feat(ark): add name & parallel_tool_calls

Author: hexiaochun

volcenginesdkarkruntime/resources/batch_chat/completions.py

@@ -5,6 +5,7 @@
 from datetime import timedelta, datetime
 from random import random
 from typing import Dict, List, Union, Iterable, Optional, Callable
+from typing_extensions import Literal
 
 import httpx
 
@@ -130,6 +131,8 @@ def create(
         top_p: Optional[float] | None = None,
         repetition_penalty: Optional[float] | None = None,
         n: Optional[int] | None = None,
+        parallel_tool_calls: Optional[bool] | None = None,
+        service_tier: Optional[Literal["auto", "default"]] | None = None,
         tool_choice: ChatCompletionToolChoiceOptionParam | None = None,
         response_format: completion_create_params.ResponseFormat | None = None,
         user: str | None = None,
@@ -172,6 +175,8 @@ def create(
                         "user": user,
                         "repetition_penalty": repetition_penalty,
                         "n": n,
+                        "parallel_tool_calls": parallel_tool_calls,
+                        "service_tier": service_tier,
                         "tool_choice": tool_choice,
                         "response_format": response_format,
                     },
@@ -272,6 +277,8 @@ async def create(
         user: str | None = None,
         repetition_penalty: Optional[float] | None = None,
         n: Optional[int] | None = None,
+        parallel_tool_calls: Optional[bool] | None = None,
+        service_tier: Optional[Literal["auto", "default"]] | None = None,
         tool_choice: ChatCompletionToolChoiceOptionParam | None = None,
         response_format: completion_create_params.ResponseFormat | None = None,
         extra_headers: Headers | None = None,
@@ -314,6 +321,8 @@ async def create(
                         "user": user,
                         "repetition_penalty": repetition_penalty,
                         "n": n,
+                        "parallel_tool_calls": parallel_tool_calls,
+                        "service_tier": service_tier,
                         "tool_choice": tool_choice,
                         "response_format": response_format,
                     },

volcenginesdkarkruntime/resources/bot/completions.py

@@ -63,6 +63,8 @@ def create(
         top_p: Optional[float] | None = None,
         repetition_penalty: Optional[float] | None = None,
         n: Optional[int] | None = None,
+        parallel_tool_calls: Optional[bool] | None = None,
+        service_tier: Optional[Literal["auto", "default"]] | None = None,
         tool_choice: ChatCompletionToolChoiceOptionParam | None = None,
         response_format: completion_create_params.ResponseFormat | None = None,
         user: str | None = None,
@@ -93,6 +95,8 @@ def create(
                 "user": user,
                 "repetition_penalty": repetition_penalty,
                 "n": n,
+                "parallel_tool_calls": parallel_tool_calls,
+                "service_tier": service_tier,
                 "tool_choice": tool_choice,
                 "response_format": response_format,
                 "metadata": metadata,
@@ -139,6 +143,8 @@ async def create(
         top_p: Optional[float] | None = None,
         repetition_penalty: Optional[float] | None = None,
         n: Optional[int] | None = None,
+        parallel_tool_calls: Optional[bool] | None = None,
+        service_tier: Optional[Literal["auto", "default"]] | None = None,
         tool_choice: ChatCompletionToolChoiceOptionParam | None = None,
         response_format: completion_create_params.ResponseFormat | None = None,
         user: str | None = None,
@@ -169,6 +175,8 @@ async def create(
                 "user": user,
                 "repetition_penalty": repetition_penalty,
                 "n": n,
+                "parallel_tool_calls": parallel_tool_calls,
+                "service_tier": service_tier,
                 "tool_choice": tool_choice,
                 "response_format": response_format,
                 "metadata": metadata,

volcenginesdkarkruntime/resources/chat/completions.py

@@ -158,6 +158,8 @@ def create(
         top_p: Optional[float] | None = None,
         repetition_penalty: Optional[float] | None = None,
         n: Optional[int] | None = None,
+        parallel_tool_calls: Optional[bool] | None = None,
+        service_tier: Optional[Literal["auto", "default"]] | None = None,
         tool_choice: ChatCompletionToolChoiceOptionParam | None = None,
         response_format: completion_create_params.ResponseFormat | None = None,
         user: str | None = None,
@@ -195,6 +197,8 @@ def create(
                 "user": user,
                 "repetition_penalty": repetition_penalty,
                 "n": n,
+                "parallel_tool_calls": parallel_tool_calls,
+                "service_tier": service_tier,
                 "tool_choice": tool_choice,
                 "response_format": response_format,
             },
@@ -296,6 +300,8 @@ async def create(
         user: str | None = None,
         repetition_penalty: Optional[float] | None = None,
         n: Optional[int] | None = None,
+        parallel_tool_calls: Optional[bool] | None = None,
+        service_tier: Optional[Literal["auto", "default"]] | None = None,
         tool_choice: ChatCompletionToolChoiceOptionParam | None = None,
         response_format: completion_create_params.ResponseFormat | None = None,
         extra_headers: Headers | None = None,
@@ -332,6 +338,8 @@ async def create(
                 "user": user,
                 "repetition_penalty": repetition_penalty,
                 "n": n,
+                "parallel_tool_calls": parallel_tool_calls,
+                "service_tier": service_tier,
                 "tool_choice": tool_choice,
                 "response_format": response_format,
             },

volcenginesdkarkruntime/types/chat/chat_completion.py

@@ -59,6 +59,24 @@ class ChatCompletion(BaseModel):
     model: str
     """The model used for the chat completion."""
 
+    service_tier: Optional[Literal["auto", "default"]]
+    """Specifies the latency tier to use for processing the request.
+
+    This parameter is relevant for customers subscribed to the scale tier service:
+
+    - If set to 'auto', and the endpoint is Scale tier enabled, the system will
+      utilize scale tier credits until they are exhausted.
+    - If set to 'auto', and the endpoint is not Scale tier enabled, the request will
+      be processed using the default service tier with a lower uptime SLA and no
+      latency guarentee.
+    - If set to 'default', the request will be processed using the default service
+      tier with a lower uptime SLA and no latency guarentee.
+    - When not set, the default behavior is 'auto'.
+
+    When this parameter is set, the response body will include the `service_tier`
+    utilized.
+    """
+
     object: Literal["chat.completion"]
     """The object type, which is always `chat.completion`."""
 

volcenginesdkarkruntime/types/chat/chat_completion_assistant_message_param.py

@@ -31,6 +31,13 @@ class ChatCompletionAssistantMessageParam(TypedDict, total=False):
     Required unless `tool_calls` or `function_call` is specified.
     """
 
+    name: Optional[str]
+    """An optional name for the participant.
+
+    Provides the model information to differentiate between participants of the same
+    role.
+    """
+
     function_call: FunctionCall
     """Deprecated and replaced by `tool_calls`.
 

volcenginesdkarkruntime/types/chat/chat_completion_chunk.py

@@ -123,6 +123,24 @@ class ChatCompletionChunk(BaseModel):
     model: str
     """The model to generate the completion."""
 
+    service_tier: Optional[Literal["auto", "default"]]
+    """Specifies the latency tier to use for processing the request.
+
+    This parameter is relevant for customers subscribed to the scale tier service:
+
+    - If set to 'auto', and the endpoint is Scale tier enabled, the system will
+      utilize scale tier credits until they are exhausted.
+    - If set to 'auto', and the endpoint is not Scale tier enabled, the request will
+      be processed using the default service tier with a lower uptime SLA and no
+      latency guarentee.
+    - If set to 'default', the request will be processed using the default service
+      tier with a lower uptime SLA and no latency guarentee.
+    - When not set, the default behavior is 'auto'.
+
+    When this parameter is set, the response body will include the `service_tier`
+    utilized.
+    """
+
     object: Literal["chat.completion.chunk"]
     """The object type, which is always `chat.completion.chunk`."""
 

volcenginesdkarkruntime/types/chat/chat_completion_system_message_param.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from typing import Optional
+
 from typing_extensions import Literal, Required, TypedDict
 
 __all__ = ["ChatCompletionSystemMessageParam"]
@@ -11,3 +13,10 @@ class ChatCompletionSystemMessageParam(TypedDict, total=False):
 
     role: Required[Literal["system"]]
     """The role of the messages author, in this case `system`."""
+
+    name: Optional[str]
+    """An optional name for the participant.
+
+    Provides the model information to differentiate between participants of the same
+    role.
+    """

volcenginesdkarkruntime/types/chat/chat_completion_tool_message_param.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from typing import Optional
+
 from typing_extensions import Literal, Required, TypedDict
 
 __all__ = ["ChatCompletionToolMessageParam"]
@@ -12,5 +14,12 @@ class ChatCompletionToolMessageParam(TypedDict, total=False):
     role: Required[Literal["tool"]]
     """The role of the messages author, in this case `tool`."""
 
+    name: Optional[str]
+    """An optional name for the participant.
+
+    Provides the model information to differentiate between participants of the same
+    role.
+    """
+
     tool_call_id: Required[str]
     """Tool call that this message is responding to."""

volcenginesdkarkruntime/types/chat/chat_completion_user_message_param.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from typing import Union, Iterable
+from typing import Union, Iterable, Optional
 from typing_extensions import Literal, Required, TypedDict
 
 from .chat_completion_content_part_param import ChatCompletionContentPartParam
@@ -14,3 +14,10 @@ class ChatCompletionUserMessageParam(TypedDict, total=False):
 
     role: Required[Literal["user"]]
     """The role of the messages author, in this case `user`."""
+
+    name: Optional[str]
+    """An optional name for the participant.
+
+    Provides the model information to differentiate between participants of the same
+    role.
+    """