feat: model the thinking switch as shape plus capability (issue #5)

enable_thinking=False was a no-op for minimax and openai sources: both
profiles had empty dicts on each side, so the payload update injected
nothing while the caller believed reasoning had been turned off. A
downstream project was blocked on exactly this.

The root cause is that an empty dict meant two different things -- "no
injection needed" and "we do not know how this provider spells it" --
and that a provider-level table cannot express what turned out to be a
per-model property. Live testing showed MiniMax-M3 can disable
reasoning via reasoning_effort while M2.7 and M2.5 cannot be disabled
at all, which two external registries independently confirm.

So the shape stays at provider level and a capability table joins it at
model level. Unknown, unsupported and no-opinion are now three distinct
values, and resolve_thinking is the single place they meet: it raises at
assembly time when a model cannot honour the request, warns and injects
for unregistered models, and injects silently otherwise. Every registered
capability carries the evidence it was derived from.

enable_thinking also joins the cache fingerprint, since it now really
does change the request body.

src/polygateway/transports/openai_compat.py

@@ -21,7 +21,13 @@ from polygateway.errors import (
     SourceDeadError,
     TransientError,
 )
-from polygateway.providers import ProviderProfile, get_provider
+from polygateway.providers import (
+    ProviderProfile,
+    ThinkingCapability,
+    get_capability,
+    get_provider,
+    resolve_thinking,
+)
 from polygateway.streaming import StreamLivenessTimeout, stream_with_liveness_timeouts
 from polygateway.types import EmbeddingTransportResult, SourceConfig, TransportResult
 
@@ -284,9 +290,11 @@ class OpenAICompatTransport:
         self,
         *,
         registry: Mapping[str, ProviderProfile] | None = None,
+        capabilities: Mapping[str, ThinkingCapability] | None = None,
         client_factory: Callable[[SourceConfig], httpx.AsyncClient] | None = None,
     ) -> None:
         self._registry = registry
+        self._capabilities = capabilities
         self._client_factory = client_factory or _default_client_factory
         self._clients: dict[str, httpx.AsyncClient] = {}
 
@@ -309,10 +317,12 @@ class OpenAICompatTransport:
         payload: dict[str, Any] = {"model": source.model, "messages": messages, "stream": stream}
         if stream:
             payload["stream_options"] = {"include_usage": True}  # 强制 usage 帧(三项目同款)
-        if source.enable_thinking is True:
-            payload.update(profile.thinking_on)
-        elif source.enable_thinking is False:
-            payload.update(profile.thinking_off)
+        # 形态(provider 级)与能力(model 级)在此相遇;不可满足时 ValueError,
+        # 由 complete() 翻译为四分类之一(issue #5)
+        capability = get_capability(source.model, table=self._capabilities)
+        payload.update(
+            resolve_thinking(profile, capability, source.enable_thinking, model=source.model)
+        )
         # 顺序即优先级(issue #4 设计决策 A): 配置级 extra_body 在前,调用级
         # overlay(含结构化注入)在后覆盖之。两行不可调换
         payload.update(source.extra_body)
@@ -330,9 +340,17 @@ class OpenAICompatTransport:
     ) -> TransportResult:
         """一次原始调用;HTTP/线路/流式异常按 ARCH §6.2 翻译为领域错误。"""
         profile = get_provider(source.provider, registry=self._registry)
-        payload = self._build_payload(
-            messages=messages, source=source, profile=profile, stream=stream, overlay=overlay
-        )
+        try:
+            payload = self._build_payload(
+                messages=messages, source=source, profile=profile, stream=stream, overlay=overlay
+            )
+        except ValueError as exc:
+            # 推理开关不可满足是**请求本身**的问题: 换源重试都救不了它
+            raise RequestRejectedError(
+                f"{source.name} 推理开关无法满足: {exc}",
+                source_name=source.name,
+                operation="chat",
+            ) from exc
         url = source.base_url.rstrip("/") + "/chat/completions"
         client = self._client_for(source)
         ctx: dict[str, Any] = {"source_name": source.name, "operation": "chat"}