fix: model fallback — stale model on Nous login + connection error fallback (#6554)

Two bugs in the model fallback system:

1. Nous login leaves stale model in config (provider=nous, model=opus
   from previous OpenRouter setup). Fixed by deferring the config.yaml
   provider write until AFTER model selection completes, and passing the
   selected model atomically via _update_config_for_provider's
   default_model parameter. Previously, _update_config_for_provider was
   called before model selection — if selection failed (free tier, no
   models, exception), config stayed as nous+opus permanently.

2. Codex/stale providers in auxiliary fallback can't connect but block
   the auto-detection chain. Added _is_connection_error() detection
   (APIConnectionError, APITimeoutError, DNS failures, connection
   refused) alongside the existing _is_payment_error() check in
   call_llm(). When a provider endpoint is unreachable, the system now
   falls back to the next available provider instead of crashing.

agent/auxiliary_client.py

@@ -1047,6 +1047,32 @@ def _is_payment_error(exc: Exception) -> bool:
     return False
 
 
+def _is_connection_error(exc: Exception) -> bool:
+    """Detect connection/network errors that warrant provider fallback.
+
+    Returns True for errors indicating the provider endpoint is unreachable
+    (DNS failure, connection refused, TLS errors, timeouts).  These are
+    distinct from API errors (4xx/5xx) which indicate the provider IS
+    reachable but returned an error.
+    """
+    from openai import APIConnectionError, APITimeoutError
+
+    if isinstance(exc, (APIConnectionError, APITimeoutError)):
+        return True
+    # urllib3 / httpx / httpcore connection errors
+    err_type = type(exc).__name__
+    if any(kw in err_type for kw in ("Connection", "Timeout", "DNS", "SSL")):
+        return True
+    err_lower = str(exc).lower()
+    if any(kw in err_lower for kw in (
+        "connection refused", "name or service not known",
+        "no route to host", "network is unreachable",
+        "timed out", "connection reset",
+    )):
+        return True
+    return False
+
+
 def _try_payment_fallback(
     failed_provider: str,
     task: str = None,
@@ -2093,7 +2119,18 @@ def call_llm(
         # try alternative providers instead of giving up.  This handles the
         # common case where a user runs out of OpenRouter credits but has
         # Codex OAuth or another provider available.
-        if _is_payment_error(first_err):
+        #
+        # ── Connection error fallback ────────────────────────────────
+        # When a provider endpoint is unreachable (DNS failure, connection
+        # refused, timeout), try alternative providers.  This handles stale
+        # Codex/OAuth tokens that authenticate but whose endpoint is down,
+        # and providers the user never configured that got picked up by
+        # the auto-detection chain.
+        should_fallback = _is_payment_error(first_err) or _is_connection_error(first_err)
+        if should_fallback:
+            reason = "payment error" if _is_payment_error(first_err) else "connection error"
+            logger.info("Auxiliary %s: %s on %s (%s), trying fallback",
+                        task or "call", reason, resolved_provider, first_err)
             fb_client, fb_model, fb_label = _try_payment_fallback(
                 resolved_provider, task)
             if fb_client is not None:

hermes_cli/auth.py

@@ -3017,12 +3017,15 @@ def _login_nous(args, pconfig: ProviderConfig) -> None:
             _save_provider_state(auth_store, "nous", auth_state)
             saved_to = _save_auth_store(auth_store)
 
-        config_path = _update_config_for_provider("nous", inference_base_url)
         print()
         print("Login successful!")
         print(f"  Auth state: {saved_to}")
-        print(f"  Config updated: {config_path} (model.provider=nous)")
 
+        # Resolve model BEFORE writing provider to config.yaml so we never
+        # leave the config in a half-updated state (provider=nous but model
+        # still set to the previous provider's model, e.g. opus from
+        # OpenRouter).  The auth.json active_provider was already set above.
+        selected_model = None
         try:
             runtime_key = auth_state.get("agent_key") or auth_state.get("access_token")
             if not isinstance(runtime_key, str) or not runtime_key:
@@ -3056,9 +3059,6 @@ def _login_nous(args, pconfig: ProviderConfig) -> None:
                     unavailable_models=unavailable_models,
                     portal_url=_portal,
                 )
-                if selected_model:
-                    _save_model_choice(selected_model)
-                    print(f"Default model set to: {selected_model}")
             elif unavailable_models:
                 _url = (_portal or DEFAULT_NOUS_PORTAL_URL).rstrip("/")
                 print("No free models currently available.")
@@ -3070,6 +3070,15 @@ def _login_nous(args, pconfig: ProviderConfig) -> None:
             print()
             print(f"Login succeeded, but could not fetch available models. Reason: {message}")
 
+        # Write provider + model atomically so config is never mismatched.
+        config_path = _update_config_for_provider(
+            "nous", inference_base_url, default_model=selected_model,
+        )
+        if selected_model:
+            _save_model_choice(selected_model)
+            print(f"Default model set to: {selected_model}")
+        print(f"  Config updated: {config_path} (model.provider=nous)")
+
     except KeyboardInterrupt:
         print("\nLogin cancelled.")
         raise SystemExit(130)