> ## Documentation Index > Fetch the complete documentation index at: https://docs.tetherai.ca/llms.txt > Use this file to discover all available pages before exploring further. # Respond to a playground tool approval card > Resolves a playground approval card by approving or rejecting it. Approving executes the requested tool with the originally captured arguments and resumes the playground turn; rejecting stashes a rejection sentinel so the agent acknowledges and moves on. Returns the resumed AI response and any new approval cards. ## OpenAPI ````yaml /api-reference/openapi.yaml post /api/ai/playground/approval/respond openapi: 3.0.3 info: title: Tether Relay and Tether API version: 1.0.0 description: >- Route-derived OpenAPI contract generated from tether-relay backend sources. Regenerate with scripts/sync-openapi-from-backend.mjs. servers: - url: https://your-instance.example.com description: Production - url: http://localhost:2212 description: Local API service security: [] tags: - name: AI - name: Applications - name: Approval - name: Auth - name: Automations - name: Calls - name: Campaigns - name: Contact Analytics - name: Contact Metrics - name: Contact Notes - name: Contacts - name: Conversation Monitor - name: Conversations - name: Departments - name: Email - name: Escalation Dashboard - name: Event Logs - name: Google Sheets - name: Marketplace - name: Messages - name: Notification Sounds - name: Notifications - name: Org Snapshots - name: Organizations - name: Outreach - name: Outreach Metrics - name: Outreach Sources - name: Pipelines - name: Processes - name: Prompts - name: Reminders - name: Sms - name: Templates - name: Traces - name: Training - name: Upload - name: User Snapshots - name: Users - name: Vertical - name: Webchats - name: Webhook paths: /api/ai/playground/approval/respond: post: tags: - AI summary: Respond to a playground tool approval card description: >- Resolves a playground approval card by approving or rejecting it. Approving executes the requested tool with the originally captured arguments and resumes the playground turn; rejecting stashes a rejection sentinel so the agent acknowledges and moves on. Returns the resumed AI response and any new approval cards. operationId: post_ai_playground_approval_respond requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/AIPlaygroundApprovalRespondRequest' responses: '200': description: Approval resolved and playground resumed content: application/json: schema: $ref: '#/components/schemas/AIPlaygroundApprovalRespondResponse' '400': description: Invalid request body content: application/json: schema: $ref: '#/components/schemas/AIErrorResponse' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/AIErrorResponse' '403': description: Approval owner or organization mismatch content: application/json: schema: $ref: '#/components/schemas/AIErrorResponse' '404': description: Approval expired or already handled content: application/json: schema: $ref: '#/components/schemas/AIErrorResponse' '500': description: Failed to resume playground after approval content: application/json: schema: $ref: '#/components/schemas/AIErrorResponse' '503': description: Approval service temporarily unavailable content: application/json: schema: $ref: '#/components/schemas/AIErrorResponse' security: - bearerAuth: [] components: schemas: AIPlaygroundApprovalRespondRequest: type: object properties: approvalKey: type: string description: >- Opaque key for the approval card being resolved. Single-use — consumed atomically; a second call returns `approval_expired`. decision: type: string enum: - approve - reject description: >- `approve` runs the tool with the captured args; `reject` stashes a sentinel so the agent acknowledges and moves on. conversation: type: array description: >- Visible playground history at the moment the user clicked the approval card. Replayed on resume; a synthetic resume note is appended server-side. items: type: object properties: role: type: string enum: - user - assistant content: type: string additionalProperties: true default: [] promptId: type: string description: >- Prompt id used for the original playground turn; the resumed turn re-runs the same prompt so behavior stays consistent. conversationId: type: string description: >- Optional conversation id used for context lookup on the resumed turn; matches the value originally passed to `/api/ai/playground`. promptOverride: type: string description: >- Optional inline prompt text that replaces the saved prompt for this resumed turn — used by editors testing un-saved edits. modelOverride: $ref: '#/components/schemas/AiModelOverride' description: >- Pin the resumed turn to a specific provider/model (e.g. `{ provider: 'anthropic', model: 'claude-sonnet-4-6' }`) overriding the org's default assignment. required: - approvalKey - decision - promptId additionalProperties: true example: approvalKey: playground:5f7b1c2e8a1d4e0012c3b4a5:tool-call-7c2a decision: approve conversation: - role: user content: Please book me for Tuesday at 2pm. - role: assistant content: I will go ahead and request that slot. promptId: 5f7b1c2e8a1d4e0012c3b4a5 conversationId: 64d2f9c5e8a1d4e001a0b1c2 modelOverride: provider: anthropic model: claude-sonnet-4-6 AIPlaygroundApprovalRespondResponse: type: object description: >- Returned after a playground approval is resolved (approve or reject). `response` carries the resumed agent reply; `toolError` flags that the underlying tool execution failed. properties: success: type: boolean enum: - true response: type: string decision: type: string enum: - approve - reject toolError: type: boolean approvalCards: type: array items: $ref: '#/components/schemas/AIApprovalCard' required: - success - response - decision additionalProperties: true example: success: true decision: approve response: Sent! I just texted Alex the confirmation. AIErrorResponse: type: object description: >- Error envelope used across AI endpoints. The `error` field is a stable machine-readable code on approval-related failures (`approval_owner_mismatch`, `approval_org_mismatch`, `approval_expired`, `approval_service_unavailable`) and a human-readable string elsewhere. `message` is set alongside on the approval paths so the UI can render both. properties: success: type: boolean enum: - false error: type: string message: type: string required: - error additionalProperties: true example: success: false error: approval_expired message: >- This approval request has expired or was already handled. Please send a new playground message to retry. AiModelOverride: type: object properties: provider: type: string enum: - anthropic - openai - google model: type: string required: - provider - model additionalProperties: false example: provider: anthropic model: claude-sonnet-4-6 AIApprovalCard: type: object description: >- Pending tool-approval card surfaced by the playground when the agent wants to run a tool that requires sign-off. properties: approvalId: type: string toolName: type: string toolArgs: type: object additionalProperties: true createdAt: type: string format: date-time expiresAt: type: string format: date-time required: - approvalId - toolName additionalProperties: true example: approvalId: apr_64d2f9c5e8a1d4e001a0b1c2 toolName: sendSms toolArgs: phone: '+14165550100' message: Hi Alex — confirming your appointment for Friday at 2pm. createdAt: '2026-05-20T15:04:01.135Z' expiresAt: '2026-05-20T15:09:01.135Z' securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT ````