✨ sync: restore parallel optimization guidance in context-based prompt formatting

sdk/nexent/core/agents/context/formatting.py

@@ -380,6 +380,7 @@ def _format_managed_agents_description(
         lines.append("     - 返回输出类型：{\"type\": \"string\", \"description\": \"执行结果\"}")
         lines.append("  2. 使用策略：")
         lines.append("     - 任务分解：单次调用中不要让助手一次做过多的事情，任务拆分是你的工作，你需要将复杂任务分解为可管理的子任务")
+        lines.append("     - 并行优化：如果你有多个互不依赖的子任务，可以在单步内发出多个助手调用，系统将并行执行以节省时间。判断标准：子任务不需要对方的输出作为输入即可并行。示例：同时检查代码风格、安全性和逻辑 → 一步内调用3个助手。反例：先搜索信息，再基于结果写报告 → 必须串行。")
         lines.append("     - 专业匹配：根据助手的专长分配任务")
         lines.append("     - 信息整合：整合不同助手的输出生成连贯解决方案")
         lines.append("     - 效率优化：避免重复工作")
@@ -400,6 +401,7 @@ def _format_managed_agents_description(
         lines.append("      - Returns output type: {\"type\": \"string\", \"description\": \"execution result\"}")
         lines.append("   2. Usage strategy:")
         lines.append("      - Task decomposition: Don't let agents do too many things in a single call, task breakdown is your job, you need to decompose complex tasks into manageable subtasks")
+        lines.append("      - Parallel optimization (important): If you have multiple independent subtasks, you can issue multiple agent calls in a single step -- the system will execute them in parallel to save time. Criterion: if subtasks do not need each other's output as input, they are parallelizable. Example: checking code style, security, and logic simultaneously → call 3 agents in one step. Counter-example: first search for information, then write a report based on results → must be serial.")
         lines.append("      - Professional matching: Assign tasks based on agent expertise")
         lines.append("      - Information integration: Integrate outputs from different agents to generate coherent solutions")
         lines.append("      - Efficiency optimization: Avoid duplicate work")