mirror of
https://github.com/anomalyco/opencode.git
synced 2026-11-16 21:15:57 +03:00
refactor(ai): default unrecognized provider failures to retry (#45825)
This commit is contained in:
committed by
GitHub
Unverified
parent
55674b858b
commit
5cbafc57c0
@@ -59,6 +59,7 @@ export const isContextOverflowFailure = (failure: unknown) =>
|
||||
|
||||
const decodeJson = Schema.decodeUnknownOption(Schema.fromJsonString(Schema.Unknown))
|
||||
const QUOTA_CODES = new Set(["insufficient_quota", "usage_not_included", "billing_error"])
|
||||
const AUTH_CODES = new Set(["authentication_error", "permission_error"])
|
||||
const SERVER_CODES = new Set([
|
||||
"api_error",
|
||||
"internal_error",
|
||||
@@ -74,7 +75,6 @@ const INVALID_REQUEST_CODES = new Set(["invalid_prompt", "invalid_request_error"
|
||||
const RATE_LIMIT_TEXT = /rate increased too quickly|rate[-_\s]?limit|too[_\s]?many[_\s]?requests/i
|
||||
const QUOTA_TEXT = /insufficient[-_\s]?quota|quota[-_\s]?exceeded/i
|
||||
const CONTENT_POLICY_TEXT = /content[-_\s]?policy|content_filter|safety/i
|
||||
const NETWORK_ERROR_TEXT = /network[-_\s]error/i
|
||||
|
||||
export interface ProviderFailure {
|
||||
readonly message: string
|
||||
@@ -90,8 +90,12 @@ export interface ProviderFailure {
|
||||
readonly rateLimit?: HttpRateLimitDetails | undefined
|
||||
}
|
||||
|
||||
// Keep HTTP failures and provider-reported stream failures on one typed path so
|
||||
// session retry policy never needs provider-specific string matching.
|
||||
// Classification records affirmative evidence about a failure. Deterministic
|
||||
// failures need positive identification (a 4xx status, quota/auth/policy
|
||||
// signals); anything unrecognized stays UnknownProvider, which the session
|
||||
// retry policy treats as retry-eligible because transient failures arrive in
|
||||
// unpredictable shapes while deterministic rejections almost always carry a
|
||||
// status or known code.
|
||||
export function classifyProviderFailure(input: ProviderFailure): AIError["reason"] {
|
||||
const details = { message: input.message, body: input.rawBody, http: input.http, cause: input.cause }
|
||||
const body = input.rawBody ?? ""
|
||||
@@ -116,46 +120,33 @@ export function classifyProviderFailure(input: ProviderFailure): AIError["reason
|
||||
if (CONTENT_POLICY_TEXT.test(text)) return new ContentPolicyError(details)
|
||||
if (codes.some((code) => QUOTA_CODES.has(code)) || (input.status === 429 && QUOTA_TEXT.test(text)))
|
||||
return new QuotaExceededError(details)
|
||||
if (input.status === 401) return new AuthenticationError({ ...details, kind: "invalid" })
|
||||
if (input.status === 403) return new AuthenticationError({ ...details, kind: "insufficient-permissions" })
|
||||
if (codes.includes("authentication_error")) return new AuthenticationError({ ...details, kind: "invalid" })
|
||||
if (codes.includes("permission_error"))
|
||||
return new AuthenticationError({ ...details, kind: "insufficient-permissions" })
|
||||
if (input.status === 401 || input.status === 403 || codes.some((code) => AUTH_CODES.has(code)))
|
||||
return new AuthenticationError(details)
|
||||
if (
|
||||
codes.some((code) => code.includes("rate_limit") || code === "too_many_requests" || code === "throttlingexception")
|
||||
input.status === 429 ||
|
||||
codes.some(
|
||||
(code) => code.includes("rate_limit") || code === "too_many_requests" || code === "throttlingexception",
|
||||
) ||
|
||||
RATE_LIMIT_TEXT.test(text)
|
||||
)
|
||||
return new RateLimitError({
|
||||
...details,
|
||||
retryAfterMs: input.retryAfterMs,
|
||||
rateLimit: input.rateLimit,
|
||||
})
|
||||
if (RATE_LIMIT_TEXT.test(text))
|
||||
return new RateLimitError({
|
||||
...details,
|
||||
retryAfterMs: input.retryAfterMs,
|
||||
rateLimit: input.rateLimit,
|
||||
})
|
||||
if (NETWORK_ERROR_TEXT.test(text)) return new ProviderInternalError(details)
|
||||
if (codes.some((code) => SERVER_CODES.has(code) || code.includes("exhausted") || code.includes("unavailable")))
|
||||
return new ProviderInternalError({
|
||||
...details,
|
||||
retryAfterMs: input.retryAfterMs,
|
||||
})
|
||||
if (input.status === 429) {
|
||||
return new RateLimitError({
|
||||
...details,
|
||||
retryAfterMs: input.retryAfterMs,
|
||||
rateLimit: input.rateLimit,
|
||||
})
|
||||
}
|
||||
if (input.status === 408 || input.status === 409 || (input.status !== undefined && input.status >= 500))
|
||||
if (
|
||||
input.status === 408 ||
|
||||
input.status === 409 ||
|
||||
(input.status !== undefined && input.status >= 500) ||
|
||||
codes.some((code) => SERVER_CODES.has(code) || code.includes("exhausted") || code.includes("unavailable"))
|
||||
)
|
||||
return new ProviderInternalError({
|
||||
...details,
|
||||
retryAfterMs: input.retryAfterMs,
|
||||
})
|
||||
if (codes.some((code) => INVALID_REQUEST_CODES.has(code))) return new InvalidRequestError(details)
|
||||
if (input.status === 400 || input.status === 404 || input.status === 413 || input.status === 422)
|
||||
return new InvalidRequestError(details)
|
||||
// Any remaining 4xx is a deterministic rejection of this request.
|
||||
if (input.status !== undefined && input.status >= 400 && input.status < 500) return new InvalidRequestError(details)
|
||||
return new UnknownProviderError(details)
|
||||
}
|
||||
|
||||
|
||||
@@ -139,7 +139,7 @@ const toAIError = (error: AuthError): AIError => {
|
||||
return new AIError({
|
||||
reason:
|
||||
error instanceof MissingCredentialError
|
||||
? new AuthenticationError({ message: error.message, cause: error, kind: "missing" })
|
||||
? new AuthenticationError({ message: error.message, cause: error })
|
||||
: new InvalidRequestError({ message: `Failed to resolve auth config: ${error.message}`, cause: error }),
|
||||
})
|
||||
}
|
||||
|
||||
@@ -44,10 +44,7 @@ export class NoRouteError extends Schema.TaggedError<NoRouteError>("AI.Error.NoR
|
||||
|
||||
export class AuthenticationError extends Schema.TaggedError<AuthenticationError>("AI.Error.Authentication")(
|
||||
"Authentication",
|
||||
{
|
||||
...ReasonFields,
|
||||
kind: Schema.Literals(["missing", "invalid", "expired", "insufficient-permissions", "unknown"]),
|
||||
},
|
||||
ReasonFields,
|
||||
) {}
|
||||
|
||||
export class RateLimitError extends Schema.TaggedError<RateLimitError>("AI.Error.RateLimit")("RateLimit", {
|
||||
|
||||
@@ -87,10 +87,12 @@ describe("provider error classification", () => {
|
||||
])
|
||||
})
|
||||
|
||||
test("classifies network error text as provider internal", () => {
|
||||
test("classifies any remaining 4xx status as an invalid request", () => {
|
||||
expect(
|
||||
["network error", "network-error", "network_error"].map((message) => classifyProviderFailure({ message })._tag),
|
||||
).toEqual(["ProviderInternal", "ProviderInternal", "ProviderInternal"])
|
||||
[400, 402, 404, 418, 422, 451].map(
|
||||
(status) => classifyProviderFailure({ message: `HTTP ${status}`, status })._tag,
|
||||
),
|
||||
).toEqual(Array(6).fill("InvalidRequest"))
|
||||
})
|
||||
|
||||
test("classifies nested provider codes when a top-level code is also present", () => {
|
||||
@@ -103,10 +105,12 @@ describe("provider error classification", () => {
|
||||
).toEqual(["QuotaExceeded", "ProviderInternal", "InvalidRequest"])
|
||||
})
|
||||
|
||||
test("keeps unknown and malformed provider payloads non-retryable", () => {
|
||||
test("leaves unrecognized failures unclassified for the retry default", () => {
|
||||
expect(classifyProviderFailure({ message: '{"error":{"message":"no_kv_space"}}' })._tag).toBe("UnknownProvider")
|
||||
expect(classifyProviderFailure({ message: '{"type":"error","error":{"code":123}}' })._tag).toBe("UnknownProvider")
|
||||
expect(classifyProviderFailure({ message: "not-json" })._tag).toBe("UnknownProvider")
|
||||
expect(classifyProviderFailure({ message: "network error" })._tag).toBe("UnknownProvider")
|
||||
expect(classifyProviderFailure({ message: "Provider returned error" })._tag).toBe("UnknownProvider")
|
||||
})
|
||||
})
|
||||
|
||||
|
||||
@@ -52,7 +52,7 @@ describe("provider error retention", () => {
|
||||
Effect.flip,
|
||||
)
|
||||
expect(error.message).toContain("Slow down")
|
||||
expect(error.reason._tag).toBe(entry.name === "Gemini" ? "ProviderInternal" : "RateLimit")
|
||||
expect(error.reason._tag).toBe("RateLimit")
|
||||
expect(error.reason.body).toBe(body)
|
||||
expect(error.reason.http).toMatchObject({ status: 200, headers: { "x-provider-trace": "trace-1" } })
|
||||
expect(error.reason.http?.url).toStartWith("https://provider.test/")
|
||||
|
||||
@@ -250,7 +250,7 @@ test("AI error reasons are tagged Errors with required messages", () => {
|
||||
provider: model.provider,
|
||||
model: model.id,
|
||||
}),
|
||||
new AuthenticationError({ message: "Missing credentials", kind: "missing" }),
|
||||
new AuthenticationError({ message: "Missing credentials" }),
|
||||
new RateLimitError({ message: "Rate limited" }),
|
||||
new QuotaExceededError({ message: "Quota exceeded" }),
|
||||
new ContentPolicyError({ message: "Content blocked" }),
|
||||
|
||||
@@ -26,12 +26,16 @@ export function isRetryable(error: AIError) {
|
||||
return error.reason.delivery === undefined || error.reason.delivery === "not-sent"
|
||||
case "InvalidProviderOutput":
|
||||
return error.reason.classification === "incomplete-stream"
|
||||
// Unrecognized failures retry: classification records affirmative
|
||||
// deterministic evidence, and transient failures are exactly the ones
|
||||
// that arrive in shapes no classifier anticipates.
|
||||
case "UnknownProvider":
|
||||
return true
|
||||
case "Authentication":
|
||||
case "QuotaExceeded":
|
||||
case "ContentPolicy":
|
||||
case "InvalidRequest":
|
||||
case "NoRoute":
|
||||
case "UnknownProvider":
|
||||
return false
|
||||
default: {
|
||||
const exhaustive: never = error.reason
|
||||
|
||||
@@ -757,7 +757,7 @@ it.effect("classifies data-only AI SDK authentication errors", () =>
|
||||
data: { error: { code: "authentication_error" } },
|
||||
}),
|
||||
)
|
||||
expect(error.reason).toMatchObject({ _tag: "Authentication", kind: "invalid" })
|
||||
expect(error.reason).toMatchObject({ _tag: "Authentication" })
|
||||
expect(SessionRunnerRetry.isRetryable(error)).toBeFalse()
|
||||
}),
|
||||
)
|
||||
@@ -776,7 +776,7 @@ Object.entries({
|
||||
responseBody,
|
||||
})
|
||||
const error = yield* streamFailure(cause)
|
||||
expect(error.reason).toMatchObject({ _tag: "Authentication", kind: "invalid" })
|
||||
expect(error.reason).toMatchObject({ _tag: "Authentication" })
|
||||
expect(SessionRunnerRetry.isRetryable(error)).toBeFalse()
|
||||
expect(error.reason.body).toBe(responseBody)
|
||||
expect(error.reason.cause).toBe(cause)
|
||||
|
||||
@@ -32,9 +32,7 @@ describe("toSessionError", () => {
|
||||
type: "provider.rate-limit",
|
||||
message: "rate",
|
||||
})
|
||||
expect(toSessionError(llm(new AuthenticationError({ message: "auth", kind: "invalid" }))).type).toBe(
|
||||
"provider.auth",
|
||||
)
|
||||
expect(toSessionError(llm(new AuthenticationError({ message: "auth" }))).type).toBe("provider.auth")
|
||||
expect(toSessionError(llm(new QuotaExceededError({ message: "quota" }))).type).toBe("provider.quota")
|
||||
expect(toSessionError(llm(new ContentPolicyError({ message: "blocked" }))).type).toBe("provider.content-filter")
|
||||
expect(
|
||||
@@ -129,14 +127,15 @@ describe("toSessionError", () => {
|
||||
})
|
||||
})
|
||||
|
||||
test("retries only rate limits, provider-internal failures, and transport failures", () => {
|
||||
test("retries rate limits, provider-internal, transport, and unrecognized failures", () => {
|
||||
const eligible = [
|
||||
llm(new RateLimitError({ message: "rate" })),
|
||||
llm(new ProviderInternalError({ message: "internal" })),
|
||||
llm(new TransportError({ message: "transport", transport: "http", operation: "request" })),
|
||||
llm(new UnknownProviderError({ message: "unknown" })),
|
||||
]
|
||||
const ineligible = [
|
||||
llm(new AuthenticationError({ message: "auth", kind: "invalid" })),
|
||||
llm(new AuthenticationError({ message: "auth" })),
|
||||
llm(new QuotaExceededError({ message: "quota" })),
|
||||
llm(new ContentPolicyError({ message: "blocked" })),
|
||||
llm(new InvalidProviderOutputError({ message: "output" })),
|
||||
@@ -149,11 +148,10 @@ describe("toSessionError", () => {
|
||||
model: ModelID.make("model"),
|
||||
}),
|
||||
),
|
||||
llm(new UnknownProviderError({ message: "unknown" })),
|
||||
]
|
||||
|
||||
expect(eligible.map(SessionRunnerRetry.isRetryable)).toEqual([true, true, true])
|
||||
expect(ineligible.map(SessionRunnerRetry.isRetryable)).toEqual([false, false, false, false, false, false, false])
|
||||
expect(eligible.map(SessionRunnerRetry.isRetryable)).toEqual([true, true, true, true])
|
||||
expect(ineligible.map(SessionRunnerRetry.isRetryable)).toEqual([false, false, false, false, false, false])
|
||||
})
|
||||
|
||||
test("retries transport failures only when delivery is absent or not sent", () => {
|
||||
|
||||
Reference in New Issue
Block a user