Run Inputs

When you queue a run you may supply initial context — a dictionary of string key/value pairs seeded onto the run before the first step executes. Inputs appear in the run's context channel with kind Input and are visible to every step.

{
  "workflowId": "…",
  "agentId": "…",
  "initialContext": {
    "task_id": "task-7f3a",
    "purpose": "instance-fulfilment",
    "fspNumber": "12345",
    "advisorName": "Jane Q. Advisor"
  }
}

Ordinary keys (like fspNumber above) are plain data for your step instructions to reference. Two keys are reserved and change how the run's identity is composed.

Reserved keys

task_id

The task this session is being composed for — typically an identifier opened in a downstream system before the run. When present, it is threaded into every step's token exchange, and the issued delegated token carries a matching task_id claim. Downstream resources can bind their fulfilment scope to it (e.g. "this session may only stage proposals attributed to task X").

purpose

The declared purpose of the session (e.g. instance-fulfilment). When present, it is sent in every step's token exchange — validated by the identity provider against the client's allowed purposes — and the issued token carries a matching purpose claim.

No purpose, no problem — fail-closed

If you omit purpose, no purpose claim is requested. Resources that require a purpose will reject the session at the door; resources that don't require one run unchanged. Forgetting a purpose can never grant broader access — it can only reduce where the session is accepted.

Both values are constant for the whole run and identical across all its steps.

Context keys produced by steps

As steps execute, outputs are promoted under predictable keys (1-based step order):

Key	Kind	Content
toolResult_<n>	ToolOutput	Step n's last tool result — authoritative data.
modelResponse_<n>	ModelText	Step n's final model text.

Reference these in later step instructions, e.g. "using the match verdict in toolResult_1, call CreateAdvisor …".

Limits

• Keys prefixed binary: are excluded from the context visible to steps.
• Runs enforce caps on the number of context entries and total context characters; breaching a cap fails the run explicitly with the limit named in the failure reason.