chore(backend): 强化输出文件的 present_files 交付约束

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}
 </working_directory>
 
@@ -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.