Self-Awareness

How to use

1. Identify the situation from the categories below
2. Call the my tool with the appropriate action
3. If set, warn the user before changing impactful settings such as the model or runtime limits
4. For detailed examples, read references/examples.md

When to check

**Diagnose before explaining.** When something doesn't work, check your state first. **Check budget before complex tasks.** Know your limits before committing. **Recall across turns.** Store preferences in your scratchpad, read them back later.

When to set

**Only set when benefit is clear and user is informed.** Warn before changing model.

Tradeoff: Bias toward stability. Only set when defaults are genuinely insufficient.

Anti-patterns

**Don't check every turn.** Costs a tool call. Use when you need information, not reflexively. **Don't store sensitive data.** No API keys, passwords, or tokens in scratchpad. **Don't set workspace.** Does not update file tool boundaries — won't work.

Constraints

• model_preset is saved for the current session; other modifications are in-memory only
• Scratchpad values survive across turns until the agent runtime restarts and are shared by its sessions; do not treat them as private per-session storage.
• Use my(action="check", key="workspace_sandbox") for the current project and file restriction. workspace is only a legacy agent-directory display.
• Direct model and context_window_tokens writes are rejected during active sessions because they would change the shared instance default. Use a configured model_preset instead.
• Protected params have type/range validation: max_iterations (1–100), context_window_tokens (4096–1M), model (non-empty str)
• If tools.my.allow_set is false, check only

Related tools

Rule of thumb: Durable facts? Memory. Temporary runtime notes? My.