feat(tester): support isolated full regression workflow

skills/tester/scripts/catalog.py

@@ -42,6 +42,7 @@ LIFECYCLE_SKIP_REASON = {
 }
 TAGS = ("smoke", "full", "slow")
 CANONICAL_RISKS = ("readonly", "mutating", "destructive")
+EXECUTION_PROFILES = ("standard", "isolated-full")
 AUTOMATIONS = ("automated", "assisted", "manual")
 RESULTS = ("pass", "fail", "environment-fail", "skipped", "not-run")
 EXPECTED_KINDS = (
@@ -351,6 +352,21 @@ def risk_index(meta: dict[str, Any], name: str) -> int:
     return risks.index(name)
 
 
+def resolve_execution_profile(meta: dict[str, Any], requested: str | None = None) -> str:
+    """Resolve the run profile without changing the meaning of ``risk``.
+
+    ``isolated-full`` is an execution policy for a resettable test environment:
+    it disables risk/authorization filtering, but leaves the catalog risk value
+    on every case so reports still describe the side effect that was exercised.
+    """
+    profile = requested or meta.get("execution_profile") or "standard"
+    if profile not in EXECUTION_PROFILES:
+        raise SystemExit(
+            f"未知 execution_profile: {profile!r}（可选: {', '.join(EXECUTION_PROFILES)}）"
+        )
+    return str(profile)
+
+
 def host_set(vars_map: dict[str, str]) -> bool:
     host = (vars_map.get("HOST") or "").strip()
     return bool(host) and "${HOST}" not in host
@@ -570,6 +586,7 @@ def expand_run_together(
     skipped: list[dict[str, str]],
     max_i: int,
     automation_filter: str = "automated",
+    bypass_risk: bool = False,
 ) -> tuple[list[dict[str, Any]], list[dict[str, Any]]]:
     groups = run_together_groups(meta)
     if not groups:
@@ -607,7 +624,7 @@ def expand_run_together(
             except SystemExit:
                 skipped.append({"id": cid, "reason": f"未知风险 {risk}"})
                 continue
-            if r_i > max_i:
+            if not bypass_risk and r_i > max_i:
                 skipped.append({"id": cid, "reason": f"risk={risk} 超过上限"})
                 continue
             members.append(public_case(case))
@@ -770,9 +787,11 @@ def mobile_preflight(
 def cmd_select(args: argparse.Namespace, root: Path) -> int:
     meta = load_catalog_meta(root)
     cases = load_all_cases(root)
+    execution_profile = resolve_execution_profile(meta, args.execution_profile)
+    bypass_risk = execution_profile == "isolated-full"
     max_risk = args.max_risk or meta.get("default_max_risk") or "readonly"
     max_i = risk_index(meta, max_risk)
-    automation_filter = args.automation or "automated"
+    automation_filter = args.automation or ("any" if bypass_risk else "automated")
     wanted = set(parse_ids(args.ids or []))
     selected: list[dict[str, Any]] = []
     skipped: list[dict[str, str]] = []
@@ -802,9 +821,15 @@ def cmd_select(args: argparse.Namespace, root: Path) -> int:
                 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":
+            # A mixed catalog keeps legacy cases runnable. Standard keeps the
+            # historical client-only implicit default; isolated-full means
+            # exactly what it says and includes every active test type.
+            if (
+                not bypass_risk
+                and not args.test_type
+                and not args.suite
+                and test_type(case) == "integration"
+            ):
                 continue
             if args.driver and case.get("driver") != args.driver:
                 continue
@@ -821,7 +846,7 @@ def cmd_select(args: argparse.Namespace, root: Path) -> int:
         except SystemExit:
             skipped.append({"id": cid, "reason": f"未知风险 {risk}"})
             continue
-        if r_i > max_i:
+        if not bypass_risk and r_i > max_i:
             skipped.append({"id": cid, "reason": f"risk={risk} 超过上限 {max_risk}"})
             continue
         selected.append(public_case(case))
@@ -833,7 +858,15 @@ def cmd_select(args: argparse.Namespace, root: Path) -> int:
         )
         return 2
 
-    selected, together = expand_run_together(meta, cases, selected, skipped, max_i, automation_filter)
+    selected, together = expand_run_together(
+        meta,
+        cases,
+        selected,
+        skipped,
+        max_i,
+        automation_filter,
+        bypass_risk=bypass_risk,
+    )
 
     # The historical key is kept in the JSON, but the gate now validates both
     # test types before any caller can start a phase.
@@ -867,6 +900,8 @@ def cmd_select(args: argparse.Namespace, root: Path) -> int:
         json.dumps(
             {
                 "max_risk": max_risk,
+                "execution_profile": execution_profile,
+                "risk_filter": "disabled" if bypass_risk else "enforced",
                 "automation": automation_filter,
                 "count": len(selected),
                 "vars": vars_map,
@@ -947,6 +982,12 @@ def validate(root: Path) -> list[str]:
     default_max = meta.get("default_max_risk")
     if default_max not in risks:
         errors.append(f"default_max_risk={default_max!r} 不在 risks 中")
+    profile = meta.get("execution_profile", "standard")
+    if profile not in EXECUTION_PROFILES:
+        errors.append(
+            f"execution_profile={profile!r} 非法，只能是 {', '.join(EXECUTION_PROFILES)}"
+        )
+    isolated_full = profile == "isolated-full"
     gates = meta.get("gates") or {}
     if gates and not isinstance(gates, dict):
         errors.append("catalog.gates 必须是 mapping")
@@ -1073,8 +1114,17 @@ def validate(root: Path) -> list[str]:
             if case.get("risk") in (None, "readonly"):
                 errors.append(f"{where}: risk=readonly 不要填 gate")
         risk = case.get("risk")
-        if risk and risk != "readonly" and risk not in authorize and not gate:
+        if risk and risk != "readonly" and risk not in authorize and not gate and not isolated_full:
             errors.append(f"{where}: {risk} 需要 authorize.{risk} 或 gate")
+        if isolated_full and case.get("lifecycle", "active") == "active" and risk != "readonly":
+            cleanup = case.get("cleanup")
+            cleanup_ok = isinstance(cleanup, dict) and (
+                bool(cleanup.get("steps"))
+                or bool(str(cleanup.get("run") or "").strip())
+                or (cleanup.get("required") is False and bool(str(cleanup.get("reason") or "").strip()))
+            )
+            if not cleanup_ok:
+                errors.append(f"{where}: isolated-full 的写入型用例必须声明 cleanup/rollback steps/run")
         automation = str(case.get("automation") or "automated")
         if automation not in AUTOMATIONS:
             errors.append(f"{where}: 非法 automation={case.get('automation')}")
@@ -1206,7 +1256,19 @@ def cmd_next_id(root: Path, category: str) -> int:
     return 0
 
 
-def authorized(vars_map: dict[str, str], meta: dict[str, Any], case: dict[str, Any]) -> bool:
+def authorized(
+    vars_map: dict[str, str],
+    meta: dict[str, Any],
+    case: dict[str, Any],
+    *,
+    execution_profile: str | None = None,
+) -> bool:
+    profile = resolve_execution_profile(meta, execution_profile)
+    if profile == "isolated-full":
+        # AUTHORIZE_* and gate variables are intentionally not run-time
+        # switches for an isolated resettable environment.  Capability and
+        # cleanup preflight are the safety boundary for this profile.
+        return True
     risk = str(case.get("risk") or "readonly")
     risks = list(meta.get("risks") or ["readonly"])
     lowest = risks[0] if risks else "readonly"
@@ -1226,6 +1288,7 @@ def authorized(vars_map: dict[str, str], meta: dict[str, Any], case: dict[str, A
 
 def cmd_run_script(root: Path, case_id: str) -> int:
     meta = load_catalog_meta(root)
+    execution_profile = resolve_execution_profile(meta)
     vars_map = resolve_vars(root, meta)
     case = next((c for c in load_all_cases(root) if c.get("id") == case_id), None)
     if not case:
@@ -1263,10 +1326,10 @@ def cmd_run_script(root: Path, case_id: str) -> int:
         )
         return 2
     risk = str(case.get("risk") or "readonly")
-    if not authorized(vars_map, meta, case):
+    if not authorized(vars_map, meta, case, execution_profile=execution_profile):
         print(
             json.dumps(
-                {"id": public_id, "result": "skipped", "evidence": f"风险 {risk} 未授权"},
+                {"id": public_id, "result": "skipped", "evidence": f"风险 {risk} 未授权", "execution_profile": execution_profile},
                 ensure_ascii=False,
             )
         )
@@ -1315,6 +1378,7 @@ def cmd_run_script(root: Path, case_id: str) -> int:
             {
                 "id": public_id,
                 "result": "executed",
+                "execution_profile": execution_profile,
                 "exit": proc.returncode,
                 "evidence": evidence,
             },
@@ -1345,6 +1409,12 @@ def build_parser() -> argparse.ArgumentParser:
         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(
+        "--execution-profile",
+        choices=EXECUTION_PROFILES,
+        default=None,
+        help="执行策略；isolated-full 在隔离可重置环境中不按 risk/authorize 筛选",
+    )
     p_sel.add_argument("--driver", choices=DRIVERS)
     p_sel.add_argument(
         "--automation",

skills/tester/scripts/failure_feedback.py

@@ -0,0 +1,150 @@
+#!/usr/bin/env python3
+"""Build structured tester issues and the development feedback route.
+
+This module only writes the run contract.  Updating a remote PR/issue or
+notifying a dispatcher remains an explicit caller-side integration step; no
+network mutation is hidden in the tester.
+"""
+
+from __future__ import annotations
+
+from copy import deepcopy
+from datetime import datetime, timezone
+from typing import Any, Iterable, Mapping
+
+
+ISSUE_TYPES = ("product", "test")
+TRIGGERS = ("pr", "requirement", "bug")
+ISSUE_RESULTS = frozenset({"fail", "environment-fail"})
+
+
+def _now() -> str:
+    return datetime.now(timezone.utc).isoformat()
+
+
+def issue_type_for(result: str) -> str:
+    if result == "fail":
+        return "product"
+    if result == "environment-fail":
+        return "test"
+    raise ValueError(f"只有 fail/environment-fail 可以生成 issue: {result}")
+
+
+def _value(row: Mapping[str, Any], key: str, defaults: Mapping[str, Any]) -> Any:
+    value = row.get(key)
+    return value if value not in (None, "") else defaults.get(key, "")
+
+
+def build_issue(
+    row: Mapping[str, Any],
+    *,
+    defaults: Mapping[str, Any] | None = None,
+    issue_type: str | None = None,
+) -> dict[str, Any]:
+    """Create the stable issue shape required by the run report."""
+    defaults = defaults or {}
+    result = str(row.get("result") or "")
+    if result not in ISSUE_RESULTS:
+        raise ValueError(f"不能为 {result!r} 结果创建 defect: {row.get('id')}")
+    selected_type = issue_type or row.get("issue_type") or issue_type_for(result)
+    if selected_type not in ISSUE_TYPES:
+        raise ValueError(f"issue_type 必须是 product/test: {selected_type}")
+    testcase = str(row.get("testcase") or row.get("id") or "")
+    if not testcase:
+        raise ValueError("issue 缺少 testcase")
+    return {
+        "id": str(row.get("issue_id") or f"TEST-{testcase}-{result}"),
+        "testcase": testcase,
+        "issue_type": selected_type,
+        "result": result,
+        "phase": _value(row, "phase", defaults),
+        "expected": _value(row, "expected", defaults),
+        "observed": _value(row, "observed", defaults),
+        "artifact_hash": _value(row, "artifact_hash", defaults),
+        "environment": _value(row, "environment", defaults),
+        "evidence_path": _value(row, "evidence_path", defaults),
+        "reproduction": _value(row, "reproduction", defaults),
+        "next_step": _value(row, "next_step", defaults),
+        "created_at": str(row.get("created_at") or _now()),
+    }
+
+
+def collect_issues(
+    results: Iterable[Mapping[str, Any]],
+    *,
+    defaults: Mapping[str, Any] | None = None,
+) -> list[dict[str, Any]]:
+    issues: list[dict[str, Any]] = []
+    for row in results:
+        if not isinstance(row, Mapping) or str(row.get("result") or "") not in ISSUE_RESULTS:
+            continue
+        explicit = row.get("issue")
+        source = dict(row)
+        if isinstance(explicit, Mapping):
+            source.update(explicit)
+        issues.append(build_issue(source, defaults=defaults))
+    return issues
+
+
+def feedback_plan(
+    trigger: str,
+    *,
+    target: str = "",
+    related_issue: str = "",
+    dispatcher: str = "dispatcher",
+) -> dict[str, Any]:
+    """Describe the required handoff without performing remote mutations."""
+    if trigger not in TRIGGERS:
+        raise ValueError(f"trigger 必须是 {', '.join(TRIGGERS)}")
+    if trigger == "pr":
+        actions = [
+            {"action": "update_pr", "target": target, "status": "required"},
+            {"action": "update_related_issue", "target": related_issue, "status": "required"},
+            {"action": "notify_dispatcher", "target": dispatcher, "status": "required"},
+            {"action": "reassign_development", "target": dispatcher, "status": "pending"},
+        ]
+        route = "pr-update-issue-dispatcher-reassign"
+    else:
+        actions = [
+            {"action": "return_to_development", "target": target or trigger, "status": "required"},
+        ]
+        route = "development"
+    return {
+        "trigger": trigger,
+        "route": route,
+        "target": target,
+        "related_issue": related_issue,
+        "actions": actions,
+        "remote_mutation": "caller-required",
+        "created_at": _now(),
+    }
+
+
+def attach_feedback(
+    run: Mapping[str, Any],
+    *,
+    trigger: str | None = None,
+    target: str = "",
+    related_issue: str = "",
+    dispatcher: str = "dispatcher",
+    defaults: Mapping[str, Any] | None = None,
+) -> dict[str, Any]:
+    """Return a new run mapping with results, defects and routing preserved."""
+    output = deepcopy(dict(run))
+    results = output.get("results")
+    if not isinstance(results, list):
+        raise ValueError("run 缺少 results 列表")
+    issues = collect_issues(results, defaults=defaults)
+    output["defects"] = issues
+    # Compatibility name for consumers that call the same structure
+    # ``test-issues``.  It is deliberately a copy, not a second source of truth.
+    output["test_issues"] = deepcopy(issues)
+    if trigger:
+        output["feedback"] = feedback_plan(
+            trigger,
+            target=target,
+            related_issue=related_issue,
+            dispatcher=dispatcher,
+        )
+    return output
+

skills/tester/scripts/generate_run_csv.py

@@ -40,6 +40,16 @@ FIELDS = (
     "risk",
     "driver",
     "maps_to",
+    "blocked_by",
+    "issue_id",
+    "issue_type",
+    "expected",
+    "observed",
+    "artifact_hash",
+    "environment",
+    "evidence_path",
+    "reproduction",
+    "next_step",
 )
 
 
@@ -112,6 +122,23 @@ def case_index(root: Path) -> dict[str, dict[str, Any]]:
     return out
 
 
+def issue_index(run: dict[str, Any]) -> dict[str, dict[str, Any]]:
+    """Index canonical defects and compatibility test_issues by testcase."""
+    indexed: dict[str, dict[str, Any]] = {}
+    raw = run.get("defects")
+    if not isinstance(raw, list):
+        raw = run.get("test_issues")
+    if not isinstance(raw, list):
+        return indexed
+    for issue in raw:
+        if not isinstance(issue, dict):
+            continue
+        testcase = str(issue.get("testcase") or issue.get("id") or "")
+        if testcase:
+            indexed.setdefault(testcase, issue)
+    return indexed
+
+
 def export_run_csv(
     root: Path,
     run_path: Path | None = None,
@@ -123,6 +150,7 @@ def export_run_csv(
     path = path.resolve()
     run = load_run(path)
     cases = case_index(root)
+    issues = issue_index(run)
     dest = out or path.with_suffix(".csv")
     dest.parent.mkdir(parents=True, exist_ok=True)
     with dest.open("w", encoding="utf-8-sig", newline="") as handle:
@@ -134,6 +162,9 @@ def export_run_csv(
             cid = str(item["id"])
             result = str(item.get("result") or "")
             case = cases.get(cid) or {}
+            issue = dict(issues.get(cid, {}))
+            if isinstance(item.get("issue"), dict):
+                issue.update(item["issue"])
             client_suite_value = case.get("client_suite") or (
                 case.get("suite") if test_type(case) == "journey" else ""
             )
@@ -154,6 +185,16 @@ def export_run_csv(
                     "risk": case.get("risk") or "",
                     "driver": case.get("driver") or "",
                     "maps_to": case.get("maps_to") or "",
+                    "blocked_by": one_line(item.get("blocked_by")),
+                    "issue_id": issue.get("id") or item.get("issue_id") or "",
+                    "issue_type": issue.get("issue_type") or item.get("issue_type") or "",
+                    "expected": one_line(issue.get("expected") or item.get("expected")),
+                    "observed": one_line(issue.get("observed") or item.get("observed")),
+                    "artifact_hash": issue.get("artifact_hash") or item.get("artifact_hash") or "",
+                    "environment": one_line(issue.get("environment") or item.get("environment")),
+                    "evidence_path": one_line(issue.get("evidence_path") or item.get("evidence_path")),
+                    "reproduction": one_line(issue.get("reproduction") or item.get("reproduction")),
+                    "next_step": one_line(issue.get("next_step") or item.get("next_step")),
                 }
             )
     return dest

skills/tester/scripts/journey.py

@@ -254,6 +254,7 @@ def propagate_results(
     skipped: Mapping[str, str] | None = None,
     continue_on_fail: bool = False,
     policies: Mapping[str, str] | None = None,
+    blocked_by: Mapping[str, Iterable[str]] | None = None,
 ) -> list[dict[str, str]]:
     """Build ordered result rows and mark cases after a blocking failure not-run.
 
@@ -263,15 +264,21 @@ def propagate_results(
     """
     skipped = skipped or {}
     policies = policies or {}
+    blocked_by = blocked_by or {}
     rows: list[dict[str, str]] = []
-    blocked = False
+    blocking_case = ""
     for raw_id in case_ids:
         case_id = str(raw_id)
         if case_id in skipped:
             rows.append({"id": case_id, "result": "skipped", "notes": skipped[case_id]})
             continue
-        if blocked:
-            rows.append({"id": case_id, "result": "not-run", "notes": "前置用例失败，未轮到执行"})
+        if blocking_case:
+            rows.append({
+                "id": case_id,
+                "result": "not-run",
+                "notes": "前置用例失败，未轮到执行",
+                "blocked_by": ",".join(blocked_by.get(case_id) or (blocking_case,)),
+            })
             continue
         result = observed.get(case_id, "not-run")
         if result not in RESULTS:
@@ -279,5 +286,5 @@ def propagate_results(
         rows.append({"id": case_id, "result": result})
         policy = policies.get(case_id)
         if result in ("fail", "environment-fail") and not (continue_on_fail or policy == "continue"):
-            blocked = True
+            blocking_case = case_id
     return rows

skills/tester/scripts/mobile_bundle.py

@@ -390,6 +390,27 @@ def write_run(root: Path, record: dict[str, Any]) -> Path:
     return path
 
 
+def all_active_result_rows(root: Path, *, blocked_by: str) -> list[dict[str, Any]]:
+    """Keep a testcase row for every active catalog entry when preflight blocks."""
+    try:
+        from generate_cases_csv import load_cases
+
+        cases = load_cases(root)
+    except (ImportError, OSError, ValueError, SystemExit):
+        cases = []
+    rows: list[dict[str, Any]] = []
+    for case in cases:
+        if case.get("lifecycle", "active") != "active":
+            continue
+        rows.append({
+            "id": str(case.get("id") or ""),
+            "result": "not-run",
+            "notes": "test-preflight 未通过，未创建移动 session",
+            "blocked_by": [blocked_by],
+        })
+    return rows
+
+
 def run_test_preflight(
     config_path: Path,
     *,
@@ -507,6 +528,7 @@ def execute(args: argparse.Namespace) -> int:
                     record["platforms"][platform].update({"status": "not-run", "reason": "全量 preflight 闸门被另一平台阻断"})
             overall = record.get("preflight", {}).get("status") if "preflight" in record else "environment-fail"
             record.update({"status": overall if overall in {"blocked", "environment-fail"} else "environment-fail", "failure_class": "test-preflight" if "preflight" in record else "automatic-repair-failed", "next_action": "修复列出的平台环境后重跑；默认不会静默降级"})
+            record["results"] = all_active_result_rows(context.root, blocked_by="test-preflight")
         else:
             for platform, (result, node, identity) in prepared.items():
                 try:
@@ -527,7 +549,18 @@ def execute(args: argparse.Namespace) -> int:
         record["evidence"] = context.evidence
     except (EnvironmentFailure, ArtifactFailure) as exc:
         record.update({"status": "environment-fail", "failure_class": "automatic-repair-failed", "error": str(exc), "evidence": context.evidence})
+    if record.get("status") != "ready" and "results" not in record:
+        record["results"] = all_active_result_rows(context.root, blocked_by="test-preflight")
     path = write_run(context.root, record)
+    try:
+        from generate_run_csv import export_run_csv
+
+        record["csv"] = str(export_run_csv(context.root, run_path=path))
+    except (OSError, SystemExit, ValueError):
+        # The YAML run remains the source of truth when a partial/provisioning
+        # root has no catalog cases yet.
+        record["csv"] = ""
+    path.write_text(json.dumps(record, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
     output = {"status": record["status"], "run": str(path), "platforms": record["platforms"], "worktree": record.get("worktree")}
     if record.get("error"):
         output["error"] = record["error"]

skills/tester/scripts/record_issues.py

@@ -0,0 +1,76 @@
+#!/usr/bin/env python3
+"""Append structured tester issue evidence to an existing run snapshot."""
+
+from __future__ import annotations
+
+import argparse
+from pathlib import Path
+from typing import Any
+
+import yaml
+
+from failure_feedback import attach_feedback
+
+
+def main(argv: list[str] | None = None) -> int:
+    parser = argparse.ArgumentParser(description="将 tester 失败结构化回流到 run YAML/CSV")
+    parser.add_argument("--run", required=True, type=Path)
+    parser.add_argument("--trigger", choices=("pr", "requirement", "bug"))
+    parser.add_argument("--target", default="")
+    parser.add_argument("--related-issue", default="")
+    parser.add_argument("--dispatcher", default="dispatcher")
+    parser.add_argument("--testcase", default="", help="为一条失败结果补充 testcase issue 字段")
+    parser.add_argument("--issue-type", choices=("product", "test"))
+    parser.add_argument("--expected", default="")
+    parser.add_argument("--observed", default="")
+    parser.add_argument("--artifact-hash", default="")
+    parser.add_argument("--environment", default="")
+    parser.add_argument("--evidence-path", default="")
+    parser.add_argument("--reproduction", default="")
+    parser.add_argument("--next-step", default="")
+    args = parser.parse_args(argv)
+
+    data: dict[str, Any] = yaml.safe_load(args.run.read_text(encoding="utf-8")) or {}
+    if args.testcase:
+        rows = data.get("results")
+        if not isinstance(rows, list):
+            raise SystemExit("run 缺少 results 列表")
+        row = next((item for item in rows if isinstance(item, dict) and str(item.get("id")) == args.testcase), None)
+        if row is None:
+            raise SystemExit(f"找不到 testcase: {args.testcase}")
+        row["issue"] = {
+            key: value
+            for key, value in {
+                "issue_type": args.issue_type,
+                "expected": args.expected,
+                "observed": args.observed,
+                "artifact_hash": args.artifact_hash,
+                "environment": args.environment,
+                "evidence_path": args.evidence_path,
+                "reproduction": args.reproduction,
+                "next_step": args.next_step,
+            }.items()
+            if value
+        }
+    output = attach_feedback(
+        data,
+        trigger=args.trigger,
+        target=args.target,
+        related_issue=args.related_issue,
+        dispatcher=args.dispatcher,
+    )
+    args.run.write_text(yaml.safe_dump(output, allow_unicode=True, sort_keys=False), encoding="utf-8")
+    csv_path = ""
+    try:
+        from generate_run_csv import export_run_csv
+
+        csv_path = str(export_run_csv(args.run.parents[3], run_path=args.run))
+    except (ImportError, OSError, SystemExit, ValueError):
+        pass
+    print(f"updated {args.run} defects={len(output.get('defects') or [])} csv={csv_path}")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())
+

skills/tester/scripts/summarize_run.py

@@ -103,6 +103,27 @@ def load_yaml_results(path: Path) -> list[dict[str, Any]]:
         errors.append(f"YAML testcase id 重复: {_format_ids(set(duplicates))}")
     if errors:
         raise SummaryError("YAML 校验失败:\n- " + "\n- ".join(errors))
+    issues = data.get("defects", data.get("test_issues"))
+    if issues is not None:
+        if not isinstance(issues, list):
+            raise SummaryError("YAML defects/test_issues 必须是列表")
+        result_ids = set(ids)
+        issue_errors: list[str] = []
+        for index, issue in enumerate(issues, start=1):
+            if not isinstance(issue, dict):
+                issue_errors.append(f"YAML defects[{index}] 不是 mapping")
+                continue
+            testcase = str(issue.get("testcase") or "")
+            issue_type = str(issue.get("issue_type") or "")
+            if not testcase or testcase not in result_ids:
+                issue_errors.append(f"YAML defects[{index}] testcase 无效: {testcase or '(missing)'}")
+            if issue_type not in {"product", "test"}:
+                issue_errors.append(f"YAML defects[{index}] issue_type 无效: {issue_type or '(missing)'}")
+            for field in ("expected", "observed", "artifact_hash", "environment", "evidence_path", "reproduction", "next_step"):
+                if field not in issue:
+                    issue_errors.append(f"YAML defects[{index}] 缺少 {field}")
+        if issue_errors:
+            raise SummaryError("YAML defects 校验失败:\n- " + "\n- ".join(issue_errors))
     return results
 
 

skills/tester/scripts/two_tier.py

@@ -12,6 +12,8 @@ from __future__ import annotations
 from collections.abc import Callable, Iterable, Mapping
 from typing import Any
 
+from failure_feedback import collect_issues
+
 RESULTS = ("pass", "fail", "environment-fail", "skipped", "not-run")
 PHASES = ("preflight", "integration", "journey")
 
@@ -29,10 +31,18 @@ def _case_id(case: Mapping[str, Any] | str) -> str:
     return str(case)
 
 
-def _not_run(cases: Iterable[Mapping[str, Any] | str], reason: str) -> list[dict[str, str]]:
+def _not_run(
+    cases: Iterable[Mapping[str, Any] | str],
+    reason: str,
+    *,
+    blocked_by: Iterable[str] = (),
+) -> list[dict[str, Any]]:
     rows: list[dict[str, str]] = []
+    blockers = [str(item) for item in blocked_by if str(item)]
     for case in cases:
-        row = {"id": _case_id(case), "result": "not-run", "notes": reason}
+        row: dict[str, Any] = {"id": _case_id(case), "result": "not-run", "notes": reason}
+        if blockers:
+            row["blocked_by"] = blockers
         if isinstance(case, Mapping):
             row["test_type"] = str(case.get("test_type") or "")
             row["suite"] = str(
@@ -45,6 +55,37 @@ def _not_run(cases: Iterable[Mapping[str, Any] | str], reason: str) -> list[dict
     return rows
 
 
+def _dependencies(
+    case: Mapping[str, Any] | str,
+    *,
+    default: Iterable[str] = (),
+) -> list[str]:
+    if not isinstance(case, Mapping):
+        return [str(item) for item in default]
+    declared = case.get("depends_on", case.get("dependencies"))
+    if declared is None:
+        return [str(item) for item in default]
+    if isinstance(declared, str):
+        return [declared]
+    if isinstance(declared, Iterable):
+        return [str(item) for item in declared if str(item)]
+    raise ValueError(f"depends_on 必须是字符串或列表: {_case_id(case)}")
+
+
+def _failed_dependencies(dependencies: Iterable[str], results: Mapping[str, Mapping[str, Any]]) -> list[str]:
+    return [
+        dependency
+        for dependency in dependencies
+        if str((results.get(dependency) or {}).get("result"))
+        in {"fail", "environment-fail", "not-run"}
+    ]
+
+
+def _issue_structures(results: list[dict[str, Any]]) -> dict[str, list[dict[str, Any]]]:
+    issues = collect_issues(results)
+    return {"defects": issues, "test_issues": [dict(issue) for issue in issues]}
+
+
 def run_integration_first(
     *,
     preflight_status: str,
@@ -65,18 +106,29 @@ def run_integration_first(
     journey = list(journey_cases)
     if preflight_status != "ready":
         reason = f"test-preflight={preflight_status}，未创建客户端 session"
+        result_rows = _not_run(integration, reason, blocked_by=("test-preflight",)) + _not_run(journey, reason, blocked_by=("test-preflight",))
         return {
             "status": preflight_status,
             "phase": "preflight",
             "session_created": False,
-            "results": _not_run(integration, reason) + _not_run(journey, reason),
+            "results": result_rows,
+            **_issue_structures(result_rows),
         }
 
     results: list[dict[str, Any]] = []
-    integration_failed = False
-    for index, case in enumerate(integration):
-        if integration_failed:
-            results.extend(_not_run([case], "前置 integration 失败，未轮到执行"))
+    results_by_id: dict[str, dict[str, Any]] = {}
+    for case in integration:
+        case_id = _case_id(case)
+        dependencies = _dependencies(case)
+        blocked_by = _failed_dependencies(dependencies, results_by_id)
+        if blocked_by:
+            rows = _not_run(
+                [case],
+                "依赖的 integration 失败，未执行",
+                blocked_by=blocked_by,
+            )
+            results.extend(rows)
+            results_by_id[case_id] = rows[0]
             continue
         outcome = execute_integration(case)
         row = dict(outcome) if isinstance(outcome, Mapping) else {"result": outcome}
@@ -89,20 +141,26 @@ def run_integration_first(
             raise ValueError(f"未知 integration 结果: {row['id']}={result}")
         row["result"] = result
         results.append(row)
-        if result in ("fail", "environment-fail"):
-            integration_failed = True
+        results_by_id[case_id] = row
 
-    if integration_failed:
-        results.extend(_not_run(journey, "integration 失败，依赖的 journey 未执行"))
-        return {
-            "status": "fail" if any(row["result"] == "fail" for row in results) else "environment-fail",
-            "phase": "integration",
-            "session_created": False,
-            "results": results,
-        }
-
-    session = create_journey_session() if journey else None
+    integration_ids = [_case_id(case) for case in integration]
+    has_runnable_journey = any(
+        not _failed_dependencies(_dependencies(case, default=integration_ids), results_by_id)
+        for case in journey
+    )
+    session = create_journey_session() if has_runnable_journey else None
     for case in journey:
+        dependencies = _dependencies(case, default=integration_ids)
+        blocked_by = _failed_dependencies(dependencies, results_by_id)
+        if blocked_by:
+            row = _not_run(
+                [case],
+                "依赖的用例失败，journey 未执行",
+                blocked_by=blocked_by,
+            )[0]
+            results.append(row)
+            results_by_id[_case_id(case)] = row
+            continue
         outcome = execute_journey(session, case)
         row = dict(outcome) if isinstance(outcome, Mapping) else {"result": outcome}
         row["id"] = _case_id(case)
@@ -114,12 +172,14 @@ def run_integration_first(
             raise ValueError(f"未知 journey 结果: {row['id']}={result}")
         row["result"] = result
         results.append(row)
+        results_by_id[_case_id(case)] = row
     status = "fail" if any(row["result"] == "fail" for row in results) else (
         "environment-fail" if any(row["result"] == "environment-fail" for row in results) else "pass"
     )
     return {
         "status": status,
         "phase": "journey" if journey else "integration",
-        "session_created": bool(journey),
+        "session_created": has_runnable_journey,
         "results": results,
+        **_issue_structures(results),
     }