session_start
Start a managed-agent session by attaching the required environment, vaults, and memory stores to ensure proper authentication and context.
Instructions
Start a managed-agent session — with the RIGHT resources attached for THIS agent.
Do NOT start bare or with mismatched resources. An agent only behaves well when its OWN environment, vault(s), and memory store(s) are attached; the wrong or missing ones cause failed tool authentication, lost memory/context, and bad outcomes.
Before calling, assemble the resources for this agent:
agent_get(agent_id)— read its description, metadata, mcp_servers, skills.Choose
environment_id+vault_ids+memory_store_idsthat BELONG to this agent by matching each resource's name/description/metadata (oftenmetadata.agent_name=<agent>, or "-vault" / "-memory"). Use environment_list / vault_list / memory_store_list (and *_get when unsure). If you can't confidently match a resource, ask the user — don't guess or skip it.
Then:
vault_ids—vlt_*credential vaults (else MCP servers needing auth fail).memory_store_ids—memstore_*persistent memory mounted in the sandbox.message— sent as the first instruction now (omit to only provision).agent_version— pin a version (default: latest).
Returns the session_id. After starting, OBSERVE by polling
session_get/session_events until status is "idle".
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | Yes | ||
| environment_id | Yes | ||
| message | No | ||
| vault_ids | No | ||
| memory_store_ids | No | ||
| agent_version | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||