Answer a run that is paused on a human-input request (from list_pending_inputs). For an approval, set approved=true/false. For an input request, set value to the requested text.

Create a new agent: a cloud computer running plori's agent, with its own disk, tools, and memory. Returns the agent id. Subject to the account's plan limits (agent count, model tier).

Permanently delete an agent and revoke its disk. This cannot be undone.

Get one agent's details (name, type, model, status) by its id.

Get the authenticated account's credit balance and plan. Running agents spends credits, so check this before invoking.

Get the authenticated account's disk state (included, purchased, used bytes, and monthly cost).

Get a run's status and, if it has completed, the assistant's reply. Use to poll a run started with invoke_agent wait=false.

Get the authenticated account's usage rollup (spend by meter and by agent, recent runs).

Send a message to an agent and, by default, wait for the turn to finish and return the assistant's reply. Running an agent spends credits. If the run pauses on a human-input request it returns status "awaiting_input" (use list_pending_inputs + answer_pending_input). Pass wait=false to return a run_id immediately and poll get_run_result.

List the agents owned by the authenticated account, with their model and live session status.

List the agent type plori provides. create_agent always provisions it, so this is informational and optional.

List the agent's runs that are paused awaiting a human approval or input (the HITL queue).

List an agent's run history (most recent first), with each run's status.

Schedule a deferred run of an agent: it will be invoked later with the given prompt. Provide either delay_seconds (relative) or fire_at (an RFC3339 timestamp).

Change an agent's model. Takes effect on the agent's next turn. Frontier models require a paid plan.