fix(openai): use max_completion_tokens for OpenAI provider (#2758)

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(

tests/providers/test_openai_compat_max_completion_tokens.py

@@ -0,0 +1,34 @@
+"""Regression tests for max_completion_tokens selection in OpenAI-compatible providers."""
+
+from unittest.mock import patch
+
+from nanobot.providers.openai_compat_provider import OpenAICompatProvider
+from nanobot.providers.registry import find_by_name
+
+
+def test_openai_provider_uses_max_completion_tokens_when_supported():
+    """OpenAI registry spec should drive max_completion_tokens payload selection."""
+    spec = find_by_name("openai")
+    assert spec is not None
+    assert spec.supports_max_completion_tokens is True
+
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):
+        provider = OpenAICompatProvider(
+            api_key="test-key",
+            api_base=None,
+            default_model="gpt-4.1",
+            spec=spec,
+        )
+
+    payload = provider._build_kwargs(
+        messages=[{"role": "user", "content": "Hello"}],
+        tools=None,
+        model="gpt-4.1",
+        max_tokens=1234,
+        temperature=0.2,
+        reasoning_effort=None,
+        tool_choice=None,
+    )
+
+    assert payload["max_completion_tokens"] == 1234
+    assert "max_tokens" not in payload