Module: LittleGhost::Agent::ContextManagement

Included in:

LittleGhost::Agent

Defined in:

lib/little_ghost/agent/context_management.rb

Overview

Keep long conversations within the model's available context window. The capability summarizes older turns while preserving trusted instructions and recent messages.

class CustomerSupportAgent < LittleGhost::Agent
manage_context compression_threshold: 0.75,
  preserve_recent_messages: 12
end

As a support thread reaches the threshold, the next model request contains a generated summary and targets retaining its 12 most recent conversation messages. System and developer messages remain intact, and tool-use/result pairs are never split merely to hit the requested count.

Context management is inactive until manage_context is declared. The configured window is a fallback: provider metadata takes precedence when it advertises a positive context-window size. Compaction uses the current model with the request's settings, cancellation token, and deadline.

Proactive compaction failures leave the original request unchanged and emit diagnostic instrumentation. A provider context-overflow error triggers one compaction replacement through the model-error callback; cancellation, deadlines, and cleanup failures still escape as control flow.

Defined Under Namespace

Modules: ClassMethods

Constant Summary

DEFAULT_CONTEXT_WINDOW_TOKENS =

:nodoc:

200_000

DEFAULT_COMPRESSION_THRESHOLD =

:nodoc:

0.85

DEFAULT_SUMMARY_RATIO =

:nodoc:

0.3

DEFAULT_PRESERVE_RECENT_MESSAGES =

:nodoc:

10

ESTIMATED_CHARS_PER_TOKEN =

:nodoc:

4

OUTPUT_LIMIT_STOP_REASONS =

:nodoc:

%i[max_tokens limit_output_tokens limit_total_tokens limit_turns].freeze

Class Method Summary

• .included(base) ⇒ Object

  :nodoc:.

Class Method Details

.included(base) ⇒ Object

:nodoc:

# File 'lib/little_ghost/agent/context_management.rb', line 38

def self.included(base) # :nodoc:
  base.extend(ClassMethods)
  base.class_attribute :context_management_configuration_value
end