| """Test requests, sized to land in each bucket. Shared by scripts/make_golden.py and the tests.""" |
|
|
| SUPPORT_TASKS = { |
| "intent": ["order_status", "refund_request", "cancel_subscription", "update_payment", "other"], |
| "urgency": ["low", "normal", "high"], |
| } |
|
|
| CASES = [ |
| { |
| "id": "short-refund", |
| "bucket": 64, |
| "text": "My subscription renewed on April 15 for 5,400 yen after the service was already down. " |
| "Can I get that charge refunded?", |
| "tasks": SUPPORT_TASKS, |
| }, |
| { |
| "id": "laptop-review-aspects", |
| "bucket": 64, |
| "text": "Battery dies before lunch, but the keyboard and the screen are the best I have used on a laptop.", |
| "tasks": { |
| "sentiment": ["positive", "negative", "mixed", "neutral"], |
| "aspects": {"labels": ["battery", "keyboard", "screen", "camera", "price", "support"], |
| "multi_label": True, "cls_threshold": 0.4}, |
| }, |
| }, |
| { |
| "id": "compliance-email-3-heads", |
| "bucket": 128, |
| "text": "From: compliance@group.example\nSubject: Protocol update, action required today\n\n" |
| "Please confirm the new retention rule is applied before Friday's audit.", |
| "tasks": { |
| "intent": ["fyi", "request", "approval", "complaint", "newsletter", "security_alert"], |
| "urgency": ["low", "normal", "high", "critical"], |
| "route": ["support", "billing", "legal", "security", "finance", "archive"], |
| }, |
| }, |
| { |
| "id": "descriptions-and-prompt", |
| "bucket": 128, |
| "text": "My subscription renewed on April 15 for 5,400 yen after the service was already down. " |
| "Can I get that charge refunded?", |
| "tasks": { |
| "intent": {"labels": { |
| "order_status": "The customer asks where an order is", |
| "refund_request": "The customer wants money back", |
| "cancel_subscription": "The customer wants to stop a recurring plan", |
| "update_payment": "The customer wants to change a card or billing method", |
| "other": "None of the above", |
| }}, |
| "urgency": {"labels": ["low", "normal", "high"], "prompt": "How urgently should support respond?"}, |
| }, |
| }, |
| { |
| "id": "hotel-complaint-4-heads", |
| "bucket": 256, |
| "text": "Hello, I'm writing from room 1408. The air conditioning stopped working yesterday afternoon " |
| "and the room is now above 30 degrees, so neither of us could sleep last night. We called the " |
| "front desk twice and were told a technician would come, but nobody showed up. We have a " |
| "conference presentation tomorrow morning and cannot spend another night like this. Please " |
| "either fix it within the next two hours or move us to another room tonight. If neither is " |
| "possible we will check out early and expect the remaining nights to be refunded. We would " |
| "also like the incidentals hold on our card to be released, since we were told at check-in " |
| "that it would only last one day. Thank you.", |
| "tasks": { |
| "intent": ["maintenance", "room_change", "checkout", "billing", "complaint", "amenity_request"], |
| "priority": ["low", "normal", "high", "urgent"], |
| "needs_human": ["yes", "no"], |
| "topics": {"labels": ["hvac", "billing", "housekeeping", "noise", "safety"], |
| "multi_label": True, "cls_threshold": 0.4}, |
| }, |
| }, |
| { |
| "id": "incident-report-long", |
| "bucket": 512, |
| "text": "Incident summary for the payments platform, prepared for the weekly operations review. " |
| "On Tuesday at 09:12 UTC the card authorization service began returning timeouts for roughly " |
| "one in five requests. The on-call engineer was paged four minutes later by the latency alert " |
| "and started investigating the database tier, which showed normal load. At 09:31 the team noticed " |
| "that a configuration change deployed the previous evening had lowered the connection pool size " |
| "for the authorization service from two hundred to twenty connections. Under the morning traffic " |
| "peak the pool was exhausted, requests queued, and the upstream gateway gave up after its " |
| "three second deadline. The change had been reviewed, but the reviewer assumed the value was " |
| "per worker rather than per service, and the staging environment does not receive enough " |
| "traffic to reveal the problem. The configuration was rolled back at 09:44 and error rates " |
| "returned to normal within two minutes. In total about eleven thousand authorizations failed; " |
| "most customers retried successfully, but around four hundred orders were abandoned. No card " |
| "data was exposed and there is no indication of any security issue. Follow-up actions: add a " |
| "load test that replays production traffic volumes against staging before configuration " |
| "changes to the authorization service are approved; make pool sizes explicit about their " |
| "scope in the configuration schema; add an alert on connection pool saturation so the " |
| "on-call engineer is pointed at the right component immediately; and review whether the " |
| "gateway deadline should be longer for authorization calls. Finance has asked for an estimate " |
| "of lost revenue from abandoned orders by the end of the week, and customer support has " |
| "prepared a short statement in case merchants ask about the failed transactions. The service " |
| "owner will present these actions at the architecture forum next Thursday and track them to " |
| "completion in the reliability backlog.", |
| "tasks": { |
| "doc_type": ["incident_report", "feature_request", "meeting_notes", "security_advisory", "marketing"], |
| "severity": ["sev1", "sev2", "sev3", "sev4"], |
| "teams": {"labels": ["payments", "security", "finance", "support", "marketing", "legal"], |
| "multi_label": True, "cls_threshold": 0.4}, |
| }, |
| }, |
| ] |
|
|
