luulam/9router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(opencode-go): clamp deepseek reasoning_effort "max" to "high" for mimo backends that reject it

Browse Source 
mimo-v2.5-pro/v2.6 on the Go lane return 400 on reasoning_effort "max"
(probed live; mimo-v2.5 accepts it). The deepseek applyFormat case now honors
the declared thinking levels, and mimo-v2.5-pro gets a levels entry.

Co-Authored-By: Claude Code <noreply@anthropic.com>
This commit is contained in:
decolua
2026-09-23 11:45:40 +07:00
parent 2aa99d9f39
commit 1b72f02e3b
2 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
open-sse/providers/thinkingLevels.js
View File

@@ -42,6 +42,8 @@ const PATTERN_THINKING = [
{ provider: "codex", pattern: "*gpt-5.6-luna*", levels: CODEX_GPT_5_6_LEVELS },
{ pattern: "*codex*", levels: ["low", "medium", "high", "xhigh"] }, // codex cannot disable thinking
{ pattern: "*mimo*v2.6*", levels: ["none", "low", "medium", "high", "xhigh"] },
// mimo-v2.5-pro on opencode-go rejects reasoning_effort "max" (probed live); v2.5 accepts it.
{ pattern: "*mimo*v2.5-pro*", levels: ["none", "low", "medium", "high", "xhigh"] },
// DeepSeek v4.* (Alibaba MaaS, probed live): effort low|medium|high|xhigh|max
// all 200 via output_config.effort; "none" is a 400 on the anthropic route
// (disable thinking instead). none kept for the picker = disable.