Sentry CEO on AI SDK fragmentation: eval model Jis stuck on incompatible SDK versions
zeeg · x · 2026-09-18
Sentry CEO David Cramer shares a friction point in Vercel's AI ecosystem: the evaluation model Jis requires AI SDK 7's experimentalevaluate, while Junior runs on AI SDK 6, and neither can use Vercel's OpenAI/Anthropic-compatible endpoints. His takeaway — "nothing is easy" — highlights how version fragmentation across AI SDK releases creates real friction for agent and eval tooling.
Related event: Developers Slam Vercel AI SDK's Version Fragmentation(2 posts)→
More from coding & agent
- Claude Code 2.1.275 release imminent — ClaudeCodeLog · 2026-09-18
- Legora's take: there is no best model — lawyers write evals and Legora BAR picks the winner — soleio · 2026-09-18
- Research with Agents: reflections and lessons from using AI agents in scientific work — _xiang_chen_ · 2026-09-18
- Addy Osmani: Running Agents in Old Codebases — Brownfield Agentic Engineering — rseroter · 2026-09-18
- Google's Stellar Colosseum: many-agent harness proves new math theorems — IgorCarron · 2026-09-18
- Official MCP extension lets agents discover and load Skills directly from MCP servers — solyarisoftware · 2026-09-18