feat(xingbang): 兴邦金租 AI 评审平台模块(构建于 mini-OpenClaw)

新增兴邦金租评审项目模块, 作为 mini-OpenClaw 之上的完整交付:
- 五智能体流水线(data_curator/risk_scout/case_finder/approval_advisor/risk_monitor)
- evolution 自进化子系统(轨迹采集+奖励计算+模式归纳prompt增强)
- /api/xingbang/* 端点(config/workflow/stream/evolution/trajectories)
- 运行时产物(客户产出情报卡 + 进化轨迹数据)已 gitignore, 不含隐私

遵循兴邦三档分级审批制度, 数据源指向兴邦实验数据包

backend/xingbang/evolution/trajectory.py

@@ -0,0 +1,110 @@
+"""Trajectory Recorder — 采集五智能体每次调用的完整轨迹。
+
+轨迹格式 (trajectory):
+{
+  "trajectory_id": "traj_<timestamp>",
+  "customer": "客户名",
+  "workflow_id": "...",
+  "steps": [
+     {
+       "agent": "data_curator",
+       "input": "任务描述",
+       "prompt_snippet": "...",
+       "tools": ["read_xingbang_data", ...],
+       "output_file": "...",
+       "output_preview": "...",
+       "success": true/false,
+       "time_ms": 1234
+     }, ...
+  ],
+  "final_result": {...},
+  "cumulative_reward": 0.0
+}
+
+轨迹保存在 <base>/xingbang_evolution/trajectories/*.json。
+"""
+
+from __future__ import annotations
+
+import json
+import time
+import uuid
+from pathlib import Path
+from typing import Any
+
+
+class TrajectoryRecorder:
+    """记录并持久化一次评审流水线的完整执行轨迹。"""
+
+    def __init__(self, base_dir: Path, enabled: bool = True):
+        self._base_dir = Path(base_dir)
+        self._dir = self._base_dir / "xingbang_evolution" / "trajectories"
+        self._dir.mkdir(parents=True, exist_ok=True)
+        self.enabled = enabled
+        # 当前正在记录的轨迹
+        self._current: dict[str, Any] | None = None
+        # metadata (customer 等)
+        self._meta: dict = {}
+        self._start_time: float = 0.0
+
+    def begin(self, workflow_id: str | None = None, customer: str = "") -> str:
+        """开始记录一条新轨迹,返回 trajectory_id。"""
+        self._start_time = time.time()
+        self._current = {
+            "trajectory_id": f"traj_{int(time.time())}_{uuid.uuid4().hex[:6]}",
+            "workflow_id": workflow_id or f"wf_{int(time.time())}",
+            "customer": customer or "",
+            "created_at": self._start_time,
+            "steps": [],
+            "final_result": {},
+            "cumulative_reward": 0.0,
+        }
+        return self._current["trajectory_id"]
+
+    def add_step(self, step: dict[str, Any]) -> None:
+        """追加一步智能体执行记录。"""
+        if self._current is not None:
+            self._current["steps"].append(step)
+
+    def finalize(self, success: bool = True, summary: str = "") -> dict[str, Any]:
+        """结束记录,保存轨迹到磁盘,返回轨迹。"""
+        if self._current is None:
+            return {}
+        self._current["final_result"] = {
+            "success": success,
+            "summary": summary,
+            "duration_ms": int((time.time() - self._start_time) * 1000),
+            "total_steps": len(self._current["steps"]),
+        }
+        # 记录成功/失败
+        trajectory = self._current
+        self._save(trajectory)
+        self._current = None
+        return trajectory
+
+    def _save(self, trajectory: dict[str, Any]) -> Path:
+        path = self._dir / f"{trajectory['trajectory_id']}.json"
+        path.write_text(
+            json.dumps(trajectory, ensure_ascii=False, indent=2),
+            encoding="utf-8",
+        )
+        return path
+
+    # ── 从调用侧采集 ────────────────────────────────────
+    def on_evidence(self, kind: str, data: dict) -> None:
+        """订阅 agents 的 evidence 回调,累积成本步记录。"""
+        if not self.enabled or self._current is None:
+            return
+        if kind == "agent_start":
+            buffered = []
+            self._current["_buffered"] = buffered
+        # 这一步先不展开, 由 workflow 显式调用 add_step 更为清晰
+
+    def list_trajectories(self) -> list[Path]:
+        return sorted(self._dir.glob("*.json"))
+
+    def load(self, trajectory_id: str) -> dict[str, Any]:
+        path = self._dir / f"{trajectory_id}.json"
+        if path.exists():
+            return json.loads(path.read_text(encoding="utf-8"))
+        return {}