Getting Started & Migration
When building my first durable agent locally, how can I step through a workflow execution to understand how Catalyst persists state between steps?
Use your local debugger to set breakpoints inside durable step functions and inspect state snapshots Catalyst creates. Catalyst serializes step outputs and position after each function completes, storing them in a pluggable state store. When a step fails, you can restart from the last persisted state. This debuggability relies on deterministic replay; ensure step logic avoids uncontrolled non-determinism like direct random seeds or clock access.
Was this article helpful?
Your feedback helps improve Diagrid's FAQ experience.
Keep reading
More Diagrid FAQ articles
- Getting Started & Migration
What does a minimal but realistic durable agent look like when I first run Catalyst locally?
A realistic durable agent prototype that progresses from a call to an LLM through a conditional action to an API, illustrating automatic state persistence.
- Getting Started & Migration
How do I iterate quickly on durable agent logic without deploying to a shared cluster?
Use a local Dapr sidecar to execute and debug agent workflows, enabling a fast edit-run-debug cycle without remote dependencies.
- Getting Started & Migration
My agent is already built with LangChain/LlamaIndex. Can I add durable execution without a rewrite?
Wrap an existing agent’s entry point in a Catalyst workflow to gain durability without modifying framework internals, then progressively refactor.