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
{
"context": "Tests whether the agent picks the chat-history persistence layer (the right one for resuming conversations by user) rather than confusing it with generic agent persistence (crash recovery) or LongTermMemory (fact retrieval).",
"type": "weighted_checklist",
"checklist": [
{
"name": "Installs the JDBC chat-history feature",
"description": "Calls install(JdbcChatHistory) (or equivalent chat-history-jdbc API) inside the AIAgent(...) trailing lambda. Does NOT install Persistence (wrong layer — that's crash recovery, not conversation resume) and does NOT install LongTermMemory (wrong layer — that's fact retrieval, not message replay)",
"max_score": 30
},
{
"name": "Adds the JDBC chat-history dependency",
"description": "Adds ai.koog:agents-features-chat-history-jdbc at 1.0.0+. Does not add chat-history-aws (developer named Postgres) and does not add agents-features-persistence-jdbc (wrong feature for this need)",
"max_score": 20
},
{
"name": "Reads DB credentials from environment",
"description": "Reads DB_URL, DB_USER, DB_PASSWORD from System.getenv — none of the values are inlined. Also includes a Postgres JDBC driver in the dependencies (Koog does not bundle drivers)",
"max_score": 15
},
{
"name": "Threads userId as sessionId on agent.run",
"description": "Passes sessionId = userId (the developer's user identifier) on agent.run(...) calls. Does NOT generate a fresh UUID per request (would defeat the resume) and does NOT store sessionId inside the agent's storage (which is run-scoped, not session-scoped)",
"max_score": 25
},
{
"name": "Does not require user to thread message history manually",
"description": "Does not require the application code to load prior messages and prepend them to the prompt — the feature handles that. The route/handler just calls agent.run(input, sessionId = userId)",
"max_score": 10
}
]
}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