fix: capture 401/403 response body and key alias for credential faults

- get_response_body() returns first 200 chars of response body (single line)
- On 401/403 model probe: report code + body + key_alias
- Monitor key alias: monitor-20260813 (from /etc/litellm-monitor.env on CT 116)
- Failed connections stay probe-failed, 200 stays plain 200
- Do not turn other statuses into credential faults

Signed-off-by: Abiba

scripts/litellm-health-check.py

@@ -73,6 +73,23 @@ def probe_http(url, method="GET", bearer_token=None, data=None, timeout=10, foll
     except subprocess.TimeoutExpired:
         return (000, "timeout after " + str(timeout) + "s")
 
+def get_response_body(url, method="POST", bearer_token=None, data=None, timeout=30):
+    """Get response body for 401/403 credential faults (truncated to 200 chars)"""
+    cmd = "curl -s -m " + str(timeout)
+    if method == "POST":
+        cmd += " -X POST"
+    if bearer_token:
+        cmd += " -H 'Authorization: Bearer " + bearer_token + "'"
+    if data:
+        cmd += " -H 'Content-Type: application/json' -d '" + data + "'"
+    cmd += " '" + url + "'"
+    
+    rc, stdout, stderr = run_command(cmd, timeout)
+    # Return first 200 chars, single line
+    body = stdout.replace('\n', ' ').replace('\t', ' ')[:200] if stdout else ""
+    return body
+
+
 def check_liveliness():
     """Step 1: Liveliness probe"""
     code, _ = probe_http("http://" + BACKEND_HOST + "/litellm/health/liveliness")
@@ -112,6 +129,16 @@ def check_model_probes():
             results.append((model, False, "probe-failed: " + model + " " + failure_kind + " (30s timeout)"))
         elif code == 200:
             results.append((model, True, str(code) + " (target: " + BACKEND_HOST + "/litellm/v1/chat/completions, model=" + model + ")"))
+        elif code in (401, 403):
+            # Credential fault - capture body and key alias
+            body = get_response_body("http://" + BACKEND_HOST + "/litellm/v1/chat/completions",
+                                    method="POST",
+                                    bearer_token=monitor_key,
+                                    data='{"model":"' + model + '","messages":[{"role":"user","content":"health"}],"max_tokens":4}',
+                                    timeout=10)
+            # Resolve key alias
+            alias = "monitor-20260813"  # Known from /etc/litellm-monitor.env on CT 116
+            results.append((model, False, str(code) + " credential fault: body=" + body + " key_alias=" + alias))
         else:
             results.append((model, False, str(code) + " (target: " + BACKEND_HOST + "/litellm/v1/chat/completions, model=" + model + ")"))
     
@@ -132,6 +159,14 @@ def check_model_probes():
                                        timeout=60)
         if code == 000 and failure_kind:
             results.append(("syslog-auto", False, "probe-failed: syslog-auto " + failure_kind + " (60s timeout, retry)"))
+        elif code in (401, 403):
+            body = get_response_body("http://" + BACKEND_HOST + "/litellm/v1/chat/completions",
+                                    method="POST",
+                                    bearer_token=monitor_key,
+                                    data='{"model":"syslog-auto","messages":[{"role":"user","content":"health"}],"max_tokens":4}',
+                                    timeout=10)
+            alias = "monitor-20260813"
+            results.append(("syslog-auto", False, str(code) + " credential fault: body=" + body + " key_alias=" + alias))
         else:
             results.append(("syslog-auto", code == 200, str(code) + " (target: " + BACKEND_HOST + "/litellm/v1/chat/completions, model=syslog-auto)"))
     else: