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.

migrations/versions/0002_ai_call_reasoning_and_rate_tier.py

@@ -0,0 +1,44 @@
+"""ob_ai_call: record reasoning tokens and the peak/off-peak tier
+
+两列都是为了让 ``ob_ai_call`` 的成本可复核 —— 这张表是 V2 定价的唯一依据
+（架构文档 §13），少一列就少一块无法事后补齐的事实。
+
+``tokens_reasoning``
+    思考模式产生的 token，按输出价计费。不并入 ``tokens_out``：混在一起就看不出
+    开关思考模式的成本差异，而 ``deepseek-v4-flash`` 默认开启该模式（T-P1-24a）。
+
+``rate_tier``
+    该次调用适用的峰谷档位。DeepSeek 自 2026-08-17 起高峰单价为空闲时段的 2 倍，
+    成本在调用当时算好落库；没有档位列，事后就无法判断某行的 ``cost_cents``
+    是按哪套单价算出来的（T-P1-25c）。
+
+Reversible: 是。降级只丢这两列的数据，不影响既有行。
+"""
+
+from __future__ import annotations
+
+from collections.abc import Sequence
+
+import sqlalchemy as sa
+from alembic import op
+
+revision: str = "0002"
+down_revision: str | None = "0001"
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    # server_default 让历史行取 0 而不是 NULL：成本聚合里 NULL 会把整个 SUM 变成 NULL。
+    op.add_column(
+        "ob_ai_call",
+        sa.Column("tokens_reasoning", sa.Integer(), nullable=False, server_default="0"),
+    )
+    # 允许 NULL：0001 之后写入的历史行确实无法判定档位，
+    # 用 NULL 表达「未知」比塞一个可能错的 'flat' 更诚实。
+    op.add_column("ob_ai_call", sa.Column("rate_tier", sa.String(length=16), nullable=True))
+
+
+def downgrade() -> None:
+    op.drop_column("ob_ai_call", "rate_tier")
+    op.drop_column("ob_ai_call", "tokens_reasoning")