fix(capacity): limit each user and queue heavy compute briefly.

Consult, rectification turns, and report generation stop before a credit reservation when the product caps are hit. A full heavy-compute gate waits up to 8 seconds, and one consultation retries that 429 inside the same request.

Co-Authored-By: Grok (agent loop)

tests/test_api_chart_subprocess_gate.py

@@ -153,7 +153,10 @@ def test_chart_overview_gate_is_off_by_default(monkeypatch) -> None:
 
 def test_chart_overview_gate_only_sync_unskipped_requests(monkeypatch) -> None:
     monkeypatch.setenv(gate.ENV_GATE_CHART_OVERVIEW, "1")
-    gate.reset_heavy_compute_gate(limit=1)
+    # 原值：reset(limit=1) 后第二次立刻 HeavyComputeBusy
+    # 新值：wait_seconds=0
+    # 原因：默认改为短排队；本测试仍锁「名额被占时同步排盘被拒绝」，等待行为不在这里
+    gate.reset_heavy_compute_gate(limit=1, wait_seconds=0)
     body = {"year": 1990, "lat": 28.6, "lon": 77.2}
     slot = gate.acquire_heavy_compute_slot_for_request("/api/chart", body)
     assert slot is not None
@@ -172,7 +175,10 @@ def test_chart_overview_gate_only_sync_unskipped_requests(monkeypatch) -> None:
 
 
 def test_busy_log_names_holders_and_not_the_body(caplog) -> None:
-    gate.reset_heavy_compute_gate(limit=1)
+    # 原值：reset(limit=1) 后拒绝日志立刻出现
+    # 新值：wait_seconds=0
+    # 原因：默认会先等 8 秒；本测试仍锁日志只有路径、没有请求正文
+    gate.reset_heavy_compute_gate(limit=1, wait_seconds=0)
     held = gate.acquire_heavy_compute_slot("/api/professional_report_reference")
     assert held is not None
     secret_body = {"birth_date": "1990-01-01", "name": "must-not-appear"}