fix(context): honor model.context_length for Ollama num_ctx and all display paths

When a user sets model.context_length in config.yaml, the value was only
used for Hermes' internal compression decisions (context_compressor) but
NOT for Ollama's num_ctx parameter. Ollama auto-detects context from GGUF
metadata (often 256K+) and allocates that much VRAM regardless of the
user's config — causing OOM on smaller GPUs like the P100 (16GB).

Root cause: two separate context values existed independently:
  - context_compressor.context_length = config value (e.g. 65536) ✓
  - _ollama_num_ctx = GGUF metadata value (e.g. 256000) ✗ ignored config

Changes:

1. Cap Ollama num_ctx to config context_length (run_agent.py)
   When model.context_length is explicitly set and no explicit
   ollama_num_ctx override exists, cap the auto-detected GGUF value
   to the user's context_length. This is the core fix — it prevents
   Ollama from allocating more VRAM than the user budgeted.

2. Pass config_context_length through all secondary call sites
   Several paths called get_model_context_length() without the config
   override, falling through to the 256K default fallback:
   - cli.py: @-reference expansion and /model switch display
   - gateway/run.py: @-reference expansion and /model switch display
   - tui_gateway/server.py: @-reference expansion
   - hermes_cli/model_switch.py: resolve_display_context_length()

3. Normalize root-level context_length in config (hermes_cli/config.py)
   _normalize_root_model_keys() now migrates root-level context_length
   into the model section, matching existing behavior for provider and
   base_url. Users who wrote `context_length: 65536` at the YAML root
   instead of under `model:` had it silently ignored.

4. Fix misleading comments (agent/model_metadata.py)
   DEFAULT_FALLBACK_CONTEXT is 256K (CONTEXT_PROBE_TIERS[0]), not 128K
   as two comments stated.

Tests: 3 new tests for root-level context_length normalization.
All existing context_length tests pass (96 tests).

tests/cli/test_cli_init.py

@@ -354,6 +354,49 @@ class TestRootLevelProviderOverride:
         assert result["model"]["provider"] == "correct-provider"
         assert "provider" not in result  # root key still cleaned up
 
+    def test_normalize_root_context_length_migrates_to_model(self):
+        """Root-level context_length is migrated into the model section."""
+        from hermes_cli.config import _normalize_root_model_keys
+
+        config = {
+            "context_length": 128000,
+            "model": {
+                "default": "my-model",
+            },
+        }
+        result = _normalize_root_model_keys(config)
+        assert result["model"]["context_length"] == 128000
+        assert "context_length" not in result  # root key cleaned up
+
+    def test_normalize_root_context_length_does_not_override_existing(self):
+        """Existing model.context_length is not overridden by root-level key."""
+        from hermes_cli.config import _normalize_root_model_keys
+
+        config = {
+            "context_length": 256000,
+            "model": {
+                "default": "my-model",
+                "context_length": 128000,
+            },
+        }
+        result = _normalize_root_model_keys(config)
+        assert result["model"]["context_length"] == 128000  # preserved
+        assert "context_length" not in result  # root key still cleaned up
+
+    def test_normalize_root_context_length_with_string_model(self):
+        """Root-level context_length is migrated even when model is a string."""
+        from hermes_cli.config import _normalize_root_model_keys
+
+        config = {
+            "context_length": 128000,
+            "model": "my-model",
+        }
+        result = _normalize_root_model_keys(config)
+        assert isinstance(result["model"], dict)
+        assert result["model"]["default"] == "my-model"
+        assert result["model"]["context_length"] == 128000
+        assert "context_length" not in result
+
 
 class TestProviderResolution:
     def test_api_key_is_string_or_none(self):