Paper: swapping coding-agent harness flips as many SWE-bench tasks as a rerun
Claude Code, OpenCode and mini-SWE-agent ran five models on SWE-bench Verified. Harness choice moved cost up to 3x but outcomes about as much as noise.
Topic · 7 stories
7 stories tagged opencode on AI Tamer, newest first.
Claude Code, OpenCode and mini-SWE-agent ran five models on SWE-bench Verified. Harness choice moved cost up to 3x but outcomes about as much as noise.
SOCRadar says an exposed server showed INC and The Gentlemen affiliates using OpenCode and OpenRouter-hosted Claude Opus 4.6 and Kimi K3, with human sign-off.
Harness², a Google Research paper and Apache-2.0 repo from 9 October, refines an agent's harness per task with model weights fixed. Gains are the authors'.
OpenCode says a breach hit 1.4% of OpenCode Console users with linked providers. If you got its email, revoke those keys at each provider.
OpenCode 2.0 is now the official upgrade from the 1.x CLI: one shared background server, a new client, and Code Mode. The 1.19.0 release adds the major upgrade and stops silent updates.
Cloudflare’s Auto Router is in public beta via AI Gateway (blog Sep 30, 2026): set model to cloudflare/auto and a classifier picks from an eligible pool. Router is free in beta; upstream inference still billed. ~30% OpenCode savings and internal benches are Cloudflare-reported only. WebSockets not yet supported.
A coding agent combines a model loop, tools, project instructions, and rules for what it may do. Here is how four CLIs arrange those parts.