fix(cli): honor user-defined providers via chat --provider and -m <alias>

Three related issues prevented user-defined providers in `providers:` and
`model_aliases:` from being reachable through standard CLI flags. Requests
silently routed to the configured `model.base_url` instead of the user-
intended endpoint.

* hermes_cli/model_switch.py — root cause of the silent misrouting:
  `_ensure_direct_aliases()` rebound `DIRECT_ALIASES` to a freshly-loaded
  dict, leaving every `from hermes_cli.model_switch import DIRECT_ALIASES`
  caller stuck on the stale empty original. Switched to `.update()` so
  module attribute references stay valid.

* hermes_cli/main.py — chat subcommand `--provider` had `choices=[...]`
  hardcoded to built-in providers, rejecting valid keys from user
  `providers:` config. Dropped the choices list; runtime resolution
  validates correctly downstream.

* hermes_cli/oneshot.py — `-m <alias>` only resolved the model name; the
  alias's base_url was never propagated. Now consults `DIRECT_ALIASES`
  before falling through to `detect_provider_for_model`, and threads the
  alias's base_url to `resolve_runtime_provider(explicit_base_url=...)`.

* hermes_cli/runtime_provider.py — `_resolve_named_custom_runtime` now
  honors `(provider="custom", explicit_base_url=...)` so a base_url
  propagated from a direct-alias resolution actually builds a runtime
  instead of falling through to provider-registry handlers that don't
  know about ad-hoc local endpoints.

Verified: `hermes chat --provider <user-key> -m <model> -q "..."` and
`hermes -m <user-alias> -z "..."` both route to the user-intended
endpoint, observable via the target server's request log.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
westers
2026-04-28 01:47:20 -07:00
committed by Teknium
co-authored by Claude Opus 4.7
parent afb9588298
commit 632ddf2a0a
4 changed files with 65 additions and 39 deletions
+28 -11
View File
@@ -128,27 +128,44 @@ def _run_agent(
# the user's configured default provider, which may not host the model
# the caller just asked for.
effective_provider = (provider or "").strip() or None
explicit_base_url_from_alias: Optional[str] = None
if effective_provider is None and (model or env_model):
# Only auto-detect when the model was explicitly requested via arg or
# env var (not when it came from config — that's the "use my defaults"
# path and the configured provider is already correct).
explicit_model = (model or "").strip() or env_model
if explicit_model:
cfg_provider = ""
if isinstance(model_cfg, dict):
cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
current_provider = (
cfg_provider
or os.getenv("HERMES_INFERENCE_PROVIDER", "").strip().lower()
or "auto"
)
detected = detect_provider_for_model(explicit_model, current_provider)
if detected:
effective_provider, effective_model = detected
# First check DIRECT_ALIASES populated from config.yaml `model_aliases:`.
# These map a user-defined alias to (model, provider, base_url) for
# endpoints not in any catalog (local servers, custom proxies, etc.).
try:
from hermes_cli import model_switch as _ms
_ms._ensure_direct_aliases()
direct = _ms.DIRECT_ALIASES.get(explicit_model.strip().lower())
except Exception:
direct = None
if direct is not None:
effective_model = direct.model
effective_provider = direct.provider
if direct.base_url:
explicit_base_url_from_alias = direct.base_url.rstrip("/")
else:
cfg_provider = ""
if isinstance(model_cfg, dict):
cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
current_provider = (
cfg_provider
or os.getenv("HERMES_INFERENCE_PROVIDER", "").strip().lower()
or "auto"
)
detected = detect_provider_for_model(explicit_model, current_provider)
if detected:
effective_provider, effective_model = detected
runtime = resolve_runtime_provider(
requested=effective_provider,
target_model=effective_model or None,
explicit_base_url=explicit_base_url_from_alias,
)
# Pull in whatever toolsets the user has enabled for "cli".