89 lines
2.9 KiB
JSON
89 lines
2.9 KiB
JSON
{
|
|
"description": "Test that workspace-level chat can synthesize information across multiple peers in a single response. Three peers have distinct attributes; workspace chat should be able to compare or list them.",
|
|
"workspace_config": {},
|
|
"steps": [
|
|
{
|
|
"step_type": "create_session",
|
|
"session_id": "ws_cross_session",
|
|
"peer_configs": {
|
|
"dan": {
|
|
"observe_me": true,
|
|
"observe_others": false
|
|
},
|
|
"emma": {
|
|
"observe_me": true,
|
|
"observe_others": false
|
|
},
|
|
"frank": {
|
|
"observe_me": true,
|
|
"observe_others": false
|
|
},
|
|
"agent": {
|
|
"observe_me": false,
|
|
"observe_others": false
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"step_type": "add_messages",
|
|
"session_id": "ws_cross_session",
|
|
"messages": [
|
|
{
|
|
"peer_id": "dan",
|
|
"content": "I'm a software engineer specializing in Rust and systems programming. I work at a startup building distributed databases."
|
|
},
|
|
{
|
|
"peer_id": "agent",
|
|
"content": "Interesting! What kind of databases?"
|
|
},
|
|
{
|
|
"peer_id": "dan",
|
|
"content": "We're building a distributed time-series database optimized for IoT sensor data."
|
|
},
|
|
{
|
|
"peer_id": "emma",
|
|
"content": "I'm a marine biologist studying coral reef ecosystems in the Great Barrier Reef. I've been doing field research there for 3 years."
|
|
},
|
|
{
|
|
"peer_id": "agent",
|
|
"content": "That must be fascinating work. What's your focus?"
|
|
},
|
|
{
|
|
"peer_id": "emma",
|
|
"content": "I'm specifically studying the impact of ocean temperature changes on coral bleaching patterns."
|
|
},
|
|
{
|
|
"peer_id": "frank",
|
|
"content": "I'm a pastry chef at a Michelin-starred restaurant in Lyon, France. My specialty is chocolate souffles."
|
|
},
|
|
{
|
|
"peer_id": "agent",
|
|
"content": "That's impressive! How did you get into pastry?"
|
|
},
|
|
{
|
|
"peer_id": "frank",
|
|
"content": "I trained at Le Cordon Bleu in Paris and then apprenticed under Chef Pierre Herme for two years."
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"step_type": "wait",
|
|
"target": "queue_empty",
|
|
"flush": true
|
|
},
|
|
{
|
|
"step_type": "query",
|
|
"target": "workspace_chat",
|
|
"input": "What professions do the people in this workspace have? List each person and what they do.",
|
|
"reasoning_level": "low",
|
|
"assertions": [
|
|
{
|
|
"assertion_type": "llm_judge",
|
|
"prompt": "Does the response mention at least 2 of the 3 peers (Dan, Emma, Frank) along with their professions? Dan is a software engineer, Emma is a marine biologist, and Frank is a pastry chef. The response should identify at least 2 of these 3 profession/person pairs correctly.",
|
|
"pass_if": true
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|