OpenAI: value can now return "max_output_tokens"

OpenAI added "max_output_tokens" as a new value on its SessionTurnErrorCodeResource, an enum reachable from 6 OpenAI operations, according to the company's published API specification. The change is additive on the producer side but breaks exhaustive switch statements, strict parsers and generated client enums that do not handle the new value. Code reading SessionTurnErrorCodeResource objects now must account for "max_output_tokens" alongside the 23 existing values, including "context_length_exceeded" and "rate_limit_exceeded".

What changed Producer-side tools call this additive. It breaks exhaustive switches, strict parsers and generated client enums. Affects this value on SessionTurnErrorCodeResource reachable from 6 operations. New value: max output tokens . can now return "max output tokens" Who is affected Code that reads OpenAI's SessionTurnErrorCodeResource objects, used by 6 OpenAI operations. Before and after | Where | Before | After | |---|---|---| | SessionTurnErrorCodeResource | "active turn not steerable", "authentication error", "billing not active", "connection failed", "context length exceeded", "credit balance exhausted", "cyber policy", "executor version incompatible", "flex unavailable", "internal error", "invalid request", "misalignment policy violation", "organization spend limit exceeded", "organization usage limit exceeded", "project spend limit exceeded", "rate limit exceeded", "request timeout", "resource not found", "sandbox error", "server error", "server overloaded", "session budget exceeded", "usage limit exceeded" | "active turn not steerable", "authentication error", "billing not active", "connection failed", "context length exceeded", "credit balance exhausted", "cyber policy", "executor version incompatible", "flex unavailable", "internal error", "invalid request", "max output tokens", "misalignment policy violation", "organization spend limit exceeded", "organization usage limit exceeded", "project spend limit exceeded", "rate limit exceeded", "request timeout", "resource not found", "sandbox error", "server error", "server overloaded", "session budget exceeded", "usage limit exceeded" | Code that breaks switch response { // existing branches … // no branch for "max output tokens" default: throw new Error "unexpected value" ; } Based on OpenAI’s published API specification. How severity is decided https://driftwatch.et/method .