feat(aux): use Portal /api/nous/recommended-models for auxiliary models

Wire the auxiliary client (compaction, vision, session search, web extract)
to the Nous Portal's curated recommended-models endpoint when running on
Nous Portal, with a TTL-cached fetch that mirrors how we pull /models for
pricing.

hermes_cli/models.py
  - fetch_nous_recommended_models(portal_base_url, force_refresh=False)
    10-minute TTL cache, keyed per portal URL (staging vs prod don't
    collide).  Public endpoint, no auth required.  Returns {} on any
    failure so callers always get a dict.
  - get_nous_recommended_aux_model(vision, free_tier=None, ...)
    Tier-aware pick from the payload:
      - Paid tier → paidRecommended{Vision,Compaction}Model, falling back
        to freeRecommended* when the paid field is null (common during
        staged rollouts of new paid models).
      - Free tier → freeRecommended* only, never leaks paid models.
    When free_tier is None, auto-detects via the existing
    check_nous_free_tier() helper (already cached 3 min against
    /api/oauth/account).  Detection errors default to paid so we never
    silently downgrade a paying user.

agent/auxiliary_client.py — _try_nous()
  - Replaces the hardcoded xiaomi/mimo free-tier branch with a single call
    to get_nous_recommended_aux_model(vision=vision).
  - Falls back to _NOUS_MODEL (google/gemini-3-flash-preview) when the
    Portal is unreachable or returns a null recommendation.
  - The Portal is now the source of truth for aux model selection; the
    xiaomi allowlist we used to carry is effectively dead.

Tests (15 new)
  - tests/hermes_cli/test_models.py::TestNousRecommendedModels
    Fetch caching, per-portal keying, network failure, force_refresh;
    paid-prefers-paid, paid-falls-to-free, free-never-leaks-paid,
    auto-detect, detection-error → paid default, null/blank modelName
    handling.
  - tests/agent/test_auxiliary_client.py::TestNousAuxiliaryRefresh
    _try_nous honors Portal recommendation for text + vision, falls
    back to google/gemini-3-flash-preview on None or exception.

Behavior won't visibly change today — both tier recommendations currently
point at google/gemini-3-flash-preview — but the moment the Portal ships
a better paid recommendation, subscribers pick it up within 10 minutes
without a Hermes release.

tests/agent/test_auxiliary_client.py

@@ -483,6 +483,7 @@ class TestNousAuxiliaryRefresh:
         with (
             patch("agent.auxiliary_client._read_nous_auth", return_value={"access_token": "stale-token"}),
             patch("agent.auxiliary_client._resolve_nous_runtime_api", return_value=("fresh-agent-key", fresh_base)),
+            patch("hermes_cli.models.get_nous_recommended_aux_model", return_value=None),
             patch("agent.auxiliary_client.OpenAI") as mock_openai,
         ):
             from agent.auxiliary_client import _try_nous
@@ -491,10 +492,60 @@ class TestNousAuxiliaryRefresh:
             client, model = _try_nous()
 
         assert client is not None
+        # No Portal recommendation → falls back to the hardcoded default.
         assert model == "google/gemini-3-flash-preview"
         assert mock_openai.call_args.kwargs["api_key"] == "fresh-agent-key"
         assert mock_openai.call_args.kwargs["base_url"] == fresh_base
 
+    def test_try_nous_uses_portal_recommendation_for_text(self):
+        """When the Portal recommends a compaction model, _try_nous honors it."""
+        fresh_base = "https://inference-api.nousresearch.com/v1"
+        with (
+            patch("agent.auxiliary_client._read_nous_auth", return_value={"access_token": "***"}),
+            patch("agent.auxiliary_client._resolve_nous_runtime_api", return_value=("fresh-agent-key", fresh_base)),
+            patch("hermes_cli.models.get_nous_recommended_aux_model", return_value="minimax/minimax-m2.7") as mock_rec,
+            patch("agent.auxiliary_client.OpenAI") as mock_openai,
+        ):
+            from agent.auxiliary_client import _try_nous
+
+            mock_openai.return_value = MagicMock()
+            client, model = _try_nous(vision=False)
+
+        assert client is not None
+        assert model == "minimax/minimax-m2.7"
+        assert mock_rec.call_args.kwargs["vision"] is False
+
+    def test_try_nous_uses_portal_recommendation_for_vision(self):
+        """Vision tasks should ask for the vision-specific recommendation."""
+        fresh_base = "https://inference-api.nousresearch.com/v1"
+        with (
+            patch("agent.auxiliary_client._read_nous_auth", return_value={"access_token": "***"}),
+            patch("agent.auxiliary_client._resolve_nous_runtime_api", return_value=("fresh-agent-key", fresh_base)),
+            patch("hermes_cli.models.get_nous_recommended_aux_model", return_value="google/gemini-3-flash-preview") as mock_rec,
+            patch("agent.auxiliary_client.OpenAI"),
+        ):
+            from agent.auxiliary_client import _try_nous
+            client, model = _try_nous(vision=True)
+
+        assert client is not None
+        assert model == "google/gemini-3-flash-preview"
+        assert mock_rec.call_args.kwargs["vision"] is True
+
+    def test_try_nous_falls_back_when_recommendation_lookup_raises(self):
+        """If the Portal lookup throws, we must still return a usable model."""
+        fresh_base = "https://inference-api.nousresearch.com/v1"
+        with (
+            patch("agent.auxiliary_client._read_nous_auth", return_value={"access_token": "***"}),
+            patch("agent.auxiliary_client._resolve_nous_runtime_api", return_value=("fresh-agent-key", fresh_base)),
+            patch("hermes_cli.models.get_nous_recommended_aux_model", side_effect=RuntimeError("portal down")),
+            patch("agent.auxiliary_client.OpenAI"),
+        ):
+            from agent.auxiliary_client import _try_nous
+            client, model = _try_nous()
+
+        assert client is not None
+        assert model == "google/gemini-3-flash-preview"
+
     def test_call_llm_retries_nous_after_401(self):
         class _Auth401(Exception):
             status_code = 401