monitor_operative
diapason.agents.monitor_operative
¶
MonitorOperativeAgent -- long-horizon agent with configurable strategies.
Extends ToolUsingAgent (not OperativeAgent) with four configurable strategy axes for long-horizon benchmark evaluation:
- memory_extraction -- how findings are persisted to memory
- observation_compression -- how tool outputs are compressed
- retrieval_strategy -- how prior context is recalled
- task_decomposition -- how complex tasks are split
The agent also inherits cross-session state persistence from the OperativeAgent pattern (session_store, memory_backend, operator_id).
MonitorOperativeAgent
¶
Bases: ToolUsingAgent
Long-horizon agent with configurable memory, compression, retrieval, and decomposition strategies.
The four strategy axes control how the agent manages information across turns and sessions:
memory_extraction: How findings are persisted (causality_graph, scratchpad, structured_json, none).observation_compression: How tool outputs are compressed before being added to context (summarize, truncate, none).retrieval_strategy: How prior context is recalled at the start of each run (hybrid_with_self_eval, keyword, semantic, none).task_decomposition: How complex tasks are broken down (phased, monolithic, hierarchical).
run(input, context=None, **kwargs)
¶
Execute the agent on input with the configured strategies.