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_tools.py

@@ -3,6 +3,8 @@ Tests for individual tool implementations
 """
 
 import json
+import shutil
+import tempfile
 
 import pytest
 
@@ -343,12 +345,17 @@ class TestAbsolutePathValidation:
     async def test_chat_tool_relative_path_rejected(self):
         """Test that chat tool rejects relative paths"""
         tool = ChatTool()
-        result = await tool.execute(
-            {
-                "prompt": "Explain this code",
-                "files": ["code.py"],  # relative path without ./
-            }
-        )
+        temp_dir = tempfile.mkdtemp()
+        try:
+            result = await tool.execute(
+                {
+                    "prompt": "Explain this code",
+                    "files": ["code.py"],  # relative path without ./
+                    "working_directory": temp_dir,
+                }
+            )
+        finally:
+            shutil.rmtree(temp_dir, ignore_errors=True)
 
         assert len(result) == 1
         response = json.loads(result[0].text)