Project 6 · Serving0/5 completeInference API
A pure request dispatcher inside the browser worker: validation, version checks, health/readiness, batching, and lifecycle traces.
requires artifacts from: classifier-lab
- L1Request Contractdefine the contract · ~12 minstart →
- L2Model Adapterpreserve an invariant · ~15 minlocked
- L3Request Dispatchermeasure behavior · ~18 minlocked
- L4Health + Readinessbound a failure · ~16 minlocked
- L5Batch + Lifecycle Tracemake an operational decision · ~22 minlocked
Artifacts this project producesL1 · Request Contractoutputs: inference-api:l1-request-contract:artifact
L2 · Model Adapteroutputs: inference-api:l2-model-adapter:artifact
L3 · Request Dispatcheroutputs: inference-api:l3-request-dispatcher:artifact
L4 · Health + Readinessoutputs: inference-api:l4-health-readiness:artifact
L5 · Batch + Lifecycle Traceoutputs: inference-api:l5-batch-lifecycle:artifact