> ## Documentation Index
> Fetch the complete documentation index at: https://docs.usenotra.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Send a follow-up message or answer a pending input request

> Sends the next turn of an agent session. The server binds the session's stored continuation token, so the client-provided one is ignored. Answer input.requested events (tool approvals, questions) from the event stream via inputResponses.



## OpenAPI

````yaml https://api.usenotra.com/openapi.json post /v2/eve/v1/session/{sessionId}
openapi: 3.1.1
info:
  title: Notra API
  version: 1.0.0
  description: >-
    OpenAPI schema for Notra content endpoints. Use GET /v1/status for public
    reachability. Error responses include recovery guidance.
servers:
  - url: https://api.usenotra.com
    description: Production
security:
  - BearerAuth: []
tags:
  - name: Discovery
    description: Public API status and authenticated workspace discovery.
  - name: Content
    description: >-
      Manage posts, brand identities, and GitHub or Linear integrations, and
      queue content generation. Organization is inferred from the API key
      (identity.externalId).
  - name: Schedules
    description: >-
      Manage scheduled content generation. Organization is inferred from the API
      key (identity.externalId).
  - name: Event Triggers
    description: >-
      Manage event-based content generation triggered by GitHub webhooks.
      Organization is inferred from the API key (identity.externalId).
  - name: Chats
    description: >-
      Manage chat sessions. Organization is inferred from the API key
      (identity.externalId).
  - name: Skills
    description: >-
      Manage reusable writing skills. Organization is inferred from the API key
      (identity.externalId).
  - name: Feedback
    description: >-
      Collect and triage feedback submitted by AI agents. Agents post to the
      organization's feedback URL without credentials; reading and triage
      require an API key with feedback.read or feedback.write.
  - name: GEO
    description: >-
      Manage generative engine optimization: projects, tracking settings,
      prompts, prompt sequences, competitors, scans, visibility reads, content
      gaps and briefs, agent readiness and AI traffic. Project-scoped endpoints
      require the GEO plan entitlement in addition to their scope;
      organization-level ingest endpoints require only the traffic scope.
paths:
  /v2/eve/v1/session/{sessionId}:
    post:
      tags:
        - Agent
      summary: Send a follow-up message or answer a pending input request
      description: >-
        Sends the next turn of an agent session. The server binds the session's
        stored continuation token, so the client-provided one is ignored. Answer
        input.requested events (tool approvals, questions) from the event stream
        via inputResponses.
      operationId: sendAgentSessionMessage
      parameters:
        - schema:
            type: string
            minLength: 1
          required: true
          name: sessionId
          in: path
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SendAgentMessageRequest'
      responses:
        '200':
          description: >-
            Upstream eve response with the next continuation token for this
            session.
          content:
            application/json:
              schema:
                type: object
        '400':
          description: Invalid request body
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Missing or invalid API key
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '403':
          description: Forbidden, or usage limit reached
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '404':
          description: Session not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '409':
          description: A message is already being processed
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '429':
          description: >-
            Rate limit exceeded. This endpoint allows 30 requests per 1 minute
            per organization.
          headers:
            RateLimit-Limit:
              description: Maximum requests allowed in the current window.
              schema:
                type: integer
            RateLimit-Remaining:
              description: Requests remaining in the current window.
              schema:
                type: integer
            RateLimit-Reset:
              description: Seconds until the current window resets.
              schema:
                type: integer
            Retry-After:
              description: Seconds the client should wait before retrying.
              schema:
                type: integer
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RateLimitErrorResponse'
        '500':
          description: Failed to check usage limits
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '503':
          description: Agent service is not configured
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
components:
  schemas:
    SendAgentMessageRequest:
      type: object
      properties:
        message:
          type: string
          minLength: 1
          maxLength: 200000
          description: >-
            The next user message. Omit when only answering a pending input
            request.
        inputResponses:
          type: array
          items:
            type: object
            properties:
              requestId:
                type: string
                minLength: 1
              optionId:
                type: string
                minLength: 1
                description: >-
                  The chosen option id from the input.requested event, e.g.
                  "approve" or "deny".
            required:
              - requestId
              - optionId
          description: >-
            Answers to pending input.requested events (tool approvals,
            questions) from the event stream.
        continuationToken:
          type: string
          minLength: 1
          description: >-
            The continuation token returned by the previous request for this
            session.
      required:
        - continuationToken
    ErrorResponse:
      type: object
      properties:
        error:
          type: string
        code:
          type: string
        recovery:
          type: string
      required:
        - error
    RateLimitErrorResponse:
      type: object
      properties:
        error:
          type: string
        limit:
          type: integer
          minimum: 1
        remaining:
          type: integer
          minimum: 0
        reset:
          type: integer
      required:
        - error
        - limit
        - remaining
        - reset
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API Key
      description: Send your API key in the Authorization header as Bearer API_KEY.

````