Context Strategies

Manage conversation context across node transitions.

Flows provides three built-in ways to manage conversation context as you move between nodes.

Strategy Types

1. APPEND (Default): New node messages are added to the existing context, preserving the full conversation history. The context grows as the conversation progresses.

2. RESET: The context is cleared and replaced with only the new node’s messages. Useful when previous conversation history is no longer relevant or to reduce context window size.

3. RESET_WITH_SUMMARY: The context is cleared but includes an AI-generated summary of the previous conversation along with the new node’s messages. Helps reduce context size while preserving key information.

RESET_WITH_SUMMARY is deprecated and will be removed in 2.0. Use Pipecat’s native LLMSummarizeContextFrame instead. To trigger on-demand summarization during a node transition, push an LLMSummarizeContextFrame in a pre-action.

Initial node behavior: The initial flow node follows its context strategy (default APPEND) instead of always replacing the context. With the default strategy, context written before the node’s first inference — for example by a tts_say pre-action — is now preserved rather than discarded. Set context_strategy=RESET on the initial node for the previous clean-slate behavior.

When to Use Each Strategy

• Use APPEND when full conversation history is important for context
• Use RESET when starting a new topic or when previous context might confuse the current task
• Use RESET_WITH_SUMMARY (deprecated) for long conversations where you need to preserve key points but reduce context size. Prefer Pipecat’s native context summarization for new code.

Configuration

Context strategies can be defined globally in the FlowManager constructor:

from pipecat_flows import ContextStrategy, ContextStrategyConfig

# Global strategy configuration
flow_manager = FlowManager(
    task=task,
    llm=llm,
    context_aggregator=context_aggregator,
    context_strategy=ContextStrategyConfig(
        strategy=ContextStrategy.APPEND,
    )
)

Or on a per-node basis:

# Per-node strategy configuration
node_config = {
    "task_messages": [...],
    "functions": [...],
    "context_strategy": ContextStrategyConfig(
        strategy=ContextStrategy.RESET_WITH_SUMMARY,
        summary_prompt="Provide a concise summary of the customer's order details and preferences."
    )
}