diff --git a/runs/frontier-code-trace-v0/experiment-card.md b/runs/frontier-code-trace-v0/experiment-card.md
index c2822a9..cb0047d 100644
--- a/runs/frontier-code-trace-v0/experiment-card.md
+++ b/runs/frontier-code-trace-v0/experiment-card.md
@@ -228,3 +228,8 @@ mode-specific：
 - source 无 Qwen-aligned prompt/token IDs。raw canonical prompt 使用 GLM
   token contract，不能同时保持 Qwen token content 与 trace ISL；本 campaign
   采用 synthetic Qwen tokens 保持 length/hash/prefix shape，并降级内容 claim。
+- 远端 Qwen3-30B `config.json` 的原生 position limit 是 40960
+  (`rope_theta=1e6`,无 rope_scaling)。147456 profile smoke 在显式
+  `VLLM_ALLOW_LONG_MAX_MODEL_LEN=1` 下成功；该 override 只支持
+  performance/shape fidelity，不形成生成质量或模型长上下文正确性 claim，
+  并作为 provenance 中的显式实验变量。
diff --git a/runs/frontier-code-trace-v0/run_flashattn_code_longctx.sh b/runs/frontier-code-trace-v0/run_flashattn_code_longctx.sh
index cb3e52e..3f17c53 100644
--- a/runs/frontier-code-trace-v0/run_flashattn_code_longctx.sh
+++ b/runs/frontier-code-trace-v0/run_flashattn_code_longctx.sh
@@ -11,6 +11,7 @@ esac
 
 OUTPUT_ROOT="${OUTPUT_ROOT:?OUTPUT_ROOT must be set}"
 MAX_MODEL_LEN="${MAX_MODEL_LEN:-147456}"
+ALLOW_LONG_CONTEXT_PROFILE="${ALLOW_LONG_CONTEXT_PROFILE:-false}"
 VENV_ROOT="${VENV_ROOT:-/home/admin/cpfs/wjh/venvs/vllm-0.20.0-cu129-workload-regime-v2}"
 VLLM_SOURCE="${VLLM_SOURCE:-/home/admin/cpfs/wjh/agentic-kv/third_party/vllm_v20_build}"
 MODEL="${MODEL:-/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B}"
@@ -42,6 +43,11 @@ test -x "${VENV_ROOT}/bin/python"
 test -f "${VLLM_SOURCE}/benchmarks/attention_benchmarks/runner.py"
 test -f "${MODEL}/config.json"
 test -f "${PROFILE_SCRIPT}"
+if [[ "${ALLOW_LONG_CONTEXT_PROFILE}" != "true" ]]; then
+  echo "ERROR: set ALLOW_LONG_CONTEXT_PROFILE=true after reviewing the model's 40960-token RoPE contract" >&2
+  exit 1
+fi
+export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
 
 echo "PROFILE_LAUNCH_ECHO host=$(hostname) gpu=${CUDA_VISIBLE_DEVICES} tp=${TP} max_model_len=${MAX_MODEL_LEN} specs=${BATCH_SPECS[*]}"
 date -u +"START_UTC=%Y-%m-%dT%H:%M:%SZ"
@@ -59,6 +65,8 @@ printf '%s\n' "${BATCH_SPECS[@]}" \
   > "${OUTPUT_ROOT}/provenance/batch-specs.txt"
 printf '%s\n' "${MAX_MODEL_LEN}" \
   > "${OUTPUT_ROOT}/provenance/max-model-len.txt"
+printf '%s\n' "${VLLM_ALLOW_LONG_MAX_MODEL_LEN}" \
+  > "${OUTPUT_ROOT}/provenance/vllm-allow-long-max-model-len.txt"
 
 timeout --signal=TERM --kill-after=30s 1800 \
   "${VENV_ROOT}/bin/python" "${PROFILE_SCRIPT}" \