feat(cost): persist reasoning tokens and the peak/off-peak tier

ob_ai_call is the only input to V2 pricing, and it was dropping the two
numbers needed to interpret its own cost column.

tokens_reasoning was captured from the provider response but never written to
the table, so the cost of thinking mode was invisible once it left the
process. Folding it into tokens_out was not an option either -- it is billed
at the output rate, and mixing the two hides exactly the difference we now
have to watch.

rate_tier records which price list applied. Without it a row's cost_cents
cannot be rechecked: DeepSeek's peak rate is double off-peak from 2026-08-17,
so recomputing an old row at "the current rate" silently produces a different
answer than what was actually billed.

Migration 0002 adds both columns. tokens_reasoning defaults to 0 rather than
NULL so cost aggregates do not collapse to NULL on historical rows;
rate_tier stays nullable because rows written before this change genuinely
have an unknown tier, and NULL says that more honestly than a guessed 'flat'.

The smoke script now asserts both: reasoning tokens must be 0 (a non-zero
value means a provider default re-enabled thinking mode behind our backs) and
rate_tier must be present. Verified against the real API -- tokens_reasoning=0,
rate_tier=off_peak, 3.9s round trip.

packages/shared/models.py

@@ -229,10 +229,16 @@ class AiCall(Base):
     tokens_in: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
     tokens_out: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
     tokens_cached: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
+    # 思考模式 token 单独记，不并入 tokens_out：它按输出价计费，混在一起就看不出
+    # 开关思考模式的成本差异，而这正是 T-P1-24a 要长期盯的数。
+    tokens_reasoning: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
     latency_ms: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
     cost_cents: Mapped[Decimal] = mapped_column(
         Numeric(14, 6), nullable=False, default=Decimal("0")
     )
+    # 该次调用适用的峰谷档位。没有它就无法事后复核 cost_cents ——
+    # 单价随时刻变化，事后按「当前价」回算会得出不同结果 (T-P1-25c)。
+    rate_tier: Mapped[str | None] = mapped_column(String(16))
     success: Mapped[bool] = mapped_column(Boolean, nullable=False, default=False)
     error_code: Mapped[str | None] = mapped_column(String(64))
     error_message: Mapped[str | None] = mapped_column(Text)