II.
OrchestrationPrimitive overview
Reference · liveorch-primitive:agent-failover
Agent Failover overview
Redirect a failing or unavailable agent's workload to a standby agent or alternate harness. When the primary agent is unhealthy, rate-limited, or exhausted after retries, agent-failover transparently re-assigns the task to the next eligible agent from the fallback roster. Preserves workspace state so the standby agent resumes from the last known-good checkpoint rather than restarting from scratch.
Attributes
displayName
Agent Failover
description
Redirect a failing or unavailable agent's workload to a standby agent
or alternate harness. When the primary agent is unhealthy, rate-limited,
or exhausted after retries, agent-failover transparently re-assigns the
task to the next eligible agent from the fallback roster. Preserves
workspace state so the standby agent resumes from the last known-good
checkpoint rather than restarting from scratch.
orchestrationKind
dispatch
trigger
on-failure
Outgoing edges
orch_applies_to2
- topic:circuit-breakers·TopicCircuit Breakers
- topic:agent-dispatch·TopicAgent Dispatch
orch_requires_skill_area2
- skill-area:multi-agent-coordination·SkillAreaMulti-Agent Coordination
- skill-area:operations-automation·SkillAreaOperations Automation
orch_triggers2
- orch-primitive:agent-dispatch·OrchestrationPrimitiveAgent Dispatch
- orch-primitive:workspace-snapshot·OrchestrationPrimitiveWorkspace Snapshot
realizes1
- layer:13-orchestration·LayerOrchestration
Incoming edges
supports_orchestration_primitive1
- agent-core-impl:droid.core@current·AgentCoreImplFactory Droid Core (current)