refactor: make config.yaml the single source of truth for endpoint URLs (#4165)

OPENAI_BASE_URL was written to .env AND config.yaml, creating a dual-source
confusion. Users (especially Docker) would see the URL in .env and assume
that's where all config lives, then wonder why LLM_MODEL in .env didn't work.

Changes:
- Remove all 27 save_env_value("OPENAI_BASE_URL", ...) calls across main.py,
  setup.py, and tools_config.py
- Remove OPENAI_BASE_URL env var reading from runtime_provider.py, cli.py,
  models.py, and gateway/run.py
- Remove LLM_MODEL/HERMES_MODEL env var reading from gateway/run.py and
  auxiliary_client.py — config.yaml model.default is authoritative
- Vision base URL now saved to config.yaml auxiliary.vision.base_url
  (both setup wizard and tools_config paths)
- Tests updated to set config values instead of env vars

Convention enforced: .env is for SECRETS only (API keys). All other
configuration (model names, base URLs, provider selection) lives
exclusively in config.yaml.
This commit is contained in:
Teknium
2026-03-30 22:02:53 -07:00
committed by GitHub
parent 4d7e3c7157
commit f890a94c12
11 changed files with 77 additions and 152 deletions

View File

@@ -7,7 +7,7 @@ the best available backend without duplicating fallback logic.
Resolution order for text tasks (auto mode):
1. OpenRouter (OPENROUTER_API_KEY)
2. Nous Portal (~/.hermes/auth.json active provider)
3. Custom endpoint (OPENAI_BASE_URL + OPENAI_API_KEY)
3. Custom endpoint (config.yaml model.base_url + OPENAI_API_KEY)
4. Codex OAuth (Responses API via chatgpt.com with gpt-5.3-codex,
wrapped to look like a chat.completions client)
5. Native Anthropic
@@ -584,15 +584,11 @@ def _try_nous() -> Tuple[Optional[OpenAI], Optional[str]]:
def _read_main_model() -> str:
"""Read the user's configured main model from config/env.
"""Read the user's configured main model from config.yaml.
Falls back through HERMES_MODEL → LLM_MODEL → config.yaml model.default
so the auxiliary client can use the same model as the main agent when no
dedicated auxiliary model is available.
config.yaml model.default is the single source of truth for the active
model. Environment variables are no longer consulted.
"""
from_env = os.getenv("OPENAI_MODEL") or os.getenv("HERMES_MODEL") or os.getenv("LLM_MODEL")
if from_env:
return from_env.strip()
try:
from hermes_cli.config import load_config
cfg = load_config()