Koog 0.4.0, an replace to the JetBrains Kotlin framework for constructing AI brokers, options native structured output meant to carry up in manufacturing. It additionally provides Apple’s iOS as a goal platform, in addition to GPT-5 mannequin and OpenTelemetry assist.
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 assist for brand spanking new platforms and fashions, JetBrains stated. Code is accessible from GitHub. Native structured output addresses a state of affairs by which a giant 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 immediately. 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 out there on Apple’s cell working system as a part of a give attention to 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 exams. However builders should use Koog 0.4.1 to construct for iOS. Moreover with Koog 0.4.0, GPT-5 assist and customized LLM parameters assist a mannequin suppose tougher on advanced parameters. Settings corresponding to reasoningEffort allow a steadiness of high quality, price, and latency for every name, in keeping with JetBrains. OpenTelemetry backing, in the meantime, helps each the W&B Weave AI growth toolkit and the Langfuse open supply LLM engineering platform.
