fix(provider): gate reasoning-to-content fallback behind spec flag

The non-streaming parse path unconditionally promoted the `reasoning`
response field to `content` when content was empty. This was intended
for StepFun (whose API returns the actual answer in `reasoning`), but
it applied to every OpenAI-compatible provider — causing internal
thinking chains from models like Xiaomi MIMO to be leaked as formal
replies.

Add `reasoning_as_content: bool` to ProviderSpec (default False) and
set it only for StepFun. The fallback now requires this flag rather
than running globally.

Fixes #3443

nanobot/providers/openai_compat_provider.py

@@ -759,8 +759,8 @@ class OpenAICompatProvider(LLMProvider):
             finish_reason = str(choice0.get("finish_reason") or "stop")
 
             raw_tool_calls: list[Any] = []
-            # StepFun Plan: fallback to reasoning field when content is empty
-            if not content and msg0.get("reasoning"):
+            # StepFun: fallback to reasoning field when content is empty
+            if not content and msg0.get("reasoning") and self._spec and self._spec.reasoning_as_content:
                 content = self._extract_text_content(msg0.get("reasoning"))
             reasoning_content = msg0.get("reasoning_content")
             if not reasoning_content and msg0.get("reasoning"):
@@ -820,7 +820,7 @@ class OpenAICompatProvider(LLMProvider):
                     finish_reason = ch.finish_reason
             if not content and m.content:
                 content = m.content
-            if not content and getattr(m, "reasoning", None):
+            if not content and getattr(m, "reasoning", None) and self._spec and self._spec.reasoning_as_content:
                 content = m.reasoning
 
         tool_calls = []