Architecture-quality audit notes from hermescheck

Hi maintainers — this is a friendly architecture-quality audit note, not a security report.

I’ve been building hermescheck, a small open-source scanner that reviews AI agent runtimes for state recovery, memory drift, tool boundaries, scheduler behavior, and other long-running agent failure modes. I ran it against modelscope/ms-agent because this repo is an active agent runtime/framework with real CLI, web UI, workflow, memory, and tool-execution surfaces.

Three runtime/architecture notes that looked worth sharing:

1. Recovery currently looks transcript-heavy rather than fully resumable.
   ms_agent/utils/utils.py persists config + message history, and ms_agent/llm/openai_llm.py continues long generations, but I didn’t see the same level of durable environment / side-effect / restart contract around those flows. That can make interrupted work harder to resume deterministically.

2. Web UI session state appears in-memory and explicit-delete driven.
   webui/backend/session_manager.py keeps sessions, messages, and deep-research events in process memory, and webui/backend/websocket_handler.py mainly cleans up task/runner references on stop or completion. This felt a bit fragile for server restarts or abandoned sessions if the goal is durable operator-facing workflows.

3. Memory surfaces look split across several layers without one obvious freshness contract.
   I saw cache/history handling in ms_agent/utils/utils.py, long-term memory logic in ms_agent/memory/default_memory.py, and separate condenser/default-memory surfaces under ms_agent/memory/. The architecture may benefit from a clearer “authoritative current memory vs derived/archive/cache layers” rule.

None of the above is meant as “you must change this”; it just looked like a useful maintainer-facing architecture snapshot from an external pass.

Repo for the tool: https://github.com/huangrichao2020/hermescheck

If this isn’t useful, feel free to close and I won’t take it personally.

Start by reading ms_agent/utils/utils.py, ms_agent/llm/openai_llm.py, webui/backend/session_manager.py, webui/backend/websocket_handler.py, and the files under ms_agent/memory/. The audit identifies possible recovery, session durability, and memory-freshness concerns, but provides no failing test, concrete change, acceptance criteria, or definition of done.