xsl
f46ecc5eb0
Two defects that only surface against the real DeepSeek API, both of which break the cost model rather than the code: deepseek-v4-flash enables thinking mode by default. The same single-turn question took 13.5s with it on and 1.8s with it off, and the thinking tokens are billed at the output rate. That misses NFR-PERF-02b (15s per turn) and inflates every conversational call. SceneConfig now carries an explicit `thinking` flag, all four V1 scenes set it to false, and the provider always sends the parameter rather than relying on the upstream default. Reasoning tokens are recorded separately in Usage.tokens_reasoning so the cost of ever turning it back on is visible. DeepSeek moves to peak/off-peak pricing on 2026-08-17, with peak (Beijing 09:00-12:00 and 14:00-18:00) at twice the off-peak rate. Reports are generated mostly during peak hours, so a single blended rate would leave ob_ai_call -- the only input to V2 pricing -- off by nearly a factor of two. PeakAwareRateTable resolves the rate at call time; cost is computed and stored then, never recomputed later at whatever the current rate happens to be. Also here: - Replace the live API key in the redaction test with a synthetic one. The test that proves we redact secrets was itself a secret leak waiting for its first commit. - Correct LLM_COST_RATES_JSON, which held placeholder rates. - Make ids.SnowflakeGenerator take an injectable clock so rollover and clock-rollback are testable without patching a slots class. - Rename exceptions to the -Error suffix (N818) and clear the remaining ruff, mypy and import-linter findings, including two dead lines: a duplicate pytestmark assignment and a no-op assert on a None return. Gates: ruff, mypy (96 files incl. tests), 4/4 import contracts, detect-secrets, 166 unit + 3 integration tests, migration up/down round-trip.
tests/
| 目录 | 内容 | 依赖 |
|---|---|---|
unit/ |
领域逻辑、LLM 网关、脱敏、错误码 | 无。不许连库、不许发网络请求 |
integration/ |
带 PostgreSQL / Redis 的链路 | make up，或 testcontainers |
golden/ |
黄金集回归（检索 / 规则 / 报告） | 尚未建立，见下 |
make test-unit # 默认只跑 unit（integration 自动跳过）
MEIDA_RUN_INTEGRATION=1 uv run pytest -m integration
覆盖率门槛
pytest 对 packages/llm 与 packages/domain 统计覆盖率，低于阈值即失败。
这两个包是 mypy strict 的范围，也是业务正确性的核心，其他层靠集成测试覆盖。
绝对不要做的事
- 不要在单测里调用真实的 DeepSeek。
scripts/smoke.sh是唯一会真的花钱的 入口。单测用httpx.MockTransport或tests/unit/test_gateway.py里的FakeProvider。 - 不要
time.sleep()。熔断器、预算闸门都支持注入时钟。 - 不要断言日志文本。断言行为。
黄金集（还没建，但这是最重要的一道防线）
架构 §16.2：
AI 改代码时最容易破坏的是那些「没有断言保护的隐性行为」。检索链路和规则引擎 必须有一套固定输入 → 期望输出的样本集。
M2 落地知识库时必须同步建立（FR-KB-11，≥ 100 条用例）： 检索 Top-5 命中率 ≥ 80%、硬过滤零漏、规则命中正确性、报告结构完整性、 硬性禁忌违反数 = 0。指标退化即阻断合并。
已覆盖的关键不变量
| 测试 | 保护的是什么 |
|---|---|
test_prompt_cache_prefix.py |
固定前缀不含易变 token，否则输入成本翻数倍 |
test_daily_budget.py |
日成本超限时拒绝非关键调用，不是只告警 |
test_gateway.py |
路由、故障转移、熔断、结构化重试、每次调用都记成本 |
test_quota_domain.py |
预扣三段式；退还幂等；服务端硬校验 |
test_task_state.py |
任务状态机没有非法跃迁 |
test_log_redaction.py |
手机号 / 令牌 / 密钥 / 诊断结论不进日志 |
test_response_envelope.py |
每个错误码都有文案；配额文案不含价格字样 |