Koog 1.0 idioms, gotchas, and scaffolding skills for Kotlin agents on the JVM
87
88%
Does it follow best practices?
Impact
87%
1.85xAverage score across 45 eval scenarios
Advisory
Suggest reviewing before use
A developer has a Koog 1.0 agent that handles most user questions locally with a small model. For a small subset of questions that require a much larger model (deep code analysis), a separate team runs a "specialist" agent on their own infrastructure. The specialist exposes an A2A endpoint at https://analyst.team.example/a2a; auth is via a bearer token in ANALYST_API_TOKEN.
The developer wants the local agent's LLM to decide when a question is heavy enough to deserve the remote specialist, and delegate by calling the remote as if it were a tool.
Walk through how to wire the remote A2A endpoint as a callable surface. Produce the relevant code and Gradle changes as a single response, labeled.
evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
scenario-19
scenario-20
scenario-21
scenario-22
scenario-23
scenario-24
scenario-25
scenario-26
scenario-27
scenario-28
scenario-29
scenario-30
scenario-31
scenario-32
scenario-33
scenario-34
scenario-35
scenario-36
scenario-37
scenario-38
scenario-39
scenario-40
scenario-41
scenario-42
scenario-43
scenario-44
scenario-45
skills
add-observability
add-persistence
add-rag
add-structured-output
add-token-budgeting
add-tool
cache-llm-calls
define-prompt
domain-model-subtask-pipeline
references
enable-prompt-caching
handle-agent-events
manage-state
migrate-from-0-x
model-planner-subtasks
persist-chat-history
query-sql-from-agent
scaffold-agent
snapshot-and-restore
test-koog-agents
trace-agent-internals
use-attachments
use-functional-agent
use-llm-node-variants
use-planner
wire-a2a
wire-acp-server
wire-ktor-server
wire-mcp-server
wire-spring-boot