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"}

tests/test_api_heavy_compute_gate.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 import json
 import threading
+import time
 from io import BytesIO
 
 import pytest
@@ -14,6 +15,7 @@ from scripts.api_heavy_compute_gate import (
     HEAVY_COMPUTE_PATHS,
     HeavyComputeBusy,
     acquire_heavy_compute_slot,
+    heavy_compute_waiter_count,
     is_heavy_compute_path,
     release_heavy_compute_slot,
     reset_heavy_compute_gate,
@@ -93,7 +95,10 @@ def limit_one_gate(monkeypatch):
     monkeypatch.setenv("JYOTISH_HEAVY_COMPUTE_CONCURRENCY", "1")
     monkeypatch.setenv("JYOTISH_HEAVY_COMPUTE_RETRY_AFTER_SECONDS", "2")
     monkeypatch.setenv("JYOTISH_API_RATE_LIMIT_PER_MINUTE", "0")
-    reset_heavy_compute_gate()
+    # 原值：reset() 使用默认「满了立刻拒绝」
+    # 新值：wait_seconds=0，本夹具里的 429 断言仍是立刻拒绝
+    # 原因：产品改为最多等 8 秒；排队成功、等待者满、超时另有测试
+    reset_heavy_compute_gate(wait_seconds=0)
     yield
     monkeypatch.delenv("JYOTISH_HEAVY_COMPUTE_CONCURRENCY", raising=False)
     monkeypatch.delenv("JYOTISH_HEAVY_COMPUTE_RETRY_AFTER_SECONDS", raising=False)
@@ -119,7 +124,10 @@ def test_health_and_light_paths_are_not_gated() -> None:
 
 
 def test_acquire_fail_fast_then_succeeds_after_release() -> None:
-    reset_heavy_compute_gate(limit=1, retry_after_seconds=3)
+    # 原值：reset(limit=1, retry_after_seconds=3) 后第二路立刻 HeavyComputeBusy
+    # 新值：多传 wait_seconds=0
+    # 原因：默认改为短排队；本测试仍锁 Retry-After=3 与 ERR_COMPUTE_BUSY，不锁「禁止等待」
+    reset_heavy_compute_gate(limit=1, retry_after_seconds=3, wait_seconds=0)
     first = acquire_heavy_compute_slot("/api/high_rigor_workflow")
     assert first is not None
     with pytest.raises(HeavyComputeBusy) as caught:
@@ -248,8 +256,87 @@ def test_warm_consultation_does_not_consume_the_user_slot(limit_one_gate, monkey
     assert "packet" not in warm_box["payload"]
 
 
+def _wait_until(predicate, timeout: float = 2.0) -> bool:
+    deadline = time.monotonic() + timeout
+    while time.monotonic() < deadline:
+        if predicate():
+            return True
+        time.sleep(0.01)
+    return False
+
+
+def test_third_request_gets_the_slot_after_one_holder_releases() -> None:
+    reset_heavy_compute_gate(limit=2, retry_after_seconds=2, wait_seconds=2, max_waiters=4)
+    first = acquire_heavy_compute_slot("/api/consultation_workflow")
+    second = acquire_heavy_compute_slot("/api/rectification/v5/score")
+    assert first is not None and second is not None
+    found: dict = {}
+
+    def _third() -> None:
+        found["slot"] = acquire_heavy_compute_slot("/api/consultation_workflow")
+
+    worker = threading.Thread(target=_third)
+    worker.start()
+    assert _wait_until(lambda: heavy_compute_waiter_count() == 1)
+    release_heavy_compute_slot(first)
+    worker.join(timeout=3)
+    assert not worker.is_alive()
+    assert found["slot"] is not None
+    release_heavy_compute_slot(second)
+    release_heavy_compute_slot(found["slot"])
+    reset_heavy_compute_gate()
+
+
+def test_waiter_overflow_rejects_immediately() -> None:
+    reset_heavy_compute_gate(limit=1, retry_after_seconds=2, wait_seconds=2, max_waiters=1)
+    held = acquire_heavy_compute_slot("/api/high_rigor_workflow")
+    assert held is not None
+    parked: dict = {}
+
+    def _wait() -> None:
+        try:
+            parked["slot"] = acquire_heavy_compute_slot("/api/consultation_workflow")
+        except HeavyComputeBusy as exc:
+            parked["error"] = exc
+
+    waiter = threading.Thread(target=_wait)
+    waiter.start()
+    assert _wait_until(lambda: heavy_compute_waiter_count() == 1)
+    started = time.monotonic()
+    with pytest.raises(HeavyComputeBusy) as caught:
+        acquire_heavy_compute_slot("/api/rectification/v5/score")
+    assert time.monotonic() - started < 0.3
+    assert caught.value.retry_after_seconds == 2
+    assert caught.value.error_code == "ERR_COMPUTE_BUSY"
+    release_heavy_compute_slot(held)
+    waiter.join(timeout=3)
+    assert not waiter.is_alive()
+    assert parked.get("slot") is not None
+    release_heavy_compute_slot(parked["slot"])
+    reset_heavy_compute_gate()
+
+
+def test_queue_timeout_still_returns_busy() -> None:
+    reset_heavy_compute_gate(limit=1, retry_after_seconds=2, wait_seconds=0.2, max_waiters=4)
+    held = acquire_heavy_compute_slot("/api/professional_report_reference")
+    assert held is not None
+    started = time.monotonic()
+    with pytest.raises(HeavyComputeBusy) as caught:
+        acquire_heavy_compute_slot("/api/consultation_workflow")
+    elapsed = time.monotonic() - started
+    assert 0.1 <= elapsed < 2.0
+    assert caught.value.retry_after_seconds == 2
+    assert caught.value.error_code == "ERR_COMPUTE_BUSY"
+    light = acquire_heavy_compute_slot("/api/health")
+    assert light is None
+    release_heavy_compute_slot(held)
+    reset_heavy_compute_gate()
+
+
 def test_quality_gate_runs_heavy_compute_gate() -> None:
     from scripts.run_quality_gate import CORE_PYTEST_TARGETS
 
     assert "tests/test_api_heavy_compute_gate.py" in CORE_PYTEST_TARGETS
     assert gate.DEFAULT_CONCURRENCY == 2
+    assert gate.DEFAULT_QUEUE_WAIT_SECONDS == 8
+    assert gate.DEFAULT_MAX_WAITERS == 4