Improved
- Faster, cheaper model calls: the LLM gateway now applies prefix prompt caching on the Bedrock and Anthropic transports, so shared context (system prompt, tools, history) isn't reprocessed on every request.
Fixed
- Blocked previews no longer break: when a site refuses to be embedded, the agent shows a link to open the preview URL instead of an empty frame.
What's Changed
- chore(release): VERSION → 0.9.77 [skip ci] by @github-actions[bot] in #3721
- Show preview URL fallback for blocked embeds by @markokraemer in #3722
- Test preview URL fallback detection by @markokraemer in #3723
- feat(llm-gateway): prefix prompt caching (fixes latency growing with chat length) by @lillyboga in #3724
- chore(dev-eks): deploy gateway dev-f1e6a7e8 [skip ci] by @github-actions[bot] in #3725
- chore(dev-eks): deploy dev-f1e6a7e8 [skip ci] by @github-actions[bot] in #3726
Full Changelog: v0.9.76...v0.9.77
Contributors
markokraemer and lillyboga