ai-agents
- Bun's fetch had no way to skip the proxy
With HTTP_PROXY set, my agents found no local models: fetch sent the LAN request to the proxy. Bun 1.3.10 had no per-request way out, and end() lost the reply.
- An exception in one layer deleted a block in another
Letting my agents delete extraction folders made a config generator drop a deny glob. That glob had been the only thing stopping $(echo rm) -rf in one agent.
- The model that only says RUN
A fake model drove six coding-agent harnesses through dangerous commands. One block I had credited to a deny rule came from print mode having nobody to ask.
- Claude Code sessions can message each other. Mine didn't
Claude Code sessions have been able to message each other since August. Until 25 October I copy-pasted between mine. What a send does and doesn't promise.
- The typo followed the tag; the failures didn't
Flint misspelled its run folder 495 times, only under run tags with a -fl token. In a renamed-tag A/B the typo moved and the scores didn't.
- Three models wrote the same circuit-breaker bug
Four agent-written circuit breakers from three models: a request sent before the outage decides the half-open trial, and all 17 hidden core tests pass.
- Flint mistyped its path and blamed the tools
Flint typed one wrong token in its workspace path. OpenCode refused 81 calls without naming the path; the model blamed a tool glitch and called its code done.
- Three bugs between K2 and a working Spring app
Two models, 0 lie cells each, same sampler: Swift-1.5 shipped both Java tasks, K2-Horizon neither. Its Spring app never booted; three patches fixed it.
- The model said it saw no output. It was right.
North-Mini scored 29 in every Claude Code cell and quit after about a minute. It named every tool call 1, and Claude Code passed it one result.
- Claude Code read my home folder as a project
The bench's Claude Code cell moved its config dir and excluded the repo's CLAUDE.md. My global ~/.claude still loaded, labelled as project instructions.