pyrit.executor.attack.MultiTurnAttackContext

class MultiTurnAttackContext(params: AttackParamsT, start_time: float = 0.0, related_conversations: set[ConversationReference] = <factory>, _next_message_override: Optional[Message] = None, _prepended_conversation_override: Optional[List[Message]] = None, _memory_labels_override: Optional[Dict[str, str]] = None, session: ConversationSession = <factory>, executed_turns: int = 0, last_response: Optional[Message] = None, last_score: Optional[Score] = None)

Bases: AttackContext[AttackParamsT]

Context for multi-turn attacks.

Holds execution state for multi-turn attacks. The immutable attack parameters (objective, next_message, prepended_conversation, memory_labels) are stored in the params field inherited from AttackContext.

__init__(params: AttackParamsT, start_time: float = 0.0, related_conversations: set[ConversationReference] = <factory>, _next_message_override: Optional[Message] = None, _prepended_conversation_override: Optional[List[Message]] = None, _memory_labels_override: Optional[Dict[str, str]] = None, session: ConversationSession = <factory>, executed_turns: int = 0, last_response: Optional[Message] = None, last_score: Optional[Score] = None) → None

Methods

__init__(params[, start_time, ...])
duplicate()	Create a deep copy of the context.

Attributes

executed_turns
last_response
last_score
memory_labels	Additional labels that can be applied to the prompts throughout the attack.
next_message	Optional message to send to the objective target.
objective	Natural-language description of what the attack tries to achieve.
prepended_conversation	Conversation that is automatically prepended to the target model.
start_time
session
params
related_conversations

executed_turns: int = 0

last_response: Message | None = None

last_score: Score | None = None

session: ConversationSession