feat: Anthropic SDK with prompt caching support #139
Closed
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Outdated suggestions cannot be applied.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
fetchcalls to Anthropic API with the official@anthropic-ai/sdkcache_control: { type: "ephemeral" }on system messagessystemmessage field toLLMRequestfor all providers (Anthropic, OpenAI, OpenRouter)Impact
Files changed
src/llm/api.ts— Refactored to use Anthropic SDK, added system message + cache supportsrc/loop/cost-tracker.ts— Added cache pricing,CacheMetrics,recordIterationWithUsage()package.json— Added@anthropic-ai/sdkdependencyTest plan
npm run buildpassesnpm run test:run— all 143 tests passtryCallLLM()with system message, verify cache metrics in responseralph-starter run --track-costand verify cache savings in cost summary🤖 Generated with Claude Code