List in-process agent records (id, status, spend, budget, capabilities).

Use before run_task to discover agent_id values. Read-only snapshot of this process. Does not create agents (create_agent) or start work (run_task).

Create an agent process with intent, USD budget, and capabilities.

Returns agent_id for later run_task / list_agents. Does not execute a goal. Side effect: writes the in-memory process table. Default model is mock-gpt.

Run one goal on an existing agent until completion, policy deny, or budget stop.

Blocks up to 120s. Missing agent_id returns an error object. Use create_agent first. Not for multi-agent orchestration (create_workflow). Side effects: task row + spend.

Return the token/$ cost ledger for this process.

Use to audit spend after run_task. Read-only. Not get_audit_log or get_metrics.

Return governance allow/deny records from AgentFence.

Use after a blocked run_task. Read-only. Not the dollar ledger (get_cost_ledger).

Return runtime counters (agents created, tasks).

Use for health checks. Read-only. Does not include cost rows or policy events.

Create specialist agents and run a sequential multi-agent workflow.

Default roles are planner then worker, sharing budget_usd. Use when a goal needs more than one agent. Do not use to run a single existing agent (run_task). Side effects: creates agents + tasks and marks the workflow completed.

List capability names that can be granted to agents.

Use before create_agent to choose the capabilities argument. Read-only.

Return an offline x402 payment quote for a named service.

Read-only simulation. Does not charge or call a facilitator. Missing services return an error object. Not create_agent or run_task.