How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

AGNTCY Thread Runs API

Thread Runs are runs created on a thread. A Thread Run can be created on a thread **only** if there is no run in the `pending` status on the same thread, i.e. if the thread is in the state `idle`Note that runs over the same thread can be executed on different agents, as long as the agents support the same thread state format.See `Thread` and `RunCreateStateful` for more info.

AGNTCY Thread Runs API is one of 21 APIs that AGNTCY publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

This API exposes 2 JSON Schema definitions.

Tagged areas include Thread Runs. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, an API reference, authentication docs, and 2 JSON Schemas.

This API exposes 10 operations across 7 paths, and defines 24 schemas. It is described by OpenAPI 3.2.0, at version 0.2.3.

Requests are made against the base URL https://schema.oasf.outshift.com/api.

10 operations 7 paths 24 schemas 1 DELETE4 GET5 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
0.2.3
Base URL
https://schema.oasf.outshift.com/api
Resource Areas
1

Paths & Operations 10

Across 7 paths, the API surfaces 10 operations — 1 DELETE, 4 GET, 5 POST. Each is listed below with its method, path, parameters, and response codes.

Thread Runs 10

Thread Runs are runs created on a thread. A Thread Run can be created on a thread only if there is no run in the pending status on the same thread, i.e. if the thread is in the st…

GET
/threads/{thread_id}/runs
List Runs for a thread
list_thread_runs 3 params → 200404422
POST
/threads/{thread_id}/runs
Create a Background Run on a thread
create_thread_run 1 param body → 200404409422
POST
/threads/{thread_id}/runs/stream
Create a run on a thread and stream its output
create_and_stream_thread_run_output 1 param body → 200404409422
POST
/threads/{thread_id}/runs/wait
Create a run on a thread and block waiting for the result of the run
create_and_wait_for_thread_run_output 1 param body → 200404409422
GET
/threads/{thread_id}/runs/{run_id}/wait
Blocks waiting for the result of the run.
wait_for_thread_run_output 2 params → 200404422
GET
/threads/{thread_id}/runs/{run_id}
Get Run
get_thread_run 2 params → 200404422
POST
/threads/{thread_id}/runs/{run_id}
Resume an interrupted Run
resume_thread_run 2 params body → 200404409422
DELETE
/threads/{thread_id}/runs/{run_id}
Delete Run
delete_thread_run 2 params → 204404422
GET
/threads/{thread_id}/runs/{run_id}/stream
Stream output from Run
stream_thread_run_output 2 params → 200404422
POST
/threads/{thread_id}/runs/{run_id}/cancel
Cancel Run
cancel_thread_run 4 params → 204404422

Schemas 24

The contract defines 24 schemas that model the data the API accepts and returns. The most detailed are RunCreate (9 properties), Run (6 properties), ValueRunResultUpdate (5 properties), CustomRunResultUpdate (4 properties). Each schema is shown below with its type and property counts.

ValueRunInterruptUpdate
object
Partial result provided as value through streaming.
ErrorResponse
string
Error message returned from the server
StreamingMode
string
InputSchema
The input of the agent. The schema is described in agent ACP descriptor under 'spec.input'.
RunOutput
Output of a Run. Can be the final result or an interrupt.
ResumePayloadSchema
This schema describes the resume payload after an interrupt. Actual schema describes a polimorphic object, which means a schema structured with oneOf and discr…
RunInterrupt
object
Interrupt occurred during a Run
2 properties 2 required
StreamUpdateSchema
object
An update in the SSE event streaming where streaming mode is set to custom. The schema is described in agent ACP descriptor under 'spec.customstreamingupdate'.
ValueRunResultUpdate
object
Partial result provided as value through streaming.
5 properties 4 required
RunError
object
Run terminated with an error
4 properties 4 required
ConfigSchema
The configuration for this agent. The schema is described in agent ACP descriptor under 'spec.config'. If missing, default values are used.
RunWaitResponseStateful
object
2 properties
InterruptPayloadSchema
This schema describes the interrupt payload. Actual schema describes a polimorphic object, which means a schema structured with oneOf and discriminator. The di…
RunCreateStateful
Payload for creating a stateful run.
RunOutputStream
object
Server-sent event containing one agent output event. Actual event type is carried inside the data.
3 properties 3 required
RunStateful
Holds all the information of a stateful run
RunCreate
object
Payload for creating a run.
9 properties
OutputSchema
The output of the agent. The schema is described in agent ACP descriptor under 'spec.output'.
RunResult
object
Final result of a Run.
3 properties 1 required
Message
object
4 properties 2 required
Run
object
Holds common information of a run
6 properties 5 required
CustomRunResultUpdate
object
Object holding a custom defined update of the agent result during streaming.
4 properties 3 required
RunStatus
string
ValueRunErrorUpdate
object
Partial result provided as value through streaming.

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

agntcy-thread-runs-api-openapi.yml Raw ↑

Other APIs AGNTCY publishes across the network.

Agent Directory (DIR)
AGNTCY Agents API
AGNTCY App Service API
AGNTCY Auth Service API
AGNTCY Badge Service API
AGNTCY Classes and Objects API
AGNTCY Device Service API
AGNTCY ID Service API
AGNTCY Issuer Service API
AGNTCY JSON Schema API
AGNTCY Policy Service API
AGNTCY Sample Data API
Where this information came from

This is an independent, third-party profile of AGNTCY Thread Runs API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.