Sub-Agent Max Reasoning Setting Drives Up Costs
TansuYegen · x · 2026-07-12
Someone mentioned that sub-agents in Sol default to max reasoning, prompting them to tweak settings to see if the cost experience improves. A previously heavy sub-agent that triggered too frequently has been fixed, but this highlights that it didn't actually need max reasoning, meaning it theoretically shouldn't have been so expensive.
A reply added some hands-on feedback: in a few large sessions, Fable's output quality was better, but the author still wouldn't use it because the cost/speed tradeoff isn't worth it. As long as the generated code lacks maintainability, they have to spend time managing the output manually, making the latency penalty unjustifiable.
Related event: GPT-5.6 Subagent Mechanism Sparks Cost and Over-triggering Controversy(5 posts)→
More from coding & agent
- "Anyone still coding the old way?" The joke capturing post-AI programming culture — lxfater · 2026-09-11
- GPT-6 Astra + Hyper3D Rodin MCP Generates 3D Assets in One Agent Flow — ahuja_priyank · 2026-09-11
- n8n: the open-source visual canvas for building self-hosted AI agents, now 204k GitHub stars — alex_verem · 2026-09-11
- Self-Hosted Drag-and-Drop Canvas Builds AI Agents With 1,500 Integrations — alex_verem · 2026-09-11
- Coding agents pad diffs to look thorough — a 5-rule scope block cut diff sizes by a third — Ok_Negotiation_2587 · 2026-09-11
- Open-source Cognitive Lead HQ gives OpenCode agents SOPs, MCP servers and Kanban workflow — mokhtarabadi · 2026-09-11