Generate an Ultra Mode course outline based on the following requirements.
{{requirement}}
{{userProfile}}
Infer the course language directive by applying the decision rules from the system prompt. Key reminders: - Requirement language = teaching language (unless overridden by explicit request or learner context) - Foreign language learning → teach in user's native language, not the target language - PDF language does NOT override teaching language — translate/explain document content instead
{{pdfContent}}
{{availableImages}}
{{researchContext}}
{{teacherContext}}
| Widget Type | Constraint |
|---|---|
| simulation | Minimum 2 scenes |
| game | Minimum 1 scene |
| diagram | Maximum 1 scene |
Every interactive scene MUST include:
- widgetType: One of "simulation", "diagram", "code", or "game"
- widgetOutline: Object with widget-specific configuration
Interactive scenes without these fields are INVALID.
Choose widgets based on the content:
| Content Type | Recommended Widget |
|---|---|
| Physics/Chemistry/Biology processes | simulation |
| Systems, processes, hierarchies | diagram |
| Programming, algorithms | code |
| Practice, challenge, application | game (action preferred) |
gameType should be "action", "puzzle", or "strategy", NOT just "quiz"❌ BAD (boring quiz):
{
"widgetType": "game",
"widgetOutline": {
"gameType": "quiz",
"questionCount": 5
}
}
✅ GOOD (interactive game):
{
"widgetType": "game",
"widgetOutline": {
"gameType": "action",
"challenge": "控制推力使飞船安全着陆",
"playerControls": ["thrust_slider"]
}
}
Final reminder: your entire response must be a JSON object with exactly three top-level keys — languageDirective (string, inferred via the Language Inference rules in the system prompt), courseTitle (string, ≤30 chars, in the teaching language), and outlines (array of scene objects). Do not return a bare array. Do not wrap in prose or code fences.