agent-platform release v4.48.2

Fixed

• model-serving: gemma-4-31b serves 8k context on the 48 GB card — vLLM needs 9.5 GiB of KV cache for 32k next to 31.7 GiB of weights and has 7.3, and named 8640 tokens as the ceiling; 32k returns with an fp8 KV cache once that is proven on the L40S (#591).