"jcB.%SSKJr SSKJr SSKJrJrJr SSKJ r SSK J r \(aSSK J r O\ b \ RO\r \S rS \S '\\-rS \S '\S r\"SS55r\\\-\-S-r\SrS \S'"SS\ SS9rSSjrg)) annotations) dataclass) TYPE_CHECKINGLiteral TypeAlias) TypedDict) legacy_httpx)TimeoutN)minimallowmediumhighxhighrThinkingEffort ThinkingLevel)nonerequiredautoc$\rSrSr%SrS\S'Srg) ToolOrOutput#aWRestricts function tools while keeping output tools and direct text/image output available. Use this when you want to control which function tools the model can use in an agent run while still allowing the agent to complete with structured output, text, or images. See the [Tool Choice guide](../tools-advanced.md#tool-choice) for examples. list[str]function_toolsN__name__ __module__ __qualname____firstlineno____doc____annotations____static_attributes__rQ/home/mande/repo/quber/.venv/lib/python3.13/site-packages/pydantic_ai/settings.pyrr#s=r$r)rdefaultflexpriority ServiceTierc\rSrSr%SrS\S'S\S'S\S'S\S'S \S 'S \S 'S \S'S\S'S\S'S\S'S\S'S\S'S\S'S\S'S\S'S\S'Srg) ModelSettingsZaSettings to configure an LLM. Includes only settings which apply to multiple models / model providers, though not all of these settings are supported by all models. Each field's `Supported by:` list names the model classes that put the setting on the wire. A bare name covers every interface that model serves, so `OpenAI` means both [`OpenAIChatModel`][pydantic_ai.models.openai.OpenAIChatModel] and [`OpenAIResponsesModel`][pydantic_ai.models.openai.OpenAIResponsesModel]; a name qualified with an interface, like `OpenAI Chat Completions`, covers only that one, because the Responses API does not accept the setting at all. These lists are parsed and checked against the wire by `tests/models/test_model_settings_support.py`, so keep the `* Name` bullet shape and put any nuance in parentheses after the name. Being listed means Pydantic AI sends the setting, not that the service honors it: the OpenAI-compatible model classes forward whatever the OpenAI schema accepts, and an individual provider behind one of them may ignore a field its own API doesn't define, or reject it. Where we know of such a case it is noted on the entry, but the provider's own API reference is the authority. All types must be serializable using Pydantic. int max_tokensfloat temperaturetop_ptop_kzint | float | Timeouttimeoutboolparallel_tool_calls ToolChoice tool_choiceseedpresence_penaltyfrequency_penaltyzdict[str, int] logit_biasrstop_sequenceszdict[str, str] extra_headersrthinkingr) service_tierobject extra_bodyrNrrr$r%r+r+Zs2O0< L8 J #"2((T I*** 0"!*%N8r$r+F)totalc<U(a U(aX-$U=(d U$)zMerge two sets of model settings, preferring the overrides. A common use case is: merge_model_settings(, ) r)base overridess r%merge_model_settingsrFs   y r$)rDModelSettings | NonerErGreturnrG) __future__r dataclassesrtypingrrrtyping_extensionsr_httpr httpxr r/rr"r4rToolChoiceScalarrliststrr6r)r+rFrr$r%rRs"!44''3&>l""EG#$OP PD.0 y0 56  > >  >S )L 84 ? 2 !FG YG!HsIUsl !r$