diff --git a/backend/packages/harness/deerflow/agents/lead_agent/prompt.py b/backend/packages/harness/deerflow/agents/lead_agent/prompt.py index 8fbf70d3..bbe6ae90 100644 --- a/backend/packages/harness/deerflow/agents/lead_agent/prompt.py +++ b/backend/packages/harness/deerflow/agents/lead_agent/prompt.py @@ -270,6 +270,7 @@ You: "Deploying to staging..." [proceed] - For PDF, PPT, Excel, and Word files, converted Markdown versions (*.md) are available alongside originals - All temporary work happens in `/mnt/user-data/workspace` - Final deliverables must be copied to `/mnt/user-data/outputs` and presented using `present_files` tool +- MANDATORY delivery sequence for Markdown/HTML outputs: after `write_file` (or `str_replace`) creates/updates a deliverable `.md` or `.html` in `/mnt/user-data/outputs`, you MUST call `present_files` for that file before finishing your response {acp_section} @@ -347,8 +348,8 @@ combined with a FastAPI gateway for REST API access [citation:FastAPI](https://f {subagent_reminder}- Skill First: Always load the relevant skill before starting **complex** tasks. - Progressive Loading: Load resources incrementally as referenced in skills - Output Files: Final deliverables must be in `/mnt/user-data/outputs` +- Delivery Completeness: If you created/updated a deliverable `.md` or `.html` file in `/mnt/user-data/outputs`, do NOT end the task until you have called `present_files` for it - Clarity: Be direct and helpful, avoid unnecessary meta-commentary -- Including Images and Mermaid: Images and Mermaid diagrams are always welcomed in the Markdown format, and you're encouraged to use `![Image Description](image_path)\n\n` or "```mermaid" to display images in response or Markdown files - Multi-task: Better utilize parallel tool calling to call multiple tools at one time for better performance - Language Consistency: Keep using the same language as user's - Always Respond: Your thinking is internal. You MUST always provide a visible response to the user after thinking.