Cache diagnostics is now available in public beta. Pass diagnostics.previous_message_id on a Messages request and the API reports a cache_miss_reason explaining where the prompt cache prefix diverged from the previous turn. Include the cache-diagnosis-2026-04-07 beta header in your requests.
Fetched June 20, 2026
Fixed cached prompt token usage reporting in Fireworks API calls. Also clarified prompt-cache session affinity guidance in documentation.
LangChain · LangChain (Python)Fixed parsing of raw OpenAI API responses and added a flag to skip tracing them. Updated API spec from upstream.
Langfuse · Python SDKAdded the agent-memory-2026-07-22 beta header, which changes listing memories to return results in a stable server-defined order, ignores o…
Anthropic · Claude PlatformThe stream-stall hint now reads "Waiting for API response · will retry in …" instead of "No response from API · Retrying in …", and trigger…
Anthropic · Claude Code