AgentTeams for DeepSeek Harness: multi-agent team collaboration (captain, members, tasks with dependencies, messaging) driven by natural language, with a tree monitor in the web GUI
Tool-call ledger foundation for trajectory review: accumulates per-tool call counts and error classes across all sessions/workspaces into DSH_HOME/storages/tool-telemetry.json, consumed by trajectory-review.py as the evidence layer.
Local-first persistent memory infrastructure for DeepSeek Harness: hot bootstrap, Chinese-BM25 cold recall, lease-lock transactional writes, read-only governance
Repository check result
Results are bound to the listed commit and cover only static checks run by this registry. The Evidence Score measures reviewable information; it is not a compatibility percentage or a security guarantee.