Koog 0.4.0, an replace to the JetBrains Kotlin framework for constructing AI brokers, options native structured output supposed to carry up in manufacturing. It additionally provides Apple’s iOS as a goal platform, in addition to GPT-5 mannequin and OpenTelemetry help.
Introduced August 28, Koog 0.4.0 is meant to make brokers observable, seamless, deployable in a person’s stack, and extra predictable, whereas including help for brand new platforms and fashions, JetBrains stated. Code is accessible from GitHub. Native structured output addresses a scenario by which a massive language mannequin (LLM) can present the precise knowledge format wanted, however then the method stops working. Koog 0.4.0 provides native structured output supported by some LLMs, with pragmatic guardrails like retries and fixing methods. When a mannequin helps structured output, the framework makes use of it straight. In any other case, Koog falls again to a tuned prompt-and-retry, with a fixing parser powered by a separate mannequin, till the payload seems to be precisely the way it ought to.
For iOS, Koog is now accessible on Apple’s cellular working system as a part of a concentrate on Kotlin Multiplatform. Builders can construct an agent as soon as and ship it to iOS, Android, and JVM again ends—all with the identical technique graphs, observability hooks, and checks. However builders should use Koog 0.4.1 to construct for iOS. Moreover with Koog 0.4.0, GPT-5 help and customized LLM parameters assist a mannequin suppose more durable on complicated parameters. Settings similar to reasoningEffort allow a stability of high quality, value, and latency for every name, based on JetBrains. OpenTelemetry backing, in the meantime, helps each the W&B Weave AI growth toolkit and the Langfuse open supply LLM engineering platform.