{ "description": "Golden fixtures for extraction-service evals. Each entry defines the minimum expected extraction classes for a given input. Used by the promptfoo eval suite and can also be consumed by custom assertion scripts.", "version": "1.0.0", "tasks": { "transcript-extraction": { "expectedClasses": ["action_item", "decision", "question", "deadline", "person", "topic"], "cases": [ { "id": "tc-001", "input": "John said we need to ship the feature by Friday. Sarah agreed to handle the testing.", "mustContainClasses": ["action_item", "deadline", "person"], "mustContainText": ["friday", "sarah", "john"], "minExtractions": 3 }, { "id": "tc-002", "input": "The team decided to postpone the launch to Q3. Alice will notify all stakeholders by Monday.", "mustContainClasses": ["decision", "action_item", "person", "deadline"], "mustContainText": ["q3", "alice"], "minExtractions": 3 }, { "id": "tc-003", "input": "Bob asked: should we use Postgres or Cosmos DB for the new service? No decision was made.", "mustContainClasses": ["question", "person"], "mustContainText": ["bob"], "minExtractions": 2 }, { "id": "tc-004", "input": "Maria: I finished the design mockups. Tom: Great, I'll review them by EOD. Maria: Can you also check the mobile screens?", "mustContainClasses": ["action_item", "person"], "mustContainText": ["maria", "tom"], "minExtractions": 3 } ] }, "triage": { "expectedClasses": ["topic", "entity", "action", "emotion", "date_reference", "brain_signal"], "cases": [ { "id": "tr-001", "input": "Remind me to call the dentist tomorrow about my appointment. I'm stressed about the cost.", "mustContainClasses": ["action", "date_reference", "emotion"], "mustContainBrainSignal": { "brain": "health", "minConfidence": 0.5 }, "minExtractions": 3 }, { "id": "tr-002", "input": "Need to finish the Q1 report for my manager by end of week. The presentation is on Thursday.", "mustContainClasses": ["action", "date_reference"], "mustContainBrainSignal": { "brain": "work", "minConfidence": 0.5 }, "minExtractions": 2 }, { "id": "tr-003", "input": "I need to pay the credit card bill before the 15th or I'll get charged interest.", "mustContainClasses": ["action", "date_reference"], "mustContainBrainSignal": { "brain": "money", "minConfidence": 0.5 }, "minExtractions": 2 }, { "id": "tr-004", "input": "Feeling really overwhelmed today. Too many things on my plate and I can't focus.", "mustContainClasses": ["emotion"], "mustContainEmotionValence": "negative", "minExtractions": 1 }, { "id": "tr-005", "input": "Doctor said I need to exercise more. Also need to check my 401k contributions before year end.", "mustContainClasses": ["action"], "mustContainBrainSignals": [ { "brain": "health", "minConfidence": 0.4 }, { "brain": "money", "minConfidence": 0.4 } ], "minExtractions": 2 } ] }, "memory-insight": { "expectedClasses": ["pattern", "recurring_theme", "relationship", "milestone"], "cases": [ { "id": "mi-001", "input": "Item 1: Skipped gym again. Item 2: Feeling tired at work. Item 3: Had coffee at 4pm to stay awake. Item 4: Skipped gym for the third time this week.", "mustContainClasses": ["pattern"], "mustContainPatternFrequency": "recurring", "minExtractions": 1 }, { "id": "mi-002", "input": "Item 1: Stayed up until 2am coding. Item 2: Missed standup the next morning. Item 3: Felt foggy all day. Item 4: Late night again, can't stop.", "mustContainClasses": ["pattern", "relationship"], "minExtractions": 2 }, { "id": "mi-003", "input": "Item 1: Started learning Spanish 3 months ago. Item 2: Had first full conversation in Spanish today. Item 3: Completed Duolingo 90-day streak.", "mustContainClasses": ["milestone"], "minExtractions": 2 }, { "id": "mi-004", "input": "Entry 1: Anxious before the presentation. Entry 2: Nervous about the client call. Entry 3: Worried about the demo tomorrow. Entry 4: Stressed about the board meeting.", "mustContainClasses": ["recurring_theme"], "minExtractions": 1 } ] }, "reflection-enrichment": { "expectedClasses": ["emotional_state", "accomplishment", "concern", "goal_progress"], "cases": [ { "id": "re-001", "input": "Good day overall. Finally finished the proposal I've been putting off. Still worried about the budget review next week.", "mustContainClasses": ["accomplishment", "concern", "emotional_state"], "minExtractions": 3 }, { "id": "re-002", "input": "Had a fantastic week. Shipped the new feature, got great feedback from users, and the team celebrated together.", "mustContainClasses": ["emotional_state", "accomplishment"], "mustContainEmotionValence": "positive", "minExtractions": 2 }, { "id": "re-003", "input": "I've been trying to read more this year. This month I finished my third book — ahead of my goal of one per month.", "mustContainClasses": ["goal_progress", "accomplishment"], "minExtractions": 2 }, { "id": "re-004", "input": "Proud of finishing the marathon training plan. But I'm really worried I won't be able to run the actual race — my knee has been acting up.", "mustContainClasses": ["accomplishment", "concern"], "minExtractions": 2 } ] }, "bug-report-extraction": { "expectedClasses": [ "steps_to_reproduce", "expected_behavior", "actual_behavior", "affected_component", "severity" ], "cases": [ { "id": "br-001", "input": "When I click the save button on the settings page, nothing happens. It should save my preferences. This is a critical issue affecting all users.", "mustContainClasses": [ "steps_to_reproduce", "expected_behavior", "actual_behavior", "affected_component", "severity" ], "mustContainSeverityLevel": "critical", "minExtractions": 4 }, { "id": "br-002", "input": "Steps: 1) Open login page, 2) Enter valid credentials, 3) Click login. Expected: redirect to dashboard. Actual: spinner shows forever. Affects the login page on mobile.", "mustContainClasses": [ "steps_to_reproduce", "expected_behavior", "actual_behavior", "affected_component" ], "minExtractions": 3 } ] } } }