For the complete documentation index, see llms.txt. This page is also available as Markdown.

Agent Runs

List framework agent runs

get

Paginated list of framework agent runs for the workspace, newest first, read from the durable world.agent_runs read model. Filter by framework / status. continuation_token is an opaque page cursor.

Authorizations
AuthorizationstringRequired

API key issued via POST /v1/{workspace_id}/api-keys. Pass the returned api_key value as a Bearer token.

Path parameters
workspace_idstring · uuidRequired
Query parameters
limitinteger · max: 200OptionalDefault: 50
continuation_tokenanyOptional
frameworkstring · enum · nullableOptionalPossible values:
statusstring · enum · nullableOptionalPossible values:
Responses
200

Successful Response

application/json
has_morebooleanRequired
continuation_tokenanyOptional
get/v1/{workspace_id}/agent-runs

Dispatch a framework agent run

post

Proxies to agent-runner, which executes the chosen framework UNMODIFIED (natural setup) against the platform MCP world-tools edge under the caller's own bearer. Non-blocking — poll GET /agent-runs/{run_id} for the result.

Authorizations
AuthorizationstringRequired

API key issued via POST /v1/{workspace_id}/api-keys. Pass the returned api_key value as a Bearer token.

Path parameters
workspace_idstring · uuidRequired
Body
service_idstring · uuid · nullableOptional

Platform-authored run: the service whose pinned config the agent runs.

version_setstring · min: 1 · max: 256Optional

Named version set on the service whose pinned config the run uses (platform runs).

Default: release
frameworkstring · enum · nullableOptional

Framework a PLATFORM run executes on. For a native run the framework comes from the definition.

Possible values:
messagestring · min: 1 · max: 8000Required

User message the framework agent is invoked with.

timeout_sinteger · max: 300Optional

Server-side wall-clock budget for the run, in seconds (max 300).

Default: 120
Responses
202

Successful Response

application/json
run_idstring · uuidRequired
statusconst: runningRequired
post/v1/{workspace_id}/agent-runs

Fetch the neutral session-bootstrap context for a service

get

The retrievable CONTEXT edge of the world-model harness: identity + reference instructions, world scope, tool descriptors, guardrails, and the REAL server-enforced write-floor — the byte-identical projection the hosted runner renders from, so a customer's own framework can bootstrap a session against the same world model. PHI-free (the API-run projection carries no scoped entities or rendered caller prose).

Authorizations
AuthorizationstringRequired

API key issued via POST /v1/{workspace_id}/api-keys. Pass the returned api_key value as a Bearer token.

Path parameters
workspace_idstring · uuidRequired
Query parameters
service_idstring · uuidRequired
version_setstring · max: 255OptionalDefault: release
Responses
200

Successful Response

application/json

The neutral, retrievable session-bootstrap context for ANY framework.

context_versionintegerOptionalDefault: 1
config_fingerprintstringOptionalDefault: ""
sourcestringOptionalDefault: ""
get/v1/{workspace_id}/agent-runs/harness-context

Get a framework agent run

get

Run status, final text, token usage, and the adapter-normalized trajectory of the framework's native output.

Authorizations
AuthorizationstringRequired

API key issued via POST /v1/{workspace_id}/api-keys. Pass the returned api_key value as a Bearer token.

Path parameters
workspace_idstring · uuidRequired
run_idstring · uuidRequired
Responses
200

Successful Response

application/json
run_idstring · uuidRequired
statusstring · enumRequiredPossible values:
frameworkstring · enumRequiredPossible values:
textstringOptional

Final agent text. Empty while the run is still running or on failure.

Default: ""
errorstringOptional

Failure detail for failed/timed_out runs. Empty otherwise.

Default: ""
duration_msnumberOptionalDefault: 0
get/v1/{workspace_id}/agent-runs/{run_id}

Last updated

Was this helpful?