject, { skipIfTooShort: true });
+  validateEmailSubjectTone(issues, email.subject);
   validateTextField(issues, "emailBody", email.body, {
-    requireIchForm: true,
-    requireObservationAndSuggestion: true,
+    requireIchForm: false,
+    requireObservationAndSuggestion: false,
   });
+  validateEmailBodyTone(issues, email.body);
 
   return { passed: issues.length === 0, issues };
 }
@@ -453,13 +692,15 @@ export function validateCustomerFacingCopy(input: GermanCustomerCopy): GermanCop
     validateTextField(issues, "emailSubject", input.emailSubject, {
       skipIfTooShort: true,
     });
+    validateEmailSubjectTone(issues, input.emailSubject);
   }
 
   if (input.emailBody !== undefined) {
     validateTextField(issues, "emailBody", input.emailBody, {
-      requireIchForm: true,
-      requireObservationAndSuggestion: true,
+      requireIchForm: false,
+      requireObservationAndSuggestion: false,
     });
+    validateEmailBodyTone(issues, input.emailBody);
   }
 
   if (input.callScript) {