Skip to main content

​
ContextManager

Defined in the manager module.
Unified facade for context management. Orchestrates budgeting, composition, optimization, and monitoring. Provides hooks for exact LLM boundary snapshots. Tracks optimization history for debugging.

​
Constructor

​
model
str
default:"'gpt-4o-mini'"
No description available.
​
config
Optional
No description available.
​
session_id
str
default:"''"
No description available.
​
agent_name
str
default:"''"
No description available.
​
session_cache
Optional
No description available.
​
llm_summarize_fn
Optional
No description available.

​
Methods

process()

Process messages through the context pipeline.

capture_llm_boundary()

Capture exact state at LLM call boundary.

register_snapshot_callback()

Register a callback for LLM boundary snapshots.

get_last_snapshot_hook()

Get the last LLM boundary snapshot.

estimate_tokens()

Estimate tokens with optional validation.

get_tool_budget()

Get token budget for a specific tool.

set_tool_budget()

Set token budget for a specific tool.

truncate_tool_output()

Truncate tool output according to its budget.

get_history()

Get optimization history.

get_stats()

Get current context statistics.

emergency_truncate()

Emergency truncation when optimization isn’t enough.

get_resolved_config()

Get the fully resolved configuration with source info.

reset()

Reset manager state.

​
Usage

manager = ContextManager(model="gpt-4o")
    
    # Process messages before LLM call
    result = manager.process(
        messages=messages,
        system_prompt=system_prompt,
        tools=tools,
    )
    
    # Get optimized messages
    optimized_messages = result["messages"]
    
    # Check if optimization occurred
    if result["optimized"]:
        print(f"Saved {result['tokens_saved']} tokens")