- Each todo item gets a unique ID (e.g., abc123) - Agent marks items complete by outputting [DONE:id] - IDs shown in chat and in execution context - Agent instructed to output [DONE:id] after each step - Removed unreliable tool-counting heuristics
- Each todo item gets a unique ID (e.g., abc123) - Agent marks items complete by outputting [DONE:id] - IDs shown in chat and in execution context - Agent instructed to output [DONE:id] after each step - Removed unreliable tool-counting heuristics