58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191

@dataclassclassModelSettings:"""Settings to use when calling an LLM.    This class holds optional model configuration parameters (e.g. temperature,    top_p, penalties, truncation, etc.).    Not all models/providers support all of these parameters, so please check the API documentation    for the specific model and provider you are using.    """temperature:float|None=None"""The temperature to use when calling the model."""top_p:float|None=None"""The top_p to use when calling the model."""frequency_penalty:float|None=None"""The frequency penalty to use when calling the model."""presence_penalty:float|None=None"""The presence penalty to use when calling the model."""tool_choice:ToolChoice|None=None"""The tool choice to use when calling the model."""parallel_tool_calls:bool|None=None"""Controls whether the model can make multiple parallel tool calls in a single turn.    If not provided (i.e., set to None), this behavior defers to the underlying    model provider's default. For most current providers (e.g., OpenAI), this typically    means parallel tool calls are enabled (True).    Set to True to explicitly enable parallel tool calls, or False to restrict the    model to at most one tool call per turn.    """truncation:Literal["auto","disabled"]|None=None"""The truncation strategy to use when calling the model.    See [Responses API documentation](https://platform.openai.com/docs/api-reference/responses/create#responses_create-truncation)    for more details.    """max_tokens:int|None=None"""The maximum number of output tokens to generate."""reasoning:Reasoning|None=None"""Configuration options for    [reasoning models](https://platform.openai.com/docs/guides/reasoning).    """verbosity:Literal["low","medium","high"]|None=None"""Constrains the verbosity of the model's response.    """metadata:dict[str,str]|None=None"""Metadata to include with the model response call."""store:bool|None=None"""Whether to store the generated model response for later retrieval.    For Responses API: automatically enabled when not specified.    For Chat Completions API: disabled when not specified."""prompt_cache_retention:Literal["in_memory","24h"]|None=None"""The retention policy for the prompt cache. Set to `24h` to enable extended    prompt caching, which keeps cached prefixes active for longer, up to a maximum    of 24 hours.    [Learn more](https://platform.openai.com/docs/guides/prompt-caching#prompt-cache-retention)."""include_usage:bool|None=None"""Whether to include usage chunk.    Only available for Chat Completions API."""# TODO: revisit ResponseIncludable | str if ResponseIncludable covers more cases# We've added str to support missing ones like# "web_search_call.action.sources" etc.response_include:list[ResponseIncludable|str]|None=None"""Additional output data to include in the model response.    [include parameter](https://platform.openai.com/docs/api-reference/responses/create#responses-create-include)"""top_logprobs:int|None=None"""Number of top tokens to return logprobs for. Setting this will    automatically include ``"message.output_text.logprobs"`` in the response."""extra_query:Query|None=None"""Additional query fields to provide with the request.    Defaults to None if not provided."""extra_body:Body|None=None"""Additional body fields to provide with the request.    Defaults to None if not provided."""extra_headers:Headers|None=None"""Additional headers to provide with the request.    Defaults to None if not provided."""extra_args:dict[str,Any]|None=None"""Arbitrary keyword arguments to pass to the model API call.    These will be passed directly to the underlying model provider's API.    Use with caution as not all models support all parameters."""defresolve(self,override:ModelSettings|None)->ModelSettings:"""Produce a new ModelSettings by overlaying any non-None values from the        override on top of this instance."""ifoverrideisNone:returnselfchanges={field.name:getattr(override,field.name)forfieldinfields(self)ifgetattr(override,field.name)isnotNone}# Handle extra_args merging specially - merge dictionaries instead of replacingifself.extra_argsisnotNoneoroverride.extra_argsisnotNone:merged_args={}ifself.extra_args:merged_args.update(self.extra_args)ifoverride.extra_args:merged_args.update(override.extra_args)changes["extra_args"]=merged_argsifmerged_argselseNonereturnreplace(self,**changes)defto_json_dict(self)->dict[str,Any]:dataclass_dict=dataclasses.asdict(self)json_dict:dict[str,Any]={}forfield_name,valueindataclass_dict.items():ifisinstance(value,BaseModel):json_dict[field_name]=value.model_dump(mode="json")else:json_dict[field_name]=valuereturnjson_dict