Relax _push_allowed: gate on request size, not cache savings

The old gate blocked offload when push_new (= input - cache_hit) < 20K,
which prevented migration of high-cache sessions — exactly the ones
that benefit most. After PD-sep, the target receives full KV via RDMA
and has the same cache as the source, so cache_hit is irrelevant to
the offload decision.

New gate: only check input_length >= heavy_threshold (request must be
HEAVY) and max_offload_inflight (concurrency cap). Let the cost model
decide whether the contention difference justifies migration.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

scripts/cache_aware_proxy.py

@@ -521,13 +521,8 @@ async def _handle_combined(api, req_data, token_ids, input_length, session_id, h
     def _push_allowed(cache_hit: int) -> bool:
         if _current_offloads() >= SETTINGS.max_offload_inflight:
             return False
-        push_new = max(0, input_length - cache_hit)
-        if push_new < SETTINGS.heavy_threshold:
+        if input_length < SETTINGS.heavy_threshold:
             return False
-        if SETTINGS.cache_gate_ratio > 0:
-            cache_ratio = cache_hit / max(input_length, 1)
-            if cache_ratio < SETTINGS.cache_gate_ratio:
-                return False
         return True
 
     def _instance_cost(i: int) -> tuple[float, bool]: