session_start
Start each session with a single call that delivers summary, recent lessons, focus-relevant insights, failures, brain stats, team telepathy, failure predictions, and memory crystals. Avoids multiple separate lookups.
Instructions
Single-call session briefing. Call this at the START of every session INSTEAD of multiple separate smart_recall/recall_best_solution calls. Returns: last session summary, recent lessons sorted by recency, relevant lessons for your focus area, open failures (topics with only failure outcomes), brain health stats, team telepathy (what teammates learned this week), predictive pre-warnings (if your focus area has known failure patterns), and memory crystals (compressed wisdom from old sessions). Also saves a session start marker so session_end can compute duration.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| instance_id | Yes | UUID of the cache instance | |
| focus | No | Keywords for what you plan to work on today (e.g. "deploy infra api"). Used to surface relevant lessons at the top. | |
| author | No | Your name or handle (e.g. "alice"). Enables Team Telepathy — filters YOUR lessons vs TEAM lessons from past 7 days. | |
| provider | No | Current AI provider (e.g. "claude-code", "copilot", "cursor", "windsurf"). Shown in the briefing header and saved so the next provider can see who was last active. | |
| workspace_path | No | Absolute path to the project root. If no session_end was found (e.g. context limit hit), reads git log to reconstruct what happened since last session. |