逐任务真实成本：上游用量事件 + 价目表计价

此前每任务只记一条 estimated（字符数/4，金额为空），注释称
host 协议不暴露真实 token 数。本轮实测推翻了该前提：
- account/usage/read 在中继上是死的（要求 ChatGPT 账号登录），
  不是来源，已在 cost.py docstring 写明死胡同
- app-server 每上游补全发 thread/tokenUsage/updated，last 是该次
  补全的用量；中继 5 调用回合实测 last 之和等于最后 total
  （input/output/cached/reasoning 四路都对得上）

实现：host.py run_turn 从事件窗口按 threadId+turnId 汇总用量，
重试/goal 各轮累加，dispatch/run JSON 与 goal 用量行透传；
sandbox 三路解析（dispatch JSON 解析改用完整 stdout，顺带修
了长 text 下 failed 被误判 completed 的潜 bug）；worker 每任务
记一条 actual（重试/fallback 用量累加进同一条），无用量时回落
estimated；cost.py 价目表（默认 OpenAI 挂牌价，env 可覆盖，
无价模型 usd 记 None、报表进 unpriced_actual_tokens 而非 0 美元），
cost_records 加 cached_input_tokens 列（SQLite/PG 两支迁移）；
报表与按天行新增 cached_input_tokens/unpriced_actual_tokens。
测试：host 32、cloud 483 全过。

cloud/tests/test_queue_sandbox.py

@@ -8,6 +8,7 @@
 top-level 目录无关。
 """
 
+import json
 import os
 import sys
 import unittest
@@ -385,5 +386,99 @@ class TestGoalExecutors(unittest.TestCase):
         self.assertIn("test -f x", seen[0])
 
 
+class TestUsageParsing(unittest.TestCase):
+    def test_result_from_runner_usage(self):
+        usage = {"input_tokens": 1000, "cached_input_tokens": 400,
+                 "cache_write_input_tokens": 0, "output_tokens": 100,
+                 "reasoning_output_tokens": 20, "total_tokens": 1100,
+                 "completions": 2}
+        fake = SimpleNamespace(
+            returncode=0,
+            stdout=json.dumps({"status": "completed", "text": "done",
+                               "usage": usage}),
+            stderr="")
+        result = LocalExecutor("/fake/host.py",
+                               runner=lambda cmd: fake
+                               )._result_from_runner("t1", fake)
+        self.assertEqual(result["usage"], usage)
+        self.assertEqual(result["status"], "completed")
+
+    def test_result_from_runner_usage_survives_long_text(self):
+        # usage 在 JSON 末尾：旧的截头解析在 text 很长时会丢 usage、
+        # 还会把 failed 误判成 completed；解析必须用完整 stdout。
+        usage = {"input_tokens": 100, "cached_input_tokens": 0,
+                 "cache_write_input_tokens": 0, "output_tokens": 10,
+                 "reasoning_output_tokens": 0, "total_tokens": 110,
+                 "completions": 1}
+        fake = SimpleNamespace(
+            returncode=0,
+            stdout=json.dumps({"status": "failed", "text": "x" * 5000,
+                               "usage": usage}),
+            stderr="")
+        result = LocalExecutor("/fake/host.py",
+                               runner=lambda cmd: fake
+                               )._result_from_runner("t1", fake)
+        self.assertEqual(result["status"], "failed")
+        self.assertEqual(result["usage"], usage)
+
+    def test_result_from_runner_dirty_usage_dropped(self):
+        for bad in ({"input_tokens": "abc"},
+                    {"input_tokens": 0, "output_tokens": 0,
+                     "total_tokens": 0},
+                    "not-a-dict"):
+            fake = SimpleNamespace(
+                returncode=0,
+                stdout=json.dumps({"status": "completed", "usage": bad}),
+                stderr="")
+            result = LocalExecutor("/fake/host.py",
+                                   runner=lambda cmd: fake
+                                   )._result_from_runner("t1", fake)
+            self.assertIsNone(result["usage"])
+
+    def test_goal_usage_line(self):
+        fake = SimpleNamespace(
+            returncode=0,
+            stdout="round 1: turn=completed verify_rc=0 verify_out=ok\n"
+                   "goal met after rounds\n"
+                   "usage input=100 cached=40 cache_write=0 output=50 "
+                   "reasoning=10 total=150 completions=2\n",
+            stderr="")
+        result = LocalExecutor("/fake/host.py",
+                               runner=lambda cmd: fake
+                               )._goal_result_from_runner("t1", fake)
+        self.assertEqual(result["usage"], {
+            "input_tokens": 100, "cached_input_tokens": 40,
+            "cache_write_input_tokens": 0, "output_tokens": 50,
+            "reasoning_output_tokens": 10, "total_tokens": 150,
+            "completions": 2})
+        fake2 = SimpleNamespace(
+            returncode=0, stdout="goal met after rounds\n", stderr="")
+        result2 = LocalExecutor("/fake/host.py",
+                                runner=lambda cmd: fake2
+                                )._goal_result_from_runner("t1", fake2)
+        self.assertIsNone(result2["usage"])
+
+    def test_docker_goal_usage_line(self):
+        def fake_runner(cmd, timeout=None):
+            return SimpleNamespace(
+                returncode=0,
+                stdout="round 1: turn=completed verify_rc=0 verify_out=ok\n"
+                       "goal met after rounds\n"
+                       "usage input=100 cached=40 cache_write=0 output=50 "
+                       "reasoning=10 total=150 completions=2\n",
+                stderr="")
+
+        with mock.patch("sandbox.shutil.which",
+                        return_value="/usr/bin/docker"):
+            executor = DockerExecutor(
+                "/fake/host.py", runner=fake_runner,
+                env={"XCM_API_KEY": "placeholder-not-a-real-key"})
+            result = executor.goal_task(
+                {"id": "t1", "prompt": "do it",
+                 "verify_command": "test -f x"})
+        self.assertEqual(result["usage"]["total_tokens"], 150)
+        self.assertEqual(result["usage"]["cached_input_tokens"], 40)
+
+
 if __name__ == "__main__":
     unittest.main()