Summarize network errors
summarize_td_errorsRead-only
Collect errors across a network, cluster by message, type, or parent, and identify worst-offending nodes with investigation suggestions. Use for network-wide triage instead of reading every node's errors individually.
Instructions
Read-only: collect errors across a network and cluster them by message, type, or parent container, with the worst-offending nodes and a suggested order to investigate. Returns {total, groups[], suggestions[]}. Use this for network-wide triage instead of reading every node's errors one by one; use get_td_node_errors when you just want the raw error list for one node or sub-tree.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | Network root to collect errors under. | /project1 |
| group_by | No | How to cluster errors: by exact message, by error type, or by parent container (to find a common upstream cause). | message |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | The network root errors were collected under, echoing the request. | |
| total | Yes | Total number of errors found across the network (0 means clean). | |
| group_by | Yes | How the errors were clustered, echoing the request. | |
| groups | Yes | Error clusters, largest first; fixing a big cluster's cause clears it at once. | |
| suggestions | Yes | Plain-language next steps, e.g. the common cause and which nodes to check first. |