fix(picker): remove max_models=50 cap in interactive model pickers

The interactive model pickers (Desktop REST API, TUI model.options, CLI
/model) were hard-capped at max_models=50, which truncated large provider
catalogs like Kilo Gateway (336 models) to just 50 entries. This made
most models undiscoverable via the picker search box.

Changes:
- Change build_models_payload() default from max_models=50 to None (unlimited)
- Change list_authenticated_providers() default from max_models=8 to None
- Change list_picker_providers() default from max_models=8 to None
- Fix all [:max_models] slicing to handle None as 'no limit'
- Remove max_models=50 from 5 interactive picker callers:
  * web_server.py: get_model_options (Desktop /api/model/options)
  * web_server.py: get_recommended_default_model
  * model_switch.py: prewarm_picker_cache_async
  * tui_gateway/server.py: model.options JSON-RPC
  * cli.py: HermesCLI model picker
- Telegram/Discord inline keyboard picker (gateway/slash_commands.py)
  still passes max_models=50 explicitly — unchanged behavior.

The total_models field was already in the response payload and is now
meaningful since models.length == total_models for interactive pickers.

Fixes #48279

cli.py

@@ -6971,7 +6971,7 @@ class HermesCLI(CLIAgentSetupMixin, CLICommandsMixin):
             try:
                 if ctx is None:
                     raise RuntimeError("inventory context unavailable")
-                providers = build_models_payload(ctx, max_models=50)["providers"]
+                providers = build_models_payload(ctx)["providers"]
             except Exception:
                 providers = []
 

hermes_cli/inventory.py

@@ -117,7 +117,7 @@ def build_models_payload(
     pricing: bool = False,
     capabilities: bool = False,
     force_fresh_nous_tier: bool = False,
-    max_models: int = 50,
+    max_models: int | None = None,
 ) -> dict:
     """Build the ``{providers, model, provider}`` shape every consumer
     needs from a single substrate call.

hermes_cli/model_switch.py

@@ -1188,7 +1188,6 @@ def prewarm_picker_cache_async() -> Optional["_threading.Thread"]:
                 current_model=ctx.current_model,
                 user_providers=ctx.user_providers,
                 custom_providers=ctx.custom_providers,
-                max_models=50,
             )
         except Exception:
             # Best-effort warmup — never surface errors into the session.
@@ -1206,7 +1205,7 @@ def list_authenticated_providers(
     custom_providers: list | None = None,
     *,
     force_fresh_nous_tier: bool = False,
-    max_models: int = 8,
+    max_models: int | None = None,
     current_model: str = "",
 ) -> List[dict]:
     """Detect which providers have credentials and list their curated models.
@@ -1426,7 +1425,7 @@ def list_authenticated_providers(
             if hermes_id in _MODELS_DEV_PREFERRED:
                 model_ids = _merge_with_models_dev(hermes_id, model_ids)
         total = len(model_ids)
-        top = model_ids[:max_models]
+        top = model_ids[:max_models] if max_models else model_ids
 
         slug = hermes_id
         pinfo = _mdev_pinfo(mdev_id)
@@ -1589,7 +1588,7 @@ def list_authenticated_providers(
                 if hermes_slug in _MODELS_DEV_PREFERRED:
                     model_ids = _merge_with_models_dev(hermes_slug, model_ids)
         total = len(model_ids)
-        top = model_ids[:max_models]
+        top = model_ids[:max_models] if max_models else model_ids
 
         results.append({
             "slug": hermes_slug,
@@ -1664,7 +1663,7 @@ def list_authenticated_providers(
             if not _cp_model_ids:
                 _cp_model_ids = curated.get(_cp.slug, [])
         _cp_total = len(_cp_model_ids)
-        _cp_top = _cp_model_ids[:max_models]
+        _cp_top = _cp_model_ids[:max_models] if max_models else _cp_model_ids
 
         results.append({
             "slug": _cp.slug,
@@ -2040,7 +2039,7 @@ def list_picker_providers(
     current_base_url: str = "",
     user_providers: dict = None,
     custom_providers: list | None = None,
-    max_models: int = 8,
+    max_models: int | None = None,
     current_model: str = "",
 ) -> List[dict]:
     """Interactive-picker variant of :func:`list_authenticated_providers`.
@@ -2083,7 +2082,7 @@ def list_picker_providers(
             except Exception:
                 live_ids = list(p.get("models", []))
             p = dict(p)
-            p["models"] = live_ids[:max_models]
+            p["models"] = live_ids[:max_models] if max_models else live_ids
             p["total_models"] = len(live_ids)
 
         has_models = bool(p.get("models"))

hermes_cli/web_server.py

@@ -3323,7 +3323,6 @@ def get_model_options(profile: Optional[str] = None):
         with _profile_scope(profile):
             return build_models_payload(
                 load_picker_context(),
-                max_models=50,
                 include_unconfigured=True,
                 picker_hints=True,
                 canonical_order=True,
@@ -3398,7 +3397,7 @@ def get_recommended_default_model(provider: str = ""):
     try:
         from hermes_cli.inventory import build_models_payload, load_picker_context
 
-        payload = build_models_payload(load_picker_context(), max_models=50)
+        payload = build_models_payload(load_picker_context())
         for row in payload.get("providers", []):
             if str(row.get("slug", "")).lower() == slug:
                 models = row.get("models") or []

tests/hermes_cli/test_inventory.py

@@ -660,3 +660,31 @@ def test_two_custom_providers_with_overlap_both_survive():
     assert a_row["total_models"] == 2
     assert b_row["total_models"] == 2
 
+
+def test_build_models_payload_no_max_models_returns_full_list():
+    """When max_models is not passed (None), build_models_payload must
+    return the full model list — not truncate to the old default of 50.
+    Regression for #48279: Kilo Gateway picker was capped at 50 of 336
+    models, making most models undiscoverable via search."""
+    full_models = [f"model-{i}" for i in range(100)]
+    rows = [
+        {
+            "slug": "kilocode",
+            "name": "Kilo Code",
+            "models": full_models,
+            "total_models": len(full_models),
+            "is_current": False,
+            "is_user_defined": False,
+            "source": "built-in",
+        },
+    ]
+    ctx = _empty_ctx()
+    with _list_auth_returning(rows):
+        # No max_models argument — should return all 100 models
+        payload = build_models_payload(ctx)
+
+    kilo_row = next(r for r in payload["providers"] if r["slug"] == "kilocode")
+    assert kilo_row["models"] == full_models
+    assert kilo_row["total_models"] == 100
+    assert len(kilo_row["models"]) == 100
+

tui_gateway/server.py

@@ -9496,7 +9496,6 @@ def _(rid, params: dict) -> dict:
             canonical_order=True,
             pricing=True,
             capabilities=True,
-            max_models=50,
         )
         return _ok(rid, payload)
     except Exception as e: