Module session

Structs§

CompactResult: Result of a manual compaction operation. Used by force_compact() to report what happened during compaction.
CompactionConfig: Configuration for conversation compaction
CompactionResult: Result of a compaction operation.
LLMCompactor: LLM-based compactor that summarizes older conversation using an LLM. It replaces older messages with a single summary message while preserving recent turns.
LLMCompactorConfig: Configuration for LLM-based conversation compaction.
LLMSession: A session that manages communication with an LLM
LLMSessionConfig: Configuration for creating an LLM session
LLMSessionManager: Manages multiple LLM sessions
SessionStatus: Current status of an LLM session
ThresholdCompactor: Compacts when context usage exceeds a threshold. It identifies turns to keep (most recent N) and applies the configured compaction strategy to older tool results.
TokenUsage: Token usage statistics for the session

AsyncCompactor: Trait for async compaction strategies that require LLM calls. Implementors must also implement Compactor with is_async() -> true.
Compactor: Trait for conversation compaction strategies. Implementations decide when and how to compact conversation history to reduce token usage while preserving important context.