fix(health): drop live LLM ping — scan agent.log instead (38s -> 0.1s)

Every /api/xmpp/health fetch ran a real LLM call (22k token system prompt
each). Dashboard refreshes every 10s -> thousands of paid LLM calls/day,
plus 38s latency hanging the health tab on '加载中...'.

LLM health is now derived from the gateway's own agent.log (zero cost,
more accurate than synthetic ping — real traffic results):
- last 'API call #N latency=Xs' -> ok
- last 'API call failed ... HTTP 429...' -> error with summary
- health() runtime 38s -> 0.1s; endpoint 38s -> 0.097s

scripts/test_noping.py

@@ -0,0 +1,20 @@
+import ast, sys
+for p in ['/home/hmo/MoFin/xmpp_logger.py']:
+    try:
+        ast.parse(open(p).read())
+        print('SYNTAX OK:', p)
+    except SyntaxError as e:
+        print('SYNTAX ERROR:', p, e)
+        sys.exit(1)
+sys.path.insert(0, '/home/hmo/MoFin')
+import xmpp_logger as x
+import time, json
+print('== _scan_agent_log ==')
+print(json.dumps(x._scan_agent_log(time.time()), ensure_ascii=False))
+print('== health (no LLM ping) ==')
+import time as t
+t0 = t.time()
+h = x.health()
+print(f'took {t.time()-t0:.1f}s')
+print('llm_provider:', h.get('llm_provider'))
+print('status:', h.get('status'))