What's New

Entries before 0.13.0 describe the earlier legacy APIs. For the typed executable DSL (0.13.0 and later), its supported capabilities and recovery limits, see Agent Workflow.

0.14.0 (2026-10-08)

Fluent DSL consolidation with no scheduling or persistence-format change.

Workflows.Sequence.build() completes a parent ending in an always-failing/cancelling child. Returning paths still need explicit terminals; unreachable successors remain invalid.
Located diagnostics explain missing/duplicate decision arms, ambiguous or inaccessible typed values, invalid bounds and reused builder stages.
Six deterministic typed lessons and public Javadocs guide the authoring path. No provider calls are required.
Store format remains 9; incompatible deployments and older stores are refused without migration. Unresolved effects may repeat and terminal failed/cancelled runs stay terminal.
Loops, waits/timers, Workflow Journal projection and other deferred capabilities remain subsequent work.

Release notes · Tutorial

0.13.0 (2026-10-08)

Available on Maven Central. First executable-DSL milestone: typed Steps and derived bindings, nested reusable workflows, exhaustive enum/native Verdict routing, static parallel groups, bounded runtime fan-out and local JDBC recovery.

Not implemented: loops and durable waits/timers.
Deferred: Workflow Journal projection, first-class non-routing evaluation, visualization and AI authoring.
Examples are deterministic fixtures, not live provider demonstrations.
Store format 9 refuses older stores; there is no migration.
Uncommitted external effects may repeat after a crash.
Terminal runs stay terminal: failed or cancelled runs cannot be restarted from saved progress.

Release notes · Tutorial

0.10.0 (2026-06-15)

Spring AI 2.0.0 GA (clears CVE-2026-41712; spring-ai-client-chat 2.0.0)

0.9.0 (2026-06-06)

Jackson 2.21.2 alignment, journal 1.4.0 + judge 0.12.0 pins, release 0.9.0
Migrate judge integration to io.github.markpollack namespace
Add journal entry for trace path wiring session

0.8.0

Trace file capture through the workflow journal. AgentClientStep now propagates trace file paths from the underlying agent model into the workflow’s StepTransition and journal events. This closes the gap between “the agent ran” and “here’s exactly what the agent did” — every tool call, token count, and thinking block is preserved in a JSONL trace file, and the path to that file is recorded in the workflow journal.

AgentClientStep trace wiring

When the backing AgentClient implementation returns a trace path via executeForResult(), AgentClientStep writes it to AgentContext.TRACE_PATH and the executor propagates it through to StepTransition.tracePath():

// Trace-aware client bridges agent-client to workflow-flows
AgentClient traceClient = new AgentClient() {
    @Override
    public String execute(String prompt, AgentContext ctx) {
        return executeForResult(prompt, ctx).text();
    }

    @Override
    public ExecutionResult executeForResult(String prompt, AgentContext ctx) {
        AgentClientResponse response = coreClient.run(prompt);
        String tracePath = (String) response.getMetadata().get("tracePath");
        return new ExecutionResult(response.getResult(), tracePath);
    }
};

AgentClientStep step = AgentClientStep.of(traceClient, "Fix the bug: {input}");

In a multi-step workflow, each AI step gets its own trace file. Deterministic steps pass through with no trace. Analysis scripts iterate over journal events to find all trace files for a run:

Workflow: remediate
  step: trivy-scan       → tracePath: null (deterministic)
  step: claude-fix       → tracePath: /traces/fix-20260528-143000.jsonl
  step: mvn-test         → tracePath: null (deterministic)
  step: claude-verify    → tracePath: /traces/verify-20260528-143500.jsonl

What changed

AgentClient.executeForResult() — new default method returning ExecutionResult(text, tracePath). Backward compatible: lambdas still work, trace path is null.
AgentClientStep — calls executeForResult(), writes TRACE_PATH to context via updateContext()
StepTransition and WorkflowStepEvent — carry optional tracePath field
JdbcTraceRecorder — new trace_path column in step_transitions table
AgentContext.TRACE_PATH — new well-known context key
AgentContext.Builder.without() — remove a key from context (used internally to clear per-step trace paths)
ClaudeStep javadoc — now recommends AgentClientStep for experiments needing trace capture

See Trace Capture for the full guide.

0.7.0

Managed Agents as a step runtime. The new ManagedAgentStep delegates workflow steps to Anthropic’s Managed Agents API. The workflow graph stays in charge — but specific steps can run in Anthropic’s cloud sandbox with full tool access (bash, file I/O, web search). This proves the core thesis: workflow is portable, execution substrate is pluggable. The same workflow definition can run steps locally, via Temporal, or in Anthropic’s hosted infrastructure — swap a single step, zero changes to the graph.

ManagedAgentStep

Reference a pre-created agent and environment:

ManagedAgentStep step = ManagedAgentStep.of(agentId, environmentId)
    .name("remediation-agent")
    .timeout(Duration.ofMinutes(10));

String result = step.execute(ctx, "Fix the failing test in AuthService.java");

Or provision a new agent inline with the default toolset:

ManagedAgentStep step = ManagedAgentStep.create(
    "claude-sonnet-4-6",
    "You are a code remediation agent. Fix failing tests.",
    environmentId);

Use it in a workflow like any other step:

var workflow = WorkflowGraph.builder()
    .step("analyze", analyzeStep)
    .step("remediate", ManagedAgentStep.of(agentId, envId).name("fix"))
    .step("validate", validateStep)
    .build();

Design choices:

Uses the official com.anthropic:anthropic-java SDK directly — no wrapper layer
Follows the A2AStep immutable pattern: factory methods, copier methods for name() / timeout(), SessionRunner functional interface for testability
One session per execute() call — agents are reused, sessions are ephemeral
Stream-first SSE pattern: opens the event stream before sending the user message, collects agentMessage text blocks, breaks on sessionStatusIdle or sessionStatusTerminated

Dependency (optional — only needed if you use ManagedAgentStep):

<dependency>
    <groupId>com.anthropic</groupId>
    <artifactId>anthropic-java</artifactId>
    <version>2.34.0</version>
</dependency>

Step runtime landscape

With 0.7.0, Agent Workflow supports five step runtimes:

Step	Runtime	Use case
`Steps.of(fn)`	Local JVM	Deterministic logic, API calls
`ChatClientStep`	Spring AI	Single LLM call, structured output
`ClaudeStep`	Claude CLI	Quick scripts (no trace capture)
`AgentClientStep`	agent-client	Full agent loop with trace capture
`A2AStep`	A2A protocol	Remote agent delegation
`ManagedAgentStep`	Anthropic cloud	Hosted agent with sandbox

0.6.0

Initial public release on Maven Central. See Getting Started and the Tutorial.

Projects

AgentWorks

Supporting Projects

Migration

Explorations

Older / Inactive Projects

0.14.0 (2026-10-08)

0.13.0 (2026-10-08)

0.10.0 (2026-06-15)

0.9.0 (2026-06-06)

0.8.0

AgentClientStep trace wiring

What changed

0.7.0

ManagedAgentStep

Step runtime landscape

0.6.0

​0.14.0 (2026-10-08)

​0.13.0 (2026-10-08)

​0.10.0 (2026-06-15)

​0.9.0 (2026-06-06)

​0.8.0

​AgentClientStep trace wiring

​What changed

​0.7.0

​ManagedAgentStep

​Step runtime landscape

​0.6.0

0.14.0 (2026-10-08)

0.13.0 (2026-10-08)

0.10.0 (2026-06-15)

0.9.0 (2026-06-06)

0.8.0

AgentClientStep trace wiring

What changed

0.7.0

ManagedAgentStep

Step runtime landscape

0.6.0