Merge: Fix recurrent merge conflic

Author: AlexsanderHamir

.circleci/config.yml

@@ -532,7 +532,7 @@ jobs:
           command: |
             pwd
             ls
-            python -m pytest -vv tests/router_unit_tests --cov=litellm --cov-report=xml -x -s -v --junitxml=test-results/junit.xml --durations=5
+            python -m pytest -vv tests/router_unit_tests --cov=litellm --cov-report=xml -x -s --junitxml=test-results/junit.xml --durations=5
           no_output_timeout: 120m
       - run:
           name: Rename the coverage files
@@ -1164,7 +1164,7 @@ jobs:
           command: |
             pwd
             ls
-            python -m pytest -vv tests/test_litellm --cov=litellm --cov-report=xml -s -v --junitxml=test-results/junit-litellm.xml --durations=10 -n 8
+            python -m pytest -vv tests/test_litellm --cov=litellm --cov-report=xml -v --junitxml=test-results/junit-litellm.xml --durations=10 -n 8
           no_output_timeout: 120m
       - run:
           name: Rename the coverage files
@@ -1396,7 +1396,7 @@ jobs:
           command: |
             pwd
             ls
-            python -m pytest -vv tests/image_gen_tests --cov=litellm --cov-report=xml -x -s -v --junitxml=test-results/junit.xml --durations=5
+            python -m pytest -vv tests/image_gen_tests --cov=litellm --cov-report=xml -x -v --junitxml=test-results/junit.xml --durations=5
           no_output_timeout: 120m
       - run:
           name: Rename the coverage files

docker/Dockerfile.dev

@@ -57,6 +57,9 @@ USER root
 # Install only runtime dependencies
 RUN apt-get update && apt-get install -y --no-install-recommends \
     libssl3 \
+    libatomic1 \
+    nodejs \
+    npm \
     && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app

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

@@ -15,16 +15,22 @@ Supported Providers:
 - Google AI Studio (`gemini`)
 - Vertex AI (`vertex_ai/`)
 
-LiteLLM will standardize the `image` response in the assistant message for models that support image generation during chat completions.
+LiteLLM will standardize the `images` response in the assistant message for models that support image generation during chat completions.
 
 ```python title="Example response from litellm"
 "message": {
     ...
     "content": "Here's the image you requested:",
-    "image": {
-        "url": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...",
-        "detail": "auto"
-    }
+    "images": [
+        {
+            "image_url": {
+                "url": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...",
+                "detail": "auto"
+            },
+            "index": 0,
+            "type": "image_url"
+        }
+    ]
 }
 ```
 
@@ -47,7 +53,7 @@ response = completion(
 )
 
 print(response.choices[0].message.content)  # Text response
-print(response.choices[0].message.image)    # Image data
+print(response.choices[0].message.images)   # List of image objects
 ```
 
 </TabItem>
@@ -103,10 +109,16 @@ curl http://0.0.0.0:4000/v1/chat/completions \
             "message": {
                 "content": "Here's the image you requested:",
                 "role": "assistant",
-                "image": {
-                    "url": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...",
-                    "detail": "auto"
-                }
+                "images": [
+                    {
+                        "image_url": {
+                            "url": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...",
+                            "detail": "auto"
+                        },
+                        "index": 0,
+                        "type": "image_url"
+                    }
+                ]
             }
         }
     ],
@@ -141,8 +153,8 @@ response = completion(
 )
 
 for chunk in response:
-    if hasattr(chunk.choices[0].delta, "image") and chunk.choices[0].delta.image is not None:
-        print("Generated image:", chunk.choices[0].delta.image["url"])
+    if hasattr(chunk.choices[0].delta, "images") and chunk.choices[0].delta.images is not None:
+        print("Generated image:", chunk.choices[0].delta.images[0]["image_url"]["url"])
         break
 ```
 
@@ -175,7 +187,7 @@ data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1723323084
 
 data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1723323084,"model":"gemini/gemini-2.5-flash-image-preview","choices":[{"index":0,"delta":{"content":"Here's the image you requested:"},"finish_reason":null}]}
 
-data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1723323084,"model":"gemini/gemini-2.5-flash-image-preview","choices":[{"index":0,"delta":{"image":{"url":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...","detail":"auto"}},"finish_reason":null}]}
+data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1723323084,"model":"gemini/gemini-2.5-flash-image-preview","choices":[{"index":0,"delta":{"images":[{"image_url":{"url":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...","detail":"auto"},"index":0,"type":"image_url"}]},"finish_reason":null}]}
 
 data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1723323084,"model":"gemini/gemini-2.5-flash-image-preview","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
 
@@ -200,8 +212,8 @@ async def generate_image():
     )
 
     print(response.choices[0].message.content)  # Text response
-    print(response.choices[0].message.image)    # Image data
-    
+    print(response.choices[0].message.images)   # List of image objects
+
     return response
 
 # Run the async function
@@ -215,18 +227,28 @@ asyncio.run(generate_image())
 | Google AI Studio | `gemini/gemini-2.5-flash-image-preview` |
 | Vertex AI | `vertex_ai/gemini-2.5-flash-image-preview` |
 
-## Spec 
+## Spec
 
-The `image` field in the response follows this structure:
+The `images` field in the response follows this structure:
 
 ```python
-"image": {
-    "url": "data:image/png;base64,<base64_encoded_image>",
-    "detail": "auto"
-}
+"images": [
+    {
+        "image_url": {
+            "url": "data:image/png;base64,<base64_encoded_image>",
+            "detail": "auto"
+        },
+        "index": 0,
+        "type": "image_url"
+    }
+]
 ```
 
-- `url` - str: Base64 encoded image data in data URI format
-- `detail` - str: Image detail level (always "auto" for generated images)
+- `images` - List[ImageURLListItem]: Array of generated images
+  - `image_url` - ImageURLObject: Container for image data
+    - `url` - str: Base64 encoded image data in data URI format
+    - `detail` - str: Image detail level (always "auto" for generated images)
+  - `index` - int: Index of the image in the response
+  - `type` - str: Type identifier (always "image_url")
 
-The image is returned as a base64-encoded data URI that can be directly used in HTML `<img>` tags or saved to a file.
+The images are returned as base64-encoded data URIs that can be directly used in HTML `<img>` tags or saved to files.

docs/my-website/docs/exception_mapping.md

@@ -112,6 +112,85 @@ except openai.APITimeoutError as e:
     print(f"should_retry: {should_retry}")
 ```
 
+## Advanced
+
+### Accessing Provider-Specific Error Details
+
+LiteLLM exceptions include a `provider_specific_fields` attribute that contains additional error information specific to each provider. This is particularly useful for Azure OpenAI, which provides detailed content filtering information.
+
+#### Azure OpenAI - Content Policy Violation Inner Error Access
+
+When Azure OpenAI returns content policy violations, you can access the detailed content filtering results through the `innererror` field:
+
+```python
+import litellm
+from litellm.exceptions import ContentPolicyViolationError
+
+try:
+    response = litellm.completion(
+        model="azure/gpt-4",
+        messages=[
+            {
+                "role": "user", 
+                "content": "Some content that might violate policies"
+            }
+        ]
+    )
+except ContentPolicyViolationError as e:
+    # Access Azure-specific error details
+    if e.provider_specific_fields and "innererror" in e.provider_specific_fields:
+        innererror = e.provider_specific_fields["innererror"]
+        
+        # Access content filter results
+        content_filter_result = innererror.get("content_filter_result", {})
+        
+        print(f"Content filter code: {innererror.get('code')}")
+        print(f"Hate filtered: {content_filter_result.get('hate', {}).get('filtered')}")
+        print(f"Violence severity: {content_filter_result.get('violence', {}).get('severity')}")
+        print(f"Sexual content filtered: {content_filter_result.get('sexual', {}).get('filtered')}")
+```
+
+**Example Response Structure:**
+
+When calling the LiteLLM proxy, content policy violations will return detailed filtering information:
+
+```json
+{
+  "error": {
+    "message": "litellm.ContentPolicyViolationError: AzureException - The response was filtered due to the prompt triggering Azure OpenAI's content management policy...",
+    "type": null,
+    "param": null,
+    "code": "400",
+    "provider_specific_fields": {
+      "innererror": {
+        "code": "ResponsibleAIPolicyViolation",
+        "content_filter_result": {
+          "hate": {
+            "filtered": true,
+            "severity": "high"
+          },
+          "jailbreak": {
+            "filtered": false,
+            "detected": false
+          },
+          "self_harm": {
+            "filtered": false,
+            "severity": "safe"
+          },
+          "sexual": {
+            "filtered": false,
+            "severity": "safe"
+          },
+          "violence": {
+            "filtered": true,
+            "severity": "medium"
+          }
+        }
+      }
+    }
+  }
+}
+
 ## Details 
 
 To see how it's implemented - [check out the code](https://github.com/BerriAI/litellm/blob/a42c197e5a6de56ea576c73715e6c7c6b19fa249/litellm/utils.py#L1217)

docs/my-website/docs/moderation.md

@@ -22,10 +22,19 @@ response = moderation(
 
 For `/moderations` endpoint, there is **no need to specify `model` in the request or on the litellm config.yaml**
 
-Start litellm proxy server 
 
+1. Setup config.yaml
+```yaml
+model_list:
+  - model_name: text-moderation-stable
+    litellm_params:
+      model: openai/omni-moderation-latest
 ```
-litellm
+
+2. Start litellm proxy server 
+
+```
+litellm --config /path/to/config.yaml
 ```
 
 
@@ -41,7 +50,7 @@ client = OpenAI(api_key="<proxy-api-key>", base_url="http://0.0.0.0:4000")
 
 response = client.moderations.create(
     input="hello from litellm",
-    model="text-moderation-stable" # optional, defaults to `omni-moderation-latest`
+    model="text-moderation-stable"
 )
 
 print(response)

docs/my-website/docs/observability/datadog.md

@@ -56,12 +56,32 @@ litellm_settings:
 
 **Step 2**: Set Required env variables for datadog
 
+#### Direct API
+
+Send logs directly to Datadog API:
+
 ```shell
 DD_API_KEY="5f2d0f310***********" # your datadog API Key
 DD_SITE="us5.datadoghq.com"       # your datadog base url
 DD_SOURCE="litellm_dev"       # [OPTIONAL] your datadog source. use to differentiate dev vs. prod deployments
 ```
 
+#### Via DataDog Agent
+
+Send logs through a local DataDog agent (useful for containerized environments):
+
+```shell
+DD_AGENT_HOST="localhost"         # hostname or IP of DataDog agent
+DD_AGENT_PORT="10518"             # [OPTIONAL] port of DataDog agent (default: 10518)
+DD_API_KEY="5f2d0f310***********" # [OPTIONAL] your datadog API Key (agent handles auth)
+DD_SOURCE="litellm_dev"           # [OPTIONAL] your datadog source
+```
+
+When `DD_AGENT_HOST` is set, logs are sent to the agent instead of directly to DataDog API. This is useful for:
+- Centralized log shipping in containerized environments
+- Reducing direct API calls from multiple services
+- Leveraging agent-side processing and filtering
+
 **Step 3**: Start the proxy, make a test request
 
 Start proxy
@@ -169,12 +189,17 @@ LiteLLM supports customizing the following Datadog environment variables
 
 | Environment Variable | Description | Default Value | Required |
 |---------------------|-------------|---------------|----------|
-| `DD_API_KEY` | Your Datadog API key for authentication | None | ✅ Yes |
-| `DD_SITE` | Your Datadog site (e.g., "us5.datadoghq.com") | None | ✅ Yes |
+| `DD_API_KEY` | Your Datadog API key for authentication (required for direct API, optional for agent) | None | Conditional* |
+| `DD_SITE` | Your Datadog site (e.g., "us5.datadoghq.com") (required for direct API) | None | Conditional* |
+| `DD_AGENT_HOST` | Hostname or IP of DataDog agent (e.g., "localhost"). When set, logs are sent to agent instead of direct API | None | ❌ No |
+| `DD_AGENT_PORT` | Port of DataDog agent for log intake | "10518" | ❌ No |
 | `DD_ENV` | Environment tag for your logs (e.g., "production", "staging") | "unknown" | ❌ No |
 | `DD_SERVICE` | Service name for your logs | "litellm-server" | ❌ No |
 | `DD_SOURCE` | Source name for your logs | "litellm" | ❌ No |
 | `DD_VERSION` | Version tag for your logs | "unknown" | ❌ No |
 | `HOSTNAME` | Hostname tag for your logs | "" | ❌ No |
 | `POD_NAME` | Pod name tag (useful for Kubernetes deployments) | "unknown" | ❌ No |
 
+\* **Required when using Direct API** (default): `DD_API_KEY` and `DD_SITE` are required  
+\* **Optional when using DataDog Agent**: Set `DD_AGENT_HOST` to use agent mode; `DD_API_KEY` and `DD_SITE` are not required
+