File size: 1,935 Bytes
eb1202c | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 | import { Schema } from "effect"
import { LLMError, ProviderErrorEvent } from "./schema"
const patterns = [
/prompt is too long/i,
/request_too_large/i,
/input is too long for requested model/i,
/exceeds the context window/i,
/exceeds (?:the )?(?:model'?s )?maximum context length(?: of [\d,]+ tokens?|\s*\([\d,]+\))/i,
/input token count.*exceeds the maximum/i,
/tokens in request more than max tokens allowed/i,
/maximum prompt length is \d+/i,
/reduce the length of the messages/i,
/maximum context length is \d+ tokens/i,
/exceeds (?:the )?maximum allowed input length of [\d,]+ tokens?/i,
/input \(\d+ tokens\) is longer than the model'?s context length \(\d+ tokens\)/i,
/exceeds the limit of \d+/i,
/exceeds the available context size/i,
/greater than the context length/i,
/context window exceeds limit/i,
/exceeded model token limit/i,
/context[_ ]length[_ ]exceeded/i,
/request entity too large/i,
/context length is only \d+ tokens/i,
/input length.*exceeds.*context length/i,
/prompt too long; exceeded (?:max )?context length/i,
/too large for model with \d+ maximum context length/i,
/prompt has [\d,]+ tokens?, but the configured context size is [\d,]+ tokens?/i,
/model_context_window_exceeded/i,
/too many tokens/i,
/token limit exceeded/i,
]
const exclusions = [/^(throttling error|service unavailable):/i, /rate limit/i, /too many requests/i]
export const isContextOverflow = (message: string) =>
!exclusions.some((pattern) => pattern.test(message)) &&
(patterns.some((pattern) => pattern.test(message)) || /^4(00|13)\s*(status code)?\s*\(no body\)/i.test(message))
export const isContextOverflowFailure = (failure: unknown) =>
failure instanceof LLMError
? failure.reason._tag === "InvalidRequest" && failure.reason.classification === "context-overflow"
: Schema.is(ProviderErrorEvent)(failure) && failure.classification === "context-overflow"
|