Stateless Reducer Agent
Design the agent as a pure function (state, event) → newState; entire execution history is held in an external event log; enables pause / resume / replay / time-travel without bespoke checkpointing.
Problem
In-memory agent state cannot be paused, resumed across processes, or time-travelled. Each capability requires bespoke checkpointing that misses edge cases. Differs from durable-workflow-snapshot (which is a snapshot mechanism) by being a programming-model constraint — the agent is *designed* as a reducer, not made into one after the fact.
Solution
The agent's core is a pure function: takes (current state, next event) → (new state, side-effect descriptors). Side effects are descriptors, not executions — the runtime dispatches them. All events are appended to a durable log. Pause = stop dispatching. Resume = restart dispatching from current log position. Replay = re-run reducer against earlier log slice. Time-travel = re-run against any log slice. Pair with durable-workflow-snapshot, event-driven-agent, deterministic-control-flow-not-prompt, own-the team's-prompts.
When to use
- Long-running agents that need pause/resume.
- Debugging by replay is valuable.
- Multiple runtimes / environments need to dispatch the same agent.
Open the full interactive page →
Diagram, neighbourhood map, code examples, related patterns and full provenance.