# What's New in 0.3

Verify transport failure, scoped cancellation, and explicit worker recovery.

After reading this guide, you will know:

* How a run continues after its client disconnects.
* How to reconnect without executing a turn twice.
* How to recover after confirmed worker loss.
* How host cancellation differs from HTTP abort and provider timeout.

## Keep the Recorded Outcome

```ruby
record = RubyLLM::AgUI::Run.new(chat: chat, input: input, scope: scope,
                              store: store).stream(to: response_stream)
```

If the response transport disconnects, the worker continues the same turn and
persists its real outcome. A failed terminal write cannot change an already
recorded result. This is not a background job: worker termination still stops
execution. See [Streaming Runs](/next/streaming-runs/).

## Reconnect with the Same Input

Resend the original input and run id after completion. The store returns its
recorded outcome without running the chat or tool again. A second stream while
the original is still running is refused. See
[Reconnects and Run Identity](/next/reconnects/).

## Recover Lost Workers Explicitly

After confirming a worker has stopped, load its authorized record and call
`store.recover(record)`. The recorded failure uses code `worker_lost` and keeps
the identity reserved. Stale record writes are refused by revision checks.
Storage acknowledgement failures propagate as `PersistenceError` rather than
inventing a terminal outcome. See
[Worker Recovery](/next/worker-recovery/).

## Cancel the Authorized Run

The client example now shows separate controls for host cancellation and HTTP
abort. Its cancel endpoint checks the fixture actor and exact run identity;
disconnecting the browser leaves the producer running. RubyLLM's HTTP timeout
is recorded as `transport_timeout`, without raw provider details. See
[Cancellation and Timeouts](/next/cancellation/).

Version 0.3 adds independent-process SQLite tests, including a producer killed
after a synthetic tool effect.
These tests do not establish live provider or other-database behavior.

Before updating, read [Upgrading](/next/upgrading/) for worker
draining, the custom-store contract, and the JSON 2.x dependency requirement.

What’s New in 0.3

Verify transport failure, scoped cancellation, and explicit worker recovery.

After reading this guide, you will know:

How a run continues after its client disconnects.
How to reconnect without executing a turn twice.
How to recover after confirmed worker loss.
How host cancellation differs from HTTP abort and provider timeout.

Keep the Recorded Outcome

record = RubyLLM::AgUI::Run.new(chat: chat, input: input, scope: scope,
                              store: store).stream(to: response_stream)

If the response transport disconnects, the worker continues the same turn and persists its real outcome. A failed terminal write cannot change an already recorded result. This is not a background job: worker termination still stops execution. See Streaming Runs.

Reconnect with the Same Input

Resend the original input and run id after completion. The store returns its recorded outcome without running the chat or tool again. A second stream while the original is still running is refused. See Reconnects and Run Identity.

Recover Lost Workers Explicitly

After confirming a worker has stopped, load its authorized record and call store.recover(record). The recorded failure uses code worker_lost and keeps the identity reserved. Stale record writes are refused by revision checks. Storage acknowledgement failures propagate as PersistenceError rather than inventing a terminal outcome. See Worker Recovery.

Cancel the Authorized Run

The client example now shows separate controls for host cancellation and HTTP abort. Its cancel endpoint checks the fixture actor and exact run identity; disconnecting the browser leaves the producer running. RubyLLM’s HTTP timeout is recorded as transport_timeout, without raw provider details. See Cancellation and Timeouts.

Version 0.3 adds independent-process SQLite tests, including a producer killed after a synthetic tool effect. These tests do not establish live provider or other-database behavior.

Before updating, read Upgrading for worker draining, the custom-store contract, and the JSON 2.x dependency requirement.