feat(arkruntime): add prefix cache mode

Author: luminghao-bytedance

volcenginesdkarkruntime/resources/context/context.py

@@ -32,7 +32,7 @@ def create(
             model: str,
             messages: Iterable[ChatCompletionMessageParam],
             ttl: Optional[TTLTypes] | None = None,
-            mode: Literal["session"] = "session",
+            mode: Literal["session", "common_prefix"] = "session",
             truncation_strategy: Optional[TruncationStrategy] | None = None,
             extra_headers: Headers | None = None,
             extra_query: Query | None = None,
@@ -68,7 +68,7 @@ async def create(
             self,
             *,
             model: str,
-            mode: Literal["session"] = "session",
+            mode: Literal["session", "common_prefix"] = "session",
             messages: Iterable[ChatCompletionMessageParam],
             ttl: Optional[TTLTypes] | None = None,
             truncation_strategy: Optional[TruncationStrategy] | None = None,
@@ -82,6 +82,7 @@ async def create(
             "/context/create",
             body={
                 "model": model,
+                "mode": mode,
                 "messages": messages,
                 "ttl": ttl,
                 "truncation_strategy": truncation_strategy,