x-litellm-semantic-filter: 50->3
x-litellm-semantic-filter-tools: tool1,tool2,tool3 +``` + +## Configuration + +Enable semantic filtering in your LiteLLM config: + +```yaml title="config.yaml" showLineNumbers +litellm_settings: + mcp_semantic_tool_filter: + enabled: true + embedding_model: "text-embedding-3-small" # Model for semantic matching + top_k: 5 # Max tools to return + similarity_threshold: 0.3 # Min similarity score +``` + +**Configuration Options:** +- `enabled` - Enable/disable semantic filtering (default: `false`) +- `embedding_model` - Model for generating embeddings (default: `"text-embedding-3-small"`) +- `top_k` - Maximum number of tools to return (default: `10`) +- `similarity_threshold` - Minimum similarity score for matches (default: `0.3`) + +## Usage + +Use MCP tools normally with the Responses API or Chat Completions. The semantic filter runs automatically: + +
- Remove unsupported
- Keep supported + + LP->>Provider: Request with filtered headers + Note over LP,Provider: anthropic-beta: header2
(header1, header3 removed) + + Provider-->>LP: Success response + LP-->>CC: Response +``` \ No newline at end of file diff --git a/docs/my-website/docs/tutorials/copilotkit_sdk.md b/docs/my-website/docs/tutorials/copilotkit_sdk.md new file mode 100644 index 00000000000..fc4db8bfe3e --- /dev/null +++ b/docs/my-website/docs/tutorials/copilotkit_sdk.md @@ -0,0 +1,99 @@ +import Tabs from '@theme/Tabs'; +import TabItem from '@theme/TabItem'; + +# CopilotKit SDK with LiteLLM + +Use CopilotKit SDK with any LLM provider through LiteLLM Proxy. + +> **Note:** CopilotKit SDK integration with LiteLLM Proxy works with LiteLLM v1.81.7-nightly or higher. + + +## Quick Start + +### 1. Add Model to Config + +```yaml title="config.yaml" +model_list: + - model_name: claude-sonnet-4-5 + litellm_params: + model: "anthropic/claude-sonnet-4-5-20250514-v1:0" + api_key: "os.environ/ANTHROPIC_API_KEY" +``` + +### 2. Start LiteLLM Proxy + +```bash +litellm --config config.yaml +``` + +### 3. Use CopilotKit SDK + +```typescript +import OpenAI from "openai"; +import { + CopilotRuntime, + OpenAIAdapter, + copilotRuntimeNextJSAppRouterEndpoint, +} from "@copilotkit/runtime"; +import { NextRequest } from "next/server"; + +const model = "claude-sonnet-4-5"; + +const openai = new OpenAI({ + apiKey: process.env.OPENAI_API_KEY || "sk-12345", + baseURL: process.env.OPENAI_BASE_URL || "http://localhost:4000/v1", +}); + +const serviceAdapter = new OpenAIAdapter({ openai, model }); +const runtime = new CopilotRuntime(); + +export const POST = async (req: NextRequest) => { + const { handleRequest } = copilotRuntimeNextJSAppRouterEndpoint({ + runtime, + serviceAdapter, + endpoint: "/api/copilotkit", + }); + return handleRequest(req); +}; +``` + +### 4. Test + +```bash +curl -X POST http://localhost:3000/api/copilotkit \ + -H "Content-Type: application/json" \ + -d '{ + "method": "agent/run", + "params": { + "agentId": "default" + }, + "runId": "your_run_id", + "threadId": "your_thread_id", + "runId": ""your_run_id"", + "tools": [], + "context": [], + "forwardedProps": {}, + "state": {}, + "messages": [ + { + "id": "166e573e-f7c6-4c0f-8685-04dbefec18be", + "content": "Hi", + "role": "user" + } + ] + } +}' +``` + +## Environment Variables + +| Variable | Value | Description | +|----------|-------|-------------| +| `OPENAI_API_KEY` | `sk-12345` | Your LiteLLM API key | +| `OPENAI_BASE_URL` | `http://localhost:4000/v1` | LiteLLM proxy URL | + + +## Related Resources + +- [CopilotKit Documentation](https://docs.copilotkit.ai) +- [LiteLLM Proxy Quick Start](../proxy/quick_start) diff --git a/docs/my-website/docs/tutorials/livekit_xai_realtime.md b/docs/my-website/docs/tutorials/livekit_xai_realtime.md new file mode 100644 index 00000000000..1d70186382f --- /dev/null +++ b/docs/my-website/docs/tutorials/livekit_xai_realtime.md @@ -0,0 +1,190 @@ +import Tabs from '@theme/Tabs'; +import TabItem from '@theme/TabItem'; + +# LiveKit xAI Realtime Voice Agent + +Use LiveKit's xAI Grok Voice Agent plugin with LiteLLM Proxy to build low-latency voice AI agents. + +The LiveKit Agents framework provides tools for building real-time voice and video AI applications. By routing through LiteLLM Proxy, you get unified access to multiple realtime voice providers, cost tracking, rate limiting, and more. + +## Quick Start + +### 1. Install Dependencies + +```bash +pip install livekit-agents[xai] +``` + +### 2. Start LiteLLM Proxy + +Create a config file with your xAI realtime model: + +```yaml title="config.yaml" showLineNumbers +model_list: + - model_name: grok-voice-agent + litellm_params: + model: xai/grok-2-vision-1212 + api_key: os.environ/XAI_API_KEY + model_info: + mode: realtime + +litellm_settings: + drop_params: True + +general_settings: + master_key: sk-1234 # Change this to a secure key +``` + +Start the proxy: + +```bash +litellm --config config.yaml --port 4000 +``` + +### 3. Configure LiveKit xAI Plugin + +Point LiveKit's xAI plugin to your LiteLLM proxy: + +```python +from livekit.plugins import xai + +# Configure xAI to use LiteLLM proxy +model = xai.realtime.RealtimeModel( + voice="ara", # Voice option + api_key="sk-1234", # Your LiteLLM proxy master key + base_url="http://localhost:4000", # LiteLLM proxy URL +) +``` + +## Complete Example + +Here's a complete working example: + +
" + + # Use team alias or generic greeting + team_alias = event.team_alias or "Team" + + email_html_content = TEAM_SOFT_BUDGET_ALERT_EMAIL_TEMPLATE.format( + email_logo_url=email_params.logo_url, + team_alias=team_alias, + soft_budget=soft_budget_str, + spend=spend_str, + max_budget_info=max_budget_info, + base_url=email_params.base_url, + email_support_contact=email_params.support_contact, + ) + + # Send email to all recipients + await self.send_email( + from_email=self.DEFAULT_LITELLM_EMAIL, + to_email=recipient_emails, + subject=email_params.subject, + html_body=email_html_content, + ) + pass + async def send_max_budget_alert_email(self, event: WebhookEvent): """ Send email to user when max budget alert threshold is reached @@ -285,15 +364,36 @@ class BaseEmailLogger(CustomLogger): # - Don't re-alert, if alert already sent _cache: DualCache = self.internal_usage_cache - # percent of max_budget left to spend - if user_info.max_budget is None and user_info.soft_budget is None: - return - # For soft_budget alerts, check if we've already sent an alert if type == "soft_budget": + # For team soft budget alerts, we only need team soft_budget to be set + # For other entity types, we need either max_budget or soft_budget + if user_info.event_group == Litellm_EntityType.TEAM: + if user_info.soft_budget is None: + return + # For team soft budget alerts, require alert_emails to be configured + # Team soft budget alerts are sent via metadata.soft_budget_alerting_emails + if user_info.alert_emails is None or len(user_info.alert_emails) == 0: + verbose_proxy_logger.debug( + "Skipping team soft budget email alert: no alert_emails configured", + ) + return + else: + # For non-team alerts, require either max_budget or soft_budget + if user_info.max_budget is None and user_info.soft_budget is None: + return if user_info.soft_budget is not None and user_info.spend >= user_info.soft_budget: # Generate cache key based on event type and identifier - _id = user_info.token or user_info.user_id or "default_id" + # Use appropriate ID based on event_group to ensure unique cache keys per entity type + if user_info.event_group == Litellm_EntityType.TEAM: + _id = user_info.team_id or "default_id" + elif user_info.event_group == Litellm_EntityType.ORGANIZATION: + _id = user_info.organization_id or "default_id" + elif user_info.event_group == Litellm_EntityType.USER: + _id = user_info.user_id or "default_id" + else: + # For KEY and other types, use token or user_id + _id = user_info.token or user_info.user_id or "default_id" _cache_key = f"email_budget_alerts:soft_budget_crossed:{_id}" # Check if we've already sent this alert @@ -318,10 +418,15 @@ class BaseEmailLogger(CustomLogger): projected_exceeded_date=user_info.projected_exceeded_date, projected_spend=user_info.projected_spend, event_group=user_info.event_group, + alert_emails=user_info.alert_emails, ) try: - await self.send_soft_budget_alert_email(webhook_event) + # Use team-specific function for team alerts, otherwise use standard function + if user_info.event_group == Litellm_EntityType.TEAM: + await self.send_team_soft_budget_alert_email(webhook_event) + else: + await self.send_soft_budget_alert_email(webhook_event) # Cache the alert to prevent duplicate sends await _cache.async_set_cache( diff --git a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py index d4ee4042b1a..bb25e4f0626 100644 --- a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py +++ b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py @@ -53,7 +53,7 @@ class CheckBatchCost: jobs = await self.prisma_client.db.litellm_managedobjecttable.find_many( where={ - "status": "validating", + "status": {"in": ["validating", "in_progress", "finalizing"]}, "file_purpose": "batch", } ) diff --git a/enterprise/litellm_enterprise/proxy/hooks/managed_files.py b/enterprise/litellm_enterprise/proxy/hooks/managed_files.py index 5ee3372cca7..569ea17f6d8 100644 --- a/enterprise/litellm_enterprise/proxy/hooks/managed_files.py +++ b/enterprise/litellm_enterprise/proxy/hooks/managed_files.py @@ -166,7 +166,11 @@ class _PROXY_LiteLLMManagedFiles(CustomLogger, BaseFileEndpoints): "updated_by": user_api_key_dict.user_id, "status": file_object.status, }, - "update": {}, # don't do anything if it already exists + "update": { + "file_object": file_object.model_dump_json(), + "status": file_object.status, + "updated_by": user_api_key_dict.user_id, + }, # FIX: Update status and file_object on every operation to keep state in sync }, ) @@ -354,6 +358,31 @@ class _PROXY_LiteLLMManagedFiles(CustomLogger, BaseFileEndpoints): ) return False + async def check_file_ids_access( + self, file_ids: List[str], user_api_key_dict: UserAPIKeyAuth + ) -> None: + """ + Check if the user has access to a list of file IDs. + Only checks managed (unified) file IDs. + + Args: + file_ids: List of file IDs to check access for + user_api_key_dict: User API key authentication details + + Raises: + HTTPException: If user doesn't have access to any of the files + """ + for file_id in file_ids: + is_unified_file_id = _is_base64_encoded_unified_file_id(file_id) + if is_unified_file_id: + if not await self.can_user_call_unified_file_id( + file_id, user_api_key_dict + ): + raise HTTPException( + status_code=403, + detail=f"User {user_api_key_dict.user_id} does not have access to the file {file_id}", + ) + async def async_pre_call_hook( # noqa: PLR0915 self, user_api_key_dict: UserAPIKeyAuth, @@ -387,6 +416,9 @@ class _PROXY_LiteLLMManagedFiles(CustomLogger, BaseFileEndpoints): if messages: file_ids = self.get_file_ids_from_messages(messages) if file_ids: + # Check user has access to all managed files + await self.check_file_ids_access(file_ids, user_api_key_dict) + # Check if any files are stored in storage backends and need base64 conversion # This is needed for Vertex AI/Gemini which requires base64 content is_vertex_ai = model and ("vertex_ai" in model or "gemini" in model.lower()) @@ -402,15 +434,27 @@ class _PROXY_LiteLLMManagedFiles(CustomLogger, BaseFileEndpoints): ) data["model_file_id_mapping"] = model_file_id_mapping elif call_type == CallTypes.aresponses.value or call_type == CallTypes.responses.value: - # Handle managed files in responses API input + # Handle managed files in responses API input and tools + file_ids = [] + + # Extract file IDs from input parameter input_data = data.get("input") if input_data: - file_ids = self.get_file_ids_from_responses_input(input_data) - if file_ids: - model_file_id_mapping = await self.get_model_file_id_mapping( - file_ids, user_api_key_dict.parent_otel_span - ) - data["model_file_id_mapping"] = model_file_id_mapping + file_ids.extend(self.get_file_ids_from_responses_input(input_data)) + + # Extract file IDs from tools parameter (e.g., code_interpreter container) + tools = data.get("tools") + if tools: + file_ids.extend(self.get_file_ids_from_responses_tools(tools)) + + if file_ids: + # Check user has access to all managed files + await self.check_file_ids_access(file_ids, user_api_key_dict) + + model_file_id_mapping = await self.get_model_file_id_mapping( + file_ids, user_api_key_dict.parent_otel_span + ) + data["model_file_id_mapping"] = model_file_id_mapping elif call_type == CallTypes.afile_content.value: retrieve_file_id = cast(Optional[str], data.get("file_id")) potential_file_id = ( @@ -460,8 +504,6 @@ class _PROXY_LiteLLMManagedFiles(CustomLogger, BaseFileEndpoints): if retrieve_object_id else False ) - print(f"🔥potential_llm_object_id: {potential_llm_object_id}") - print(f"🔥retrieve_object_id: {retrieve_object_id}") if potential_llm_object_id and retrieve_object_id: ## VALIDATE USER HAS ACCESS TO THE OBJECT ## if not await self.can_user_call_unified_object_id( @@ -614,6 +656,41 @@ class _PROXY_LiteLLMManagedFiles(CustomLogger, BaseFileEndpoints): return file_ids + def get_file_ids_from_responses_tools( + self, tools: List[Dict[str, Any]] + ) -> List[str]: + """ + Gets file ids from responses API tools parameter. + + The tools can contain code_interpreter with container.file_ids: + [ + { + "type": "code_interpreter", + "container": {"type": "auto", "file_ids": ["file-123", "file-456"]} + } + ] + """ + file_ids: List[str] = [] + + if not isinstance(tools, list): + return file_ids + + for tool in tools: + if not isinstance(tool, dict): + continue + + # Check for code_interpreter with container file_ids + if tool.get("type") == "code_interpreter": + container = tool.get("container") + if isinstance(container, dict): + container_file_ids = container.get("file_ids") + if isinstance(container_file_ids, list): + for file_id in container_file_ids: + if isinstance(file_id, str): + file_ids.append(file_id) + + return file_ids + async def get_model_file_id_mapping( self, file_ids: List[str], litellm_parent_otel_span: Span ) -> dict: diff --git a/enterprise/pyproject.toml b/enterprise/pyproject.toml index 0d86460a649..eca5cdb97df 100644 --- a/enterprise/pyproject.toml +++ b/enterprise/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "litellm-enterprise" -version = "0.1.28" +version = "0.1.31" description = "Package for LiteLLM Enterprise features" authors = ["BerriAI"] readme = "README.md" @@ -22,7 +22,7 @@ requires = ["poetry-core"] build-backend = "poetry.core.masonry.api" [tool.commitizen] -version = "0.1.28" +version = "0.1.31" version_files = [ "pyproject.toml:version", "../requirements.txt:litellm-enterprise==", diff --git a/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.30-py3-none-any.whl b/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.30-py3-none-any.whl new file mode 100644 index 00000000000..383f9b7b43f Binary files /dev/null and b/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.30-py3-none-any.whl differ diff --git a/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.30.tar.gz b/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.30.tar.gz new file mode 100644 index 00000000000..484c28ba7b1 Binary files /dev/null and b/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.30.tar.gz differ diff --git a/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.31-py3-none-any.whl b/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.31-py3-none-any.whl new file mode 100644 index 00000000000..90b36bd78ac Binary files /dev/null and b/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.31-py3-none-any.whl differ diff --git a/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.31.tar.gz b/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.31.tar.gz new file mode 100644 index 00000000000..64607235479 Binary files /dev/null and b/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.31.tar.gz differ diff --git a/litellm-proxy-extras/litellm_proxy_extras/migrations/20260205091235_allow_team_guardrail_config/migration.sql b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260205091235_allow_team_guardrail_config/migration.sql new file mode 100644 index 00000000000..000b96b3b87 --- /dev/null +++ b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260205091235_allow_team_guardrail_config/migration.sql @@ -0,0 +1,6 @@ +-- AlterTable +ALTER TABLE "LiteLLM_DeletedTeamTable" ADD COLUMN "allow_team_guardrail_config" BOOLEAN NOT NULL DEFAULT false; + +-- AlterTable +ALTER TABLE "LiteLLM_TeamTable" ADD COLUMN "allow_team_guardrail_config" BOOLEAN NOT NULL DEFAULT false; + diff --git a/litellm-proxy-extras/litellm_proxy_extras/migrations/20260205144610_add_soft_budget_to_team_table/migration.sql b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260205144610_add_soft_budget_to_team_table/migration.sql new file mode 100644 index 00000000000..a64f1de342f --- /dev/null +++ b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260205144610_add_soft_budget_to_team_table/migration.sql @@ -0,0 +1,3 @@ +-- AlterTable +ALTER TABLE "LiteLLM_TeamTable" ADD COLUMN "soft_budget" DOUBLE PRECISION; + diff --git a/litellm-proxy-extras/litellm_proxy_extras/schema.prisma b/litellm-proxy-extras/litellm_proxy_extras/schema.prisma index b118400b620..e713e6ca87a 100644 --- a/litellm-proxy-extras/litellm_proxy_extras/schema.prisma +++ b/litellm-proxy-extras/litellm_proxy_extras/schema.prisma @@ -113,6 +113,7 @@ model LiteLLM_TeamTable { members_with_roles Json @default("{}") metadata Json @default("{}") max_budget Float? + soft_budget Float? spend Float @default(0.0) models String[] max_parallel_requests Int? @@ -129,6 +130,7 @@ model LiteLLM_TeamTable { team_member_permissions String[] @default([]) policies String[] @default([]) model_id Int? @unique // id for LiteLLM_ModelTable -> stores team-level model aliases + allow_team_guardrail_config Boolean @default(false) // if true, team admin can configure guardrails for this team litellm_organization_table LiteLLM_OrganizationTable? @relation(fields: [organization_id], references: [organization_id]) litellm_model_table LiteLLM_ModelTable? @relation(fields: [model_id], references: [id]) object_permission LiteLLM_ObjectPermissionTable? @relation(fields: [object_permission_id], references: [object_permission_id]) @@ -160,7 +162,8 @@ model LiteLLM_DeletedTeamTable { team_member_permissions String[] @default([]) policies String[] @default([]) model_id Int? // id for LiteLLM_ModelTable -> stores team-level model aliases - + allow_team_guardrail_config Boolean @default(false) + // Original timestamps from team creation/updates created_at DateTime? @map("created_at") updated_at DateTime? @map("updated_at") @@ -774,6 +777,7 @@ model LiteLLM_GuardrailsTable { guardrail_name String @unique litellm_params Json guardrail_info Json? + team_id String? created_at DateTime @default(now()) updated_at DateTime @updatedAt } diff --git a/litellm-proxy-extras/pyproject.toml b/litellm-proxy-extras/pyproject.toml index fb6996b71db..0e72cd90813 100644 --- a/litellm-proxy-extras/pyproject.toml +++ b/litellm-proxy-extras/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "litellm-proxy-extras" -version = "0.4.29" +version = "0.4.31" description = "Additional files for the LiteLLM Proxy. Reduces the size of the main litellm package." authors = ["BerriAI"] readme = "README.md" @@ -22,7 +22,7 @@ requires = ["poetry-core"] build-backend = "poetry.core.masonry.api" [tool.commitizen] -version = "0.4.29" +version = "0.4.31" version_files = [ "pyproject.toml:version", "../requirements.txt:litellm-proxy-extras==", diff --git a/litellm/__init__.py b/litellm/__init__.py index a74a79635f0..8174b9d2655 100644 --- a/litellm/__init__.py +++ b/litellm/__init__.py @@ -261,6 +261,8 @@ extra_spend_tag_headers: Optional[List[str]] = None in_memory_llm_clients_cache: "LLMClientCache" safe_memory_mode: bool = False enable_azure_ad_token_refresh: Optional[bool] = False +# Proxy Authentication - auto-obtain/refresh OAuth2/JWT tokens for LiteLLM Proxy +proxy_auth: Optional[Any] = None ### DEFAULT AZURE API VERSION ### AZURE_DEFAULT_API_VERSION = "2025-02-01-preview" # this is updated to the latest ### DEFAULT WATSONX API VERSION ### @@ -351,7 +353,7 @@ default_team_settings: Optional[List] = None max_user_budget: Optional[float] = None default_max_internal_user_budget: Optional[float] = None max_internal_user_budget: Optional[float] = None -max_ui_session_budget: Optional[float] = 10 # $10 USD budgets for UI Chat sessions +max_ui_session_budget: Optional[float] = 0.25 # $0.25 USD budgets for UI Chat sessions internal_user_budget_duration: Optional[str] = None tag_budget_config: Optional[Dict[str, "BudgetConfig"]] = None max_end_user_budget: Optional[float] = None @@ -1378,6 +1380,7 @@ if TYPE_CHECKING: from .llms.topaz.image_variations.transformation import TopazImageVariationConfig as TopazImageVariationConfig from litellm.llms.openai.completion.transformation import OpenAITextCompletionConfig as OpenAITextCompletionConfig from .llms.groq.chat.transformation import GroqChatConfig as GroqChatConfig + from .llms.a2a.chat.transformation import A2AConfig as A2AConfig from .llms.voyage.embedding.transformation import VoyageEmbeddingConfig as VoyageEmbeddingConfig from .llms.voyage.embedding.transformation_contextual import VoyageContextualEmbeddingConfig as VoyageContextualEmbeddingConfig from .llms.infinity.embedding.transformation import InfinityEmbeddingConfig as InfinityEmbeddingConfig diff --git a/litellm/_lazy_imports_registry.py b/litellm/_lazy_imports_registry.py index 0e52e9a59eb..a01fe9c11db 100644 --- a/litellm/_lazy_imports_registry.py +++ b/litellm/_lazy_imports_registry.py @@ -213,6 +213,7 @@ LLM_CONFIG_NAMES = ( "TopazImageVariationConfig", "OpenAITextCompletionConfig", "GroqChatConfig", + "A2AConfig", "GenAIHubOrchestrationConfig", "VoyageEmbeddingConfig", "VoyageContextualEmbeddingConfig", @@ -850,6 +851,7 @@ _LLM_CONFIGS_IMPORT_MAP = { "OpenAITextCompletionConfig", ), "GroqChatConfig": (".llms.groq.chat.transformation", "GroqChatConfig"), + "A2AConfig": (".llms.a2a.chat.transformation", "A2AConfig"), "GenAIHubOrchestrationConfig": ( ".llms.sap.chat.transformation", "GenAIHubOrchestrationConfig", diff --git a/litellm/anthropic_beta_headers_config.json b/litellm/anthropic_beta_headers_config.json new file mode 100644 index 00000000000..193091c0176 --- /dev/null +++ b/litellm/anthropic_beta_headers_config.json @@ -0,0 +1,30 @@ +{ + "description": "Unsupported Anthropic beta headers for each provider. Headers listed here will be dropped. Headers not listed are passed through as-is.", + "anthropic": [], + "azure_ai": [], + "bedrock_converse": [ + "prompt-caching-scope-2026-01-05", + "bash_20250124", + "bash_20241022", + "text_editor_20250124", + "text_editor_20241022", + "compact-2026-01-12", + "advanced-tool-use-2025-11-20", + "web-fetch-2025-09-10", + "code-execution-2025-08-25", + "skills-2025-10-02", + "files-api-2025-04-14" + ], + "bedrock": [ + "advanced-tool-use-2025-11-20", + "prompt-caching-scope-2026-01-05", + "structured-outputs-2025-11-13", + "web-fetch-2025-09-10", + "code-execution-2025-08-25", + "skills-2025-10-02", + "files-api-2025-04-14" + ], + "vertex_ai": [ + "prompt-caching-scope-2026-01-05" + ] +} diff --git a/litellm/anthropic_beta_headers_manager.py b/litellm/anthropic_beta_headers_manager.py new file mode 100644 index 00000000000..2643f4c03fa --- /dev/null +++ b/litellm/anthropic_beta_headers_manager.py @@ -0,0 +1,221 @@ +""" +Centralized manager for Anthropic beta headers across different providers. + +This module provides utilities to: +1. Load beta header configuration from JSON (lists unsupported headers per provider) +2. Filter out unsupported beta headers +3. Handle provider-specific header name mappings (e.g., advanced-tool-use -> tool-search-tool) + +Design: +- JSON config lists UNSUPPORTED headers for each provider +- Headers not in the unsupported list are passed through +- Header mappings allow renaming headers for specific providers +""" + +import json +import os +from typing import Dict, List, Optional, Set + +from litellm.litellm_core_utils.litellm_logging import verbose_logger + +# Cache for the loaded configuration +_BETA_HEADERS_CONFIG: Optional[Dict] = None + + +def _load_beta_headers_config() -> Dict: + """ + Load the beta headers configuration from JSON file. + Uses caching to avoid repeated file reads. + + Returns: + Dict containing the beta headers configuration + """ + global _BETA_HEADERS_CONFIG + + if _BETA_HEADERS_CONFIG is not None: + return _BETA_HEADERS_CONFIG + + config_path = os.path.join( + os.path.dirname(__file__), + "anthropic_beta_headers_config.json" + ) + + try: + with open(config_path, "r") as f: + _BETA_HEADERS_CONFIG = json.load(f) + verbose_logger.debug(f"Loaded beta headers config from {config_path}") + return _BETA_HEADERS_CONFIG + except Exception as e: + verbose_logger.error(f"Failed to load beta headers config: {e}") + # Return empty config as fallback + return { + "anthropic": [], + "azure_ai": [], + "bedrock": [], + "bedrock_converse": [], + "vertex_ai": [] + } + + +def get_provider_name(provider: str) -> str: + """ + Resolve provider aliases to canonical provider names. + + Args: + provider: Provider name (may be an alias) + + Returns: + Canonical provider name + """ + config = _load_beta_headers_config() + aliases = config.get("provider_aliases", {}) + return aliases.get(provider, provider) + + +def filter_and_transform_beta_headers( + beta_headers: List[str], + provider: str, +) -> List[str]: + """ + Filter beta headers based on provider's unsupported list. + + This function: + 1. Removes headers that are in the provider's unsupported list + 2. Passes through all other headers as-is + + Note: Header transformations/mappings (e.g., advanced-tool-use -> tool-search-tool) + are handled in each provider's transformation code, not here. + + Args: + beta_headers: List of Anthropic beta header values + provider: Provider name (e.g., "anthropic", "bedrock", "vertex_ai") + + Returns: + List of filtered beta headers for the provider + """ + if not beta_headers: + return [] + + config = _load_beta_headers_config() + provider = get_provider_name(provider) + + # Get unsupported headers for this provider + unsupported_headers = set(config.get(provider, [])) + + filtered_headers: Set[str] = set() + + for header in beta_headers: + header = header.strip() + + # Skip if header is unsupported + if header in unsupported_headers: + verbose_logger.debug( + f"Dropping unsupported beta header '{header}' for provider '{provider}'" + ) + continue + + # Pass through as-is + filtered_headers.add(header) + + return sorted(list(filtered_headers)) + + +def is_beta_header_supported( + beta_header: str, + provider: str, +) -> bool: + """ + Check if a specific beta header is supported by a provider. + + Args: + beta_header: The Anthropic beta header value + provider: Provider name + + Returns: + True if the header is supported (not in unsupported list), False otherwise + """ + config = _load_beta_headers_config() + provider = get_provider_name(provider) + unsupported_headers = set(config.get(provider, [])) + return beta_header not in unsupported_headers + + +def get_provider_beta_header( + anthropic_beta_header: str, + provider: str, +) -> Optional[str]: + """ + Check if a beta header is supported by a provider. + + Note: This does NOT handle header transformations/mappings. + Those are handled in each provider's transformation code. + + Args: + anthropic_beta_header: The Anthropic beta header value + provider: Provider name + + Returns: + The original header if supported, or None if unsupported + """ + config = _load_beta_headers_config() + provider = get_provider_name(provider) + + # Check if unsupported + unsupported_headers = set(config.get(provider, [])) + if anthropic_beta_header in unsupported_headers: + return None + + return anthropic_beta_header + + +def update_headers_with_filtered_beta( + headers: dict, + provider: str, +) -> dict: + """ + Update headers dict by filtering and transforming anthropic-beta header values. + Modifies the headers dict in place and returns it. + + Args: + headers: Request headers dict (will be modified in place) + provider: Provider name + + Returns: + Updated headers dict + """ + existing_beta = headers.get("anthropic-beta") + if not existing_beta: + return headers + + # Parse existing beta headers + beta_values = [b.strip() for b in existing_beta.split(",") if b.strip()] + + # Filter and transform based on provider + filtered_beta_values = filter_and_transform_beta_headers( + beta_headers=beta_values, + provider=provider, + ) + + # Update or remove the header + if filtered_beta_values: + headers["anthropic-beta"] = ",".join(filtered_beta_values) + else: + # Remove the header if no values remain + headers.pop("anthropic-beta", None) + + return headers + + +def get_unsupported_headers(provider: str) -> List[str]: + """ + Get all beta headers that are unsupported by a provider. + + Args: + provider: Provider name + + Returns: + List of unsupported Anthropic beta header names + """ + config = _load_beta_headers_config() + provider = get_provider_name(provider) + return config.get(provider, []) diff --git a/litellm/completion_extras/litellm_responses_transformation/transformation.py b/litellm/completion_extras/litellm_responses_transformation/transformation.py index 57bd05124aa..753a94295b3 100644 --- a/litellm/completion_extras/litellm_responses_transformation/transformation.py +++ b/litellm/completion_extras/litellm_responses_transformation/transformation.py @@ -329,6 +329,9 @@ class LiteLLMResponsesTransformationHandler(CompletionTransformationBridge): else: request_data[key] = value + if headers: + request_data["extra_headers"] = headers + return request_data @staticmethod diff --git a/litellm/constants.py b/litellm/constants.py index 3c84547d7ce..25decd363a6 100644 --- a/litellm/constants.py +++ b/litellm/constants.py @@ -67,6 +67,25 @@ DEFAULT_REASONING_EFFORT_DISABLE_THINKING_BUDGET = int( os.getenv("DEFAULT_REASONING_EFFORT_DISABLE_THINKING_BUDGET", 0) ) +# MCP Semantic Tool Filter Defaults +DEFAULT_MCP_SEMANTIC_FILTER_EMBEDDING_MODEL = str( + os.getenv("DEFAULT_MCP_SEMANTIC_FILTER_EMBEDDING_MODEL", "text-embedding-3-small") +) +DEFAULT_MCP_SEMANTIC_FILTER_TOP_K = int( + os.getenv("DEFAULT_MCP_SEMANTIC_FILTER_TOP_K", 10) +) +DEFAULT_MCP_SEMANTIC_FILTER_SIMILARITY_THRESHOLD = float( + os.getenv("DEFAULT_MCP_SEMANTIC_FILTER_SIMILARITY_THRESHOLD", 0.3) +) +MAX_MCP_SEMANTIC_FILTER_TOOLS_HEADER_LENGTH = int( + os.getenv("MAX_MCP_SEMANTIC_FILTER_TOOLS_HEADER_LENGTH", 150) +) + +LITELLM_UI_ALLOW_HEADERS = [ + "x-litellm-semantic-filter", + "x-litellm-semantic-filter-tools", +] + # Gemini model-specific minimal thinking budget constants DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET_GEMINI_2_5_FLASH = int( os.getenv("DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET_GEMINI_2_5_FLASH", 1) @@ -85,6 +104,9 @@ DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET = int( os.getenv("DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET", 128) ) +# Provider-specific API base URLs +XAI_API_BASE = "https://api.x.ai/v1" + DEFAULT_REASONING_EFFORT_LOW_THINKING_BUDGET = int( os.getenv("DEFAULT_REASONING_EFFORT_LOW_THINKING_BUDGET", 1024) ) @@ -948,6 +970,8 @@ BEDROCK_CONVERSE_MODELS = [ "openai.gpt-oss-120b-1:0", "anthropic.claude-haiku-4-5-20251001-v1:0", "anthropic.claude-sonnet-4-5-20250929-v1:0", + "anthropic.claude-opus-4-6-v1:0", + "anthropic.claude-opus-4-6-v1", "anthropic.claude-opus-4-1-20250805-v1:0", "anthropic.claude-opus-4-20250514-v1:0", "anthropic.claude-sonnet-4-20250514-v1:0", diff --git a/litellm/integrations/SlackAlerting/slack_alerting.py b/litellm/integrations/SlackAlerting/slack_alerting.py index 0c36e15db01..8fb3e132ded 100644 --- a/litellm/integrations/SlackAlerting/slack_alerting.py +++ b/litellm/integrations/SlackAlerting/slack_alerting.py @@ -1378,6 +1378,11 @@ Model Info: """ if self.alerting is None: return + + # Start periodic flush if not already started + if not self.periodic_started and self.alerting is not None and len(self.alerting) > 0: + asyncio.create_task(self.periodic_flush()) + self.periodic_started = True if ( "webhook" in self.alerting diff --git a/litellm/integrations/custom_guardrail.py b/litellm/integrations/custom_guardrail.py index a5bb530fc56..1652ec2aa0c 100644 --- a/litellm/integrations/custom_guardrail.py +++ b/litellm/integrations/custom_guardrail.py @@ -475,11 +475,18 @@ class CustomGuardrail(CustomLogger): guardrail_config: DynamicGuardrailParams = DynamicGuardrailParams( **guardrail[self.guardrail_name] ) + extra_body = guardrail_config.get("extra_body", {}) if self._validate_premium_user() is not True: + if isinstance(extra_body, dict) and extra_body: + verbose_logger.warning( + "Guardrail %s: ignoring dynamic extra_body keys %s because premium_user is False", + self.guardrail_name, + list(extra_body.keys()), + ) return {} # Return the extra_body if it exists, otherwise empty dict - return guardrail_config.get("extra_body", {}) + return extra_body return {} diff --git a/litellm/integrations/email_templates/templates.py b/litellm/integrations/email_templates/templates.py index 5de23db0f24..091351df2bb 100644 --- a/litellm/integrations/email_templates/templates.py +++ b/litellm/integrations/email_templates/templates.py @@ -85,6 +85,30 @@ SOFT_BUDGET_ALERT_EMAIL_TEMPLATE = """ The LiteLLM team
""" +TEAM_SOFT_BUDGET_ALERT_EMAIL_TEMPLATE = """ +
Hi {team_alias} team member,
+
+ Your LiteLLM team has crossed its soft budget limit of {soft_budget}.
+
+ Current Spend: {spend}
+ Soft Budget: {soft_budget}
+ {max_budget_info}
+
+
+ ⚠️ Note: Your API requests will continue to work, but you should monitor your usage closely. + If you reach your maximum budget, requests will be rejected. +
+ + You can view your usage and manage your budget in the LiteLLM Dashboard.+ + If you have any questions, please send an email to {email_support_contact}
+ + Best,
+ The LiteLLM team
+""" + MAX_BUDGET_ALERT_EMAIL_TEMPLATE = """
Test email body
" + # Create mock HTTP client and inject it directly into the logger + # This ensures the mock is used regardless of any caching/import issues + mock_response = mock.Mock(spec=Response) + mock_response.status_code = 200 + mock_response.json.return_value = {"id": "test_email_id"} + mock_response.raise_for_status.return_value = None + + mock_async_client = mock.AsyncMock() + mock_async_client.post.return_value = mock_response + + # Directly inject the mock client to bypass any caching + logger.async_httpx_client = mock_async_client + # Send email await logger.send_email( from_email=from_email, to_email=to_email, subject=subject, html_body=html_body ) # Verify the HTTP client was called correctly - mock_httpx_client.post.assert_called_once() - call_args = mock_httpx_client.post.call_args + mock_async_client.post.assert_called_once() + call_args = mock_async_client.post.call_args # Verify the URL assert call_args[1]["url"] == "https://api.resend.com/emails" @@ -97,13 +84,7 @@ async def test_send_email_success(mock_env_vars, mock_httpx_client): @pytest.mark.asyncio -@respx.mock -async def test_send_email_missing_api_key(mock_httpx_client): - # Block all HTTP requests at network level to prevent real API calls - respx.post("https://api.resend.com/emails").mock( - return_value=httpx.Response(200, json={"id": "test_email_id"}) - ) - +async def test_send_email_missing_api_key(): # Remove the API key from environment before initializing logger original_key = os.environ.pop("RESEND_API_KEY", None) @@ -117,13 +98,18 @@ async def test_send_email_missing_api_key(mock_httpx_client): subject = "Test Subject" html_body = "Test email body
" - # Mock the response to avoid making real HTTP requests + # Create mock HTTP client and inject it directly into the logger + # This ensures the mock is used regardless of any caching issues mock_response = mock.Mock(spec=Response) mock_response.raise_for_status.return_value = None - mock_response.status_code = 200 mock_response.json.return_value = {"id": "test_email_id"} - mock_httpx_client.post.return_value = mock_response + + mock_async_client = mock.AsyncMock() + mock_async_client.post.return_value = mock_response + + # Directly inject the mock client to bypass any caching + logger.async_httpx_client = mock_async_client # Send email await logger.send_email( @@ -131,8 +117,8 @@ async def test_send_email_missing_api_key(mock_httpx_client): ) # Verify the HTTP client was called with None as the API key - mock_httpx_client.post.assert_called_once() - call_args = mock_httpx_client.post.call_args + mock_async_client.post.assert_called_once() + call_args = mock_async_client.post.call_args assert call_args[1]["headers"] == {"Authorization": "Bearer None"} finally: # Restore the original key if it existed @@ -141,13 +127,7 @@ async def test_send_email_missing_api_key(mock_httpx_client): @pytest.mark.asyncio -@respx.mock -async def test_send_email_multiple_recipients(mock_env_vars, mock_httpx_client): - # Block all HTTP requests at network level to prevent real API calls - respx.post("https://api.resend.com/emails").mock( - return_value=httpx.Response(200, json={"id": "test_email_id"}) - ) - +async def test_send_email_multiple_recipients(mock_env_vars): # Initialize the logger logger = ResendEmailLogger() @@ -157,13 +137,17 @@ async def test_send_email_multiple_recipients(mock_env_vars, mock_httpx_client): subject = "Test Subject" html_body = "Test email body
" - # Mock the response to avoid making real HTTP requests + # Create mock HTTP client and inject it directly into the logger mock_response = mock.Mock(spec=Response) - mock_response.raise_for_status.return_value = None - mock_response.status_code = 200 mock_response.json.return_value = {"id": "test_email_id"} - mock_httpx_client.post.return_value = mock_response + mock_response.raise_for_status.return_value = None + + mock_async_client = mock.AsyncMock() + mock_async_client.post.return_value = mock_response + + # Directly inject the mock client to bypass any caching + logger.async_httpx_client = mock_async_client # Send email await logger.send_email( @@ -171,7 +155,7 @@ async def test_send_email_multiple_recipients(mock_env_vars, mock_httpx_client): ) # Verify the HTTP client was called with multiple recipients - mock_httpx_client.post.assert_called_once() - call_args = mock_httpx_client.post.call_args + mock_async_client.post.assert_called_once() + call_args = mock_async_client.post.call_args request_body = call_args[1]["json"] assert request_body["to"] == to_email diff --git a/tests/test_litellm/google_genai/test_google_genai_handler.py b/tests/test_litellm/google_genai/test_google_genai_handler.py index fc120280511..17a6cba2d63 100644 --- a/tests/test_litellm/google_genai/test_google_genai_handler.py +++ b/tests/test_litellm/google_genai/test_google_genai_handler.py @@ -183,10 +183,8 @@ def test_stream_transformation_error_sync(): "translate_completion_output_params_streaming", return_value=None ): - # Mock litellm.completion at the module level where it's imported - # We need to patch it in the handler module, not in litellm itself - with patch("litellm.google_genai.adapters.handler.litellm") as mock_litellm: - mock_litellm.completion.return_value = mock_stream + # Patch litellm.completion directly to prevent real API calls + with patch("litellm.completion", return_value=mock_stream): # Call the handler with stream=True and expect a ValueError with pytest.raises(ValueError, match="Failed to transform streaming response"): GenerateContentToCompletionHandler.generate_content_handler( diff --git a/tests/test_litellm/integrations/test_langfuse.py b/tests/test_litellm/integrations/test_langfuse.py index 97011df0ba7..7168f5a4332 100644 --- a/tests/test_litellm/integrations/test_langfuse.py +++ b/tests/test_litellm/integrations/test_langfuse.py @@ -256,9 +256,22 @@ class TestLangfuseUsageDetails(unittest.TestCase): Test that _log_langfuse_v2 correctly handles None values in the usage object by converting them to 0, preventing validation errors. """ - # Reset mock call counts to ensure clean state - self.mock_langfuse_trace.reset_mock() - self.mock_langfuse_client.reset_mock() + # Create fresh mocks for this test to avoid state pollution from setUp's side_effect + # The setUp configures trace.side_effect which can interfere with return_value + mock_trace = MagicMock() + mock_generation = MagicMock() + mock_generation.trace_id = "test-trace-id" + mock_span = MagicMock() + mock_span.end = MagicMock() + + mock_trace.generation.return_value = mock_generation + mock_trace.span.return_value = mock_span + + mock_client = MagicMock() + mock_client.trace.return_value = mock_trace + + # Use our fresh mock client + self.logger.Langfuse = mock_client with patch( "litellm.integrations.langfuse.langfuse._add_prompt_to_generation_params", @@ -294,13 +307,6 @@ class TestLangfuseUsageDetails(unittest.TestCase): # Use fixed timestamps to avoid timing-related flakiness fixed_time = datetime.datetime(2024, 1, 1, 12, 0, 0) - # Ensure the mock trace is properly set up before the call - # Re-setup the trace chain to ensure it's fresh - self.mock_langfuse_trace.generation.return_value = self.mock_langfuse_generation - self.mock_langfuse_trace.span.return_value = self.mock_langfuse_span - self.mock_langfuse_client.trace.return_value = self.mock_langfuse_trace - self.logger.Langfuse = self.mock_langfuse_client - # Call the method under test try: self.logger._log_langfuse_v2( @@ -321,11 +327,11 @@ class TestLangfuseUsageDetails(unittest.TestCase): self.fail(f"_log_langfuse_v2 raised an exception: {e}") # Verify that trace was called first - self.mock_langfuse_client.trace.assert_called() + mock_client.trace.assert_called() # Check the arguments passed to the mocked langfuse generation call - self.mock_langfuse_trace.generation.assert_called_once() - call_args, call_kwargs = self.mock_langfuse_trace.generation.call_args + mock_trace.generation.assert_called_once() + call_args, call_kwargs = mock_trace.generation.call_args # Inspect the usage and usage_details dictionaries usage_arg = call_kwargs.get("usage") diff --git a/tests/test_litellm/integrations/test_langfuse_otel.py b/tests/test_litellm/integrations/test_langfuse_otel.py index f8c662979ad..ba4a096be24 100644 --- a/tests/test_litellm/integrations/test_langfuse_otel.py +++ b/tests/test_litellm/integrations/test_langfuse_otel.py @@ -1,92 +1,119 @@ import json import os -from datetime import datetime from unittest.mock import MagicMock, patch import pytest from litellm.integrations.langfuse.langfuse_otel import LangfuseOtelLogger -from litellm.types.integrations.langfuse_otel import LangfuseOtelConfig +from litellm.integrations.opentelemetry import OpenTelemetryConfig from litellm.types.llms.openai import ResponsesAPIResponse class TestLangfuseOtelIntegration: - def test_get_langfuse_otel_config_with_required_env_vars(self): """Test that config is created correctly with required environment variables.""" # Clean environment of any Langfuse-related variables - env_vars_to_clean = ['LANGFUSE_HOST', 'OTEL_EXPORTER_OTLP_ENDPOINT', 'OTEL_EXPORTER_OTLP_HEADERS'] - with patch.dict(os.environ, { - 'LANGFUSE_PUBLIC_KEY': 'test_public_key', - 'LANGFUSE_SECRET_KEY': 'test_secret_key' - }, clear=False): + env_vars_to_clean = [ + "LANGFUSE_HOST", + "OTEL_EXPORTER_OTLP_ENDPOINT", + "OTEL_EXPORTER_OTLP_HEADERS", + ] + with patch.dict( + os.environ, + { + "LANGFUSE_PUBLIC_KEY": "test_public_key", + "LANGFUSE_SECRET_KEY": "test_secret_key", + }, + clear=False, + ): # Remove any existing Langfuse variables for var in env_vars_to_clean: if var in os.environ: del os.environ[var] - + config = LangfuseOtelLogger.get_langfuse_otel_config() - - assert isinstance(config, LangfuseOtelConfig) - assert config.protocol == "otlp_http" - assert "Authorization=Basic" in config.otlp_auth_headers - # Check that environment variables are set correctly (US default) - assert os.environ.get("OTEL_EXPORTER_OTLP_ENDPOINT") == "https://us.cloud.langfuse.com/api/public/otel" - assert "Authorization=Basic" in os.environ.get("OTEL_EXPORTER_OTLP_HEADERS", "") - + + assert isinstance(config, OpenTelemetryConfig) + assert config.exporter == "otlp_http" + assert "Authorization=Basic" in config.headers + # Note: We no longer set os.environ explicitly to avoid leakage + # assert os.environ.get("OTEL_EXPORTER_OTLP_ENDPOINT") == "https://us.cloud.langfuse.com/api/public/otel" + # assert "Authorization=Basic" in os.environ.get("OTEL_EXPORTER_OTLP_HEADERS", "") + def test_get_langfuse_otel_config_missing_keys(self): """Test that ValueError is raised when required keys are missing.""" with patch.dict(os.environ, {}, clear=True): - with pytest.raises(ValueError, match="LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY must be set"): + with pytest.raises( + ValueError, + match="LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY must be set", + ): LangfuseOtelLogger.get_langfuse_otel_config() - + def test_get_langfuse_otel_config_with_eu_host(self): """Test config with EU host.""" - with patch.dict(os.environ, { - 'LANGFUSE_PUBLIC_KEY': 'test_public_key', - 'LANGFUSE_SECRET_KEY': 'test_secret_key', - 'LANGFUSE_HOST': 'https://cloud.langfuse.com' - }, clear=False): + with patch.dict( + os.environ, + { + "LANGFUSE_PUBLIC_KEY": "test_public_key", + "LANGFUSE_SECRET_KEY": "test_secret_key", + "LANGFUSE_HOST": "https://cloud.langfuse.com", + }, + clear=False, + ): config = LangfuseOtelLogger.get_langfuse_otel_config() - - assert os.environ.get("OTEL_EXPORTER_OTLP_ENDPOINT") == "https://cloud.langfuse.com/api/public/otel" - + # Endpoint assertion removed as side effect is gone + assert isinstance(config, OpenTelemetryConfig) + def test_get_langfuse_otel_config_with_custom_host(self): """Test config with custom host.""" - with patch.dict(os.environ, { - 'LANGFUSE_PUBLIC_KEY': 'test_public_key', - 'LANGFUSE_SECRET_KEY': 'test_secret_key', - 'LANGFUSE_HOST': 'https://my-langfuse.com' - }, clear=False): + with patch.dict( + os.environ, + { + "LANGFUSE_PUBLIC_KEY": "test_public_key", + "LANGFUSE_SECRET_KEY": "test_secret_key", + "LANGFUSE_HOST": "https://my-langfuse.com", + }, + clear=False, + ): config = LangfuseOtelLogger.get_langfuse_otel_config() - - assert os.environ.get("OTEL_EXPORTER_OTLP_ENDPOINT") == "https://my-langfuse.com/api/public/otel" - + # Endpoint assertion removed as side effect is gone + assert isinstance(config, OpenTelemetryConfig) + def test_get_langfuse_otel_config_with_host_no_protocol(self): """Test config with custom host without protocol.""" - with patch.dict(os.environ, { - 'LANGFUSE_PUBLIC_KEY': 'test_public_key', - 'LANGFUSE_SECRET_KEY': 'test_secret_key', - 'LANGFUSE_HOST': 'my-langfuse.com' - }, clear=False): + with patch.dict( + os.environ, + { + "LANGFUSE_PUBLIC_KEY": "test_public_key", + "LANGFUSE_SECRET_KEY": "test_secret_key", + "LANGFUSE_HOST": "my-langfuse.com", + }, + clear=False, + ): config = LangfuseOtelLogger.get_langfuse_otel_config() - - assert os.environ.get("OTEL_EXPORTER_OTLP_ENDPOINT") == "https://my-langfuse.com/api/public/otel" - + # Endpoint assertion removed as side effect is gone + assert isinstance(config, OpenTelemetryConfig) + def test_set_langfuse_otel_attributes(self): """Test that set_langfuse_otel_attributes calls the Arize utils function.""" from litellm.integrations.langfuse.langfuse_otel_attributes import ( LangfuseLLMObsOTELAttributes, ) - + mock_span = MagicMock() mock_kwargs = {"test": "kwargs"} mock_response = {"test": "response"} - - with patch('litellm.integrations.arize._utils.set_attributes') as mock_set_attributes: - LangfuseOtelLogger.set_langfuse_otel_attributes(mock_span, mock_kwargs, mock_response) - - mock_set_attributes.assert_called_once_with(mock_span, mock_kwargs, mock_response, LangfuseLLMObsOTELAttributes) + + with patch( + "litellm.integrations.arize._utils.set_attributes" + ) as mock_set_attributes: + LangfuseOtelLogger.set_langfuse_otel_attributes( + mock_span, mock_kwargs, mock_response + ) + + mock_set_attributes.assert_called_once_with( + mock_span, mock_kwargs, mock_response, LangfuseLLMObsOTELAttributes + ) def test_set_langfuse_environment_attribute(self): """Test that Langfuse environment is set correctly when environment variable is present.""" @@ -94,15 +121,17 @@ class TestLangfuseOtelIntegration: mock_kwargs = {"test": "kwargs"} test_env = "staging" - with patch.dict(os.environ, {'LANGFUSE_TRACING_ENVIRONMENT': test_env}): - with patch('litellm.integrations.arize._utils.safe_set_attribute') as mock_safe_set_attribute: - LangfuseOtelLogger._set_langfuse_specific_attributes(mock_span, mock_kwargs, {}) - + with patch.dict(os.environ, {"LANGFUSE_TRACING_ENVIRONMENT": test_env}): + with patch( + "litellm.integrations.arize._utils.safe_set_attribute" + ) as mock_safe_set_attribute: + LangfuseOtelLogger._set_langfuse_specific_attributes( + mock_span, mock_kwargs, {} + ) + # safe_set_attribute(span, key, value) → positional args mock_safe_set_attribute.assert_called_once_with( - mock_span, - "langfuse.environment", - test_env + mock_span, "langfuse.environment", test_env ) def test_extract_langfuse_metadata_basic(self): @@ -119,11 +148,13 @@ class TestLangfuseOtelIntegration: # Build a stub module + class on-the-fly stub_module = types.ModuleType("litellm.integrations.langfuse.langfuse") + class StubLFLogger: @staticmethod def add_metadata_from_header(litellm_params, metadata): # Echo back existing metadata plus a marker return {**metadata, "enriched": True} + stub_module.LangFuseLogger = StubLFLogger # type: ignore # Register stub in sys.modules so import inside method succeeds @@ -159,11 +190,16 @@ class TestLangfuseOtelIntegration: kwargs = {"litellm_params": {"metadata": metadata}} # Capture calls to safe_set_attribute - with patch('litellm.integrations.arize._utils.safe_set_attribute') as mock_safe_set_attribute: - LangfuseOtelLogger._set_langfuse_specific_attributes(MagicMock(), kwargs, None) + with patch( + "litellm.integrations.arize._utils.safe_set_attribute" + ) as mock_safe_set_attribute: + LangfuseOtelLogger._set_langfuse_specific_attributes( + MagicMock(), kwargs, None + ) # Build expected calls manually for clarity from litellm.types.integrations.langfuse_otel import LangfuseSpanAttributes + expected = { LangfuseSpanAttributes.GENERATION_NAME.value: "gen-name", LangfuseSpanAttributes.GENERATION_ID.value: "gen-id", @@ -176,12 +212,14 @@ class TestLangfuseOtelIntegration: # Lists / dicts should be JSON strings LangfuseSpanAttributes.TAGS.value: json.dumps(["tagA", "tagB"]), LangfuseSpanAttributes.TRACE_NAME.value: "trace-name", - LangfuseSpanAttributes.TRACE_ID.value: "trace-id", + LangfuseSpanAttributes.TRACE_ID.value: "traceid", # stripped dashes LangfuseSpanAttributes.TRACE_METADATA.value: json.dumps({"k": "v"}), LangfuseSpanAttributes.TRACE_VERSION.value: "t-ver", LangfuseSpanAttributes.TRACE_RELEASE.value: "rel-1", LangfuseSpanAttributes.EXISTING_TRACE_ID.value: "existing-id", - LangfuseSpanAttributes.UPDATE_TRACE_KEYS.value: json.dumps(["key1", "key2"]), + LangfuseSpanAttributes.UPDATE_TRACE_KEYS.value: json.dumps( + ["key1", "key2"] + ), LangfuseSpanAttributes.DEBUG_LANGFUSE.value: True, } @@ -191,7 +229,9 @@ class TestLangfuseOtelIntegration: for call in mock_safe_set_attribute.call_args_list } - assert actual == expected, "Mismatch between expected and actual OTEL attribute mapping." + assert ( + actual == expected + ), "Mismatch between expected and actual OTEL attribute mapping." def test_set_langfuse_specific_attributes_with_content(self): """Test that _set_langfuse_specific_attributes correctly sets observation.output with regular content response.""" @@ -200,15 +240,15 @@ class TestLangfuseOtelIntegration: # Create response with content response_obj = ModelResponse( - id='chatcmpl-test', - model='gpt-4o', + id="chatcmpl-test", + model="gpt-4o", choices=[ Choices( - finish_reason='stop', + finish_reason="stop", message={ "role": "assistant", - "content": "The weather in Tokyo is sunny." - } + "content": "The weather in Tokyo is sunny.", + }, ) ], ) @@ -217,20 +257,21 @@ class TestLangfuseOtelIntegration: "messages": [{"role": "user", "content": "What's the weather in Tokyo?"}], } - with patch('litellm.integrations.arize._utils.safe_set_attribute') as mock_safe_set_attribute: - LangfuseOtelLogger._set_langfuse_specific_attributes(MagicMock(), kwargs, response_obj) + with patch( + "litellm.integrations.arize._utils.safe_set_attribute" + ) as mock_safe_set_attribute: + LangfuseOtelLogger._set_langfuse_specific_attributes( + MagicMock(), kwargs, response_obj + ) expect_output = { LangfuseSpanAttributes.OBSERVATION_INPUT.value: [ - { - "role": "user", - "content": "What's the weather in Tokyo?" - } + {"role": "user", "content": "What's the weather in Tokyo?"} ], LangfuseSpanAttributes.OBSERVATION_OUTPUT.value: { "role": "assistant", - "content": "The weather in Tokyo is sunny." - } + "content": "The weather in Tokyo is sunny.", + }, } # Flatten the actual calls into {key: value} @@ -239,8 +280,9 @@ class TestLangfuseOtelIntegration: for call in mock_safe_set_attribute.call_args_list } - assert actual == expect_output, "Mismatch in observation input/output OTEL attributes." - + assert ( + actual == expect_output + ), "Mismatch in observation input/output OTEL attributes." def test_set_langfuse_specific_attributes_with_tool_calls(self): """Test that _set_langfuse_specific_attributes correctly sets observation.output with tool calls in Langfuse format.""" @@ -254,42 +296,44 @@ class TestLangfuseOtelIntegration: # Create response with tool calls response_obj = ModelResponse( - id='chatcmpl-test', - model='gpt-4o', + id="chatcmpl-test", + model="gpt-4o", choices=[ Choices( - finish_reason='tool_calls', + finish_reason="tool_calls", message={ "role": "assistant", "content": None, "tool_calls": [ ChatCompletionMessageToolCall( function=Function( - arguments='{"location":"Tokyo"}', - name='get_weather' + arguments='{"location":"Tokyo"}', name="get_weather" ), - id='call_123', - type='function' + id="call_123", + type="function", ) - ] - } + ], + }, ) ], ) - with patch('litellm.integrations.arize._utils.safe_set_attribute') as mock_safe_set_attribute: - LangfuseOtelLogger._set_langfuse_specific_attributes(MagicMock(), {}, - response_obj) + with patch( + "litellm.integrations.arize._utils.safe_set_attribute" + ) as mock_safe_set_attribute: + LangfuseOtelLogger._set_langfuse_specific_attributes( + MagicMock(), {}, response_obj + ) expected = { LangfuseSpanAttributes.OBSERVATION_OUTPUT.value: [ - { - "id": "chatcmpl-test", - "name": "get_weather", - "arguments": {"location": "Tokyo"}, - "call_id": "call_123", - "type": "function_call" - } + { + "id": "chatcmpl-test", + "name": "get_weather", + "arguments": {"location": "Tokyo"}, + "call_id": "call_123", + "type": "function_call", + } ] } @@ -298,8 +342,9 @@ class TestLangfuseOtelIntegration: call.args[1]: json.loads(call.args[2]) for call in mock_safe_set_attribute.call_args_list } - assert actual == expected, "Mismatch in observation output OTEL attribute for tool calls." - + assert ( + actual == expected + ), "Mismatch in observation output OTEL attribute for tool calls." def test_construct_dynamic_otel_headers_with_langfuse_keys(self): """Test that construct_dynamic_otel_headers creates proper auth headers when langfuse keys are provided.""" @@ -307,28 +352,27 @@ class TestLangfuseOtelIntegration: # Create dynamic params with langfuse keys dynamic_params = StandardCallbackDynamicParams( - langfuse_public_key="test_public_key", - langfuse_secret_key="test_secret_key" + langfuse_public_key="test_public_key", langfuse_secret_key="test_secret_key" ) - + logger = LangfuseOtelLogger() result = logger.construct_dynamic_otel_headers(dynamic_params) - + # Should return a dict with otlp_auth_headers assert result is not None assert "Authorization" in result - + # The auth header should contain the basic auth format auth_header = result["Authorization"] assert auth_header.startswith("Basic ") - + # Verify the header format by decoding import base64 # Extract the base64 part from "Authorization=BasicPublic Model Hub
,
}));
+vi.mock("@/app/(dashboard)/hooks/uiSettings/useUISettings", () => ({
+ useUISettings: mockUseUISettings,
+}));
+
+vi.mock("@/utils/cookieUtils", () => ({
+ getCookie: mockGetCookie,
+}));
+
+vi.mock("@/utils/jwtUtils", () => ({
+ checkTokenValidity: mockCheckTokenValidity,
+}));
+
describe("ModelHubTable", () => {
afterEach(() => {
vi.clearAllMocks();
});
+ // Reusable helper function to setup mocks for auth redirect tests
+ const setupAuthRedirectTest = (
+ requireAuth: boolean,
+ tokenValue: string | null,
+ isTokenValid: boolean
+ ) => {
+ mockUseUISettings.mockReturnValue({
+ data: {
+ values: {
+ require_auth_for_public_ai_hub: requireAuth,
+ },
+ },
+ isLoading: false,
+ });
+ mockGetCookie.mockReturnValue(tokenValue);
+ mockCheckTokenValidity.mockReturnValue(isTokenValid);
+ mockRouterReplace.mockClear();
+
+ // Setup other required mocks
+ vi.mocked(networking.getUiConfig).mockResolvedValue({
+ server_root_path: "/",
+ proxy_base_url: "http://localhost:4000",
+ auto_redirect_to_sso: false,
+ admin_ui_disabled: false,
+ });
+ vi.mocked(networking.modelHubPublicModelsCall).mockResolvedValue([]);
+ vi.mocked(networking.getUiSettings).mockResolvedValue({
+ values: {
+ require_auth_for_public_ai_hub: requireAuth,
+ },
+ });
+ };
+
+ // Reusable test function for auth redirect scenarios
+ const testAuthRedirect = (
+ requireAuth: boolean,
+ tokenValue: string | null,
+ isTokenValid: boolean,
+ shouldRedirect: boolean,
+ description: string
+ ) => {
+ it(description, async () => {
+ setupAuthRedirectTest(requireAuth, tokenValue, isTokenValid);
+
+ renderWithProviders(
+ SSO Settings
,
+}));
+
+vi.mock("./Settings/AdminSettings/UISettings/UISettings", () => ({
+ default: () => UI Settings
,
+}));
+
+vi.mock("./SCIM", () => ({
+ default: () => SCIM Config
,
+}));
+
+vi.mock("./SSOModals", () => ({
+ default: () => SSO Modals
,
+}));
+
+vi.mock("./UIAccessControlForm", () => ({
+ default: () => UI Access Control Form
,
+}));
+
+const mockUseAuthorized = vi.fn();
+vi.mock("@/app/(dashboard)/hooks/useAuthorized", () => ({
+ default: () => mockUseAuthorized(),
+}));
+
+describe("AdminPanel", () => {
+ beforeEach(() => {
+ vi.clearAllMocks();
+ mockUseAuthorized.mockReturnValue({
+ premiumUser: false,
+ accessToken: "test-token",
+ userId: "user-1",
+ });
+ mockGetSSOSettings.mockResolvedValue({
+ values: {},
+ });
+ mockGetAllowedIPs.mockResolvedValue([]);
+ mockAddAllowedIP.mockResolvedValue({});
+ mockDeleteAllowedIP.mockResolvedValue({});
+ });
+
+ it("should render the admin panel", () => {
+ render(
+
+
+
+
+
+
+
+
+
+
+
+ setIsAllowedIPModalVisible(false)}
+ footer={[
+ ,
+ ,
+ ]}
+ >
+
+
+
+
+ setIsAddIPModalVisible(false)}
+ footer={null}
+ >
+
+
+
+ setIsDeleteIPModalVisible(false)}
+ onOk={confirmDeleteIP}
+ footer={[
+ ,
+ ,
+ ]}
+ >
+ Are you sure you want to delete the IP address: {ipToDelete}?
+
+
+ {/* UI Access Control Modal */}
+
+ {
+ handleUIAccessControlOk();
+ NotificationsManager.success("UI Access Control settings updated successfully");
+ }}
+ />
+
+
+
+ Admin Access
+ Go to 'Internal Users' page to add other admins.
+
+ );
+};
+
+export default AdminPanel;
diff --git a/ui/litellm-dashboard/src/components/ModelSelect/ModelSelect.test.tsx b/ui/litellm-dashboard/src/components/ModelSelect/ModelSelect.test.tsx
index 3052f790098..6da2f82a2f1 100644
--- a/ui/litellm-dashboard/src/components/ModelSelect/ModelSelect.test.tsx
+++ b/ui/litellm-dashboard/src/components/ModelSelect/ModelSelect.test.tsx
@@ -37,12 +37,19 @@ vi.mock("antd", async (importOriginal) => {
mode,
...props
}: any) => {
+ // Simulate maxTagCount responsive behavior - if value length > 5, call maxTagPlaceholder
+ const shouldShowPlaceholder = maxTagCount === "responsive" && Array.isArray(value) && value.length > 5;
+ const visibleValues = shouldShowPlaceholder ? value.slice(0, 5) : value;
+ const omittedValues = shouldShowPlaceholder
+ ? value.slice(5).map((v: string) => ({ value: v, label: v }))
+ : [];
+
return (
+ {shouldShowPlaceholder && maxTagPlaceholder && (
+
);
},
@@ -82,6 +92,24 @@ const mockUseTeam = vi.mocked(useTeam);
const mockUseOrganization = vi.mocked(useOrganization);
const mockUseCurrentUser = vi.mocked(useCurrentUser);
+const createMockOrganization = (models: string[]): Organization => ({
+ organization_id: "org-1",
+ organization_alias: "Test Org",
+ budget_id: "budget-1",
+ metadata: {},
+ models,
+ spend: 0,
+ model_spend: {},
+ created_at: "2024-01-01",
+ created_by: "user-1",
+ updated_at: "2024-01-01",
+ updated_by: "user-1",
+ litellm_budget_table: null,
+ teams: null,
+ users: null,
+ members: null,
+});
+
describe("ModelSelect", () => {
const mockProxyModels: ProxyModel[] = [
{ id: "gpt-4", object: "model", created: 1234567890, owned_by: "openai" },
@@ -112,125 +140,44 @@ describe("ModelSelect", () => {
} as any);
});
- it("should render", async () => {
+ it("should render with all option groups", async () => {
renderWithProviders(
{maxTagPlaceholder(omittedValues)}
+ )}
+ {
+ if (toolId && !isFromConfig) {
+ onEdit(toolId);
+ }
+ }}
+ />
+ {
+ if (toolId && !isFromConfig) {
+ onDelete(toolId);
+ }
+ }}
+ />
+
+ );
+ },
+ },
+ ];
diff --git a/ui/litellm-dashboard/src/components/SearchTools/SearchToolTester.test.tsx b/ui/litellm-dashboard/src/components/SearchTools/SearchToolTester.test.tsx
new file mode 100644
index 00000000000..254a634e3b3
--- /dev/null
+++ b/ui/litellm-dashboard/src/components/SearchTools/SearchToolTester.test.tsx
@@ -0,0 +1,426 @@
+import { render, screen, waitFor } from "@testing-library/react";
+import userEvent from "@testing-library/user-event";
+import { beforeEach, describe, expect, it, vi } from "vitest";
+import { SearchToolTester } from "./SearchToolTester";
+import * as networking from "../networking";
+import NotificationsManager from "../molecules/notifications_manager";
+import * as antd from "antd";
+
+vi.mock("../networking", () => ({
+ searchToolQueryCall: vi.fn(),
+}));
+
+vi.mock("antd", async () => {
+ const actual = await vi.importActual("antd");
+ return {
+ ...actual,
+ message: {
+ warning: vi.fn(),
+ success: vi.fn(),
+ error: vi.fn(),
+ },
+ };
+});
+
+const mockSearchResults = {
+ results: [
+ {
+ title: "Test Result 1",
+ url: "https://example.com/result1",
+ snippet: "This is a short snippet for the first result.",
+ },
+ {
+ title: "Test Result 2",
+ url: "https://example.com/result2",
+ snippet: "This is a longer snippet that exceeds two hundred characters and should be truncated when displayed in the results. It contains more detailed information about the search result that would normally be shown in a search engine result page.",
+ },
+ ],
+};
+
+const defaultProps = {
+ searchToolName: "test-search-tool",
+ accessToken: "test-token",
+};
+
+describe("SearchToolTester", () => {
+ beforeEach(() => {
+ vi.clearAllMocks();
+ vi.mocked(networking.searchToolQueryCall).mockResolvedValue(mockSearchResults);
+ vi.spyOn(Date, "now").mockReturnValue(1000000000000);
+ });
+
+ it("should render", () => {
+ render(
+ Search Tool Tester for {searchToolName}
+ Access Token: {accessToken}
+
+ ),
+}));
+
+describe("SearchToolView", () => {
+ const mockSearchTool: SearchTool = {
+ search_tool_id: "test-tool-id-123",
+ search_tool_name: "Test Search Tool",
+ litellm_params: {
+ search_provider: "perplexity",
+ api_key: "sk-test-key",
+ },
+ search_tool_info: {
+ description: "Test description",
+ },
+ created_at: "2024-01-15T10:30:00Z",
+ };
+
+ const mockAvailableProviders: AvailableSearchProvider[] = [
+ {
+ provider_name: "perplexity",
+ ui_friendly_name: "Perplexity AI",
+ },
+ {
+ provider_name: "tavily",
+ ui_friendly_name: "Tavily Search",
+ },
+ ];
+
+ const defaultProps = {
+ searchTool: mockSearchTool,
+ onBack: vi.fn(),
+ isEditing: false,
+ accessToken: "test-token",
+ availableProviders: mockAvailableProviders,
+ };
+
+ beforeEach(async () => {
+ vi.clearAllMocks();
+ const { copyToClipboard } = await import("@/utils/dataUtils");
+ vi.mocked(copyToClipboard).mockResolvedValue(true);
+ });
+
+ it("should render", () => {
+ render(
@@ -67,11 +66,10 @@ export const SearchToolView: React.FC = ({
size="small"
icon={copiedStates["search-tool-id"] ?
diff --git a/ui/litellm-dashboard/src/components/SearchTools/SearchTools.test.tsx b/ui/litellm-dashboard/src/components/SearchTools/SearchTools.test.tsx
new file mode 100644
index 00000000000..f1f7bf8ab42
--- /dev/null
+++ b/ui/litellm-dashboard/src/components/SearchTools/SearchTools.test.tsx
@@ -0,0 +1,234 @@
+import * as roles from "@/utils/roles";
+import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
+import { render, screen, waitFor } from "@testing-library/react";
+import userEvent from "@testing-library/user-event";
+import { beforeEach, describe, expect, it, vi } from "vitest";
+import * as networking from "../networking";
+import SearchTools from "./SearchTools";
+import { AvailableSearchProvider, SearchTool } from "./types";
+
+vi.mock("../networking", () => ({
+ fetchSearchTools: vi.fn(),
+ updateSearchTool: vi.fn(),
+ deleteSearchTool: vi.fn(),
+ fetchAvailableSearchProviders: vi.fn(),
+}));
+
+vi.mock("@/utils/roles", () => ({
+ isAdminRole: vi.fn(),
+}));
+
+vi.mock("./SearchToolView", () => ({
+ SearchToolView: ({ searchTool, onBack }: { searchTool: SearchTool; onBack: () => void }) => (
+
+
+ ),
+}));
+
+vi.mock("./CreateSearchTools", () => ({
+ default: ({
+ isModalVisible,
+ setModalVisible,
+ }: {
+ isModalVisible: boolean;
+ setModalVisible: (visible: boolean) => void;
+ }) =>
+ isModalVisible ? (
+ Search Tool View: {searchTool.search_tool_name}
+
+
+
+
+ ) : null,
+}));
+
+vi.mock("../common_components/DeleteResourceModal", () => ({
+ default: ({
+ isOpen,
+ onOk,
+ onCancel,
+ }: {
+ isOpen: boolean;
+ onOk: () => void;
+ onCancel: () => void;
+ }) =>
+ isOpen ? (
+
+
+
+
+ ) : null,
+}));
+
+const mockSearchTools: SearchTool[] = [
+ {
+ search_tool_id: "tool-1",
+ search_tool_name: "Perplexity Search",
+ litellm_params: {
+ search_provider: "perplexity",
+ api_key: "sk-test-key",
+ },
+ search_tool_info: {
+ description: "Test description",
+ },
+ created_at: "2024-01-15T10:30:00Z",
+ },
+ {
+ search_tool_id: "tool-2",
+ search_tool_name: "Tavily Search",
+ litellm_params: {
+ search_provider: "tavily",
+ },
+ created_at: "2024-01-16T10:30:00Z",
+ },
+];
+
+const mockAvailableProviders: AvailableSearchProvider[] = [
+ {
+ provider_name: "perplexity",
+ ui_friendly_name: "Perplexity AI",
+ },
+ {
+ provider_name: "tavily",
+ ui_friendly_name: "Tavily Search",
+ },
+];
+
+const createWrapper = () => {
+ const queryClient = new QueryClient({
+ defaultOptions: {
+ queries: {
+ retry: false,
+ },
+ },
+ });
+ return ({ children }: { children: React.ReactNode }) => (
+ Are you sure you want to delete this search tool?
- -
-
- }
- getRowCanExpand={() => false}
- isLoading={isLoadingTools}
- noDataMessage="No search tools configured"
+ rowKey={(record) => record.search_tool_id || record.search_tool_name}
+ pagination={false}
+ locale={{
+ emptyText: "No search tools configured",
+ }}
+ size="small"
/>
-
+
+
);
return (
- Admin Access
- Go to 'Internal Users' page to add other admins.
-
-
- SSO Settings
- Security Settings
- SCIM
- UI Settings
-
-
-
-
-
-
- ✨ Security Settings
-
-
-
- If you need to login without sso, you can access{" "}
-
- {nonSssoUrl}{" "}
-
-
-
-
-
-
-
-
-
-
- );
-};
-
-export default AdminPanel;
diff --git a/ui/litellm-dashboard/src/components/budgets/budget_modal.tsx b/ui/litellm-dashboard/src/components/budgets/budget_modal.tsx
index 3afac21aae1..490613de254 100644
--- a/ui/litellm-dashboard/src/components/budgets/budget_modal.tsx
+++ b/ui/litellm-dashboard/src/components/budgets/budget_modal.tsx
@@ -43,7 +43,7 @@ const BudgetModal: React.FC
-
-
-
-
-
-
-
-
-
-
-
- setIsAllowedIPModalVisible(false)}
- footer={[
- ,
- ,
- ]}
- >
-
-
-
-
- setIsAddIPModalVisible(false)}
- footer={null}
- >
-
-
-
- setIsDeleteIPModalVisible(false)}
- onOk={confirmDeleteIP}
- footer={[
- ,
- ,
- ]}
- >
-
-
- {/* UI Access Control Modal */}
-
- {
- handleUIAccessControlOk();
- NotificationsManager.success("UI Access Control settings updated successfully");
- }}
- />
-
-
- Are you sure you want to delete the IP address: {ipToDelete}?
-
{/* Export Type Selection */}
diff --git a/ui/litellm-dashboard/src/components/common_components/chartUtils.test.tsx b/ui/litellm-dashboard/src/components/common_components/chartUtils.test.tsx
new file mode 100644
index 00000000000..b924021863a
--- /dev/null
+++ b/ui/litellm-dashboard/src/components/common_components/chartUtils.test.tsx
@@ -0,0 +1,382 @@
+import { render, screen } from "@testing-library/react";
+import { describe, expect, it } from "vitest";
+import { CustomLegend, CustomTooltip } from "./chartUtils";
+import type { CustomTooltipProps } from "@tremor/react";
+import { SpendMetrics } from "../UsagePage/types";
+
+describe("CustomTooltip", () => {
+ const mockPayload = [
+ {
+ dataKey: "metrics.total_tokens",
+ value: 1000,
+ color: "blue",
+ payload: {
+ date: "2024-01-15",
+ metrics: {
+ total_tokens: 1000,
+ prompt_tokens: 600,
+ completion_tokens: 400,
+ spend: 0.05,
+ api_requests: 10,
+ successful_requests: 9,
+ failed_requests: 1,
+ cache_read_input_tokens: 0,
+ cache_creation_input_tokens: 0,
+ } as SpendMetrics,
+ },
+ },
+ ];
+
+ it("should render", () => {
+ const props: CustomTooltipProps = {
+ active: true,
+ payload: mockPayload,
+ label: "2024-01-15",
+ };
+ render( = ({
= ({
,
]}
width={1000}
- destroyOnClose
+ destroyOnHidden
>
diff --git a/ui/litellm-dashboard/src/components/edit_model/edit_model_modal.tsx b/ui/litellm-dashboard/src/components/edit_model/edit_model_modal.tsx
index 88753b7df3b..95ceb65d10d 100644
--- a/ui/litellm-dashboard/src/components/edit_model/edit_model_modal.tsx
+++ b/ui/litellm-dashboard/src/components/edit_model/edit_model_modal.tsx
@@ -53,8 +53,8 @@ export const handleEditModelSubmit = async (
model_info:
model_info_model_id !== undefined
? {
- id: model_info_model_id,
- }
+ id: model_info_model_id,
+ }
: undefined,
};
@@ -119,7 +119,7 @@ const EditModelModal: React.FC = ({ visible, onCancel, mode
return (
= ({ visible, possibleUIRoles,
}
return (
-
+