feat: add flex mode option for cost savings (#372)

Adding in an option to turn on flex processing mode to reduce costs when
running the agent.

Bumped the openai typescript version to add the new feature.

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>

codex-cli/src/utils/config.ts

@@ -79,6 +79,9 @@ export type AppConfig = {
   memory?: MemoryConfig;
   /** Whether to enable desktop notifications for responses */
   notify: boolean;
+
+  /** Enable the "flex-mode" processing mode for supported models (o3, o4-mini) */
+  flexMode?: boolean;
   history?: {
     maxSize: number;
     saveHistory: boolean;