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 2026-04-27 21:15:12 -05:00 committed by Teknium
parent afb9588298
commit 632ddf2a0a
4 changed files with 65 additions and 39 deletions

View file

@ -7903,32 +7903,12 @@ For more help on a command:
)
chat_parser.add_argument(
"--provider",
choices=[
"auto",
"openrouter",
"nous",
"openai-codex",
"copilot-acp",
"copilot",
"anthropic",
"gemini",
"xai",
"ollama-cloud",
"huggingface",
"zai",
"kimi-coding",
"kimi-coding-cn",
"stepfun",
"minimax",
"minimax-cn",
"kilocode",
"xiaomi",
"arcee",
"gmi",
"nvidia",
],
# No `choices=` here: user-defined providers from config.yaml `providers:`
# are also valid values, and runtime resolution (resolve_runtime_provider)
# handles validation/error reporting consistently with the top-level
# `--provider` flag.
default=None,
help="Inference provider (default: auto)",
help="Inference provider (default: auto). Built-in or a user-defined name from `providers:` in config.yaml.",
)
chat_parser.add_argument(
"-v", "--verbose", action="store_true", help="Verbose output"