Skip to content

[Bug]: Guardrail AI guardrails defined via GUI/API do not work #15584

Description

@orolega

What happened?

When creating a guardrail with the guardrail ai provider, whether in the GUI or with the API, it appears in the UI however when using it in a request it is never invoked/used. If I define the exact same guardrail in the config.yaml it does work.

Relevant log output

LiteLLM Proxy:DEBUG: guardrail_registry.py:395 - litellm_params= {'guardrail': 'guardrails_ai', 'guard_name': 'global-banned-words', 'mode': 'pre_call', 'guardrails_ai_api_input_format': 'llmOutput', 'api_base': 'http://REMOVED'}
LiteLLM Proxy:DEBUG: init_guardrails.py:34 - 
Guardrail List:[{'guardrail_id': '49859989-fa24-4600-a0e0-11b3d119991f', 'guardrail_name': 'global-banned-guard', 'litellm_params': LitellmParams(api_key=None, api_base='http://REMOVED', category_thresholds=None, detect_secrets_config=None, guard_name='global-banned-words', default_on=False, mask_request_content=None, mask_response_content=None, pangea_input_recipe=None, pangea_output_recipe=None, model=None, template_id=None, location=None, credentials=None, api_endpoint=None, fail_on_error=True, rules=None, default_action='Deny', application_id=None, monitor_mode=None, block_failures=None, anonymize_input=None, on_flagged_action='monitor', lasso_user_id=None, lasso_conversation_id=None, project_id=None, payload=True, breakdown=True, metadata=None, dev_info=True, guardrailIdentifier=None, guardrailVersion=None, disable_exception_on_block=False, aws_region_name=None, aws_access_key_id=None, aws_secret_access_key=None, aws_session_token=None, aws_session_name=None, aws_profile_name=None, aws_role_name=None, aws_web_identity_token=None, aws_sts_endpoint=None, aws_bedrock_runtime_endpoint=None, presidio_analyzer_api_base=None, presidio_anonymizer_api_base=None, output_parse_pii=None, presidio_language='en', pii_entities_config=None, presidio_ad_hoc_recognizers=None, mock_redacted_text=None, guardrail='guardrails_ai', mode='pre_call', guardrails_ai_api_input_format='llmOutput')}]

LiteLLM:DEBUG: mcp_server_manager.py:116 - Loading MCP Servers from config-----
LiteLLM:DEBUG: mcp_server_manager.py:145 - Mapped alias 'gitmcp' to server 'gitmcp'
LiteLLM:DEBUG: mcp_server_manager.py:218 - Loaded MCP Servers: {
    "39ba93086874ef716d528c37547711c5": "server_id='39ba93086874ef716d528c37547711c5' name='deepwiki_mcp' alias=None server_name='deepwiki_mcp' url='https://mcp.deepwiki.com/mcp' transport=<MCPTransport.http: 'http'> auth_type=None authentication_token=None mcp_info={'server_name': 'deepwiki_mcp', 'description': 'My Deepwiki MCP server'} client_id=None client_secret=None scopes=None authorization_url=None token_url=None command='' args=[] env={} access_groups=None",
    "676c3e13273883061d27560d188b5059": "server_id='676c3e13273883061d27560d188b5059' name='gitmcp' alias=None server_name='gitmcp' url='https://gitmcp.io/langchain-ai/langgraph' transport=<MCPTransport.http: 'http'> auth_type=None authentication_token=None mcp_info={'server_name': 'gitmcp', 'description': 'My Git MCP server'} client_id=None client_secret=None scopes=None authorization_url=None token_url=None command='' args=[] env={} access_groups=None"
}
LiteLLM Proxy:DEBUG: utils.py:1595 - Creating Prisma Client..
LiteLLM Proxy:DEBUG: utils.py:1627 - Success - Created Prisma Client
LiteLLM Proxy:DEBUG: utils.py:2764 - PrismaClient: connect() called Attempting to Connect to DB
LiteLLM Proxy:DEBUG: utils.py:2768 - PrismaClient: DB not connected, Attempting to Connect to DB
LiteLLM:DEBUG: mcp_server_manager.py:445 - Connecting to url: https://mcp.deepwiki.com/mcp
LiteLLM:INFO: mcp_server_manager.py:446 - _get_tools_from_server for deepwiki_mcp...
LiteLLM:DEBUG: client.py:120 - litellm headers for streamablehttp_client: 
LiteLLM Proxy:DEBUG: proxy_server.py:643 - prisma_client: <litellm.proxy.utils.PrismaClient object at 0xffff87aa5400>
LiteLLM Proxy:DEBUG: hanging_request_check.py:148 - Checking for hanging requests....
LiteLLM Proxy:INFO: utils.py:1734 - All necessary views exist!
LiteLLM Proxy:DEBUG: proxy_server.py:3851 - key_rotation_enabled: False
LiteLLM Proxy:DEBUG: proxy_server.py:3875 - Key rotation disabled (set LITELLM_KEY_ROTATION_ENABLED=true to enable)
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:4000 (Press CTRL+C to quit)
LiteLLM:DEBUG: mcp_server_manager.py:494 - Tools from deepwiki_mcp: [Tool(name='read_wiki_structure', title=None, description='Get a list of documentation topics for a GitHub repository', inputSchema={'type': 'object', 'properties': {'repoName': {'type': 'string', 'description': 'GitHub repository: owner/repo (e.g. "facebook/react")'}}, 'required': ['repoName'], 'additionalProperties': False, '$schema': 'http://json-schema.org/draft-07/schema#'}, outputSchema=None, annotations=None, meta=None), Tool(name='read_wiki_contents', title=None, description='View documentation about a GitHub repository', inputSchema={'type': 'object', 'properties': {'repoName': {'type': 'string', 'description': 'GitHub repository: owner/repo (e.g. "facebook/react")'}}, 'required': ['repoName'], 'additionalProperties': False, '$schema': 'http://json-schema.org/draft-07/schema#'}, outputSchema=None, annotations=None, meta=None), Tool(name='ask_question', title=None, description='Ask any question about a GitHub repository', inputSchema={'type': 'object', 'properties': {'repoName': {'type': 'string', 'description': 'GitHub repository: owner/repo (e.g. "facebook/react")'}, 'question': {'type': 'string', 'description': 'The question to ask about the repository'}}, 'required': ['repoName', 'question'], 'additionalProperties': False, '$schema': 'http://json-schema.org/draft-07/schema#'}, outputSchema=None, annotations=None, meta=None)]
LiteLLM:INFO: mcp_server_manager.py:559 - Successfully fetched 3 tools from server deepwiki_mcp
LiteLLM:DEBUG: mcp_server_manager.py:445 - Connecting to url: https://gitmcp.io/langchain-ai/langgraph
LiteLLM:INFO: mcp_server_manager.py:446 - _get_tools_from_server for gitmcp...
LiteLLM:DEBUG: client.py:120 - litellm headers for streamablehttp_client: 
LiteLLM:DEBUG: mcp_server_manager.py:494 - Tools from gitmcp: [Tool(name='fetch_langgraph_documentation', title=None, description='Fetch entire documentation file from GitHub repository: langchain-ai/langgraph. Useful for general questions. Always call this tool first if asked about langchain-ai/langgraph.', inputSchema={'type': 'object'}, outputSchema=None, annotations=ToolAnnotations(title=None, readOnlyHint=None, destructiveHint=None, idempotentHint=None, openWorldHint=None, _def={'options': [{'_def': {'unknownKeys': 'strip', 'catchall': {'_def': {'typeName': 'ZodNever'}, '~standard': {'version': 1, 'vendor': 'zod'}}, 'typeName': 'ZodObject'}, '~standard': {'version': 1, 'vendor': 'zod'}, '_cached': None}, {'_def': {'typeName': 'ZodNull'}, '~standard': {'version': 1, 'vendor': 'zod'}}], 'typeName': 'ZodUnion'}, ~standard={'version': 1, 'vendor': 'zod'}), meta=None), Tool(name='search_langgraph_documentation', title=None, description='Semantically search within the fetched documentation from GitHub repository: langchain-ai/langgraph. Useful for specific queries.', inputSchema={'type': 'object', 'properties': {'query': {'type': 'string', 'description': 'The search query to find relevant documentation'}}, 'required': ['query'], 'additionalProperties': False, '$schema': 'http://json-schema.org/draft-07/schema#'}, outputSchema=None, annotations=None, meta=None), Tool(name='search_langgraph_code', title=None, description='Search for code within the GitHub repository: "langchain-ai/langgraph" using the GitHub Search API (exact match). Returns matching files for you to query further if relevant.', inputSchema={'type': 'object', 'properties': {'query': {'type': 'string', 'description': 'The search query to find relevant code files'}, 'page': {'type': 'number', 'description': 'Page number to retrieve (starting from 1). Each page contains 30 results.'}}, 'required': ['query'], 'additionalProperties': False, '$schema': 'http://json-schema.org/draft-07/schema#'}, outputSchema=None, annotations=None, meta=None), Tool(name='fetch_generic_url_content', title=None, description='Generic tool to fetch content from any absolute URL, respecting robots.txt rules. Use this to retrieve referenced urls (absolute urls) that were mentioned in previously fetched documentation.', inputSchema={'type': 'object', 'properties': {'url': {'type': 'string', 'description': 'The URL of the document or page to fetch'}}, 'required': ['url'], 'additionalProperties': False, '$schema': 'http://json-schema.org/draft-07/schema#'}, outputSchema=None, annotations=None, meta=None)]
LiteLLM:INFO: mcp_server_manager.py:559 - Successfully fetched 4 tools from server gitmcp
LiteLLM Proxy:DEBUG: No new spend transactions to process (empty update cycle)
INFO:     127.0.0.1:39652 - "GET / HTTP/1.1" 200 OK
INFO:     127.0.0.1:39652 - "GET /swagger/swagger-ui.css HTTP/1.1" 200 OK
INFO:     127.0.0.1:39668 - "GET /swagger/swagger-ui-bundle.js HTTP/1.1" 200 OK
LiteLLM Proxy:DEBUG: custom_openapi_spec.py:216 - Successfully added ProxyChatCompletionRequest schema to OpenAPI spec
LiteLLM Proxy:DEBUG: custom_openapi_spec.py:216 - Successfully added EmbeddingRequest schema to OpenAPI spec
LiteLLM Proxy:DEBUG: custom_openapi_spec.py:218 - Could not get schema for ResponsesAPIRequestParams
INFO:     127.0.0.1:39668 - "GET /openapi.json HTTP/1.1" 200 OK
INFO:     127.0.0.1:39668 - "GET /ui/ HTTP/1.1" 200 OK
INFO:     127.0.0.1:39668 - "GET /litellm-asset-prefix/_next/static/chunks/webpack-a426aae3231a8df1.js HTTP/1.1" 200 OK
INFO:     127.0.0.1:39652 - "GET /litellm-asset-prefix/_next/static/chunks/fd9d1056-205af899b895cbac.js HTTP/1.1" 200 OK
INFO:     127.0.0.1:39688 - "GET /litellm-asset-prefix/_next/static/chunks/main-app-bb35cb240fbb9dca.js HTTP/1.1" 200 OK
INFO:     127.0.0.1:39678 - "GET /litellm-asset-prefix/_next/static/chunks/117-6a9f6a591033d4a0.js HTTP/1.1" 200 OK
INFO:     127.0.0.1:39668 - "GET /litellm-asset-prefix/_next/static/media/e4af272ccee01ff0-s.p.woff2 HTTP/1.1" 200 OK
INFO:     127.0.0.1:39688 - "GET /litellm-asset-prefix/_next/static/chunks/3014691f-b7b79b78e27792f3.js HTTP/1.1" 200 OK
INFO:     127.0.0.1:39678 - "GET /litellm-asset-prefix/_next/static/css/4103fa525703177b.css HTTP/1.1" 200 OK
INFO:     127.0.0.1:39652 - "GET /litellm-asset-prefix/_next/static/css/349654da14372cd9.css HTTP/1.1" 200 OK
INFO:     127.0.0.1:39668 - "GET /litellm-asset-prefix/_next/static/chunks/13b76428-ebdf3012af0e4489.js HTTP/1.1" 200 OK
INFO:     127.0.0.1:39652 - "GET /litellm-asset-prefix/_next/static/chunks/866-9e1803a09e9ae8da.js HTTP/1.1" 200 OK
INFO:     127.0.0.1:39688 - "GET /litellm-asset-prefix/_next/static/chunks/313-0025fb08e386c4b8.js HTTP/1.1" 200 OK
INFO:     127.0.0.1:39668 - "GET /litellm-asset-prefix/_next/static/chunks/154-b1f2a106d0e0d77b.js HTTP/1.1" 200 OK
INFO:     127.0.0.1:39678 - "GET /litellm-asset-prefix/_next/static/chunks/162-dd6427ff1a4ad9f4.js HTTP/1.1" 200 OK
INFO:     127.0.0.1:39668 - "GET /litellm-asset-prefix/_next/static/chunks/851-bbe6d02cf41bb87a.js HTTP/1.1" 200 OK
INFO:     127.0.0.1:39678 - "GET /litellm-asset-prefix/_next/static/chunks/app/page-46f79791404274c7.js HTTP/1.1" 200 OK
INFO:     127.0.0.1:39696 - "GET /litellm-asset-prefix/_next/static/chunks/50-d0da2dd7acce2eb9.js HTTP/1.1" 200 OK
INFO:     127.0.0.1:39712 - "GET /litellm-asset-prefix/_next/static/chunks/521-d97d355792d44830.js HTTP/1.1" 200 OK
INFO:     127.0.0.1:39688 - "GET /litellm/.well-known/litellm-ui-config HTTP/1.1" 200 OK
LiteLLM:DEBUG: user_api_key_auth.py:679 - api key not found in cache.
LiteLLM Proxy:DEBUG: utils.py:2121 - PrismaClient: find_unique for token: 7b8830bf1e3529bf2039233a71dd32795365438a0079a2d7c08476108ccf86c2
LiteLLM:DEBUG: user_api_key_auth.py:679 - api key not found in cache.
LiteLLM Proxy:DEBUG: utils.py:2121 - PrismaClient: find_unique for token: 7b8830bf1e3529bf2039233a71dd32795365438a0079a2d7c08476108ccf86c2
LiteLLM:DEBUG: user_api_key_auth.py:679 - api key not found in cache.
LiteLLM Proxy:DEBUG: utils.py:2121 - PrismaClient: find_unique for token: 7b8830bf1e3529bf2039233a71dd32795365438a0079a2d7c08476108ccf86c2
LiteLLM:DEBUG: user_api_key_auth.py:679 - api key not found in cache.
LiteLLM Proxy:DEBUG: utils.py:2121 - PrismaClient: find_unique for token: 7b8830bf1e3529bf2039233a71dd32795365438a0079a2d7c08476108ccf86c2
LiteLLM:DEBUG: user_api_key_auth.py:679 - api key not found in cache.
LiteLLM Proxy:DEBUG: utils.py:2121 - PrismaClient: find_unique for token: 7b8830bf1e3529bf2039233a71dd32795365438a0079a2d7c08476108ccf86c2
LiteLLM:DEBUG: user_api_key_auth.py:679 - api key not found in cache.
LiteLLM Proxy:DEBUG: utils.py:2121 - PrismaClient: find_unique for token: 7b8830bf1e3529bf2039233a71dd32795365438a0079a2d7c08476108ccf86c2
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
INFO:     127.0.0.1:39688 - "GET /sso/get/ui_settings HTTP/1.1" 200 OK
INFO:     127.0.0.1:39668 - "POST /v2/key/info HTTP/1.1" 200 OK
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.bitbucket
LiteLLM Proxy:DEBUG: prompt_registry.py:65 - Found prompt_initializer_registry in litellm.integrations.bitbucket: ['bitbucket']
LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.deepeval
LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.agentops
LiteLLM Proxy:DEBUG: prompt_registry.py:54 - Discovering prompt integrations in: litellm.integrations.dotprompt
LiteLLM Proxy:DEBUG: prompt_registry.py:65 - Found prompt_initializer_registry in litellm.integrations.dotprompt: ['dotprompt']
LiteLLM Proxy:DEBUG: prompt_registry.py:76 - Discovered 2 prompt initializers: ['bitbucket', 'dotprompt']
INFO:     127.0.0.1:39688 - "GET /prompts/list HTTP/1.1" 200 OK
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
LiteLLM Proxy:DEBUG: model_checks.py:121 - ALL KEY MODELS - 0
LiteLLM Proxy:DEBUG: model_checks.py:153 - ALL TEAM MODELS - 0
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
INFO:     127.0.0.1:39678 - "GET /user/available_users HTTP/1.1" 200 OK
INFO:     127.0.0.1:39652 - "GET /models?include_model_access_groups=True HTTP/1.1" 200 OK
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
INFO:     127.0.0.1:39668 - "GET /user/available_roles HTTP/1.1" 200 OK
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
LiteLLM Proxy:DEBUG: model_checks.py:121 - ALL KEY MODELS - 0
LiteLLM Proxy:DEBUG: model_checks.py:153 - ALL TEAM MODELS - 0
INFO:     127.0.0.1:39688 - "GET /models?include_model_access_groups=True&return_wildcard_routes=True HTTP/1.1" 200 OK
INFO:     127.0.0.1:39712 - "GET /v2/guardrails/list HTTP/1.1" 200 OK
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
LiteLLM Proxy:DEBUG: key_management_endpoints.py:2548 - Entering list_keys function
LiteLLM Proxy:DEBUG: key_management_endpoints.py:2732 - Filter conditions: {'OR': [{'team_id': None}, {'team_id': {'not': 'litellm-dashboard'}}]}
LiteLLM Proxy:DEBUG: key_management_endpoints.py:2737 - Pagination: skip=0, take=100
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
INFO:     127.0.0.1:39696 - "GET /v1/mcp/access_groups HTTP/1.1" 200 OK
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
LiteLLM Proxy:DEBUG: key_management_endpoints.py:2761 - Fetched 0 keys
INFO:     127.0.0.1:39688 - "GET /get/ui_theme_settings HTTP/1.1" 200 OK
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
LiteLLM Proxy:DEBUG: key_management_endpoints.py:2548 - Entering list_keys function
LiteLLM Proxy:DEBUG: key_management_endpoints.py:2732 - Filter conditions: {'OR': [{'team_id': None}, {'team_id': {'not': 'litellm-dashboard'}}]}
LiteLLM Proxy:DEBUG: key_management_endpoints.py:2737 - Pagination: skip=0, take=100
LiteLLM Proxy:DEBUG: key_management_endpoints.py:2768 - Total count of keys: 0
LiteLLM Proxy:DEBUG: key_management_endpoints.py:2595 - Successfully prepared response
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
LiteLLM Proxy:DEBUG: model_checks.py:121 - ALL KEY MODELS - 0
LiteLLM Proxy:DEBUG: model_checks.py:153 - ALL TEAM MODELS - 0
INFO:     127.0.0.1:39712 - "GET /organization/list HTTP/1.1" 200 OK
INFO:     127.0.0.1:39652 - "GET /key/list?page=1&size=100&return_full_object=true&include_team_keys=true&include_created_by_keys=true HTTP/1.1" 200 OK
INFO:     127.0.0.1:39678 - "GET /team/list HTTP/1.1" 200 OK
INFO:     127.0.0.1:39688 - "GET /models?include_model_access_groups=True&return_wildcard_routes=True HTTP/1.1" 200 OK
LiteLLM Proxy:DEBUG: key_management_endpoints.py:2761 - Fetched 0 keys
LiteLLM Proxy:DEBUG: internal_user_endpoints.py:1515 - Total count of users: 1
INFO:     127.0.0.1:39678 - "GET /index.txt?_rsc=144pr HTTP/1.1" 404 Not Found
INFO:     127.0.0.1:39668 - "GET /user/list?page=1&page_size=100 HTTP/1.1" 200 OK
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
LiteLLM Proxy:DEBUG: model_checks.py:121 - ALL KEY MODELS - 0
LiteLLM Proxy:DEBUG: model_checks.py:153 - ALL TEAM MODELS - 0
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
INFO:     127.0.0.1:39712 - "GET /models?include_model_access_groups=True HTTP/1.1" 200 OK
LiteLLM Proxy:DEBUG: proxy_server.py:8039 - Reading logo from path: /workspace/local_dev/.venv/lib/python3.13/site-packages/litellm/proxy/logo.jpg
LiteLLM Proxy:DEBUG: key_management_endpoints.py:2768 - Total count of keys: 0
LiteLLM Proxy:DEBUG: key_management_endpoints.py:2595 - Successfully prepared response
INFO:     127.0.0.1:39696 - "GET /key/list?page=1&size=100&return_full_object=true&include_team_keys=true&include_created_by_keys=true HTTP/1.1" 200 OK
INFO:     127.0.0.1:39688 - "GET /get_image HTTP/1.1" 200 OK
INFO:     127.0.0.1:39652 - "GET /team/list HTTP/1.1" 200 OK
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
INFO:     127.0.0.1:39668 - "GET /organization/list HTTP/1.1" 200 OK
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
LiteLLM Proxy:DEBUG: internal_user_endpoints.py:1515 - Total count of users: 1
INFO:     127.0.0.1:39688 - "GET /user/list?page=1&page_size=100 HTTP/1.1" 200 OK
LiteLLM Proxy:DEBUG: Spend update cycle completed (no transactions)
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
INFO:     127.0.0.1:42344 - "GET /guardrails/ui/add_guardrail_settings HTTP/1.1" 200 OK
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
INFO:     127.0.0.1:42370 - "GET /guardrails/ui/provider_specific_params HTTP/1.1" 200 OK
INFO:     127.0.0.1:42358 - "GET /v2/guardrails/list HTTP/1.1" 200 OK
LiteLLM Proxy:DEBUG: Spend update cycle completed (no transactions)
LiteLLM Proxy:DEBUG: Spend update cycle completed (no transactions)
INFO:     127.0.0.1:60860 - "GET /ui/assets/logos/lakeraai.jpeg HTTP/1.1" 200 OK
INFO:     127.0.0.1:60878 - "GET /ui/assets/logos/presidio.png HTTP/1.1" 200 OK
INFO:     127.0.0.1:60870 - "GET /ui/assets/logos/bedrock.svg HTTP/1.1" 200 OK
LiteLLM Proxy:DEBUG: Spend update cycle completed (no transactions)
LiteLLM Proxy:DEBUG: Spend update cycle completed (no transactions)
LiteLLM Proxy:DEBUG: Spend update cycle completed (no transactions)
LiteLLM Proxy:DEBUG: Spend update cycle completed (no transactions)
LiteLLM Proxy:DEBUG: Spend update cycle completed (no transactions)
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
INFO:     127.0.0.1:38706 - "POST /guardrails HTTP/1.1" 200 OK
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
INFO:     127.0.0.1:38706 - "GET /v2/guardrails/list HTTP/1.1" 200 OK
LiteLLM Proxy:DEBUG: Spend update cycle completed (no transactions)
LiteLLM Proxy:DEBUG: Spend update cycle completed (no transactions)
LiteLLM Proxy:DEBUG: Spend update cycle completed (no transactions)
LiteLLM Proxy:DEBUG: Spend update cycle completed (no transactions)
LiteLLM Proxy:DEBUG: Spend update cycle completed (no transactions)
LiteLLM:DEBUG: Multiple API key cache misses for token authentication
LiteLLM Proxy:DEBUG: Token authentication successful (multiple requests)
LiteLLM Proxy:DEBUG: model_checks.py:121 - ALL KEY MODELS - 0
LiteLLM Proxy:DEBUG: model_checks.py:153 - ALL TEAM MODELS - 0
LiteLLM:DEBUG: utils.py:4763 - checking potential_model_names in litellm.model_cost: {'split_model': 'fake', 'combined_model_name': 'openai/fake', 'stripped_model_name': 'openai/fake', 'combined_stripped_model_name': 'openai/fake', 'custom_llm_provider': 'openai'}
LiteLLM:DEBUG: utils.py:5078 - model_info: {'key': 'openai/fake', 'max_tokens': None, 'max_input_tokens': None, 'max_output_tokens': None, 'input_cost_per_token': 0.015, 'input_cost_per_token_flex': None, 'input_cost_per_token_priority': None, 'cache_creation_input_token_cost': None, 'cache_read_input_token_cost': None, 'cache_read_input_token_cost_flex': None, 'cache_read_input_token_cost_priority': None, 'cache_creation_input_token_cost_above_1hr': None, 'input_cost_per_character': None, 'input_cost_per_token_above_128k_tokens': None, 'input_cost_per_token_above_200k_tokens': None, 'input_cost_per_query': None, 'input_cost_per_second': None, 'input_cost_per_audio_token': None, 'input_cost_per_token_batches': None, 'output_cost_per_token_batches': None, 'output_cost_per_token': 0.025, 'output_cost_per_token_flex': None, 'output_cost_per_token_priority': None, 'output_cost_per_audio_token': None, 'output_cost_per_character': None, 'output_cost_per_reasoning_token': None, 'output_cost_per_token_above_128k_tokens': None, 'output_cost_per_character_above_128k_tokens': None, 'output_cost_per_token_above_200k_tokens': None, 'output_cost_per_second': None, 'output_cost_per_image': None, 'output_vector_size': None, 'citation_cost_per_token': None, 'tiered_pricing': None, 'litellm_provider': 'openai', 'mode': None, 'supports_system_messages': None, 'supports_response_schema': None, 'supports_vision': None, 'supports_function_calling': None, 'supports_tool_choice': None, 'supports_assistant_prefill': None, 'supports_prompt_caching': None, 'supports_audio_input': None, 'supports_audio_output': None, 'supports_pdf_input': None, 'supports_embedding_image_input': None, 'supports_native_streaming': None, 'supports_web_search': None, 'supports_url_context': None, 'supports_reasoning': None, 'supports_computer_use': None, 'search_context_cost_per_query': None, 'tpm': 1000, 'rpm': 1}
LiteLLM:DEBUG: utils.py:4763 - checking potential_model_names in litellm.model_cost: {'split_model': 'bedrock/openai.gpt-oss-20b-1:0', 'combined_model_name': 'bedrock_converse/bedrock/openai.gpt-oss-20b-1:0', 'stripped_model_name': 'openai.gpt-oss-20b-1:0', 'combined_stripped_model_name': 'bedrock_converse/openai.gpt-oss-20b-1:0', 'custom_llm_provider': 'bedrock_converse'}
LiteLLM:DEBUG: utils.py:4763 - checking potential_model_names in litellm.model_cost: {'split_model': 'bedrock/openai.gpt-oss-20b-1:0', 'combined_model_name': 'bedrock_converse/bedrock/openai.gpt-oss-20b-1:0', 'stripped_model_name': 'openai.gpt-oss-20b-1:0', 'combined_stripped_model_name': 'bedrock_converse/openai.gpt-oss-20b-1:0', 'custom_llm_provider': 'bedrock_converse'}
LiteLLM:DEBUG: utils.py:4763 - checking potential_model_names in litellm.model_cost: {'split_model': 'openai.gpt-oss-20b-1:0', 'combined_model_name': 'bedrock/openai.gpt-oss-20b-1:0', 'stripped_model_name': 'openai.gpt-oss-20b-1:0', 'combined_stripped_model_name': 'openai.gpt-oss-20b-1:0', 'custom_llm_provider': 'bedrock'}
LiteLLM:DEBUG: utils.py:5078 - model_info: {'key': 'openai.gpt-oss-20b-1:0', 'max_tokens': 128000, 'max_input_tokens': 128000, 'max_output_tokens': 128000, 'input_cost_per_token': 7e-08, 'input_cost_per_token_flex': None, 'input_cost_per_token_priority': None, 'cache_creation_input_token_cost': None, 'cache_read_input_token_cost': None, 'cache_read_input_token_cost_flex': None, 'cache_read_input_token_cost_priority': None, 'cache_creation_input_token_cost_above_1hr': None, 'input_cost_per_character': None, 'input_cost_per_token_above_128k_tokens': None, 'input_cost_per_token_above_200k_tokens': None, 'input_cost_per_query': None, 'input_cost_per_second': None, 'input_cost_per_audio_token': None, 'input_cost_per_token_batches': None, 'output_cost_per_token_batches': None, 'output_cost_per_token': 3e-07, 'output_cost_per_token_flex': None, 'output_cost_per_token_priority': None, 'output_cost_per_audio_token': None, 'output_cost_per_character': None, 'output_cost_per_reasoning_token': None, 'output_cost_per_token_above_128k_tokens': None, 'output_cost_per_character_above_128k_tokens': None, 'output_cost_per_token_above_200k_tokens': None, 'output_cost_per_second': None, 'output_cost_per_image': None, 'output_vector_size': None, 'citation_cost_per_token': None, 'tiered_pricing': None, 'litellm_provider': 'bedrock_converse', 'mode': 'chat', 'supports_system_messages': None, 'supports_response_schema': True, 'supports_vision': None, 'supports_function_calling': True, 'supports_tool_choice': True, 'supports_assistant_prefill': None, 'supports_prompt_caching': None, 'supports_audio_input': None, 'supports_audio_output': None, 'supports_pdf_input': None, 'supports_embedding_image_input': None, 'supports_native_streaming': None, 'supports_web_search': None, 'supports_url_context': None, 'supports_reasoning': True, 'supports_computer_use': None, 'search_context_cost_per_query': None, 'tpm': None, 'rpm': None}
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
INFO:     127.0.0.1:54458 - "GET /model_group/info HTTP/1.1" 200 OK
LiteLLM:DEBUG: user_api_key_auth_mcp.py:391 - team_obj is None
LiteLLM:DEBUG: mcp_server_manager.py:286 - Allowed MCP Servers for user api key auth: []
LiteLLM:DEBUG: mcp_server_manager.py:292 - No allowed MCP Servers found for user api key auth, returning default registry servers
LiteLLM:DEBUG: mcp_server_manager.py:445 - Connecting to url: https://mcp.deepwiki.com/mcp
LiteLLM:INFO: mcp_server_manager.py:446 - _get_tools_from_server for deepwiki_mcp...
LiteLLM:DEBUG: client.py:120 - litellm headers for streamablehttp_client: 
INFO:     127.0.0.1:54456 - "GET /v2/guardrails/list HTTP/1.1" 200 OK
INFO:     127.0.0.1:54474 - "GET /vector_store/list HTTP/1.1" 200 OK
INFO:     127.0.0.1:54454 - "GET /tag/list HTTP/1.1" 200 OK
LiteLLM:DEBUG: mcp_server_manager.py:494 - Tools from deepwiki_mcp: [Tool(name='read_wiki_structure', title=None, description='Get a list of documentation topics for a GitHub repository', inputSchema={'type': 'object', 'properties': {'repoName': {'type': 'string', 'description': 'GitHub repository: owner/repo (e.g. "facebook/react")'}}, 'required': ['repoName'], 'additionalProperties': False, '$schema': 'http://json-schema.org/draft-07/schema#'}, outputSchema=None, annotations=None, meta=None), Tool(name='read_wiki_contents', title=None, description='View documentation about a GitHub repository', inputSchema={'type': 'object', 'properties': {'repoName': {'type': 'string', 'description': 'GitHub repository: owner/repo (e.g. "facebook/react")'}}, 'required': ['repoName'], 'additionalProperties': False, '$schema': 'http://json-schema.org/draft-07/schema#'}, outputSchema=None, annotations=None, meta=None), Tool(name='ask_question', title=None, description='Ask any question about a GitHub repository', inputSchema={'type': 'object', 'properties': {'repoName': {'type': 'string', 'description': 'GitHub repository: owner/repo (e.g. "facebook/react")'}, 'question': {'type': 'string', 'description': 'The question to ask about the repository'}}, 'required': ['repoName', 'question'], 'additionalProperties': False, '$schema': 'http://json-schema.org/draft-07/schema#'}, outputSchema=None, annotations=None, meta=None)]
LiteLLM:INFO: mcp_server_manager.py:559 - Successfully fetched 3 tools from server deepwiki_mcp
LiteLLM:DEBUG: server.py:423 - Successfully fetched 3 tools from server deepwiki_mcp
LiteLLM:DEBUG: mcp_server_manager.py:445 - Connecting to url: https://gitmcp.io/langchain-ai/langgraph
LiteLLM:INFO: mcp_server_manager.py:446 - _get_tools_from_server for gitmcp...
LiteLLM:DEBUG: client.py:120 - litellm headers for streamablehttp_client: 
LiteLLM:DEBUG: mcp_server_manager.py:494 - Tools from gitmcp: [Tool(name='fetch_langgraph_documentation', title=None, description='Fetch entire documentation file from GitHub repository: langchain-ai/langgraph. Useful for general questions. Always call this tool first if asked about langchain-ai/langgraph.', inputSchema={'type': 'object'}, outputSchema=None, annotations=ToolAnnotations(title=None, readOnlyHint=None, destructiveHint=None, idempotentHint=None, openWorldHint=None, _def={'options': [{'_def': {'unknownKeys': 'strip', 'catchall': {'_def': {'typeName': 'ZodNever'}, '~standard': {'version': 1, 'vendor': 'zod'}}, 'typeName': 'ZodObject'}, '~standard': {'version': 1, 'vendor': 'zod'}, '_cached': None}, {'_def': {'typeName': 'ZodNull'}, '~standard': {'version': 1, 'vendor': 'zod'}}], 'typeName': 'ZodUnion'}, ~standard={'version': 1, 'vendor': 'zod'}), meta=None), Tool(name='search_langgraph_documentation', title=None, description='Semantically search within the fetched documentation from GitHub repository: langchain-ai/langgraph. Useful for specific queries.', inputSchema={'type': 'object', 'properties': {'query': {'type': 'string', 'description': 'The search query to find relevant documentation'}}, 'required': ['query'], 'additionalProperties': False, '$schema': 'http://json-schema.org/draft-07/schema#'}, outputSchema=None, annotations=None, meta=None), Tool(name='search_langgraph_code', title=None, description='Search for code within the GitHub repository: "langchain-ai/langgraph" using the GitHub Search API (exact match). Returns matching files for you to query further if relevant.', inputSchema={'type': 'object', 'properties': {'query': {'type': 'string', 'description': 'The search query to find relevant code files'}, 'page': {'type': 'number', 'description': 'Page number to retrieve (starting from 1). Each page contains 30 results.'}}, 'required': ['query'], 'additionalProperties': False, '$schema': 'http://json-schema.org/draft-07/schema#'}, outputSchema=None, annotations=None, meta=None), Tool(name='fetch_generic_url_content', title=None, description='Generic tool to fetch content from any absolute URL, respecting robots.txt rules. Use this to retrieve referenced urls (absolute urls) that were mentioned in previously fetched documentation.', inputSchema={'type': 'object', 'properties': {'url': {'type': 'string', 'description': 'The URL of the document or page to fetch'}}, 'required': ['url'], 'additionalProperties': False, '$schema': 'http://json-schema.org/draft-07/schema#'}, outputSchema=None, annotations=None, meta=None)]
LiteLLM:INFO: mcp_server_manager.py:559 - Successfully fetched 4 tools from server gitmcp
LiteLLM:DEBUG: server.py:423 - Successfully fetched 4 tools from server gitmcp
LiteLLM:INFO: server.py:432 - Successfully fetched 7 tools total from all MCP servers
LiteLLM:DEBUG: server.py:468 - Successfully fetched 7 tools from managed MCP servers
INFO:     127.0.0.1:54490 - "GET /v1/mcp/tools HTTP/1.1" 200 OK
LiteLLM Proxy:DEBUG: Spend update cycle completed (no transactions)
LiteLLM:DEBUG: user_api_key_auth.py:729 - Team doesn't exist in cache + check_cache_only=True. Team=litellm-dashboard.
LiteLLM Proxy:DEBUG: user_api_key_auth.py:985 - Checking if token expired, expiry time 2025-10-17 00:00:00+00:00 and current time 2025-10-16 00:00
LiteLLM Proxy:DEBUG: auth_checks.py:1699 - Vector store registry not found, skipping vector store access check
LiteLLM Proxy:DEBUG: common_request_processing.py:387 - Request received by LiteLLM:

Are you a ML Ops Team?

No

What LiteLLM version are you on ?

v1.77.5

Twitter / LinkedIn details

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't working

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions