fix: M1 exclude_paths '/' jamulix, M2 seed-should_crawl filter, M3 alert dedup

- M1: Removed '/' from jamulix.de exclude_paths (blockaded ALL paths via startswith)
- M2: Seed URLs now pass through should_crawl() in crawler.py
- M3: Alert deduplication via last_alert.json (hash of reasons+level+score)
- Added 11 tests for alert deduplication (277 total, all green)

scanner/alerter.py

@@ -2,11 +2,15 @@
 Alert dispatch: e-mail (smtplib) and HTTP webhook.
 
 Alerts are only sent when the assessment level meets or exceeds min_level.
+Duplicate alerts (identical reasons since last send) are suppressed.
 """
+import hashlib
+import json
 import logging
 import os
 import smtplib
 from email.message import EmailMessage
+from pathlib import Path
 
 import requests
 
@@ -16,10 +20,15 @@ from .report import render_markdown
 logger = logging.getLogger(__name__)
 
 _LEVEL_ORDER = {"green": 0, "yellow": 1, "red": 2}
+_ALERT_STATE_FILE = "last_alert.json"
 
 
 def send_alert(report: dict, cfg: dict) -> None:
-    """Send alert if the report's level is at or above min_level."""
+    """Send alert if the report's level is at or above min_level.
+
+    Duplicate alerts (identical assessment reasons since last send) are suppressed.
+    The dedup state is persisted in data_dir/last_alert.json per site.
+    """
     alerting = cfg.get("alerting", {})
     level = report.get("assessment", {}).get("level", "green")
     min_level = alerting.get("min_level", "yellow")
@@ -28,6 +37,16 @@ def send_alert(report: dict, cfg: dict) -> None:
         logger.debug("Alert suppressed: level=%s < min_level=%s", level, min_level)
         return
 
+    # --- Deduplizierung: nur senden wenn sich die Alarm-Gründe geändert haben ---
+    alert_key = _compute_alert_key(report)
+    data_dir = cfg.get("data_dir")
+    if data_dir:
+        last = _load_last_alert(Path(data_dir))
+        if last and last.get("key") == alert_key:
+            logger.info("Alert suppressed (duplicate, reasons unchanged since %s)",
+                        last.get("sent_at", "unknown"))
+            return
+
     subject = _make_subject(report)
     body = _format_body(report)
 
@@ -39,6 +58,10 @@ def send_alert(report: dict, cfg: dict) -> None:
     if webhook_cfg.get("enabled") and webhook_cfg.get("url"):
         _send_webhook(webhook_cfg["url"], report, subject)
 
+    # Zustand speichern — für nächste Dedup-Runde
+    if data_dir:
+        _save_last_alert(Path(data_dir), alert_key)
+
 
 # ---------------------------------------------------------------------------
 # Formatting
@@ -112,3 +135,40 @@ def _send_webhook(url: str, report: dict, subject: str) -> None:
         logger.info("Webhook delivered: HTTP %s", resp.status_code)
     except Exception as exc:
         logger.error("Webhook alert failed: %s", exc)
+
+
+# ---------------------------------------------------------------------------
+# Deduplication state (last_alert.json in data_dir)
+# ---------------------------------------------------------------------------
+
+def _compute_alert_key(report: dict) -> str:
+    """Stable hash of the assessment reasons + level for deduplication."""
+    payload = {
+        "level": report.get("assessment", {}).get("level", "green"),
+        "score": report.get("assessment", {}).get("score", 0),
+        "reasons": sorted(report.get("assessment", {}).get("reasons", [])),
+    }
+    return hashlib.sha256(json.dumps(payload, sort_keys=True).encode()).hexdigest()
+
+
+def _load_last_alert(data_dir: Path) -> dict:
+    """Load previous alert state. Returns {} on missing/corrupt file."""
+    path = data_dir / _ALERT_STATE_FILE
+    try:
+        return json.loads(path.read_text())
+    except (FileNotFoundError, json.JSONDecodeError, OSError):
+        return {}
+
+
+def _save_last_alert(data_dir: Path, alert_key: str) -> None:
+    """Persist current alert state for next dedup round."""
+    from datetime import datetime, timezone
+    path = data_dir / _ALERT_STATE_FILE
+    state = {
+        "key": alert_key,
+        "sent_at": datetime.now(timezone.utc).isoformat(),
+    }
+    try:
+        path.write_text(json.dumps(state))
+    except OSError as exc:
+        logger.debug("Alert state write failed: %s", exc)