session_ping
Store a lightweight checkpoint of your current task and files to preserve progress across AI provider switches, enabling reconstruction even if the session ends unexpectedly.
Instructions
Lightweight checkpoint — call this every ~5 tool calls or whenever you complete a significant step. Stores the current task + files touched so session_start on the NEXT provider can reconstruct what happened even if session_end was never called (e.g. Claude context limit hit, window crashed). This solves the provider-switching problem: Claude → Copilot → Cursor all see the same last checkpoint. Extremely fast — one Redis SET, no blocking operations.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| instance_id | Yes | UUID of the cache instance | |
| task | Yes | What you are currently working on (e.g. "Implementing invite handler in handler/invite.go") | |
| files_touched | No | Files modified so far this session | |
| next_step | No | What the NEXT step is after this checkpoint (helps next provider resume immediately) | |
| provider | No | Current AI provider (e.g. "claude-code", "copilot", "cursor", "windsurf") |