v44

latestOpenAPI 3.1.0Proprietaryraw.githubusercontent.com2026-05-192301780.0 KB

Agents

Execute ad-hoc agent

Creates an ephemeral agent and immediately executes a run. Returns the run ID for polling status and results. This is the fastest way to run an agent without managing agent lifecycle.

Ephemeral agent lifecycle: The agent created by this endpoint is automatically soft-deleted and its scoped API key revoked when the run completes (whether it succeeds, fails, or times out). Ephemeral agents do not appear in GET /agent/v1/agents listings. The returned agentId is valid only for the duration of the run — do not store it for reuse. For persistent, reusable agents, use POST /agent/v1/agents instead.

post/agent/v1/execute

Request body

promptstring required

Task prompt for the agent

instructionsstring

System instructions. Defaults to a general-purpose legal assistant prompt if not provided.

modelstring

LLM model identifier. Defaults to anthropic/claude-sonnet-4.6

vaultIdsstring[] nullable

Restrict agent to specific vault IDs

objectIdsstring[] nullable

Scope this run to specific vault object IDs. The agent will only access these objects.

guidancestring nullable

Additional context or constraints for this run

enabledToolsstring[] nullable

Allowlist of tools the agent can use. Mutually exclusive with disabledTools — set one or the other, not both.

disabledToolsstring[] nullable

Denylist of tools the agent cannot use. Mutually exclusive with enabledTools — set one or the other, not both.

Response

Run started

runIdstring

Run ID — poll /agent/v1/run/:id/status

agentIdstring

Ephemeral agent ID (auto-created). This agent is soft-deleted when the run completes and should not be stored for reuse.

status'running'

messagestring