#Subagent

Trace and debug eve subagents in Vercel Observability. Explore nested runs, prompts, durations, failures, costs, token usage, model calls, and tool calls.

Continuing the cache TTL audit series, this time breaking down by model. The server silently switched main agent models three times (Opus 4.6 → Sonnet 4.6 → Opus 4.7 → Sonnet 4.6), and Claude Code autonomously assigns sub-agent models.…

From Dev.to - opensource: My Subagents Kept Lying to Me — So I Wired Ed25519 Verification Into Our Own Protocol Stack

From XDA Developers: I ignored Claude Code's subagents until I realized what I was missing

When developers worry about runaway AI API costs, they think about infinite loops. An agent that...