memory

name	memory
description	Two-layer memory system with Dream-managed knowledge files.
always	true

Memory

Structure

Static files (workspace root):

• SOUL.md — Bot personality. Static; do NOT edit.
• USER.md — User profile (name, language, region). Set during fincat onboard --wizard; do NOT edit.

Dream-generated:

• memory/memory.md — LLM summary of all category files. Auto-regenerated nightly. Do NOT edit.

Category files (managed by Dream):

• memory/profile/ — 用户画像
• memory/preferences/ — 用户偏好
• memory/knowledge/ — 产品知识
• memory/behavioral_insights/ — 行为洞察
• memory/compliance/ — 合规规则
• memory/custom/ — 对话案例 + Dream 自动发现的新类别

History:

• memory/history.jsonl — Consolidator 摘要，append-only JSONL

Search Past Events

memory/history.jsonl is JSONL format — each line is a JSON object with cursor, timestamp, content.

• For broad searches, start with grep(..., path="memory", glob="*.jsonl", output_mode="count") or the default files_with_matches mode before expanding to full content
• Use output_mode="content" plus context_before / context_after when you need the exact matching lines
• Use fixed_strings=true for literal timestamps or JSON fragments
• Use head_limit / offset to page through long histories
• Use exec only as a last-resort fallback when the built-in search cannot express what you need

Examples (replace keyword):

• grep(pattern="keyword", path="memory/history.jsonl", case_insensitive=true)
• grep(pattern="2026-04-02 10:00", path="memory/history.jsonl", fixed_strings=true)
• grep(pattern="keyword", path="memory", glob="*.jsonl", output_mode="count", case_insensitive=true)
• grep(pattern="oauth|token", path="memory", glob="*.jsonl", output_mode="content", case_insensitive=true)

Important

• Do NOT edit SOUL.md, USER.md, or memory/memory.md. SOUL.md and USER.md are static; memory.md is auto-generated by Dream.
• If you notice outdated information in category files, it will be corrected when Dream runs next.
• Users can view Dream's activity with the /dream-log command.