> ## Documentation Index > Fetch the complete documentation index at: https://docs.cotool.ai/llms.txt > Use this file to discover all available pages before exploring further. # List agent run messages > Page through an agent run's conversation, oldest first: messages to the agent, its replies, and its tool calls with their output. Works at any run status. A message keeps its offset as the run grows; the latest page starts at `totalCount - limit`. ## OpenAPI ````yaml https://app.cotool.ai/api/docs/openapi.json get /api/agents/{agentId}/run-async/{runId}/messages openapi: 3.1.0 info: title: Cotool API version: 1.0.0 description: >- The Cotool REST API. Authenticate with an API key from `/settings/api-keys` sent as `Authorization: Bearer `. Authentication, error formats, pagination, and common integration recipes are documented in the [API overview](https://docs.cotool.ai/api-reference/introduction). Endpoints marked **Deprecated** keep working; each one's description names its replacement. servers: - url: https://app.cotool.ai description: Production server security: - ApiKeyAuth: [] tags: - name: Agents description: Create, update, run, and version agents. - name: Agent Runs description: Inspect agent runs, submit feedback, and read evaluation metrics. - name: Agent Triggers description: Webhook, schedule, and integration triggers that start agent runs. - name: Agents as Code description: Validate agents and skills defined as YAML in a Git repository. - name: Skills description: Reusable instructions and tool grants attached to agents. - name: Chat description: Chat sessions and their transcripts. - name: Alerts description: Alert triage, routing, and escalation notifications. - name: Output Destinations description: Webhook, Slack, Jira, and Linear destinations for agent output. - name: Detections description: Detection agents, detection hits, and the Cotool detection library. - name: Hunt description: Autonomous hunt threats, gaps, and settings. - name: Intel description: Threat-intelligence feed items, indicators, and sources. - name: Threat Model description: The organization threat model and its version history. - name: MITRE Coverage description: MITRE ATT&CK coverage across detections. - name: Tools description: Connected tool integrations and captured tool output. - name: CLIs description: Connected CLI integrations. - name: Artifacts description: Files and reports produced by agent runs. - name: Audit Logs description: Organization audit log export and event catalog. - name: Users description: Users, memberships, and the current session. - name: Roles description: Role-based permissions. - name: Organizations description: Organization-level metrics. paths: /api/agents/{agentId}/run-async/{runId}/messages: get: tags: - Agents summary: List agent run messages description: >- Page through an agent run's conversation, oldest first: messages to the agent, its replies, and its tool calls with their output. Works at any run status. A message keeps its offset as the run grows; the latest page starts at `totalCount - limit`. parameters: - in: path name: agentId description: Unique identifier of the agent schema: type: string format: uuid description: Unique identifier of the agent required: true - in: path name: runId description: Unique identifier of the asynchronous run to check status for schema: type: string format: uuid description: Unique identifier of the asynchronous run to check status for required: true - in: query name: offset description: Messages to skip, counting from the oldest (default 0) schema: type: integer minimum: 0 description: Messages to skip, counting from the oldest (default 0) - in: query name: limit description: Most messages to return (default 20) schema: type: integer minimum: 1 maximum: 100 description: Most messages to return (default 20) responses: '200': description: Successful response content: application/json: schema: type: object properties: totalCount: type: integer description: Messages in the run so far messages: type: array items: oneOf: - type: object properties: type: type: string const: user text: type: string timestamp: type: string description: ISO 8601 time it was written required: - type - text - timestamp - type: object properties: type: type: string const: agent text: type: string timestamp: type: string description: ISO 8601 time it was written required: - type - text - timestamp - type: object properties: type: type: string const: tool action: type: string description: Integration action the agent called status: type: string enum: - inProgress - success - error input: {} output: type: string description: >- The result the agent read, cut at 10000 characters timestamp: type: string description: ISO 8601 time it was written required: - type - action - status - timestamp description: A message, reply, or tool call in an agent run required: - totalCount - messages description: A page of an agent run conversation '400': description: Bad request — input validation failed or the request was malformed content: application/json: schema: $ref: '#/components/schemas/ValidationError' '401': description: Unauthorized — missing or invalid API key / session content: application/json: schema: $ref: '#/components/schemas/Error' '403': description: Forbidden — the authenticated user lacks the required permissions content: application/json: schema: $ref: '#/components/schemas/PermissionError' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/Error' x-codeSamples: - lang: shell label: cURL source: >- curl -X GET "https://app.cotool.ai/api/agents/:agentId/run-async/:runId/messages" \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" components: schemas: ValidationError: type: object properties: error: type: string description: Error message describing what went wrong issues: type: array description: >- Detailed validation issues, present when request or response schema validation fails items: type: object additionalProperties: true required: - error Error: type: object properties: error: type: string description: Error message describing what went wrong required: - error PermissionError: type: object properties: error: type: string description: Error message describing what went wrong missingPerms: type: array description: Permissions the authenticated user is missing for this operation items: type: string required: - error securitySchemes: ApiKeyAuth: type: http scheme: bearer bearerFormat: API Key description: >- API Key authentication for programmatic access. Include your API key in the Authorization header as: `Bearer your_api_key_here` ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.