fix: use SystemMessage+HumanMessage for follow-up question generation (#1751)

* fix: use SystemMessage+HumanMessage for follow-up question generation (fixes #1697)

Some models (e.g. MiniMax-M2.7) require the system prompt and user
content to be passed as separate message objects rather than a single
combined string. Invoking with a plain string sends everything as a
HumanMessage, which causes these models to ignore the generation
instructions and fail to produce valid follow-up questions.

* test: verify model is invoked with SystemMessage and HumanMessage

backend/app/gateway/routers/suggestions.py

@@ -2,6 +2,7 @@ import json
 import logging
 
 from fastapi import APIRouter
+from langchain_core.messages import HumanMessage, SystemMessage
 from pydantic import BaseModel, Field
 
 from deerflow.models import create_chat_model
@@ -106,7 +107,7 @@ async def generate_suggestions(thread_id: str, request: SuggestionsRequest) -> S
     if not conversation:
         return SuggestionsResponse(suggestions=[])
 
-    prompt = (
+    system_instruction = (
         "You are generating follow-up questions to help the user continue the conversation.\n"
         f"Based on the conversation below, produce EXACTLY {n} short questions the user might ask next.\n"
         "Requirements:\n"
@@ -114,14 +115,13 @@ async def generate_suggestions(thread_id: str, request: SuggestionsRequest) -> S
         "- Questions must be written in the same language as the user.\n"
         "- Keep each question concise (ideally <= 20 words / <= 40 Chinese characters).\n"
         "- Do NOT include numbering, markdown, or any extra text.\n"
-        "- Output MUST be a JSON array of strings only.\n\n"
-        "Conversation:\n"
-        f"{conversation}\n"
+        "- Output MUST be a JSON array of strings only.\n"
     )
+    user_content = f"Conversation Context:\n{conversation}\n\nGenerate {n} follow-up questions"
 
     try:
         model = create_chat_model(name=request.model_name, thinking_enabled=False)
-        response = model.invoke(prompt)
+        response = model.invoke([SystemMessage(content=system_instruction), HumanMessage(content=user_content)])
         raw = _extract_response_text(response.content)
         suggestions = _parse_json_string_list(raw) or []
         cleaned = [s.replace("\n", " ").strip() for s in suggestions if s.strip()]