Budget Enforcement

Fuze enforces hard budget ceilings at two levels: per-step and per-run. The step doesn't execute if it would exceed the ceiling.

How it works

1. Before each guarded call, Fuze estimates the cost based on the model and expected token usage
2. If estimated_cost + accumulated_cost > ceiling, the call is blocked before execution
3. After each call, the actual cost is recorded and accumulated

const search = guard(searchFn, {
  maxCost: 0.50,  // Per-step ceiling
})

Configuration

[defaults]
max_cost_per_step = 1.00  # USD per individual call
max_cost_per_run = 10.00  # USD for the entire run
max_tokens = 100000       # Token ceiling per run
timeout = "30s"           # Time ceiling per call

Budget types

Provider price registry

Fuze maintains a price registry for major LLM providers:

• OpenAI (GPT-4o, GPT-4, GPT-3.5)
• Anthropic (Claude 3.5 Sonnet, Claude 3 Opus, Claude 3 Haiku)
• Google (Gemini Pro, Gemini Flash)

Override pricing for enterprise discounts:

[providers]
"openai/gpt-4o" = { input = 0.0020, output = 0.008 }
"anthropic/claude-3-5-sonnet" = { input = 0.003, output = 0.015 }

Timer cleanup

When a timeout is configured, Fuze sets up an internal timer for each guarded call. On successful completion, the timer is properly cleaned up — there are no leaked timers. If the timeout fires before the call completes, Fuze throws a GuardTimeout error.

Error handling

Fuze throws specific error classes for budget violations so you can catch and inspect them programmatically.

import { BudgetExceeded, GuardTimeout } from 'fuze-ai'

try {
  await guardedSearch('query')
} catch (err) {
  if (err instanceof BudgetExceeded) {
    console.log(err.accumulated)  // Total spent so far
    console.log(err.ceiling)      // The ceiling that was hit
    console.log(err.estimated)    // Estimated cost of blocked call
  }

  if (err instanceof GuardTimeout) {
    // The guarded call exceeded its configured timeout
    console.log(err.message)
  }
}