fix(P0): protocol.py extra=allow — recover 180 rejected replay requests

Sub655 root cause: OpenAIBaseModel had extra='forbid', rejecting
max_completion_tokens and reasoning_effort as 'Extra inputs not permitted'.
180/881 replay requests returned HTTP 400 instead of being processed.

Fix: extra='allow'. The fold_max_completion_tokens validator already
converts max_completion_tokens→max_tokens correctly. Unknown fields
like reasoning_effort are now silently accepted instead of 400'd.

Also resolved yaml merge conflict (keep upstream 0.80 gpu-mem, no LD_PRELOAD).

computility-run.yaml

@@ -49,4 +49,3 @@ env:
       value: '1'
     - name: PYTORCH_CUDA_ALLOC_CONF
       value: max_split_size_mb:512
-

qwen3_6_scripts/protocol.py

@@ -58,7 +58,7 @@ class CustomChatCompletionMessageParam(TypedDict, total=False):
 
 class OpenAIBaseModel(BaseModel):
     # OpenAI API does not allow extra fields
-    model_config = ConfigDict(extra="forbid")
+    model_config = ConfigDict(extra="allow")
 
 
 class ErrorResponse(OpenAIBaseModel):