> ## Documentation Index > Fetch the complete documentation index at: https://agentcommunicationprotocol.dev/llms.txt > Use this file to discover all available pages before exploring further. # Get run status > Returns the current status and details of a run. ## OpenAPI ````yaml GET /runs/{run_id} openapi: 3.1.1 info: title: ACP - Agent Communication Protocol description: >- The Agent Communication Protocol (ACP) provides a standardized RESTful API for managing, orchestrating, and executing AI agents. It supports synchronous, asynchronous, and streamed agent interactions, with both stateless and stateful execution modes. license: name: Apache 2.0 url: https://www.apache.org/licenses/LICENSE-2.0.html version: 0.2.0 servers: - url: http://localhost:8000 security: [] tags: - name: agent description: >- Operations for listing, describing, and managing agent definitions and metadata. - name: run description: >- Operations for creating, managing, controlling, and monitoring agent runs and their lifecycles. externalDocs: description: Comprehensive documentation for ACP url: https://agentcommunicationprotocol.dev paths: /runs/{run_id}: get: tags: - run summary: Get run status description: Returns the current status and details of a run. operationId: getRun parameters: - name: run_id in: path required: true description: UUID of the run. schema: $ref: '#/components/schemas/RunId' responses: '200': description: Run status content: application/json: schema: $ref: '#/components/schemas/Run' default: $ref: '#/components/responses/Error' components: schemas: RunId: type: string format: uuid description: Identifier of a run Run: type: object properties: agent_name: $ref: '#/components/schemas/AgentName' session_id: $ref: '#/components/schemas/SessionId' run_id: $ref: '#/components/schemas/RunId' status: $ref: '#/components/schemas/RunStatus' await_request: $ref: '#/components/schemas/AwaitRequest' nullable: true output: type: array items: $ref: '#/components/schemas/Message' error: $ref: '#/components/schemas/Error' nullable: true created_at: type: string format: date-time finished_at: type: string format: date-time required: - agent_name - run_id - status - output - created_at AgentName: type: string pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$ minLength: 1 maxLength: 63 description: >- A unique identifier for the agent following the RFC 1123 DNS label naming convention. example: chat SessionId: type: string format: uuid description: Identifier of a session RunStatus: type: string enum: - created - in-progress - awaiting - cancelling - cancelled - completed - failed description: Status of the run AwaitRequest: type: object description: Payload describing what is awaited from the client to continue the run. Message: type: object required: - parts - role properties: role: type: string description: > Specifies the sender of the message. Allowed values: - `"user"` for messages sent by an end-user. - `"agent` for anonymous agent. - `"agent/{agent_name}"` for messages sent by an agent, where `{agent_name}` is the identifier of the agent. examples: - user - agent - agent/summarizer - agent/data_processor pattern: ^(user|agent(\/[a-zA-Z0-9_\-]+)?)$ parts: type: array items: $ref: '#/components/schemas/MessagePart' minItems: 1 description: Ordered sequence of message parts created_at: type: string format: date-time completed_at: type: string format: date-time Error: type: object properties: code: type: string enum: - server_error - invalid_input - not_found message: type: string data: type: object nullable: true required: - code - message MessagePart: type: object properties: name: type: string content_type: type: string default: text/plain content: type: string content_encoding: type: string enum: - plain - base64 default: plain content_url: type: string format: uri metadata: oneOf: - $ref: '#/components/schemas/CitationMetadata' - $ref: '#/components/schemas/TrajectoryMetadata' nullable: true required: - content_type not: allOf: - required: - content - required: - content_url description: >- A part of a message, containing a specific `content_type` and either inline `content` or `content_url`, or neither. Only one of `content` or `content_url` can be provided. CitationMetadata: type: object description: > Represents an inline citation, providing info about information source. This is supposed to be rendered as an inline icon, optionally marking a text range it belongs to. If CitationMetadata is included together with content in the message part, the citation belongs to that content and renders at the MessagePart position. This way may be used for non-text content, like images and files. Alternatively, `start_index` and `end_index` may define a text range, counting characters in the current Message across all MessageParts with content type `text/*`, where the citation will be rendered. If one of `start_index` and `end_index` is missing or their values are equal, the citation renders only as an inline icon at that position. If both `start_index` and `end_index` are not present and MessagePart has no content, the citation renders as inline icon only at the MessagePart position. properties: kind: type: string const: citation default: citation start_index: type: integer nullable: true end_index: type: integer nullable: true url: type: string nullable: true title: type: string nullable: true description: type: string nullable: true description: > Accompanying text, which may be a general description of the source document, or a specific snippet. required: - kind TrajectoryMetadata: type: object description: > Represents trajectory information for an agent's reasoning or tool execution steps. This metadata helps track the agent's decision-making process and provides transparency into how the agent arrived at its response. TrajectoryMetadata can capture either: 1. A reasoning step with a message 2. A tool execution with tool name, input, and output This information can be used for debugging, audit trails, and providing users with insight into the agent's thought process. properties: kind: type: string const: trajectory default: trajectory message: type: string nullable: true description: A reasoning step or thought in the agent's decision process. tool_name: type: string nullable: true description: Name of the tool that was executed. tool_input: type: object nullable: true description: Input parameters passed to the tool. tool_output: type: object nullable: true description: Output or result returned by the tool. required: - kind responses: Error: description: Error response content: application/json: schema: $ref: '#/components/schemas/Error' ````