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)

tests/test_alerter.py

@@ -1,10 +1,20 @@
 """Tests for scanner/alerter.py — alert dispatch (e-mail + webhook)."""
+import json
 import os
+from pathlib import Path
+from tempfile import TemporaryDirectory
 from unittest.mock import MagicMock, call, patch
 
 import pytest
 
-from scanner.alerter import _make_subject, _format_body, send_alert
+from scanner.alerter import (
+    _compute_alert_key,
+    _load_last_alert,
+    _save_last_alert,
+    _make_subject,
+    _format_body,
+    send_alert,
+)
 
 
 # ---------------------------------------------------------------------------
@@ -38,8 +48,9 @@ def _cfg(
     pw_env: str = "TEST_SMTP_PW",
     webhook_enabled: bool = False,
     webhook_url: str = "",
+    data_dir: str | None = None,
 ) -> dict:
-    return {
+    cfg: dict = {
         "alerting": {
             "min_level": min_level,
             "email": {
@@ -58,6 +69,9 @@ def _cfg(
             },
         }
     }
+    if data_dir is not None:
+        cfg["data_dir"] = data_dir
+    return cfg
 
 
 # ---------------------------------------------------------------------------
@@ -284,3 +298,93 @@ class TestSendAlertWebhook:
         # green is below min_level yellow → suppressed anyway, but let's test enabled+green=red path
         cfg["alerting"]["min_level"] = "green"
         send_alert(_report("green"), cfg)
+
+
+# ---------------------------------------------------------------------------
+# Deduplication
+# ---------------------------------------------------------------------------
+
+class TestComputeAlertKey:
+    def test_same_reasons_same_key(self):
+        r1 = _report("red", "https://a.de")
+        r2 = _report("red", "https://b.de")  # anderer Target, gleiche reasons/level/score
+        assert _compute_alert_key(r1) == _compute_alert_key(r2)
+
+    def test_different_score_different_key(self):
+        r1 = _report("yellow")  # score=30
+        r2 = _report("red")     # score=80
+        assert _compute_alert_key(r1) != _compute_alert_key(r2)
+
+    def test_different_reasons_different_key(self):
+        r1 = _report("yellow")
+        r1["assessment"]["reasons"] = ["Grund A"]
+        r2 = _report("yellow")
+        r2["assessment"]["reasons"] = ["Grund B"]
+        assert _compute_alert_key(r1) != _compute_alert_key(r2)
+
+    def test_reasons_order_independent(self):
+        r1 = _report("yellow")
+        r1["assessment"]["reasons"] = ["B", "A", "C"]
+        r2 = _report("yellow")
+        r2["assessment"]["reasons"] = ["C", "A", "B"]  # gleiche, andere Reihenfolge
+        assert _compute_alert_key(r1) == _compute_alert_key(r2)
+
+
+class TestLoadSaveLastAlert:
+    def test_load_missing_file_returns_empty(self):
+        with TemporaryDirectory() as tmp:
+            state = _load_last_alert(Path(tmp))
+            assert state == {}
+
+    def test_load_corrupt_json_returns_empty(self):
+        with TemporaryDirectory() as tmp:
+            (Path(tmp) / "last_alert.json").write_text("{invalid")
+            state = _load_last_alert(Path(tmp))
+            assert state == {}
+
+    def test_save_and_load_roundtrip(self):
+        with TemporaryDirectory() as tmp:
+            d = Path(tmp)
+            _save_last_alert(d, "abc123")
+            state = _load_last_alert(d)
+            assert state["key"] == "abc123"
+            assert "sent_at" in state
+
+
+class TestSendAlertDedup:
+    @patch("scanner.alerter._send_email")
+    def test_first_alert_sent(self, mock_email):
+        with TemporaryDirectory() as tmp:
+            cfg = _cfg(data_dir=tmp)
+            send_alert(_report("yellow"), cfg)
+            mock_email.assert_called_once()
+
+    @patch("scanner.alerter._send_email")
+    def test_identical_second_alert_suppressed(self, mock_email):
+        with TemporaryDirectory() as tmp:
+            cfg = _cfg(data_dir=tmp)
+            report = _report("yellow")
+            send_alert(report, cfg)
+            send_alert(report, cfg)  # gleiche reasons → unterdrückt
+            assert mock_email.call_count == 1
+
+    @patch("scanner.alerter._send_email")
+    def test_changed_reasons_triggers_new_alert(self, mock_email):
+        with TemporaryDirectory() as tmp:
+            cfg = _cfg(data_dir=tmp)
+            r1 = _report("yellow")
+            r1["assessment"]["reasons"] = ["Grund A"]
+            send_alert(r1, cfg)
+
+            r2 = _report("yellow")
+            r2["assessment"]["reasons"] = ["Grund B"]  # anderer Grund
+            send_alert(r2, cfg)
+
+            assert mock_email.call_count == 2
+
+    @patch("scanner.alerter._send_email")
+    def test_no_data_dir_sends_every_time(self, mock_email):
+        cfg = _cfg(data_dir=None)  # kein data_dir → keine Dedup
+        send_alert(_report("yellow"), cfg)
+        send_alert(_report("yellow"), cfg)
+        assert mock_email.call_count == 2