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/llm/recording.py

@@ -36,8 +36,10 @@ class SqlAlchemyAICallRecorder:
                     tokens_in=record.usage.tokens_in,
                     tokens_out=record.usage.tokens_out,
                     tokens_cached=record.usage.tokens_cached,
+                    tokens_reasoning=record.usage.tokens_reasoning,
                     latency_ms=record.latency_ms,
                     cost_cents=record.cost_cents,
+                    rate_tier=record.rate_tier,
                     success=record.success,
                     error_code=record.error_code,
                     error_message=record.error_message,
@@ -59,3 +61,5 @@ class PrometheusAICallRecorder:
         LLM_TOKENS.labels(*labels, "in").inc(record.usage.tokens_in)
         LLM_TOKENS.labels(*labels, "out").inc(record.usage.tokens_out)
         LLM_TOKENS.labels(*labels, "cached").inc(record.usage.tokens_cached)
+        # 思考模式 token 单独出一条曲线：它按输出价计费，是最容易悄悄涨上去的一项。
+        LLM_TOKENS.labels(*labels, "reasoning").inc(record.usage.tokens_reasoning)