chore(scripts): add verify-prompt-cache.mjs diagnostic#8
Merged
Conversation
Standalone Node script that probes whether the configured Anthropic endpoint actually supports prompt caching. Issues three back-to-back non-streaming requests with identical, padded-past-1024-token system content and a `cache_control: ephemeral` marker. Prints per-call input/output/cache token counts and a final OK/WARNING line. Surfaced during M1.5b verification: - The agent loop (streaming) showed all-zero usage against the claude.proai.love gateway, which made it look like our caching plumbing was broken. - A non-streaming probe confirmed the same gateway returns real token counts via the non-streaming response, but still zero on cache_creation/cache_read — the gateway silently drops cache_control on outbound requests to Anthropic. - Documented both quirks in scripts/README.md so the next person to hit "myagent usage shows 0s" knows where to look. Use: node scripts/verify-prompt-cache.mjs Not added to `npm test` — it makes real API calls. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Standalone Node script that probes whether the configured Anthropic endpoint actually supports prompt caching. Issues three back-to-back non-streaming requests with identical, padded-past-1024-token system content and a
cache_control: ephemeralmarker. Prints per-call input/output/cache token counts and a final OK/WARNING line.Surfaced during M1.5b verification:
Use:
node scripts/verify-prompt-cache.mjs
Not added to
npm test— it makes real API calls.