qwen-code silently downgrades reasoning.effort 'max' to 'xhigh' via local reverse proxies
Michael-Logies · ghdev · 2026-10-22
Issue #15235 on QwenLM/qwen-code: setting reasoning.effort: max passes through verbatim on the direct Z.ai endpoint, but via a local reverse proxy the client silently rewrites the request to reasoning.effort="xhigh", leaving only a one-time debug warning. Root cause: DefaultOpenAICompatibleProvider's OPENAICOMPATIBLEEFFORTS list omits max, so clampReasoningEffort silently steps down one tier. The author argues it should forward verbatim or surface a visible, accurate reason.
More from coding & agent
- Claude Code Pushes Urgent Security Update Across All Installations — umeshonai · 2026-10-23
- Claude cut a 2.6-hour video export to 20 minutes — but only after being told to rebuild the server — byhewar · 2026-10-23
- 3 flight-booking rules my AI agent checks that I'd never do by hand — Efistoffeles · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23