Merge remote-tracking branch 'origin/main' into feat/search-tools

Made-with: Cursor

nanobot/skills/memory/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: memory
-description: Two-layer memory system with grep-based recall.
+description: Two-layer memory system with Dream-managed knowledge files.
 always: true
 ---
 
@@ -8,38 +8,29 @@ always: true
 
 ## Structure
 
-- `memory/MEMORY.md` — Long-term facts (preferences, project context, relationships). Always loaded into your context.
-- `memory/HISTORY.md` — Append-only event log. NOT loaded into context. Search it with grep-style tools or in-memory filters. Each entry starts with [YYYY-MM-DD HH:MM].
+- `SOUL.md` — Bot personality and communication style. **Managed by Dream.** Do NOT edit.
+- `USER.md` — User profile and preferences. **Managed by Dream.** Do NOT edit.
+- `memory/MEMORY.md` — Long-term facts (project context, important events). **Managed by Dream.** Do NOT edit.
+- `memory/history.jsonl` — append-only JSONL, not loaded into context. Prefer the built-in `grep` tool to search it.
 
 ## Search Past Events
 
-Choose the search method based on file size:
+`memory/history.jsonl` is JSONL format — each line is a JSON object with `cursor`, `timestamp`, `content`.
 
-- Small `memory/HISTORY.md`: use `read_file`, then search in-memory
-- Large or long-lived `memory/HISTORY.md`: use the built-in `grep` tool first
-- For broad searches, start with `grep(..., output_mode="count")` or accept the default `files_with_matches` output to scope the result set before asking for full matching lines
-- Use `head_limit` / `offset` when browsing long histories in chunks
-- Use `exec` only as a last-resort fallback when you truly need shell-specific behavior
+- 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:
-- `grep(pattern="keyword", path="memory/HISTORY.md", case_insensitive=true)`
-- `grep(pattern="[2026-04-02 10:00]", path="memory/HISTORY.md", fixed_strings=true)`
-- `grep(pattern="keyword", path="memory/HISTORY.md", output_mode="count", case_insensitive=true)`
-- `grep(pattern="token", path="memory", glob="*.md", output_mode="files_with_matches", case_insensitive=true)`
-- `grep(pattern="oauth|token", path="memory", glob="*.md", case_insensitive=true)`
-- Fallback shell examples:
-  - **Linux/macOS:** `grep -i "keyword" memory/HISTORY.md`
-  - **Windows:** `findstr /i "keyword" memory\HISTORY.md`
+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)`
 
-Prefer the built-in `grep` tool for large history files; only drop to shell when the built-in search cannot express what you need.
+## Important
 
-## When to Update MEMORY.md
-
-Write important facts immediately using `edit_file` or `write_file`:
-- User preferences ("I prefer dark mode")
-- Project context ("The API uses OAuth2")
-- Relationships ("Alice is the project lead")
-
-## Auto-consolidation
-
-Old conversations are automatically summarized and appended to HISTORY.md when the session grows large. Long-term facts are extracted to MEMORY.md. You don't need to manage this.
+- **Do NOT edit SOUL.md, USER.md, or MEMORY.md.** They are automatically managed by Dream.
+- If you notice outdated information, it will be corrected when Dream runs next.
+- Users can view Dream's activity with the `/dream-log` command.