feat: routing shadow evaluation v0b (read-only, never auto-activates)

New pure module cloud/routing_shadow.py: parse worker_routing
audit details (old format without suggested model parses with
suggested unknown, never guessed), evaluate per-tier routed
samples with one-task-one-sample dedup, explicit tasks counted
separately, status under the chosen model, token/USD with
unpriced tokens kept apart, and a min-20 gate per tier. The
report explicitly marks the counterfactual not_measured:
shadow suggested models never ran, so no suggested-vs-chosen
cost/quality comparison is possible. Worker audit detail now
includes suggested/chosen for future rows. GET /routing-shadow
serves the report (project read permission, truncated flag
over 10000 audit rows, cost table ensured so a fresh DB does
not 500).

Tests: test_routing_shadow.py (5 tests).

cloud/server.py

@@ -66,6 +66,7 @@ from cloud.auth import AuthStore
 from cloud.coordinator import parse_parts as _coord_parse_parts
 from cloud.coordinator import validate_parts as _coord_validate_parts
 from cloud.cost import CostStore, unpriced_token_cap
+from cloud.routing_shadow import evaluate_shadow as _evaluate_shadow
 from cloud.db import connect as _db_connect
 from cloud.db import create_database as _create_database
 from cloud.db import init_postgres_schema as _init_postgres_schema
@@ -2341,6 +2342,8 @@ class CloudControlPlaneHandler(BaseHTTPRequestHandler):
             self._create_upload(user_id)
         elif path == "/tasks" and method == "GET":
             self._list_tasks(user_id, query)
+        elif path == "/routing-shadow" and method == "GET":
+            self._routing_shadow(user_id, query)
         elif path == "/admin/sweep" and method == "POST":
             self._admin_sweep(user_id)
         elif path == "/admin/backup" and method == "POST":
@@ -4129,6 +4132,80 @@ class CloudControlPlaneHandler(BaseHTTPRequestHandler):
                               "daily": daily})
 
     # -- 任务成本与模型总览 ----------------------------------------------
+    def _routing_shadow(self, user_id, query):
+        # GET /routing-shadow?project_id=...：路由 v0b 影子评估，
+        # 只读，不改任何模式、不激活任何档。权限同 _list_tasks：
+        # 项目 read 权限，没有则 403。审计行按 created_at 升序
+        # 取（评估里按任务去重，第一次出现即样本），上限 10000
+        # 行——超过时报告里仍按取到的行算，调用方须知样本被
+        # 截断（见 response 的 truncated 字段），不假装全量。
+        project_ids = query.get("project_id")
+        project_id = project_ids[0] if project_ids else None
+        if not project_id:
+            self._send_json(400, {"error": "project_id required"})
+            return
+        with _auth_store(self.server.db_path) as store:
+            if not store.check_permission(user_id, project_id, "read"):
+                self._send_json(403, {"error": "forbidden"})
+                return
+        # cost_records 表只在 CostStore 首次初始化时建：新鲜
+        # 库上直接查会报 no such table，报告端点不应因此 500。
+        # 先建表（幂等），再读；建表失败时成本按空算、报告
+        # 里 token/usd 为 0，不假装成本已计。
+        try:
+            _cost_store = CostStore(self.server.db_path)
+            try:
+                _cost_store._conn.close()
+            except Exception:
+                pass
+        except Exception:
+            pass
+        conn = self._db()
+        try:
+            audit_rows = conn.execute(
+                "SELECT detail FROM audit_log"
+                " WHERE project_id = ? AND action = 'worker_routing'"
+                " ORDER BY created_at, id LIMIT 10001",
+                (project_id,),
+            ).fetchall()
+            truncated = len(audit_rows) > 10000
+            audit_rows = audit_rows[:10000]
+            task_rows = conn.execute(
+                "SELECT id, status, model FROM tasks"
+                " WHERE project_id = ?",
+                (project_id,),
+            ).fetchall()
+            cost_rows = conn.execute(
+                "SELECT task_id, total_tokens, usd_micros"
+                " FROM cost_records WHERE project_id = ?",
+                (project_id,),
+            ).fetchall()
+        finally:
+            conn.close()
+        tasks_by_id = {}
+        explicit_n = 0
+        for row in task_rows:
+            tasks_by_id[row["id"]] = {"status": row["status"]}
+            if row["model"]:
+                explicit_n += 1
+        costs_by_task = {}
+        for row in cost_rows:
+            entry = costs_by_task.setdefault(
+                row["task_id"],
+                {"total_tokens": 0, "usd_micros": 0,
+                 "unpriced_tokens": 0})
+            entry["total_tokens"] += int(row["total_tokens"] or 0)
+            if row["usd_micros"] is None:
+                entry["unpriced_tokens"] += int(row["total_tokens"] or 0)
+            else:
+                entry["usd_micros"] += int(row["usd_micros"])
+        report = _evaluate_shadow(
+            [{"detail": row["detail"]} for row in audit_rows],
+            tasks_by_id, costs_by_task, explicit_n=explicit_n)
+        report["project_id"] = project_id
+        report["truncated"] = truncated
+        self._send_json(200, report)
+
     def _task_cost(self, user_id, task_id):
         row = self._fetch_task(task_id)
         if row is None: