[Cohere] Bound remaining request priorities to the MessagePack int64 range (#56146)

Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>

vllm/entrypoints/cohere/protocol.py

@@ -170,7 +170,7 @@ class CohereChatV2Request(BaseModel):
     thinking: Thinking | None = None
 
     # Scheduling
-    priority: int | None = None
+    priority: int | None = Field(default=None, ge=-(2**63), le=2**63 - 1)
 
     # vLLM-specific extensions (not in Cohere spec). These mirror what the
     # Anthropic and OpenAI surfaces already expose so V2 callers can reach

vllm/entrypoints/generate/generative_scoring/serving.py

@@ -93,6 +93,8 @@ class GenerativeScoringRequest(OpenAIBaseModel):
     )
     priority: int = Field(
         default=0,
+        ge=-(2**63),
+        le=2**63 - 1,
         description=(
             "The priority of the request (lower means earlier handling; default: 0)."
         ),

vllm/entrypoints/pooling/embed/protocol.py

@@ -236,7 +236,7 @@ class CohereEmbedRequest(BaseModel):
     embedding_types: list[CohereEmbeddingType] | None = None
     truncate: CohereTruncate = "END"
     max_tokens: int | None = None
-    priority: int = 0
+    priority: int = Field(default=0, ge=-(2**63), le=2**63 - 1)
 
     @model_validator(mode="after")
     def validate_input_fields(self):