Spot on. The persistence layer is a huge part of what makes the canvas work.
For failures, we handle it at multiple levels: first, standard retries and fallbacks to alternate models/providers. If that fails, the agents look for alternate approaches to accomplish the same task (e.g. falling back to web search instead of browser use).
For completeness, you can also manually re-run or edit individual blocks if they fail (though the agents may or may not consider this depending on where they are in their flow).
For failures, we handle it at multiple levels: first, standard retries and fallbacks to alternate models/providers. If that fails, the agents look for alternate approaches to accomplish the same task (e.g. falling back to web search instead of browser use).
For completeness, you can also manually re-run or edit individual blocks if they fail (though the agents may or may not consider this depending on where they are in their flow).