# USER.md

<!-- OPENCLAW_SYNC_FILE: USER.md -->
# USER.md - User Model

Store stable user preferences and profile facts as directives that can guide future sessions.

Use one directive per entry:

```md
<!-- observed: YYYY-MM-DD | status: active -->

- Prefer concise progress updates during implementation work.
```

- Begin each directive with an imperative such as `Always`, `Never`, or `Prefer`.
- Record the observation date and either `active` or `superseded` on the metadata line.
- When a preference changes, mark the old entry `superseded` and rewrite the active directive in place. Never append a contradictory active directive.
- Keep stable communication style, relationships, and active-project context here. Put durable non-profile facts and decisions in `MEMORY.md`.
- Save this file at the workspace root as `USER.md`. It loads every session with a separate 4,000-character budget.

## Directives

<!-- observed: 2026-09-12 | status: active -->

- Always use the configured OpenAI `openai/gpt-5.6-luna` model by default.

<!-- observed: 2026-09-14 | status: active -->

- Always treat a newly requested ongoing action as a one-time trial first; after the trial, ask whether to promote it to a permanent behaviour, discard it, or—only when truly important—incorporate it into the agent instructions.

<!-- observed: 2026-09-14 | status: active -->

- Always collect non-urgent, destructive, ambiguous, or externally visible follow-up decisions in a dashboard approval queue for periodic review; do not apply them until explicitly approved.

## Related

- [Agent workspace](/concepts/agent-workspace)