mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(cli): hint about /v1 suffix when configuring local model endpoints

Browse source 
When a user enters a local model server URL (Ollama, vLLM, llama.cpp)
without a /v1 suffix during 'hermes model' custom endpoint setup,
prompt them to add it. Most OpenAI-compatible local servers require
/v1 in the base URL for chat completions to work.
This commit is contained in:
Teknium 2026-04-15 22:36:35 -07:00 • committed by Teknium
parent 8798b069d3
commit 5c397876b9
2 changed files with 22 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

21
hermes_cli/main.py
View file

@ -1568,6 +1568,27 @@ def _model_flow_custom(config):
effective_key = api_key or current_key
# Hint: most local model servers (Ollama, vLLM, llama.cpp) require /v1
# in the base URL for OpenAI-compatible chat completions. Prompt the
# user if the URL looks like a local server without /v1.
_url_lower = effective_url.rstrip("/").lower()
_looks_local = any(h in _url_lower for h in ("localhost", "127.0.0.1", "0.0.0.0", ":11434", ":8080", ":5000"))
if _looks_local and not _url_lower.endswith("/v1"):
print()
print(f" Hint: Did you mean to add /v1 at the end?")
print(f" Most local model servers (Ollama, vLLM, llama.cpp) require it.")
print(f" e.g. {effective_url.rstrip('/')}/v1")
try:
_add_v1 = input(" Add /v1? [Y/n]: ").strip().lower()
except (KeyboardInterrupt, EOFError):
_add_v1 = "n"
if _add_v1 in ("", "y", "yes"):
effective_url = effective_url.rstrip("/") + "/v1"
if base_url:
base_url = effective_url
print(f" Updated URL: {effective_url}")
print()
from hermes_cli.models import probe_api_models
probe = probe_api_models(effective_key, effective_url)