fix: follow-up for salvaged PR #17061

- Remove dead _lmstudio_loaded_context attribute from run_agent.py (set
  but never read — the loaded context is pushed to context_compressor.update_model
  which is the actual consumer)
- Cache empty reasoning options with 60s TTL to avoid per-turn HTTP probe
  for non-reasoning LM Studio models. Non-empty results cached permanently.
- Extract _lmstudio_server_root(), _lmstudio_request_headers(), and
  _lmstudio_fetch_raw_models() shared helpers in models.py — eliminates
  URL-strip + auth-header + HTTP-call duplication across probe_lmstudio_models,
  ensure_lmstudio_model_loaded, and lmstudio_model_reasoning_options
- Revert runtime_provider.py base_url precedence change: preserve the
  established contract (saved config.base_url > env var > default) for all
  api_key providers
- Remove unnecessary config version bump 22→23
- Fix TUI test: relax target_model assertion to avoid module-cache flake
- AUTHOR_MAP: added rugved@lmstudio.ai → rugvedS07

hermes_cli/runtime_provider.py

@@ -1245,20 +1245,14 @@ def resolve_runtime_provider(
     if pconfig and pconfig.auth_type == "api_key":
         creds = resolve_api_key_provider_credentials(provider)
         # Honour model.base_url from config.yaml when the configured provider
-        # matches this provider, unless the provider-specific BASE_URL env var
-        # is set. That keeps temporary env overrides (e.g. LM_BASE_URL) in sync
-        # with picker-time probing while still preserving saved config URLs when
-        # no override is present.
+        # matches this provider — mirrors the Anthropic path above.  Without
+        # this, users who set model.base_url to e.g. api.minimaxi.com/anthropic
+        # (China endpoint) still get the hardcoded api.minimax.io default (#6039).
         cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
         cfg_base_url = ""
         if cfg_provider == provider:
             cfg_base_url = (model_cfg.get("base_url") or "").strip().rstrip("/")
-        env_base_url = ""
-        if pconfig.base_url_env_var:
-            env_base_url = os.getenv(pconfig.base_url_env_var, "").strip().rstrip("/")
-        base_url = creds.get("base_url", "").rstrip("/")
-        if cfg_base_url and not env_base_url:
-            base_url = cfg_base_url
+        base_url = cfg_base_url or creds.get("base_url", "").rstrip("/")
         api_mode = "chat_completions"
         if provider == "copilot":
             api_mode = _copilot_runtime_api_mode(model_cfg, creds.get("api_key", ""))