All Implemented Interfaces:
```
public final class RealtimeTruncation

                    
```
When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit.

Nested Class Summary

Nested Classes
Modifier and Type	Class	Description
`public interface`	`RealtimeTruncation.Visitor`	An interface that defines how to map each variant of RealtimeTruncation to a value of type T.
`public final class`	`RealtimeTruncation.RealtimeTruncationStrategy`	The truncation strategy to use for the session. `auto` is the default truncation strategy. `disabled` will disable truncation and emit errors when the conversation exceeds the input token limit.

Field Summary

Fields
Modifier and Type	Field	Description

Constructor Summary

Constructors
Constructor	Description

Enum Constant Summary

Enum Constants
Enum Constant	Description

Method Summary

Modifier and Type	Method	Description
`final Optional<RealtimeTruncation.RealtimeTruncationStrategy>`	`strategy()`	The truncation strategy to use for the session.
`final Optional<RealtimeTruncationRetentionRatio>`	`retentionRatio()`	Retain a fraction of the conversation tokens when the conversation exceeds the input token limit.
`final Boolean`	`isStrategy()`
`final Boolean`	`isRetentionRatio()`
`final RealtimeTruncation.RealtimeTruncationStrategy`	`asStrategy()`	The truncation strategy to use for the session.
`final RealtimeTruncationRetentionRatio`	`asRetentionRatio()`	Retain a fraction of the conversation tokens when the conversation exceeds the input token limit.
`final Optional<JsonValue>`	`_json()`
`final <T extends Any> T`	`accept(RealtimeTruncation.Visitor<T> visitor)`
`final RealtimeTruncation`	`validate()`
`final Boolean`	`isValid()`
`Boolean`	`equals(Object other)`
`Integer`	`hashCode()`
`String`	`toString()`
`final static RealtimeTruncation`	`ofStrategy(RealtimeTruncation.RealtimeTruncationStrategy strategy)`	The truncation strategy to use for the session.
`final static RealtimeTruncation`	`ofRetentionRatio(RealtimeTruncationRetentionRatio retentionRatio)`	Retain a fraction of the conversation tokens when the conversation exceeds the input token limit.

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Constructor Detail
- Method Detail
  - strategy
```
 final Optional<RealtimeTruncation.RealtimeTruncationStrategy> strategy()
```
    The truncation strategy to use for the session. auto is the default truncation strategy. disabled will disable truncation and emit errors when the conversation exceeds the input token limit.
  - retentionRatio
```
 final Optional<RealtimeTruncationRetentionRatio> retentionRatio()
```
    Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage.
  - isStrategy
```
 final Boolean isStrategy()
```
  - isRetentionRatio
```
 final Boolean isRetentionRatio()
```
  - asStrategy
```
 final RealtimeTruncation.RealtimeTruncationStrategy asStrategy()
```
    The truncation strategy to use for the session. auto is the default truncation strategy. disabled will disable truncation and emit errors when the conversation exceeds the input token limit.
  - asRetentionRatio
```
 final RealtimeTruncationRetentionRatio asRetentionRatio()
```
    Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage.
  - _json
```
 final Optional<JsonValue> _json()
```
  - accept
```
 final <T extends Any> T accept(RealtimeTruncation.Visitor<T> visitor)
```
  - validate
```
 final RealtimeTruncation validate()
```
  - isValid
```
 final Boolean isValid()
```
  - equals
```
 Boolean equals(Object other)
```
  - hashCode
```
 Integer hashCode()
```
  - toString
```
 String toString()
```
  - ofStrategy
```
 final static RealtimeTruncation ofStrategy(RealtimeTruncation.RealtimeTruncationStrategy strategy)
```
    The truncation strategy to use for the session. auto is the default truncation strategy. disabled will disable truncation and emit errors when the conversation exceeds the input token limit.
  - ofRetentionRatio
```
 final static RealtimeTruncation ofRetentionRatio(RealtimeTruncationRetentionRatio retentionRatio)
```
    Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage.

Class RealtimeTruncation

Nested Class Summary

Field Summary

Constructor Summary

Enum Constant Summary

Method Summary

Methods inherited from class java.lang.Object

Constructor Detail

Method Detail

strategy

retentionRatio

isStrategy

isRetentionRatio

asStrategy

asRetentionRatio

_json

accept

validate

isValid

equals

hashCode

toString

ofStrategy

ofRetentionRatio