- No longer relies on agent outputting [STEP N DONE] tags - Each successful tool_result marks the next uncompleted step done - Much more reliable than expecting LLM to follow tag format - Simplified execution context (no special instructions needed)
- No longer relies on agent outputting [STEP N DONE] tags - Each successful tool_result marks the next uncompleted step done - Much more reliable than expecting LLM to follow tag format - Simplified execution context (no special instructions needed)