feat: refuse an impossible tier with the cheapest one that model does have

resolve_thinking now takes an Effort instead of a tri-state bool, and the
four gates become five. The new one sits ahead of the generic tier check
on purpose: asking for `none` on GLM-5.3 used to fall through to "none is
not supported, pick low/high/max", which loses both the fact that the
model cannot stop reasoning and the one tier the caller could switch to
right now. Without that alternative, downstream goes looking for
extra_body — which is how issue #20 happened in the first place.

The return type is a ThinkingResolution rather than the payload alone.
Under fallback="nearest" the tier that goes out is not the tier that was
asked for, and telemetry has to record the one that ran, or task 10 files
a call under a tier it never used. Ties in that mapping go to the weaker
side: a silent medium -> max is a multiple of the bill, and the library
does not raise a caller's price on its own.

Two readings the design left implicit, both settled the way its own
compatibility promise requires:

- `auto` is exempt from the tier list. It means "on, no tier named",
  which in the body is the absence of the effort key, not a value of it.
  Checking it against the list would break every existing source that
  sets ENABLE_THINKING=true against deepseek-v4 or glm-5.3.
- `none` is never a mapping target. Turning "think less" into "do not
  think" reverses the decision instead of cheapening it; a switch-only
  model maps to `auto` and a model that only has `none` still errors.

Both call sites convert enable_thinking in place for now; task 5 folds
that into effective_effort along with the source- and call-level tiers.

src/polygateway/client.py

@@ -38,6 +38,7 @@ from polygateway.thinking import get_capability, resolve_thinking
 from polygateway.transports.openai_compat import OpenAICompatTransport
 from polygateway.types import (
     ChatRequest,
+    Effort,
     LLMResponse,
     TelemetryStatus,
     validate_caller_dimensions,
@@ -80,10 +81,15 @@ def _guard_thinking(
     就带着指路信息炸掉。`get_provider` 现在就是同一形态的双点调用。
     """
     for source, profile in zip(sources, profiles, strict=True):
+        # `enable_thinking` 的档位语法糖(True → auto,False → none,None 不表态);
+        # 两个调用点各自就地转换是过渡形态,T5 起由 thinking.effective_effort()
+        # 统一收口并接上源级/请求级档位(设计 §4.2)
+        enabled = source.enable_thinking
+        effort = None if enabled is None else (Effort.AUTO if enabled else Effort.NONE)
         resolve_thinking(
             profile,
             get_capability(source.model, table=capabilities),
-            source.enable_thinking,
+            effort,
             model=source.model,
         )