OpenCode Zen's big-pickle model leaks inline chain-of-thought into text output, reproduced
ashaker20 · ghdev · 2026-10-12
On OpenCode 2.0.25, the opencode/big-pickle model via OpenCode Zen intermittently emits its chain-of-thought inline in the assistant content — sometimes terminated by a literal </think> — which OpenCode stores as a single text part instead of a separate reasoning part, so the TUI renders the model's internal monologue as ordinary output.
- Most likely to trigger during multi-step agentic tasks with tool calls.
- This is the V2 re-report of #43770, which was closed as not planned; the new issue is now confirmed with the reproduced label and 6 comments.
- Expected behavior: inline reasoning should be extracted into a collapsible thinking block, the same way reasoningcontent is handled.
More from coding & agent
- Garry Tan endorses Aside Browser as the fix for agents getting blocked on the web — garrytan · 2026-10-23
- 1Password launches tool letting AI agents log in for you without seeing your password — AndrewSchmidtFC · 2026-10-23
- MCP server turned rogue 30 days after approval, prompting open-source mcp-guard lockfile tool — ErgoniaWorks · 2026-10-23
- Test: Coding Agents Won't Use an MCP Tool Unless AGENTS.md Mentions It — colinmcnamara · 2026-10-23
- Open-Source Tennis Models Plus Claude Turn Video Into a World-Class Coach — tweetsatpreet · 2026-10-23
- awesome-ai-apps: 132 Free Open-Source AI Agent and RAG Projects on GitHub — Arindam_1729 · 2026-10-23