feat(cli): per-role --mem-fraction-static + use in E4-pressured

E4-v1 / v2 / pressured-v1 all failed to fire admission rejections in
this workload because the default 0.6 mem-fraction-static gives
288K-token kv_pool per decoder, more than enough to absorb the
50-session trace even at concurrency=32.

This commit adds:
  --decode-mem-fraction-static  (overrides per-decode SGLang arg)
  --prefill-mem-fraction-static (symmetric for completeness)

Plumbed via topology.{decode,prefill}_extra_server_args. The
pressured sweep now uses --decode-mem-fraction-static 0.4 which
shrinks decoder kv_pool to ~192K tokens — should force enough
admission rejections to actually exercise the D→P snapshot path.

src/agentic_pd_hybrid/cli.py

@@ -566,6 +566,23 @@ def main() -> None:
             "See docs/D_TO_P_SYNC_DESIGN_ZH.md."
         ),
     )
+    benchmark.add_argument(
+        "--decode-mem-fraction-static",
+        type=float,
+        default=None,
+        help=(
+            "Override SGLang's --mem-fraction-static on decode workers. "
+            "Smaller value → smaller KV pool → admit_direct_append rejects "
+            "more often → reseed path fires more often. Pressure tool for "
+            "E4-style D→P sync experiments."
+        ),
+    )
+    benchmark.add_argument(
+        "--prefill-mem-fraction-static",
+        type=float,
+        default=None,
+        help="Override --mem-fraction-static on prefill workers.",
+    )
     benchmark.add_argument(
         "--sample-profile",
         choices=["default", "small-append"],
@@ -897,11 +914,25 @@ def _topology_from_args(args: argparse.Namespace):
         trust_remote_code=not args.no_trust_remote_code,
         ib_device=args.ib_device,
         enable_d_to_p_sync=getattr(args, "enable_d_to_p_sync", False),
-        prefill_extra_server_args=("--disable-overlap-schedule",),
-        decode_extra_server_args=("--disable-overlap-schedule",),
-        direct_extra_server_args=("--enable-streaming-session",),
+        prefill_extra_server_args=_build_extra_server_args(args, "prefill"),
+        decode_extra_server_args=_build_extra_server_args(args, "decode"),
+        direct_extra_server_args=_build_extra_server_args(args, "direct"),
     )
 
 
+def _build_extra_server_args(args, role: str) -> tuple[str, ...]:
+    base: tuple[str, ...]
+    if role == "direct":
+        base = ("--enable-streaming-session",)
+    else:
+        base = ("--disable-overlap-schedule",)
+    mem_frac = getattr(args, "decode_mem_fraction_static", None) if role == "decode" else None
+    if mem_frac is None and role == "prefill":
+        mem_frac = getattr(args, "prefill_mem_fraction_static", None)
+    if mem_frac is not None and mem_frac > 0:
+        base = base + ("--mem-fraction-static", f"{mem_frac:.3f}")
+    return base
+
+
 if __name__ == "__main__":
     main()