batch_dataset
Previews batch analysis inputs from per-run files, returning sample, seed, and condition identities with eligible members and exclusions before generating batch-samples.json via analysis_submit.
Instructions
Preview batch analysis inputs from collected per-run files. Return independent sample/seed/condition identities, eligible members and all exclusions. files are relative to each run directory. Use analysis_submit(batch_id,batch_files) to generate batch-samples.json and samples/<run_id>/... automatically. Partial failed-run analysis can use ordinary input_bindings with an explicit method.
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": {
"task_id": "<task_id>",
"batch_id": "<batch_id>",
"files": "<files>"
},
"name": "batch_dataset"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| files | Yes | ||
| task_id | Yes | ||
| batch_id | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |