OpenAIAnthropicGooglexAIPerplexity
← Back to all updatesPublished ·Anthropic• Minor
Anthropic launched cache diagnostics in public beta for Messages requests using diagnostics.previous_message_id.
The read
Builders can see where a prompt cache prefix diverged instead of treating cache misses as opaque.
The frame
It sits inside Messages requests: pass diagnostics.previous_message_id and the beta header to get cache_miss_reason.
Primary source
Anthropic →Keep reading
See what Nova3 builds →Related updates
- Jun 12, 2026Anthropic publicly documented stop_details on refusal responses, with category and explanation fields for routing.
- Jun 12, 2026Claude Opus 4.8 defaults the effort parameter to high across all surfaces.
- Jun 12, 2026Claude Opus 4.8 lowers prompt caching’s minimum cacheable prompt length to 1,024 tokens versus Opus 4.7.
This is the world we build in. It moves this fast. We move with it.
Bring us your project →