fix(agentic): normalize Kimi MI355X max context

Author: cquil11

benchmarks/single_node/agentic/kimik2.5_fp4_mi355x.sh

@@ -23,9 +23,12 @@ ADVANCE_MIN=${ADVANCE_MIN:-0.0}
 ADVANCE_MAX=${ADVANCE_MAX:-0.7}
 EP_SIZE=${EP_SIZE:-1}
 # Kimi-K2.5 advertises a 262144-token context window in vLLM 0.21.0.
-# Keep the benchmark loader's trace filter aligned with the server so
-# prompt+max_tokens overflows are removed before replay.
-MAX_MODEL_LEN=${MAX_MODEL_LEN:-262144}
+# Matrix defaults may export MAX_MODEL_LEN=0 to mean "server default"; for this
+# script we need the concrete value so AgentX filters prompt+max_tokens against
+# the same limit vLLM enforces.
+if [[ -z "${MAX_MODEL_LEN:-}" || "$MAX_MODEL_LEN" == "0" ]]; then
+    MAX_MODEL_LEN=262144
+fi
 
 if [[ -n "${SLURM_JOB_ID:-}" ]]; then
     echo "JOB $SLURM_JOB_ID running on ${SLURMD_NODENAME:-unknown}"