fix: auto-detect local model name and context length for local servers

Cherry-picked from PR #2043 by sudoingX.

- Auto-detect model name from local server's /v1/models when only one
  model is loaded (no manual model name config needed)
- Add n_ctx_train and n_ctx to context length detection keys for llama.cpp
- Query llama.cpp /props endpoint for actual allocated context (not just
  training context from GGUF metadata)
- Strip .gguf suffix from display in banner and status bar
- _auto_detect_local_model() in runtime_provider.py for CLI init

Co-authored-by: sudo <sudoingx@users.noreply.github.com>

agent/model_metadata.py

@@ -136,6 +136,8 @@ _CONTEXT_LENGTH_KEYS = (
     "max_input_tokens",
     "max_sequence_length",
     "max_seq_len",
+    "n_ctx_train",
+    "n_ctx",
 )
 
 _MAX_COMPLETION_KEYS = (
@@ -342,6 +344,25 @@ def fetch_endpoint_model_metadata(
                     entry["pricing"] = pricing
                 _add_model_aliases(cache, model_id, entry)
 
+            # If this is a llama.cpp server, query /props for actual allocated context
+            is_llamacpp = any(
+                m.get("owned_by") == "llamacpp"
+                for m in payload.get("data", []) if isinstance(m, dict)
+            )
+            if is_llamacpp:
+                try:
+                    props_url = candidate.rstrip("/").replace("/v1", "") + "/props"
+                    props_resp = requests.get(props_url, headers=headers, timeout=5)
+                    if props_resp.ok:
+                        props = props_resp.json()
+                        gen_settings = props.get("default_generation_settings", {})
+                        n_ctx = gen_settings.get("n_ctx")
+                        model_alias = props.get("model_alias", "")
+                        if n_ctx and model_alias and model_alias in cache:
+                            cache[model_alias]["context_length"] = n_ctx
+                except Exception:
+                    pass
+
             _endpoint_model_metadata_cache[normalized] = cache
             _endpoint_model_metadata_cache_time[normalized] = time.time()
             return cache

cli.py

@@ -1046,6 +1046,14 @@ class HermesCLI:
         _config_model = _model_config.get("default", "") if isinstance(_model_config, dict) else (_model_config or "")
         _FALLBACK_MODEL = "anthropic/claude-opus-4.6"
         self.model = model or _config_model or _FALLBACK_MODEL
+        # Auto-detect model from local server if still on fallback
+        if self.model == _FALLBACK_MODEL:
+            _base_url = _model_config.get("base_url", "") if isinstance(_model_config, dict) else ""
+            if "localhost" in _base_url or "127.0.0.1" in _base_url:
+                from hermes_cli.runtime_provider import _auto_detect_local_model
+                _detected = _auto_detect_local_model(_base_url)
+                if _detected:
+                    self.model = _detected
         # Track whether model was explicitly chosen by the user or fell back
         # to the global default.  Provider-specific normalisation may override
         # the default silently but should warn when overriding an explicit choice.
@@ -1251,6 +1259,8 @@ class HermesCLI:
     def _get_status_bar_snapshot(self) -> Dict[str, Any]:
         model_name = self.model or "unknown"
         model_short = model_name.split("/")[-1] if "/" in model_name else model_name
+        if model_short.endswith(".gguf"):
+            model_short = model_short[:-5]
         if len(model_short) > 26:
             model_short = f"{model_short[:23]}..."
 

hermes_cli/banner.py

@@ -289,6 +289,8 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
         _hero = HERMES_CADUCEUS
     left_lines = ["", _hero, ""]
     model_short = model.split("/")[-1] if "/" in model else model
+    if model_short.endswith(".gguf"):
+        model_short = model_short[:-5]
     if len(model_short) > 28:
         model_short = model_short[:25] + "..."
     ctx_str = f" [dim {dim}]·[/] [dim {dim}]{_format_context_length(context_length)} context[/]" if context_length else ""

hermes_cli/runtime_provider.py

@@ -24,11 +24,41 @@ def _normalize_custom_provider_name(value: str) -> str:
     return value.strip().lower().replace(" ", "-")
 
 
+def _auto_detect_local_model(base_url: str) -> str:
+    """Query a local server for its model name when only one model is loaded."""
+    if not base_url:
+        return ""
+    try:
+        import requests
+        url = base_url.rstrip("/")
+        if not url.endswith("/v1"):
+            url += "/v1"
+        resp = requests.get(url + "/models", timeout=5)
+        if resp.ok:
+            models = resp.json().get("data", [])
+            if len(models) == 1:
+                model_id = models[0].get("id", "")
+                if model_id:
+                    return model_id
+    except Exception:
+        pass
+    return ""
+
+
 def _get_model_config() -> Dict[str, Any]:
     config = load_config()
     model_cfg = config.get("model")
     if isinstance(model_cfg, dict):
-        return dict(model_cfg)
+        cfg = dict(model_cfg)
+        default = cfg.get("default", "").strip()
+        base_url = cfg.get("base_url", "").strip()
+        is_local = "localhost" in base_url or "127.0.0.1" in base_url
+        is_fallback = not default or default == "anthropic/claude-opus-4.6"
+        if is_local and is_fallback and base_url:
+            detected = _auto_detect_local_model(base_url)
+            if detected:
+                cfg["default"] = detected
+        return cfg
     if isinstance(model_cfg, str) and model_cfg.strip():
         return {"default": model_cfg.strip()}
     return {}