fix: enable vision capability for MiniMax-M3

The pattern matcher marked *minimax-m3* as vision: false, causing
9Router to strip image attachments before forwarding upstream. This
broke Claude Code / Cursor / Cline vision flows when routing through
MiniMax-M3.

Scoped vision: true to *minimax-m3* only. M2.7 and the catch-all
*minimax* pattern remain vision: false: those models are text-only
(per MiniMax docs / NVIDIA NIM model card), so forcing vision there
would send images to a model that errors instead of degrading.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
swatker
2026-06-21 17:50:08 +07:00
committed by decolua
parent 50ed79fe9e
commit b4d2754d32

View File

@@ -201,7 +201,7 @@ export const PATTERN_CAPABILITIES = [
// ── MiniMax (M3 = adaptive; M2.x cannot disable) ─────────────────
{ pattern: "*minimax*image*", caps: { imageOutput: true } },
{ pattern: "*minimax-m3*", caps: { reasoning: true, thinkingFormat: "minimax", contextWindow: 1048576, maxOutput: 512000 } },
{ pattern: "*minimax-m3*", caps: { vision: true, reasoning: true, thinkingFormat: "minimax", contextWindow: 1048576, maxOutput: 512000 } },
{ pattern: "*minimax-m2.7*", caps: { reasoning: true, thinkingFormat: "minimax", thinkingCanDisable: false, contextWindow: 204800, maxOutput: 131072 } },
{ pattern: "*minimax*", caps: { reasoning: true, thinkingFormat: "minimax", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 131072 } },