feat: improve sub2api recent error analysis

scripts/src/platform-infra-sub2api-codex/remote-python-sync.ts

@@ -3006,6 +3006,16 @@ def trace_untried_schedulable_accounts(failovers, final_event, account_snapshot)
             })
     return result
 
+def ops_start_time_for_since(since):
+    if not isinstance(since, str):
+        return None
+    match = re.fullmatch(r"\s*(\d+)\s*([smhd])\s*", since.lower())
+    if match is None:
+        return None
+    value = int(match.group(1))
+    multiplier = {"s": 1, "m": 60, "h": 3600, "d": 86400}[match.group(2)]
+    return (datetime.now(timezone.utc) - timedelta(seconds=value * multiplier)).strftime("%Y-%m-%dT%H:%M:%SZ")
+
 def run_trace():
     payload = json.loads(base64.b64decode(PAYLOAD_B64).decode("utf-8")) if PAYLOAD_B64 else {}
     request_id = payload.get("requestId")
@@ -3032,6 +3042,35 @@ def run_trace():
             "returned": len(request_items),
             "total": request_data.get("total", len(request_items)) if isinstance(request_data, dict) else len(request_items),
         }
+        if native_request is None:
+            ops_start_time = ops_start_time_for_since(since)
+            error_query = f"/api/v1/admin/ops/request-errors?q={request_query}&view=all&page=1&page_size=20"
+            if isinstance(ops_start_time, str):
+                error_query += "&start_time=" + quote(ops_start_time, safe="")
+            error_data = ensure_success(
+                curl_api("GET", error_query, bearer=token),
+                "get ops request error fallback",
+            )
+            error_items = extract_items(error_data)
+            native_request = next((item for item in error_items if isinstance(item, dict) and item.get("request_id") == request_id), None)
+            native_request_status.update({
+                "fallback": "sub2api-native-admin-ops-request-errors",
+                "fallbackStartTime": ops_start_time,
+                "fallbackReturned": len(error_items),
+                "fallbackTotal": error_data.get("total", len(error_items)) if isinstance(error_data, dict) else len(error_items),
+            })
+            if isinstance(native_request, dict):
+                native_request = dict(native_request)
+                native_request["kind"] = "error"
+                error_id = native_request.get("id")
+                if isinstance(error_id, int):
+                    try:
+                        detail = ensure_success(curl_api("GET", f"/api/v1/admin/ops/request-errors/{error_id}", bearer=token), "get ops request error detail")
+                        if isinstance(detail, dict):
+                            native_request.update(detail)
+                    except Exception:
+                        pass
+                native_request_status.update({"matched": True, "source": "sub2api-native-admin-ops-request-errors"})
     except Exception as exc:
         native_request_status = {"status": "unavailable", "reason": text(str(exc), 500)}
 
@@ -3119,7 +3158,7 @@ def run_trace():
                 "type": "request-start",
                 "at": native_request.get("created_at"),
                 "requestId": native_request.get("request_id"),
-                "path": None,
+                "path": native_request.get("request_path") or native_request.get("inbound_endpoint"),
                 "model": native_request.get("model"),
                 "accountId": native_request.get("account_id"),
                 "accountName": account_names_by_id.get(native_request.get("account_id")),
@@ -3137,7 +3176,7 @@ def run_trace():
             "type": "final",
             "at": native_request.get("created_at"),
             "requestId": native_request.get("request_id"),
-            "path": None,
+            "path": native_request.get("request_path") or native_request.get("inbound_endpoint"),
             "model": native_request.get("model"),
             "accountId": native_request.get("account_id"),
             "accountName": account_names_by_id.get(native_request.get("account_id")),
@@ -3182,7 +3221,7 @@ def run_trace():
     final_elapsed = round((final_epoch - reference_epoch) * 1000) if final_epoch is not None and reference_epoch is not None else None
     failover_to_final = final_elapsed - first_failover_elapsed if isinstance(final_elapsed, int) and isinstance(first_failover_elapsed, int) else None
     reason = trace_reason(events, final_event)
-    if not matched:
+    if not matched and not isinstance(native_request, dict):
         outcome = "not-found"
     elif isinstance(final_event, dict) and isinstance(final_event.get("statusCode"), int) and final_event.get("statusCode") < 400:
         outcome = "degraded" if forward_failures else ("succeeded-with-failover" if failovers else "succeeded")
@@ -3191,7 +3230,7 @@ def run_trace():
     else:
         outcome = "incomplete"
     return {
-        "ok": proc.returncode == 0 and len(matched) > 0,
+        "ok": proc.returncode == 0 and (len(matched) > 0 or isinstance(native_request, dict)),
         "mode": "trace",
         "targetId": TARGET_ID,
         "runtimeMode": RUNTIME_MODE,