console
Read Houdini logs and node errors to diagnose unexpected results, empty geometry, or cook failures, returning only new entries since the last call.
Instructions
Read the Houdini log and the node errors.
Use it when something did not do what you expected. A cook error often
hides behind an empty result: the geometry has no points, and the reason is
here.
Do not use it for the errors of nodes that you cook now: cook returns them,
with the nodes upstream that failed. scene_overview mode "errors" lists every
node with a cook error, without the log.
Each call takes the log entries away, so a call returns only what is new
since the call before it.
Returns JSON.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "console"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many log entries come back, the newest ones. | |
| source | No | Keep the entries whose source holds this text, for example "Python". | |
| severity | No | Keep one level only: "message", "important", "warning", "error" or "fatal". | |
| root_path | No | The network that node_errors walks, for example /obj or /stage. | /obj |
| node_limit | No | How many nodes with an error or a warning come back. Errors come first, and the report says how many it left out. | |
| node_errors | No | Also report the nodes under root_path that hold an error or a warning. False gives the log alone. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |