How to interpret AI Agent termination reasons from Execution PlanIssue <!-- /*NS Branding Styles*/ --> .ns-kb-css-body-editor-container { p { font-size: 12pt; font-family: Lato; color: var(--now-color--text-primary, #000000); } span { font-size: 12pt; font-family: Lato; color: var(--now-color--text-primary, #000000); } h2 { font-size: 24pt; font-family: Lato; color: var(--now-color--text-primary, black); } h3 { font-size: 18pt; font-family: Lato; color: var(--now-color--text-primary, black); } h4 { font-size: 14pt; font-family: Lato; color: var(--now-color--text-primary, black); } a { font-size: 12pt; font-family: Lato; color: var(--now-color--link-primary, #00718F); } a:hover { font-size: 12pt; color: var(--now-color--link-primary, #024F69); } a:target { font-size: 12pt; color: var(--now-color--link-primary, #032D42); } a:visited { font-size: 12pt; color: var(--now-color--link-primary, #00718f); } ul { font-size: 12pt; font-family: Lato; } li { font-size: 12pt; font-family: Lato; } img { display: ; max-width: ; width: ; height: ; } } Users want to understand how the termination reasons of an AI Agent execution are classified in the sn_aia_execution_plan and sn_aia_execution_task tables. Release<!-- /*NS Branding Styles*/ --> .ns-kb-css-body-editor-container { p { font-size: 12pt; font-family: Lato; color: var(--now-color--text-primary, #000000); } span { font-size: 12pt; font-family: Lato; color: var(--now-color--text-primary, #000000); } h2 { font-size: 24pt; font-family: Lato; color: var(--now-color--text-primary, black); } h3 { font-size: 18pt; font-family: Lato; color: var(--now-color--text-primary, black); } h4 { font-size: 14pt; font-family: Lato; color: var(--now-color--text-primary, black); } a { font-size: 12pt; font-family: Lato; color: var(--now-color--link-primary, #00718F); } a:hover { font-size: 12pt; color: var(--now-color--link-primary, #024F69); } a:target { font-size: 12pt; color: var(--now-color--link-primary, #032D42); } a:visited { font-size: 12pt; color: var(--now-color--link-primary, #00718f); } ul { font-size: 12pt; font-family: Lato; } li { font-size: 12pt; font-family: Lato; } img { display: ; max-width: ; width: ; height: ; } } Australia Patch 2 Resolution<!-- /*NS Branding Styles*/ --> .ns-kb-css-body-editor-container { p { font-size: 12pt; font-family: Lato; color: var(--now-color--text-primary, #000000); } span { font-size: 12pt; font-family: Lato; color: var(--now-color--text-primary, #000000); } h2 { font-size: 24pt; font-family: Lato; color: var(--now-color--text-primary, black); } h3 { font-size: 18pt; font-family: Lato; color: var(--now-color--text-primary, black); } h4 { font-size: 14pt; font-family: Lato; color: var(--now-color--text-primary, black); } a { font-size: 12pt; font-family: Lato; color: var(--now-color--link-primary, #00718F); } a:hover { font-size: 12pt; color: var(--now-color--link-primary, #024F69); } a:target { font-size: 12pt; color: var(--now-color--link-primary, #032D42); } a:visited { font-size: 12pt; color: var(--now-color--link-primary, #00718f); } ul { font-size: 12pt; font-family: Lato; } li { font-size: 12pt; font-family: Lato; } img { display: ; max-width: ; width: ; height: ; } } Please note: The sn_aia_execution_plan and sn_aia_execution_task tables are internal table records of the AI Agent runtime. They're intended for observability/troubleshooting, and their exact field values structure (like metadata, output, etc) can change between releases. 1. Execution failed (processing error, tool failure, etc.)- On the execution_plan record: `state = terminated`, and `state_reason = execution_failed` (a runtime failure).- On the execution_task record, the step that actually failed generally isn't recorded as errored state. When the plan terminates, its ongoing execution_tasks are set to "cancelled". So execution_plan's "state_reason" should be checked for the classification.- If the failure was inside a tool call, "sn_aia_tools_execution" for that run will show "execution_status = error" (or "timeout") with details in "error_message" / "response".2. Blocked/failed by security or access restrictions- On the execution_plan record: `state = terminated`, `state_reason = security_violation`.- Access checks that run as part of a flow create a execution_task record of `type = access_verification`. A `status = success` on that execution_task means the check executed, not that access was granted. That execution_task's "output" (JSON) field can be checked for more details on which entities ACL access was denied.3. Cancelled / ended by the user- On the execution_plan record: a `state_reason = user_exited` indicates the user chose to end the interaction.- Note: If the user simply closed or walked away from the conversation without anything in progress, the run is typically closed as `state = completed` with `state_reason = no_activity`, or marked `state = abandoned`. In all of these, any still-running child execution_task records are set to state = cancelled.4. Other interruptions- `state_reason = live_agent_requested` - handed off to a live agent.