fix: planner e2e test config file using new CLI format (#7014)

Signed-off-by: hongkuanz <hongkuanz@nvidia.com>

tests/planner/scaling/disagg_planner_load.yaml

@@ -27,18 +27,13 @@ spec:
       extraPodSpec:
         mainContainer:
           image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
-          workingDir: /workspace/components/src/dynamo/planner
           command:
           - python3
           - -m
-          - planner_sla
+          - dynamo.planner
           args:
-            - --environment=kubernetes
-            - --backend=vllm
-            - --enable-loadbased-scaling
-            - --disable-throughput-scaling
-            - --loadbased-adjustment-interval=5
-            - --loadbased-min-observations=5
+            - --config
+            - '{"environment": "kubernetes", "backend": "vllm", "enable_load_scaling": true, "enable_throughput_scaling": false, "pre_deployment_sweeping_mode": "none", "load_adjustment_interval": 5, "load_min_observations": 5}'
     VllmDecodeWorker:
       envFromSecret: hf-token-secret
       componentType: worker

tests/planner/scaling/disagg_planner_throughput.yaml

@@ -19,17 +19,13 @@ spec:
       extraPodSpec:
         mainContainer:
           image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
-          workingDir: /workspace/components/src/dynamo/planner
           command:
           - python3
           - -m
-          - planner_sla
+          - dynamo.planner
           args:
-            - --environment=kubernetes
-            - --backend=vllm
-            - --adjustment-interval=60
-            - --profile-results-dir=/workspace/tests/planner/profiling_results/H200_TP1P_TP1D
-            - --no-correction
+            - --config
+            - '{"environment": "kubernetes", "backend": "vllm", "throughput_adjustment_interval": 60, "profile_results_dir": "/workspace/tests/planner/profiling_results/H200_TP1P_TP1D", "no_correction": true}'
     VllmDecodeWorker:
       envFromSecret: hf-token-secret
       componentType: worker