scenario_create
Consolidate five or more related memory atoms into a single high-signal scenario summary, cutting recall cost from many tokens to roughly one hundred. Write the summary yourself to preserve the key insight.
Instructions
Consolidate multiple L1 atoms into an L2 scenario summary. Call this when you have 5+ atoms about the same topic — it creates a high-signal summary that recall injects in ~100 tokens instead of 5+ individual atoms. No LLM needed — you write the summary yourself based on the atoms you've seen.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| summary | Yes | A 1-3 sentence summary that captures the key insight from these atoms. Write it as a self-contained fact useful on its own. | |
| task_id | No | The task ID. Use this to isolate memory by a specific task. Link captures to a task for finer isolation. | |
| team_id | No | The team ID. Use this to isolate memory by team. When set, all queries filter by this value. | |
| user_id | No | The user ID. Use this to isolate memory by user within a team. When set with team_id, queries filter by both. | |
| agent_id | No | The agent ID. Use this to isolate memory by agent role within a team. Defaults to the detected agent. | |
| atom_ids | Yes | The L1 atom IDs to consolidate (1-20). | |
| persona_tags | No | Optional tags for categorization (e.g., ['database', 'migration']). |