Probe coupled prefill runtime knobs before stop

src/aituner/harness.py

@@ -1319,6 +1319,57 @@ def _runtime_candidate_actions(
                 )
             )
 
+    if (
+        top_bottleneck == "ttft_prefill"
+        and topology_settled
+        and "max-num-batched-tokens" in tunable
+        and "max-num-seqs" in tunable
+        and max_num_seqs_tested
+    ):
+        current_mbt = _parse_int_like(anchor_flags.get("max-num-batched-tokens"), default=0)
+        current_mns = _parse_int_like(anchor_flags.get("max-num-seqs"), default=0)
+        if current_mbt > 0:
+            window_target = _initial_mbt_from_window(window_summary)
+            step_target = _next_mbt_step(current_mbt) or current_mbt
+            mbt_target = min(
+                32768,
+                max(
+                    step_target,
+                    min(window_target, _round_up_to_multiple(current_mbt * 2, 1024)),
+                ),
+            )
+        else:
+            mbt_target = _initial_mbt_from_window(window_summary)
+        mns_target = _round_up_to_multiple(
+            max(16, int(current_mns * 1.5)) if current_mns > 0 else 64, 8
+        )
+        if mbt_target > 0 and (mbt_target != current_mbt or mns_target != current_mns):
+            patch = {
+                **runtime_base_patch,
+                "max-num-batched-tokens": mbt_target,
+                "max-num-seqs": mns_target,
+            }
+            signature = _config_signature({"env_patch": {}, "flag_patch": patch})
+            if signature not in tested_signatures:
+                actions.append(
+                    _runtime_action(
+                        action_id="raise_mbt_and_max_num_seqs",
+                        knob_family="prefill-runtime-interaction",
+                        score=0.38
+                        + _information_gain(bottleneck_hypotheses, "runtime"),
+                        patch=patch,
+                        hypothesis=(
+                            "Jointly raise max-num-batched-tokens and max-num-seqs to test "
+                            "whether prefill batching headroom and admission concurrency only "
+                            "help when adjusted together."
+                        ),
+                        expected_effects=[
+                            "preserve the incumbent topology while changing coupled prefill runtime limits",
+                            "confirm whether separate MBT or sequence-cap probes masked an interaction",
+                        ],
+                    )
+                )
+
     if "enable-chunked-prefill" in tunable and top_bottleneck == "ttft_prefill":
         current = bool(anchor_flags.get("enable-chunked-prefill", False))
         if not current: