Skip to navigation

Warnings

How Gateway tells you a request was served but changed on the way

A warnings array means Gateway served your request but changed it, such as removing a tool the route can’t run or adjusting a reasoning level it doesn’t accept. Log it wherever you measure cost or quality. Requests that don’t run at all are errors.

{
  "warnings": [
    {
      "code": "reasoning_effort_adjusted",
      "message": "reasoning effort 'max' was adjusted to 'xhigh': the highest level the resolved route accepts",
      "detail": {
        "requested_effort": "max",
        "applied_effort": "xhigh",
        "model": "moonshot/kimi-k3",
        "vendor": "baseten"
      }
    }
  ]
}

Branch on code; message is for humans. detail is optional with keys that vary by code, so read it defensively. On a clean request the field is absent or null, never an empty array.

Warning codes

codeSurfacesMeaning
reasoning_effort_adjustedAllThe requested effort isn’t one the route accepts, so the closest level ran. detail.applied_effort is null when the route has no effort control. See Reasoning.
reasoning_effort_policy_boundAllThe routing policy’s effort bounds for the model changed the effort you asked for
reasoning_exhaustedAllThe model billed output tokens but returned no content, usually because reasoning used the whole budget. The response is still a 200, with finish_reason max_tokens on native /v1/responses (length on OpenAI-compatible surfaces). Raise the token limit or lower the effort.
reasoning_summary_unavailableAllreasoning.summary wasn’t returned, because the output budget was too small or ran out, or the OpenAI model doesn’t reason. detail.reason says which.
cache_control_ignoredAllThe route can’t honor your cache markers, so they were removed. detail names the vendor and prompt_caching_mode. See Prompt caching.
server_tool_iteration_limit_reachedAllA web search loop hit its limit of 6 iterations, so the model answered from the results it had. detail.max_iterations is 6.
web_search_remappedAllA vendor-hosted search tool ran as merge:web_search under your organization’s web search mode. detail lists remapped_tools and web_search_mode.
openai_fields_ignoredPOST /v1/responsesOpenAI-only fields with no native equivalent were ignored. detail.ignored_fields lists them. Call /v1/openai/responses or send X-Merge-Wire-Format: openai instead. See OpenAI Responses API clients.
tools_dropped/v1/openai/responsesCustom tool types the route can’t express were removed. detail.dropped_tools names them.
tools_mapped/v1/openai/responsesA custom tool was sent as a function tool, so its grammar isn’t enforced. detail.mapped_tools names them.
openai_tool_search_dropped/v1/openai/responsesThe route moved off OpenAI after the request was accepted, so tool_search was removed and every deferred tool was loaded up front
openai_web_search_dropped/v1/openai/responsesOpenAI hosted web_search was removed because the route isn’t direct OpenAI. Use {"type": "merge:web_search"} for search on any model
openai_image_generation_dropped/v1/openai/responsesOpenAI hosted image_generation was removed because the route isn’t direct OpenAI. Route to an openai/ model or call POST /v1/images/generations
openai_params_ignored/v1/openai/responsesThe route is served through chat completions, so parameters with no equivalent had no effect. detail.ignored_params lists them.
input_items_dropped/v1/openai/responsesThe route is served through chat completions, so replayed reasoning and other items it can’t represent were dropped. detail.dropped_item_types counts them.

Where warnings arrive

On SDK-compatible surfaces warnings is a Gateway extension that a strict SDK may drop from its typed object, so read it from the raw response or event.

SurfaceNon-streamingStreaming
POST /v1/responsesTop-level warningsThe terminal response.done frame
/v1/openai/chat/completionsTop-level warningsThe final chunk
/v1/openai/responsesTop-level warnings, omitted when emptyInside response.completed
/v1/anthropic/v1/messagesTop-level warnings, null when emptyThe final message_delta, repeated on message_stop
/v1/ai-sdk/chat/completionsTop-level warningsThe final chunk
/v1/ai-sdk/responsesNot returnedInside response.completed
/v1/langchain/chat/completionsTop-level warningsThe final chunk

Non-streaming /v1/openai/responses requests that use OpenAI’s server-executed tool_search return OpenAI’s response without warnings. Interim stream frames never carry warnings, and a warning raised mid-stream still reaches the terminal frame.

Next steps

Errors

Every error code grouped by HTTP status

Streaming

Which frame carries the terminal payload on each surface

Reasoning

Effort levels per route, and the warning when yours is adjusted