fix(memory): batch semantic processing in _process_memory_directory

[chuanbao666]

Summary

修复记忆目录分批语义处理以防止协程调度风暴
fix: batch semantic processing in _process_memory_directory to prevent CPU spikes (#1245)

Type of Change

• New feature (feat)
• Bug fix (fix)
• Documentation (docs)
• Refactoring (refactor)
• Other

Testing

分批并发控制 : 在 semantic_processor.py 中，将无限制的 asyncio.gather 改造为按批次循环执行。

• 动态计算批大小： min(max_concurrent_llm, 10) ，确保单次提交给事件循环的任务量可控。

• 增加批次处理日志，提升后台任务的可观测性。

• Unit tests pass

• Manual testing completed

Related Issues

• Fixes [Bug]: _process_memory_directory launches hundreds of concurrent coroutines via asyncio.gather, causing 100% CPU on low-core machines #1245

Checklist

• Code follows project style guidelines
• Tests added for new functionality
• Documentation updated (if needed)
• All tests pass

[github-actions]

PR Reviewer Guide 🔍

Here are some key observations to aid the review process:

🎫 Ticket compliance analysis 🔶 1245 - Partially compliant Compliant requirements: Fix _process_memory_directory to avoid launching hundreds of concurrent coroutines at once Batch asyncio.gather calls to prevent CPU spikes on low-core machines Ensure steady progress through the memory file queue Maintain existing functionality while adding batching Non-compliant requirements: Requires further human verification:

⏱️ Estimated effort to review: 2 🔵🔵⚪⚪⚪

🏅 Score: 92

🧪 PR contains tests

🔒 No security concerns identified

✅ No TODO sections

🔀 No multiple PR themes

⚡ No major issues detected

[github-actions]

PR Code Suggestions ✨

No code suggestions found for the PR.