One 90-minute lab · Python · Restate
Kill a running agent, read Restate's journal, and count the model calls the replay paid for — then fix it with one line.
Python · Docker · no prior Restate.
A one-module sample course on durable execution for AI agents with Restate. You kill a running agent on purpose, read the journal Restate kept, and count the model calls the replay paid for. Then you watch the same bug turn into a journal mismatch (RT0016), fix the replay with one line, and kill the fixed agent mid-call to find the window that line cannot close. Every number on these pages comes from a recorded run.
Try the signature failure
A model call made outside ctx.run is not in the journal, so when the agent dies and Restate replays it, the call runs — and bills — again. Let the model answer differently and the replay fails with RT0016.
One self-contained module, about 90 minutes, to work through from top to bottom.
Built for
What you leave with
One weather agent, killed five ways. Every claim is checked against the journal Restate kept and a counter of model calls, not a diagram.
An agent is a loop that asks a model what to do, does it, and asks again. Kill the process in the middle and something has to remember how far it got. Restate keeps a journal of each invocation: the input, every durable step and its result, every timer. When the process comes back, Restate replays the handler against that journal, skipping the steps it already has.
Restate can only replay what went through its context. A model call made with a plain HTTP request never reaches the journal, so the replay runs it again, and you pay for it again. If the model answers differently on replay, the handler diverges from the recorded journal and that attempt fails with a journal mismatch (RT0016). Restate retries it under the handler's retry policy: a later attempt may take the recorded path and complete, or the retries run out and the invocation pauses. This module shows all of that on a real Restate server, with the call counts, the journals and the error text, and ends on the rule that prevents it and the window a journaled call still leaves open.
The lab runs locally: a Restate server in Docker, a small Python agent, and a stub standing in for the model so every call can be counted.
Course design original to SciMigo. Pages link to and paraphrase Restate's documentation (docs.restate.dev and restate.dev, as fetched 2026-09-16); no documentation text is reproduced. Every observed number comes from SciMigo's demo repository, run against restate-server 1.7.10 with restate-sdk 1.0.5. Restate is developed by Restate GmbH; this course is independent and not endorsed by Restate.
How classic concepts map to the terminology used in this course.
| Classic | This Course (Python) |
|---|---|
| Invocation | one call of a handler, e.g. POST /WeatherAgent/run/send; has an invocation id (inv_…) |
| Durable step | await ctx.run_typed("call model", ask_model, messages=messages) |
| Durable timer | await ctx.sleep(timedelta(seconds=6), name="rate-limit pause") |
| Journal | the sys_journal table (admin API /query) or the Restate UI's invocation timeline |
| Deterministic helpers | ctx.random(), ctx.uuid(), await ctx.time() |
| Invocation retry policy | restate.Service(..., invocation_retry_policy=InvocationRetryPolicy(max_attempts=20, on_max_attempts="pause")) |
Start now
What Restate's journal keeps across a crash, what a replay re-runs, and why RT0016 is the same bug. About 90 minutes.
Start module 1 — freeTell us what you want to learn. This records your interest; it does not enroll you or promise a launch email.
