feat: give zhipu, moonshot, anthropic and google a wire of their own

Eight segments now, and each one holds a ThinkingWire instead of two
fixed fragments: off, on_base, and the key a tier gets written to. The
two fragments could not say "on, at this depth", which is what every
current generation model wants.

Two deliberate behaviour changes fall out of it. The openai segment stops
reporting its shape as unknown — reasoning_effort is OpenAI's own field,
not a vendor dialect, so a compatible endpoint behind the gateway takes
it. And minimax's on-tier stops carrying a hardcoded medium: that was the
library picking a price for the caller, and medium is not even a tier GLM,
kimi or deepseek serve.

The issue #5 guards stay; their sample moves from "the openai segment" to
an explicitly registered unknown one, which is what they always meant to test.

src/polygateway/thinking.py

@@ -315,8 +315,9 @@ def resolve_thinking(
     # Phase 1: 调用方不表态 —— 与 False 严格区分,用模型默认档
     if enable_thinking is None:
         return {}
-    slot = profile.thinking_on if enable_thinking else profile.thinking_off
-    direction = "thinking_on" if enable_thinking else "thinking_off"
+    wire = profile.thinking
+    slot = wire.on_base if enable_thinking else wire.off
+    direction = "on_base" if enable_thinking else "off"
     # Phase 2: 形态未知 —— 提供了开关却不知道怎么发,静默放行就是欺骗调用方
     if slot is None:
         raise ThinkingUnsupportedError(