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)

providers/shared/model_capabilities.py

@@ -28,6 +28,8 @@ class ModelCapabilities:
         * Tool selection logic inspects attributes such as
           ``supports_extended_thinking`` or ``context_window`` to choose an
           appropriate model for a task.
+        * The ``allow_code_generation`` flag enables structured code generation
+          in the chat tool for models more capable than the primary CLI.
     """
 
     provider: ProviderType
@@ -52,6 +54,9 @@ class ModelCapabilities:
     supports_temperature: bool = True
     use_openai_response_api: bool = False
     default_reasoning_effort: Optional[str] = None
+    allow_code_generation: bool = (
+        False  # Enables structured code generation in chat tool for substantial implementations
+    )
 
     # Additional attributes
     max_image_size_mb: float = 0.0