debugCoreTempDummy.ts
Fires a hardcoded core temperature inference call for manual model verification
Purpose
This module provides a one-shot debug helper for verifying that the core temperature ONNX model loads, runs, and produces a result for a known set of hardcoded inputs. It is intended to be called from the Debug screen or a test harness and has no effect on application state.
Its responsibilities include:
- Constructing a fixed feature set from hardcoded physiological and environmental values
- Logging the ordered feature vector before inference for comparison against expected model input
- Invoking
runCoreTempInferencewith the"onnx"model variant - Returning the raw inference result for inspection
Invariants
Hardcoded Inputs Only
All inputs are compile-time constants. This function is not parameterizable and should never be used as a production inference path.
| Input | Value |
|---|---|
wbgt | 25.302024 |
cpm40 | 227.55 |
gender | 1 (male) |
bmi | 30.55411248 |
age | 44 |
daysActive14 | 7 |
Exports
debugCoreTempDummy()
async function debugCoreTempDummy(): Promise<CoreTempResult>
Runs a single core temperature inference with fixed inputs using the "onnx" model variant. Returns the raw CoreTempResult.