APEX/BrowserUse_and_ComputerUse_skills
5
0
Fork 0
Code Issues 6 Pull requests 1 Projects 1 Releases Packages Wiki Activity Actions

fix(setup): prevent OpenRouter model list fallback for Nous provider

Browse source 
When `fetch_nous_models()` fails silently during setup, the model
selection falls through to the OpenRouter static list. Users then pick
models in OpenRouter format (e.g. `anthropic/claude-opus-4.6`) which
the Nous inference API rejects with a 400 "missing model" error.

Add an explicit `elif selected_provider == "nous"` branch that prompts
for manual model entry instead of falling through to the generic
OpenRouter fallback.
This commit is contained in:
PercyDikec 2026-03-07 07:16:22 +03:00
parent ce28f847ce
commit 8bf28e1441
No known key found for this signature in database
GPG key ID: 8838A85B2422556A
1 changed files with 9 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

9
hermes_cli/setup.py
View file

@ -1050,6 +1050,15 @@ def run_setup_wizard(args):
config['model'] = custom
save_env_value("LLM_MODEL", custom)
# else: keep current
elif selected_provider == "nous":
# Nous login succeeded but model fetch failed — prompt manually
# instead of falling through to the OpenRouter static list.
print_warning("Could not fetch available models from Nous Portal.")
print_info("Enter a Nous model name manually (e.g., claude-opus-4-6).")
custom = prompt(f" Model name (Enter to keep '{current_model}')")
if custom:
config['model'] = custom
save_env_value("LLM_MODEL", custom)
elif selected_provider == "openai-codex":
from hermes_cli.codex_models import get_codex_model_ids
# Try to get the access token for live model discovery