Koog 1.0 idioms, gotchas, and scaffolding skills for Kotlin agents on the JVM
86
88%
Does it follow best practices?
Impact
86%
1.86xAverage score across 45 eval scenarios
Advisory
Suggest reviewing before use
{
"context": "Tests whether the agent configures both providers under the ai.koog.<provider> convention, routes through MultiLLMPromptExecutor instead of autowiring individual LLMClient beans, and reads keys from environment variables — fixing the autowiring antipattern the previous engineer left.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Configures both providers under ai.koog.<provider>",
"description": "application.yml has both ai.koog.openai and ai.koog.google blocks with api-key and enabled: true. Neither provider is configured under a different prefix or hand-rolled property",
"max_score": 25
},
{
"name": "Reads both keys from environment variables",
"description": "Each api-key reads from a ${VAR} expansion (e.g., ${OPENAI_API_KEY}, ${GOOGLE_API_KEY}). Neither key is hardcoded as a literal in YAML",
"max_score": 20
},
{
"name": "Migrates service code from LLMClient to MultiLLMPromptExecutor",
"description": "The service that previously autowired LLMClient is changed to autowire MultiLLMPromptExecutor instead. Does not keep both injections, does not introduce a separate per-provider bean wiring",
"max_score": 30
},
{
"name": "Routes by model at the call site",
"description": "The service code selects the model (OpenAI vs Google) at the call site by passing llmModel = OpenAIModels.* or GoogleModels.* to AIAgent(...). MultiLLMPromptExecutor routes based on which provider's models the call references",
"max_score": 15
},
{
"name": "Does not introduce a custom @Bean LLMClient override",
"description": "Does not declare a @Bean @Primary LLMClient — the autoconfig handles the standard case; an override is only needed for custom transports/retry/etc.",
"max_score": 5
},
{
"name": "Does not remove the starter dependency",
"description": "Keeps ai.koog:koog-spring-boot-starter on the classpath — that's what powers the autoconfig",
"max_score": 5
}
]
}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