19855efacc
Some checks failed
Tests / Go Tests (push) Has been cancelled
Tests / Python Tests (push) Has been cancelled
Tests / Integration Tests (push) Has been cancelled
Tests / Go Lint (push) Has been cancelled
Tests / Python Lint (push) Has been cancelled
Tests / Security Scan (push) Has been cancelled
Tests / All Checks Passed (push) Has been cancelled
Security Scanning / Secret Scanning (push) Has been cancelled
Security Scanning / Dependency Vulnerability Scan (push) Has been cancelled
Security Scanning / Go Security Scan (push) Has been cancelled
Security Scanning / Python Security Scan (push) Has been cancelled
Security Scanning / Node.js Security Scan (push) Has been cancelled
Security Scanning / Docker Image Security (push) Has been cancelled
Security Scanning / Security Summary (push) Has been cancelled
CI/CD Pipeline / Go Tests (push) Has been cancelled
CI/CD Pipeline / Python Tests (push) Has been cancelled
CI/CD Pipeline / Website Tests (push) Has been cancelled
CI/CD Pipeline / Linting (push) Has been cancelled
CI/CD Pipeline / Security Scan (push) Has been cancelled
CI/CD Pipeline / Docker Build & Push (push) Has been cancelled
CI/CD Pipeline / Integration Tests (push) Has been cancelled
CI/CD Pipeline / Deploy to Staging (push) Has been cancelled
CI/CD Pipeline / Deploy to Production (push) Has been cancelled
CI/CD Pipeline / CI Summary (push) Has been cancelled
ci/woodpecker/manual/build-ci-image Pipeline was successful
ci/woodpecker/manual/main Pipeline failed
All services: admin-v2, studio-v2, website, ai-compliance-sdk, consent-service, klausur-service, voice-service, and infrastructure. Large PDFs and compiled binaries excluded via .gitignore.
162 lines
4.3 KiB
YAML
162 lines
4.3 KiB
YAML
# Golden Test Suite - Multi-Turn Workflow Tests
|
|
# Tests for conversation context and follow-up handling
|
|
|
|
workflow_tests:
|
|
- id: WF-001
|
|
name: "Worksheet Creation Workflow"
|
|
steps:
|
|
- input: "Erstelle Arbeitsblatt zu Bruchrechnung"
|
|
expected_intent: "worksheet_generate"
|
|
expected_response_contains: "Arbeitsblatt"
|
|
|
|
- input: "Mit 5 Aufgaben"
|
|
expected_intent: "worksheet_modify"
|
|
context_required: true
|
|
expected_slots:
|
|
task_count: 5
|
|
|
|
- input: "Zwei Schwierigkeitsstufen bitte"
|
|
expected_intent: "worksheet_differentiate"
|
|
context_required: true
|
|
|
|
- input: "Fertig, speichern"
|
|
expected_intent: "confirmation"
|
|
expected_response_contains: "gespeichert"
|
|
|
|
- id: WF-002
|
|
name: "Student Observation to Letter"
|
|
steps:
|
|
- input: "Notiz zu Max: heute dreimal gestört"
|
|
expected_intent: "student_observation"
|
|
expected_response_contains: "notiert"
|
|
|
|
- input: "Mach daraus einen Elternbrief"
|
|
expected_intent: "parent_letter"
|
|
context_required: true
|
|
expected_slots:
|
|
source: "previous_observation"
|
|
|
|
- id: WF-003
|
|
name: "Quiz with Refinement"
|
|
steps:
|
|
- input: "Vokabeltest erstellen"
|
|
expected_intent: "quiz_generate"
|
|
|
|
- input: "Lektion 5"
|
|
expected_intent: "context_addition"
|
|
context_required: true
|
|
|
|
- input: "Mit Loesungsbogen"
|
|
expected_intent: "quiz_modify"
|
|
context_required: true
|
|
expected_slots:
|
|
with_solutions: true
|
|
|
|
- id: WF-004
|
|
name: "Reminder Chain"
|
|
steps:
|
|
- input: "Erinner mich morgen an Elterngespraech"
|
|
expected_intent: "reminder_schedule"
|
|
|
|
- input: "Und uebermorgen an die Nachbereitung"
|
|
expected_intent: "reminder_schedule"
|
|
context_required: true
|
|
|
|
- id: WF-005
|
|
name: "Canvas Editing Session"
|
|
steps:
|
|
- input: "Oeffne das Arbeitsblatt von gestern"
|
|
expected_intent: "document_open"
|
|
|
|
- input: "Ueberschrift groesser"
|
|
expected_intent: "canvas_edit"
|
|
context_required: true
|
|
|
|
- input: "Bild nach links"
|
|
expected_intent: "canvas_edit"
|
|
context_required: true
|
|
|
|
- input: "Drucklayout A4"
|
|
expected_intent: "canvas_layout"
|
|
context_required: true
|
|
|
|
- input: "Als PDF exportieren"
|
|
expected_intent: "export"
|
|
|
|
- id: WF-006
|
|
name: "Correction Assistance"
|
|
steps:
|
|
- input: "Zeig Operatoren fuer Textanalyse"
|
|
expected_intent: "operator_checklist"
|
|
is_actionable: false
|
|
|
|
- input: "Was sagt der EH dazu?"
|
|
expected_intent: "eh_passage"
|
|
context_required: true
|
|
is_actionable: false
|
|
|
|
- input: "Formuliere kurzes Feedback"
|
|
expected_intent: "feedback_suggest"
|
|
|
|
- id: WF-007
|
|
name: "Error Recovery"
|
|
steps:
|
|
- input: "Arbeitsblatt mit Vokablen"
|
|
expected_intent: "worksheet_generate"
|
|
|
|
- input: "Nein, mit Grammatik"
|
|
expected_intent: "correction"
|
|
context_required: true
|
|
expected_slots:
|
|
new_topic: "Grammatik"
|
|
|
|
- input: "Genau, das meinte ich"
|
|
expected_intent: "confirmation"
|
|
|
|
- id: WF-008
|
|
name: "Multi-Class Communication"
|
|
steps:
|
|
- input: "Nachricht an 7a"
|
|
expected_intent: "class_message"
|
|
expected_slots:
|
|
class_name: "7a"
|
|
|
|
- input: "Auch an 7b"
|
|
expected_intent: "class_message"
|
|
context_required: true
|
|
expected_slots:
|
|
class_name: "7b"
|
|
|
|
- input: "Hausaufgaben bis Freitag abgeben"
|
|
expected_intent: "context_addition"
|
|
context_required: true
|
|
|
|
- id: WF-009
|
|
name: "Weekly Summary"
|
|
steps:
|
|
- input: "Was habe ich diese Woche notiert?"
|
|
expected_intent: "task_summary"
|
|
is_actionable: false
|
|
|
|
- input: "Zeig nur die zu Max"
|
|
expected_intent: "filter"
|
|
context_required: true
|
|
expected_slots:
|
|
filter_student: "Max"
|
|
|
|
- id: WF-010
|
|
name: "Interruption Handling"
|
|
steps:
|
|
- input: "Erstelle Arbeitsblatt zu"
|
|
expected_intent: "incomplete"
|
|
|
|
- input: "Moment, erst Notiz zu Lisa"
|
|
expected_intent: "interrupt"
|
|
|
|
- input: "Lisa war heute super"
|
|
expected_intent: "student_observation"
|
|
|
|
- input: "Jetzt weiter mit dem Arbeitsblatt"
|
|
expected_intent: "resume"
|
|
context_required: true
|