The product plan is the only source for quota numbers, but the 0001 seed
used a second set (agent_chat 20/50, tryon hard 10) and omitted hairstyle,
hd_export and report regen. Migration 0003 replaces the seed and renames
points_reserved → quota_reserved and bonus_value → bonus_granted so the
docs and the schema stop contradicting each other.
Effective limit now clips at hard_cap. CI runs the integration slice
against the Postgres/Redis services it already starts.
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.
Typed pydantic-settings config, structlog JSON logging with request/trace id
propagation and redaction of phone numbers, tokens and face keys, the unified
response envelope and error-code table from 架构文档 §9.2, async SQLAlchemy
session management, ORM models for the eight foundation tables, and the
OpenTelemetry/Prometheus wiring.
packages/domain stays pure logic -- snowflake ids, the quota three-phase
protocol and the tk_task state machine -- so it can be tested without a
database and is held to mypy strict.
xsl