As of PraisonAI #4334 (2026-08-25),
skip_on_failure=True and on_error="continue" are honored across every failure-cascade path (AgentTeam sync + async, AgentFlow, Process.sequential / asequential). Previously these flags were inert on cascade paths and dependents were force-failed the moment any upstream dependency failed. If you were working around this by removing context=[...] dependencies, you can put them back.How It Works
Quick Start
1
Simple Usage
2
With Configuration
Full YAML with retries, optional steps, and execution history:
How Graceful Degradation Now Works
A dependent task that opts in still runs even when an upstream dependency in itscontext fails.
Equivalent Flags
Two flags opt into graceful degradation — pick either one.skip_on_failure=True— legacy boolean, still works, means “keep the workflow moving”.on_error="continue"— richer three-state field ("stop"/"continue"/"retry"). Prefer this in new code.- Either flag alone is enough; setting both is redundant but harmless.
Configuration Options
Task Parameters
skip_on_failure
on_error
retry_delay
Workflow History
Conditional Branching
Best Practices
Mark optional steps with skip_on_failure
Mark optional steps with skip_on_failure
Enhancement and enrichment tasks should not block the main workflow path.
Use higher retry_delay for rate-limited APIs
Use higher retry_delay for rate-limited APIs
Set
retry_delay=2.0 or more when calling external APIs with throttling.Enable history during development
Enable history during development
Always set
history=True while building workflows — inspect get_history() after failures.Separate critical from optional in YAML
Separate critical from optional in YAML
Keep required steps strict (
skip_on_failure: false) and flag enrichers as optional explicitly.Related
Workflows
Workflow patterns and orchestration
Workflow Error Recovery
Recover from workflow failures gracefully

