fix(ai): recover Anthropic request_too_large as overflow (#45144)

This commit is contained in:
Aiden Cline
2026-08-25 22:30:14 -05:00
committed by GitHub
Unverified
parent 474c3588c1
commit a78d3c5438
3 changed files with 35 additions and 6 deletions
+4 -2
View File
@@ -40,15 +40,16 @@ const patterns = [
/model_context_window_exceeded/i,
/too many tokens/i,
/token limit exceeded/i,
/request_too_large/i,
]
const payloadPatterns = [/request_too_large/i, /request entity too large/i, /payload too large/i, /request too large/i]
const payloadPatterns = [/request entity too large/i, /payload too large/i, /request too large/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)) || /^400\s*(status code)?\s*\(no body\)/i.test(message))
(patterns.some((pattern) => pattern.test(message)) || /^4(?:00|13)\s*(status code)?\s*\(no body\)/i.test(message))
export const isPayloadTooLarge = (message: string) => payloadPatterns.some((pattern) => pattern.test(message))
@@ -106,6 +107,7 @@ export function classifyProviderFailure(input: ProviderFailure): AIError["reason
clientScoped &&
(codes.includes("context_length_exceeded") ||
codes.includes("model_context_window_exceeded") ||
codes.includes("request_too_large") ||
isContextOverflow(text))
)
return new InvalidRequestReason({ ...common, classification: "context-overflow" })
+22
View File
@@ -211,6 +211,28 @@ describe("RequestExecutor", () => {
}).pipe(Effect.provide(responsesLayer([new Response("request too large", { status: 413 })]))),
)
it.effect("classifies Anthropic request_too_large as context overflow", () =>
Effect.gen(function* () {
const executor = yield* RequestExecutor.Service
const error = yield* executor.execute(request).pipe(Effect.flip)
expectAIError(error)
expect(error.reason).toMatchObject({
_tag: "InvalidRequest",
classification: "context-overflow",
http: { response: { status: 413 } },
})
}).pipe(
Effect.provide(
responsesLayer([
new Response('{"error":{"type":"request_too_large","message":"Request exceeds the maximum size"}}', {
status: 413,
}),
]),
),
),
)
it.effect("does not classify ordinary invalid requests as context overflow", () =>
Effect.gen(function* () {
const executor = yield* RequestExecutor.Service
+9 -4
View File
@@ -18,13 +18,19 @@ describe("provider error classification", () => {
expect(messages.every(isContextOverflow)).toBe(true)
})
test("classifies request size failures separately from context overflow", () => {
const failures = [
classifyProviderFailure({ message: "request too large", status: 413 }),
test("classifies Anthropic request_too_large as recoverable overflow", () => {
expect(
classifyProviderFailure({
message: '{"error":{"type":"request_too_large","message":"Request exceeds the maximum size"}}',
status: 400,
}),
).toMatchObject({ _tag: "InvalidRequest", classification: "context-overflow" })
expect(isContextOverflow("413 status code (no body)")).toBe(true)
})
test("classifies generic request size failures separately from context overflow", () => {
const failures = [
classifyProviderFailure({ message: "request too large", status: 413 }),
classifyProviderFailure({ message: "upstream request entity too large", status: 502 }),
]
@@ -33,7 +39,6 @@ describe("provider error classification", () => {
expect.objectContaining({ _tag: "InvalidRequest", classification: "payload-too-large" }),
),
)
expect(isContextOverflow("413 status code (no body)")).toBe(false)
})
test("does not classify rate limits as context overflow", () => {