record_replay
Replay a recorded JSONL trajectory to verify each step as verified, unverified, or failed; use plan-only mode to preview actions or live mode to send real input and judge against expectations.
Instructions
Replay a recorded trajectory (JSONL) and report, per step, whether it was verified / unverified / failed. live=false (the default) sends no input: the actions come back as 'planned'. live=true delivers real keyboard and mouse input and judges each step against the expectation recorded in the trajectory. 'sent' only means delivered - it is not proof of effect, and a step with no recorded expectation stays 'unverified'. Failed steps keep their reason and error in actions[] and in failed_steps[], together with the step's 'activation' receipt (null when no activation was attempted).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"trajectory_path": "<trajectory_path>"
},
"name": "record_replay"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| live | No | false = plan only and send nothing; true = send real input and verify | |
| retries | No | attempts per step when the expectation is judged | |
| timeout | No | seconds to wait for the expectation to hold | |
| activate | No | live only: bring each step's window to the foreground before delivering. Real input lands on whatever is in front, so without it a background target fails. Steals focus. Ignored when live=false: a dry run never moves a window. | |
| interval | No | seconds between probes | |
| trajectory_path | Yes | path to a trajectory.jsonl (header + one step per line) |