feat(proxy): add model-like search tool access control

Treat search tools like models by adding team/key allowed_search_tools controls, enforcing search tool authorization checks, and moving credential ownership to search tool config only to avoid exposing secrets in team metadata.

Made-with: Cursor

docs/my-website/docs/proxy/search_tools_access.md

@@ -0,0 +1,439 @@
+# Search Tools Access Control
+
+Control which teams and keys can access specific search tools using model-like allowlists.
+
+## Overview
+
+Search tools in LiteLLM Proxy use the same access control pattern as models:
+
+- **Team-level allowlist**: `allowed_search_tools` on teams
+- **Key-level allowlist**: `allowed_search_tools` on keys
+- **Tool-only credentials**: API keys stored ONLY in search tool configuration
+- **Secure by default**: Credentials never exposed in team/key metadata
+
+## Quick Start
+
+### Step 1: Configure Search Tools
+
+Define search tools in your `proxy_server_config.yaml`:
+
+```yaml
+search_tools:
+  - search_tool_name: perplexity-search
+    litellm_params:
+      search_provider: perplexity
+      api_key: os.environ/PERPLEXITYAI_API_KEY
+  
+  - search_tool_name: tavily-search
+    litellm_params:
+      search_provider: tavily
+      api_key: os.environ/TAVILY_API_KEY
+
+  - search_tool_name: tavily-marketing
+    litellm_params:
+      search_provider: tavily
+      api_key: os.environ/TAVILY_MARKETING_API_KEY
+      
+  - search_tool_name: brave-search
+    litellm_params:
+      search_provider: brave
+      api_key: os.environ/BRAVE_API_KEY
+```
+
+### Step 2: Create Teams with Search Tool Access
+
+```bash
+curl -X POST 'http://localhost:4000/team/new' \
+  -H 'Authorization: Bearer <master-key>' \
+  -H 'Content-Type: application/json' \
+  -d '{
+    "team_alias": "marketing-team",
+    "models": ["gpt-4"],
+    "allowed_search_tools": ["tavily-marketing", "perplexity-search"]
+  }'
+```
+
+### Step 3: Generate Keys for Teams
+
+```bash
+curl -X POST 'http://localhost:4000/key/generate' \
+  -H 'Authorization: Bearer <master-key>' \
+  -H 'Content-Type: application/json' \
+  -d '{
+    "team_id": "<team-id>",
+    "models": ["gpt-4"],
+    "allowed_search_tools": ["tavily-marketing"]
+  }'
+```
+
+### Step 4: Use Search Tools
+
+```bash
+curl -X POST 'http://localhost:4000/v1/search/tavily-marketing' \
+  -H 'Authorization: Bearer sk-...' \
+  -d '{"query": "latest marketing trends"}'
+```
+
+## Access Control Rules
+
+### Authorization Flow
+
+```mermaid
+flowchart TD
+    Request["/v1/search/tavily-search"] --> KeyCheck{Key has access?}
+    KeyCheck -->|No| Deny403[403 Forbidden]
+    KeyCheck -->|Yes| TeamCheck{Team has access?}
+    TeamCheck -->|No| Deny403
+    TeamCheck -->|Yes| GetCreds[Get credentials from tool config]
+    GetCreds --> CallAPI[Call Tavily API]
+```
+
+### Allowlist Behavior
+
+| Allowlist Value | Behavior |
+|----------------|----------|
+| `[]` (empty) | Access to **all** search tools |
+| `["tool-a", "tool-b"]` | Access only to `tool-a` and `tool-b` |
+| Not set / `null` | Access to **all** search tools |
+
+### Examples
+
+**Example 1: Team restricts tools, key further restricts**
+
+```yaml
+# Team allows 3 tools
+team.allowed_search_tools = ["tavily", "perplexity", "brave"]
+
+# Key only allows 1 tool
+key.allowed_search_tools = ["tavily"]
+
+# Result: Key can ONLY access "tavily"
+```
+
+**Example 2: Empty allowlists grant full access**
+
+```yaml
+# Team allows all
+team.allowed_search_tools = []
+
+# Key allows all
+key.allowed_search_tools = []
+
+# Result: Key can access ANY search tool
+```
+
+**Example 3: Team blocks access even if key allows**
+
+```yaml
+# Team restricts to perplexity
+team.allowed_search_tools = ["perplexity"]
+
+# Key allows tavily
+key.allowed_search_tools = ["tavily"]
+
+# Result: Access DENIED - team doesn't allow tavily
+```
+
+## Configuration Patterns
+
+### Pattern 1: Per-Team Search Tool Isolation
+
+Each team gets their own search tool with dedicated credentials:
+
+```yaml
+search_tools:
+  - search_tool_name: tavily-team-a
+    litellm_params:
+      search_provider: tavily
+      api_key: os.environ/TAVILY_TEAM_A_KEY
+      
+  - search_tool_name: tavily-team-b
+    litellm_params:
+      search_provider: tavily
+      api_key: os.environ/TAVILY_TEAM_B_KEY
+```
+
+```bash
+# Create teams with isolated tools
+curl -X POST 'http://localhost:4000/team/new' \
+  -H 'Authorization: Bearer <master-key>' \
+  -d '{
+    "team_alias": "team-a",
+    "allowed_search_tools": ["tavily-team-a"]
+  }'
+```
+
+**Benefits**:
+- Complete cost isolation (different Tavily accounts)
+- Separate rate limits per team
+- Independent billing
+
+### Pattern 2: Shared Tools with Access Control
+
+Share search tools across teams with allowlist restrictions:
+
+```yaml
+search_tools:
+  - search_tool_name: tavily-premium
+    litellm_params:
+      search_provider: tavily
+      api_key: os.environ/TAVILY_PREMIUM_KEY
+      
+  - search_tool_name: perplexity-standard
+    litellm_params:
+      search_provider: perplexity
+      api_key: os.environ/PERPLEXITY_KEY
+```
+
+```bash
+# Enterprise team gets premium tools
+curl -X POST 'http://localhost:4000/team/new' \
+  -d '{
+    "team_alias": "enterprise",
+    "allowed_search_tools": ["tavily-premium", "perplexity-standard"]
+  }'
+
+# Regular team gets standard tools only
+curl -X POST 'http://localhost:4000/team/new' \
+  -d '{
+    "team_alias": "standard",
+    "allowed_search_tools": ["perplexity-standard"]
+  }'
+```
+
+### Pattern 3: Open Access with Cost Tracking
+
+Allow all teams to access tools, track costs via `team_id`:
+
+```yaml
+search_tools:
+  - search_tool_name: tavily-shared
+    litellm_params:
+      search_provider: tavily
+      api_key: os.environ/TAVILY_SHARED_KEY
+```
+
+```bash
+# Teams with empty allowlists can access all tools
+curl -X POST 'http://localhost:4000/team/new' \
+  -d '{
+    "team_alias": "team-a",
+    "allowed_search_tools": []
+  }'
+```
+
+Query spend by team:
+
+```sql
+SELECT 
+    team_id,
+    SUM(spend) as total_spend,
+    COUNT(*) as request_count
+FROM "LiteLLM_SpendLogs"
+WHERE call_type = 'search'
+  AND model LIKE 'tavily%'
+GROUP BY team_id;
+```
+
+## Security Model
+
+### Credentials Storage
+
+**Secure**: Credentials stored ONLY in search tool configuration
+
+```yaml
+# ✅ CORRECT - Credentials in tool config
+search_tools:
+  - search_tool_name: tavily-search
+    litellm_params:
+      api_key: os.environ/TAVILY_API_KEY  # Stored here
+```
+
+**Never in team/key metadata**:
+
+```json
+{
+  "team_id": "team-123",
+  "allowed_search_tools": ["tavily-search"],
+  "metadata": {}  // ✅ No credentials here
+}
+```
+
+### Access Control Only
+
+Teams and keys only specify **which tools** they can access, not credentials:
+
+```json
+{
+  "team": {
+    "allowed_search_tools": ["tool-a", "tool-b"]  // Access control
+  },
+  "key": {
+    "allowed_search_tools": ["tool-a"]  // Access control
+  }
+}
+```
+
+## API Reference
+
+### Create Team with Search Tools
+
+```bash
+POST /team/new
+
+{
+  "team_alias": "marketing",
+  "models": ["gpt-4"],
+  "allowed_search_tools": ["tavily-search", "perplexity-search"]
+}
+```
+
+### Update Team Search Tools
+
+```bash
+POST /team/update
+
+{
+  "team_id": "team-123",
+  "allowed_search_tools": ["brave-search"]
+}
+```
+
+### Generate Key with Search Tools
+
+```bash
+POST /key/generate
+
+{
+  "team_id": "team-123",
+  "models": ["gpt-4"],
+  "allowed_search_tools": ["tavily-search"]
+}
+```
+
+### List Available Search Tools
+
+```bash
+GET /v1/search/tools
+
+# Response:
+{
+  "object": "list",
+  "data": [
+    {
+      "search_tool_name": "tavily-search",
+      "search_provider": "tavily"
+    }
+  ]
+}
+```
+
+## Cost Attribution
+
+Search requests are automatically attributed to the team via `team_id` in spend logs:
+
+```sql
+SELECT 
+    team_id,
+    model as search_tool,
+    SUM(spend) as cost,
+    COUNT(*) as requests
+FROM "LiteLLM_SpendLogs"
+WHERE call_type = 'search'
+  AND created_at >= NOW() - INTERVAL '30 days'
+GROUP BY team_id, model
+ORDER BY cost DESC;
+```
+
+**Example output**:
+
+| team_id | search_tool | cost | requests |
+|---------|-------------|------|----------|
+| team-marketing | tavily-search | $45.20 | 904 |
+| team-engineering | perplexity-search | $32.15 | 643 |
+| team-research | brave-search | $8.50 | 170 |
+
+## Migration from Legacy Approach
+
+If you previously stored credentials in team metadata, migrate to the new approach:
+
+### Before (Insecure)
+
+```json
+{
+  "team": {
+    "metadata": {
+      "search_provider_config": {
+        "tavily": {"api_key": "tvly-..."}  // ❌ Exposed
+      }
+    }
+  }
+}
+```
+
+### After (Secure)
+
+```yaml
+# 1. Move credentials to search tool config
+search_tools:
+  - search_tool_name: tavily-marketing
+    litellm_params:
+      search_provider: tavily
+      api_key: os.environ/TAVILY_MARKETING_KEY  # ✅ Secure
+
+# 2. Update team with allowlist
+team:
+  allowed_search_tools: ["tavily-marketing"]  # ✅ Access control only
+```
+
+## Troubleshooting
+
+### 403 Forbidden Error
+
+```json
+{
+  "error": "Key not allowed to access search tool: tavily-search. 
+           Allowed search tools: [perplexity-search]"
+}
+```
+
+**Solution**: Add the search tool to key's `allowed_search_tools`:
+
+```bash
+curl -X POST 'http://localhost:4000/key/update' \
+  -d '{
+    "key": "sk-...",
+    "allowed_search_tools": ["tavily-search", "perplexity-search"]
+  }'
+```
+
+### Search Tool Not Found
+
+```json
+{"error": "Search tool not found: tavily-search"}
+```
+
+**Solution**: Add the search tool to your `proxy_server_config.yaml`:
+
+```yaml
+search_tools:
+  - search_tool_name: tavily-search
+    litellm_params:
+      search_provider: tavily
+      api_key: os.environ/TAVILY_API_KEY
+```
+
+## Best Practices
+
+1. **Use descriptive tool names**: `tavily-marketing` vs `tavily-1`
+2. **Empty allowlists for admins**: Grant full access to admin teams
+3. **Restrict by role**: Marketing gets marketing tools, engineering gets code search
+4. **Monitor costs per team**: Query spend logs regularly
+5. **Rotate credentials in tools**: Update environment variables, not team metadata
+6. **Start restrictive**: Add tools to allowlists as needed
+
+## Related
+
+- [Search API Reference](./search.md)
+- [Team Management](./team_budgets.md)
+- [Cost Tracking](./cost_tracking.md)

litellm/proxy/_types.py

@@ -1725,7 +1725,7 @@ class TeamBase(LiteLLMPydanticObjectBase):
     members: list = []
     members_with_roles: List[Member] = []
     team_member_permissions: Optional[List[str]] = None
-    metadata: Optional[dict] = None  # may include search_provider_config
+    metadata: Optional[dict] = None
     tpm_limit: Optional[int] = None
     rpm_limit: Optional[int] = None
 
@@ -1738,6 +1738,7 @@ class TeamBase(LiteLLMPydanticObjectBase):
     )
 
     models: list = []
+    allowed_search_tools: list = []  # list of search_tool_name values team can access
     blocked: bool = False
     router_settings: Optional[dict] = None
     access_group_ids: Optional[List[str]] = None
@@ -1845,13 +1846,6 @@ class UpdateTeamRequest(LiteLLMPydanticObjectBase):
     )
 
 
-class TeamSearchProviderConfigUpdateRequest(LiteLLMPydanticObjectBase):
-    team_id: str
-    provider: str
-    api_key: Optional[str] = None
-    api_base: Optional[str] = None
-
-
 class ResetTeamBudgetRequest(LiteLLMPydanticObjectBase):
     """
     internal type used to reset the budget on a team
@@ -2451,6 +2445,7 @@ class LiteLLM_VerificationToken(LiteLLMPydanticObjectBase):
     max_budget: Optional[float] = None
     expires: Optional[Union[str, datetime]] = None
     models: List = []
+    allowed_search_tools: List = []  # list of search_tool_name values key can access
     aliases: Dict = {}
     config: Dict = {}
     user_id: Optional[str] = None

litellm/proxy/auth/auth_checks.py

@@ -2962,6 +2962,100 @@ async def can_user_call_model(
     )
 
 
+def _can_object_call_search_tool(
+    search_tool_name: str,
+    allowed_search_tools: List[str],
+    object_type: Literal["key", "team", "project"],
+) -> Literal[True]:
+    """
+    Check if an object (key/team/project) can access a specific search tool.
+    
+    Similar to _can_object_call_model but for search tools.
+    
+    Args:
+        search_tool_name: The search tool being requested
+        allowed_search_tools: List of allowed search tool names for this object
+        object_type: Type of object for error messaging
+        
+    Returns:
+        True if access is allowed
+        
+    Raises:
+        ProxyException if access is denied
+    """
+    # Empty list means all search tools are allowed
+    if not allowed_search_tools:
+        return True
+        
+    # Check if the search tool is in the allowlist
+    if search_tool_name in allowed_search_tools:
+        return True
+        
+    # Access denied
+    raise ProxyException(
+        message=f"{object_type.capitalize()} not allowed to access search tool: {search_tool_name}. "
+        f"Allowed search tools: {allowed_search_tools}",
+        type=ProxyErrorTypes.key_model_access_denied,
+        param="search_tool_name",
+        code=status.HTTP_403_FORBIDDEN,
+    )
+
+
+async def can_key_call_search_tool(
+    search_tool_name: str,
+    valid_token: UserAPIKeyAuth,
+) -> Literal[True]:
+    """
+    Check if a key can access a specific search tool.
+    
+    Similar to can_key_call_model but for search tools.
+    
+    Args:
+        search_tool_name: The search tool being requested
+        valid_token: The authenticated key
+        
+    Returns:
+        True if access is allowed
+        
+    Raises:
+        ProxyException if access is denied
+    """
+    return _can_object_call_search_tool(
+        search_tool_name=search_tool_name,
+        allowed_search_tools=valid_token.allowed_search_tools or [],
+        object_type="key",
+    )
+
+
+async def can_team_call_search_tool(
+    search_tool_name: str,
+    team_object: Optional[LiteLLM_TeamTable],
+) -> Literal[True]:
+    """
+    Check if a team can access a specific search tool.
+    
+    Similar to can_team_access_model but for search tools.
+    
+    Args:
+        search_tool_name: The search tool being requested
+        team_object: The team object
+        
+    Returns:
+        True if access is allowed
+        
+    Raises:
+        ProxyException if access is denied
+    """
+    if team_object is None:
+        return True
+        
+    return _can_object_call_search_tool(
+        search_tool_name=search_tool_name,
+        allowed_search_tools=team_object.allowed_search_tools or [],
+        object_type="team",
+    )
+
+
 async def is_valid_fallback_model(
     model: str,
     llm_router: Optional[Router],

litellm/proxy/management_endpoints/team_endpoints.py

@@ -59,7 +59,6 @@ from litellm.proxy._types import (
     TeamMemberUpdateResponse,
     TeamModelAddRequest,
     TeamModelDeleteRequest,
-    TeamSearchProviderConfigUpdateRequest,
     UpdateTeamRequest,
     UserAPIKeyAuth,
 )
@@ -1857,108 +1856,6 @@ async def update_team(  # noqa: PLR0915
         raise handle_exception_on_proxy(e)
 
 
-@router.post(
-    "/team/search_provider_config/update",
-    tags=["team management"],
-    dependencies=[Depends(user_api_key_auth)],
-)
-@management_endpoint_wrapper
-async def update_team_search_provider_config(
-    data: TeamSearchProviderConfigUpdateRequest,
-    user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
-):
-    """
-    Update per-team search provider credentials in team metadata.
-
-    Stored under:
-    metadata.search_provider_config.<provider>.{api_key, api_base}
-    """
-    from litellm.proxy.auth.auth_checks import _cache_team_object
-    from litellm.proxy.proxy_server import (
-        prisma_client,
-        proxy_logging_obj,
-        user_api_key_cache,
-    )
-
-    if prisma_client is None:
-        raise HTTPException(
-            status_code=500,
-            detail={"error": CommonProxyErrors.db_not_connected_error.value},
-        )
-
-    provider = data.provider.strip().lower()
-    if provider == "":
-        raise HTTPException(
-            status_code=400, detail={"error": "provider cannot be empty"}
-        )
-
-    existing_team_row = await prisma_client.db.litellm_teamtable.find_unique(
-        where={"team_id": data.team_id}
-    )
-    if existing_team_row is None:
-        raise HTTPException(
-            status_code=404,
-            detail={"error": f"Team not found, passed team_id={data.team_id}"},
-        )
-
-    await _verify_team_access(
-        team_obj=LiteLLM_TeamTable(**existing_team_row.model_dump()),
-        user_api_key_dict=user_api_key_dict,
-    )
-
-    metadata: Dict[str, Any] = {}
-    if isinstance(existing_team_row.metadata, dict):
-        metadata = dict(existing_team_row.metadata)
-
-    search_provider_config = metadata.get("search_provider_config")
-    if not isinstance(search_provider_config, dict):
-        search_provider_config = {}
-
-    provider_config = search_provider_config.get(provider)
-    if not isinstance(provider_config, dict):
-        provider_config = {}
-
-    if data.api_key is not None:
-        provider_config["api_key"] = data.api_key
-    if data.api_base is not None:
-        provider_config["api_base"] = data.api_base
-
-    if provider_config.get("api_key") in (None, "") and provider_config.get(
-        "api_base"
-    ) in (
-        None,
-        "",
-    ):
-        search_provider_config.pop(provider, None)
-    else:
-        search_provider_config[provider] = provider_config
-
-    metadata["search_provider_config"] = search_provider_config
-
-    team_row: Optional[LiteLLM_TeamTable] = (
-        await prisma_client.db.litellm_teamtable.update(
-            where={"team_id": data.team_id},
-            data={"metadata": metadata},
-            include={"litellm_model_table": True},  # type: ignore
-        )
-    )
-
-    if team_row is not None and team_row.team_id is not None:
-        await _cache_team_object(
-            team_id=team_row.team_id,
-            team_table=LiteLLM_TeamTableCachedObj(**team_row.model_dump()),
-            user_api_key_cache=user_api_key_cache,
-            proxy_logging_obj=proxy_logging_obj,
-        )
-
-    return {
-        "message": "Team search provider configuration updated",
-        "team_id": data.team_id,
-        "provider": provider,
-        "search_provider_config": search_provider_config,
-    }
-
-
 def _set_budget_reset_at(data: UpdateTeamRequest, updated_kv: dict) -> None:
     """Set budget_reset_at in updated_kv if budget_duration is provided."""
     if data.budget_duration is not None:

litellm/proxy/schema.prisma

@@ -127,6 +127,7 @@ model LiteLLM_TeamTable {
     soft_budget Float?
     spend      Float    @default(0.0)
     models     String[]
+    allowed_search_tools String[] @default([]) // search_tool_name values team can access
     max_parallel_requests Int?
     tpm_limit     BigInt?
     rpm_limit     BigInt?
@@ -369,6 +370,7 @@ model LiteLLM_VerificationToken {
     spend      Float    @default(0.0)
     expires    DateTime?
     models     String[]
+    allowed_search_tools String[] @default([]) // search_tool_name values key can access
     aliases    Json  @default("{}")
     config     Json  @default("{}")
     router_settings Json? @default("{}")

litellm/proxy/search_endpoints/endpoints.py

@@ -134,10 +134,41 @@ async def search(
 
     if "search_tool_name" in data and data["search_tool_name"]:
         data["model"] = data["search_tool_name"]
+        search_tool_name_value = data["search_tool_name"]
+
+        # Authorization check: verify key can access this search tool
+        from litellm.proxy.auth.auth_checks import (
+            can_key_call_search_tool,
+            can_team_call_search_tool,
+            get_team_object,
+        )
+
+        try:
+            # Check key-level access
+            await can_key_call_search_tool(
+                search_tool_name=search_tool_name_value,
+                valid_token=user_api_key_dict,
+            )
+
+            # Check team-level access if key is associated with a team
+            if user_api_key_dict.team_id:
+                team_object = await get_team_object(
+                    team_id=user_api_key_dict.team_id,
+                    user_api_key_cache=None,  # Will use internal cache
+                    parent_otel_span=None,
+                    proxy_logging_obj=None,
+                )
+                await can_team_call_search_tool(
+                    search_tool_name=search_tool_name_value,
+                    team_object=team_object,
+                )
+        except Exception as e:
+            verbose_proxy_logger.error(
+                f"Search tool authorization failed for {search_tool_name_value}: {str(e)}"
+            )
+            raise
 
         if llm_router is not None and hasattr(llm_router, "search_tools"):
-            search_tool_name_value = data["search_tool_name"]
-
             verbose_proxy_logger.debug(
                 f"Search endpoint - Looking for search_tool_name: {search_tool_name_value}. "
                 f"Available search tools in router: {[tool.get('search_tool_name') for tool in llm_router.search_tools]}. "

litellm/router_utils/search_api_router.py

@@ -56,58 +56,19 @@ class SearchAPIRouter:
         team_config: Optional[Dict[str, Any]] = None,
     ) -> Tuple[Optional[str], Optional[str]]:
         """
-        Resolve search provider credentials with precedence:
-        1. request metadata.search_provider_config.{provider}
-        2. team metadata.search_provider_config.{provider}
-        3. default_team_settings.search_provider_config.{provider}
-        4. search_tool.litellm_params
-        5. env fallback in provider validate_environment()
+        Resolve search provider credentials from tool configuration ONLY.
+        
+        Credentials are stored only in search_tool.litellm_params, never in team/key metadata.
+        This ensures secrets are not exposed in team/key API responses.
+        
+        Args:
+            tool_litellm_params: Search tool litellm_params with credentials
+            
+        Returns:
+            Tuple of (api_key, api_base) from tool configuration
         """
-        resolved_api_key: Optional[str] = None
-        resolved_api_base: Optional[str] = None
-
-        request_provider_config = {}
-        if isinstance(request_metadata, dict):
-            search_provider_config = request_metadata.get("search_provider_config")
-            if isinstance(search_provider_config, dict):
-                request_provider_config = search_provider_config.get(
-                    search_provider, {}
-                )
-
-        team_provider_config = {}
-        if isinstance(team_metadata, dict):
-            search_provider_config = team_metadata.get("search_provider_config")
-            if isinstance(search_provider_config, dict):
-                team_provider_config = search_provider_config.get(search_provider, {})
-
-        team_settings_provider_config = {}
-        if isinstance(team_config, dict):
-            search_provider_config = team_config.get("search_provider_config")
-            if isinstance(search_provider_config, dict):
-                team_settings_provider_config = search_provider_config.get(
-                    search_provider, {}
-                )
-
-        if isinstance(request_provider_config, dict):
-            resolved_api_key = request_provider_config.get("api_key")
-            resolved_api_base = request_provider_config.get("api_base")
-
-        if resolved_api_key is None and isinstance(team_provider_config, dict):
-            resolved_api_key = team_provider_config.get("api_key")
-        if resolved_api_base is None and isinstance(team_provider_config, dict):
-            resolved_api_base = team_provider_config.get("api_base")
-
-        if resolved_api_key is None and isinstance(team_settings_provider_config, dict):
-            resolved_api_key = team_settings_provider_config.get("api_key")
-        if resolved_api_base is None and isinstance(
-            team_settings_provider_config, dict
-        ):
-            resolved_api_base = team_settings_provider_config.get("api_base")
-
-        if resolved_api_key is None:
-            resolved_api_key = tool_litellm_params.get("api_key")
-        if resolved_api_base is None:
-            resolved_api_base = tool_litellm_params.get("api_base")
+        resolved_api_key: Optional[str] = tool_litellm_params.get("api_key")
+        resolved_api_base: Optional[str] = tool_litellm_params.get("api_base")
 
         return resolved_api_key, resolved_api_base
 

proxy_server.log

@@ -0,0 +1,659 @@
+<frozen runpy>:128: RuntimeWarning: 'litellm.proxy.proxy_cli' found in sys.modules after import of package 'litellm.proxy', but prior to execution of 'litellm.proxy.proxy_cli'; this may result in unpredictable behaviour
+2026-04-28 18:52:10,288 - litellm_proxy_extras - INFO - Running prisma migrate deploy
+2026-04-28 18:52:13,736 - litellm_proxy_extras - INFO - prisma migrate deploy stdout: Environment variables loaded from ../../.env
+Prisma schema loaded from schema.prisma
+Datasource "client": PostgreSQL database "litellm", schema "public" at "localhost:5432"
+
+118 migrations found in prisma/migrations
+
+
+No pending migrations to apply.
+
+2026-04-28 18:52:13,737 - litellm_proxy_extras - INFO - prisma migrate deploy completed
+2026-04-28 18:52:13,737 - litellm_proxy_extras - INFO - No pending migrations — skipping post-migration sanity check
+INFO:     Started server process [19856]
+INFO:     Waiting for application startup.
+18:52:13 - LiteLLM Proxy:DEBUG: proxy_server.py:803 - litellm.proxy.proxy_server.py::startup() - CHECKING PREMIUM USER - True
+18:52:13 - LiteLLM Proxy:DEBUG: proxy_server.py:816 - worker_config: {"model": null, "alias": null, "api_base": null, "api_version": "2025-02-01-preview", "debug": false, "detailed_debug": true, "temperature": null, "max_tokens": null, "request_timeout": null, "max_budget": null, "telemetry": true, "drop_params": false, "add_function_to_prompt": false, "headers": null, "save": false, "config": "proxy_server_config.yaml", "use_queue": false}
+LiteLLM Proxy: Using default (v1) migration resolver. If your deployment has seen schema thrashing during rolling deploys, try --use_v2_migration_resolver (safer: avoids the diff-and-force recovery that caused the thrash).
+
+   ██╗     ██╗████████╗███████╗██╗     ██╗     ███╗   ███╗
+   ██║     ██║╚══██╔══╝██╔════╝██║     ██║     ████╗ ████║
+   ██║     ██║   ██║   █████╗  ██║     ██║     ██╔████╔██║
+   ██║     ██║   ██║   ██╔══╝  ██║     ██║     ██║╚██╔╝██║
+   ███████╗██║   ██║   ███████╗███████╗███████╗██║ ╚═╝ ██║
+   ╚══════╝╚═╝   ╚═╝   ╚══════╝╚══════╝╚══════╝╚═╝     ╚═╝
+
+18:52:13 - LiteLLM:DEBUG: utils.py:5620 - checking potential_model_names in litellm.model_cost: {'split_model': '170fb9c8e18f87663825b69e7e54393b7a3392d1ecbfb0d6a8a543f0723173fd', 'combined_model_name': '170fb9c8e18f87663825b69e7e54393b7a3392d1ecbfb0d6a8a543f0723173fd', 'stripped_model_name': '170fb9c8e18f87663825b69e7e54393b7a3392d1ecbfb0d6a8a543f0723173fd', 'combined_stripped_model_name': '170fb9c8e18f87663825b69e7e54393b7a3392d1ecbfb0d6a8a543f0723173fd', 'custom_llm_provider': None}
+18:52:13 - LiteLLM:DEBUG: utils.py:5921 - Error getting model info: This model isn't mapped yet. Add it here - https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json
+18:52:13 - LiteLLM:DEBUG: utils.py:2900 - added/updated model=170fb9c8e18f87663825b69e7e54393b7a3392d1ecbfb0d6a8a543f0723173fd in litellm.model_cost: 170fb9c8e18f87663825b69e7e54393b7a3392d1ecbfb0d6a8a543f0723173fd
+18:52:13 - LiteLLM:DEBUG: utils.py:5620 - checking potential_model_names in litellm.model_cost: {'split_model': 'gpt-5.3-codex', 'combined_model_name': 'openai/gpt-5.3-codex', 'stripped_model_name': 'gpt-5.3-codex', 'combined_stripped_model_name': 'openai/gpt-5.3-codex', 'custom_llm_provider': 'openai'}
+18:52:13 - LiteLLM:DEBUG: utils.py:5620 - checking potential_model_names in litellm.model_cost: {'split_model': 'gpt-5.3-codex', 'combined_model_name': 'openai/gpt-5.3-codex', 'stripped_model_name': 'gpt-5.3-codex', 'combined_stripped_model_name': 'openai/gpt-5.3-codex', 'custom_llm_provider': 'openai'}
+18:52:13 - LiteLLM:DEBUG: utils.py:5620 - checking potential_model_names in litellm.model_cost: {'split_model': 'gpt-5.3-codex', 'combined_model_name': 'openai/gpt-5.3-codex', 'stripped_model_name': 'openai/gpt-5.3-codex', 'combined_stripped_model_name': 'openai/gpt-5.3-codex', 'custom_llm_provider': 'openai'}
+18:52:13 - LiteLLM:DEBUG: utils.py:2900 - added/updated model=gpt-5.3-codex in litellm.model_cost: gpt-5.3-codex
+18:52:13 - LiteLLM Router:DEBUG: router.py:7223 - 
+Initialized Model List ['gpt-5.3-codex']
+18:52:13 - LiteLLM Router:INFO: router.py:812 - Routing strategy: simple-shuffle
+18:52:13 - LiteLLM Proxy:DEBUG: proxy_server.py:3915 - Policy engine: no policies in config, skipping
+18:52:13 - LiteLLM Proxy:DEBUG: utils.py:2460 - Creating Prisma Client..
+18:52:13 - LiteLLM Proxy:DEBUG: utils.py:2527 - Success - Created Prisma Client
+18:52:13 - LiteLLM Proxy:DEBUG: utils.py:3745 - PrismaClient: connect() called Attempting to Connect to DB
+18:52:13 - LiteLLM Proxy:DEBUG: utils.py:3749 - PrismaClient: DB not connected, Attempting to Connect to DB
+query-engine ac9d7041ed77bcc8a8dbd2ab6616b39013829574
+18:52:13 - LiteLLM Proxy:DEBUG: prisma_client.py:247 - IAM token auth not enabled, skipping token refresh task
+18:52:13 - LiteLLM Proxy:INFO: utils.py:4307 - Started Prisma DB health watchdog (interval=30s, reconnect_cooldown=15s, probe_timeout=5.0s, reconnect_timeout=30.0s)
+18:52:13 - LiteLLM Proxy:INFO: utils.py:4062 - Found prisma-query-engine at PID 20355.
+18:52:13 - LiteLLM Proxy:INFO: utils.py:4066 - Watching engine PID 20355 via waitpid thread.
+18:52:13 - LiteLLM:DEBUG: logging_callback_manager.py:336 - Custom logger of type SkillsInjectionHook, key: SkillsInjectionHook-max_iterations=10-sandbox_timeout=120-message_logging=True-turn_off_message_logging=False already exists in [<litellm.proxy.hooks.litellm_skills.main.SkillsInjectionHook object at 0x114eb7620>, <litellm.proxy.hooks.model_max_budget_limiter._PROXY_VirtualKeyModelMaxBudgetLimiter object at 0x1561309e0>, <litellm.proxy.hooks.proxy_track_cost_callback._ProxyDBLogger object at 0x16f90b9e0>, <litellm.proxy.hooks.max_budget_limiter._PROXY_MaxBudgetLimiter object at 0x16f90ba40>, <litellm.proxy.hooks.parallel_request_limiter_v3._PROXY_MaxParallelRequestsHandler_v3 object at 0x16f909040>, <litellm.proxy.hooks.cache_control_check._PROXY_CacheControlCheck object at 0x16f90bd10>, <litellm.proxy.hooks.responses_id_security.ResponsesIDSecurity object at 0x16f77fc50>], not adding again..
+18:52:13 - LiteLLM Proxy:DEBUG: proxy_server.py:895 - About to initialize semantic tool filter
+18:52:13 - LiteLLM Proxy:DEBUG: proxy_server.py:898 - litellm_settings keys = []
+18:52:13 - LiteLLM Proxy:DEBUG: proxy_server.py:6220 - Semantic tool filter not configured or not enabled, skipping initialization
+18:52:13 - LiteLLM Proxy:DEBUG: proxy_server.py:905 - After semantic tool filter initialization
+18:52:13 - LiteLLM Proxy:DEBUG: proxy_server.py:919 - prisma_client: <litellm.proxy.utils.PrismaClient object at 0x16f787950>
+18:52:13 - LiteLLM Proxy:INFO: proxy_server.py:6467 - Tag spend update job scheduled at 25s interval (2.3x main job interval)
+18:52:13 - LiteLLM Proxy:DEBUG: hanging_request_check.py:148 - Checking for hanging requests....
+18:52:13 - LiteLLM Proxy:INFO: utils.py:5083 - Starting spend logs queue monitor (threshold: 100, poll_interval: 2.0s)
+18:52:14 - LiteLLM Proxy:INFO: utils.py:2634 - All necessary views exist!
+18:52:14 - LiteLLM Proxy:INFO: proxy_server.py:874 - Password migration: No plaintext passwords found
+18:52:14 - LiteLLM Proxy:DEBUG: proxy_server.py:4256 - len new_models: 2
+18:52:14 - LiteLLM:DEBUG: utils.py:5620 - checking potential_model_names in litellm.model_cost: {'split_model': '88d4dde8-817a-4c20-9bec-442961096d25', 'combined_model_name': '88d4dde8-817a-4c20-9bec-442961096d25', 'stripped_model_name': '88d4dde8-817a-4c20-9bec-442961096d25', 'combined_stripped_model_name': '88d4dde8-817a-4c20-9bec-442961096d25', 'custom_llm_provider': None}
+18:52:14 - LiteLLM:DEBUG: utils.py:5921 - Error getting model info: This model isn't mapped yet. Add it here - https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json
+18:52:14 - LiteLLM:DEBUG: utils.py:2900 - added/updated model=88d4dde8-817a-4c20-9bec-442961096d25 in litellm.model_cost: 88d4dde8-817a-4c20-9bec-442961096d25
+18:52:14 - LiteLLM:DEBUG: utils.py:5620 - checking potential_model_names in litellm.model_cost: {'split_model': '2ab3179b-62e9-4720-9ba7-0a2f12536cfa', 'combined_model_name': '2ab3179b-62e9-4720-9ba7-0a2f12536cfa', 'stripped_model_name': '2ab3179b-62e9-4720-9ba7-0a2f12536cfa', 'combined_stripped_model_name': '2ab3179b-62e9-4720-9ba7-0a2f12536cfa', 'custom_llm_provider': None}
+18:52:14 - LiteLLM:DEBUG: utils.py:5921 - Error getting model info: This model isn't mapped yet. Add it here - https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json
+18:52:14 - LiteLLM:DEBUG: utils.py:2900 - added/updated model=2ab3179b-62e9-4720-9ba7-0a2f12536cfa in litellm.model_cost: 2ab3179b-62e9-4720-9ba7-0a2f12536cfa
+18:52:14 - LiteLLM Proxy:DEBUG: proxy_server.py:5461 - guardrails from the DB []
+18:52:14 - LiteLLM Proxy:INFO: policy_registry.py:577 - Synced 0 production policies and 0 draft/published (by ID) from DB to in-memory registry
+18:52:14 - LiteLLM Proxy:INFO: attachment_registry.py:481 - Synced 0 attachments from DB to in-memory registry
+18:52:14 - LiteLLM Proxy:DEBUG: proxy_server.py:5497 - Successfully synced policies and attachments from DB
+18:52:14 - LiteLLM:DEBUG: mcp_server_manager.py:2644 - Loading MCP servers from database into registry...
+18:52:14 - LiteLLM:INFO: mcp_server_manager.py:2664 - Found 1 MCP servers in database
+18:52:14 - LiteLLM:DEBUG: mcp_server_manager.py:2688 - Building server from DB: 28a195c6-0224-4765-af9b-46f7a7f65ccb (deepwiki)
+18:52:14 - LiteLLM:DEBUG: mcp_server_manager.py:2697 - MCP registry refreshed (1 servers in registry)
+18:52:14 - LiteLLM Proxy:DEBUG: pass_through_endpoints.py:2409 - initializing pass through endpoints
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.weave
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.litellm_agent
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.dotprompt
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:65 - Found prompt_initializer_registry in litellm.integrations.dotprompt: ['dotprompt']
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.gitlab
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:65 - Found prompt_initializer_registry in litellm.integrations.gitlab: ['gitlab']
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.azure_sentinel
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.arize
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:65 - Found prompt_initializer_registry in litellm.integrations.arize: ['arize_phoenix']
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.agentops
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.compression_interception
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.focus
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.prometheus_helpers
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.generic_prompt_management
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:65 - Found prompt_initializer_registry in litellm.integrations.generic_prompt_management: ['generic_prompt_management']
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.levo
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.websearch_interception
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.deepeval
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.bitbucket
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:65 - Found prompt_initializer_registry in litellm.integrations.bitbucket: ['bitbucket']
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.vantage
+18:52:14 - LiteLLM Proxy:DEBUG: prompt_registry.py:76 - Discovered 5 prompt initializers: ['dotprompt', 'gitlab', 'arize_phoenix', 'generic_prompt_management', 'bitbucket']
+18:52:14 - LiteLLM Proxy:INFO: proxy_server.py:5640 - Loading 0 search tool(s) from database into router
+18:52:14 - LiteLLM Proxy:DEBUG: proxy_server.py:5660 - No search tools found in database, keeping config-loaded search tools (if any)
+18:52:14 - LiteLLM Proxy:INFO: tool_registry_writer.py:329 - ToolPolicyRegistry: synced 17 tool policies and 1 object permissions from DB
+18:52:14 - LiteLLM Proxy:DEBUG: proxy_server.py:5517 - Successfully synced tool policy from DB
+18:52:14 - LiteLLM:DEBUG: focus_logger.py:167 - No Focus export logger registered; skipping scheduler
+18:52:14 - LiteLLM Proxy:DEBUG: proxy_server.py:6759 - key_rotation_enabled: False
+18:52:14 - LiteLLM Proxy:DEBUG: proxy_server.py:6793 - Key rotation disabled (set LITELLM_KEY_ROTATION_ENABLED=true to enable)
+18:52:14 - LiteLLM Proxy:DEBUG: proxy_server.py:6824 - expired_ui_session_key_cleanup_enabled: False
+18:52:14 - LiteLLM Proxy:DEBUG: proxy_server.py:6869 - Expired UI session key cleanup disabled (set LITELLM_EXPIRED_UI_SESSION_KEY_CLEANUP_ENABLED=true to enable)
+18:52:14 - LiteLLM Proxy:INFO: proxy_server.py:6622 - Batch cost check job scheduled successfully
+18:52:14 - LiteLLM Proxy:INFO: proxy_server.py:6653 - Responses cost check job scheduled successfully
+18:52:14 - LiteLLM Proxy:INFO: proxy_server.py:6672 - APScheduler started with memory leak prevention settings: removed jitter, increased intervals, misfire_grace_time=3600
+18:52:14 - LiteLLM Proxy:DEBUG: proxy_server.py:7036 - LiteLLM: Pyroscope profiling is disabled (set LITELLM_ENABLE_PYROSCOPE=true to enable).
+18:52:14 - LiteLLM Proxy:INFO: proxy_server.py:755 - SESSION REUSE: Created shared aiohttp session for connection pooling (ID: 6165409104, limit=1000, limit_per_host=500)
+INFO:     Application startup complete.
+INFO:     Uvicorn running on http://0.0.0.0:4000 (Press CTRL+C to quit)
+18:52:21 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/organization/list
+18:52:21 - LiteLLM:DEBUG: user_api_key_auth.py:1023 - api key not found in cache.
+18:52:21 - LiteLLM Proxy:DEBUG: utils.py:3061 - PrismaClient: find_unique for token: 00f60cfa9df317dade7cb93c0bdb83b44250c865daf6920ea0de433d523a894e
+18:52:21 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/team/list
+18:52:21 - LiteLLM:DEBUG: user_api_key_auth.py:1023 - api key not found in cache.
+18:52:21 - LiteLLM Proxy:DEBUG: utils.py:3061 - PrismaClient: find_unique for token: 00f60cfa9df317dade7cb93c0bdb83b44250c865daf6920ea0de433d523a894e
+18:52:21 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/tag/list
+18:52:21 - LiteLLM:DEBUG: user_api_key_auth.py:1023 - api key not found in cache.
+18:52:21 - LiteLLM Proxy:DEBUG: utils.py:3061 - PrismaClient: find_unique for token: 00f60cfa9df317dade7cb93c0bdb83b44250c865daf6920ea0de433d523a894e
+18:52:21 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/key/list
+18:52:21 - LiteLLM:DEBUG: user_api_key_auth.py:1023 - api key not found in cache.
+18:52:21 - LiteLLM Proxy:DEBUG: utils.py:3061 - PrismaClient: find_unique for token: 00f60cfa9df317dade7cb93c0bdb83b44250c865daf6920ea0de433d523a894e
+
+#------------------------------------------------------------#
+#                                                            #
+#            'The thing I wish you improved is...'            #
+#        https://github.com/BerriAI/litellm/issues/new        #
+#                                                            #
+#------------------------------------------------------------#
+
+ Thank you for using LiteLLM! - Krrish & Ishaan
+
+
+
+Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
+
+
+LiteLLM: Proxy initialized with Config, Set models:
+    gpt-5.3-codex
+INFO:     127.0.0.1:65291 - "GET /project/list HTTP/1.1" 404 Not Found
+INFO:     127.0.0.1:65293 - "HEAD / HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65293 - "GET /__next._tree.txt?_rsc=1r34m HTTP/1.1" 404 Not Found
+18:52:21 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:21.984645+00:00
+18:52:21 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:21.987707+00:00
+18:52:21 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:21.988286+00:00
+18:52:21 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:21.988897+00:00
+18:52:21 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:22 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:22 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:22 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:22 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:52:22 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:52:22 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:52:22 - LiteLLM Proxy:DEBUG: key_management_endpoints.py:4526 - Entering list_keys function
+18:52:22 - LiteLLM Proxy:DEBUG: key_management_endpoints.py:4950 - Filter conditions: {'OR': [{'team_id': None}, {'team_id': {'not': 'litellm-dashboard'}}]}
+18:52:22 - LiteLLM Proxy:DEBUG: key_management_endpoints.py:5020 - Pagination: skip=0, take=50
+18:52:22 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+INFO:     127.0.0.1:65283 - "GET /organization/list HTTP/1.1" 200 OK
+18:52:22 - LiteLLM Proxy:DEBUG: key_management_endpoints.py:5062 - Fetched 4 keys
+18:52:22 - LiteLLM Proxy:DEBUG: key_management_endpoints.py:5074 - Total count of keys: 4
+INFO:     127.0.0.1:65285 - "GET /team/list HTTP/1.1" 200 OK
+18:52:22 - LiteLLM Proxy:DEBUG: key_management_endpoints.py:4604 - Successfully prepared response
+INFO:     127.0.0.1:65290 - "GET /key/list?page=1&size=50&sort_by=created_at&sort_order=desc&expand=user&return_full_object=true&include_team_keys=true&include_created_by_keys=true HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65288 - "GET /tag/list HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65290 - "GET /project/list HTTP/1.1" 404 Not Found
+18:52:24 - LiteLLM Proxy:DEBUG: spend_update_queue.py:39 - Aggregating updates by entity type: []
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1122 - User Spend transactions: {}
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1165 - End-User Spend transactions: {}
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1180 - KEY Spend transactions: {}
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1221 - Team Spend transactions: {}
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1269 - Team Membership Spend transactions: {}
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1342 - Org Spend transactions: {}
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1435 - Tag Spend transactions: {}
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1435 - Agent Spend transactions: {}
+18:52:24 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily User Spend transactions: 0
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily user spend update
+18:52:24 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Team Spend transactions: 0
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily team spend update
+18:52:24 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Org Spend transactions: 0
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily org spend update
+18:52:24 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily End_user Spend transactions: 0
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily end_user spend update
+18:52:24 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Agent Spend transactions: 0
+18:52:24 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily agent spend update
+18:52:24 - LiteLLM Proxy:DEBUG: utils.py:4936 - Spend Logs transactions: 0
+INFO:     127.0.0.1:65290 - "GET /project/list HTTP/1.1" 404 Not Found
+18:52:28 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/organization/list
+18:52:28 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:28 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:28.414705+00:00
+18:52:28 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/team/list
+18:52:28 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:28 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:28.416982+00:00
+18:52:28 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/models
+18:52:28 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:28 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:28.426995+00:00
+18:52:28 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/v2/user/info
+18:52:28 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:28 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:28.430882+00:00
+18:52:28 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/v1/access_group
+18:52:28 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:28 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:28.434375+00:00
+18:52:28 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/v1/mcp/server
+18:52:28 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:28 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:28.437819+00:00
+18:52:28 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:28 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:28 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:28 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:52:28 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:28 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:28 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:52:28 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:52:28 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+INFO:     127.0.0.1:65326 - "GET /v2/user/info HTTP/1.1" 200 OK
+18:52:28 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:52:28 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/v1/mcp/access_groups
+18:52:28 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:28 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:28.460826+00:00
+18:52:28 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+INFO:     127.0.0.1:65324 - "GET /models?include_model_access_groups=True&return_wildcard_routes=True&scope=expand HTTP/1.1" 200 OK
+18:52:28 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/v1/mcp/toolset
+18:52:28 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:28 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:28.463333+00:00
+INFO:     127.0.0.1:65290 - "GET /organization/list HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65328 - "GET /v1/access_group HTTP/1.1" 200 OK
+18:52:28 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:52:28 - LiteLLM:DEBUG: mcp_server_manager.py:796 - Admin user without explicit object_permission - returning all servers
+INFO:     127.0.0.1:65329 - "GET /v1/mcp/server HTTP/1.1" 200 OK
+18:52:28 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:28 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+INFO:     127.0.0.1:65321 - "GET /team/list HTTP/1.1" 200 OK
+18:52:28 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:52:28 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:52:28 - LiteLLM Proxy:WARNING: toolset_db.py:60 - litellm.proxy._experimental.mcp_server.toolset_db::list_mcp_toolsets - 'Prisma' object has no attribute 'litellm_mcptoolsettable'
+INFO:     127.0.0.1:65324 - "GET /v1/mcp/toolset HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65326 - "GET /v1/mcp/access_groups HTTP/1.1" 200 OK
+18:52:30 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/organization/list
+18:52:30 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:30 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:30.307066+00:00
+18:52:30 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/team/list
+18:52:30 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:30 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:30.310005+00:00
+INFO:     127.0.0.1:65321 - "GET /project/list HTTP/1.1" 404 Not Found
+18:52:30 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/tag/list
+18:52:30 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:30 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:30.314509+00:00
+18:52:30 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:30 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:30 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:30 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:52:30 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:52:30 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+INFO:     127.0.0.1:65326 - "GET /organization/list HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65324 - "GET /team/list HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65329 - "GET /tag/list HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65329 - "GET /project/list HTTP/1.1" 404 Not Found
+18:52:34 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/organization/list
+18:52:34 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:34 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:34.018157+00:00
+18:52:34 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/team/list
+18:52:34 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:34 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:34.038105+00:00
+18:52:34 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/tag/list
+18:52:34 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:34 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:34.045120+00:00
+INFO:     127.0.0.1:65321 - "GET /project/list HTTP/1.1" 404 Not Found
+18:52:34 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:34 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:34 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:34 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:52:34 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:52:34 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+INFO:     127.0.0.1:65329 - "GET /organization/list HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65324 - "GET /team/list HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65326 - "GET /tag/list HTTP/1.1" 200 OK
+18:52:35 - LiteLLM Proxy:DEBUG: spend_update_queue.py:39 - Aggregating updates by entity type: []
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1122 - User Spend transactions: {}
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1165 - End-User Spend transactions: {}
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1180 - KEY Spend transactions: {}
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1221 - Team Spend transactions: {}
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1269 - Team Membership Spend transactions: {}
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1342 - Org Spend transactions: {}
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1435 - Tag Spend transactions: {}
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1435 - Agent Spend transactions: {}
+18:52:35 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily User Spend transactions: 0
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily user spend update
+18:52:35 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Team Spend transactions: 0
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily team spend update
+18:52:35 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Org Spend transactions: 0
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily org spend update
+18:52:35 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily End_user Spend transactions: 0
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily end_user spend update
+18:52:35 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Agent Spend transactions: 0
+18:52:35 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily agent spend update
+18:52:35 - LiteLLM Proxy:DEBUG: utils.py:4936 - Spend Logs transactions: 0
+INFO:     127.0.0.1:65326 - "GET /project/list HTTP/1.1" 404 Not Found
+18:52:39 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:44 - LiteLLM Proxy:DEBUG: proxy_server.py:4256 - len new_models: 2
+18:52:44 - LiteLLM Proxy:DEBUG: proxy_server.py:5461 - guardrails from the DB []
+18:52:44 - LiteLLM Proxy:INFO: policy_registry.py:577 - Synced 0 production policies and 0 draft/published (by ID) from DB to in-memory registry
+18:52:44 - LiteLLM Proxy:INFO: attachment_registry.py:481 - Synced 0 attachments from DB to in-memory registry
+18:52:44 - LiteLLM Proxy:DEBUG: proxy_server.py:5497 - Successfully synced policies and attachments from DB
+18:52:44 - LiteLLM:DEBUG: mcp_server_manager.py:2644 - Loading MCP servers from database into registry...
+18:52:44 - LiteLLM:INFO: mcp_server_manager.py:2664 - Found 1 MCP servers in database
+18:52:44 - LiteLLM:DEBUG: mcp_server_manager.py:2697 - MCP registry refreshed (1 servers in registry)
+18:52:44 - LiteLLM Proxy:DEBUG: pass_through_endpoints.py:2409 - initializing pass through endpoints
+18:52:44 - LiteLLM Proxy:INFO: proxy_server.py:5640 - Loading 0 search tool(s) from database into router
+18:52:44 - LiteLLM Proxy:DEBUG: proxy_server.py:5660 - No search tools found in database, keeping config-loaded search tools (if any)
+18:52:44 - LiteLLM Proxy:INFO: tool_registry_writer.py:329 - ToolPolicyRegistry: synced 17 tool policies and 1 object permissions from DB
+18:52:44 - LiteLLM Proxy:DEBUG: proxy_server.py:5517 - Successfully synced tool policy from DB
+18:52:46 - LiteLLM Proxy:DEBUG: spend_update_queue.py:39 - Aggregating updates by entity type: []
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1122 - User Spend transactions: {}
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1165 - End-User Spend transactions: {}
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1180 - KEY Spend transactions: {}
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1221 - Team Spend transactions: {}
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1269 - Team Membership Spend transactions: {}
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1342 - Org Spend transactions: {}
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1435 - Tag Spend transactions: {}
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1435 - Agent Spend transactions: {}
+18:52:46 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily User Spend transactions: 0
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily user spend update
+18:52:46 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Team Spend transactions: 0
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily team spend update
+18:52:46 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Org Spend transactions: 0
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily org spend update
+18:52:46 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily End_user Spend transactions: 0
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily end_user spend update
+18:52:46 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Agent Spend transactions: 0
+18:52:46 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily agent spend update
+18:52:46 - LiteLLM Proxy:DEBUG: utils.py:4936 - Spend Logs transactions: 0
+18:52:54 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/organization/list
+18:52:54 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:54 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:54.075515+00:00
+18:52:54 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/team/list
+18:52:54 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:54 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:54.133027+00:00
+INFO:     127.0.0.1:65389 - "GET /project/list HTTP/1.1" 404 Not Found
+18:52:54 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/tag/list
+18:52:54 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:54 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:54.284965+00:00
+18:52:54 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/key/list
+18:52:54 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:52:54 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:22:54.295543+00:00
+18:52:54 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:54 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:54 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:54 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:52:54 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:52:54 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:52:54 - LiteLLM Proxy:DEBUG: key_management_endpoints.py:4526 - Entering list_keys function
+18:52:54 - LiteLLM Proxy:DEBUG: key_management_endpoints.py:4950 - Filter conditions: {'OR': [{'team_id': None}, {'team_id': {'not': 'litellm-dashboard'}}]}
+18:52:54 - LiteLLM Proxy:DEBUG: key_management_endpoints.py:5020 - Pagination: skip=0, take=50
+18:52:54 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:52:54 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+INFO:     127.0.0.1:65385 - "GET /organization/list HTTP/1.1" 200 OK
+18:52:54 - LiteLLM Proxy:DEBUG: key_management_endpoints.py:5062 - Fetched 4 keys
+INFO:     127.0.0.1:65392 - "GET /tag/list HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65387 - "GET /team/list HTTP/1.1" 200 OK
+18:52:54 - LiteLLM Proxy:DEBUG: key_management_endpoints.py:5074 - Total count of keys: 4
+18:52:54 - LiteLLM Proxy:DEBUG: key_management_endpoints.py:4604 - Successfully prepared response
+INFO:     127.0.0.1:65393 - "GET /key/list?page=1&size=50&sort_by=created_at&sort_order=desc&expand=user&return_full_object=true&include_team_keys=true&include_created_by_keys=true HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65393 - "GET /project/list HTTP/1.1" 404 Not Found
+18:52:58 - LiteLLM Proxy:DEBUG: spend_update_queue.py:39 - Aggregating updates by entity type: []
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1122 - User Spend transactions: {}
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1165 - End-User Spend transactions: {}
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1180 - KEY Spend transactions: {}
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1221 - Team Spend transactions: {}
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1269 - Team Membership Spend transactions: {}
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1342 - Org Spend transactions: {}
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1435 - Tag Spend transactions: {}
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1435 - Agent Spend transactions: {}
+18:52:58 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily User Spend transactions: 0
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily user spend update
+18:52:58 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Team Spend transactions: 0
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily team spend update
+18:52:58 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Org Spend transactions: 0
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily org spend update
+18:52:58 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily End_user Spend transactions: 0
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily end_user spend update
+18:52:58 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Agent Spend transactions: 0
+18:52:58 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily agent spend update
+18:52:58 - LiteLLM Proxy:DEBUG: utils.py:4936 - Spend Logs transactions: 0
+18:53:04 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:53:05 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/health/readiness
+18:53:05 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/organization/list
+18:53:05 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:05 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:05.652862+00:00
+18:53:06 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/team/list
+18:53:06 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:06 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:06.042541+00:00
+18:53:06 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/tag/list
+18:53:06 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:06 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:06.085990+00:00
+INFO:     127.0.0.1:65443 - "GET /project/list HTTP/1.1" 404 Not Found
+18:53:06 - LiteLLM:DEBUG: http_handler.py:840 - Using AiohttpTransport...
+INFO:     127.0.0.1:65436 - "GET /health/readiness HTTP/1.1" 200 OK
+18:53:06 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:53:06 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:53:06 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:53:06 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:53:06 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:53:06 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+INFO:     127.0.0.1:65438 - "GET /organization/list HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65442 - "GET /tag/list HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65440 - "GET /team/list HTTP/1.1" 200 OK
+18:53:08 - LiteLLM Proxy:DEBUG: spend_update_queue.py:39 - Aggregating updates by entity type: []
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1122 - User Spend transactions: {}
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1165 - End-User Spend transactions: {}
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1180 - KEY Spend transactions: {}
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1221 - Team Spend transactions: {}
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1269 - Team Membership Spend transactions: {}
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1342 - Org Spend transactions: {}
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1435 - Tag Spend transactions: {}
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1435 - Agent Spend transactions: {}
+18:53:09 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily User Spend transactions: 0
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily user spend update
+18:53:09 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Team Spend transactions: 0
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily team spend update
+18:53:09 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Org Spend transactions: 0
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily org spend update
+18:53:09 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily End_user Spend transactions: 0
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily end_user spend update
+18:53:09 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Agent Spend transactions: 0
+18:53:09 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily agent spend update
+18:53:09 - LiteLLM Proxy:DEBUG: utils.py:4936 - Spend Logs transactions: 0
+18:53:09 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/v1/mcp/server
+18:53:09 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:09.447694+00:00
+18:53:09 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/v1/mcp/toolset
+18:53:09 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:09.480143+00:00
+18:53:09 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/get/mcp_semantic_filter_settings
+18:53:09 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:09.511525+00:00
+18:53:09 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/model_group/info
+18:53:09 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:09.521031+00:00
+18:53:09 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/config/list
+18:53:09 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:09.525741+00:00
+18:53:09 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/v1/mcp/network/client-ip
+18:53:09 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:09.533092+00:00
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:53:09 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+INFO:     127.0.0.1:65461 - "GET /v1/mcp/network/client-ip HTTP/1.1" 200 OK
+18:53:09 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:53:09 - LiteLLM Proxy:DEBUG: model_checks.py:131 - ALL KEY MODELS - 0
+18:53:09 - LiteLLM Proxy:DEBUG: model_checks.py:166 - ALL TEAM MODELS - 0
+18:53:09 - LiteLLM:DEBUG: utils.py:5620 - checking potential_model_names in litellm.model_cost: {'split_model': 'gpt-5.3-codex', 'combined_model_name': 'openai/gpt-5.3-codex', 'stripped_model_name': 'gpt-5.3-codex', 'combined_stripped_model_name': 'openai/gpt-5.3-codex', 'custom_llm_provider': 'openai'}
+18:53:09 - LiteLLM:DEBUG: utils.py:5620 - checking potential_model_names in litellm.model_cost: {'split_model': 'gpt-5.3-codex', 'combined_model_name': 'openai/gpt-5.3-codex', 'stripped_model_name': 'gpt-5.3-codex', 'combined_stripped_model_name': 'openai/gpt-5.3-codex', 'custom_llm_provider': 'openai'}
+18:53:09 - LiteLLM:DEBUG: utils.py:5620 - checking potential_model_names in litellm.model_cost: {'split_model': 'gpt-5.3-codex', 'combined_model_name': 'openai/gpt-5.3-codex', 'stripped_model_name': 'openai/gpt-5.3-codex', 'combined_stripped_model_name': 'openai/gpt-5.3-codex', 'custom_llm_provider': 'openai'}
+18:53:09 - LiteLLM:DEBUG: utils.py:5620 - checking potential_model_names in litellm.model_cost: {'split_model': 'oia-gpt-realtime', 'combined_model_name': 'azure/oia-gpt-realtime', 'stripped_model_name': 'azure/oia-gpt-realtime', 'combined_stripped_model_name': 'azure/oia-gpt-realtime', 'custom_llm_provider': 'azure'}
+18:53:09 - LiteLLM:DEBUG: utils.py:5921 - Error getting model info: This model isn't mapped yet. Add it here - https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json
+18:53:09 - LiteLLM:DEBUG: utils.py:5620 - checking potential_model_names in litellm.model_cost: {'split_model': 'oia-gpt-realtime', 'combined_model_name': 'azure/oia-gpt-realtime', 'stripped_model_name': 'azure/oia-gpt-realtime', 'combined_stripped_model_name': 'azure/oia-gpt-realtime', 'custom_llm_provider': 'azure'}
+18:53:09 - LiteLLM:DEBUG: utils.py:5921 - Error getting model info: This model isn't mapped yet. Add it here - https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json
+18:53:09 - LiteLLM:DEBUG: utils.py:5620 - checking potential_model_names in litellm.model_cost: {'split_model': 'gemini-3.1-flash-image-preview', 'combined_model_name': 'vertex_ai/gemini-3.1-flash-image-preview', 'stripped_model_name': 'gemini-3.1-flash-image-preview', 'combined_stripped_model_name': 'vertex_ai/gemini-3.1-flash-image-preview', 'custom_llm_provider': 'vertex_ai'}
+18:53:09 - LiteLLM:DEBUG: utils.py:5620 - checking potential_model_names in litellm.model_cost: {'split_model': 'gemini-3.1-flash-image-preview', 'combined_model_name': 'gemini-3.1-flash-image-preview', 'stripped_model_name': 'gemini-3.1-flash-image-preview', 'combined_stripped_model_name': 'gemini-3.1-flash-image-preview', 'custom_llm_provider': 'vertex_ai'}
+18:53:09 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/v1/mcp/server/submissions
+18:53:09 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:09.669506+00:00
+18:53:09 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:53:09 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:53:09 - LiteLLM:DEBUG: mcp_server_manager.py:796 - Admin user without explicit object_permission - returning all servers
+INFO:     127.0.0.1:65440 - "GET /v1/mcp/server HTTP/1.1" 200 OK
+18:53:09 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:53:09 - LiteLLM Proxy:WARNING: toolset_db.py:60 - litellm.proxy._experimental.mcp_server.toolset_db::list_mcp_toolsets - 'Prisma' object has no attribute 'litellm_mcptoolsettable'
+INFO:     127.0.0.1:65442 - "GET /v1/mcp/toolset HTTP/1.1" 200 OK
+18:53:09 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:53:09 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/v1/mcp/server/health
+18:53:09 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:09.692446+00:00
+INFO:     127.0.0.1:65442 - "HEAD / HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65436 - "GET /model_group/info HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65443 - "GET /config/list?config_type=general_settings HTTP/1.1" 200 OK
+18:53:09 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/config/list
+18:53:09 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:09.731878+00:00
+INFO:     127.0.0.1:65436 - "GET /ui/assets/logos/github.svg HTTP/1.1" 304 Not Modified
+INFO:     127.0.0.1:65443 - "GET /ui/assets/logos/slack.svg HTTP/1.1" 304 Not Modified
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+INFO:     127.0.0.1:65436 - "GET /ui/assets/logos/notion.svg HTTP/1.1" 304 Not Modified
+INFO:     127.0.0.1:65443 - "GET /ui/assets/logos/linear.svg HTTP/1.1" 304 Not Modified
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+INFO:     127.0.0.1:65436 - "GET /ui/assets/logos/jira.svg HTTP/1.1" 304 Not Modified
+INFO:     127.0.0.1:65438 - "GET /get/mcp_semantic_filter_settings HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65443 - "GET /ui/assets/logos/figma.svg HTTP/1.1" 304 Not Modified
+18:53:09 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:53:09 - LiteLLM:DEBUG: mcp_server_manager.py:796 - Admin user without explicit object_permission - returning all servers
+18:53:09 - LiteLLM:DEBUG: client.py:273 - litellm headers for streamable_http_client: {}
+18:53:09 - LiteLLM:DEBUG: client.py:402 - MCP client using SSL configuration: SSLContext
+18:53:09 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+INFO:     127.0.0.1:65436 - "GET /ui/assets/logos/gmail.svg HTTP/1.1" 304 Not Modified
+18:53:09 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/model_group/info
+18:53:09 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:09 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:09.989425+00:00
+INFO:     127.0.0.1:65443 - "GET /ui/assets/logos/stripe.svg HTTP/1.1" 304 Not Modified
+INFO:     127.0.0.1:65438 - "GET /ui/assets/logos/google_drive.svg HTTP/1.1" 304 Not Modified
+18:53:09 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+INFO:     127.0.0.1:65443 - "GET /ui/assets/logos/shopify.svg HTTP/1.1" 304 Not Modified
+INFO:     127.0.0.1:65438 - "GET /ui/assets/logos/salesforce.svg HTTP/1.1" 304 Not Modified
+INFO:     127.0.0.1:65442 - "GET /config/list?config_type=general_settings HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65438 - "GET /ui/assets/logos/hubspot.svg HTTP/1.1" 304 Not Modified
+INFO:     127.0.0.1:65443 - "GET /ui/assets/logos/twilio.svg HTTP/1.1" 304 Not Modified
+INFO:     127.0.0.1:65461 - "GET /v1/mcp/server/submissions HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65442 - "GET /ui/assets/logos/cloudflare.svg HTTP/1.1" 304 Not Modified
+18:53:10 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+INFO:     127.0.0.1:65438 - "GET /ui/assets/logos/postgresql.svg HTTP/1.1" 304 Not Modified
+INFO:     127.0.0.1:65443 - "GET /ui/assets/logos/sentry.svg HTTP/1.1" 304 Not Modified
+INFO:     127.0.0.1:65461 - "GET /ui/assets/logos/snowflake.svg HTTP/1.1" 304 Not Modified
+INFO:     127.0.0.1:65442 - "GET /ui/assets/logos/zapier.svg HTTP/1.1" 304 Not Modified
+INFO:     127.0.0.1:65461 - "GET /__next._tree.txt?_rsc=1r34m HTTP/1.1" 404 Not Found
+18:53:10 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:53:10 - LiteLLM Proxy:DEBUG: model_checks.py:131 - ALL KEY MODELS - 0
+18:53:10 - LiteLLM Proxy:DEBUG: model_checks.py:166 - ALL TEAM MODELS - 0
+18:53:10 - LiteLLM:DEBUG: utils.py:5620 - checking potential_model_names in litellm.model_cost: {'split_model': 'oia-gpt-realtime', 'combined_model_name': 'azure/oia-gpt-realtime', 'stripped_model_name': 'azure/oia-gpt-realtime', 'combined_stripped_model_name': 'azure/oia-gpt-realtime', 'custom_llm_provider': 'azure'}
+18:53:10 - LiteLLM:DEBUG: utils.py:5921 - Error getting model info: This model isn't mapped yet. Add it here - https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json
+18:53:10 - LiteLLM:DEBUG: utils.py:5620 - checking potential_model_names in litellm.model_cost: {'split_model': 'oia-gpt-realtime', 'combined_model_name': 'azure/oia-gpt-realtime', 'stripped_model_name': 'azure/oia-gpt-realtime', 'combined_stripped_model_name': 'azure/oia-gpt-realtime', 'custom_llm_provider': 'azure'}
+18:53:10 - LiteLLM:DEBUG: utils.py:5921 - Error getting model info: This model isn't mapped yet. Add it here - https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json
+INFO:     127.0.0.1:65443 - "GET /ui/assets/logos/gitlab.svg HTTP/1.1" 304 Not Modified
+INFO:     127.0.0.1:65438 - "GET /ui/assets/logos/google.svg HTTP/1.1" 304 Not Modified
+INFO:     127.0.0.1:65436 - "GET /model_group/info HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65440 - "GET /v1/mcp/server/health HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65440 - "GET / HTTP/1.1" 200 OK
+18:53:17 - LiteLLM Proxy:DEBUG: custom_openapi_spec.py:311 - Successfully added ProxyChatCompletionRequest schema to OpenAPI spec
+18:53:17 - LiteLLM Proxy:DEBUG: custom_openapi_spec.py:311 - Successfully added EmbeddingRequest schema to OpenAPI spec
+18:53:17 - LiteLLM Proxy:DEBUG: custom_openapi_spec.py:315 - Could not get schema for ResponsesAPIRequestParams
+INFO:     127.0.0.1:65440 - "GET /openapi.json HTTP/1.1" 200 OK
+18:53:17 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/organization/list
+18:53:17 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:17 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:17.073159+00:00
+18:53:17 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/team/list
+18:53:17 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:17 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:17.085893+00:00
+18:53:17 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/v1/mcp/server
+18:53:17 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:17 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:17.089077+00:00
+18:53:17 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/v1/mcp/server/health
+18:53:17 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:17 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:17.093754+00:00
+18:53:17 - LiteLLM Proxy:DEBUG: http_parsing_utils.py:529 - populate_request_with_path_params: No vector_store_id present in path=/v1/mcp/toolset
+18:53:17 - LiteLLM:DEBUG: user_api_key_auth.py:1099 - 404: {'error': "Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard."}
+18:53:17 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1348 - Checking if token expired, expiry time 2026-04-29 11:16:22.190000+00:00 and current time 2026-04-28 13:23:17.096736+00:00
+18:53:17 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:53:17 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:53:17 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:53:17 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:53:17 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:53:17 - LiteLLM:DEBUG: mcp_server_manager.py:796 - Admin user without explicit object_permission - returning all servers
+INFO:     127.0.0.1:65438 - "GET /v1/mcp/server HTTP/1.1" 200 OK
+18:53:17 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:53:17 - LiteLLM Proxy:DEBUG: user_api_key_auth.py:1567 - centralized auth: team fetch failed (HTTPException: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."})
+18:53:17 - LiteLLM Proxy:DEBUG: proxy_server.py:4256 - len new_models: 2
+18:53:17 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:53:17 - LiteLLM:DEBUG: mcp_server_manager.py:796 - Admin user without explicit object_permission - returning all servers
+18:53:17 - LiteLLM:DEBUG: client.py:273 - litellm headers for streamable_http_client: {}
+18:53:17 - LiteLLM:DEBUG: client.py:402 - MCP client using SSL configuration: SSLContext
+18:53:17 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+18:53:17 - LiteLLM Proxy:WARNING: toolset_db.py:60 - litellm.proxy._experimental.mcp_server.toolset_db::list_mcp_toolsets - 'Prisma' object has no attribute 'litellm_mcptoolsettable'
+INFO:     127.0.0.1:65442 - "GET /v1/mcp/toolset HTTP/1.1" 200 OK
+18:53:17 - LiteLLM Proxy:DEBUG: auth_checks.py:4036 - Vector store registry not found, skipping vector store access check
+INFO:     127.0.0.1:65436 - "GET /organization/list HTTP/1.1" 200 OK
+INFO:     127.0.0.1:65443 - "GET /team/list HTTP/1.1" 200 OK
+18:53:17 - LiteLLM Proxy:DEBUG: proxy_server.py:5461 - guardrails from the DB []
+18:53:17 - LiteLLM Proxy:INFO: policy_registry.py:577 - Synced 0 production policies and 0 draft/published (by ID) from DB to in-memory registry
+18:53:17 - LiteLLM Proxy:INFO: attachment_registry.py:481 - Synced 0 attachments from DB to in-memory registry
+18:53:17 - LiteLLM Proxy:DEBUG: proxy_server.py:5497 - Successfully synced policies and attachments from DB
+18:53:17 - LiteLLM:DEBUG: mcp_server_manager.py:2644 - Loading MCP servers from database into registry...
+18:53:17 - LiteLLM:INFO: mcp_server_manager.py:2664 - Found 1 MCP servers in database
+18:53:17 - LiteLLM:DEBUG: mcp_server_manager.py:2697 - MCP registry refreshed (1 servers in registry)
+18:53:17 - LiteLLM Proxy:DEBUG: pass_through_endpoints.py:2409 - initializing pass through endpoints
+18:53:17 - LiteLLM Proxy:INFO: proxy_server.py:5640 - Loading 0 search tool(s) from database into router
+18:53:17 - LiteLLM Proxy:DEBUG: proxy_server.py:5660 - No search tools found in database, keeping config-loaded search tools (if any)
+18:53:17 - LiteLLM Proxy:INFO: tool_registry_writer.py:329 - ToolPolicyRegistry: synced 17 tool policies and 1 object permissions from DB
+18:53:17 - LiteLLM Proxy:DEBUG: proxy_server.py:5517 - Successfully synced tool policy from DB
+INFO:     127.0.0.1:65461 - "GET /v1/mcp/server/health HTTP/1.1" 200 OK
+18:53:19 - LiteLLM Proxy:DEBUG: spend_update_queue.py:39 - Aggregating updates by entity type: []
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1122 - User Spend transactions: {}
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1165 - End-User Spend transactions: {}
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1180 - KEY Spend transactions: {}
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1221 - Team Spend transactions: {}
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1269 - Team Membership Spend transactions: {}
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1342 - Org Spend transactions: {}
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1435 - Tag Spend transactions: {}
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1435 - Agent Spend transactions: {}
+18:53:20 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily User Spend transactions: 0
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily user spend update
+18:53:20 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Team Spend transactions: 0
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily team spend update
+18:53:20 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Org Spend transactions: 0
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily org spend update
+18:53:20 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily End_user Spend transactions: 0
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily end_user spend update
+18:53:20 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Agent Spend transactions: 0
+18:53:20 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily agent spend update
+18:53:20 - LiteLLM Proxy:DEBUG: utils.py:4936 - Spend Logs transactions: 0
+18:53:29 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:53:31 - LiteLLM Proxy:DEBUG: spend_update_queue.py:39 - Aggregating updates by entity type: []
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1122 - User Spend transactions: {}
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1165 - End-User Spend transactions: {}
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1180 - KEY Spend transactions: {}
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1221 - Team Spend transactions: {}
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1269 - Team Membership Spend transactions: {}
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1342 - Org Spend transactions: {}
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1435 - Tag Spend transactions: {}
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1435 - Agent Spend transactions: {}
+18:53:31 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily User Spend transactions: 0
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily user spend update
+18:53:31 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Team Spend transactions: 0
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily team spend update
+18:53:31 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Org Spend transactions: 0
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily org spend update
+18:53:31 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily End_user Spend transactions: 0
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily end_user spend update
+18:53:31 - LiteLLM Proxy:DEBUG: daily_spend_update_queue.py:99 - Aggregated daily spend update transactions: {}
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1576 - Daily Agent Spend transactions: 0
+18:53:31 - LiteLLM Proxy:DEBUG: db_spend_update_writer.py:1609 - No new transactions to process for daily agent spend update
+18:53:31 - LiteLLM Proxy:DEBUG: utils.py:4936 - Spend Logs transactions: 0

proxy_server_config.yaml

@@ -1,231 +1,7 @@
 model_list:
-  - model_name: gpt-3.5-turbo-end-user-test
+  # Gemini 2.5 Flash Native Audio (Latest - recommended)
+  - model_name: gpt-5.3-codex
     litellm_params:
-      model: gpt-3.5-turbo
-      region_name: "eu"
-    model_info:
-      id: "1"
-  - model_name: gpt-3.5-turbo-end-user-test
-    litellm_params:
-      model: openai/gpt-4.1-mini
-      api_key: os.environ/OPENAI_API_KEY # The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault
-  - model_name: gpt-3.5-turbo
-    litellm_params:
-      model: openai/gpt-4.1-mini
-      api_key: os.environ/OPENAI_API_KEY # The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault
-  - model_name: gpt-3.5-turbo-large
-    litellm_params: 
-      model: "gpt-3.5-turbo-1106"
+      model: openai/gpt-5.3-codex
       api_key: os.environ/OPENAI_API_KEY
-      rpm: 480
-      timeout: 300
-      stream_timeout: 60
-  - model_name: gpt-4
-    litellm_params:
-      model: openai/gpt-4.1-mini
-      api_key: os.environ/OPENAI_API_KEY # The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault
-      rpm: 480
-      timeout: 300
-      stream_timeout: 60
-  - model_name: sagemaker-completion-model
-    litellm_params:
-      model: sagemaker/berri-benchmarking-Llama-2-70b-chat-hf-4
-      input_cost_per_second: 0.000420  
-  - model_name: text-embedding-ada-002
-    litellm_params: 
-      model: openai/text-embedding-ada-002
-      api_key: os.environ/OPENAI_API_KEY
-    model_info:
-      mode: embedding
-      base_model: text-embedding-ada-002
-  - model_name: dall-e-2 # some tests use dall-e-2 which is now deprecated, alias to dall-e-3
-    litellm_params:
-      model: openai/dall-e-3
-  - model_name: openai-dall-e-3
-    litellm_params:
-      model: dall-e-3
-  - model_name: fake-openai-endpoint
-    litellm_params:
-      model: openai/gpt-3.5-turbo
-      api_key: fake-key
-      api_base: https://exampleopenaiendpoint-production.up.railway.app/
-  - model_name: fake-openai-endpoint-2
-    litellm_params:
-      model: openai/my-fake-model
-      api_key: my-fake-key
-      api_base: https://exampleopenaiendpoint-production.up.railway.app/
-      stream_timeout: 0.001
-      rpm: 1
-  - model_name: fake-openai-endpoint-3
-    litellm_params:
-      model: openai/my-fake-model
-      api_key: my-fake-key
-      api_base: https://exampleopenaiendpoint-production.up.railway.app/
-      stream_timeout: 0.001
-      rpm: 1000
-  - model_name: fake-openai-endpoint-4
-    litellm_params:
-      model: openai/my-fake-model
-      api_key: my-fake-key
-      api_base: https://exampleopenaiendpoint-production.up.railway.app/
-      num_retries: 50
-  - model_name: fake-openai-endpoint-3
-    litellm_params:
-      model: openai/my-fake-model-2
-      api_key: my-fake-key
-      api_base: https://exampleopenaiendpoint-production.up.railway.app/
-      stream_timeout: 0.001
-      rpm: 1000
-  - model_name: bad-model
-    litellm_params:
-      model: openai/bad-model
-      api_key: os.environ/OPENAI_API_KEY
-      api_base: https://exampleopenaiendpoint-production.up.railway.app/
-      mock_timeout: True
-      timeout: 60
-      rpm: 1000
-    model_info:
-      health_check_timeout: 1
-  - model_name: good-model
-    litellm_params:
-      model: openai/bad-model
-      api_key: os.environ/OPENAI_API_KEY
-      api_base: https://exampleopenaiendpoint-production.up.railway.app/
-      rpm: 1000
-    model_info:
-      health_check_timeout: 1
-  - model_name: "*"
-    litellm_params:
-      model: openai/*
-      api_key: os.environ/OPENAI_API_KEY
-  - model_name: realtime-v1
-    litellm_params:
-      model: azure/gpt-realtime-20250828-standard
-      api_version: "2025-08-28"
-      realtime_protocol: GA # Possible values: "GA"/ "v1", "beta" 
-
-  - model_name: realtime-beta
-    litellm_params:
-      model: azure/gpt-realtime-20250828-standard
-      api_version: 2025-04-01-preview
-
-
-  # provider specific wildcard routing
-  - model_name: "anthropic/*"
-    litellm_params:
-      model: "anthropic/*"
-      api_key: os.environ/ANTHROPIC_API_KEY
-  - model_name: "bedrock/*"
-    litellm_params:
-      model: "bedrock/*"
-  - model_name: "groq/*"
-    litellm_params:
-      model: "groq/*"
-      api_key: os.environ/GROQ_API_KEY
-  - model_name: mistral-embed
-    litellm_params:
-      model: mistral/mistral-embed
-  - model_name: gpt-instruct # [PROD TEST] - tests if `/health` automatically infers this to be a text completion model
-    litellm_params:
-      model: text-completion-openai/gpt-3.5-turbo-instruct
-  - model_name: fake-openai-endpoint-5
-    litellm_params:
-      model: openai/my-fake-model
-      api_key: my-fake-key
-      api_base: https://exampleopenaiendpoint-production.up.railway.app/
-      timeout: 1
-  - model_name: badly-configured-openai-endpoint
-    litellm_params:
-      model: openai/my-fake-model
-      api_key: my-fake-key
-      api_base: https://exampleopenaiendpoint-production.up.railway.appxxxx/
-  - model_name: gemini-1.5-flash
-    litellm_params:
-      model: gemini/gemini-1.5-flash
-      api_key: os.environ/GOOGLE_API_KEY
-  - model_name: gpt-4o
-    litellm_params:
-      model: gpt-4o
-      api_key: os.environ/OPENAI_API_KEY
-
-
-litellm_settings:
-  # set_verbose: True  # Uncomment this if you want to see verbose logs; not recommended in production
-  drop_params: True
-  success_callback: ["prometheus"]
-  # max_budget: 100 
-  # budget_duration: 30d
-  num_retries: 5
-  request_timeout: 600
-  telemetry: False
-  context_window_fallbacks: [{"gpt-3.5-turbo": ["gpt-3.5-turbo-large"]}]
-  default_team_settings: 
-    - team_id: team-1
-      success_callback: ["langfuse"]
-      failure_callback: ["langfuse"]
-      langfuse_public_key: os.environ/LANGFUSE_PROJECT1_PUBLIC # Project 1
-      langfuse_secret: os.environ/LANGFUSE_PROJECT1_SECRET # Project 1
-    - team_id: team-2
-      success_callback: ["langfuse"]
-      failure_callback: ["langfuse"]
-      langfuse_public_key: os.environ/LANGFUSE_PROJECT2_PUBLIC # Project 2
-      langfuse_secret: os.environ/LANGFUSE_PROJECT2_SECRET # Project 2
-      langfuse_host: https://us.cloud.langfuse.com
-  # cache: true   # [OPTIONAL] use for caching responses 
-  # enable_caching_on_provider_specific_optional_params: True  # Include provider-specific params in cache keys
-  # cache_params:  # And for shared health check
-  #   type: redis
-  #   host: localhost
-  #   port: 6379
-
-# For /fine_tuning/jobs endpoints
-finetune_settings:
-  - custom_llm_provider: azure
-    api_base: os.environ/AZURE_API_BASE
-    api_key: os.environ/AZURE_API_KEY
-    api_version: "2023-03-15-preview"
-  - custom_llm_provider: openai
-    api_key: os.environ/OPENAI_API_KEY
-
-# for /files endpoints
-files_settings:
-  - custom_llm_provider: azure
-    api_base: os.environ/AZURE_API_BASE
-    api_key: os.environ/AZURE_API_KEY
-    api_version: "2023-03-15-preview"
-  - custom_llm_provider: openai
-    api_key: os.environ/OPENAI_API_KEY
-
-router_settings:
-  routing_strategy: usage-based-routing-v2 
-  redis_host: os.environ/REDIS_HOST
-  redis_password: os.environ/REDIS_PASSWORD
-  redis_port: os.environ/REDIS_PORT
-  enable_pre_call_checks: true
-  model_group_alias: {"my-special-fake-model-alias-name": "fake-openai-endpoint-3"} 
-
-general_settings: 
-  master_key: sk-1234 # [OPTIONAL] Use to enforce auth on proxy. See - https://docs.litellm.ai/docs/proxy/virtual_keys
-  store_model_in_db: True
-  proxy_budget_rescheduler_min_time: 60
-  proxy_budget_rescheduler_max_time: 64
-  proxy_batch_write_at: 1
-  database_connection_pool_limit: 10
-  # background_health_checks: true
-  # use_shared_health_check: true
-  # health_check_interval: 30
-  # database_url: "postgresql://<user>:<password>@<host>:<port>/<dbname>" # [OPTIONAL] use for token-based auth to proxy
-
-  pass_through_endpoints:
-    - path: "/v1/rerank"                                  # route you want to add to LiteLLM Proxy Server
-      target: "https://api.cohere.com/v1/rerank"          # URL this route should forward requests to
-      headers:                                            # headers to forward to this URL
-        content-type: application/json                    # (Optional) Extra Headers to pass to this endpoint 
-        accept: application/json
-      forward_headers: True
-
-# environment_variables:
-  # settings for using redis caching
-  # REDIS_HOST: redis-16337.c322.us-east-1-2.ec2.cloud.redislabs.com
-  # REDIS_PORT: "16337"
-  # REDIS_PASSWORD: 
+  

tests/test_proxy_search_tool_auth.py

@@ -0,0 +1,212 @@
+"""
+Test search tool authorization - verify model-like access control for search tools.
+
+Tests that:
+1. Keys can only access search tools in their allowed_search_tools list
+2. Teams can only access search tools in their allowed_search_tools list
+3. Empty allowlists grant access to all search tools
+4. Credentials are never exposed in team/key metadata
+"""
+
+import pytest
+from unittest.mock import MagicMock, patch
+from fastapi import HTTPException
+
+# Import types and functions to test
+from litellm.proxy._types import LiteLLM_TeamTable, UserAPIKeyAuth
+from litellm.proxy.auth.auth_checks import (
+    can_key_call_search_tool,
+    can_team_call_search_tool,
+)
+
+
+@pytest.mark.asyncio
+async def test_key_can_access_allowed_search_tool():
+    """Test that a key can access a search tool in its allowlist."""
+    # Create a mock key with allowed_search_tools
+    mock_key = UserAPIKeyAuth(
+        token="sk-test-key",
+        models=["gpt-4"],
+        allowed_search_tools=["tavily-search", "perplexity-search"],
+    )
+
+    # Should succeed - tool is in allowlist
+    result = await can_key_call_search_tool(
+        search_tool_name="tavily-search",
+        valid_token=mock_key,
+    )
+    assert result is True
+
+
+@pytest.mark.asyncio
+async def test_key_denied_non_allowed_search_tool():
+    """Test that a key is denied access to a search tool not in its allowlist."""
+    mock_key = UserAPIKeyAuth(
+        token="sk-test-key",
+        models=["gpt-4"],
+        allowed_search_tools=["tavily-search"],  # Only tavily allowed
+    )
+
+    # Should raise exception - brave-search not in allowlist
+    with pytest.raises(Exception) as exc_info:
+        await can_key_call_search_tool(
+            search_tool_name="brave-search",
+            valid_token=mock_key,
+        )
+    assert "not allowed to access search tool" in str(exc_info.value)
+    assert "brave-search" in str(exc_info.value)
+
+
+@pytest.mark.asyncio
+async def test_key_empty_allowlist_grants_all_access():
+    """Test that an empty allowlist grants access to all search tools."""
+    mock_key = UserAPIKeyAuth(
+        token="sk-test-key",
+        models=["gpt-4"],
+        allowed_search_tools=[],  # Empty = all allowed
+    )
+
+    # Should succeed - empty list allows all
+    result = await can_key_call_search_tool(
+        search_tool_name="any-search-tool",
+        valid_token=mock_key,
+    )
+    assert result is True
+
+
+@pytest.mark.asyncio
+async def test_team_can_access_allowed_search_tool():
+    """Test that a team can access a search tool in its allowlist."""
+    mock_team = LiteLLM_TeamTable(
+        team_id="team-123",
+        team_alias="Marketing Team",
+        models=["gpt-4"],
+        allowed_search_tools=["tavily-search", "exa-search"],
+    )
+
+    # Should succeed - tool is in allowlist
+    result = await can_team_call_search_tool(
+        search_tool_name="tavily-search",
+        team_object=mock_team,
+    )
+    assert result is True
+
+
+@pytest.mark.asyncio
+async def test_team_denied_non_allowed_search_tool():
+    """Test that a team is denied access to a search tool not in its allowlist."""
+    mock_team = LiteLLM_TeamTable(
+        team_id="team-123",
+        team_alias="Engineering Team",
+        models=["gpt-4"],
+        allowed_search_tools=["perplexity-search"],  # Only perplexity allowed
+    )
+
+    # Should raise exception - tavily-search not in allowlist
+    with pytest.raises(Exception) as exc_info:
+        await can_team_call_search_tool(
+            search_tool_name="tavily-search",
+            team_object=mock_team,
+        )
+    assert "not allowed to access search tool" in str(exc_info.value)
+    assert "tavily-search" in str(exc_info.value)
+
+
+@pytest.mark.asyncio
+async def test_team_empty_allowlist_grants_all_access():
+    """Test that an empty team allowlist grants access to all search tools."""
+    mock_team = LiteLLM_TeamTable(
+        team_id="team-123",
+        team_alias="Admin Team",
+        models=["gpt-4"],
+        allowed_search_tools=[],  # Empty = all allowed
+    )
+
+    # Should succeed - empty list allows all
+    result = await can_team_call_search_tool(
+        search_tool_name="any-search-tool",
+        team_object=mock_team,
+    )
+    assert result is True
+
+
+@pytest.mark.asyncio
+async def test_team_none_allowed_search_tools():
+    """Test that None for allowed_search_tools (not set) grants access to all."""
+    mock_team = LiteLLM_TeamTable(
+        team_id="team-123",
+        team_alias="Legacy Team",
+        models=["gpt-4"],
+        allowed_search_tools=None,  # Not set = all allowed
+    )
+
+    # Should succeed - None allows all
+    result = await can_team_call_search_tool(
+        search_tool_name="any-search-tool",
+        team_object=mock_team,
+    )
+    assert result is True
+
+
+def test_credentials_not_in_team_metadata():
+    """Verify that search provider credentials are never stored in team metadata."""
+    mock_team = LiteLLM_TeamTable(
+        team_id="team-123",
+        team_alias="Test Team",
+        models=["gpt-4"],
+        allowed_search_tools=["tavily-search"],
+        metadata={"custom_field": "value"},  # No search_provider_config
+    )
+
+    # Verify metadata does not contain search_provider_config
+    assert mock_team.metadata is not None
+    assert "search_provider_config" not in mock_team.metadata
+    assert "api_key" not in str(mock_team.metadata)
+
+
+def test_credentials_not_in_key_metadata():
+    """Verify that search provider credentials are never stored in key metadata."""
+    mock_key = UserAPIKeyAuth(
+        token="sk-test-key",
+        models=["gpt-4"],
+        allowed_search_tools=["tavily-search"],
+        metadata={"user_info": "test"},  # No search_provider_config
+    )
+
+    # Verify metadata does not contain search_provider_config
+    assert mock_key.metadata is not None
+    assert "search_provider_config" not in mock_key.metadata
+    assert "api_key" not in str(mock_key.metadata)
+
+
+@pytest.mark.asyncio
+async def test_both_key_and_team_checks_required():
+    """Test that both key-level and team-level checks are enforced."""
+    # Key has access to tool
+    mock_key = UserAPIKeyAuth(
+        token="sk-test-key",
+        models=["gpt-4"],
+        allowed_search_tools=["tavily-search"],
+    )
+
+    # Team does NOT have access to tool
+    mock_team = LiteLLM_TeamTable(
+        team_id="team-123",
+        team_alias="Restricted Team",
+        models=["gpt-4"],
+        allowed_search_tools=["perplexity-search"],  # Different tool
+    )
+
+    # Key check passes
+    await can_key_call_search_tool(
+        search_tool_name="tavily-search",
+        valid_token=mock_key,
+    )
+
+    # Team check fails
+    with pytest.raises(Exception) as exc_info:
+        await can_team_call_search_tool(
+            search_tool_name="tavily-search",
+            team_object=mock_team,
+        )
+    assert "not allowed to access search tool" in str(exc_info.value)

ui/litellm-dashboard/src/app/(dashboard)/teams/components/modals/CreateTeamModal.tsx

@@ -15,7 +15,15 @@ import ModelAliasManager from "@/components/common_components/ModelAliasManager"
 import React, { useEffect, useState } from "react";
 import { useQueryClient } from "@tanstack/react-query";
 import NotificationsManager from "@/components/molecules/notifications_manager";
-import { fetchMCPAccessGroups, getGuardrailsList, getPoliciesList, Organization, Team, teamCreateCall } from "@/components/networking";
+import {
+  fetchMCPAccessGroups,
+  fetchSearchTools,
+  getGuardrailsList,
+  getPoliciesList,
+  Organization,
+  Team,
+  teamCreateCall,
+} from "@/components/networking";
 import useAuthorized from "@/app/(dashboard)/hooks/useAuthorized";
 import { organizationKeys } from "@/app/(dashboard)/hooks/organizations/useOrganizations";
 import MCPToolPermissions from "@/components/mcp_server_management/MCPToolPermissions";
@@ -80,6 +88,7 @@ const CreateTeamModal = ({
   const [modelsToPick, setModelsToPick] = useState<string[]>([]);
   const [guardrailsList, setGuardrailsList] = useState<string[]>([]);
   const [policiesList, setPoliciesList] = useState<string[]>([]);
+  const [searchToolNames, setSearchToolNames] = useState<string[]>([]);
   const [mcpAccessGroups, setMcpAccessGroups] = useState<string[]>([]);
   const [mcpAccessGroupsLoaded, setMcpAccessGroupsLoaded] = useState(false);
 
@@ -158,6 +167,24 @@ const CreateTeamModal = ({
     fetchPolicies();
   }, [accessToken]);
 
+  useEffect(() => {
+    const loadSearchTools = async () => {
+      try {
+        if (!accessToken) return;
+        const response = await fetchSearchTools(accessToken);
+        const tools = Array.isArray(response?.data) ? response.data : [];
+        setSearchToolNames(
+          tools
+            .map((tool: any) => tool?.search_tool_name)
+            .filter((name: unknown): name is string => typeof name === "string" && name.length > 0),
+        );
+      } catch (error) {
+        console.error("Failed to fetch search tools for team create modal:", error);
+      }
+    };
+    loadSearchTools();
+  }, [accessToken]);
+
   const handleCreate = async (formValues: Record<string, any>) => {
     try {
       console.log(`formValues: ${JSON.stringify(formValues)}`);
@@ -395,6 +422,27 @@ const CreateTeamModal = ({
             </Select2>
           </Form.Item>
 
+          <Form.Item
+            label={
+              <span>
+                Allowed Search Tools{" "}
+                <Tooltip title="Select which search tools this team can access. Leave empty to allow all search tools.">
+                  <InfoCircleOutlined style={{ marginLeft: "4px" }} />
+                </Tooltip>
+              </span>
+            }
+            name="allowed_search_tools"
+          >
+            <Select2
+              mode="multiple"
+              placeholder="Select search tools (empty = all search tools allowed)"
+              style={{ width: "100%" }}
+              options={searchToolNames.map((name) => ({ label: name, value: name }))}
+              showSearch
+              optionFilterProp="label"
+            />
+          </Form.Item>
+
           <Accordion className="mt-8 mb-8">
             <AccordionHeader>
               <b>Team Member Settings</b>

ui/litellm-dashboard/src/components/OldTeams.tsx

@@ -57,7 +57,14 @@ import type { KeyResponse, Team } from "./key_team_helpers/key_list";
 import MCPServerSelector from "./mcp_server_management/MCPServerSelector";
 import MCPToolPermissions from "./mcp_server_management/MCPToolPermissions";
 import NotificationsManager from "./molecules/notifications_manager";
-import { Organization, fetchMCPAccessGroups, getGuardrailsList, getPoliciesList, teamDeleteCall } from "./networking";
+import {
+  Organization,
+  fetchMCPAccessGroups,
+  fetchSearchTools,
+  getGuardrailsList,
+  getPoliciesList,
+  teamDeleteCall,
+} from "./networking";
 import NumericalInput from "./shared/numerical_input";
 import VectorStoreSelector from "./vector_store_management/VectorStoreSelector";
 
@@ -267,6 +274,7 @@ const Teams: React.FC<TeamProps> = ({
   // Add this state near the other useState declarations
   const [guardrailsList, setGuardrailsList] = useState<string[]>([]);
   const [policiesList, setPoliciesList] = useState<string[]>([]);
+  const [searchToolNames, setSearchToolNames] = useState<string[]>([]);
   const [loggingSettings, setLoggingSettings] = useState<any[]>([]);
   const [mcpAccessGroups, setMcpAccessGroups] = useState<string[]>([]);
   const [mcpAccessGroupsLoaded, setMcpAccessGroupsLoaded] = useState(false);
@@ -334,6 +342,24 @@ const Teams: React.FC<TeamProps> = ({
     fetchPolicies();
   }, [accessToken]);
 
+  useEffect(() => {
+    const loadSearchTools = async () => {
+      try {
+        if (!accessToken) return;
+        const response = await fetchSearchTools(accessToken);
+        const tools = Array.isArray(response?.data) ? response.data : [];
+        setSearchToolNames(
+          tools
+            .map((tool: any) => tool?.search_tool_name)
+            .filter((name: unknown): name is string => typeof name === "string" && name.length > 0),
+        );
+      } catch (error) {
+        console.error("Failed to fetch search tools:", error);
+      }
+    };
+    loadSearchTools();
+  }, [accessToken]);
+
   const fetchMcpAccessGroups = async () => {
     try {
       if (accessToken == null) {
@@ -1207,6 +1233,27 @@ const Teams: React.FC<TeamProps> = ({
                     />
                   </Form.Item>
 
+                  <Form.Item
+                    label={
+                      <span>
+                        Allowed Search Tools{" "}
+                        <Tooltip title="Select which search tools this team can access. Leave empty to allow all search tools.">
+                          <InfoCircleOutlined style={{ marginLeft: "4px" }} />
+                        </Tooltip>
+                      </span>
+                    }
+                    name="allowed_search_tools"
+                  >
+                    <Select
+                      mode="multiple"
+                      placeholder="Select search tools (empty = all search tools allowed)"
+                      style={{ width: "100%" }}
+                      options={searchToolNames.map((name) => ({ label: name, value: name }))}
+                      showSearch
+                      optionFilterProp="label"
+                    />
+                  </Form.Item>
+
                   <Form.Item label="Max Budget (USD)" name="max_budget">
                     <NumericalInput step={0.01} precision={2} width={200} />
                   </Form.Item>

ui/litellm-dashboard/src/components/networking.tsx

@@ -3725,40 +3725,6 @@ export const teamUpdateCall = async (
   }
 };
 
-export const updateTeamSearchProviderConfigCall = async (
-  accessToken: string,
-  formValues: {
-    team_id: string;
-    provider: string;
-    api_key?: string | null;
-    api_base?: string | null;
-  },
-) => {
-  try {
-    const url = proxyBaseUrl
-      ? `${proxyBaseUrl}/team/search_provider_config/update`
-      : `/team/search_provider_config/update`;
-    const response = await fetch(url, {
-      method: "POST",
-      headers: {
-        [globalLitellmHeaderName]: `Bearer ${accessToken}`,
-        "Content-Type": "application/json",
-      },
-      body: JSON.stringify(formValues),
-    });
-
-    if (!response.ok) {
-      const errorData = await response.text();
-      handleError(errorData);
-      throw new Error(errorData);
-    }
-    return await response.json();
-  } catch (error) {
-    console.error("Failed to update team search provider config:", error);
-    throw error;
-  }
-};
-
 /**
  * Patch update a model
  *

ui/litellm-dashboard/src/components/team/TeamInfo.tsx

@@ -3,6 +3,7 @@ import { organizationKeys, useOrganizations } from "@/app/(dashboard)/hooks/orga
 import { useQueryClient } from "@tanstack/react-query";
 import UserSearchModal from "@/components/common_components/user_search_modal";
 import {
+  fetchSearchTools,
   getPoliciesList,
   getPolicyInfoWithGuardrails,
   Member,
@@ -102,6 +103,7 @@ export interface TeamData {
     } | null;
     created_at: string;
     access_group_ids?: string[];
+    allowed_search_tools?: string[];
     default_team_member_models?: string[];
     access_group_models?: string[];
     access_group_mcp_server_ids?: string[];
@@ -191,6 +193,7 @@ const TeamInfoView: React.FC<TeamInfoProps> = ({
   const { data: guardrailsData, isLoading: isGuardrailsLoading } = useGuardrails();
   const globalGuardrailNames = guardrailsData?.globalGuardrailNames ?? new Set<string>();
   const [policiesList, setPoliciesList] = useState<string[]>([]);
+  const [searchToolNames, setSearchToolNames] = useState<string[]>([]);
   const [policyGuardrails, setPolicyGuardrails] = useState<Record<string, string[]>>({});
   const [loadingPolicies, setLoadingPolicies] = useState(false);
   const [memberToDelete, setMemberToDelete] = useState<Member | null>(null);
@@ -300,6 +303,24 @@ const TeamInfoView: React.FC<TeamInfoProps> = ({
     fetchPolicies();
   }, [accessToken]);
 
+  useEffect(() => {
+    const loadSearchTools = async () => {
+      try {
+        if (!accessToken) return;
+        const response = await fetchSearchTools(accessToken);
+        const tools = Array.isArray(response?.data) ? response.data : [];
+        setSearchToolNames(
+          tools
+            .map((tool: any) => tool?.search_tool_name)
+            .filter((name: unknown): name is string => typeof name === "string" && name.length > 0),
+        );
+      } catch (error) {
+        console.error("Failed to fetch search tools in team info:", error);
+      }
+    };
+    loadSearchTools();
+  }, [accessToken]);
+
   // Fetch resolved guardrails for all policies
   useEffect(() => {
     const fetchPolicyGuardrails = async () => {
@@ -457,26 +478,13 @@ const TeamInfoView: React.FC<TeamInfoProps> = ({
       try {
         const rawMetadata = values.metadata ? JSON.parse(values.metadata) : {};
         // Exclude soft_budget_alerting_emails from parsed metadata since it's handled separately
-        const { soft_budget_alerting_emails, search_provider_config, ...rest } = rawMetadata;
+        const { soft_budget_alerting_emails, ...rest } = rawMetadata;
         parsedMetadata = rest;
       } catch (e) {
         NotificationsManager.fromBackend("Invalid JSON in metadata field");
         return;
       }
 
-      let searchProviderConfig: Record<string, any> | undefined;
-      if (typeof values.search_provider_config === "string") {
-        const trimmedSearchProviderConfig = values.search_provider_config.trim();
-        if (trimmedSearchProviderConfig.length > 0) {
-          try {
-            searchProviderConfig = JSON.parse(trimmedSearchProviderConfig);
-          } catch (e) {
-            NotificationsManager.fromBackend("Invalid JSON in search provider configuration");
-            return;
-          }
-        }
-      }
-
       let secretManagerSettings: Record<string, any> | undefined;
       if (typeof values.secret_manager_settings === "string") {
         const trimmedSecretConfig = values.secret_manager_settings.trim();
@@ -517,6 +525,7 @@ const TeamInfoView: React.FC<TeamInfoProps> = ({
         team_id: teamId,
         team_alias: values.team_alias,
         models: values.models,
+        allowed_search_tools: values.allowed_search_tools || [],
         tpm_limit: sanitizeNumeric(values.tpm_limit),
         rpm_limit: sanitizeNumeric(values.rpm_limit),
         model_tpm_limit: modelTpmLimit,
@@ -526,7 +535,6 @@ const TeamInfoView: React.FC<TeamInfoProps> = ({
         budget_duration: values.budget_duration,
         metadata: {
           ...parsedMetadata,
-          ...(searchProviderConfig !== undefined ? { search_provider_config: searchProviderConfig } : {}),
           guardrails: (values.guardrails || []).filter((n: string) => !globalGuardrailNames.has(n)),
           opted_out_global_guardrails: optedOutGlobalGuardrails,
           ...(values.logging_settings?.length > 0 ? { logging: values.logging_settings } : {}),
@@ -940,6 +948,7 @@ const TeamInfoView: React.FC<TeamInfoProps> = ({
                       models: info.models,
                       tpm_limit: info.tpm_limit,
                       rpm_limit: info.rpm_limit,
+                      allowed_search_tools: info.allowed_search_tools || [],
                       modelLimits: Array.from(
                         new Set([
                           ...Object.keys(info.metadata?.model_tpm_limit ?? {}),
@@ -966,14 +975,11 @@ const TeamInfoView: React.FC<TeamInfoProps> = ({
                           : "",
                       metadata: info.metadata
                         ? JSON.stringify(
-                          (({ logging, secret_manager_settings, soft_budget_alerting_emails, search_provider_config, model_tpm_limit, model_rpm_limit, ...rest }) => rest)(info.metadata),
+                          (({ logging, secret_manager_settings, soft_budget_alerting_emails, model_tpm_limit, model_rpm_limit, ...rest }) => rest)(info.metadata),
                           null,
                           2,
                         )
                         : "",
-                      search_provider_config: info.metadata?.search_provider_config
-                        ? JSON.stringify(info.metadata.search_provider_config, null, 2)
-                        : "",
                       logging_settings: info.metadata?.logging || [],
                       secret_manager_settings: info.metadata?.secret_manager_settings
                         ? JSON.stringify(info.metadata.secret_manager_settings, null, 2)
@@ -1025,6 +1031,23 @@ const TeamInfoView: React.FC<TeamInfoProps> = ({
                       />
                     </Form.Item>
 
+                    <Form.Item
+                      label="Allowed Search Tools"
+                      name="allowed_search_tools"
+                      tooltip="Select which search tools this team can access. Leave empty to allow all search tools."
+                    >
+                      <Select
+                        mode="multiple"
+                        placeholder="Select search tools (empty = all tools allowed)"
+                        style={{ width: "100%" }}
+                        options={searchToolNames.map((name) => ({ label: name, value: name }))}
+                        showSearch
+                        filterOption={(input, option) =>
+                          (option?.label ?? "").toLowerCase().includes(input.toLowerCase())
+                        }
+                      />
+                    </Form.Item>
+
                     <Form.Item label="Max Budget (USD)" name="max_budget">
                       <NumericalInput step={0.01} precision={2} style={{ width: "100%" }} />
                     </Form.Item>
@@ -1416,29 +1439,6 @@ const TeamInfoView: React.FC<TeamInfoProps> = ({
                       />
                     </Form.Item>
 
-                    <Form.Item
-                      label="Search Provider Configuration"
-                      name="search_provider_config"
-                      tooltip='Team-level provider credentials. Example: {"tavily": {"api_key": "tvly-...", "api_base": "https://api.tavily.com"}}'
-                      rules={[
-                        {
-                          validator: async (_, value) => {
-                            if (!value || (typeof value === "string" && value.trim() === "")) {
-                              return Promise.resolve();
-                            }
-                            try {
-                              JSON.parse(value);
-                              return Promise.resolve();
-                            } catch (error) {
-                              return Promise.reject(new Error("Please enter valid JSON"));
-                            }
-                          },
-                        },
-                      ]}
-                    >
-                      <Input.TextArea rows={8} placeholder='{"tavily":{"api_key":"tvly-...","api_base":"https://api.tavily.com"}}' />
-                    </Form.Item>
-
                     <Form.Item
                       label="Secret Manager Settings"
                       name="secret_manager_settings"
@@ -1655,14 +1655,6 @@ const TeamInfoView: React.FC<TeamInfoProps> = ({
                       </div>
                     )}
 
-                    {info.metadata?.search_provider_config && (
-                      <div className="pt-4 border-t border-gray-200">
-                        <Text className="font-medium">Search Provider Configuration</Text>
-                        <pre className="mt-2 bg-gray-50 p-3 rounded text-xs overflow-x-auto">
-                          {JSON.stringify(info.metadata.search_provider_config, null, 2)}
-                        </pre>
-                      </div>
-                    )}
                   </div>
                 )}
               </Card>