Story

Release highlights

• Added maxEffortLevel setting (top-level or per model under modelSettings ): caps the effort level on every provider, including Bedrock, Vertex and Foundry; u...
• Added --system-prompt-snapshot off to render the system prompt fresh on every request instead of reusing the conversation's recorded prompt (for iterating on...
• Fixed Cowork scheduled tasks in the cloud failing at startup for organizations whose managed settings require sandboxing