Add project README and reason/quote fields to classifier response

- README.md: full project overview with setup, training, API, and RSpamd integration docs
- server.py: add reason (human-readable explanation) and quote (suspicious snippet) to response
- spamllm.lua: pass reason and quote through to RSpamd symbol description for logs/UI

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

server.py

@@ -62,6 +62,8 @@ class ClassifyResponse(BaseModel):
     score: float  # RSpamd-kompatibler Score (0-15)
     language: str  # Erkannte Sprache
     foreign_lang_bonus: float  # Zusätzlicher Score für Fremdsprache
+    reason: str  # Menschenlesbare Begründung
+    quote: str  # Verdächtigster Textausschnitt
 
 
 def detect_language(text: str) -> tuple[str, bool]:
@@ -79,6 +81,65 @@ def detect_language(text: str) -> tuple[str, bool]:
         return "unknown", False
 
 
+# Spam-Signalwörter für Quote-Extraktion (DE + EN)
+SPAM_PATTERNS = [
+    "click here", "klicken sie", "jetzt bestellen", "order now",
+    "act now", "sofort", "dringend", "urgent", "verify your",
+    "bestätigen sie", "gewonnen", "you won", "congratulations",
+    "herzlichen glückwunsch", "free", "gratis", "kostenlos",
+    "100%", "guarantee", "garantie", "limited time", "nur heute",
+    "unsubscribe", "abmelden", "no risk", "kein risiko",
+    "bank details", "bankdaten", "password", "passwort",
+    "account suspended", "konto gesperrt", "credit card", "kreditkarte",
+    "viagra", "cialis", "pharmacy", "apotheke", "discount", "rabatt",
+    "million", "prize", "preis", "winner", "gewinner",
+]
+
+
+def find_spam_quote(subject: str, body: str) -> str:
+    """Findet den verdächtigsten Textausschnitt in der Mail."""
+    full_text = f"{subject} {body}".lower()
+
+    for pattern in SPAM_PATTERNS:
+        pos = full_text.find(pattern)
+        if pos != -1:
+            # Kontext um das Match herum extrahieren (max 120 Zeichen)
+            original = f"{subject} {body}"
+            start = max(0, pos - 30)
+            end = min(len(original), pos + len(pattern) + 60)
+            snippet = original[start:end].strip()
+            if start > 0:
+                snippet = "..." + snippet
+            if end < len(original):
+                snippet = snippet + "..."
+            return snippet
+
+    # Kein Pattern gefunden -> ersten Satz des Bodys als Fallback
+    if body:
+        first_sentence = body.split(".")[0].strip()
+        return first_sentence[:120] + ("..." if len(first_sentence) > 120 else "")
+    return subject[:120] if subject else ""
+
+
+def build_reason(spam_prob: float, is_foreign: bool, language: str) -> str:
+    """Baut eine menschenlesbare Begründung zusammen."""
+    reasons = []
+
+    if spam_prob > 0.8:
+        reasons.append(f"High spam confidence ({spam_prob:.0%})")
+    elif spam_prob > 0.5:
+        reasons.append(f"Moderate spam confidence ({spam_prob:.0%})")
+    elif spam_prob > 0.3:
+        reasons.append(f"Low spam confidence ({spam_prob:.0%})")
+    else:
+        reasons.append(f"Likely ham ({1 - spam_prob:.0%} confidence)")
+
+    if is_foreign:
+        reasons.append(f"Unexpected language: {language} (not DE/EN)")
+
+    return "; ".join(reasons)
+
+
 @app.post("/classify", response_model=ClassifyResponse)
 async def classify(request: ClassifyRequest):
     # Kombiniere Mail-Felder zu einem Text
@@ -106,12 +167,17 @@ async def classify(request: ClassifyRequest):
     # Spam-Schwelle nach Bonus neu bewerten
     effective_spam = spam_prob > 0.5 or (is_foreign and spam_prob > 0.3)
 
+    reason = build_reason(spam_prob, is_foreign, language)
+    quote = find_spam_quote(request.subject, request.body) if effective_spam else ""
+
     return ClassifyResponse(
         is_spam=effective_spam,
         confidence=spam_prob,
         score=round(rspamd_score, 2),
         language=language,
         foreign_lang_bonus=lang_bonus,
+        reason=reason,
+        quote=quote,
     )