chore(repo): establish project baseline
Track the source-of-truth code, skills, bootstrap rules, docs, and packaging files before adding new features. Exclude local vault config, generated skill mirrors, temporary exports, virtual environments, and business data files from version control. Validation: inspected staged file list and git ignored status before commit.
This commit is contained in:
nac
@@ -0,0 +1,154 @@
|
||||
# OpenClaw Agent — Data Format Reference
|
||||
|
||||
Field-level notes for parsing `~/.openclaw/` artifacts during wiki ingest.
|
||||
|
||||
## Cache Root
|
||||
|
||||
`~/.openclaw/` — all paths below are relative to this root.
|
||||
|
||||
## workspace/MEMORY.md
|
||||
|
||||
Plain markdown. No required frontmatter — structure varies by user and agent configuration. Typically looks like:
|
||||
|
||||
```markdown
|
||||
# Memory
|
||||
|
||||
## User Preferences
|
||||
- Prefers concise responses without trailing summaries
|
||||
- Uses pnpm over npm
|
||||
|
||||
## Projects
|
||||
### my-api
|
||||
- FastAPI app, deployed on Fly.io
|
||||
- Uses Postgres via Supabase
|
||||
|
||||
## Patterns
|
||||
- Debugging: always check logs before code changes
|
||||
```
|
||||
|
||||
This is the single most valuable source in the entire `~/.openclaw/` tree. Read it fully before touching session logs.
|
||||
|
||||
## workspace/memory/YYYY-MM-DD.md
|
||||
|
||||
Daily note files. Auto-generated by OpenClaw at the start of each day. Format:
|
||||
|
||||
```markdown
|
||||
# 2026-04-15
|
||||
|
||||
## Session: my-api refactor
|
||||
- Rewrote auth middleware to use JWT instead of sessions
|
||||
- Decision: keep refresh tokens in httpOnly cookies
|
||||
|
||||
## Session: obsidian-wiki
|
||||
- Added cross-linker skill
|
||||
- Fixed broken wikilinks in concepts/
|
||||
```
|
||||
|
||||
Today's and yesterday's files are loaded into every session automatically. Files older than ~7 days have sharply diminishing signal.
|
||||
|
||||
## workspace/DREAMS.md
|
||||
|
||||
Optional. Some OpenClaw configurations generate end-of-day summaries here. Plain markdown. Treat as a lower-priority supplement to MEMORY.md — skim for novel insights not already captured in MEMORY.md.
|
||||
|
||||
## agents/\<agentId\>/sessions/sessions.json
|
||||
|
||||
Session index. JSON array:
|
||||
|
||||
```json
|
||||
[
|
||||
{
|
||||
"id": "abc123",
|
||||
"name": "my-api refactor",
|
||||
"created_at": "2026-04-15T10:00:00Z",
|
||||
"updated_at": "2026-04-15T12:30:00Z",
|
||||
"message_count": 47,
|
||||
"agent_id": "default"
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
Use this to:
|
||||
- Build a session inventory before opening JSONL files
|
||||
- Prioritize by `updated_at` (most recent = highest signal)
|
||||
- Map session IDs to human-readable names
|
||||
|
||||
## agents/\<agentId\>/sessions/\<sessionId\>.jsonl
|
||||
|
||||
Per-session transcript. JSONL, append-only. One JSON object per line:
|
||||
|
||||
**User turn:**
|
||||
```json
|
||||
{"role": "user", "content": "How do I debounce a React input?", "timestamp": "2026-04-15T10:01:00Z"}
|
||||
```
|
||||
|
||||
**Assistant turn:**
|
||||
```json
|
||||
{"role": "assistant", "content": "Use useCallback + useEffect with a clearTimeout...", "timestamp": "2026-04-15T10:01:02Z"}
|
||||
```
|
||||
|
||||
**Tool call:**
|
||||
```json
|
||||
{"role": "tool", "name": "read_file", "input": {"path": "/home/ubuntu/app/src/App.tsx"}, "timestamp": "2026-04-15T10:01:05Z"}
|
||||
```
|
||||
|
||||
**Tool result:**
|
||||
```json
|
||||
{"role": "tool_result", "name": "read_file", "content": "...", "timestamp": "2026-04-15T10:01:05Z"}
|
||||
```
|
||||
|
||||
`role` is the primary dispatch field. `timestamp` is ISO 8601. `content` may be a string or a structured object (for multi-part responses).
|
||||
|
||||
## agents/\<agentId\>/sessions/\<sessionId\>-topic-\<threadId\>.jsonl
|
||||
|
||||
Telegram topic variant — same schema as the base session JSONL. The `-topic-<threadId>` suffix identifies which Telegram thread generated the session. Parse identically to a regular session file.
|
||||
|
||||
## openclaw.json
|
||||
|
||||
Global config. Rarely useful for ingest. Fields of interest if needed:
|
||||
|
||||
```json
|
||||
{
|
||||
"agents": {
|
||||
"defaults": {
|
||||
"workspace": "~/.openclaw/workspace",
|
||||
"bootstrapMaxChars": 20000
|
||||
}
|
||||
},
|
||||
"skills": {
|
||||
"load": {
|
||||
"extraDirs": []
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
`agents.defaults.workspace` is the canonical path for MEMORY.md and daily notes if non-default.
|
||||
|
||||
## Bootstrap file priority (for reference)
|
||||
|
||||
OpenClaw loads context files in this order at session start:
|
||||
|
||||
| Priority | File | Notes |
|
||||
|---|---|---|
|
||||
| 10 | `AGENTS.md` | Always-on project instructions |
|
||||
| 20 | `SOUL.md` | Agent identity |
|
||||
| 30 | `IDENTITY.md` | Agent persona |
|
||||
| 40 | `USER.md` | User profile |
|
||||
| 50 | `TOOLS.md` | Tool config |
|
||||
| 60 | `BOOTSTRAP.md` | Custom bootstrap |
|
||||
| 70 | `MEMORY.md` | Long-term memory (workspace copy) |
|
||||
|
||||
All files are truncated at `bootstrapMaxChars` (default 20,000 chars) per file.
|
||||
|
||||
## Extraction Priority
|
||||
|
||||
| Source | Signal | Noise |
|
||||
|---|---|---|
|
||||
| `workspace/MEMORY.md` | Very high — curated, durable | Very low |
|
||||
| `workspace/memory/YYYY-MM-DD.md` (recent) | High — active context | Low |
|
||||
| `workspace/DREAMS.md` | Medium — summaries | Low |
|
||||
| `workspace/memory/YYYY-MM-DD.md` (old) | Low — stale | Medium |
|
||||
| `sessions/*.jsonl` — assistant turns | Medium | Medium |
|
||||
| `sessions/*.jsonl` — tool pairs | Low | High |
|
||||
| `openclaw.json` | Very low | — |
|
||||
| `credentials/` | None — skip | — |
|
||||
Reference in New Issue
Block a user