Back to Signal Feed
CodeTracked since May 20, 2026

Gate tool-pair summarization to context windows of 64K or less

PR #9152 changes Goose so tool-pair summarization is skipped when context grows beyond 64K tokens, while leaving small-context behavior unchanged; users can still fully disable it with GOOSE_TOOL_PAIR_SUMMARIZATION=false.

tool-pair summarizationcontext window64K tokensGOOSE_TOOL_PAIR_SUMMARIZATION

What Happened

  • PR #9152 changes Goose so tool-pair summarization is skipped when context grows beyond 64K tokens, while leaving small-context behavior unchanged; users can still fully disable it with GOOSE_TOOL_PAIR_SUMMARIZATION=false.
  • PR #9152 changes Goose so tool-pair summarization is skipped when context grows beyond 64K tokens, while leaving small-context behavior unchanged; users can still fully disable it with GOOSE_TOOL_PAIR_SUMMARIZATION=false.
  • 1 evidence item attached for review.

What is Different

Before

Scattered source updates, isolated context, and manual follow-up across multiple feeds.

Now

Added a context-length guard around the tool-pair summarization path so it runs only within 64K-context sessions, preventing the known long-session degradation while preserving short-context behavior and an explicit opt-out flag.

Why Track This

Why It Matters

Operators of Goose in long sessions with many tool calls should see fewer harmful long-run behaviors because summarization is no longer applied unconditionally at high context lengths, reducing the chance of session quality drops. Technical follow-up: the cutoff is now fixed at 64K tokens, so teams should monitor whether this threshold is too strict for some workloads and verify the disable flag consistently applies in all deployment environments.

Impact

Operators of Goose in long sessions with many tool calls should see fewer harmful long-run behaviors because summarization is no longer applied unconditionally at high context lengths, reducing the chance of session quality drops. Technical follow-up: the cutoff is now fixed at 64K tokens, so teams should monitor whether this threshold is too strict for some workloads and verify the disable flag consistently applies in all deployment environments.

What To Watch Next

  • Watch whether tool-pair summarization becomes a repeated pattern.
  • Track follow-up changes around Tool Calling.
  • Compare future signals against this evidence trail.
  • Re-check risk flags: 64k_cutoff_might_drop_summarization_benefit_for_some_long_sessions, inconsistent_env_flag_behavior_across_runtimes.
Open Topic TimelineOpen Technical EventOpen Original Source64k_cutoff_might_drop_summarization_benefit_for_some_long_sessions / inconsistent_env_flag_behavior_across_runtimes / watch_for_regression_in_context_boundary_transitions

Supporting Evidence