model.context_exceeded

The inputs exceed what the model can read


Type	`https://mthds.ai/errors/model.context_exceeded`
Family	`model`: The model a step names.
Domain	`input`: the caller acts, by changing the request or its inputs
Retry	`no`: repeating the operation fails the same way
HTTP status	`422`
Raised as	a problem document, sent as the body of an HTTP response or kept in a run's record

What it means

The prompt built from the inputs passes the model's context window or the number of images it takes.

What to do

Shorten the inputs, split a long document into parts, or send fewer images. The method's author can instead pick a model with a larger window.

Next steps

A problem carries the step aimed at whoever reads it: the first when its reader is the domain's actor, the caller, and the second for any other reader.

Reader	Kind	Detail
The domain's actor	`change_input`	Send smaller inputs, or fewer images, then send the request again.
Any other reader	`change_input`	Pass this to the caller, whose inputs exceed what the model '`{model}`' can read.

Detail

The problem's detail is written from this template, filled with the occurrence's parameters:

The prompt for the model '{model}' reaches {count} against a {limit} of {max}.

Parameters

Every parameter is present on every occurrence of the code.

Name	Type	Description
`model`	`identifier`	The model.
`limit`	one of `context_window`, `prompt_images`	Which bound the prompt passes: the context window, or the number of images.
`count`	`integer`	What the prompt reached.
`max`	`integer`	The bound.