feat: carry the per-call tier down to the transport that must send it

The Transport port took the request apart into five arguments, so a tier
placed on ChatRequest could never reach _build_payload: the field was set,
read by nobody, and silently ignored - the exact shape of failure that sent
downstream to extra_body in the first place.

complete() now takes reasoning_effort with no default, matching the
TelemetryRecorder convention: a default would turn a missing hand-off into
a silent 'no opinion'. All four fakes move with it, since @runtime_checkable
checks method names and not signatures.

EmbeddingTransport and OcrTransport are deliberately left alone - they have
no reasoning semantics - and a test now holds that line.

_build_payload drops its inline sugar conversion for effective_effort(), so
the guard and the hot path share one judgement, and passes the source's
effort_fallback for the same reason.

src/polygateway/middleware/retry.py

@@ -285,6 +285,9 @@ class RetryMW:
                 stream=request.stream,
                 overlay=request.overlay,
                 call_id=call_id,
+                # 逐次尝试原样重传: 换源不改变调用方要的档位(源级默认由 transport
+                # 自己按选中的源解析,两者在 effective_effort 里汇合)
+                reasoning_effort=request.reasoning_effort,
             )
             if result.usage_source == "unavailable":
                 # 用量不可得时按入场预扣量结算(delta==0),否则押金会被整笔退回,