"""TPM 双桶限流与缓存命中率透出（T-X12，采纳 enterprise-ai-gateway 设计）。"""
import time

from gateway.proxy.auth import RateLimiter
from gateway.proxy.semcache import SemanticCache


def test_tpm_bucket_capacity_and_consume():
    """容量内放行并扣减；超过余量拒绝。"""
    rl = RateLimiter()
    assert rl.allow_tokens(1, 100, 1000) is True
    assert rl.allow_tokens(1, 500, 1000) is True
    # 已扣 600，剩 400 + 回流（瞬时近似 0）：700 > 400+eps -> 拒
    assert rl.allow_tokens(1, 700, 1000) is False


def test_tpm_bucket_continuous_refill(monkeypatch):
    """连续时间回流：elapsed * tpm/60 补充（容量封顶）。"""
    rl = RateLimiter()
    clock = {"t": 100.0}
    monkeypatch.setattr(time, "monotonic", lambda: clock["t"])
    assert rl.allow_tokens(2, 1000, 2000) is True   # 剩 1000
    clock["t"] = 130.0                              # 30s 回流 1000 -> 满 2000
    assert rl.allow_tokens(2, 1500, 2000) is True   # 扣 1500 剩 500
    clock["t"] = 145.0                              # 15s 回流 500 -> 1000
    assert rl.allow_tokens(2, 1000, 2000) is True   # 精确扣空
    assert rl.allow_tokens(2, 1, 2000) is False     # 空桶拒绝


def test_tpm_disabled_when_cap_zero():
    """tpm_cap <= 0 = 不限流（恒放行）。"""
    rl = RateLimiter()
    assert rl.allow_tokens(3, 10**9, 0) is True


def test_tpm_independent_from_rpm_bucket():
    """双桶相互独立：打满 TPM 不影响 RPM 放行，RPM 打空不影响 TPM 记账。"""
    rl = RateLimiter()
    assert rl.allow_tokens(4, 5000, 5000) is True   # TPM 打空
    assert rl.allow(4, 10) is True                  # RPM 仍放行
    for _ in range(9):                              # 共 10 次 = 打满 RPM
        assert rl.allow(4, 10) is True
    assert rl.allow(4, 10) is False                 # RPM 空桶
    assert rl.allow_tokens(4, 1, 5000) is False     # TPM 仍空（未被 RPM 动过）


def test_tpm_per_key_isolation():
    """按 key 隔离：一个 key 打满不影响另一个。"""
    rl = RateLimiter()
    assert rl.allow_tokens(5, 5000, 5000) is True
    assert rl.allow_tokens(6, 5000, 5000) is True
    assert rl.allow_tokens(5, 5000, 5000) is False


def test_semcache_stats_hit_rate():
    """stats 透出 misses 与 hit_rate（命中率口径 = hits / (hits + misses)）。"""
    class _S:
        def semcache_rows(self, limit=0):
            return []

        def put_semcache(self, *a, **k):
            pass

    c = SemanticCache(_S(), max_entries=10, sim_threshold=0.5, promote_frequency=5)
    c.put("k1", "请解释一下递归函数的概念", "答案", "m", doc_version=1)
    assert c.lookup("k1", "请解释一下递归函数的概念", doc_version=1) is not None
    assert c.lookup("k9", "完全无关的问题内容呢", doc_version=1) is None
    s = c.stats()
    assert s["hits_exact"] == 1 and s["misses"] == 1
    assert s["hit_rate"] == 0.5