fix(llm): port provider retry classification (#36887)

packages/llm/src/provider-error.ts

@@ -1,5 +1,18 @@
-import { Schema } from "effect"
-import { LLMError, ProviderErrorEvent } from "./schema"
+import { Option, Schema } from "effect"
+import {
+  AuthenticationReason,
+  ContentPolicyReason,
+  InvalidRequestReason,
+  LLMError,
+  ProviderErrorEvent,
+  ProviderInternalReason,
+  QuotaExceededReason,
+  RateLimitReason,
+  UnknownProviderReason,
+  type HttpContext,
+  type HttpRateLimitDetails,
+  type ProviderMetadata,
+} from "./schema"
 
 const patterns = [
   /prompt is too long/i,
@@ -31,3 +44,112 @@ 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"
+
+const decodeJson = Schema.decodeUnknownOption(Schema.UnknownFromJsonString)
+const QUOTA_CODES = new Set(["insufficient_quota", "usage_not_included", "billing_error"])
+const SERVER_CODES = new Set([
+  "api_error",
+  "internal_error",
+  "internalserverexception",
+  "modelstreamerrorexception",
+  "overloaded_error",
+  "server_error",
+  "server_is_overloaded",
+  "serviceunavailableexception",
+])
+const INVALID_REQUEST_CODES = new Set(["invalid_prompt", "invalid_request_error", "validationexception"])
+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
+
+export interface ProviderFailure {
+  readonly message: string
+  readonly status?: number | undefined
+  readonly code?: string | undefined
+  readonly retryAfterMs?: number | undefined
+  readonly rateLimit?: HttpRateLimitDetails | undefined
+  readonly http?: HttpContext | undefined
+  readonly providerMetadata?: ProviderMetadata | undefined
+}
+
+// Keep HTTP failures and provider-reported stream failures on one typed path so
+// session retry policy never needs provider-specific string matching.
+export function classifyProviderFailure(input: ProviderFailure): LLMError["reason"] {
+  const body = input.http?.body ?? ""
+  const codes = [input.code, ...providerCodes(body), ...providerCodes(input.message)]
+    .filter((code): code is string => code !== undefined)
+    .map((code) => code.toLowerCase())
+  const text = body || input.message
+  const common = { message: input.message, providerMetadata: input.providerMetadata, http: input.http }
+  const clientScoped = input.status === undefined || (input.status >= 400 && input.status < 500)
+
+  if (
+    clientScoped &&
+    (codes.includes("context_length_exceeded") ||
+      codes.includes("model_context_window_exceeded") ||
+      isContextOverflow(text))
+  )
+    return new InvalidRequestReason({ ...common, classification: "context-overflow" })
+  if (CONTENT_POLICY_TEXT.test(text)) return new ContentPolicyReason(common)
+  if (codes.some((code) => QUOTA_CODES.has(code)) || (input.status === 429 && QUOTA_TEXT.test(text)))
+    return new QuotaExceededReason(common)
+  if (input.status === 401) return new AuthenticationReason({ ...common, kind: "invalid" })
+  if (input.status === 403) return new AuthenticationReason({ ...common, kind: "insufficient-permissions" })
+  if (codes.includes("authentication_error")) return new AuthenticationReason({ ...common, kind: "invalid" })
+  if (codes.includes("permission_error"))
+    return new AuthenticationReason({ ...common, kind: "insufficient-permissions" })
+  if (
+    codes.some((code) => code.includes("rate_limit") || code === "too_many_requests" || code === "throttlingexception")
+  )
+    return new RateLimitReason({
+      ...common,
+      retryAfterMs: input.retryAfterMs,
+      rateLimit: input.rateLimit,
+    })
+  if (RATE_LIMIT_TEXT.test(text))
+    return new RateLimitReason({
+      ...common,
+      retryAfterMs: input.retryAfterMs,
+      rateLimit: input.rateLimit,
+    })
+  if (codes.some((code) => SERVER_CODES.has(code) || code.includes("exhausted") || code.includes("unavailable")))
+    return new ProviderInternalReason({
+      ...common,
+      status: input.status,
+      retryAfterMs: input.retryAfterMs,
+    })
+  if (input.status === 429) {
+    return new RateLimitReason({
+      ...common,
+      retryAfterMs: input.retryAfterMs,
+      rateLimit: input.rateLimit,
+    })
+  }
+  if (input.status !== undefined && input.status >= 500)
+    return new ProviderInternalReason({
+      ...common,
+      status: input.status,
+      retryAfterMs: input.retryAfterMs,
+    })
+  if (codes.some((code) => INVALID_REQUEST_CODES.has(code))) return new InvalidRequestReason(common)
+  if (
+    input.status === 400 ||
+    input.status === 404 ||
+    input.status === 409 ||
+    input.status === 413 ||
+    input.status === 422
+  )
+    return new InvalidRequestReason(common)
+  return new UnknownProviderReason({ ...common, status: input.status })
+}
+
+function providerCodes(value: string) {
+  const decoded = Option.getOrUndefined(decodeJson(value))
+  if (!isRecord(decoded)) return []
+  const error = isRecord(decoded.error) ? decoded.error : undefined
+  return [decoded.code, error?.code, error?.type].filter((value): value is string => typeof value === "string")
+}
+
+function isRecord(value: unknown): value is Record<string, unknown> {
+  return typeof value === "object" && value !== null
+}