> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ag2.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# autogen.agentchat.contrib.capabilities.transforms.MessageTokenLimiter

<h2 id="autogen.agentchat.contrib.capabilities.transforms.MessageTokenLimiter" class="doc doc-heading">
  <code class="doc-symbol doc-symbol-heading doc-symbol-class" />

  <span class="doc doc-object-name doc-class-name">MessageTokenLimiter</span>
</h2>

```python theme={null}
MessageTokenLimiter(
    max_tokens_per_message: int | None = None,
    max_tokens: int | None = None,
    min_tokens: int | None = None,
    model: str = 'gpt-3.5-turbo-0613',
    filter_dict: dict[str, Any] | None = None,
    exclude_filter: bool = True
)
```

Truncates messages to meet token limits for efficient processing and response generation.<br />This transformation applies two levels of truncation to the conversation history: <br />1. Truncates each individual message to the maximum number of tokens specified by max\_tokens\_per\_message.<br />2. Truncates the overall conversation history to the maximum number of tokens specified by max\_tokens.<br />NOTE: Tokens are counted using the encoder for the specified model. Different models may yield different token
counts for the same text.<br />NOTE: For multimodal LLMs, the token count may be inaccurate as it does not account for the non-text input
(e.g images).<br />The truncation process follows these steps in order: <br />1. The minimum tokens threshold (`min_tokens`) is checked (0 by default). If the total number of tokens in messages
is less than this threshold, then the messages are returned as is. In other case, the following process is applied.<br />2. Messages are processed in reverse order (newest to oldest).<br />3. Individual messages are truncated based on max\_tokens\_per\_message. For multimodal messages containing both text
and other types of content, only the text content is truncated.<br />4. The overall conversation history is truncated based on the max\_tokens limit. Once the accumulated token count
exceeds this limit, the current message being processed get truncated to meet the total token count and any
remaining messages get discarded.<br />5. The truncated conversation history is reconstructed by prepending the messages to a new list to preserve the
original message order.<br />

<b>Parameters:</b>

| Name                     | Description                                                           |
| ------------------------ | --------------------------------------------------------------------- |
| `max_tokens_per_message` | **Type:** int \| None<br /><br />**Default:** None                    |
| `max_tokens`             | **Type:** int \| None<br /><br />**Default:** None                    |
| `min_tokens`             | **Type:** int \| None<br /><br />**Default:** None                    |
| `model`                  | **Type:** str<br /><br />**Default:** 'gpt-3.5-turbo-0613'            |
| `filter_dict`            | **Type:** dict\[str, typing.Any] \| None<br /><br />**Default:** None |
| `exclude_filter`         | **Type:** bool<br /><br />**Default:** True                           |

### Instance Methods

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### apply\_transform

```python theme={null}
apply_transform(self, messages: list[dict[str, Any]]) -> list[dict[str, Any]]
```

Applies token truncation to the conversation history.<br />

<b>Parameters:</b>

| Name       | Description                                                                                                    |
| ---------- | -------------------------------------------------------------------------------------------------------------- |
| `messages` | The list of messages representing the conversation history.<br /><br />**Type:** list\[dict\[str, typing.Any]] |

<b>Returns:</b>

| Type                          | Description                                                                                 |
| ----------------------------- | ------------------------------------------------------------------------------------------- |
| list\[dict\[str, typing.Any]] | List\[Dict]: A new list containing the truncated messages up to the specified token limits. |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### get\_logs

```python theme={null}
get_logs(
    self,
    pre_transform_messages: list[dict[str, Any]],
    post_transform_messages: list[dict[str, Any]]
) -> tuple[str, bool]
```

<b>Parameters:</b>

| Name                      | Description                             |
| ------------------------- | --------------------------------------- |
| `pre_transform_messages`  | **Type:** list\[dict\[str, typing.Any]] |
| `post_transform_messages` | **Type:** list\[dict\[str, typing.Any]] |

<br />