Add opt-in retention for turn tool outputs (#52686)

## What changed

Add an optional `retain` flag to `TurnToolOutput` for `turn/start`. When set to `true`, pass the output to the core with a retention annotation to request retention in the thread's model history. The flag defaults to `false`, preserving existing behavior.

Update the generated JSON schemas, TypeScript types, and Python bindings to expose the flag.

## Testing

Add an integration test verifying that a retained tool output reaches the model and preserves client-authored sender metadata in persisted history, including the receiver message ID.

GitOrigin-RevId: 52893a8fcb308f26e77ba8f0bee9990073b26d54

sdk/python/src/openai_codex/generated/v2_all.py

@@ -11832,6 +11832,10 @@ class TurnToolOutput(BaseModel):
     name: str
     namespace: str | None = None
     output: FunctionCallOutputBody
+    retain: Annotated[
+        bool | None,
+        Field(description="Requests retention of this output in the thread's model history."),
+    ] = None
 
 
 class TurnsPage(BaseModel):