Merge nucleic/sleek-ember-seal-uady into dev

README.md

@@ -237,7 +237,10 @@ ml/purpose-classifier/venv/bin/python ml/purpose-classifier/quantize_coreml.py \
 Activation calibration writes its temporary packages under the candidate output directory
 and removes each package immediately after prediction; this avoids Core ML Tools retaining
 one full weight copy per calibration step until process exit. It prints progress while it
-runs. The candidate uses per-tensor asymmetric uint8 activations,
+runs. The successfully rewritten A8 package is cached beside the W8A8 output and reused
+only when its source hash, Core ML Tools version, activation policy, calibration seed, and
+prompt hashes match exactly. This prevents a later weight-stage failure from forcing
+another calibration. The candidate uses per-tensor asymmetric uint8 activations,
 per-channel symmetric int8 linear weights, and per-tensor asymmetric uint8 embedding
 weights. Activation quantization is limited to floating-point linear operations; applying
 Core ML Tools' global policy also selects integer embedding-index additions and produces