Skip to main content Link Menu Expand (external link) Document Search Copy Copied

News · release

LLM4S 0.6.0: subagents, agents across machines, and the Kotlin API

Agents can delegate to typed subagents and run across several machines, credentials are secrets, and the Kotlin API is on Maven Central for the first time.

What is new

  • Subagents: TypedAgent[I, O] specialists offered through AgentBuilder.withSubagents, each in its own child thread with a token budget, supervision, cancellation with its parent and nested streams (#2044). The delegation guide walks through them.
  • Agents across machines: PostgresCheckpointer shares threads between runtimes, a durable run queue and AgentWorker take and recover runs, and each run is one OpenTelemetry trace (#2129); see several machines.
  • Credentials and data protection: credentials are Secrets, a key can come from a file (apiKeyFile) or an ApiKeyProvider, and console and OpenTelemetry tracing withhold message content unless you opt in (data protection guide).
  • Providers: xAI, Perplexity’s Agent API, keyless Microsoft Entra ID for Azure OpenAI, web search for Anthropic and Gemini, one proxy and CA setting for every client, your own HTTP client or sttp 4 backend (llm4s-sttp), a key read from HashiCorp Vault (llm4s-secrets-vault), and llm4s-jlama, a small model run inside the JVM so a first answer needs no key and no server (providers guide).
  • Honest usage and options: a Completion lists the options its provider could not honour (adjustments, also on the agent’s ModelCallCompleted), and thinking tokens are counted once in usage and cost, whichever way the provider reports them.
  • Java and Kotlin: a Java agent builder, streaming, annotated tools, declarative AI services (an annotated interface llm4s implements), structured output into records and a RAG facade (llm4s-java-rag); more Spring Boot starter beans, Spring AI interop both ways (llm4s-spring-ai), and guides for Micronaut, Helidon and Quarkus; and llm4s-kotlin-api is published (Java guide).
  • New experimental modules: llm4s-ox (direct style), llm4s-reactor, llm4s-capabilities, llm4s-prompt, llm4s-schema-iron, llm4s-tapir and llm4s-repl, plus the Elasticsearch/OpenSearch and Redis vector stores and the llm4s-doctor setup checker.

Upgrading

llm4s is still stabilising before 1.0, and 0.6.0 sets no binary-compatibility baseline: any release may break (compatibility policy). 0.6.0 has more breaking changes than usual. The ones most code meets:

  • Credentials are Secret, not String (migration note).
  • Many data types are growth-safe: a private constructor and copy, with with* setters instead, which breaks .copy(...) and positional patterns. The migration guide lists each type.
  • Console tracing prints no content by default (migration note).
  • llm4s-java-api and the Spring Boot starter no longer bring the provider modules: add the one you use (migration note).
  • TokenUsage.completionTokens no longer includes thinking tokens, and every output token count does (migration note).
  • A Gemini or Vertex AI reply a content filter stopped is a ContentFilteredError, not a partial answer (migration note).

The Scalafix rule Llm4sMigrate_1_0 rewrites most of the mechanical source breaks; it is not published yet (#2330, Scalafix). Which releases get fixes, and for how long, is in the support policy.

Install

libraryDependencies ++= Seq(
  "org.llm4s" %% "llm4s-core"   % "0.6.0",
  "org.llm4s" %% "llm4s-openai" % "0.6.0" // or the provider module you use
)

Every artifact, with its tier: installation guide.

Full list of changes: CHANGELOG · GitHub release


All news · Subscribe (Atom)