opencode bug: interrupted agent runs re-inject queued user messages into model context once per step
fluffyspace · ghdev · 2026-10-14
An opencode v2.0.28 issue shows a prompt-assembly bug: after an interrupted/resumed run, persisted user messages get re-appended to the model context each loop step (model saw 4 copies of one message) while the DB stays correct — confusing the model, wasting tokens, and making interrupt+resume unsafe for chat frontends.
More from coding & agent
- Decisions API hits GA as agents automate cloud video editing via feedback loops — dkundel · 2026-10-23
- Swarms API changelog: 8 months of streaming, multi-agent orchestration, and dynamic model pricing — KyeGomezB · 2026-10-23
- A curated library of 50+ free AI agent resources: videos, repos, one Google Doc — ifioknkem · 2026-10-23
- Vercel adds no-account deploys: drag and drop a file to get a live URL — steren · 2026-10-23
- Dev runs 5 Claude Code sessions that coordinate via MCP Agent Mail to root his network cameras — doodlestein · 2026-10-23
- Vercel ships 'vercel deploy --temporary' for ephemeral agent-built deployments — cramforce · 2026-10-23