[Staging] - Ishaan March 17th

CLAUDE.md

@@ -140,6 +140,11 @@ LiteLLM is a unified interface for 100+ LLM providers with two main components:
 - **Check index coverage.** For new or modified queries, check `schema.prisma` for a supporting index. Prefer extending an existing index (e.g. `@@index([a])` → `@@index([a, b])`) over adding a new one, unless it's a `@@unique`. Only add indexes for large/frequent queries.
 - **Keep schema files in sync.** Apply schema changes to all `schema.prisma` copies (`schema.prisma`, `litellm/proxy/`, `litellm-proxy-extras/`, `litellm-js/spend-logs/` for SpendLogs) with a migration under `litellm-proxy-extras/litellm_proxy_extras/migrations/`.
 
+### Setup Wizard (`litellm/setup_wizard.py`)
+- The wizard is implemented as a single `SetupWizard` class with `@staticmethod` methods — keep it that way. No module-level functions except `run_setup_wizard()` (the public entrypoint) and pure helpers (color, ANSI).
+- Use `litellm.utils.check_valid_key(model, api_key)` for credential validation — never roll a custom completion call.
+- Do not hardcode provider env-key names or model lists that already exist in the codebase. Add a `test_model` field to each provider entry to drive `check_valid_key`; set it to `None` for providers that can't be validated with a single API key (Azure, Bedrock, Ollama).
+
 ### Enterprise Features
 - Enterprise-specific code in `enterprise/` directory
 - Optional features enabled via environment variables

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

@@ -5,11 +5,76 @@ import Image from '@theme/IdealImage';
 # Getting Started Tutorial
 
 End-to-End tutorial for LiteLLM Proxy to:
-- Add an Azure OpenAI model 
-- Make a successful /chat/completion call 
-- Generate a virtual key 
-- Set RPM limit on virtual key 
+- Add an Azure OpenAI model
+- Make a successful /chat/completion call
+- Generate a virtual key
+- Set RPM limit on virtual key
 
+## Quick Install (Recommended for local / beginners)
+
+New to LiteLLM? This is the easiest way to get started locally. One command installs LiteLLM and walks you through setup interactively — no config files to write by hand.
+
+### 1. Install
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/BerriAI/litellm/main/scripts/install.sh | sh
+```
+
+This detects your OS, installs `litellm[proxy]`, and drops you straight into the setup wizard.
+
+### 2. Follow the wizard
+
+```
+$ litellm --setup
+
+  Welcome to LiteLLM
+
+  Choose your LLM providers
+  ○ 1. OpenAI        GPT-4o, GPT-4o-mini, o1
+  ○ 2. Anthropic     Claude Opus, Sonnet, Haiku
+  ○ 3. Azure OpenAI  GPT-4o via Azure
+  ○ 4. Google Gemini Gemini 2.0 Flash, 1.5 Pro
+  ○ 5. AWS Bedrock   Claude, Llama via AWS
+  ○ 6. Ollama        Local models
+
+  ❯ Provider(s): 1,2
+
+  ❯ OpenAI API key: sk-...
+  ❯ Anthropic API key: sk-ant-...
+
+  ❯ Port [4000]:
+  ❯ Master key [auto-generate]:
+
+  ✔ Config saved → ./litellm_config.yaml
+
+  ❯ Start the proxy now? (Y/n):
+```
+
+The wizard walks you through:
+1. Pick your LLM providers (OpenAI, Anthropic, Azure, Bedrock, Gemini, Ollama)
+2. Enter API keys for each provider
+3. Set a port and master key (or accept the defaults)
+4. Config is saved to `./litellm_config.yaml` and the proxy starts immediately
+
+### 3. Make a call
+
+Your proxy is running on `http://0.0.0.0:4000`. Test it:
+
+```bash
+curl -X POST 'http://0.0.0.0:4000/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer <your-master-key>' \
+-d '{
+    "model": "gpt-4o",
+    "messages": [{"role": "user", "content": "Hello!"}]
+}'
+```
+
+:::tip Already have pip installed?
+You can skip the curl install and run `litellm --setup` directly after `pip install 'litellm[proxy]'`.
+:::
+
+---
 
 ## Pre-Requisites 
 

docs/my-website/sidebars.js

@@ -672,6 +672,7 @@ const sidebars = {
             "mcp_control",
             "mcp_cost",
             "mcp_guardrail",
+            "mcp_zero_trust",
             "mcp_troubleshoot",
           ]
         },

litellm/__init__.py

@@ -1465,9 +1465,15 @@ def set_global_gitlab_config(config: Dict[str, Any]) -> None:
     from .llms.petals.completion.transformation import PetalsConfig as PetalsConfig
     from .llms.ollama.chat.transformation import OllamaChatConfig as OllamaChatConfig
     from .llms.ollama.completion.transformation import OllamaConfig as OllamaConfig
-    from .llms.sagemaker.completion.transformation import SagemakerConfig as SagemakerConfig
-    from .llms.sagemaker.chat.transformation import SagemakerChatConfig as SagemakerChatConfig
-    from .llms.sagemaker.nova.transformation import SagemakerNovaConfig as SagemakerNovaConfig
+    from .llms.sagemaker.completion.transformation import (
+        SagemakerConfig as SagemakerConfig,
+    )
+    from .llms.sagemaker.chat.transformation import (
+        SagemakerChatConfig as SagemakerChatConfig,
+    )
+    from .llms.sagemaker.nova.transformation import (
+        SagemakerNovaConfig as SagemakerNovaConfig,
+    )
     from .llms.cohere.chat.transformation import CohereChatConfig as CohereChatConfig
     from .llms.anthropic.experimental_pass_through.messages.transformation import (
         AnthropicMessagesConfig as AnthropicMessagesConfig,

litellm/_logging.py

@@ -17,7 +17,9 @@
         "`litellm.set_verbose` is deprecated. Please set `os.environ['LITELLM_LOG'] = 'DEBUG'` for debug logs."
     )
 
-_ENABLE_SECRET_REDACTION = os.getenv("LITELLM_DISABLE_REDACT_SECRETS", "").lower() != "true"
+_ENABLE_SECRET_REDACTION = (
+    os.getenv("LITELLM_DISABLE_REDACT_SECRETS", "").lower() != "true"
+)
 
 _REDACTED = "REDACTED"
 
@@ -199,7 +201,9 @@ def format(self, record):
                 json_record[key] = value
 
         if record.exc_info:
-            json_record["stacktrace"] = record.exc_text or self.formatException(record.exc_info)
+            json_record["stacktrace"] = record.exc_text or self.formatException(
+                record.exc_info
+            )
 
         return safe_dumps(json_record)
 

litellm/cost_calculator.py

@@ -1189,7 +1189,9 @@ def completion_cost(  # noqa: PLR0915
                         and _usage["prompt_tokens_details"] != {}
                         and _usage["prompt_tokens_details"]
                     ):
-                        prompt_tokens_details = _usage.get("prompt_tokens_details") or {}
+                        prompt_tokens_details = (
+                            _usage.get("prompt_tokens_details") or {}
+                        )
                         cache_read_input_tokens = prompt_tokens_details.get(
                             "cached_tokens", 0
                         )
@@ -1515,7 +1517,9 @@ def completion_cost(  # noqa: PLR0915
                 if custom_llm_provider == "azure_ai":
                     model_for_additional_costs = request_model_for_cost
                     if completion_response is not None:
-                        hidden_params = getattr(completion_response, "_hidden_params", None) or {}
+                        hidden_params = (
+                            getattr(completion_response, "_hidden_params", None) or {}
+                        )
                         hidden_model = hidden_params.get("model") or hidden_params.get(
                             "litellm_model_name"
                         )

litellm/integrations/focus/destinations/factory.py

@@ -59,17 +59,14 @@ def _resolve_config(
             return {k: v for k, v in resolved.items() if v is not None}
         if provider == "vantage":
             resolved = {
-                "api_key": overrides.get("api_key")
-                or os.getenv("VANTAGE_API_KEY"),
+                "api_key": overrides.get("api_key") or os.getenv("VANTAGE_API_KEY"),
                 "integration_token": overrides.get("integration_token")
                 or os.getenv("VANTAGE_INTEGRATION_TOKEN"),
                 "base_url": overrides.get("base_url")
                 or os.getenv("VANTAGE_BASE_URL", "https://api.vantage.sh"),
             }
             if not resolved.get("api_key"):
-                raise ValueError(
-                    "VANTAGE_API_KEY must be provided for Vantage exports"
-                )
+                raise ValueError("VANTAGE_API_KEY must be provided for Vantage exports")
             if not resolved.get("integration_token"):
                 raise ValueError(
                     "VANTAGE_INTEGRATION_TOKEN must be provided for Vantage exports"

litellm/integrations/langfuse/langfuse_prompt_management.py

@@ -340,9 +340,9 @@ async def async_log_failure_event(self, kwargs, response_obj, start_time, end_ti
             )
             status_message = str(kwargs.get("exception", "Unknown error"))
             if standard_logging_object is not None:
-                status_message = standard_logging_object.get(
-                    "error_str", None
-                ) or status_message
+                status_message = (
+                    standard_logging_object.get("error_str", None) or status_message
+                )
             langfuse_logger_to_use.log_event_on_langfuse(
                 start_time=start_time,
                 end_time=end_time,

litellm/integrations/vantage/vantage_logger.py

@@ -83,7 +83,9 @@ def __init__(
 
         verbose_logger.debug(
             "VantageLogger initialized (integration_token=%s)",
-            resolved_token[:4] + "***" if resolved_token and len(resolved_token) > 4 else "***",
+            resolved_token[:4] + "***"
+            if resolved_token and len(resolved_token) > 4
+            else "***",
         )
 
     async def initialize_focus_export_job(self) -> None:
@@ -128,9 +130,7 @@ async def init_vantage_background_job(
             callback_type=VantageLogger
         )
         if not vantage_loggers:
-            verbose_logger.debug(
-                "No Vantage logger registered; skipping scheduler"
-            )
+            verbose_logger.debug("No Vantage logger registered; skipping scheduler")
             return
 
         vantage_logger = cast(VantageLogger, vantage_loggers[0])

litellm/litellm_core_utils/default_encoding.py

@@ -26,7 +26,9 @@
 else:
     cache_dir = filename
 
-os.environ["TIKTOKEN_CACHE_DIR"] = cache_dir  # use local copy of tiktoken b/c of - https://github.com/BerriAI/litellm/issues/1071
+os.environ[
+    "TIKTOKEN_CACHE_DIR"
+] = cache_dir  # use local copy of tiktoken b/c of - https://github.com/BerriAI/litellm/issues/1071
 
 import tiktoken
 import time
@@ -48,4 +50,3 @@
         # Exponential backoff with jitter to reduce collision probability
         delay = _retry_delay * (2**attempt) + random.uniform(0, 0.1)
         time.sleep(delay)
-