feat(providers): add GPT-5 model family support for OpenAI provider

Enable GPT-5 models (gpt-5, gpt-5.4, gpt-5.4-mini, etc.) to work
correctly with the OpenAI-compatible provider by:

- Setting `supports_max_completion_tokens=True` on the OpenAI provider
  spec so `max_completion_tokens` is sent instead of the deprecated
  `max_tokens` parameter that GPT-5 rejects.
- Adding `_supports_temperature()` to conditionally omit the
  `temperature` parameter for reasoning models (o1/o3/o4) and when
  `reasoning_effort` is active, matching the existing Azure provider
  behaviour.

Both changes are backward-compatible: older GPT-4 models continue to
work as before since `max_completion_tokens` is accepted by all recent
OpenAI models and temperature is only omitted when reasoning is active.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

nanobot/providers/openai_compat_provider.py

@@ -223,6 +223,21 @@ class OpenAICompatProvider(LLMProvider):
     # Build kwargs
     # ------------------------------------------------------------------
 
+    @staticmethod
+    def _supports_temperature(
+        model_name: str,
+        reasoning_effort: str | None = None,
+    ) -> bool:
+        """Return True when the model accepts a temperature parameter.
+
+        GPT-5 family and reasoning models (o1/o3/o4) reject temperature
+        when reasoning_effort is set to anything other than ``"none"``.
+        """
+        if reasoning_effort and reasoning_effort.lower() != "none":
+            return False
+        name = model_name.lower()
+        return not any(token in name for token in ("o1", "o3", "o4"))
+
     def _build_kwargs(
         self,
         messages: list[dict[str, Any]],
@@ -247,9 +262,13 @@ class OpenAICompatProvider(LLMProvider):
         kwargs: dict[str, Any] = {
             "model": model_name,
             "messages": self._sanitize_messages(self._sanitize_empty_content(messages)),
-            "temperature": temperature,
         }
 
+        # GPT-5 and reasoning models (o1/o3/o4) reject temperature when
+        # reasoning_effort is active.  Only include it when safe.
+        if self._supports_temperature(model_name, reasoning_effort):
+            kwargs["temperature"] = temperature
+
         if spec and getattr(spec, "supports_max_completion_tokens", False):
             kwargs["max_completion_tokens"] = max(1, max_tokens)
         else:

nanobot/providers/registry.py

@@ -200,6 +200,7 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
         env_key="OPENAI_API_KEY",
         display_name="OpenAI",
         backend="openai_compat",
+        supports_max_completion_tokens=True,
     ),
     # OpenAI Codex: OAuth-based, dedicated provider
     ProviderSpec(