feat(responses): add prompt_cache_key to CreateModelResponseQuery#412
Merged
nezhyborets merged 1 commit intomainfrom Apr 30, 2026
Merged
feat(responses): add prompt_cache_key to CreateModelResponseQuery#412nezhyborets merged 1 commit intomainfrom
nezhyborets merged 1 commit intomainfrom
Conversation
OpenAI's Responses API accepts a `prompt_cache_key` parameter that groups requests for cache-hit-rate reporting and routing. The library had no way to set it, so users had to fork or work around it. Add `promptCacheKey: String?` as an optional init parameter, defaulting to nil so the field is omitted from the request when unset (verified by a new encode test). Existing call sites are unaffected. Closes #386 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
nezhyborets
approved these changes
Apr 30, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Closes #386.
OpenAI's Responses API accepts a
prompt_cache_keyparameter that buckets similar requests together for improved cache hit rates and routing. Previously there was no way to set it fromCreateModelResponseQuery, forcing users to fork or fall back to lower-level workarounds.This PR adds a single optional
promptCacheKey: String?property + matching init parameter (defaultnil) +CodingKeymapping to"prompt_cache_key". Pure addition — no existing call site needs to change.Test plan
testCreateResponseQueryEncodesPromptCacheKey— when set, the encoded JSON contains"prompt_cache_key": "user-1234".testCreateResponseQueryOmitsPromptCacheKeyWhenNil— when not provided, the encoded JSON has noprompt_cache_keyfield (verifies we don't accidentally sendnulland pollute requests).swift test— all 177 tests pass locally.🤖 Generated with Claude Code