fix: 排序作用于组内事件+时间线限高滚动+UTM别名归一消冲突误报

- attribution.py：新增 _canon 归一（小写/去协议与域名后缀/别名表 fb→facebook、百度→baidu 等/仅留字母数字汉字），
  冲突判定改为两路各自归一后比较——同源升级 combined 并在 detail 记 utm_source 原文，仍不同才 conflict
- detail.vue：orderedDays 组内会话/事件同步翻转（desc=组与组内都最新在前，asc=都最早在前）；
  .tl-body 限高 calc(100vh - 380px) 卡内滚动，日期组头随内容滚动
- test_attribution.py：+4 用例（fb↔facebook、chatgpt.com↔ChatGPT、google↔facebook 仍冲突、百度↔baidu）

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

server/tracker/tests/test_attribution.py

@@ -113,6 +113,38 @@ def test_utm_contradicting_referrer_is_conflict_with_both_evidences():
     assert utm_ev["platform"] == "google" and utm_ev["evidence_kind"] == "utm_label"
 
 
+# ------------------------------------------- 别名归一（消 conflict 误报）
+def test_utm_alias_fb_matches_facebook_referrer():
+    r = classify(referrer_url="https://facebook.com/l/abc", utm={"utm_source": "fb"})
+    assert r["resolution"] != "conflict"                # fb↔Facebook 归一后同源，不是矛盾
+    assert r["channel"] == "social" and r["platform"] == "Facebook"
+    assert r["evidence_kind"] == "combined"
+    assert r["detail"].get("utm_source") == "fb"        # 归一对齐时原文并记进 detail
+
+
+def test_utm_with_domain_suffix_matches_bare_platform():
+    r = classify(referrer_url="https://chatgpt.com/c/abc", utm={"utm_source": "chatgpt.com"})
+    assert r["evidence_kind"] == "combined"             # chatgpt.com → chatgpt 与 ChatGPT 同源
+    assert r["platform"] == "ChatGPT"
+    assert r["detail"].get("utm_source") == "chatgpt.com"
+    r2 = classify(referrer_url="https://www.google.com/search?q=x",
+                  utm={"utm_source": "google.ru"})      # 国家域名后缀 → google
+    assert r2["evidence_kind"] == "combined" and r2["platform"] == "Google"
+
+
+def test_utm_alias_still_conflict_when_platforms_differ():
+    r = classify(referrer_url="https://facebook.com/l/abc", utm={"utm_source": "google"})
+    assert r["resolution"] == "conflict"                # 归一后仍不同 → 保持矛盾并列
+
+
+def test_utm_chinese_alias_baidu_matches():
+    r = classify(referrer_url="https://www.baidu.com/s?wd=x", utm={"utm_source": "百度"})
+    assert r["resolution"] != "conflict"                # 百度 ↔ baidu.com(平台"百度") 同源
+    assert r["channel"] == "natural_search" and r["platform"] == "百度"
+    assert r["evidence_kind"] == "combined"
+    assert r["detail"].get("utm_source") == "百度"
+
+
 def test_utm_only_is_label_only():
     r = classify(utm={"utm_source": "newsletter"})
     assert r["channel"] == "referral"               # 未知标签 → 有名 referral，但状态诚实标注