v0.5.0

Published 2 Oct 2025

Major Features

• Full Agent-to-Agent (A2A) Protocol Support:
  • Multiplatform Kotlin A2A SDK: Including server and client with JSON-RPC HTTP support.
  • A2A Agent Feature: seamlessly integrate A2A in your Koog agents
• Non-Graph API for Strategies: Introduced non-graph API for creating AI Agent strategies as Kotlin extension
  functions with most of Koog's features supported (#​560)
• Agent Persistence and Checkpointing:
  • Roll back Tool Side-Effects: Add RollbackToolRegistry in the Persistence feature in order to roll back
    tool calls with side effects when checkpointing.
  • State-Machine Persistence / Message History Switch: Support switching between full state-machine persistence
    and message history persistence (#​856)
• Tool API Improvements:
  • Make ToolDescriptor auto-generated for class-based tools (#​791)
  • Get rid of ToolArgs and ToolResult limitations for Tool<*, *> class (#​791)
• subgraphWithTask Simplification: Get rid of required finishTool and support tools as functions in
  subgraphWithTask, deduce final step automatically by data class (#​791)
• AIAgentService Introduced: Make AIAgent state-manageable and single-run explicitly, introduce AIAgentService
  to manage multiple uniform running agents.
• New components:
  • Add LLM as a Judge component (#​866)
  • Tool Calling loop with Structured Output strategy (#​829)

Improvements

• Make Koog-based tools exportable via MCP server (KG-388)
• Add additionalProperties to LLM clients in order to support custom LLM configurations (#​836)
• Allow adjusting context window sizes for Ollama dynamically (#​883)
• Refactor streaming api to support tool calls (#​747)
• Provide an ability to collect and send a list of nodes and edges out of AIAgentStrategy to the client when running
  an agent (KG-160)
• Add excludedProperties to inline createJsonStructure too, update KDocs (#​826)
• Refactor binary attachment handling and introduce Base64 serializer (#​838)
• In JsonStructuredData.defaultJson instance rename class discriminator
  from #type to kind to align with common practices (#​772, KG-384)
• Make standard json generator default when creating JsonStructuredData
  (it was basic before) (#​772, KG-384)
• Add default audio configuration and modalities (#​817)
• Add GptAudio model in OpenAI client (#​818)
• Allow re-running of finished agents that have Persistence feature installed (#​828, KG-193)
• Allow ideomatic node transformations with .transform { ...} lambda function (#​684)
• Add ability to filter messages for every agent feature (KG-376)
• Add support for trace-level attributes in Langfuse integration (#​860, KG-427)
• Keep all system messages when compressing message history of the agent(#​857)
• Add support for Anthropic's Sonnet 4.5 model in Anthropic/Bedrock providers (#​885)
• Refactored LLM client auto-configuration in Spring Boot integration, to modular provider-specific classes with
  improved validation and security (#​886)
• Add LLM Streaming agent events (KG-148)

Bug Fixes

• Fix broken Anthropic models support via Amazon Bedrock (#​789)
• Make AIAgentStorageKey in agent storage actually unique by removing data modifier (#​825)
• Fix rerun for agents with Persistence (#​828, KG-193)
• Update mcp version to 0.7.2 with fix for Android target (#​835)
• Do not include an empty system message in Anthropic request (#​887, KG-317)
• Use maxTokens from params in Google models (#​734)
• Fix finishReason nullability (#​771)

Deprecations

• Rename agent interceptors in EventHandler and related feature events (KG-376)
• Deprecate concurrent unsafe AIAgent.asTool in favor of AIAgentService.createAgentTool (#​873)
• Rename Persistency to Persistence everywhere (#​896)
• Add agentId argument to all Persistence methods instead of persistencyId class field (#​904)

Examples

• Add a basic code-agent example (#​808, KG-227)
• Add iOS and Web targets for demo-compose-app (#​779, #​780)

v0.4.2

Compare Source

Published 15 Sep 2025

Improvements

• Make agents‑mcp support KMP targets to run across more platforms (#​756).
• Add LLM client retry support to Spring Boot auto‑configuration to improve resilience on transient failures (#​748).
• Add Claude Opus 4.1 model support to Anthropic client to unlock latest reasoning capabilities (#​730).
• Add Gemini 2.5 Flash Lite model support to Google client to enable lower‑latency, cost‑efficient generations (#​769).
• Add Java‑compatible non‑streaming Prompt Executor so Java apps can call Koog without
  coroutines (KG-312, #​715).
• Support excluding properties in JSON Schema generation to fine‑tune structured outputs (#​638).
• Update AWS SDK to latest compatible version for Bedrock integrations.
• Introduce Postgres persistence provider to store agent state and artifacts (#​705).
• Update Kotlin to 2.2.10 in dependency configuration for improved performance and language features (#​764).
• Refactor executeStreaming to remove suspend for simpler interop and better call sites (#​720).
• Add Java‑compatible prompt executor (non‑streaming) wiring and polish across
  modules (KG-312, #​715).
• Decouple FileSystemEntry from FileSystemProvider to simplify testing and enable alternative providers (#​664).

Bug Fixes

• Add missing tool calling support for Bedrock Nova models so agents can invoke functions when using
  Nova (KG-239).
• Add Android target support and migrate Android app to Kotlin Multiplatform to widen KMP
  coverage (KG-315, #​728, #​767).
• Add Spring Boot Java example to jump‑start integration (#​739).
• Add Java Spring auto‑config fixes: correct property binding and make Koog starter work out of the box (#​698).
• Fix split package issues in OpenAI LLM clients to avoid classpath/load
  errors (KG-305, #​694).
• Ensure Anthropic tool schemas include the required "type" field in serialized request bodies to prevent validation
  errors during tool calling (#​582).
• Fix AbstractOpenAILLMClient to correctly handle plain‑text responses in capabilities flow; add integration tests to
  prevent regressions (#​564).
• Fix GraalVM native image build failure so projects can compile native binaries again (#​774).
• Fix usages in OpenAI‑based data model to align with recent API changes (#​688).
• Fix SpringBootStarters initialization and improve RetryingClient (#​894)

CI and Build

• Nightly build configuration and dependency submission workflow added (#​695, #​737).