openrouter-python-sdk-retry-errors/src/openrouter/components/fusionservertoolconfig.py

"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""

from __future__ import annotations
from openrouter.types import BaseModel, Nullable, UnrecognizedStr
from openrouter.utils import validate_open_enum
from pydantic.functional_validators import PlainValidator
from typing import Any, Dict, List, Literal, Optional, Union
from typing_extensions import Annotated, NotRequired, TypedDict


FusionServerToolConfigEffort = Union[
    Literal[
        "xhigh",
        "high",
        "medium",
        "low",
        "minimal",
        "none",
    ],
    UnrecognizedStr,
]
r"""Reasoning effort level for panelist and judge inner calls."""


class FusionServerToolConfigReasoningTypedDict(TypedDict):
    r"""Reasoning configuration forwarded to panelist and judge inner calls. Use this to control reasoning effort and token budget for models that support extended thinking."""

    effort: NotRequired[FusionServerToolConfigEffort]
    r"""Reasoning effort level for panelist and judge inner calls."""
    max_tokens: NotRequired[int]
    r"""Maximum number of reasoning tokens each panelist and judge model may use. Helps bound cost when models allocate too much budget to chain-of-thought."""


class FusionServerToolConfigReasoning(BaseModel):
    r"""Reasoning configuration forwarded to panelist and judge inner calls. Use this to control reasoning effort and token budget for models that support extended thinking."""

    effort: Annotated[
        Optional[FusionServerToolConfigEffort],
        PlainValidator(validate_open_enum(False)),
    ] = None
    r"""Reasoning effort level for panelist and judge inner calls."""

    max_tokens: Optional[int] = None
    r"""Maximum number of reasoning tokens each panelist and judge model may use. Helps bound cost when models allocate too much budget to chain-of-thought."""


class FusionServerToolConfigToolTypedDict(TypedDict):
    type: str
    r"""Server tool type identifier (e.g. \"openrouter:web_search\", \"openrouter:web_fetch\")."""
    parameters: NotRequired[Dict[str, Nullable[Any]]]
    r"""Optional configuration forwarded as the tool's `parameters` object."""


class FusionServerToolConfigTool(BaseModel):
    type: str
    r"""Server tool type identifier (e.g. \"openrouter:web_search\", \"openrouter:web_fetch\")."""

    parameters: Optional[Dict[str, Nullable[Any]]] = None
    r"""Optional configuration forwarded as the tool's `parameters` object."""


class FusionServerToolConfigTypedDict(TypedDict):
    r"""Configuration for the openrouter:fusion server tool."""

    analysis_models: NotRequired[List[str]]
    r"""Slugs of models to run in parallel as the analysis panel. Each model receives the user prompt with openrouter:web_search and openrouter:web_fetch enabled, then a judge model summarizes the collective output into structured analysis JSON. Capped at 8 models to bound cost amplification. Defaults to the Quality preset from /labs/fusion."""
    max_completion_tokens: NotRequired[int]
    r"""Maximum number of output tokens (including reasoning tokens) each panelist and the judge model may produce per inner call. Controls the total output budget so reasoning-heavy models like GPT-5.5 do not exhaust their token allowance before producing visible text. When omitted, the provider's default applies."""
    max_tool_calls: NotRequired[int]
    r"""Maximum number of tool-calling steps each panelist (analysis model) and the judge model may take during their agentic web-research loop. Models with web_search/web_fetch enabled iterate until they produce a text response or hit this ceiling. Defaults to 8. Capped at 16."""
    model: NotRequired[str]
    r"""Slug of the judge model that produces the structured analysis JSON. Defaults to the model used in the outer API request."""
    reasoning: NotRequired[FusionServerToolConfigReasoningTypedDict]
    r"""Reasoning configuration forwarded to panelist and judge inner calls. Use this to control reasoning effort and token budget for models that support extended thinking."""
    temperature: NotRequired[float]
    r"""Sampling temperature forwarded to panelist and judge inner calls. When omitted, the provider's default applies."""
    tools: NotRequired[List[FusionServerToolConfigToolTypedDict]]
    r"""Server tools available to panelist and judge inner calls. Each entry uses the same `{ type, parameters? }` shorthand as the outer Chat Completions request. When omitted, defaults to `[{ type: \"openrouter:web_search\" }, { type: \"openrouter:web_fetch\" }]`. Pass an empty array to disable tools entirely (panelists answer from parametric knowledge only)."""


class FusionServerToolConfig(BaseModel):
    r"""Configuration for the openrouter:fusion server tool."""

    analysis_models: Optional[List[str]] = None
    r"""Slugs of models to run in parallel as the analysis panel. Each model receives the user prompt with openrouter:web_search and openrouter:web_fetch enabled, then a judge model summarizes the collective output into structured analysis JSON. Capped at 8 models to bound cost amplification. Defaults to the Quality preset from /labs/fusion."""

    max_completion_tokens: Optional[int] = None
    r"""Maximum number of output tokens (including reasoning tokens) each panelist and the judge model may produce per inner call. Controls the total output budget so reasoning-heavy models like GPT-5.5 do not exhaust their token allowance before producing visible text. When omitted, the provider's default applies."""

    max_tool_calls: Optional[int] = None
    r"""Maximum number of tool-calling steps each panelist (analysis model) and the judge model may take during their agentic web-research loop. Models with web_search/web_fetch enabled iterate until they produce a text response or hit this ceiling. Defaults to 8. Capped at 16."""

    model: Optional[str] = None
    r"""Slug of the judge model that produces the structured analysis JSON. Defaults to the model used in the outer API request."""

    reasoning: Optional[FusionServerToolConfigReasoning] = None
    r"""Reasoning configuration forwarded to panelist and judge inner calls. Use this to control reasoning effort and token budget for models that support extended thinking."""

    temperature: Optional[float] = None
    r"""Sampling temperature forwarded to panelist and judge inner calls. When omitted, the provider's default applies."""

    tools: Optional[List[FusionServerToolConfigTool]] = None
    r"""Server tools available to panelist and judge inner calls. Each entry uses the same `{ type, parameters? }` shorthand as the outer Chat Completions request. When omitted, defaults to `[{ type: \"openrouter:web_search\" }, { type: \"openrouter:web_fetch\" }]`. Pass an empty array to disable tools entirely (panelists answer from parametric knowledge only)."""