fix: show default embedding model when provider is not yet registered (#15511)

### What problem does this PR solve?

### Problem

On the Model Providers page, the Embedding Model dropdown in System
Model Settings shows empty (no default selected), even though a default
embedding model is configured in `service_conf.yaml`.

### Root Cause

Two issues were identified:

1. **Backend: `_get_model_info` fails for unregistered providers**
The tenant's `embd_id` is set to `bge-m3@xxxx` during initialization
(from the placeholder config `factory: 'xxxx'`). The `_get_model_info`
function requires the provider to exist in `tenant_model_provider`
table, but `xxxx` is never a real provider. Even after the user adds a
real provider (e.g., ZHIPU-AI), the stale `embd_id` still references the
non-existent one, causing the function to return `None`.

2. **Frontend: default models cache not invalidated after adding
provider**
`useAddProviderInstance` only invalidates `addedProviders` and
`allModels` caches after adding a provider instance, but does **not**
invalidate the `defaultModels` cache. This means the default model list
is not re-fetched until the user manually refreshes the page.

### Fix

**`api/apps/services/models_api_service.py`**

- Added `_resolve_model_from_tenant_providers()` helper: when the
default model's provider doesn't exist (e.g., placeholder `xxxx`), it
searches through the tenant's actually registered providers for a model
of the same type and returns the first match.
- When an instance name doesn't match (e.g., `"default"` vs actual name
`"1"`), the function now auto-resolves to the first real instance under
that provider.
- Falls back to `FACTORY_LLM_INFOS` validation when neither provider nor
instance exists.

**`web/src/hooks/use-llm-request.tsx`**

- Added `queryClient.invalidateQueries({ queryKey:
LlmKeys.defaultModels() })` to `useAddProviderInstance` so that the
default model list is re-fetched immediately after a provider instance
is added, eliminating the need for a manual page refresh.

### Testing

- Verified with a tenant whose `embd_id=bge-m3@xxxx` and only provider
is ZHIPU-AI (instance `1`): `_resolve_model_from_tenant_providers`
correctly resolves to `embedding-2@1@ZHIPU-AI`.
- After adding a provider via the UI, the embedding model dropdown now
immediately shows the resolved default without requiring a page refresh.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

---------

Signed-off-by: noob <yixiao121314@outlook.com>

api/apps/services/models_api_service.py

@@ -68,6 +68,10 @@ def _get_model_info(tenant_id: str, default_model: str, model_type: str):
     elif len(parts) == 2:
         model_name, provider_name = parts
         instance_name = "default"
+    elif len(parts) == 1:
+        model_name = parts[0]
+        provider_name = ""
+        instance_name = "default"
     else:
         logging.warning(f"Invalid model string: {default_model}")
         return None
@@ -83,6 +87,22 @@ def _get_model_info(tenant_id: str, default_model: str, model_type: str):
             "enable": True,
         }
 
+    # Special case: TEI Builtin embedding model
+    compose_profiles = os.getenv("COMPOSE_PROFILES", "")
+    tei_model = os.getenv("TEI_MODEL", "")
+    if (model_type == "embedding"
+        and "tei-" in compose_profiles
+        and tei_model
+        and model_name == tei_model
+        and (not provider_name or provider_name == "Builtin")):
+        return {
+            "model_provider": "Builtin",
+            "model_instance": "default",
+            "model_name": model_name,
+            "model_type": model_type,
+            "enable": True,
+        }
+
     # Check if the provider exists for the tenant
     provider_obj = TenantModelProviderService.get_by_tenant_id_and_provider_name(tenant_id, provider_name)
     if not provider_obj:
@@ -161,7 +181,7 @@ def _check_model_available(tenant_id: str, provider_name: str, instance_name: st
             model_type == LLMType.EMBEDDING.value
             and "tei-" in compose_profiles
             and model_name == os.getenv("TEI_MODEL", "")
-            and (provider_name == "Builtin" or provider_name is None)
+            and (provider_name == "Builtin" or not provider_name)
     )
     if is_tei_builtin_embedding:
         return True, None
@@ -365,6 +385,25 @@ def list_tenant_added_models(tenant_id: str, model_type_filter: str=None):
                 "instance_name": instance_info_map[instance_id].instance_name if instance_info_map.get(instance_id) else ""
             })
 
+    # Add TEI Builtin embedding model if configured
+    compose_profiles = os.getenv("COMPOSE_PROFILES", "")
+    tei_model = os.getenv("TEI_MODEL", "")
+    if "tei-" in compose_profiles and tei_model:
+        if not model_type_filter or model_type_filter == "embedding":
+            tei_already_added = any(
+                m["provider_name"] == "Builtin" and m["name"] == tei_model
+                for m in added_models
+            )
+            if not tei_already_added:
+                added_models.append({
+                    "model_type": ["embedding"],
+                    "name": tei_model,
+                    "provider_id": "",
+                    "provider_name": "Builtin",
+                    "instance_id": "",
+                    "instance_name": "default",
+                })
+
     added_models.sort(key=lambda x: (factory_rank_mapping.get(x["provider_name"]), x["provider_name"], x["instance_name"]))
 
     return True, added_models

api/db/joint_services/tenant_model_service.py

@@ -82,7 +82,7 @@ def get_model_config_from_provider_instance(tenant_id, model_type: str|enum.Enum
             model_type_val == LLMType.EMBEDDING.value
             and "tei-" in compose_profiles
             and pure_model_name == os.getenv("TEI_MODEL", "")
-            and (provider_name == "Builtin" or provider_name is None)
+            and (provider_name == "Builtin" or not provider_name)
     )
     if is_tei_builtin_embedding:
         # configured local embedding model