xsl
a4d59aca30
把单一日预算熔断升级为架构 §13.3 的四档分级降级（T-P1-25b / NFR-COST-02）：
- budget.py：新增 BudgetTier 配置模型与档位判定（current_tier/tier_name/
blocked_scenes）。阈值相对 LLM_DAILY_BUDGET_CENTS：warn ≥60% 只告警；
degrade_secondary ≥80% 拒 hd_export/report_regen；degrade_generation ≥90%
追加拒 hairstyle/tryon；block_all ≥100% 拒全部非 critical、allow 名单
（默认 agent_chat）放行。高档位 blocked 取「截至当前档的并集」（架构原文
「追加拒绝」）。critical 场景全档豁免但照常计成本。
- 手动 override：Redis 键 llm:budget:override（值 "1"~"4"），优先于成本水
位，读不到/非法则忽略；set_override TTL 到当日 UTC+8 24 点，跨预算日必然
失效。CostCounter 协议相应增加 set/delete。
- 指标：Gauge llm_budget_tier + Counter llm_budget_blocked_total{scene}
挂到共享 REGISTRY 随 /metrics 暴露；档位上升沿只告警一次
（budget_tier_raised，实例内记 last_tier）。
- errors.py 新增 SceneDegradedError（tier2/3 拒绝）；gateway.py 调用点换成
ensure_scene_allowed（保留 ensure_within_budget 兼容入口）；agent.py 映射
LLM_SCENE_DEGRADED(60006)；100% 档维持 DailyBudgetExceededError/60003 语义。
- 单测：新增 tests/unit/test_tiered_budget.py（27 例：四档边界、各档放行/
拒绝、critical 豁免、override 加严/放宽/非法值/TTL、配置驱动）。
- 集成：tests/integration/test_vertical_slice.py 新增用例——预算 1 分 +
block_all allow 清空 + Redis 注入当日成本，POST /agent/chat 返回 60003，
断言 bl_ledger 中 consume(refunded,-1)+refund(committed,+1) 净和为 0，
覆盖「reserve 之后才熔断 → refund」路径；fixture 重构为共享
FakeProvider/fake_client，断言语义未弱化。
门禁：ruff check/format、mypy（packages/llm strict + 其余包）、lint-imports、
单测 196 passed、集成 4 passed。
偏差说明：
1. tests/unit/test_gateway.py 的 test_daily_budget_rejects_non_critical_
scenes_before_spending 把被测场景 AGENT_CHAT 换成 REPORT_COPY（test_daily_
budget.py 同用例换 tryon）：block_all 档默认 allow=["agent_chat"]（架构
「仅保留纯文本对话」）后 agent_chat 在 100% 档不再被拒，原场景选择与新
语义冲突；断言本身（进 provider 前被拒）未弱化。
2. 集成测试的 block_all 档配置为 blocked="*"+allow=[]（文档示例为
blocked=["agent_chat"]）：后者按档位规则会走 SceneDegradedError/60006，
前者才能按设计走既有 60003 语义（文档允许二者取其一且"按上面设计应为
60003"）。
87 lines
3.0 KiB
Python
Executable File
87 lines
3.0 KiB
Python
Executable File
"""Global daily cost circuit breaker (架构文档 §13 三道成本闸门).
|
|
|
|
The requirement is enforcement, not alerting: once the platform-wide daily
|
|
spend crosses the threshold, non-critical AI calls are rejected.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from datetime import UTC, datetime
|
|
from decimal import Decimal
|
|
|
|
import pytest
|
|
|
|
from packages.llm.budget import DailyBudgetGuard, InMemoryCostCounter
|
|
from packages.llm.errors import DailyBudgetExceededError
|
|
|
|
|
|
def make_guard(
|
|
budget: str = "100", *, enabled: bool = True, now: datetime | None = None
|
|
) -> tuple[DailyBudgetGuard, InMemoryCostCounter]:
|
|
counter = InMemoryCostCounter()
|
|
guard = DailyBudgetGuard(
|
|
counter,
|
|
daily_budget_cents=Decimal(budget),
|
|
enabled=enabled,
|
|
clock=(lambda: now) if now else None,
|
|
)
|
|
return guard, counter
|
|
|
|
|
|
async def test_allows_calls_below_the_threshold() -> None:
|
|
guard, _ = make_guard("100")
|
|
await guard.add_cost(Decimal("99.9"))
|
|
await guard.ensure_within_budget(scene="agent_chat")
|
|
|
|
|
|
async def test_rejects_non_critical_scenes_once_the_budget_is_reached() -> None:
|
|
guard, _ = make_guard("100")
|
|
await guard.add_cost(Decimal("100"))
|
|
# block_all 档默认放行 agent_chat（「仅保留纯文本对话」），用非 allow 场景
|
|
# 断言 100% 档的既有拒绝语义不变
|
|
with pytest.raises(DailyBudgetExceededError) as excinfo:
|
|
await guard.ensure_within_budget(scene="tryon")
|
|
assert "tryon" in str(excinfo.value)
|
|
|
|
|
|
async def test_critical_scenes_bypass_the_breaker() -> None:
|
|
guard, _ = make_guard("100")
|
|
await guard.add_cost(Decimal("500"))
|
|
# Degrade the product, do not break it: 意图识别/越界拒答 must keep working.
|
|
await guard.ensure_within_budget(scene="intent_classify", critical=True)
|
|
|
|
|
|
async def test_disabled_guard_never_blocks_and_never_counts() -> None:
|
|
guard, counter = make_guard("1", enabled=False)
|
|
await guard.add_cost(Decimal("999"))
|
|
await guard.ensure_within_budget(scene="agent_chat")
|
|
assert await counter.get(guard.current_key()) == Decimal("0")
|
|
|
|
|
|
async def test_cost_accumulates_across_calls() -> None:
|
|
guard, _ = make_guard("100")
|
|
await guard.add_cost(Decimal("1.5"))
|
|
await guard.add_cost(Decimal("2.25"))
|
|
assert await guard.spent_today() == Decimal("3.75")
|
|
|
|
|
|
async def test_zero_cost_is_not_counted() -> None:
|
|
guard, _ = make_guard("100")
|
|
await guard.add_cost(Decimal("0"))
|
|
assert await guard.spent_today() == Decimal("0")
|
|
|
|
|
|
async def test_budget_day_boundary_follows_utc_plus_8() -> None:
|
|
"""FR-BILL-01: 跨时区按 UTC+8 统一。17:00Z already belongs to the next day."""
|
|
guard, _ = make_guard(now=datetime(2026, 8, 13, 17, 0, tzinfo=UTC))
|
|
assert guard.current_key().endswith("2026-08-14")
|
|
|
|
guard_before, _ = make_guard(now=datetime(2026, 8, 13, 15, 0, tzinfo=UTC))
|
|
assert guard_before.current_key().endswith("2026-08-13")
|
|
|
|
|
|
async def test_budget_properties_are_exposed_for_dashboards() -> None:
|
|
guard, _ = make_guard("42")
|
|
assert guard.enabled is True
|
|
assert guard.budget_cents == Decimal("42")
|