honcho/tests/unified/test_cases/dialectic_tool_calls.json

104 lines
3.2 KiB
JSON

{
"description": "Force the dialectic agent to actually invoke tools (grep/search) by asking an enumeration+aggregation question that the prefetched first turn cannot answer in one shot. Used to verify Langfuse tool-call observations nest under the step span.",
"workspace_config": {},
"steps": [
{
"step_type": "create_session",
"session_id": "tool_calls_test",
"config": {
"reasoning": {
"enabled": false
}
},
"peer_configs": {
"user": {
"observe_me": true,
"observe_others": false
},
"assistant": {
"observe_me": false,
"observe_others": true
}
}
},
{
"step_type": "add_messages",
"session_id": "tool_calls_test",
"messages": [
{
"peer_id": "user",
"content": "Monday I grabbed a $5 latte at Starbucks before my standup.",
"created_at": "2024-03-04T08:30:00"
},
{
"peer_id": "assistant",
"content": "Nice, a classic way to start the week.",
"created_at": "2024-03-04T08:31:00"
},
{
"peer_id": "user",
"content": "Tuesday I tried a $4 cold brew from Blue Bottle, really smooth.",
"created_at": "2024-03-05T09:15:00"
},
{
"peer_id": "assistant",
"content": "Blue Bottle makes a solid cold brew.",
"created_at": "2024-03-05T09:16:00"
},
{
"peer_id": "user",
"content": "Wednesday was a $6 oat-milk mocha at a little place downtown.",
"created_at": "2024-03-06T08:45:00"
},
{
"peer_id": "assistant",
"content": "Oat milk mochas are underrated.",
"created_at": "2024-03-06T08:46:00"
},
{
"peer_id": "user",
"content": "Thursday I skipped coffee and just had tea at home.",
"created_at": "2024-03-07T08:20:00"
},
{
"peer_id": "assistant",
"content": "A calm morning, sounds good.",
"created_at": "2024-03-07T08:21:00"
},
{
"peer_id": "user",
"content": "Friday I splurged on a $7 pour-over at the roastery near the office.",
"created_at": "2024-03-08T08:50:00"
},
{
"peer_id": "assistant",
"content": "Ending the week strong!",
"created_at": "2024-03-08T08:51:00"
}
]
},
{
"step_type": "wait",
"target": "queue_empty",
"timeout": 180,
"flush": true
},
{
"step_type": "query",
"description": "Global query (no session history) + empty prefetch (reasoning off) forces grep/search tool calls",
"target": "chat",
"observer_peer_id": "assistant",
"observed_peer_id": "user",
"reasoning_level": "max",
"input": "How many separate coffees did I buy this week, and exactly how much did I spend in total across all of them?",
"assertions": [
{
"assertion_type": "llm_judge",
"prompt": "Does the response state that the user bought 4 coffees totaling $22 (or correctly enumerate the $5, $4, $6, and $7 purchases)?",
"pass_if": true
}
]
}
]
}