Add kvcache-centric profiling and admission controls

src/agentic_pd_hybrid/launcher.py

@@ -33,6 +33,7 @@ def build_launch_plan(
     prefill_policy: str = "round_robin",
     decode_policy: str = "manual",
     include_router: bool = True,
+    router_request_timeout_s: float | None = None,
 ) -> LaunchPlan:
     return LaunchPlan(
         prefill_commands=tuple(
@@ -49,6 +50,7 @@ def build_launch_plan(
                 topology,
                 prefill_policy=prefill_policy,
                 decode_policy=decode_policy,
+                request_timeout_s=router_request_timeout_s,
             )
             if include_router and topology.prefill_workers and topology.decode_workers
             else None
@@ -105,6 +107,7 @@ def _build_router_command(
     *,
     prefill_policy: str,
     decode_policy: str,
+    request_timeout_s: float | None,
 ) -> tuple[str, ...]:
     command: list[str] = [
         sys.executable,
@@ -121,6 +124,8 @@ def _build_router_command(
         "--decode-policy",
         decode_policy,
     ]
+    if request_timeout_s is not None:
+        command.extend(["--request-timeout-s", str(request_timeout_s)])
     for worker in topology.prefill_workers:
         command.extend(
             ["--prefill", worker.url, str(worker.bootstrap_port or topology.router_port)]