Class AIProcessingInfo

Namespace

Mythosia.AI.Models

Assembly

Mythosia.AI.Abstractions.dll

An immutable processing-mode observation for one provider inference attempt.

public sealed class AIProcessingInfo

Inheritance

object

AIProcessingInfo

Inherited Members

object.GetType()

object.ToString()

object.Equals(object)

object.Equals(object, object)

object.ReferenceEquals(object, object)

object.GetHashCode()

Remarks

The index counts inference attempts, including server continuations, rather than HTTP requests or LLM rounds. Retries and format repairs can add attempts. AppliedSpeed is null when the server did not report a recognized mode, including failed attempts. This describes a service mode, not a measured token generation rate.

Constructors

AIProcessingInfo(int, InferenceSpeed, InferenceSpeed?, string?, string?)

public AIProcessingInfo(int requestIndex, InferenceSpeed requestedSpeed, InferenceSpeed? appliedSpeed = null, string? rawAppliedMode = null, string? responseId = null)

Parameters

requestIndex int

requestedSpeed InferenceSpeed

appliedSpeed InferenceSpeed?

rawAppliedMode string

responseId string

Properties

AppliedSpeed

public InferenceSpeed? AppliedSpeed { get; }

Property Value

InferenceSpeed?

IsDowngraded

True only when a Fast request was explicitly reported as Standard.

public bool IsDowngraded { get; }

Property Value

bool

RawAppliedMode

public string? RawAppliedMode { get; }

Property Value

string

RequestIndex

public int RequestIndex { get; }

Property Value

int

RequestedSpeed

public InferenceSpeed RequestedSpeed { get; }

Property Value

InferenceSpeed

ResponseId

public string? ResponseId { get; }

Property Value

string