Context Budgeter

from praisonaiagents import Agent, ManagerConfig

agent = Agent(
    name="budget-agent",
    instructions="Stay within token budgets.",
    context=ManagerConfig(output_reserve=16000),
)
agent.start("Summarise this thread without using the full window.")

from praisonaiagents.context import get_model_limit, get_output_reserve

# Consults litellm.model_cost first, then falls back to the static table.
limit = get_model_limit("gpt-4o-mini")  # 128000
reserve = get_output_reserve("gpt-4o-mini")  # 16384

from praisonaiagents.context import ContextBudgeter

budgeter = ContextBudgeter(
    model="gpt-4o",
    system_prompt_budget=3000,
    rules_budget=1000,
    skills_budget=500,
    memory_budget=5000,
    tools_schema_budget=3000,
    tool_outputs_budget=30000,
    buffer_budget=2000,
)
budget = budgeter.allocate()

from praisonaiagents.context import ContextBudgeter

budgeter = ContextBudgeter(model="gpt-4o-mini")

# Check if current usage exceeds budget
current_tokens = 100000
is_overflow = budgeter.check_overflow(current_tokens)

# Get utilization percentage
utilization = budgeter.get_utilization(current_tokens)
print(f"Utilization: {utilization:.1%}")

# Get remaining capacity
remaining = budgeter.get_remaining(current_tokens)
print(f"Remaining: {remaining:,} tokens")

from praisonaiagents.context import ContextBudgeter

budgeter = ContextBudgeter(model="gpt-4o-mini")
budget = budgeter.allocate()

# Trigger optimization at 80% utilization
threshold = 0.8
trigger_at = int(budget.usable * threshold)

current_tokens = 95000
if current_tokens > trigger_at:
    print("Time to optimize!")

# Set output reserve
praisonai chat --context-output-reserve 10000

# Set optimization threshold
praisonai chat --context-threshold 0.8

PRAISONAI_CONTEXT_OUTPUT_RESERVE=8000
PRAISONAI_CONTEXT_THRESHOLD=0.8

from praisonaiagents.context import ContextBudgeter

budgeter = ContextBudgeter(model="gpt-4o-mini")
budget_dict = budgeter.to_dict()

# Returns:
# {
#     'model': 'gpt-4o-mini',
#     'model_limit': 128000,
#     'output_reserve': 16384,
#     'usable': 111616,
#     'allocation': {...}
# }