PalveronPalveronDocs

Agent Budgets

Daily request, token, and cost limits per agent.

Agent budgets cap what each agent can do in a 24-hour window. Three dimensions run independently — exceed any one and the configured enforcement action fires.

DimensionUnitWhat it measures
Request budgetgovernance checks / dayVerify calls + MCP tool calls + extension events
Token budgettokens / dayEstimated LLM token usage (observability only — not billed)
Cost budgetEUR / dayEstimated LLM spend at current model rates

Enforcement

When a budget is breached, the agent's configured enforcement kicks in:

ActionBehavior
BLOCK (default)All further requests rejected with BUDGET_EXCEEDED until the counter resets
WARNRequests still pass; every response carries an x-palveron-budget-warning header
APPROVALRequests are queued for human approval — reviewer can grant a one-off pass

Configure per agent under Agents → {agent} → Budgets or via PATCH /api/v1/agents/{id}.

Counter reset

All counters reset daily at 00:00 UTC. Resets are atomic — no half-counted requests at the boundary. Historical counter values are retained for 90 days and surface in the usage dashboard.

Token and cost figures are estimates — Palveron infers them from the prompt + response payload using the model's published per-token price. For exact billing, reconcile against your LLM provider's invoice.

On this page