feat: wire the tier through the transport and keep each tier's warning distinct

The transport now hands back the tier it actually sent, and that tier
rides TransportResult into LLMResponse. It is not the requested one:
under EFFORT_FALLBACK=nearest a medium request goes out as low, and
telemetry grouping by the requested tier would file the row under a tier
that never left the process.

Reconciliation judges the same tier instead of the old enable_thinking
bool, and the warning throttle keys on it. Keyed on the bool, every tier
of one model shared a single key, so the second contradiction was
silenced for the lifetime of the transport. The predicate is an identity
check against Effort.NONE on purpose -- the member's value is the
non-empty string "none", so any truthiness test would send every strength
tier down the "asked to disable" branch and invert the alarm.
This commit is contained in:
2026-09-05 05:00:29 -04:00
parent 5dfb15e6a2
commit 848dc0aa7f
8 changed files with 279 additions and 48 deletions
+3
View File
@@ -395,6 +395,9 @@ class RetryMW:
reasoning_tokens=result.reasoning_tokens,
# 裁定归 transport(它才见得到原始信号),本层只搬运不改判
thinking_observation=result.thinking_observation,
# 同理: 实际档由做注入的那一层裁定(`nearest` 映射后与请求档分叉),
# 本层若"顺手"改读 request.reasoning_effort,记的就是从未发出过的档
applied_effort=result.applied_effort,
)
async def _emit(