Context Budgeter CLI

CLI reference for context budget configuration

Configure context budget allocation via CLI flags and interactive commands.

CLI Flags

Output Reserve

# Set output token reserve
praisonai chat --context-output-reserve 16000

Default: 8000 tokens

Interactive Commands

View Budget

> /context budget

Output:

Budget Allocation
  Model Limit:     128,000
  Output Reserve:  8,000
  Usable:          120,000

  Segment Budgets:
    System Prompt: 2,000
    Rules:         500
    Skills:        500
    Memory:        1,000
    Tool Schemas:  2,000
    Tool Outputs:  20,000
    History:       84,616
    Buffer:        1,000

View Stats

> /context stats

Shows current usage vs budget per segment.

Environment Variables

export PRAISONAI_CONTEXT_OUTPUT_RESERVE=8000

config.yaml

context:
  output_reserve: 8000
  default_tool_output_max: 10000

Model Limits

Model	Context Limit	Default Reserve
gpt-4o	128,000	16,384
gpt-4o-mini	128,000	16,384
gpt-4-turbo	128,000	4,096
claude-3-opus	200,000	8,192
gemini-1.5-pro	2,097,152	8,192

Troubleshooting

Not enough space for output

# Increase output reserve
praisonai chat --context-output-reserve 16000

Context filling too fast

# Lower threshold for earlier compaction
praisonai chat --context-threshold 0.7