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

refactor: remove LLM_MODEL env var dependency — config.yaml is sole source of truth

Browse source 
Model selection now comes exclusively from config.yaml (set via
'hermes model' or 'hermes setup'). The LLM_MODEL env var is no longer
read or written anywhere in production code.

Why: env vars are per-process/per-user and would conflict in
multi-agent or multi-tenant setups. Config.yaml is file-based and
can be scoped per-user or eventually per-session.

Changes:
- cli.py: Read model from CLI_CONFIG only, not LLM_MODEL/OPENAI_MODEL
- hermes_cli/auth.py: _save_model_choice() no longer writes LLM_MODEL
  to .env
- hermes_cli/setup.py: Remove 12 save_env_value('LLM_MODEL', ...)
  calls from all provider setup flows
- gateway/run.py: Remove LLM_MODEL fallback (HERMES_MODEL still works
  for gateway process runtime)
- cron/scheduler.py: Same
- agent/auxiliary_client.py: Remove LLM_MODEL from custom endpoint
  model detection
This commit is contained in:
teknium1 2026-03-11 22:04:42 -07:00
parent a29801286f
commit 9302690e1b
7 changed files with 36 additions and 32 deletions
Download patch file Download diff file Expand all files Collapse all files

2
agent/auxiliary_client.py
View file

@ -443,7 +443,7 @@ def _try_custom_endpoint() -> Tuple[Optional[OpenAI], Optional[str]]:
custom_key = os.getenv("OPENAI_API_KEY")
if not custom_base or not custom_key:
return None, None
model = os.getenv("OPENAI_MODEL") or os.getenv("LLM_MODEL") or "gpt-4o-mini"
model = os.getenv("OPENAI_MODEL") or "gpt-4o-mini"
logger.debug("Auxiliary client: custom endpoint (%s)", model)
return OpenAI(api_key=custom_key, base_url=custom_base), model

11
cli.py
View file

@ -1129,12 +1129,17 @@ class HermesCLI:
self.verbose = verbose if verbose is not None else (self.tool_progress_mode == "verbose")
# Configuration - priority: CLI args > env vars > config file
# Model can come from: CLI arg, LLM_MODEL env, OPENAI_MODEL env (custom endpoint), or config
self.model = model or os.getenv("LLM_MODEL") or os.getenv("OPENAI_MODEL") or CLI_CONFIG["model"]["default"]
# Model comes from: CLI arg or config.yaml (single source of truth).
# LLM_MODEL/OPENAI_MODEL env vars are NOT checked — config.yaml is
# authoritative. This avoids conflicts in multi-agent setups where
# env vars would stomp each other.
_model_config = CLI_CONFIG.get("model", {})
_config_model = _model_config.get("default", "") if isinstance(_model_config, dict) else (_model_config or "")
self.model = model or _config_model or "anthropic/claude-opus-4.6"
# Track whether model was explicitly chosen by the user or fell back
# to the global default. Provider-specific normalisation may override
# the default silently but should warn when overriding an explicit choice.
self._model_is_default = not (model or os.getenv("LLM_MODEL") or os.getenv("OPENAI_MODEL"))
self._model_is_default = not model
self._explicit_api_key = api_key
self._explicit_base_url = base_url

2
cron/scheduler.py
View file

@ -180,7 +180,7 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
except UnicodeDecodeError:
load_dotenv(str(_hermes_home / ".env"), override=True, encoding="latin-1")
model = os.getenv("HERMES_MODEL") or os.getenv("LLM_MODEL") or "anthropic/claude-opus-4.6"
model = os.getenv("HERMES_MODEL") or "anthropic/claude-opus-4.6"
# Load config.yaml for model, reasoning, prefill, toolsets, provider routing
_cfg = {}

6
gateway/run.py
View file

@ -1544,7 +1544,7 @@ class GatewayRunner:
config_path = _hermes_home / 'config.yaml'
# Resolve current model and provider from config
current = os.getenv("HERMES_MODEL") or os.getenv("LLM_MODEL") or "anthropic/claude-opus-4.6"
current = os.getenv("HERMES_MODEL") or "anthropic/claude-opus-4.6"
current_provider = "openrouter"
try:
if config_path.exists():
@ -1999,7 +1999,7 @@ class GatewayRunner:
return
# Read model from config (same as _run_agent)
model = os.getenv("HERMES_MODEL") or os.getenv("LLM_MODEL") or "anthropic/claude-opus-4.6"
model = os.getenv("HERMES_MODEL") or "anthropic/claude-opus-4.6"
try:
import yaml as _y
_cfg_path = _hermes_home / "config.yaml"
@ -3093,7 +3093,7 @@ class GatewayRunner:
except Exception:
pass
model = os.getenv("HERMES_MODEL") or os.getenv("LLM_MODEL") or "anthropic/claude-opus-4.6"
model = os.getenv("HERMES_MODEL") or "anthropic/claude-opus-4.6"
try:
import yaml as _y

9
hermes_cli/auth.py
View file

@ -1671,8 +1671,12 @@ def _prompt_model_selection(model_ids: List[str], current_model: str = "") -> Op
def _save_model_choice(model_id: str) -> None:
"""Save the selected model to config.yaml and .env."""
from hermes_cli.config import save_config, load_config, save_env_value
"""Save the selected model to config.yaml (single source of truth).
The model is stored in config.yaml only — NOT in .env. This avoids
conflicts in multi-agent setups where env vars would stomp each other.
"""
from hermes_cli.config import save_config, load_config
config = load_config()
# Always use dict format so provider/base_url can be stored alongside
@ -1681,7 +1685,6 @@ def _save_model_choice(model_id: str) -> None:
else:
config["model"] = {"default": model_id}
save_config(config)
save_env_value("LLM_MODEL", model_id)
def login_command(args) -> None:

12
hermes_cli/setup.py
View file

@ -681,7 +681,6 @@ def setup_model_provider(config: dict):
save_env_value("OPENAI_API_KEY", api_key)
if model_name:
config['model'] = model_name
save_env_value("LLM_MODEL", model_name)
# Save provider and base_url to config.yaml so the gateway and CLI
# both resolve the correct provider without relying on env-var heuristics.
@ -913,7 +912,6 @@ def setup_model_provider(config: dict):
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
codex_models = get_codex_model_ids()
@ -927,12 +925,10 @@ def setup_model_provider(config: dict):
model_idx = prompt_choice("Select default model:", model_choices, default_codex)
if model_idx < len(codex_models):
config['model'] = codex_models[model_idx]
save_env_value("LLM_MODEL", codex_models[model_idx])
elif model_idx == len(codex_models):
custom = prompt("Enter model name")
if custom:
config['model'] = custom
save_env_value("LLM_MODEL", custom)
_update_config_for_provider("openai-codex", DEFAULT_CODEX_BASE_URL)
elif selected_provider == "zai":
# Coding Plan endpoints don't have GLM-5
@ -950,12 +946,10 @@ def setup_model_provider(config: dict):
if model_idx < len(zai_models):
config['model'] = zai_models[model_idx]
save_env_value("LLM_MODEL", zai_models[model_idx])
elif model_idx == len(zai_models):
custom = prompt("Enter model name")
if custom:
config['model'] = custom
save_env_value("LLM_MODEL", custom)
# else: keep current
elif selected_provider == "kimi-coding":
kimi_models = ["kimi-k2.5", "kimi-k2-thinking", "kimi-k2-turbo-preview"]
@ -968,12 +962,10 @@ def setup_model_provider(config: dict):
if model_idx < len(kimi_models):
config['model'] = kimi_models[model_idx]
save_env_value("LLM_MODEL", kimi_models[model_idx])
elif model_idx == len(kimi_models):
custom = prompt("Enter model name")
if custom:
config['model'] = custom
save_env_value("LLM_MODEL", custom)
# else: keep current
elif selected_provider in ("minimax", "minimax-cn"):
minimax_models = ["MiniMax-M2.5", "MiniMax-M2.5-highspeed", "MiniMax-M2.1"]
@ -986,12 +978,10 @@ def setup_model_provider(config: dict):
if model_idx < len(minimax_models):
config['model'] = minimax_models[model_idx]
save_env_value("LLM_MODEL", minimax_models[model_idx])
elif model_idx == len(minimax_models):
custom = prompt("Enter model name")
if custom:
config['model'] = custom
save_env_value("LLM_MODEL", custom)
# else: keep current
else:
# Static list for OpenRouter / fallback (from canonical list)
@ -1008,12 +998,10 @@ def setup_model_provider(config: dict):
if model_idx < len(ids):
config['model'] = ids[model_idx]
save_env_value("LLM_MODEL", ids[model_idx])
elif model_idx == len(ids): # Custom
custom = prompt("Enter model name (e.g., anthropic/claude-opus-4.6)")
if custom:
config['model'] = custom
save_env_value("LLM_MODEL", custom)
# else: Keep current
_final_model = config.get('model', '')

26
tests/test_cli_provider_resolution.py
View file

@ -197,21 +197,28 @@ def test_codex_provider_replaces_incompatible_default_model(monkeypatch):
assert shell.model == "gpt-5.2-codex"
def test_codex_provider_trusts_explicit_envvar_model(monkeypatch):
"""When the user explicitly sets LLM_MODEL, we trust their choice and
let the API be the judge — even if it's a non-OpenAI model. Only
provider prefixes are stripped; the bare model passes through."""
def test_codex_provider_uses_config_model(monkeypatch):
"""Model comes from config.yaml, not LLM_MODEL env var.
Config.yaml is the single source of truth to avoid multi-agent conflicts."""
cli = _import_cli()
monkeypatch.setenv("LLM_MODEL", "claude-opus-4-6")
# LLM_MODEL env var should be IGNORED (even if set)
monkeypatch.setenv("LLM_MODEL", "should-be-ignored")
monkeypatch.delenv("OPENAI_MODEL", raising=False)
# Set model via config
monkeypatch.setitem(cli.CLI_CONFIG, "model", {
"default": "gpt-5.2-codex",
"provider": "openai-codex",
"base_url": "https://chatgpt.com/backend-api/codex",
})
def _runtime_resolve(**kwargs):
return {
"provider": "openai-codex",
"api_mode": "codex_responses",
"base_url": "https://chatgpt.com/backend-api/codex",
"api_key": "test-key",
"api_key": "fake-codex-token",
"source": "env/config",
}
@ -220,11 +227,12 @@ def test_codex_provider_trusts_explicit_envvar_model(monkeypatch):
shell = cli.HermesCLI(compact=True, max_turns=1)
assert shell._model_is_default is False
assert shell._ensure_runtime_credentials() is True
assert shell.provider == "openai-codex"
# User explicitly chose this model — it passes through untouched
assert shell.model == "claude-opus-4-6"
# Model from config (may be normalized by codex provider logic)
assert "codex" in shell.model.lower()
# LLM_MODEL env var is NOT used
assert shell.model != "should-be-ignored"
def test_codex_provider_preserves_explicit_codex_model(monkeypatch):