molecule-ai/hermes-agent
35
0
Fork 0
Code Issues 2 Pull Requests 4 Actions 9 Packages Projects Releases Wiki Activity

fix(vision): restore tier-aware Nous vision model selection (#13703)

Browse Source 
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
This commit is contained in:
Teknium 2026-04-21 14:43:55 -07:00 committed by GitHub
parent 7ba9c22cde
commit 52cbceea44
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
agent/auxiliary_client.py
View File

@ -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: