test: lock settlement on measured usage in RetryMW

tests/unit/test_retry.py

@@ -152,6 +152,25 @@ class TestSuccessPath:
         # 预扣 400,实际 15 → settle 后窗口只记 15
         assert (await limiter.source_stats("a")).tpm_used == 15
 
+    @pytest.mark.parametrize("usage_source", ["measured", "estimated"])
+    async def test_settle_uses_measured_sum_when_usage_available(self, usage_source):
+        """用量可得(含打捞降级的 estimated)时结算恒取实测之和,不落派生兜底分支。"""
+        src = _src("a", tpm=1000, est_tokens=400)
+        result = TransportResult(
+            content="ok",
+            thinking="",
+            prompt_tokens=40,
+            completion_tokens=60,
+            usage_source=usage_source,
+            ttft_ms=12.0,
+            max_inter_token_ms=3.0,
+            raw={},
+        )
+        mw, limiter, *_ = _harness([src], [result])
+        await mw(_REQ)
+        # 预扣 400,实测 40+60 → settle 后窗口记 100(而非派生兜底的 400)
+        assert (await limiter.source_stats("a")).tpm_used == 100
+
 
 class TestRetryAndFailover:
     async def test_transient_switches_source_then_succeeds(self):