_find_safe_cutoff() — langchain Function Reference

Architecture documentation for the _find_safe_cutoff() function in summarization.py from the langchain codebase.

Function python LangChainCore MessageInterface calls 1 called by 1

Entity Profile

LangChainCore→ MessageInterface→ _find_safe_cutoff() — langchain Function Reference

Dependency Diagram

graph TD
  d7f278f1_55ee_3351_0744_37d80b5a183d["_find_safe_cutoff()"]
  a622f56b_f697_966d_5bc7_095699ccca34["SummarizationMiddleware"]
  d7f278f1_55ee_3351_0744_37d80b5a183d -->|defined in| a622f56b_f697_966d_5bc7_095699ccca34
  1de03e59_b58a_edd7_ef83_95d7ab3cd1da["_determine_cutoff_index()"]
  1de03e59_b58a_edd7_ef83_95d7ab3cd1da -->|calls| d7f278f1_55ee_3351_0744_37d80b5a183d
  6bd2bf47_a4ef_fe6f_a2a2_89f8125a4eaa["_find_safe_cutoff_point()"]
  d7f278f1_55ee_3351_0744_37d80b5a183d -->|calls| 6bd2bf47_a4ef_fe6f_a2a2_89f8125a4eaa
  style d7f278f1_55ee_3351_0744_37d80b5a183d fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain_v1/langchain/agents/middleware/summarization.py lines 537–550

    def _find_safe_cutoff(self, messages: list[AnyMessage], messages_to_keep: int) -> int:
        """Find safe cutoff point that preserves AI/Tool message pairs.

        Returns the index where messages can be safely cut without separating
        related AI and Tool messages. Returns `0` if no safe cutoff is found.

        This is aggressive with summarization - if the target cutoff lands in the
        middle of tool messages, we advance past all of them (summarizing more).
        """
        if len(messages) <= messages_to_keep:
            return 0

        target_cutoff = len(messages) - messages_to_keep
        return self._find_safe_cutoff_point(messages, target_cutoff)