enginex-bi100-compat: 改为拦截 vllm 二进制（对齐 zhengzhongwei/vLLM-Iluvatar_bi-100-opt 模式），平台命令无需改动

test_engine.py

@@ -25,7 +25,7 @@ import tempfile
 
 HERE = os.path.dirname(os.path.abspath(__file__))
 PREFLIGHT = os.path.join(HERE, "preflight.py")
-ENTRYPOINT = os.path.join(HERE, "entrypoint.sh")
+WRAPPER = os.path.join(HERE, "vllm_wrapper.sh")
 DETECT = os.path.join(HERE, "detect_tokenizer.py")
 PASS, FAIL = [], []
 
@@ -163,11 +163,13 @@ def main():
 
         # ---- 9：entrypoint 语法 + detect ----
         print("[8] entrypoint.sh / detect_tokenizer.py")
-        p = subprocess.run(["bash", "-n", "entrypoint.sh"], capture_output=True, text=True, cwd=HERE)
-        check("entrypoint.sh bash 语法正确", p.returncode == 0, p.stderr[:200])
-        shutil.copy2(ENTRYPOINT, os.path.join(tmp, "ep.sh"))
-        p1 = subprocess.run(["bash", "-n", "ep.sh"], capture_output=True, text=True, cwd=tmp)
-        check("entrypoint.sh 复制后语法仍正确", p1.returncode == 0, p1.stderr[:200])
+        p1 = subprocess.run(["bash", "-n", "vllm_wrapper.sh"], capture_output=True, text=True, cwd=HERE)
+        check("vllm_wrapper.sh bash 语法正确", p1.returncode == 0, p1.stderr[:200])
+        # wrapper 必须拦截 serve 且不外改其它子命令
+        wr = io.open(os.path.join(HERE, "vllm_wrapper.sh"), encoding="utf-8").read()
+        check("wrapper 拦截 serve <model_dir>", 'serve' in wr and 'MODEL_DIR="$2"' in wr)
+        check("wrapper 里 preflight 失败不阻断（有 try/兜底）", 'preflight 非 0 退出' in wr)
+        check("wrapper 最终 exec 的是 vllm_real", 'exec "$REAL" serve' in wr)
         p2 = subprocess.run([sys.executable, DETECT, d], capture_output=True, text=True)
         check("detect_tokenizer 可执行且报 fast", "fast" in p2.stdout, p2.stdout[:100] + p2.stderr[:200])