Add Default usage data configuration

docs/my-website/docs/completion/usage.md

@@ -50,3 +50,51 @@ for chunk in completion:
   print(chunk.choices[0].delta)
 
 ```
+
+### Proxy: Always Include Streaming Usage
+
+When using the LiteLLM Proxy, you can configure it to automatically include usage information in all streaming responses, even if the client doesn't send `stream_options={"include_usage": True}`.
+
+#### Configuration
+
+Add the following to your config.yaml:
+
+```yaml
+general_settings:
+  always_include_stream_usage: true
+```
+
+Alternatively, configure it through the UI:
+
+1. Navigate to the LiteLLM Proxy UI
+2. Go to `Settings` >  `Router Settings` > `General`
+3. Find the `always_include_stream_usage` setting
+4. Toggle it to `true`
+5. Click `Update` to save
+
+#### How it works
+
+When `always_include_stream_usage` is enabled:
+- All streaming requests will automatically have `stream_options={"include_usage": True}` added
+- Clients will receive usage information in the final chunk, even if they didn't explicitly request it
+- If a client already provides `stream_options`, `include_usage: True` will be added without overwriting other options
+- Non-streaming requests are not affected
+
+#### Example
+
+With this setting enabled, a simple streaming request like:
+
+```bash
+curl -X POST http://localhost:4000/v1/chat/completions \
+  -H "Authorization: Bearer sk-1234" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gpt-4o",
+    "messages": [{"role": "user", "content": "Hello!"}],
+    "stream": true
+  }'
+```
+
+Will automatically receive usage information in the response, without needing to explicitly include `stream_options`.
+
+```

litellm/proxy/_types.py

@@ -1909,6 +1909,10 @@ class PassThroughGenericEndpoint(LiteLLMPydanticObjectBase):
         default={},
         description="Key-value pairs of headers to be forwarded with the request. You can set any key value pair here and it will be forwarded to your target endpoint",
     )
+    default_query_params: dict = Field(
+        default={},
+        description="Key-value pairs of default query parameters to be sent with every request to this endpoint. These can be overridden by client-provided query parameters. For example: {'key': 'default_value', 'api_version': '2023-01'}",
+    )
     include_subpath: bool = Field(
         default=False,
         description="If True, requests to subpaths of the path will be forwarded to the target endpoint. For example, if the path is /bria and include_subpath is True, requests to /bria/v1/text-to-image/base/2.3 will be forwarded to the target endpoint.",
@@ -1929,6 +1933,10 @@ class PassThroughGenericEndpoint(LiteLLMPydanticObjectBase):
         default=False,
         description="True if this endpoint is defined in the config file, False if from DB. Config-defined endpoints cannot be edited via the UI.",
     )
+    methods: Optional[List[str]] = Field(
+        default=None,
+        description="List of HTTP methods this endpoint handles (e.g., ['GET', 'POST']). If None or empty, all methods (GET, POST, PUT, DELETE, PATCH) are supported for backward compatibility. This allows the same path to have different targets for different HTTP methods.",
+    )
 
 
 class PassThroughEndpointResponse(LiteLLMPydanticObjectBase):

litellm/proxy/common_request_processing.py

@@ -619,6 +619,23 @@ class ProxyBaseLLMRequestProcessing:
         self.data["litellm_call_id"] = request.headers.get(
             "x-litellm-call-id", str(uuid.uuid4())
         )
+        
+        ### AUTO STREAM USAGE TRACKING ###
+        # If always_include_stream_usage is enabled and this is a streaming request
+        # automatically add stream_options={'include_usage': True} if not already set
+        if (
+            general_settings.get("always_include_stream_usage", False) is True
+            and self.data.get("stream", False) is True
+        ):
+            # Only set if stream_options is not already provided by the client
+            if "stream_options" not in self.data:
+                self.data["stream_options"] = {"include_usage": True}
+            elif (
+                isinstance(self.data["stream_options"], dict)
+                and "include_usage" not in self.data["stream_options"]
+            ):
+                self.data["stream_options"]["include_usage"] = True
+        
         ### CALL HOOKS ### - modify/reject incoming data before calling the model
 
         ## LOGGING OBJECT ## - initialize logging object for logging success/failure events for call

litellm/proxy/proxy_server.py

@@ -11361,6 +11361,7 @@ async def get_config_list(
         "maximum_spend_logs_retention_period": {"type": "String"},
         "mcp_internal_ip_ranges": {"type": "List"},
         "mcp_trusted_proxy_ranges": {"type": "List"},
+        "always_include_stream_usage": {"type": "Boolean"},
     }
 
     return_val = []

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

@@ -11,6 +11,7 @@ import {
   Text,
   Button,
   Icon,
+  Switch,
 } from "@tremor/react";
 import { TabPanel, TabPanels, TabGroup, TabList, Tab } from "@tremor/react";
 import {
@@ -163,7 +164,12 @@ const GeneralSettings: React.FC<GeneralSettingsPageProps> = ({ accessToken, user
                             <InputNumber
                               step={1}
                               value={value.field_value}
-                              onChange={(newValue) => handleInputChange(value.field_name, newValue)} // Handle value change
+                              onChange={(newValue) => handleInputChange(value.field_name, newValue)}
+                            />
+                          ) : value.field_type == "Boolean" ? (
+                            <Switch
+                              checked={value.field_value === true || value.field_value === "true"}
+                              onChange={(checked) => handleInputChange(value.field_name, checked)}
                             />
                           ) : null}
                         </TableCell>