agent_debug_run_failure · action · Utility · Available · v1.0.0
AI agent for post-mortem debugging of failed workflow runs: analyses the errored run (step outputs, error stacks, node configs) and produces actionable fix recommendations with confidence scores — cutting mean-time-to-resolution dramatically.
Fields shown in the editor when configuring the node. Generated directly from the NodeDefconfigFields.
| Field | Type | Required | Default | Description |
|---|---|---|---|---|
runIdRun ID | expression | yes | — {{input.runId}} o "run_a1b2c3..." | ID del run da analizzare. Recuperabile da run history o trigger error_handler. |
failedNodeIdFailed Node ID (opzionale) | expression | no | — | Se vuoto, auto-detect dal primo step con status=error. Specifica per analisi mirata su nodo non terminale. |
includeTestsGenera test cases | boolean | no | true | Se on, l'agente genera test scenarios + mock data + expected output per ogni fix proposto. |
maxFixesNumero max fix proposti | number | no | 3 | Da 1 a 5. Più fix = più tempo LLM ma più alternative. |
autoReplayReplay automatico con fix top-1 | boolean | no | false | PERICOLO: se on, applica il fix con confidence più alta e replaya il run automaticamente. Solo per workflow non-critici o con guard a valle. |
JSON snippet of the node as it appears in the workflow. Values are derived fromdefaultValue and from required parameters.
{
"id": "node-agent_debug_run_failure-1",
"defId": "agent_debug_run_failure",
"label": "AI Debug Run Failure",
"config": {
"runId": "{{input.runId}} o \"run_a1b2c3...\"",
"includeTests": true,
"maxFixes": 3,
"autoReplay": false
}
}Available now on all FlowForge plans. Try it free without a credit card.
Start freeBrowse all nodes