> ## Documentation Index
> Fetch the complete documentation index at: https://docs.portkey.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Anthropic transform

# Parameter Mappings & Transformations

## Basic Parameter Mappings

* `model` → direct mapping (default: 'claude-2.1')
* `max_tokens` → direct mapping to `max_tokens`
* `temperature` → direct mapping (constrained: 0-1)
* `top_p` → direct mapping (default: -1)
* `stream` → direct mapping (default: false)
* `user` → mapped to `metadata.user_id`
* `stop` → mapped to `stop_sequences`
* `max_completion_tokens` → mapped to `max_tokens`

## Anthropic Sampling + Token Rules

* For Anthropic models (across providers), `temperature` and `top_p` are direct mappings when sent individually.
* If both `temperature` and `top_p` are sent together, Portkey keeps `temperature` and drops `top_p`.

## Complex Transformations

### Messages Transformation

1. System Messages:
   * Extracted from messages array where `role === 'system'`
   * Transformed into `AnthropicMessageContentItem[]`
   * Handles both string content and object content with text
   * Preserves cache control metadata if present

2. Assistant Messages (`transformAssistantMessage`):
   * Transforms content into Anthropic's content array format
   * Handles tool calls by converting them into Anthropic's tool\_use format
   * Text content is wrapped in `{type: 'text', text: content}`
   * Tool calls are transformed into `{type: 'tool_use', name: function.name, id: toolCall.id, input: parsed_arguments}`

3. Tool Messages (`transformToolMessage`):
   * Converted to user role with tool\_result type
   * Preserves tool\_call\_id as tool\_use\_id
   * Content wrapped in specific format: `{type: 'tool_result', tool_use_id: id, content: string}`

4. User Messages with Images:
   * Handles base64 encoded images in content
   * Transforms them into Anthropic's image format with proper media type
   * Preserves cache control metadata

### Tools Transformation

* Converts OpenAI-style function definitions to Anthropic tool format
* Maps function parameters to input\_schema
* Preserves cache control metadata
* Structure transformation:
  ```typescript theme={"system"}
  OpenAI: {function: {name, description, parameters}}
  ↓
  Anthropic: {name, description, input_schema: {type, properties, required}}
  ```

### Tool Choice Transformation

* 'required' → `{type: 'any'}`
* 'auto' → `{type: 'auto'}`
* Function specification → `{type: 'tool', name: function.name}`

# Response Transformations

## Regular Response

1. Content Processing:
   * Extracts text content from first content item if type is 'text'
   * Processes tool\_use items into OpenAI tool\_calls format
   * Preserves tool IDs and function names

2. Usage Statistics:
   * Maps input\_tokens → prompt\_tokens
   * Maps output\_tokens → completion\_tokens
   * Calculates total\_tokens
   * Preserves cache-related tokens if present

## Streaming Response

1. Event Handling:
   * Filters out 'ping' and 'content\_block\_stop' events
   * Converts 'message\_stop' to '\[DONE]'
   * Handles multiple event types: content\_block\_delta, content\_block\_start, message\_delta, message\_start

2. Special States:
   * Tracks chain of thought messages
   * Maintains usage statistics across stream
   * Handles tool streaming differently based on message context

# Edge Cases & Special Handling

1. Image Content:
   * Special handling for base64 encoded images
   * Parses media type from data URL
   * Validates image URL format

2. Tool Streaming:
   * Handles partial JSON in tool arguments
   * Manages tool indices differently when chain-of-thought messages are present
   * Separates tool name and arguments into different stream chunks

3. Cache Control:
   * Preserves ephemeral cache control metadata throughout transformations
   * Handles cache usage statistics in both regular and streaming responses

4. Error Handling:
   * Transforms Anthropic-specific error format to universal format
   * Preserves error types and messages
   * Handles non-200 response status codes

5. Empty/Null Handling:
   * Safely handles missing usage statistics
   * Manages undefined tool calls
   * Handles empty content arrays