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).

cli.py

@@ -5328,6 +5328,7 @@ class HermesCLI:
                 base_url=result.base_url or self.base_url or "",
                 api_key=result.api_key or self.api_key or "",
                 model_info=mi,
+                config_context_length=getattr(self.agent, "_config_context_length", None) if self.agent else None,
             )
             if ctx:
                 _cprint(f"    Context: {ctx:,} tokens")
@@ -5554,6 +5555,7 @@ class HermesCLI:
             base_url=result.base_url or self.base_url or "",
             api_key=result.api_key or self.api_key or "",
             model_info=mi,
+            config_context_length=getattr(self.agent, "_config_context_length", None) if self.agent else None,
         )
         if ctx:
             _cprint(f"    Context: {ctx:,} tokens")
@@ -8728,7 +8730,8 @@ class HermesCLI:
                 from agent.context_references import preprocess_context_references
                 from agent.model_metadata import get_model_context_length
                 _ctx_len = get_model_context_length(
-                    self.model, base_url=self.base_url or "", api_key=self.api_key or "")
+                    self.model, base_url=self.base_url or "", api_key=self.api_key or "",
+                    config_context_length=getattr(self.agent, "_config_context_length", None) if self.agent else None)
                 _ctx_result = preprocess_context_references(
                     message, cwd=os.getcwd(), context_length=_ctx_len)
                 if _ctx_result.expanded or _ctx_result.blocked: