feat!: Full code can now be generated by an external model and shared with the AI tool (Claude Code / Codex etc)!

model definitions now support a new `allow_code_generation` flag, only to be used with higher reasoning models such as GPT-5-Pro and-Gemini 2.5-Pro

 When `true`, the `chat` tool can now request the external model to generate a full implementation / update / instructions etc and then share the implementation with the calling agent.

 This effectively allows us to utilize more powerful models such as GPT-5-Pro to generate code for us or entire implementations (which are either API-only or part of the $200 Pro plan from within the ChatGPT app)

tests/test_auto_mode.py

@@ -137,7 +137,7 @@ class TestAutoMode:
             importlib.reload(config)
 
     @pytest.mark.asyncio
-    async def test_auto_mode_requires_model_parameter(self):
+    async def test_auto_mode_requires_model_parameter(self, tmp_path):
         """Test that auto mode enforces model parameter"""
         # Save original
         original = os.environ.get("DEFAULT_MODEL", "")
@@ -154,7 +154,7 @@ class TestAutoMode:
             # Mock the provider to avoid real API calls
             with patch.object(tool, "get_model_provider"):
                 # Execute without model parameter
-                result = await tool.execute({"prompt": "Test prompt"})
+                result = await tool.execute({"prompt": "Test prompt", "working_directory": str(tmp_path)})
 
             # Should get error
             assert len(result) == 1