From 52cbceea448a05d151434d2063bd79f92e5fdbb9 Mon Sep 17 00:00:00 2001
From: Teknium <127238744+teknium1@users.noreply.github.com>
Date: Tue, 21 Apr 2026 14:43:55 -0700
Subject: [PATCH] fix(vision): restore tier-aware Nous vision model selection
 (#13703)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Revert two overreaches from #13699 that forced paid Nous vision to
xiaomi/mimo-v2-omni instead of the tier-appropriate gemini-3-flash-preview:

1. Remove "nous": "xiaomi/mimo-v2-omni" from _PROVIDER_VISION_MODELS —
   #13696 already routes nous main-provider vision through the strict
   backend, and this entry caused any direct resolve_provider_client(
   "nous", ...) aggregator-lookup path to pick the wrong model for paid.

2. Drop the 'elif vision' paid override in _try_nous() that forced
   mimo-v2-omni on every Nous vision call regardless of tier. Paid
   accounts now keep gemini-3-flash-preview for vision as well as text.

Free-tier behavior unchanged: still uses mimo-v2-omni for vision,
mimo-v2-pro for text (check_nous_free_tier() branch).

E2E verified:
  paid vision → google/gemini-3-flash-preview
  free vision → xiaomi/mimo-v2-omni
  paid text   → google/gemini-3-flash-preview
  free text   → xiaomi/mimo-v2-pro
---
 agent/auxiliary_client.py | 14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/agent/auxiliary_client.py b/agent/auxiliary_client.py
index 2854873b..5195b095 100644
--- a/agent/auxiliary_client.py
+++ b/agent/auxiliary_client.py
@@ -152,7 +152,6 @@ _API_KEY_PROVIDER_AUX_MODELS: Dict[str, str] = {
 _PROVIDER_VISION_MODELS: Dict[str, str] = {
     "xiaomi": "mimo-v2-omni",
     "zai": "glm-5v-turbo",
-    "nous": "xiaomi/mimo-v2-omni",
 }
 
 # OpenRouter app attribution headers
@@ -934,23 +933,16 @@ def _try_nous(vision: bool = False) -> Tuple[Optional[OpenAI], Optional[str]]:
         model = _NOUS_MODEL
     # Free-tier users can't use paid auxiliary models — use the free
     # models instead: mimo-v2-omni for vision, mimo-v2-pro for text tasks.
-    # For vision tasks, always use mimo-v2-omni regardless of tier —
-    # Nous inference API does not support image inputs for gemini models.
+    # Paid accounts keep their tier-appropriate models: gemini-3-flash-preview
+    # for both text and vision tasks.
     try:
         from hermes_cli.models import check_nous_free_tier
         if check_nous_free_tier():
             model = _NOUS_FREE_TIER_VISION_MODEL if vision else _NOUS_FREE_TIER_AUX_MODEL
             logger.debug("Free-tier Nous account — using %s for auxiliary/%s",
                          model, "vision" if vision else "text")
-        elif vision:
-            model = _NOUS_FREE_TIER_VISION_MODEL
-            logger.debug("Nous vision task — using %s (gemini models lack "
-                         "image support on Nous inference API)", model)
     except Exception:
-        if vision:
-            model = _NOUS_FREE_TIER_VISION_MODEL
-    if vision:
-        logger.debug("Nous vision: final model = %s", model)
+        pass
     if runtime is not None:
         api_key, base_url = runtime
     else: