robbond
956fc2e31e
Two bugs were causing the model to return {"status":"ok"} / {"status":"ready"}
instead of structured reconstruction data, resulting in POST /api/analyse 500:
1. DOUBLE-WRAPPING BUG (lib/llm/provider.js):
generateReconstruction() called buildPrompt(scenario) on input that was
already a fully-built prompt string from analyseScenario(). This wrapped the
v0.1 prompt (~5000+ chars) in another template layer, producing incomprehensible
output that the model could not parse as structured JSON.
Fix: Pass scenario through directly (it is ALREADY a built prompt).
2. MISSING JSON SPEC (prompts/reconstruct-v0.2.md):
The v0.2 prompt template said 'matching the structure exactly' but never
defined what that structure was. The model invented its own field names
(input_classification, reasoning_mode, anchors) with snake_case instead of
camelCase, which failed Zod validation -> 500 errors.
Fix: Added explicit JSON schema section with exact key names, enum values,
and nested structure matching the Zod validation layer.
Additionally:
- Refactored route to use analyseScenario from lib/analysis (centralized)
- Added lib/analysis.js with shared analysis logic
- Updated components to display promptVersion and validation errors
- Added lib/reconstruction/prompt.js v0.1/v0.2 versioning
- Added lib/reconstruction/schema.js v0.2 Zod schemas
- Added debug tool scripts, evaluation results, and comparison findings
57 lines
1.3 KiB
JSON
57 lines
1.3 KiB
JSON
{
|
|
"id": "diag-05",
|
|
"description": "Unexpected continuity — changed context but no outcome change.",
|
|
"input": "Our production line changed suppliers three months ago but still delivers the same defect rate as before.",
|
|
"responseDurationMs": 1,
|
|
"actualPrimaryType": "unexplained_change",
|
|
"actualReasoningModes": [
|
|
"identify_difference",
|
|
"establish_baseline",
|
|
"validate_measurement"
|
|
],
|
|
"technical": {
|
|
"schemaValid": true,
|
|
"classificationMatch": true,
|
|
"reasoningModeMatch": true,
|
|
"nextQuestionPresent": true,
|
|
"pass": true,
|
|
"errors": []
|
|
},
|
|
"reasoningQuality": {
|
|
"requiredConcepts": {
|
|
"pass": false,
|
|
"details": [
|
|
{
|
|
"concept": "supplier change",
|
|
"found": false
|
|
},
|
|
{
|
|
"concept": "three months ago",
|
|
"found": false
|
|
},
|
|
{
|
|
"concept": "same defect rate",
|
|
"found": false
|
|
}
|
|
]
|
|
},
|
|
"unsupportedInferencesAbsent": {
|
|
"pass": true,
|
|
"details": [
|
|
{
|
|
"concept": "new supplier is worse",
|
|
"absent": true
|
|
},
|
|
{
|
|
"concept": "old supplier was better",
|
|
"absent": true
|
|
},
|
|
{
|
|
"concept": "quality process is broken",
|
|
"absent": true
|
|
}
|
|
]
|
|
},
|
|
"pass": false
|
|
}
|
|
} |