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.

scripts/smoke.sh

@@ -115,7 +115,8 @@ PY
 bold "6/7  ob_ai_call row (成本归因的唯一数据源, 架构文档 §13)"
 ${COMPOSE} exec -T postgres psql -U meida -d meida -x -c \
   "SELECT call_id, user_id, scene, provider, model, prompt_id, prompt_version,
-          tokens_in, tokens_out, tokens_cached, latency_ms, cost_cents,
+          tokens_in, tokens_out, tokens_cached, tokens_reasoning,
+          latency_ms, cost_cents, rate_tier,
           success, error_code, ref_type, created_at
      FROM ob_ai_call
     WHERE user_id = ${USER_ID}
@@ -124,6 +125,19 @@ ROWS=$(${COMPOSE} exec -T postgres psql -U meida -d meida -tAc \
   "SELECT count(*) FROM ob_ai_call WHERE user_id = ${USER_ID} AND success")
 [[ "${ROWS// /}" -ge 1 ]] || fail "no successful ob_ai_call row was written"
 
+# 思考模式若被上游默认打开，这里会立刻变成非 0 —— 延迟与输出侧成本会一起涨（T-P1-24a）。
+REASONING=$(${COMPOSE} exec -T postgres psql -U meida -d meida -tAc \
+  "SELECT coalesce(max(tokens_reasoning), 0) FROM ob_ai_call WHERE user_id = ${USER_ID}")
+[[ "${REASONING// /}" == "0" ]] \
+  || fail "思考模式 token 非 0（${REASONING}）：V1 场景应显式关闭 thinking，请检查 routing 配置"
+
+# 档位必须落库，否则事后无法复核 cost_cents 是按哪套单价算的（T-P1-25c）。
+TIER=$(${COMPOSE} exec -T postgres psql -U meida -d meida -tAc \
+  "SELECT coalesce(rate_tier, '') FROM ob_ai_call
+    WHERE user_id = ${USER_ID} ORDER BY created_at DESC LIMIT 1")
+[[ -n "${TIER// /}" ]] || fail "ob_ai_call.rate_tier 为空：成本无法事后复核"
+printf 'rate_tier=%s  tokens_reasoning=%s\n' "${TIER// /}" "${REASONING// /}"
+
 bold "7/7  bl_ledger rows (预扣三段式, 架构文档 §7.4)"
 ${COMPOSE} exec -T postgres psql -U meida -d meida -c \
   "SELECT tx_id, delta, tx_type, status, quota_key, period_key, balance_after,