Python 88.3%
TypeScript 7.6%
Shell 4.1%
1[2 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": "invalid_type", "message_semantics": "A body field has the wrong JSON type, e.g. \"Invalid type for 'max_output_tokens': expected an integer, but got a string instead.\" `param` names the field.", "retryable": false, "recommended_action": "Fix the request; never retry unchanged.", "status": ["LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "endpoint": "POST /v1/responses", "param": "max_output_tokens"}, "source": "https://developers.openai.com/api/docs/guides/error-codes"},3 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": "missing_required_parameter", "message_semantics": "\"Missing required parameter: 'model'.\" `param` = missing field.", "retryable": false, "recommended_action": "Add the parameter.", "status": ["LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "endpoint": "POST /v1/responses"}, "source": "https://developers.openai.com/api/docs/guides/error-codes"},4 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": "unknown_parameter", "message_semantics": "\"Unknown parameter: 'x'.\" The API rejects unrecognised body fields (strict schema).", "retryable": false, "recommended_action": "Remove/rename the field; check for Chat-vs-Responses parameter differences.", "status": ["LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "endpoint": "POST /v1/responses"}, "source": "https://developers.openai.com/api/docs/guides/error-codes"},5 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": "unsupported_parameter", "message_semantics": "Parameter exists but is not supported for this model/endpoint combination (e.g. `temperature` on reasoning models, `dimensions` on ada-002).", "retryable": false, "recommended_action": "Drop the parameter for that model.", "status": ["LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "note": "seen in other agents' probes (tmp-live)"}, "source": "https://developers.openai.com/api/docs/guides/error-codes"},6 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": "invalid_value", "message_semantics": "Value out of range or not allowed, e.g. \"max_tokens is too large: 100000000. This model supports at most 32768 completion tokens\" (param=max_tokens), invalid enum member, bad model for the endpoint.", "retryable": false, "recommended_action": "Correct the value; read `param` + message.", "status": ["LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "endpoint": "POST /v1/chat/completions", "param": "max_tokens"}, "source": "https://developers.openai.com/api/docs/guides/error-codes"},7 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": "integer_below_min_value", "message_semantics": "Integer below the allowed minimum (also `integer_above_max_value`, `string_above_max_length`, `array_above_max_length` family).", "retryable": false, "recommended_action": "Clamp the value.", "status": ["LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "note": "seen in other agents' probes"}, "source": "https://developers.openai.com/api/docs/guides/error-codes"},8 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": "mutually_exclusive_parameters", "message_semantics": "Two body parameters cannot be combined (e.g. `previous_response_id` + `conversation`).", "retryable": false, "recommended_action": "Send only one of them.", "status": ["LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "note": "seen in other agents' probes"}, "source": "https://developers.openai.com/api/docs/guides/error-codes"},9 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": "invalid_json", "message_semantics": "\"Invalid body: failed to parse JSON value...\" Body is not valid JSON.", "retryable": false, "recommended_action": "Fix serialisation (trailing commas, quotes).", "status": ["LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "endpoint": "POST /v1/responses"}, "source": "https://developers.openai.com/api/docs/guides/error-codes"},10 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": "unsupported_content_type", "message_semantics": "\"Unsupported content type: 'text/plain'. This API method only accepts 'application/json' requests\".", "retryable": false, "recommended_action": "Send Content-Type: application/json (multipart/form-data only for file endpoints).", "status": ["LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "endpoint": "POST /v1/responses"}, "source": "https://developers.openai.com/api/docs/guides/error-codes"},11 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": null, "message_semantics": "\"X-Client-Request-Id header contains non-ASCII characters\" (also >512 chars).", "retryable": false, "recommended_action": "Use ASCII, <= 512 chars, unique per request.", "status": ["DOCUMENTED", "LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "endpoint": "GET /v1/models"}, "source": "https://developers.openai.com/api/reference/overview#supplying-your-own-request-id-with-x-client-request-id"},12 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": "invalid_beta", "message_semantics": "Endpoint requires an `OpenAI-Beta` header value that was missing/invalid (e.g. `agents=v1`, `assistants=v2`).", "retryable": false, "recommended_action": "Add the documented OpenAI-Beta header.", "status": ["LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "note": "GET /v1/agents without OpenAI-Beta (other agent's probe)"}, "source": "https://developers.openai.com/api/reference/resources/beta"},13 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": "previous_response_not_found", "message_semantics": "`previous_response_id` cannot be resolved (deleted, unstored `store=false`, wrong project, or WebSocket-mode state lost).", "retryable": false, "recommended_action": "Retry with full input context and `previous_response_id: null`.", "status": ["DOCUMENTED", "LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "note": "other agent's probe"}, "source": "https://developers.openai.com/api/docs/guides/error-codes#websocket-mode-errors"},14 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": "websocket_connection_limit_reached", "message_semantics": "Responses WebSocket mode connection hit the 60-minute limit.", "retryable": true, "recommended_action": "Open a new WebSocket connection and continue.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/error-codes#websocket-mode-errors"},15 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": "context_length_exceeded", "message_semantics": "Prompt + requested output exceed the model context window (\"This model's maximum context length is N tokens...\").", "retryable": false, "recommended_action": "Truncate/summarise input, lower max output tokens, or use Responses `truncation: \"auto\"`.", "status": ["DOCUMENTED"], "note": "Documented historically in the error-codes guide/community; in our probe an oversized max_tokens returned code `invalid_value` instead.", "source": "https://developers.openai.com/api/docs/guides/error-codes"},16 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": "invalid_prompt", "message_semantics": "Prompt rejected (e.g. flagged by safety system / unsupported content) before generation.", "retryable": false, "recommended_action": "Change the prompt; do not retry unchanged.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/moderation"},17 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": null, "message_semantics": "\"Invalid service_tier argument: The requested service tier is not allowed for this project.\" (`param` = service_tier). Applies to default/flex/priority (fast counts as priority); auto/omitted can also resolve to a disallowed tier.", "retryable": false, "recommended_action": "Choose an allowed tier or change project settings.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/error-codes#400---invalid-service_tier-argument"},18 {"provider": "openai", "http_status": 400, "type": "image_generation_user_error", "code": "moderation_blocked", "message_semantics": "Image prompt/input blocked by moderation; optional `error.moderation_details {moderation_stage: input|output, categories[]}`.", "retryable": false, "recommended_action": "Do not auto-retry; change prompt/input.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/image-generation"},19 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": "content_policy_violation", "message_semantics": "Request violates usage policies (legacy images/moderation wording; current image endpoints use `moderation_blocked`).", "retryable": false, "recommended_action": "Change the content.", "status": ["DOCUMENTED", "LEGACY"], "source": "https://developers.openai.com/api/docs/guides/error-codes"},20 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": "invalid_image / invalid_image_format / image_parse_error", "message_semantics": "Image input cannot be decoded, wrong format, or too large.", "retryable": false, "recommended_action": "Re-encode (PNG/JPEG/WEBP/GIF), respect size limits.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/images-vision"},21 {"provider": "openai", "http_status": 400, "type": "invalid_request_error", "code": "response_already_completed", "message_semantics": "Responses multi-agent `response.inject` failed because the target response already completed (delivered as stream event `response.inject.failed`).", "retryable": false, "recommended_action": "Re-send the injected input in the next turn.", "status": ["DOCUMENTED", "BETA"], "source": "https://developers.openai.com/api/docs/guides/responses-multi-agent"},22 {"provider": "openai", "http_status": 401, "type": "invalid_request_error", "code": "invalid_api_key", "message_semantics": "\"Incorrect API key provided: sk-inv***. You can find your API key at https://platform.openai.com/account/api-keys.\" Note: type is `invalid_request_error` (NOT `authentication_error`).", "retryable": false, "recommended_action": "Fix/rotate the key; SDKs raise AuthenticationError.", "status": ["DOCUMENTED", "LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "endpoint": "GET /v1/models", "request_note": "Authorization: Bearer sk-invalid (literal)"}, "source": "https://developers.openai.com/api/docs/guides/error-codes#401---incorrect-api-key-provided"},23 {"provider": "openai", "http_status": 401, "type": "invalid_request_error", "code": null, "message_semantics": "\"Missing bearer authentication in header\" when Authorization is absent/empty.", "retryable": false, "recommended_action": "Send `Authorization: Bearer <key>`.", "status": ["LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "endpoint": "GET /v1/models"}, "source": "https://developers.openai.com/api/reference/overview#authentication"},24 {"provider": "openai", "http_status": 401, "type": "invalid_request_error", "code": "mismatched_organization", "message_semantics": "\"OpenAI-Organization header should match organization for API key\".", "retryable": false, "recommended_action": "Remove the header or use the key's organization id.", "status": ["LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "endpoint": "GET /v1/models"}, "source": "https://developers.openai.com/api/reference/overview#authentication"},25 {"provider": "openai", "http_status": 401, "type": "invalid_request_error", "code": "invalid_project", "message_semantics": "\"No such project: 'proj_...'\" when OpenAI-Project does not exist / does not belong to the key.", "retryable": false, "recommended_action": "Fix the OpenAI-Project header (only meaningful with legacy user keys).", "status": ["LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "endpoint": "GET /v1/models"}, "source": "https://developers.openai.com/api/reference/overview#authentication"},26 {"provider": "openai", "http_status": 401, "type": "invalid_request_error", "code": null, "message_semantics": "\"You have insufficient permissions for this operation. Missing scopes: api.audit_logs.read...\" — audit logs endpoint answers 401 (others answer 403) when the key lacks the scope.", "retryable": false, "recommended_action": "Use an Admin API key.", "status": ["LIVE_VERIFIED", "ACCOUNT_RESTRICTED"], "observed": {"verified_at": "2026-09-18", "endpoint": "GET /v1/organization/audit_logs"}, "source": "https://developers.openai.com/api/reference/administration/overview"},27 {"provider": "openai", "http_status": 401, "type": "invalid_request_error", "code": "ip_not_authorized", "message_semantics": "Request IP is outside the active IP allowlist of the project/org.", "retryable": false, "recommended_action": "Send from an allowed IP or update the allowlist.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/ip-allowlist"},28 {"provider": "openai", "http_status": 401, "type": "invalid_request_error", "code": null, "message_semantics": "\"You must be a member of an organization to use the API\" / revoked key / key from another org.", "retryable": false, "recommended_action": "Get invited to an organization or use a valid key.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/error-codes#401---you-must-be-a-member-of-an-organization-to-use-the-api"},29 {"provider": "openai", "http_status": 403, "type": null, "code": null, "message_semantics": "Admin endpoints with a non-admin key: body is a BARE STRING under `error` (not an object): {\"error\": \"You have insufficient permissions for this operation. Missing scopes: api.management.read. Check that you have the correct role in your organization, and if you're using a restricted API key, that it has the necessary scopes.\"}. Scopes seen: api.management.read, api.usage.read, api.mtls.read (message adds '(Owner)'), api.roles.read, api.groups.read.", "retryable": false, "recommended_action": "Use an Admin API key (or a restricted key carrying the scope). Parsers must accept `error` being a string.", "status": ["LIVE_VERIFIED", "ACCOUNT_RESTRICTED"], "observed": {"verified_at": "2026-09-18", "endpoints": ["GET /v1/organization/users", "GET /v1/organization/projects", "GET /v1/organization/usage/completions", "GET /v1/organization/costs", "GET /v1/organization/certificates", "GET /v1/organization/roles", "GET /v1/organization/groups", "GET /v1/organization/spend_limit", "GET /v1/organization/data_retention", "GET /v1/organization/spend_alerts", "GET /v1/organization/admin_api_keys", "GET /v1/organization/invites"]}, "source": "https://developers.openai.com/api/reference/administration/overview"},30 {"provider": "openai", "http_status": 403, "type": "invalid_request_error", "code": "insufficient_permissions", "message_semantics": "Structured variant of the scope error: {\"error\": {\"message\": \"... Missing scopes: api.external_storage.read ...\", \"type\": \"invalid_request_error\", \"code\": \"insufficient_permissions\"}}.", "retryable": false, "recommended_action": "Use a key with the required scope.", "status": ["LIVE_VERIFIED", "ACCOUNT_RESTRICTED"], "observed": {"verified_at": "2026-09-18", "endpoint": "GET /v1/organization/external_storage"}, "source": "https://developers.openai.com/api/reference/administration/overview"},31 {"provider": "openai", "http_status": 403, "type": "invalid_request_error", "code": "misalignment_policy_violation", "message_semantics": "Misalignment monitoring blocked the request before streaming; Error object may carry `misalignment{classification, message, continuation_instruction}`.", "retryable": false, "recommended_action": "Stop the workflow; do not auto-retry; surface to an operator.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/safety-checks/misalignment-monitoring"},32 {"provider": "openai", "http_status": 403, "type": "invalid_request_error", "code": "cyber_policy", "message_semantics": "Cybersecurity safeguard classified the request as suspicious (ZDR orgs); may arrive mid-stream as an error event.", "retryable": false, "recommended_action": "Do not retry; see appeals in the cybersecurity guide.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/safety-checks/cybersecurity"},33 {"provider": "openai", "http_status": 403, "type": "invalid_request_error", "code": "unsupported_country_region_territory", "message_semantics": "\"Country, region, or territory not supported\".", "retryable": false, "recommended_action": "See the supported countries page.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/error-codes#api-errors"},34 {"provider": "openai", "http_status": 403, "type": null, "code": null, "message_semantics": "mtls.auth.openai.com: any method/path other than exact POST /oauth/token.", "retryable": false, "recommended_action": "Use POST https://mtls.auth.openai.com/oauth/token.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/reference/workload-identity-federation"},35 {"provider": "openai", "http_status": 404, "type": "invalid_request_error", "code": "model_not_found", "message_semantics": "\"The model `x` does not exist or you do not have access to it.\" Also returned for models denied by project model permissions or not yet enabled for the org (e.g. computer_use_preview).", "retryable": false, "recommended_action": "Check GET /v1/models; check project model_permissions; a 404 does not prove the model does not exist.", "status": ["DOCUMENTED", "LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "endpoint": "POST /v1/responses"}, "source": "https://developers.openai.com/api/docs/guides/error-codes"},36 {"provider": "openai", "http_status": 404, "type": "invalid_request_error", "code": null, "message_semantics": "\"Response with id 'resp_...' not found.\" Resource lookups (responses, conversations, files, evals, fine-tuning jobs) — `code` is often null but some resources return `not_found_error` / `fine_tune_not_found` / `safety_alert_not_found` / `call_id_not_found`.", "retryable": false, "recommended_action": "Verify the id and project; `store=false` responses are never retrievable.", "status": ["LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "endpoint": "GET /v1/responses/{id}"}, "source": "https://developers.openai.com/api/docs/guides/error-codes"},37 {"provider": "openai", "http_status": 404, "type": "not_found_error", "code": "not_found_error", "message_semantics": "Stainless-style typed 404 used by newer resources (vaults, skills, chatkit, agents sessions, videos).", "retryable": false, "recommended_action": "Verify the id.", "status": ["LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "note": "other agents' probes"}, "source": "https://developers.openai.com/api/docs/guides/error-codes"},38 {"provider": "openai", "http_status": 404, "type": null, "code": null, "message_semantics": "Unknown URL: EMPTY body (Cloudflare edge), no `x-request-id`/`openai-*` headers. E.g. GET /v1/this_endpoint_does_not_exist. Legacy Assistants/Threads routes also 404 (retired).", "retryable": false, "recommended_action": "Check the path and API version prefix /v1.", "status": ["LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "endpoint": "GET /v1/this_endpoint_does_not_exist"}, "source": "https://developers.openai.com/api/reference/overview"},39 {"provider": "openai", "http_status": 405, "type": "invalid_request_error", "code": null, "message_semantics": "\"Invalid method for URL (PATCH /v1/models)\".", "retryable": false, "recommended_action": "Use the documented method (OpenAI uses POST for updates, never PATCH/PUT).", "status": ["LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "endpoint": "PATCH /v1/models"}, "source": "https://developers.openai.com/api/reference/overview"},40 {"provider": "openai", "http_status": 409, "type": "invalid_request_error", "code": null, "message_semantics": "Conflict: resource modified concurrently / state conflict (SDK ConflictError). Example codes seen: `upload_not_pending` (400 in practice).", "retryable": true, "recommended_action": "Re-read the resource and retry once.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/error-codes#python-library-error-types"},41 {"provider": "openai", "http_status": 422, "type": "invalid_request_error", "code": null, "message_semantics": "Unprocessable entity: well-formed but cannot be processed (SDK UnprocessableEntityError).", "retryable": true, "recommended_action": "Docs say 'try the request again'; validate content first.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/error-codes#python-library-error-types"},42 {"provider": "openai", "http_status": 429, "type": "rate_limit_error", "code": "rate_limit_exceeded", "message_semantics": "\"Rate limit reached for <model> in organization <org> on requests|tokens per min (RPM|TPM): Limit N, Used M, Requested K. Please try again in Xs.\" `Retry-After` may be present.", "retryable": true, "recommended_action": "Wait >= Retry-After (else exponential backoff + jitter, bounded attempts). SDKs auto-retry 2x by default. Failed requests still count.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/rate-limits"},43 {"provider": "openai", "http_status": 429, "type": "rate_limit_error", "code": "slow_down", "message_semantics": "Traffic ramped too fast (can happen under RPM/TPM). Rule of thumb: above 1M TPM grow <= 50% per 15 min.", "retryable": true, "recommended_action": "Follow Retry-After, reduce rate, ramp gradually.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/error-codes#429---slow-down"},44 {"provider": "openai", "http_status": 429, "type": "insufficient_quota", "code": "insufficient_quota", "message_semantics": "\"You exceeded your current quota, please check your plan and billing details.\" Billing/quota exhaustion; retrying never helps.", "retryable": false, "recommended_action": "Add credits / raise limits; inspect `error.code` for the specific cause.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/error-codes"},45 {"provider": "openai", "http_status": 429, "type": "insufficient_quota", "code": "credit_balance_exhausted", "message_semantics": "Prepaid credit balance depleted.", "retryable": false, "recommended_action": "Add credits.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/error-codes#429---credit-balance-exhausted"},46 {"provider": "openai", "http_status": 429, "type": "insufficient_quota", "code": "organization_spend_limit_exceeded", "message_semantics": "Organization monthly hard spend limit reached (configured via POST /v1/organization/spend_limit).", "retryable": false, "recommended_action": "Raise/remove the org limit or wait for monthly reset.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/spend-limits"},47 {"provider": "openai", "http_status": 429, "type": "insufficient_quota", "code": "project_spend_limit_exceeded", "message_semantics": "Project monthly hard spend limit reached.", "retryable": false, "recommended_action": "Raise/remove the project limit.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/spend-limits"},48 {"provider": "openai", "http_status": 429, "type": "insufficient_quota", "code": "organization_usage_limit_exceeded", "message_semantics": "OpenAI-assigned monthly usage limit (usage tier) reached; distinct from self-configured spend limits.", "retryable": false, "recommended_action": "Request a higher approved usage limit / contact support.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/error-codes#429---organization-usage-limit-reached"},49 {"provider": "openai", "http_status": 429, "type": "insufficient_quota", "code": "billing_hard_limit_reached", "message_semantics": "Legacy name of the hard-limit error (pre spend-limits API).", "retryable": false, "recommended_action": "Treat like *_spend_limit_exceeded.", "status": ["LEGACY", "UNVERIFIED"], "source": "https://developers.openai.com/api/docs/guides/error-codes"},50 {"provider": "openai", "http_status": 500, "type": "server_error", "code": null, "message_semantics": "\"The server had an error while processing your request. Sorry about that!\" Transient server fault.", "retryable": true, "recommended_action": "Retry with backoff; check status.openai.com; log x-request-id.", "status": ["DOCUMENTED", "LIVE_VERIFIED"], "observed": {"verified_at": "2026-09-18", "note": "1 occurrence in other agents' probes (vector store file_batches cancel)"}, "source": "https://developers.openai.com/api/docs/guides/error-codes"},51 {"provider": "openai", "http_status": 503, "type": "service_unavailable_error", "code": "server_is_overloaded", "message_semantics": "\"The engine is currently overloaded\" — model temporarily lacks capacity. Formerly some endpoints returned 503 slow_down / 429 rate_limit_exceeded for this.", "retryable": true, "recommended_action": "Follow Retry-After, then retry with increasing delay. Python SDK raises InternalServerError (not RateLimitError) for 503.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/error-codes#503---model-temporarily-overloaded"},52 {"provider": "openai", "http_status": 200, "type": "stream", "code": "error (SSE event)", "message_semantics": "Responses streaming: after HTTP 200 an `error` event {type:'error', code, message, param, sequence_number} or a `response.failed` event with `response.error {code, message}` may occur (codes: server_error, rate_limit_exceeded, invalid_prompt, vector_store_timeout, invalid_image, invalid_image_format, invalid_base64_image, invalid_image_url, image_too_large, image_too_small, image_parse_error, image_content_policy_violation, invalid_image_mode, image_file_too_large, unsupported_image_media_type, empty_image_file, failed_to_download_image, image_file_not_found).", "retryable": "depends on code (server_error/rate_limit_exceeded yes; do not replay after output was consumed)", "recommended_action": "Handle stream errors explicitly; do not auto-replay a request whose output was already consumed.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/reference/resources/responses/streaming-events"},53 {"provider": "openai", "http_status": 200, "type": "response.status=incomplete", "code": "incomplete_details.reason", "message_semantics": "Responses object with status `incomplete`: reasons `max_output_tokens`, `max_messages`, `content_filter`, `steered` (WebSocket response.steer). Chat Completions equivalent: finish_reason `length` / `content_filter`.", "retryable": false, "recommended_action": "Raise max_output_tokens / continue the conversation; content_filter -> change input.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/reference/resources/responses"},54 {"provider": "openai", "http_status": 400, "type": "oauth", "code": "invalid_grant | invalid_subject_token | invalid_request", "message_semantics": "Workload identity token exchange failures at auth.openai.com / mtls.auth.openai.com: invalid_subject_token (JWT/certificate verification), invalid_grant (attribute conditions, mapping/provider config), missing/unsupported parameters.", "retryable": false, "recommended_action": "Decode the JWT locally and compare iss/aud/sub/exp/iat with the provider config.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/reference/workload-identity-federation#token-exchange-errors"},55 {"provider": "openai", "http_status": null, "type": "sdk", "code": "APIConnectionError | APITimeoutError", "message_semantics": "Client-side: network/proxy/SSL failure or request exceeded the SDK timeout (default 600 s Python / 10 min Node).", "retryable": true, "recommended_action": "Retry with backoff; check network; raise timeout for long generations or use background mode.", "status": ["DOCUMENTED"], "source": "https://developers.openai.com/api/docs/guides/error-codes#python-library-error-types"}56]57