{"slug": "breaking-openai-value-can-now-return-max-output-tokens", "title": "OpenAI: value can now return \"max_output_tokens\"", "summary": "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\".", "body_md": "## What changed\n\nProducer-side tools call this additive. It breaks exhaustive switches, strict parsers and generated client enums.\n\nAffects this value on `SessionTurnErrorCodeResource` reachable from 6 operations.\n\nNew value: `max_output_tokens`.\n\ncan now return \"max_output_tokens\"\n\n## Who is affected\n\nCode that reads OpenAI's SessionTurnErrorCodeResource objects, used by 6 OpenAI operations.\n\n## Before and after\n\n| Where | Before | After | \n|---|---|---|\n| 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\" | \n\n## Code that breaks\n\n```\nswitch (response) {\n  // existing branches …\n  // no branch for \"max_output_tokens\"\n  default:\n    throw new Error(\"unexpected value\");\n}\n```\n\nBased on OpenAI’s published API specification. [How severity is decided](https://driftwatch.et/method).", "url": "https://wpnews.pro/news/breaking-openai-value-can-now-return-max-output-tokens", "canonical_source": "https://driftwatch.et/changes/openai-2026-11-03-2cc3309f", "published_at": "2026-11-03 22:29:31+00:00", "updated_at": "2026-11-04 00:20:25.462611+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-products", "developer-tools"], "entities": ["OpenAI", "SessionTurnErrorCodeResource"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/breaking-openai-value-can-now-return-max-output-tokens", "markdown": "https://wpnews.pro/news/breaking-openai-value-can-now-return-max-output-tokens.md", "text": "https://wpnews.pro/news/breaking-openai-value-can-now-return-max-output-tokens.txt", "jsonld": "https://wpnews.pro/news/breaking-openai-value-can-now-return-max-output-tokens.jsonld"}}