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
22 lines
552 B
Markdown
22 lines
552 B
Markdown
# Diagnostic Case: diag-07
|
|
|
|
Single reported claim — needs validation, not acceptance as fact.
|
|
|
|
## Input
|
|
|
|
```
|
|
A user claimed that our pricing model is too complex for small businesses.
|
|
```
|
|
|
|
## Result
|
|
|
|
- **Technical**: ✅ PASS (1/4 sub-checks pass)
|
|
- **Reasoning Quality**: ❌ FAIL (0/2 sub-checks pass)
|
|
- **Actual Primary Type**: reported_claim
|
|
- **Actual Reasoning Modes**: identify_difference, validate_claim
|
|
- **Response Duration**: 1ms
|
|
|
|
### Reasoning Quality Failures
|
|
|
|
missing required concept(s): pricing complexity, small business, user claim
|