fix(unbound): enable prompt caching for Claude 4 models #4589
Conversation
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
- Update model ID check from 'anthropic/claude-3' to 'anthropic/claude-' to include both Claude 3 and Claude 4 models - Add comprehensive test coverage for Claude 4 models (sonnet-4, opus-4) - Ensure cache breakpoints are properly applied for performance optimization - Verify non-Claude models continue to work without caching Fixes caching support for claude-sonnet-4-20250514 and claude-opus-4-20250514 models, enabling cost savings and improved response times.
dosubot
bot
added
the
size:L
lupuletic
commented
Jun 12, 2025
src/api/providers/unbound.ts
Outdated
| ...convertToOpenAiMessages(messages), | ||
| ] | ||
|
|
||
| if (modelId.startsWith("anthropic/claude-3")) { |
Contributor
Author
There was a problem hiding this comment.
this will cause issues for haiku -- should be limited to models that support caching
![ellipsis-dev[bot]](https://avatars.githubusercontent.com/in/64358?s=60&v=4){kind=small}
| }) | ||
| }) | ||
|
|
||
| describe("cache breakpoints", () => { |
Contributor
There was a problem hiding this comment.
Consider parameterizing the cache breakpoint tests for Claude 3, Claude Sonnet 4, and Claude Opus 4 models to reduce duplication and improve maintainability.
hannesrudolph
added
the
Issue/PR - Triage
Add support for Claude 3 and 3.5 Haiku models in caching logic based on Unbound API indicating `supportsPromptCaching: true`. Updates pattern matching to include: - anthropic/claude-3-haiku-* - anthropic/claude-3-5-haiku-*
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Outdated suggestions cannot be applied.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.
Fixes caching support for claude-sonnet-4-20250514 and claude-opus-4-20250514 models, enabling cost savings and improved response times.
Related GitHub Issue
Closes: #
Description
Test Procedure
Type of Change
srcor test files.Pre-Submission Checklist
npm run lint).console.log) has been removed.npm test).mainbranch.npm run changesetif this PR includes user-facing changes or dependency updates.Screenshots / Videos
Documentation Updates
Additional Notes
Get in Touch
Important
Enable prompt caching for Claude 4 models and add tests for cache breakpoints in
unbound.ts.unbound.tsfrom'anthropic/claude-3'to'anthropic/claude-'to include Claude 4 models.unbound.ts.unbound.ts.claude-sonnet-4-20250514,claude-opus-4-20250514) inunbound.test.ts.unbound.test.ts.This description was created by
for d37e86f. You can customize this summary. It will automatically update as commits are pushed.