feat(tester): add integration-first journey execution

skills/tester/scripts/catalog.py

@@ -18,7 +18,15 @@ from datetime import datetime, timezone
 from pathlib import Path
 from typing import Any
 
-from journey import CLIENT_SUITES, client_suite, contract_errors, preflight as journey_preflight
+from journey import (
+    CLIENT_SUITES,
+    INTEGRATION_SUITES,
+    TEST_TYPES,
+    contract_errors,
+    preflight as journey_preflight,
+    suite as case_suite,
+    test_type,
+)
 
 try:
     import yaml
@@ -370,7 +378,7 @@ def cmd_list(root: Path) -> int:
     pending = [c for c in cases if c.get("lifecycle") == "pending"]
     print(f"## 测试目录  active {len(active)} / pending {len(pending)} / retired {len(retired)}")
     print()
-    headers = ["分类", "标题", "条数", "smoke"] + risks + list(DRIVERS)
+    headers = ["分类", "标题", "条数", "journey", "integration", "smoke"] + risks + list(DRIVERS)
     print("| " + " | ".join(headers) + " |")
     print("| " + " | ".join("---" for _ in headers) + " |")
 
@@ -388,7 +396,14 @@ def cmd_list(root: Path) -> int:
         title = (cats_meta.get(cat) or {}).get("title") or (
             group[0].get("_file_title") if group else ""
         )
-        row = [cat, str(title), str(len(group)), str(sum(1 for c in group if c.get("tag") == "smoke"))]
+        row = [
+            cat,
+            str(title),
+            str(len(group)),
+            str(sum(1 for c in group if test_type(c) == "journey")),
+            str(sum(1 for c in group if test_type(c) == "integration")),
+            str(sum(1 for c in group if c.get("tag") == "smoke")),
+        ]
         for risk in risks:
             row.append(str(sum(1 for c in group if c.get("risk") == risk)))
         for driver in DRIVERS:
@@ -783,7 +798,13 @@ def cmd_select(args: argparse.Namespace, root: Path) -> int:
                 continue
             if args.tag and case.get("tag") != args.tag:
                 continue
-            if args.suite and client_suite(case) != args.suite:
+            if args.test_type and test_type(case) != args.test_type:
+                continue
+            if args.suite and case_suite(case) != args.suite:
+                continue
+            # A mixed catalog keeps legacy cases runnable, but the implicit
+            # default is the client journey surface. Integration is opt-in.
+            if not args.test_type and not args.suite and test_type(case) == "integration":
                 continue
             if args.driver and case.get("driver") != args.driver:
                 continue
@@ -814,6 +835,8 @@ def cmd_select(args: argparse.Namespace, root: Path) -> int:
 
     selected, together = expand_run_together(meta, cases, selected, skipped, max_i, automation_filter)
 
+    # The historical key is kept in the JSON, but the gate now validates both
+    # test types before any caller can start a phase.
     journey_gate = journey_preflight(selected, sessions=meta.get("sessions") or {})
     if journey_gate["status"] == "blocked":
         print(json.dumps({"preflight": journey_gate, "journey_preflight": journey_gate}, ensure_ascii=False, indent=2))
@@ -850,6 +873,10 @@ def cmd_select(args: argparse.Namespace, root: Path) -> int:
                 "artifacts": meta.get("artifacts") or {},
                 "preflight": preflight,
                 "journey_preflight": journey_gate,
+                "test_types": {
+                    "journey": sum(1 for case in selected if test_type(case) == "journey"),
+                    "integration": sum(1 for case in selected if test_type(case) == "integration"),
+                },
                 "skipped": skipped,
                 "run_together": together,
                 "status_probe": status_probes,
@@ -943,6 +970,17 @@ def validate(root: Path) -> list[str]:
             missing_suites = sorted(set(CLIENT_SUITES) - set(client_suites))
             if missing_suites:
                 errors.append("catalog.client_suites 缺少标准套件: " + ", ".join(missing_suites))
+    integration_suites = meta.get("integration_suites")
+    if integration_suites is not None:
+        if not isinstance(integration_suites, dict):
+            errors.append("catalog.integration_suites 必须是 mapping")
+        else:
+            unknown = sorted(set(integration_suites) - set(INTEGRATION_SUITES))
+            if unknown:
+                errors.append("catalog.integration_suites 含非法套件: " + ", ".join(unknown))
+            missing_suites = sorted(set(INTEGRATION_SUITES) - set(integration_suites))
+            if missing_suites:
+                errors.append("catalog.integration_suites 缺少标准套件: " + ", ".join(missing_suites))
     artifacts = meta.get("artifacts")
     if artifacts is not None:
         if not isinstance(artifacts, dict):
@@ -1297,8 +1335,15 @@ def build_parser() -> argparse.ArgumentParser:
     p_sel.add_argument("--category")
     p_sel.add_argument("--id", action="append", dest="ids", default=[])
     p_sel.add_argument("--tag", choices=TAGS)
-    p_sel.add_argument("--suite", "--client-suite", dest="suite", choices=CLIENT_SUITES,
-                       help="客户端旅程套件")
+    p_sel.add_argument(
+        "--suite", "--client-suite", dest="suite",
+        choices=[*CLIENT_SUITES, *INTEGRATION_SUITES],
+        help="客户端或集成测试套件；不传时默认不选 integration",
+    )
+    p_sel.add_argument(
+        "--test-type", choices=TEST_TYPES, default=None,
+        help="按顶层 test_type 筛选；integration 必须显式选择",
+    )
     p_sel.add_argument("--max-risk")
     p_sel.add_argument("--driver", choices=DRIVERS)
     p_sel.add_argument(