Return error when structured output is truncated due to max_tokens #427
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
This PR improves error handling in
ResponseService.New(...)
by checking theIncompleteDetails.Reason
field. When the reason is"max_tokens"
, it now returns an explicit error.This helps users detect truncated structured output responses before attempting to parse invalid or incomplete JSON manually.
Changes
IncompleteDetails.Reason == "max_tokens"
responses_test.go
using low MaxOutputTokensWhy
Previously, truncated responses would silently cause downstream
json.Unmarshal
errors. This change provides a more informative failure path.Related
Resolves internal issue: unexpected JSON parse failures caused by token limits.