Session Memory Structured

在 /new 或 /reset 时，为刚结束的会话生成结构化纪要并归档到 memory/YYYY-MM-DD.md

This hook is internally consistent with its stated goal, but before installing: 1) edit the placeholder values (<YOUR_AGENT_ID>, <YOUR_PROVIDER_ID>) as instructed so it targets the correct local paths; 2) inspect your ~/.openclaw/.../models.json to verify the provider's baseUrl is a trusted endpoint (the code will send session text and use the apiKey from that entry); 3) if you need strict offline behavior, do not install or ensure the provider entry points to a local/offline model; 4) consider testing in a safe workspace (no sensitive session contents) to confirm behavior; 5) note the code uses global fetch (Node 18+ has fetch built-in) — ensure your runtime supports it or adapt accordingly.

Type: OpenClaw Skill Name: session-memory-structured Version: 1.0.0 The skill bundle accesses sensitive local files, including the agent's 'models.json' (which contains API keys) and private session history logs, to generate summaries via an external LLM provider. While this behavior is documented in 'README.md' and 'skill.md' as the intended functionality, the direct programmatic access to credentials and conversation data in 'handler.js' constitutes a high-risk capability. The script also requires manual user intervention to hardcode agent and provider IDs, and it transmits session content to an external endpoint defined in the user's local configuration.