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。

tests/test_host.py

@@ -572,6 +572,85 @@ class GithubPRTest(unittest.TestCase):
             self.assertIn("remote", r.stdout + r.stderr)
 
 
+class TurnUsageSumTest(unittest.TestCase):
+    def _note(self, thread_id, turn_id, last):
+        return {"method": "thread/tokenUsage/updated",
+                "params": {"threadId": thread_id, "turnId": turn_id,
+                           "tokenUsage": {"last": last}}}
+
+    def test_sums_last_across_completions(self):
+        # 2026-10-26 中继实测前两次通知：last 之和等于第二次的 total。
+        evs = [
+            self._note("t1", "u1", {
+                "inputTokens": 10906, "cachedInputTokens": 9192,
+                "cacheWriteInputTokens": 0, "outputTokens": 346,
+                "reasoningOutputTokens": 256, "totalTokens": 11252}),
+            self._note("t1", "u1", {
+                "inputTokens": 11041, "cachedInputTokens": 9192,
+                "cacheWriteInputTokens": 0, "outputTokens": 230,
+                "reasoningOutputTokens": 161, "totalTokens": 11271}),
+        ]
+        self.assertEqual(host._sum_turn_usage(evs, "t1", "u1"), {
+            "input_tokens": 21947, "cached_input_tokens": 18384,
+            "cache_write_input_tokens": 0, "output_tokens": 576,
+            "reasoning_output_tokens": 417, "total_tokens": 22523,
+            "completions": 2})
+
+    def test_filters_by_thread_and_turn(self):
+        evs = [
+            self._note("t1", "u1", {
+                "inputTokens": 10, "cachedInputTokens": 0,
+                "cacheWriteInputTokens": 0, "outputTokens": 5,
+                "reasoningOutputTokens": 0, "totalTokens": 15}),
+            self._note("t1", "u2", {
+                "inputTokens": 999, "cachedInputTokens": 0,
+                "cacheWriteInputTokens": 0, "outputTokens": 999,
+                "reasoningOutputTokens": 0, "totalTokens": 1998}),
+            self._note("t2", "u1", {
+                "inputTokens": 999, "cachedInputTokens": 0,
+                "cacheWriteInputTokens": 0, "outputTokens": 999,
+                "reasoningOutputTokens": 0, "totalTokens": 1998}),
+            {"method": "item/completed", "params": {}},
+        ]
+        usage = host._sum_turn_usage(evs, "t1", "u1")
+        self.assertEqual(usage["input_tokens"], 10)
+        self.assertEqual(usage["completions"], 1)
+        self.assertIsNone(host._sum_turn_usage(evs, "t1", "u9"))
+        self.assertIsNone(host._sum_turn_usage([], "t1", "u1"))
+
+    def test_retry_sums_usage_across_attempts(self):
+        class FakeServer:
+            def __init__(self, results):
+                self.results = list(results)
+
+            def run_turn(self, thread_id, prompt, model=None, effort=None,
+                         sandbox=None):
+                return self.results.pop(0)
+
+        task = {"name": "t", "thread_id": "x", "sandbox": None,
+                "max_retries": 1, "retry_count": 0, "turns": []}
+        state = {"tasks": {"t": task}, "automations": []}
+        srv = FakeServer([
+            {"status": "failed", "text": "", "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}},
+            {"status": "completed", "text": "ok", "usage": {
+                "input_tokens": 200, "cached_input_tokens": 50,
+                "cache_write_input_tokens": 0, "output_tokens": 20,
+                "reasoning_output_tokens": 5, "total_tokens": 220,
+                "completions": 1}},
+        ])
+        result = host.run_task_turn_with_retry(
+            srv, state, task, "do it", "m", "low", cfg={})
+        self.assertEqual(result["status"], "completed")
+        self.assertEqual(result["usage"]["input_tokens"], 300)
+        self.assertEqual(result["usage"]["cached_input_tokens"], 50)
+        self.assertEqual(result["usage"]["total_tokens"], 330)
+        self.assertEqual(result["usage"]["completions"], 2)
+
+
 if __name__ == "__main__":
     unittest.main()