> ## Documentation Index > Fetch the complete documentation index at: https://docs.threetone.in/llms.txt > Use this file to discover all available pages before exploring further. # Patches An Agent Settings > Patches an Agent settings ## OpenAPI ````yaml /api-reference/openapi.json patch /v1/convai/agents/{agent_id} openapi: 3.1.0 info: title: Threetone API Documentation description: >- This is the documentation for the Threetone API. You can use this API to use our service programmatically with API keys sent in the x-api-key header. You can create and manage API keys in the dashboard at https://threetone.in/app/developers/api-keys. version: '1.0' servers: - url: https://api.threetone.in description: Production security: [] paths: /v1/convai/agents/{agent_id}: patch: tags: - Agents Platform summary: Patches An Agent Settings description: Patches an Agent settings operationId: patch_agent_settings_route parameters: - name: agent_id in: path required: true schema: type: string description: The id of an agent. This is returned on agent creation. examples: - agent_3701k3ttaq12ewp8b7qv5rfyszkz embed: true title: Agent Id description: The id of an agent. This is returned on agent creation. - name: branch_id in: query required: false schema: anyOf: - type: string - type: 'null' description: The ID of the branch to use examples: - agtbrch_0901k4aafjxxfxt93gd841r7tv5t title: Branch Id description: The ID of the branch to use - name: x-api-key in: header required: false schema: anyOf: - type: string - type: 'null' description: >- Your API key for programmatic access. Send it in the x-api-key header; you can create and manage keys from the Developers page. title: X-Api-Key description: >- Your API key for programmatic access. Send it in the x-api-key header; you can create and manage keys from the Developers page. requestBody: content: application/json: schema: $ref: >- #/components/schemas/Body_Patches_an_Agent_settings_v1_convai_agents__agent_id__patch responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/GetAgentResponseModel' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: Body_Patches_an_Agent_settings_v1_convai_agents__agent_id__patch: properties: conversation_config: anyOf: - $ref: '#/components/schemas/ConversationalConfigAuthoringPatch' - type: 'null' description: Conversation configuration for an agent platform_settings: anyOf: - additionalProperties: true type: object - type: 'null' title: Platform Settings description: >- Platform settings for the agent are all settings that aren't related to the conversation orchestration and content. workflow: $ref: '#/components/schemas/AgentWorkflowRequestModel' description: >- Workflow for the agent. This is used to define the flow of the conversation and how the agent interacts with tools. name: anyOf: - type: string - type: 'null' title: Name description: A name to make the agent easier to find examples: - My agent optional: true tags: anyOf: - items: type: string type: array - type: 'null' title: Tags description: Tags to help classify and filter the agent examples: - - Customer Support - Technical Help - Three optional: true version_description: anyOf: - type: string - type: 'null' title: Version Description description: >- Description for this version when publishing changes (only applicable for versioned agents) procedures: anyOf: - additionalProperties: $ref: '#/components/schemas/ProcedureVersionRef' type: object - type: 'null' title: Procedures description: >- Procedure versions to publish, keyed by procedure_id. When provided, this map replaces the procedures from the current draft or branch tip. When omitted or null, unpublished procedure edits are used if present; otherwise, the branch tip's procedures are retained. Pass an empty object to remove all procedures. type: object title: Body_Patches_an_Agent_settings_v1_convai_agents__agent_id__patch GetAgentResponseModel: properties: agent_id: type: string title: Agent Id description: The ID of the agent name: type: string title: Name description: The name of the agent conversation_config: $ref: '#/components/schemas/ConversationalConfigAPIModel-Output' description: The conversation configuration of the agent metadata: $ref: '#/components/schemas/AgentMetadataResponseModel' description: The metadata of the agent platform_settings: $ref: '#/components/schemas/AgentPlatformSettingsResponseModel' description: The platform settings of the agent phone_numbers: items: oneOf: - $ref: '#/components/schemas/GetPhoneNumberManagedPSTNResponseModel' - $ref: '#/components/schemas/GetPhoneNumberSIPTrunkResponseModel' discriminator: propertyName: source_type mapping: managed_pstn: $ref: '#/components/schemas/GetPhoneNumberManagedPSTNResponseModel' sip_trunk: $ref: '#/components/schemas/GetPhoneNumberSIPTrunkResponseModel' type: array title: Phone Numbers description: The phone numbers of the agent whatsapp_accounts: items: $ref: '#/components/schemas/GetWhatsAppAccountResponse' type: array title: Whatsapp Accounts description: WhatsApp accounts assigned to the agent workflow: $ref: '#/components/schemas/AgentWorkflowResponseModel' description: The workflow of the agent access_info: anyOf: - $ref: '#/components/schemas/ResourceAccessInfo' - type: 'null' description: The access information of the agent for the user tags: items: type: string type: array title: Tags description: Agent tags used to categorize the agent version_id: anyOf: - type: string - type: 'null' title: Version Id description: The ID of the version the agent is on branch_id: anyOf: - type: string - type: 'null' title: Branch Id description: The ID of the branch the agent is on main_branch_id: anyOf: - type: string - type: 'null' title: Main Branch Id description: The ID of the main branch for this agent type: object required: - agent_id - name - conversation_config - metadata title: GetAgentResponseModel example: agent_id: agent_4m8q7z2pxn5r9vkt6d3h1c0b name: My Agent workflow: edges: entry_to_tool_a: forward_condition: condition: Tool A condition type: llm source: entry_node target: tool_node_a start_to_entry: forward_condition: type: unconditional source: start_node target: entry_node tool_a_to_failure: forward_condition: successful: false type: result source: tool_node_a target: failure_node tool_a_to_tool_b: forward_condition: successful: true type: result source: tool_node_a target: tool_node_b tool_b_to_agent_transfer: forward_condition: type: unconditional source: tool_node_b target: success_transfer tool_b_to_conversation: forward_condition: condition: Conversation condition type: llm source: tool_node_b target: success_conversation tool_b_to_end: forward_condition: condition: End condition type: llm source: tool_node_b target: success_end tool_b_to_phone: forward_condition: expression: children: - name: force_phone_transfer type: dynamic_variable - prompt: Phone condition type: llm value_schema: description: Phone condition type: boolean - left: name: mode type: dynamic_variable right: type: string_literal value: dev type: eq_operator type: or_operator type: expression source: tool_node_b target: success_phone nodes: entry_node: additional_knowledge_base: [] additional_prompt: '' additional_tool_ids: [] auto_advance_after_first_response: false conversation_config: {} edge_order: - entry_to_tool_a entry_behavior: auto label: Entry position: x: 0 'y': 0 type: override_agent failure_node: additional_knowledge_base: [] additional_prompt: '' additional_tool_ids: [] auto_advance_after_first_response: false conversation_config: {} edge_order: [] entry_behavior: auto label: Failure position: x: 0 'y': 0 type: override_agent start_node: edge_order: - start_to_entry position: x: 0 'y': 0 type: start success_conversation: additional_knowledge_base: [] additional_prompt: '' additional_tool_ids: [] auto_advance_after_first_response: false conversation_config: {} edge_order: [] entry_behavior: auto label: Success A position: x: 0 'y': 0 type: override_agent success_end: edge_order: [] position: x: 0 'y': 0 type: end success_phone: custom_sip_headers: [] edge_order: [] position: x: 0 'y': 0 require_acceptance: false transfer_destination: phone_number: '+1234567890' type: phone transfer_type: conference type: phone_number success_transfer: agent_id: success_transfer_agent delay_ms: 0 edge_order: [] enable_transferred_agent_first_message: false position: x: 0 'y': 0 type: standalone_agent tool_node_a: edge_order: - tool_a_to_failure - tool_a_to_tool_b position: x: 0 'y': 0 tools: - tool_id: tool_a - tool_id: tool_b type: tool tool_node_b: edge_order: - tool_b_to_conversation - tool_b_to_end - tool_b_to_phone - tool_b_to_agent_transfer position: x: 0 'y': 0 tools: - tool_id: tool_a type: tool prevent_subagent_loops: false HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ConversationalConfigAuthoringPatch: properties: turn: anyOf: - $ref: '#/components/schemas/TurnConfigWorkflowOverride' - type: 'null' description: Configuration for turn detection tts: anyOf: - $ref: '#/components/schemas/TTSConversationalConfigPatch' - type: 'null' description: Sparse text-to-speech authoring changes. conversation: anyOf: - $ref: '#/components/schemas/ConversationConfigWorkflowOverride' - type: 'null' description: Configuration for conversational events language_presets: anyOf: - additionalProperties: $ref: '#/components/schemas/LanguagePreset' type: object - type: 'null' title: Language Presets description: Language presets for conversations vad: anyOf: - $ref: '#/components/schemas/VADConfigWorkflowOverride' - type: 'null' description: Configuration for voice activity detection agent: anyOf: - $ref: '#/components/schemas/AgentConfigAPIModelWorkflowOverride-Input' - type: 'null' description: Agent specific configuration asr: anyOf: - $ref: '#/components/schemas/ASRConversationalConfigPatch' - type: 'null' description: Sparse speech-recognition authoring changes. additionalProperties: false type: object title: ConversationalConfigAuthoringPatch description: Strict sparse patch for branch and agent authoring endpoints. example: agent: disable_first_message_interruptions: false dynamic_variables: dynamic_variable_placeholders: user_name: John Doe first_message: Hello, how can I help you today? language: en prompt: knowledge_base: [] llm: gemini-2.0-flash-001 max_tokens: -1 prompt: >- You are a helpful assistant that can answer questions about the topic of the conversation. temperature: 0 tool_ids: [] conversation: client_events: - audio - interruption max_duration_seconds: 600 tts: performance: latency voice_id: ME9RtCnWp5vX2LhJdF3k turn: interruption_ignore_term_languages: [] interruption_ignore_terms: [] merge_with_default_ignore_terms: false mode: turn retranscribe_on_turn_timeout: false silence_end_call_timeout: -1 soft_timeout_config: message: Hhmmmm...yeah. timeout_seconds: -1 use_llm_generated_message: false speculative_turn: false spelling_patience: auto transcribe_on_disabled_interruptions: false turn_eagerness: normal turn_model: turn_v3 turn_timeout: 7 AgentWorkflowRequestModel: properties: edges: additionalProperties: $ref: '#/components/schemas/WorkflowEdgeModel-Input' type: object title: Edges nodes: additionalProperties: oneOf: - $ref: '#/components/schemas/WorkflowStartNodeModel-Input' description: Entry point of the workflow. - $ref: '#/components/schemas/WorkflowEndNodeModel-Input' description: Terminates the conversation upon reaching this node. - $ref: '#/components/schemas/WorkflowPhoneNumberNodeModel-Input' description: Transfers the conversation to a phone number. - $ref: '#/components/schemas/WorkflowOverrideAgentNodeModel-Input' description: >- A subagent conducting the conversation until one of the exit conditions is met. Each subagent can override the base settings, changing the prompt, knowledge base, and more. - $ref: '#/components/schemas/WorkflowStandaloneAgentNodeModel-Input' description: Transfer the conversation to a standalone agent. - $ref: '#/components/schemas/WorkflowToolNodeModel-Input' description: Executes one or more tools in parallel. discriminator: propertyName: type mapping: end: $ref: '#/components/schemas/WorkflowEndNodeModel-Input' override_agent: $ref: '#/components/schemas/WorkflowOverrideAgentNodeModel-Input' phone_number: $ref: '#/components/schemas/WorkflowPhoneNumberNodeModel-Input' standalone_agent: $ref: '#/components/schemas/WorkflowStandaloneAgentNodeModel-Input' start: $ref: '#/components/schemas/WorkflowStartNodeModel-Input' tool: $ref: '#/components/schemas/WorkflowToolNodeModel-Input' type: object title: Nodes prevent_subagent_loops: type: boolean title: Prevent Subagent Loops description: Whether to prevent loops in the workflow execution. default: false additionalProperties: false type: object title: AgentWorkflowRequestModel example: edges: start_to_support: forward_condition: type: unconditional source: start_node target: support support_to_end: forward_condition: condition: The request is resolved type: llm source: support target: end nodes: end: type: end start_node: edge_order: - start_to_support type: start support: edge_order: - support_to_end label: Support type: override_agent ProcedureVersionRef: properties: procedure_id: type: string title: Procedure Id description: Procedure ID version_id: type: string title: Version Id description: Version ID of the procedure version. additionalProperties: false type: object required: - procedure_id - version_id title: ProcedureVersionRef ConversationalConfigAPIModel-Output: properties: schema_version: anyOf: - type: integer const: 2 - type: 'null' title: Schema Version description: >- Version 2 identifies a strictly authored conversation document; null identifies legacy data. asr: anyOf: - $ref: '#/components/schemas/ASRConversationalConfig' - type: 'null' description: >- Speech-recognition selection. It may be absent only for legacy agents whose runtime selection has not yet been migrated to the catalog. turn: $ref: '#/components/schemas/TurnConfig' description: Configuration for turn detection tts: $ref: '#/components/schemas/TTSConversationalConfig-Output' description: Configuration for conversational text to speech conversation: $ref: '#/components/schemas/ConversationConfig' description: Configuration for conversational events language_presets: additionalProperties: $ref: '#/components/schemas/LanguagePreset' type: object title: Language Presets description: Language presets for conversations vad: $ref: '#/components/schemas/VADConfig' description: Configuration for voice activity detection agent: $ref: '#/components/schemas/AgentConfigAPIModel-Output' description: Agent specific configuration type: object title: ConversationalConfigAPIModel AgentMetadataResponseModel: properties: created_at_unix_secs: type: integer title: Created At Unix Secs description: The creation time of the agent in unix seconds updated_at_unix_secs: type: integer title: Updated At Unix Secs description: The last update time of the agent in unix seconds type: object required: - created_at_unix_secs - updated_at_unix_secs title: AgentMetadataResponseModel AgentPlatformSettingsResponseModel: properties: evaluation: $ref: '#/components/schemas/EvaluationSettings' description: Settings for evaluation widget: $ref: '#/components/schemas/WidgetConfig' description: Configuration for the widget data_collection: additionalProperties: $ref: '#/components/schemas/AnalysisProperty' type: object title: Data Collection description: Data collection settings data_collection_scopes: additionalProperties: $ref: '#/components/schemas/AnalysisScope' type: object title: Data Collection Scopes description: >- Scope per data collection item ID. Missing keys default to conversation scope. analysis_items: anyOf: - $ref: '#/components/schemas/AgentAnalysisItems' - type: 'null' description: >- Evaluation + data-collection items attached by reference. None means the agent has not been migrated onto analysis items yet (distinct from an empty, migrated set); reads fall back to the legacy evaluation/data_collection fields in that case. overrides: $ref: '#/components/schemas/ConversationInitiationClientDataConfig' description: Additional overrides for the agent during conversation initiation workspace_overrides: $ref: '#/components/schemas/AgentWorkspaceOverrides' description: Workspace overrides for the agent testing: $ref: '#/components/schemas/AgentTestingSettings' description: Testing configuration for the agent archived: type: boolean title: Archived description: Whether the agent is archived default: false guardrails: $ref: '#/components/schemas/GuardrailsV1' title: Guardrails description: Guardrails configuration for the agent discriminator: propertyName: version mapping: '1': '#/components/schemas/GuardrailsV1' summary_language: anyOf: - type: string - type: 'null' title: Summary Language description: >- Language for all conversation analysis outputs (summaries, titles, evaluation rationales, data collection rationales). If not set, the language will be inferred from the conversation. Must be one of the supported conversation languages. auto_translate_transcript_to_app_language: anyOf: - type: boolean - type: 'null' title: Auto Translate Transcript To App Language description: >- When enabled, a conversation transcript is automatically translated to the viewer's application language when they open the transcript page. If not set or false, transcripts are shown in their original language unless the viewer manually selects a translation. auth: $ref: '#/components/schemas/AuthSettings' description: Settings for authentication call_limits: $ref: '#/components/schemas/AgentCallLimits' description: Call limits for the agent privacy: $ref: '#/components/schemas/PrivacyConfig' description: Privacy settings for the agent trust_context: $ref: '#/components/schemas/AgentTrustContext' description: The trust context in which the agent operates. default: unknown analysis_llm: $ref: '#/components/schemas/LLM' description: >- Default LLM model for post-call analysis (evaluation and data collection) default: gemini-2.5-flash topic_discovery: $ref: '#/components/schemas/TopicDiscoverySettings' description: Per-agent topic discovery configuration sentiment_analysis: $ref: '#/components/schemas/SentimentAnalysisSettings' description: Per-agent post-call sentiment analysis configuration alerting: anyOf: - $ref: '#/components/schemas/AlertingSettingsResponse' - type: 'null' description: Agent-level alerting configuration overriding workspace settings. safety: $ref: '#/components/schemas/SafetyResponseModel' type: object title: AgentPlatformSettingsResponseModel GetPhoneNumberManagedPSTNResponseModel: properties: phone_number: type: string title: Phone Number description: Phone number label: type: string title: Label description: Label for the phone number phone_number_id: type: string title: Phone Number Id description: The ID of the phone number assigned_agent: anyOf: - $ref: '#/components/schemas/PhoneNumberAgentInfo' - type: 'null' description: The agent that is assigned to the phone number source_type: type: string const: managed_pstn title: Source Type description: >- Phone number source type. Managed PSTN numbers are fulfilled internally by Threetone. default: managed_pstn fulfillment_provider: $ref: '#/components/schemas/PhoneNumberFulfillmentProvider' description: Backend fulfillment provider for this managed PSTN number type: object required: - phone_number - label - phone_number_id - fulfillment_provider title: GetPhoneNumberManagedPSTNResponseModel example: fulfillment_provider: twilio label: Customer Support phone_number: '+1234567890' phone_number_id: phone_123 source_type: managed_pstn GetPhoneNumberSIPTrunkResponseModel: properties: phone_number: type: string title: Phone Number description: Phone number label: type: string title: Label description: Label for the phone number phone_number_id: type: string title: Phone Number Id description: The ID of the phone number assigned_agent: anyOf: - $ref: '#/components/schemas/PhoneNumberAgentInfo' - type: 'null' description: The agent that is assigned to the phone number provider: type: string const: sip_trunk title: Provider description: Phone provider default: sip_trunk source_type: type: string const: sip_trunk title: Source Type description: Phone number source type default: sip_trunk outbound_trunk: anyOf: - $ref: >- #/components/schemas/GetPhoneNumberOutboundSIPTrunkConfigResponseModel - type: 'null' description: Configuration of the Outbound SIP trunk - if configured. inbound_trunk: anyOf: - $ref: >- #/components/schemas/GetPhoneNumberInboundSIPTrunkConfigResponseModel - type: 'null' description: Configuration of the Inbound SIP trunk - if configured. livekit_stack: $ref: '#/components/schemas/LivekitStackType' description: Type of Livekit stack used for this number. store_sip_messages: type: boolean title: Store Sip Messages description: Whether to store SIP messages for this phone number. default: true type: object required: - phone_number - label - phone_number_id - livekit_stack title: GetPhoneNumberSIPTrunkResponseModel description: >- SIP-trunk-backed phone number row. Inbound/outbound capability is implied by `inbound_trunk` / `outbound_trunk` (and related flags), not by separate booleans. example: label: Sales Team livekit_stack: standard phone_number: '+1987654321' phone_number_id: phone_456 source_type: sip_trunk GetWhatsAppAccountResponse: properties: business_account_id: type: string title: Business Account Id phone_number_id: type: string title: Phone Number Id business_account_name: type: string title: Business Account Name phone_number_name: type: string title: Phone Number Name phone_number: type: string title: Phone Number account_type: type: string const: cloud_api title: Account Type description: Which Embedded Signup flow produced this account. default: cloud_api assigned_agent_id: anyOf: - type: string - type: 'null' title: Assigned Agent Id enable_messaging: type: boolean title: Enable Messaging default: true enable_audio_message_response: type: boolean title: Enable Audio Message Response default: true enable_typing_indicator: type: boolean title: Enable Typing Indicator default: true assigned_agent_name: anyOf: - type: string - type: 'null' title: Assigned Agent Name is_token_expired: type: boolean title: Is Token Expired default: false registration_status: $ref: '#/components/schemas/WhatsAppRegistrationStatus' title: Registration Status type: object required: - business_account_id - phone_number_id - business_account_name - phone_number_name - phone_number - assigned_agent_name - registration_status title: GetWhatsAppAccountResponse AgentWorkflowResponseModel: properties: edges: additionalProperties: $ref: '#/components/schemas/WorkflowEdgeModel-Output' type: object title: Edges nodes: additionalProperties: oneOf: - $ref: '#/components/schemas/WorkflowStartNodeModel-Output' description: Entry point of the workflow. - $ref: '#/components/schemas/WorkflowEndNodeModel-Output' description: Terminates the conversation upon reaching this node. - $ref: '#/components/schemas/WorkflowPhoneNumberNodeModel-Output' description: Transfers the conversation to a phone number. - $ref: '#/components/schemas/WorkflowOverrideAgentNodeModel-Output' description: >- A subagent conducting the conversation until one of the exit conditions is met. Each subagent can override the base settings, changing the prompt, knowledge base, and more. - $ref: '#/components/schemas/WorkflowStandaloneAgentNodeModel-Output' description: Transfer the conversation to a standalone agent. - $ref: '#/components/schemas/WorkflowToolNodeModel-Output' description: Executes one or more tools in parallel. discriminator: propertyName: type mapping: end: $ref: '#/components/schemas/WorkflowEndNodeModel-Output' override_agent: $ref: '#/components/schemas/WorkflowOverrideAgentNodeModel-Output' phone_number: $ref: '#/components/schemas/WorkflowPhoneNumberNodeModel-Output' standalone_agent: $ref: '#/components/schemas/WorkflowStandaloneAgentNodeModel-Output' start: $ref: '#/components/schemas/WorkflowStartNodeModel-Output' tool: $ref: '#/components/schemas/WorkflowToolNodeModel-Output' type: object title: Nodes prevent_subagent_loops: type: boolean title: Prevent Subagent Loops description: Whether to prevent loops in the workflow execution. default: false type: object required: - edges - nodes - prevent_subagent_loops title: AgentWorkflowResponseModel example: edges: start_to_support: forward_condition: type: unconditional source: start_node target: support support_to_end: forward_condition: condition: The request is resolved type: llm source: support target: end nodes: end: edge_order: [] position: x: 0 'y': 0 type: end start_node: edge_order: - start_to_support position: x: 0 'y': 0 type: start support: additional_knowledge_base: [] additional_prompt: '' additional_tool_ids: [] conversation_config: {} edge_order: - support_to_end entry_behavior: auto label: Support position: x: 0 'y': 0 type: override_agent prevent_subagent_loops: false ResourceAccessInfo: properties: is_creator: type: boolean title: Is Creator description: Whether the user making the request is the creator of the agent creator_name: type: string title: Creator Name description: Name of the agent's creator creator_email: type: string title: Creator Email description: Email of the agent's creator role: type: string enum: - admin - editor - commenter - viewer title: Role description: The role of the user making the request anonymous_access_level_override: anyOf: - type: string enum: - admin - editor - commenter - viewer - type: 'null' title: Anonymous Access Level Override description: >- The access level for anonymous users. If None, the resource is not shared publicly. access_source: anyOf: - type: string enum: - creator - explicit - workspace_admin - workspace_default - type: 'null' title: Access Source description: >- Why the requesting user has access to this resource. 'creator' = caller is the owner. 'explicit' = caller (or one of their workspace groups) is listed in role_to_group_ids beyond the workspace-wide everyone group. 'workspace_default' = the workspace-wide everyone group is listed in role_to_group_ids (every non-anon workspace member, including admins, sees this resource). 'workspace_admin' = caller is a workspace admin and the admin seat is the *only* path to access; reserved for docs nobody else can see. Lets the UI disclose why an admin-bypass viewer sees a doc that wasn't explicitly shared with them. type: object required: - is_creator - creator_name - creator_email - role title: ResourceAccessInfo example: access_source: creator creator_email: john.doe@example.com creator_name: John Doe is_creator: true role: admin ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError TurnConfigWorkflowOverride: properties: turn_timeout: anyOf: - type: number - type: 'null' title: Turn Timeout description: Maximum wait time for the user's reply before re-engaging the user initial_wait_time: anyOf: - type: number - type: 'null' title: Initial Wait Time description: >- How long the agent will wait for the user to start the conversation if the first message is empty. If not set, uses the regular turn_timeout. silence_end_call_timeout: anyOf: - type: number - type: 'null' title: Silence End Call Timeout description: >- Maximum wait time since the user last spoke before terminating the call mode: anyOf: - $ref: '#/components/schemas/TurnMode' - type: 'null' description: The mode of turn detection x-fern-ignore: true turn_eagerness: anyOf: - $ref: '#/components/schemas/TurnEagerness' - type: 'null' description: >- Controls how eager the agent is to respond. Low = less eager (waits longer), Standard = default eagerness, High = more eager (responds sooner) spelling_patience: anyOf: - $ref: '#/components/schemas/SpellingPatience' - type: 'null' description: >- Controls if the agent should be more patient when user is spelling numbers and named entities. Auto = model based, Off = never wait extra speculative_turn: anyOf: - type: boolean - type: 'null' title: Speculative Turn description: >- When enabled, starts generating LLM responses during silence before full turn confidence is reached, reducing perceived latency. May increase LLM costs. retranscribe_on_turn_timeout: anyOf: - type: boolean - type: 'null' title: Retranscribe On Turn Timeout description: >- When enabled, if VAD detects no speech, attempts to re-transcribe accumulated audio at turn timeout. Disables silence discount billing for affected turns. turn_model: anyOf: - $ref: '#/components/schemas/TurnModel' - type: 'null' description: Version of the turn detection model to use. interruption_ignore_terms: anyOf: - items: type: string type: array - type: 'null' title: Interruption Ignore Terms description: >- List of terms that should not trigger an interruption when spoken by the user (e.g. 'gotcha', 'understood'). Uses case-insensitive exact matching. interruption_ignore_term_languages: anyOf: - items: type: string type: array - type: 'null' title: Interruption Ignore Term Languages description: >- Language codes for which preset ignore-term categories have been activated. Stored explicitly so display is not inferred from term overlap. merge_with_default_ignore_terms: anyOf: - type: boolean - type: 'null' title: Merge With Default Ignore Terms description: >- When enabled, the curated default terms for interruption_ignore_term_languages are used in addition to interruption_ignore_terms. transcribe_on_disabled_interruptions: anyOf: - type: boolean - type: 'null' title: Transcribe On Disabled Interruptions description: >- When interruptions are disabled, still transcribe what the user says so it can carry into the next turn. When off, user speech during a non-interruptible turn is ignored and won't trigger a turn. soft_timeout_config: anyOf: - $ref: '#/components/schemas/SoftTimeoutConfigWorkflowOverride' - type: 'null' description: >- Configuration for soft timeout functionality. Provides immediate feedback during longer LLM responses. type: object title: TurnConfigWorkflowOverride example: interruption_ignore_term_languages: [] interruption_ignore_terms: [] merge_with_default_ignore_terms: false mode: turn retranscribe_on_turn_timeout: false silence_end_call_timeout: -1 soft_timeout_config: message: Hhmmmm...yeah. timeout_seconds: -1 use_llm_generated_message: false speculative_turn: false spelling_patience: auto transcribe_on_disabled_interruptions: false turn_eagerness: normal turn_model: turn_v3 turn_timeout: 7 TTSConversationalConfigPatch: properties: voice_id: anyOf: - type: string - type: 'null' title: Voice Id description: The voice ID to use for TTS performance: anyOf: - $ref: '#/components/schemas/TTSPerformance' - type: 'null' description: >- User-facing TTS performance tier (latency or quality). The concrete provider/model is selected by the voice-server based on this value. pronunciation_dictionary_locators: anyOf: - items: $ref: >- #/components/schemas/PydanticPronunciationDictionaryVersionLocator type: array - type: 'null' title: Pronunciation Dictionary Locators description: The pronunciation dictionary locators x-convai-client-override: true enable_phoneme_tags: anyOf: - type: boolean - type: 'null' title: Enable Phoneme Tags description: >- Opt-in to SSML phoneme tag handling. When enabled, phoneme tags from inline content and pronunciation dictionaries may be normalized before synthesis when the selected provider supports them. model_id: anyOf: - type: string maxLength: 128 minLength: 5 pattern: ^tts\.[a-z0-9][a-z0-9._:-]*$ description: Stable Threetone TTS catalog model identifier. - type: 'null' title: Model Id description: >- Stable Threetone TTS catalog model ID; null clears an unpublished selection. options: anyOf: - oneOf: - $ref: >- #/components/schemas/CartesiaSonic36LiveKitInferenceTTSOptions - $ref: '#/components/schemas/SarvamBulbulV3LiveKitPluginTTSOptions' discriminator: propertyName: adapter_contract mapping: livekit_inference_cartesia_sonic_3_6_2026_08_27_v1: $ref: >- #/components/schemas/CartesiaSonic36LiveKitInferenceTTSOptions livekit_plugin_python_sarvam_bulbul_v3_v1: $ref: '#/components/schemas/SarvamBulbulV3LiveKitPluginTTSOptions' - type: 'null' title: Options description: >- Validated options for the selected catalog model; null clears existing options. additionalProperties: false type: object title: TTSConversationalConfigPatch description: Sparse TTS authoring patch kept separate from workflow overrides. example: performance: latency voice_id: ME9RtCnWp5vX2LhJdF3k ConversationConfigWorkflowOverride: properties: text_only: anyOf: - type: boolean - type: 'null' title: Text Only description: >- If enabled audio will not be processed and only text will be used, use to avoid audio pricing. x-convai-client-override: true max_duration_seconds: anyOf: - type: integer - type: 'null' title: Max Duration Seconds description: The maximum duration of a conversation in seconds x-convai-client-override: true client_events: anyOf: - items: $ref: '#/components/schemas/ClientEvent' type: array - type: 'null' title: Client Events description: The events that will be sent to the client file_input: anyOf: - $ref: '#/components/schemas/FileInputConfigWorkflowOverride' - type: 'null' description: >- Configuration for file input (image/PDF uploads) during conversations. x-convai-client-override: true monitoring_enabled: anyOf: - type: boolean - type: 'null' title: Monitoring Enabled description: Enable real-time monitoring of conversations via WebSocket monitoring_events: anyOf: - items: $ref: '#/components/schemas/ClientEvent' type: array - type: 'null' title: Monitoring Events description: The events that will be sent to monitoring connections. dtmf_input_settings: anyOf: - $ref: '#/components/schemas/DTMFInputConfig' - type: 'null' description: Configure DTMF (keypad) input collection during phone calls background_sound: anyOf: - $ref: '#/components/schemas/BackgroundSoundConfigWorkflowOverride' - type: 'null' description: Configuration for background sound during conversations. source_attribution: anyOf: - type: boolean - type: 'null' title: Source Attribution description: >- When enabled and knowledge base content is present, the LLM is instructed to report which sources it used. type: object title: ConversationConfigWorkflowOverride example: client_events: - audio - interruption max_duration_seconds: 600 LanguagePreset: properties: overrides: $ref: '#/components/schemas/ConversationConfigClientOverride' description: The overrides for the language preset first_message_translation: anyOf: - $ref: '#/components/schemas/LanguagePresetTranslation' - type: 'null' description: The translation of the first message soft_timeout_translation: anyOf: - $ref: '#/components/schemas/LanguagePresetTranslation' - type: 'null' description: The translation of the soft timeout message type: object required: - overrides title: LanguagePreset VADConfigWorkflowOverride: properties: background_voice_detection: anyOf: - type: boolean - type: 'null' title: Background Voice Detection description: Whether to use background voice filtering x-fern-ignore: true type: object title: VADConfigWorkflowOverride example: background_voice_detection: false AgentConfigAPIModelWorkflowOverride-Input: properties: first_message: anyOf: - type: string - type: 'null' title: First Message description: >- If non-empty, the first message the agent will say. If empty, the agent waits for the user to start the discussion. x-convai-client-override: true x-convai-language-override: true language: anyOf: - type: string - type: 'null' title: Language description: Language of the agent - used for ASR and TTS x-convai-client-override: true dynamic_variables: anyOf: - $ref: >- #/components/schemas/DynamicVariablesConfigWorkflowOverride-Input - type: 'null' description: Configuration for dynamic variables disable_first_message_interruptions: anyOf: - type: boolean - type: 'null' title: Disable First Message Interruptions description: >- If true, the user will not be able to interrupt the agent while the first message is being delivered. max_conversation_duration_message: anyOf: - type: string - type: 'null' title: Max Conversation Duration Message description: >- If non-empty, the message the agent will send when max conversation duration is reached. x-convai-client-override: true x-convai-language-override: true text_behavior_overrides: anyOf: - additionalProperties: $ref: '#/components/schemas/BehaviorOverride' propertyNames: $ref: '#/components/schemas/ConversationInitiationSource' type: object - type: 'null' title: Text Behavior Overrides description: >- Per-channel response behavior overrides for text conversations. Built-in channel defaults apply when unset. prompt: anyOf: - $ref: '#/components/schemas/PromptAgentAPIModelWorkflowOverride-Input' - type: 'null' description: The prompt for the agent type: object title: AgentConfigAPIModelWorkflowOverride example: disable_first_message_interruptions: false dynamic_variables: dynamic_variable_placeholders: user_name: John Doe first_message: Hello, how can I help you today? language: en prompt: knowledge_base: [] llm: gemini-2.0-flash-001 max_tokens: -1 prompt: >- You are a helpful assistant that can answer questions about the topic of the conversation. temperature: 0 tool_ids: [] ASRConversationalConfigPatch: properties: model_id: anyOf: - type: string maxLength: 128 minLength: 5 pattern: ^asr\.[a-z0-9][a-z0-9._:-]*$ description: Stable Threetone ASR catalog model identifier. - type: 'null' title: Model Id recognition: anyOf: - oneOf: - $ref: '#/components/schemas/ASRFixedRecognition' - $ref: '#/components/schemas/ASRAutomaticAgentLanguagesRecognition' - $ref: >- #/components/schemas/ASRAutomaticProviderLanguagesRecognition discriminator: propertyName: mode mapping: automatic_agent_languages: $ref: '#/components/schemas/ASRAutomaticAgentLanguagesRecognition' automatic_provider_languages: $ref: >- #/components/schemas/ASRAutomaticProviderLanguagesRecognition fixed: $ref: '#/components/schemas/ASRFixedRecognition' - type: 'null' title: Recognition task: anyOf: - $ref: '#/components/schemas/ASRTranscriptTask' - type: 'null' keyterms: anyOf: - items: type: string type: array - type: 'null' title: Keyterms options: anyOf: - oneOf: - $ref: '#/components/schemas/CartesiaInk2LiveKitInferenceASROptions' - $ref: >- #/components/schemas/CartesiaInkWhisperLiveKitInferenceASROptions - $ref: '#/components/schemas/SarvamSaarasV4DirectRealtimeASROptions' discriminator: propertyName: adapter_contract mapping: livekit_inference_cartesia_ink_2_v1: $ref: >- #/components/schemas/CartesiaInk2LiveKitInferenceASROptions livekit_inference_cartesia_ink_whisper_v1: $ref: >- #/components/schemas/CartesiaInkWhisperLiveKitInferenceASROptions sarvam_direct_realtime_saaras_v4_2026_09_v1: $ref: >- #/components/schemas/SarvamSaarasV4DirectRealtimeASROptions - type: 'null' title: Options additionalProperties: false type: object title: ASRConversationalConfigPatch description: Sparse ASR authoring patch; compatibility is checked after merge. WorkflowEdgeModel-Input: properties: source: type: string title: Source description: ID of the source node. target: type: string title: Target description: ID of the target node. forward_condition: anyOf: - oneOf: - $ref: '#/components/schemas/WorkflowUnconditionalModel' description: Condition that is always true. - $ref: '#/components/schemas/WorkflowLLMConditionModel' description: >- Condition described using human language and evaluated by an LLM. - $ref: '#/components/schemas/WorkflowResultConditionModel' description: >- Condition based on the result of the last executed tool dispatch node. - $ref: '#/components/schemas/WorkflowExpressionConditionModel-Input' description: Condition described using a deterministic expression. discriminator: propertyName: type mapping: expression: $ref: >- #/components/schemas/WorkflowExpressionConditionModel-Input llm: $ref: '#/components/schemas/WorkflowLLMConditionModel' result: $ref: '#/components/schemas/WorkflowResultConditionModel' unconditional: $ref: '#/components/schemas/WorkflowUnconditionalModel' - type: 'null' title: Forward Condition description: >- Condition that must be met for the edge to be traversed in the forward direction (source to target). backward_condition: anyOf: - oneOf: - $ref: '#/components/schemas/WorkflowUnconditionalModel' description: Condition that is always true. - $ref: '#/components/schemas/WorkflowLLMConditionModel' description: >- Condition described using human language and evaluated by an LLM. - $ref: '#/components/schemas/WorkflowResultConditionModel' description: >- Condition based on the result of the last executed tool dispatch node. - $ref: '#/components/schemas/WorkflowExpressionConditionModel-Input' description: Condition described using a deterministic expression. discriminator: propertyName: type mapping: expression: $ref: >- #/components/schemas/WorkflowExpressionConditionModel-Input llm: $ref: '#/components/schemas/WorkflowLLMConditionModel' result: $ref: '#/components/schemas/WorkflowResultConditionModel' unconditional: $ref: '#/components/schemas/WorkflowUnconditionalModel' - type: 'null' title: Backward Condition description: >- Condition that must be met for the edge to be traversed in the backward direction (target to source). type: object required: - source - target title: WorkflowEdgeModel WorkflowStartNodeModel-Input: properties: type: type: string const: start title: Type default: start position: $ref: '#/components/schemas/Position-Input' description: Position of the node in the workflow. edge_order: items: type: string type: array title: Edge Order description: The ids of outgoing edges in the order they should be evaluated. type: object title: WorkflowStartNodeModel WorkflowEndNodeModel-Input: properties: type: type: string const: end title: Type default: end position: $ref: '#/components/schemas/Position-Input' description: Position of the node in the workflow. edge_order: items: type: string type: array title: Edge Order description: The ids of outgoing edges in the order they should be evaluated. type: object title: WorkflowEndNodeModel WorkflowPhoneNumberNodeModel-Input: properties: custom_sip_headers: items: oneOf: - $ref: '#/components/schemas/CustomSIPHeader' - $ref: '#/components/schemas/CustomSIPHeaderWithDynamicVariable' discriminator: propertyName: type mapping: dynamic: $ref: '#/components/schemas/CustomSIPHeaderWithDynamicVariable' static: $ref: '#/components/schemas/CustomSIPHeader' type: array maxItems: 20 title: Custom Sip Headers description: >- Custom SIP headers to include when transferring the call. Each header can be either a static value or a dynamic variable reference. transfer_destination: oneOf: - $ref: '#/components/schemas/PhoneNumberTransferDestination' - $ref: '#/components/schemas/SIPUriTransferDestination' - $ref: >- #/components/schemas/PhoneNumberDynamicVariableTransferDestination - $ref: '#/components/schemas/SIPUriDynamicVariableTransferDestination' title: Transfer Destination discriminator: propertyName: type mapping: phone: $ref: '#/components/schemas/PhoneNumberTransferDestination' phone_dynamic_variable: $ref: >- #/components/schemas/PhoneNumberDynamicVariableTransferDestination sip_uri: $ref: '#/components/schemas/SIPUriTransferDestination' sip_uri_dynamic_variable: $ref: '#/components/schemas/SIPUriDynamicVariableTransferDestination' transfer_type: $ref: '#/components/schemas/TransferTypeEnum' default: conference sip_refer_play_dialtone: type: boolean title: Sip Refer Play Dialtone description: >- When True, a ringing tone is played on the original call leg while a SIP REFER transfer completes. The tone is carried over RTP to the SIP peer executing the REFER, so disable this if the receiving system (e.g. an SBC or contact center) should not hear it. When disabled the caller hears silence until the transfer completes. SIP REFER transfers only. default: true uui: anyOf: - $ref: '#/components/schemas/UUITransferConfig' - type: 'null' description: >- User-to-User Information (RFC 7433) to attach to SIP REFER transfers. Carries call context such as CRM identifiers or escalation reason across the transfer boundary. post_dial_digits: anyOf: - oneOf: - $ref: '#/components/schemas/PostDialDigitsStatic' - $ref: '#/components/schemas/PostDialDigitsDynamicVariable' discriminator: propertyName: type mapping: dynamic: $ref: '#/components/schemas/PostDialDigitsDynamicVariable' static: $ref: '#/components/schemas/PostDialDigitsStatic' - type: 'null' title: Post Dial Digits description: >- DTMF digits to send after call connects (e.g., 'ww1234' for extension). Can be either a static value or a dynamic variable reference. Use 'w' for 0.5s pause. Only supported for Twilio transfers. type: type: string const: phone_number title: Type default: phone_number position: $ref: '#/components/schemas/Position-Input' description: Position of the node in the workflow. edge_order: items: type: string type: array title: Edge Order description: The ids of outgoing edges in the order they should be evaluated. type: object required: - transfer_destination title: WorkflowPhoneNumberNodeModel WorkflowOverrideAgentNodeModel-Input: properties: type: type: string const: override_agent title: Type default: override_agent position: $ref: '#/components/schemas/Position-Input' description: Position of the node in the workflow. edge_order: items: type: string type: array title: Edge Order description: The ids of outgoing edges in the order they should be evaluated. conversation_config: $ref: >- #/components/schemas/ConversationalConfigAPIModelWorkflowOverride-Input description: >- Configuration overrides applied while the subagent is conducting the conversation. additional_prompt: type: string title: Additional Prompt description: >- Specific goal for this subagent. It will be added to the system prompt and can be used to further refine the agent's behavior in this specific context. additional_knowledge_base: items: $ref: '#/components/schemas/KnowledgeBaseLocator' type: array title: Additional Knowledge Base description: >- Additional knowledge base documents that the subagent has access to. These will be used in addition to the main agent's documents. additional_tool_ids: items: type: string type: array title: Additional Tool Ids description: >- IDs of additional tools that the subagent has access to. These will be used in addition to the main agent's tools. label: type: string title: Label description: Human-readable label for the node used throughout the UI. entry_behavior: $ref: '#/components/schemas/EntryBehavior' description: >- Dictates whether this node should immediately generate a response upon entry or wait for the user input. When set to "auto", the behavior will be decided based on the type of the preceding node: "wait_for_user" after the "say" and "start" nodes and "generate_immediately" otherwise. default: auto type: object required: - label title: WorkflowOverrideAgentNodeModel WorkflowStandaloneAgentNodeModel-Input: properties: type: type: string const: standalone_agent title: Type default: standalone_agent position: $ref: '#/components/schemas/Position-Input' description: Position of the node in the workflow. edge_order: items: type: string type: array title: Edge Order description: The ids of outgoing edges in the order they should be evaluated. agent_id: type: string title: Agent Id description: The ID of the agent to transfer the conversation to. delay_ms: type: integer title: Delay Ms description: >- Artificial delay in milliseconds applied before transferring the conversation. default: 0 transfer_message: anyOf: - type: string - type: 'null' title: Transfer Message description: Optional message sent to the user before the transfer is initiated. enable_transferred_agent_first_message: type: boolean title: Enable Transferred Agent First Message description: >- Whether to enable the transferred agent to send its configured first message after the transfer. default: false type: object required: - agent_id title: WorkflowStandaloneAgentNodeModel WorkflowToolNodeModel-Input: properties: type: type: string const: tool title: Type default: tool position: $ref: '#/components/schemas/Position-Input' description: Position of the node in the workflow. edge_order: items: type: string type: array title: Edge Order description: The ids of outgoing edges in the order they should be evaluated. tools: items: $ref: '#/components/schemas/WorkflowToolLocator' type: array title: Tools description: >- List of tools to execute in parallel. The entire node is considered successful if all tools are executed successfully. type: object title: WorkflowToolNodeModel ASRConversationalConfig: properties: model_id: type: string maxLength: 128 minLength: 5 pattern: ^asr\.[a-z0-9][a-z0-9._:-]*$ title: Model Id description: Stable Threetone ASR catalog model identifier. recognition: oneOf: - $ref: '#/components/schemas/ASRFixedRecognition' - $ref: '#/components/schemas/ASRAutomaticAgentLanguagesRecognition' - $ref: '#/components/schemas/ASRAutomaticProviderLanguagesRecognition' title: Recognition discriminator: propertyName: mode mapping: automatic_agent_languages: $ref: '#/components/schemas/ASRAutomaticAgentLanguagesRecognition' automatic_provider_languages: $ref: '#/components/schemas/ASRAutomaticProviderLanguagesRecognition' fixed: $ref: '#/components/schemas/ASRFixedRecognition' task: $ref: '#/components/schemas/ASRTranscriptTask' default: transcribe keyterms: items: type: string type: array title: Keyterms options: anyOf: - oneOf: - $ref: '#/components/schemas/CartesiaInk2LiveKitInferenceASROptions' - $ref: >- #/components/schemas/CartesiaInkWhisperLiveKitInferenceASROptions - $ref: '#/components/schemas/SarvamSaarasV4DirectRealtimeASROptions' discriminator: propertyName: adapter_contract mapping: livekit_inference_cartesia_ink_2_v1: $ref: >- #/components/schemas/CartesiaInk2LiveKitInferenceASROptions livekit_inference_cartesia_ink_whisper_v1: $ref: >- #/components/schemas/CartesiaInkWhisperLiveKitInferenceASROptions sarvam_direct_realtime_saaras_v4_2026_09_v1: $ref: >- #/components/schemas/SarvamSaarasV4DirectRealtimeASROptions - type: 'null' title: Options additionalProperties: false type: object required: - model_id title: ASRConversationalConfig description: Speech-recognition selection and authored behavior for an agent. TurnConfig: properties: turn_timeout: type: number title: Turn Timeout description: Maximum wait time for the user's reply before re-engaging the user default: 7 initial_wait_time: anyOf: - type: number - type: 'null' title: Initial Wait Time description: >- How long the agent will wait for the user to start the conversation if the first message is empty. If not set, uses the regular turn_timeout. silence_end_call_timeout: type: number title: Silence End Call Timeout description: >- Maximum wait time since the user last spoke before terminating the call default: -1 mode: $ref: '#/components/schemas/TurnMode' description: The mode of turn detection default: turn x-fern-ignore: true turn_eagerness: $ref: '#/components/schemas/TurnEagerness' description: >- Controls how eager the agent is to respond. Low = less eager (waits longer), Standard = default eagerness, High = more eager (responds sooner) default: normal spelling_patience: $ref: '#/components/schemas/SpellingPatience' description: >- Controls if the agent should be more patient when user is spelling numbers and named entities. Auto = model based, Off = never wait extra default: auto speculative_turn: type: boolean title: Speculative Turn description: >- When enabled, starts generating LLM responses during silence before full turn confidence is reached, reducing perceived latency. May increase LLM costs. default: false retranscribe_on_turn_timeout: type: boolean title: Retranscribe On Turn Timeout description: >- When enabled, if VAD detects no speech, attempts to re-transcribe accumulated audio at turn timeout. Disables silence discount billing for affected turns. default: false turn_model: $ref: '#/components/schemas/TurnModel' default: turn_v3 interruption_ignore_terms: items: type: string type: array title: Interruption Ignore Terms description: >- List of terms that should not trigger an interruption when spoken by the user (e.g. 'gotcha', 'understood'). Uses case-insensitive exact matching. interruption_ignore_term_languages: items: type: string type: array title: Interruption Ignore Term Languages description: >- Language codes for which preset ignore-term categories have been activated. Stored explicitly so display is not inferred from term overlap. merge_with_default_ignore_terms: type: boolean title: Merge With Default Ignore Terms description: >- When enabled, the curated default terms for interruption_ignore_term_languages are used in addition to interruption_ignore_terms. default: false transcribe_on_disabled_interruptions: type: boolean title: Transcribe On Disabled Interruptions description: >- When interruptions are disabled, still transcribe what the user says so it can carry into the next turn. When off, user speech during a non-interruptible turn is ignored and won't trigger a turn. default: false soft_timeout_config: $ref: '#/components/schemas/SoftTimeoutConfig' description: >- Configuration for soft timeout functionality. Provides immediate feedback during longer LLM responses. type: object title: TurnConfig example: interruption_ignore_term_languages: [] interruption_ignore_terms: [] merge_with_default_ignore_terms: false mode: turn retranscribe_on_turn_timeout: false silence_end_call_timeout: -1 soft_timeout_config: message: Hhmmmm...yeah. timeout_seconds: -1 speculative_turn: false spelling_patience: auto transcribe_on_disabled_interruptions: false turn_eagerness: normal turn_model: turn_v3 turn_timeout: 7 TTSConversationalConfig-Output: properties: model_id: anyOf: - type: string maxLength: 128 minLength: 5 pattern: ^tts\.[a-z0-9][a-z0-9._:-]*$ description: Stable Threetone TTS catalog model identifier. - type: 'null' title: Model Id description: >- Stable Threetone TTS catalog model ID. It may be absent only for legacy agents that still use performance-tier migration behavior. voice_id: type: string title: Voice Id description: The voice ID to use for TTS default: ME9RtCnWp5vX2LhJdF3k performance: $ref: '#/components/schemas/TTSPerformance' description: >- User-facing TTS performance tier (latency or quality). The concrete provider/model is selected by the voice-server based on this value. default: latency pronunciation_dictionary_locators: items: $ref: '#/components/schemas/PydanticPronunciationDictionaryVersionLocator' type: array title: Pronunciation Dictionary Locators description: The pronunciation dictionary locators x-convai-client-override: true enable_phoneme_tags: type: boolean title: Enable Phoneme Tags description: >- Opt-in to SSML phoneme tag handling. When enabled, phoneme tags from inline content and pronunciation dictionaries may be normalized before synthesis when the selected provider supports them. default: true options: anyOf: - oneOf: - $ref: >- #/components/schemas/CartesiaSonic36LiveKitInferenceTTSOptions - $ref: '#/components/schemas/SarvamBulbulV3LiveKitPluginTTSOptions' discriminator: propertyName: adapter_contract mapping: livekit_inference_cartesia_sonic_3_6_2026_08_27_v1: $ref: >- #/components/schemas/CartesiaSonic36LiveKitInferenceTTSOptions livekit_plugin_python_sarvam_bulbul_v3_v1: $ref: '#/components/schemas/SarvamBulbulV3LiveKitPluginTTSOptions' - type: 'null' title: Options description: >- Validated model-specific authoring options for the selected catalog model. type: object required: - model_id - voice_id - performance - pronunciation_dictionary_locators - enable_phoneme_tags - options title: TTSConversationalConfig ConversationConfig: properties: text_only: type: boolean title: Text Only description: >- If enabled audio will not be processed and only text will be used, use to avoid audio pricing. default: false x-convai-client-override: true max_duration_seconds: type: integer title: Max Duration Seconds description: The maximum duration of a conversation in seconds default: 600 x-convai-client-override: true client_events: items: $ref: '#/components/schemas/ClientEvent' type: array title: Client Events description: The events that will be sent to the client file_input: $ref: '#/components/schemas/FileInputConfig' description: >- Configuration for file input (image/PDF uploads) during conversations. x-convai-client-override: true monitoring_enabled: type: boolean title: Monitoring Enabled description: Enable real-time monitoring of conversations via WebSocket default: false monitoring_events: items: $ref: '#/components/schemas/ClientEvent' type: array title: Monitoring Events description: The events that will be sent to monitoring connections. dtmf_input_settings: anyOf: - $ref: '#/components/schemas/DTMFInputConfig' - type: 'null' description: Configure DTMF (keypad) input collection during phone calls background_sound: $ref: '#/components/schemas/BackgroundSoundConfig' description: Configuration for background sound during conversations. source_attribution: type: boolean title: Source Attribution description: >- When enabled and knowledge base content is present, the LLM is instructed to report which sources it used. default: false type: object title: ConversationConfig example: client_events: - audio - interruption max_duration_seconds: 600 VADConfig: properties: background_voice_detection: type: boolean title: Background Voice Detection description: Whether to use background voice filtering default: false x-fern-ignore: true type: object title: VADConfig example: background_voice_detection: false AgentConfigAPIModel-Output: properties: first_message: type: string title: First Message description: >- If non-empty, the first message the agent will say. If empty, the agent waits for the user to start the discussion. default: '' x-convai-client-override: true x-convai-language-override: true language: type: string title: Language description: Language of the agent - used for ASR and TTS default: en x-convai-client-override: true dynamic_variables: $ref: '#/components/schemas/DynamicVariablesConfig-Output' description: Configuration for dynamic variables disable_first_message_interruptions: type: boolean title: Disable First Message Interruptions description: >- If true, the user will not be able to interrupt the agent while the first message is being delivered. default: false max_conversation_duration_message: type: string title: Max Conversation Duration Message description: >- If non-empty, the message the agent will send when max conversation duration is reached. default: '' x-convai-client-override: true x-convai-language-override: true text_behavior_overrides: anyOf: - additionalProperties: $ref: '#/components/schemas/BehaviorOverride' propertyNames: $ref: '#/components/schemas/ConversationInitiationSource' type: object - type: 'null' title: Text Behavior Overrides description: >- Per-channel response behavior overrides for text conversations. Built-in channel defaults apply when unset. prompt: $ref: '#/components/schemas/PromptAgentAPIModel' description: The prompt for the agent type: object title: AgentConfigAPIModel example: disable_first_message_interruptions: false first_message: Hello, how can I help you today? language: en EvaluationSettings: properties: criteria: items: $ref: '#/components/schemas/PromptEvaluationCriteria' type: array title: Criteria description: Individual criteria that the agent should be evaluated against type: object title: EvaluationSettings description: >- Settings to evaluate an agent's performance. Agents are evaluated against a set of criteria, with success being defined as meeting some combination of those criteria. WidgetConfig: properties: variant: $ref: '#/components/schemas/EmbedVariant' description: The variant of the widget default: full placement: $ref: '#/components/schemas/WidgetPlacement' description: The placement of the widget on the screen default: bottom-right expandable: $ref: '#/components/schemas/WidgetExpandable' description: Whether the widget is expandable default: never avatar: anyOf: - $ref: '#/components/schemas/OrbAvatar' - $ref: '#/components/schemas/URLAvatar' - $ref: '#/components/schemas/ImageAvatar' title: Avatar description: The avatar of the widget feedback_mode: $ref: '#/components/schemas/WidgetFeedbackMode' description: The feedback mode of the widget default: none end_feedback: anyOf: - $ref: '#/components/schemas/WidgetEndFeedbackConfig' - type: 'null' description: Configuration for feedback collected at the end of the conversation bg_color: type: string title: Bg Color description: The background color of the widget default: '#ffffff' text_color: type: string title: Text Color description: The text color of the widget default: '#000000' btn_color: type: string title: Btn Color description: The button color of the widget default: '#000000' btn_text_color: type: string title: Btn Text Color description: The button text color of the widget default: '#ffffff' border_color: type: string title: Border Color description: The border color of the widget default: '#e1e1e1' focus_color: type: string title: Focus Color description: The focus color of the widget default: '#000000' border_radius: anyOf: - type: integer - type: 'null' title: Border Radius description: The border radius of the widget btn_radius: anyOf: - type: integer - type: 'null' title: Btn Radius description: The button radius of the widget action_text: anyOf: - type: string - type: 'null' title: Action Text description: The action text of the widget start_call_text: anyOf: - type: string - type: 'null' title: Start Call Text description: The start call text of the widget end_call_text: anyOf: - type: string - type: 'null' title: End Call Text description: The end call text of the widget expand_text: anyOf: - type: string - type: 'null' title: Expand Text description: The expand text of the widget listening_text: anyOf: - type: string - type: 'null' title: Listening Text description: The text to display when the agent is listening speaking_text: anyOf: - type: string - type: 'null' title: Speaking Text description: The text to display when the agent is speaking shareable_page_text: anyOf: - type: string - type: 'null' title: Shareable Page Text description: The text to display when sharing shareable_page_show_terms: type: boolean title: Shareable Page Show Terms description: Whether to show terms and conditions on the shareable page default: true terms_text: anyOf: - type: string - type: 'null' title: Terms Text description: The text to display for terms and conditions terms_html: anyOf: - type: string - type: 'null' title: Terms Html description: The HTML to display for terms and conditions terms_key: anyOf: - type: string - type: 'null' title: Terms Key description: The key to display for terms and conditions show_avatar_when_collapsed: anyOf: - type: boolean - type: 'null' title: Show Avatar When Collapsed description: Whether to show the avatar when the widget is collapsed default: false disable_banner: type: boolean title: Disable Banner description: Whether to disable the banner default: false override_link: anyOf: - type: string - type: 'null' title: Override Link description: The override link for the widget markdown_link_allowed_hosts: items: $ref: '#/components/schemas/AllowlistItem' type: array title: Markdown Link Allowed Hosts description: >- List of allowed hostnames for clickable markdown links. Use { hostname: '*' } to allow any domain. Empty means no links are allowed. markdown_link_include_www: type: boolean title: Markdown Link Include Www description: Whether to automatically include www. variants of allowed hosts default: true markdown_link_allow_http: type: boolean title: Markdown Link Allow Http description: Whether to allow http:// in addition to https:// for allowed hosts default: true mic_muting_enabled: type: boolean title: Mic Muting Enabled description: Whether to enable mic muting default: true transcript_enabled: type: boolean title: Transcript Enabled description: >- Whether the widget should show the conversation transcript as it goes on default: true text_input_enabled: type: boolean title: Text Input Enabled description: Whether the user should be able to send text messages default: true conversation_mode_toggle_enabled: type: boolean title: Conversation Mode Toggle Enabled description: Whether to enable the conversation mode toggle in the widget default: false default_expanded: type: boolean title: Default Expanded description: Whether the widget should be expanded by default default: false always_expanded: type: boolean title: Always Expanded description: Whether the widget should always be expanded default: false dismissible: type: boolean title: Dismissible description: Whether the widget can be dismissed by the user default: false show_agent_status: type: boolean title: Show Agent Status description: Whether to show agent working/done/error status during tool use default: false show_conversation_id: type: boolean title: Show Conversation Id description: Whether to show the conversation ID after disconnection. default: true strip_audio_tags: type: boolean title: Strip Audio Tags description: Whether to strip audio markup from messages. default: true syntax_highlight_theme: anyOf: - type: string enum: - light - dark - type: 'null' title: Syntax Highlight Theme description: >- Theme for code block syntax highlighting. Defaults to auto-detection by the widget when not set. text_contents: $ref: '#/components/schemas/WidgetTextContents' description: Text contents of the widget styles: $ref: '#/components/schemas/WidgetStyles' description: Styles for the widget show_resize_button: type: boolean title: Show Resize Button description: Whether to show the resize button default: true language_selector: type: boolean title: Language Selector description: Whether to show the language selector default: false supports_text_only: type: boolean title: Supports Text Only description: Whether the widget can switch to text only mode default: true custom_avatar_path: anyOf: - type: string - type: 'null' title: Custom Avatar Path description: The custom avatar path language_presets: additionalProperties: $ref: '#/components/schemas/WidgetLanguagePreset' type: object title: Language Presets description: Language presets for the widget type: object title: WidgetConfig example: custom_avatar_path: https://example.com/avatar.png language_selector: false AnalysisProperty: properties: type: type: string enum: - boolean - string - integer - number title: Type description: type: string title: Description description: >- The description of the property. When set, the LLM will provide the value based on this description. Mutually exclusive with dynamic_variable, is_system_provided, constant_value, and is_omitted. default: '' enum: anyOf: - items: type: string type: array - type: 'null' title: Enum description: List of allowed string values for string type parameters is_system_provided: type: boolean title: Is System Provided description: >- If true, the value will be populated by the system at runtime. Used by API Integration Webhook tools for templating. Mutually exclusive with description, dynamic_variable, constant_value, and is_omitted. default: false dynamic_variable: type: string title: Dynamic Variable description: >- The name of the dynamic variable to use for this property's value. Mutually exclusive with description, is_system_provided, constant_value, and is_omitted. default: '' allowed_values_dynamic_variable: type: string title: Allowed Values Dynamic Variable description: >- When set, the LLM provides the value but the runtime rejects any value not present in the list held by this dynamic variable. Use to let the LLM pick from a server-verified set (e.g. the IDs the current user is allowed to access). Requires description; mutually exclusive with dynamic_variable, is_system_provided, constant_value, and is_omitted. default: '' constant_value: anyOf: - type: string - type: integer - type: number - type: boolean - type: 'null' title: Constant Value description: >- A constant value to use for this property. Mutually exclusive with description, dynamic_variable, is_system_provided, and is_omitted. default: '' is_omitted: type: boolean title: Is Omitted description: >- If true, this parameter will be completely omitted from the request. Only valid for optional parameters. Mutually exclusive with description, dynamic_variable, is_system_provided, and constant_value. default: false llm: anyOf: - $ref: '#/components/schemas/LLM' - type: 'null' description: >- LLM model to use for this analysis item. If not set, uses agent's analysis_llm default. type: object required: - type title: AnalysisProperty description: >- Data collection property with optional per-item LLM override for post-call analysis. TODO: migrate to composition (value_schema: LiteralJsonSchemaProperty + llm) instead of inheritance, so this generalizes cleanly to object/array schemas in the future. example: constant_value: '' description: My property dynamic_variable: '' is_system_provided: false type: string AnalysisScope: type: string enum: - conversation - agent title: AnalysisScope default: conversation AgentAnalysisItems: properties: evaluation_criteria: items: oneOf: - $ref: '#/components/schemas/AttachedUserEvaluationRef' - $ref: '#/components/schemas/AttachedSystemEvaluationRef' discriminator: propertyName: source mapping: system: $ref: '#/components/schemas/AttachedSystemEvaluationRef' user: $ref: '#/components/schemas/AttachedUserEvaluationRef' type: array title: Evaluation Criteria data_collection: items: oneOf: - $ref: '#/components/schemas/AttachedUserDataCollectionRef' - $ref: '#/components/schemas/AttachedSystemDataCollectionRef' discriminator: propertyName: source mapping: system: $ref: '#/components/schemas/AttachedSystemDataCollectionRef' user: $ref: '#/components/schemas/AttachedUserDataCollectionRef' type: array title: Data Collection type: object title: AgentAnalysisItems ConversationInitiationClientDataConfig: properties: conversation_config_override: $ref: '#/components/schemas/ConversationConfigClientOverrideConfig' description: Overrides for the conversation configuration custom_llm_extra_body: type: boolean title: Custom Llm Extra Body description: Whether to include custom LLM extra body default: false enable_conversation_initiation_client_data_from_webhook: type: boolean title: Enable Conversation Initiation Client Data From Webhook description: Whether to enable conversation initiation client data from webhooks default: false enable_starting_workflow_node_id_from_client: type: boolean title: Enable Starting Workflow Node Id From Client description: >- Whether clients may pass starting_workflow_node_id in initiation client data; if false, sending it fails conversation start. default: false enable_procedure_ids_from_client: type: boolean title: Enable Procedure Ids From Client description: >- Whether clients may pass procedure_ids in initiation client data to select which of the agent's procedures are available for the conversation; if false, sending it fails conversation start. default: false type: object title: ConversationInitiationClientDataConfig example: custom_llm_extra_body: true enable_conversation_initiation_client_data_from_webhook: true enable_procedure_ids_from_client: true enable_starting_workflow_node_id_from_client: true AgentWorkspaceOverrides: properties: conversation_initiation_client_data_webhook: anyOf: - $ref: '#/components/schemas/ConversationInitiationClientDataWebhook' - type: 'null' description: The webhook to send conversation initiation client data to webhooks: $ref: '#/components/schemas/ConvAIWebhooks' type: object title: AgentWorkspaceOverrides AgentTestingSettings: properties: attached_tests: items: $ref: '#/components/schemas/AttachedTestModel' type: array maxItems: 5000 minItems: 0 title: Attached Tests description: List of test IDs that should be run for this agent type: object title: AgentTestingSettings description: Settings for agent testing configuration. example: attached_tests: - environment: staging test_id: test_123 workflow_node_id: node_abc - test_id: test_456 referenced_tests_ids: - test_123 - test_456 GuardrailsV1: properties: version: type: string const: '1' title: Version default: '1' focus: $ref: '#/components/schemas/FocusGuardrail' prompt_injection: $ref: '#/components/schemas/PromptInjectionGuardrail' content: $ref: '#/components/schemas/ContentGuardrail' moderation: anyOf: - $ref: '#/components/schemas/ModerationGuardrail' - type: 'null' x-fern-ignore: true custom: $ref: '#/components/schemas/CustomGuardrail' type: object title: GuardrailsV1 AuthSettings: properties: enable_auth: type: boolean title: Enable Auth description: >- If set to true, starting a conversation with an agent will require a signed token default: false allowlist: items: $ref: '#/components/schemas/AllowlistItem' type: array title: Allowlist description: >- A list of hosts that are allowed to start conversations with the agent require_origin_header: type: boolean title: Require Origin Header description: >- When enabled, connections with no origin header will be rejected. If the allowlist is empty, this option has no effect. default: false shareable_token: anyOf: - type: string - type: 'null' title: Shareable Token description: >- A shareable token that can be used to start a conversation with the agent type: object title: AuthSettings example: allowlist: - hostname: https://example.com enable_auth: true require_origin_header: true shareable_token: '1234567890' AgentCallLimits: properties: agent_concurrency_limit: type: integer title: Agent Concurrency Limit description: >- The maximum number of concurrent conversations. -1 indicates that there is no maximum default: -1 daily_limit: type: integer title: Daily Limit description: The maximum number of conversations per day default: 100000 bursting_enabled: type: boolean title: Bursting Enabled description: >- Whether to enable bursting. If true, exceeding workspace concurrency limit will be allowed up to 3 times the limit. Calls will be charged at double rate when exceeding the limit. default: true type: object title: AgentCallLimits example: agent_concurrency_limit: -1 bursting_enabled: true daily_limit: 100000 PrivacyConfig: properties: record_voice: type: boolean title: Record Voice description: Whether to record the conversation default: true retention_days: type: integer title: Retention Days description: >- The number of days to retain the conversation. -1 indicates there is no retention limit default: -1 delete_transcript_and_pii: type: boolean title: Delete Transcript And Pii description: Whether to delete the transcript and PII default: false delete_audio: type: boolean title: Delete Audio description: Whether to delete the audio default: false apply_to_existing_conversations: type: boolean title: Apply To Existing Conversations description: Whether to apply the privacy settings to existing conversations default: false zero_retention_mode: type: boolean title: Zero Retention Mode description: Whether to enable zero retention mode - no PII data is stored default: false conversation_history_redaction: $ref: '#/components/schemas/ConversationHistoryRedactionConfig' description: Config for PII redaction in the conversation history type: object title: PrivacyConfig example: apply_to_existing_conversations: false delete_audio: false delete_transcript_and_pii: false record_voice: true retention_days: -1 zero_retention_mode: false AgentTrustContext: type: string enum: - unknown - low - high title: AgentTrustContext description: >- The trust context in which the agent operates. UNKNOWN: not yet classified (existing agents created before this feature). LOW: serves untrusted external participants (e.g. customer support, sales) — outputs should be vetted and tool access scoped. HIGH: serves the owner (e.g. personal assistant) — full tool access is appropriate. LLM: type: string enum: - gpt-4o-mini - gpt-4o - gpt-4 - gpt-4-turbo - gpt-4.1 - gpt-4.1-mini - gpt-4.1-nano - gpt-5 - gpt-5.1 - gpt-5.2 - gpt-5.2-chat-latest - gpt-5.4 - gpt-5.5 - gpt-5.6-sol - gpt-5.6-terra - gpt-5.6-luna - gpt-5-mini - gpt-5-nano - gpt-3.5-turbo - gemini-1.5-pro - gemini-1.5-flash - gemini-2.0-flash - gemini-2.0-flash-lite - gemini-2.5-flash-lite - gemini-2.5-flash - gemini-3-pro-preview - gemini-3-flash-preview - gemini-3.1-pro-preview - gemini-3.1-flash-lite-preview - gemini-3.6-flash - gemini-3.7-flash - claude-sonnet-4-5 - claude-opus-4-7 - claude-sonnet-4-6 - claude-sonnet-4 - claude-haiku-4-5 - claude-3-7-sonnet - claude-3-5-sonnet - claude-3-5-sonnet-v1 - claude-3-haiku - grok-beta - custom-llm - qwen3-4b - qwen3-30b-a3b - qwen36-35b-a3b - gpt-oss-20b - gpt-oss-120b - glm-45-air-fp8 - gemini-2.5-flash-preview-09-2025 - gemini-2.5-flash-lite-preview-09-2025 - gemini-2.5-flash-preview-05-20 - gemini-2.5-flash-preview-04-17 - gemini-2.5-flash-lite-preview-06-17 - gemini-2.0-flash-lite-001 - gemini-2.0-flash-001 - gemini-1.5-flash-002 - gemini-1.5-flash-001 - gemini-1.5-pro-002 - gemini-1.5-pro-001 - claude-sonnet-4@20250514 - claude-sonnet-4-5@20250929 - claude-haiku-4-5@20251001 - claude-3-7-sonnet@20250219 - claude-3-5-sonnet@20240620 - claude-3-5-sonnet-v2@20241022 - claude-3-haiku@20240307 - gpt-5-2025-08-07 - gpt-5.1-2025-11-13 - gpt-5.2-2025-12-11 - gpt-5.4-2026-03-05 - gpt-5.5-2026-04-23 - gpt-5-mini-2025-08-07 - gpt-5-nano-2025-08-07 - gpt-4.1-2025-04-14 - gpt-4.1-mini-2025-04-14 - gpt-4.1-nano-2025-04-14 - gpt-4o-mini-2024-07-18 - gpt-4o-2024-11-20 - gpt-4o-2024-08-06 - gpt-4o-2024-05-13 - gpt-4-0613 - gpt-4-0314 - gpt-4-turbo-2024-04-09 - gpt-3.5-turbo-0125 - gpt-3.5-turbo-1106 - watt-tool-8b - watt-tool-70b title: LLM TopicDiscoverySettings: properties: {} type: object title: TopicDiscoverySettings description: |- Per-agent topic-discovery configuration. Cadence and analysis window are managed internally; this only exposes the customer-facing on/off toggle. SentimentAnalysisSettings: properties: {} type: object title: SentimentAnalysisSettings description: Per-agent post-call sentiment analysis configuration. AlertingSettingsResponse: properties: monitor_configs: additionalProperties: $ref: '#/components/schemas/AlertingMonitorConfig' type: object title: Monitor Configs auto_resolve_after_inactive_minutes: anyOf: - type: integer - type: 'null' title: Auto Resolve After Inactive Minutes notifiers: items: oneOf: - $ref: '#/components/schemas/AlertingWebhookNotifierResponse' - $ref: '#/components/schemas/AlertingIntegrationNotifierResponse' discriminator: propertyName: type mapping: integration: $ref: '#/components/schemas/AlertingIntegrationNotifierResponse' webhook: $ref: '#/components/schemas/AlertingWebhookNotifierResponse' type: array title: Notifiers type: object title: AlertingSettingsResponse description: >- Customer-facing view of alerting settings. Unlike AdminAlertingSettingsResponse, it has no internal_notifiers field: those are ElevenLabs-internal delivery channels whose URLs must never be returned outside the admin API. SafetyResponseModel: properties: is_blocked_ivc: type: boolean title: Is Blocked Ivc default: false is_blocked_non_ivc: type: boolean title: Is Blocked Non Ivc default: false ignore_safety_evaluation: type: boolean title: Ignore Safety Evaluation default: false type: object title: SafetyResponseModel PhoneNumberAgentInfo: properties: agent_id: type: string title: Agent Id description: The ID of the agent agent_name: type: string title: Agent Name description: The name of the agent environment: anyOf: - type: string - type: 'null' title: Environment description: >- Environment to use for resolving environment variables on calls to this number. branch_id: anyOf: - type: string - type: 'null' title: Branch Id description: Agent branch to use for calls to this number. type: object required: - agent_id - agent_name title: PhoneNumberAgentInfo example: agent_id: F3Pbu5gP6NNKBscdCdwB agent_name: My Agent PhoneNumberFulfillmentProvider: type: string enum: - twilio - exotel title: PhoneNumberFulfillmentProvider GetPhoneNumberOutboundSIPTrunkConfigResponseModel: properties: address: type: string title: Address description: Hostname or IP the SIP INVITE is sent to transport: $ref: '#/components/schemas/SIPTrunkTransportEnum' description: Protocol to use for SIP transport media_encryption: $ref: '#/components/schemas/SIPMediaEncryptionEnum' description: Whether or not to encrypt media (data layer). headers: additionalProperties: type: string type: object title: Headers description: SIP headers for INVITE request attributes_to_headers: additionalProperties: type: string type: object title: Attributes To Headers description: >- Map of dynamic variable name to header name for attributes_to_headers has_auth_credentials: type: boolean title: Has Auth Credentials description: Whether authentication credentials are configured username: anyOf: - type: string - type: 'null' title: Username description: SIP trunk username (if available) has_outbound_trunk: type: boolean title: Has Outbound Trunk description: Whether a LiveKit SIP outbound trunk is configured default: false enabled_codecs: items: $ref: '#/components/schemas/MediaCodec' type: array title: Enabled Codecs description: >- Media codecs that are offered in the SDP for outbound calls. If empty, all supported codecs are offered. type: object required: - address - transport - media_encryption - has_auth_credentials title: GetPhoneNumberOutboundSIPTrunkConfigResponseModel description: SIP Trunk configuration details for a phone number GetPhoneNumberInboundSIPTrunkConfigResponseModel: properties: allowed_addresses: items: type: string type: array title: Allowed Addresses description: >- List of IP addresses that are allowed to use the trunk. Each item in the list can be an individual IP address or a Classless Inter-Domain Routing notation representing a CIDR block. allowed_numbers: anyOf: - items: type: string type: array - type: 'null' title: Allowed Numbers description: List of phone numbers that are allowed to use the trunk. media_encryption: $ref: '#/components/schemas/SIPMediaEncryptionEnum' has_auth_credentials: type: boolean title: Has Auth Credentials description: Whether authentication credentials are configured username: anyOf: - type: string - type: 'null' title: Username description: SIP trunk username (if available) remote_domains: anyOf: - items: type: string type: array - type: 'null' title: Remote Domains description: Domains of remote SIP servers used to validate TLS certificates. attributes_to_headers: additionalProperties: type: string type: object title: Attributes To Headers description: >- Map of dynamic variable name to header name for attributes_to_headers type: object required: - allowed_addresses - allowed_numbers - media_encryption - has_auth_credentials title: GetPhoneNumberInboundSIPTrunkConfigResponseModel LivekitStackType: type: string enum: - standard - static title: LivekitStackType WhatsAppRegistrationStatus: type: string enum: - UNKNOWN - REGISTERING - REGISTERED - UNCERTAIN - ACTION_REQUIRED title: WhatsAppRegistrationStatus WorkflowEdgeModel-Output: properties: source: type: string title: Source description: ID of the source node. target: type: string title: Target description: ID of the target node. forward_condition: anyOf: - oneOf: - $ref: '#/components/schemas/WorkflowUnconditionalModel' description: Condition that is always true. - $ref: '#/components/schemas/WorkflowLLMConditionModel' description: >- Condition described using human language and evaluated by an LLM. - $ref: '#/components/schemas/WorkflowResultConditionModel' description: >- Condition based on the result of the last executed tool dispatch node. - $ref: '#/components/schemas/WorkflowExpressionConditionModel-Output' description: Condition described using a deterministic expression. discriminator: propertyName: type mapping: expression: $ref: >- #/components/schemas/WorkflowExpressionConditionModel-Output llm: $ref: '#/components/schemas/WorkflowLLMConditionModel' result: $ref: '#/components/schemas/WorkflowResultConditionModel' unconditional: $ref: '#/components/schemas/WorkflowUnconditionalModel' - type: 'null' title: Forward Condition description: >- Condition that must be met for the edge to be traversed in the forward direction (source to target). backward_condition: anyOf: - oneOf: - $ref: '#/components/schemas/WorkflowUnconditionalModel' description: Condition that is always true. - $ref: '#/components/schemas/WorkflowLLMConditionModel' description: >- Condition described using human language and evaluated by an LLM. - $ref: '#/components/schemas/WorkflowResultConditionModel' description: >- Condition based on the result of the last executed tool dispatch node. - $ref: '#/components/schemas/WorkflowExpressionConditionModel-Output' description: Condition described using a deterministic expression. discriminator: propertyName: type mapping: expression: $ref: >- #/components/schemas/WorkflowExpressionConditionModel-Output llm: $ref: '#/components/schemas/WorkflowLLMConditionModel' result: $ref: '#/components/schemas/WorkflowResultConditionModel' unconditional: $ref: '#/components/schemas/WorkflowUnconditionalModel' - type: 'null' title: Backward Condition description: >- Condition that must be met for the edge to be traversed in the backward direction (target to source). type: object required: - source - target title: WorkflowEdgeModel WorkflowStartNodeModel-Output: properties: type: type: string const: start title: Type default: start position: $ref: '#/components/schemas/Position-Output' description: Position of the node in the workflow. edge_order: items: type: string type: array title: Edge Order description: The ids of outgoing edges in the order they should be evaluated. type: object required: - type - position - edge_order title: WorkflowStartNodeModel WorkflowEndNodeModel-Output: properties: type: type: string const: end title: Type default: end position: $ref: '#/components/schemas/Position-Output' description: Position of the node in the workflow. edge_order: items: type: string type: array title: Edge Order description: The ids of outgoing edges in the order they should be evaluated. type: object required: - type - position - edge_order title: WorkflowEndNodeModel WorkflowPhoneNumberNodeModel-Output: properties: custom_sip_headers: items: oneOf: - $ref: '#/components/schemas/CustomSIPHeader' - $ref: '#/components/schemas/CustomSIPHeaderWithDynamicVariable' discriminator: propertyName: type mapping: dynamic: $ref: '#/components/schemas/CustomSIPHeaderWithDynamicVariable' static: $ref: '#/components/schemas/CustomSIPHeader' type: array maxItems: 20 title: Custom Sip Headers description: >- Custom SIP headers to include when transferring the call. Each header can be either a static value or a dynamic variable reference. transfer_destination: oneOf: - $ref: '#/components/schemas/PhoneNumberTransferDestination' - $ref: '#/components/schemas/SIPUriTransferDestination' - $ref: >- #/components/schemas/PhoneNumberDynamicVariableTransferDestination - $ref: '#/components/schemas/SIPUriDynamicVariableTransferDestination' title: Transfer Destination discriminator: propertyName: type mapping: phone: $ref: '#/components/schemas/PhoneNumberTransferDestination' phone_dynamic_variable: $ref: >- #/components/schemas/PhoneNumberDynamicVariableTransferDestination sip_uri: $ref: '#/components/schemas/SIPUriTransferDestination' sip_uri_dynamic_variable: $ref: '#/components/schemas/SIPUriDynamicVariableTransferDestination' transfer_type: $ref: '#/components/schemas/TransferTypeEnum' default: conference sip_refer_play_dialtone: type: boolean title: Sip Refer Play Dialtone description: >- When True, a ringing tone is played on the original call leg while a SIP REFER transfer completes. The tone is carried over RTP to the SIP peer executing the REFER, so disable this if the receiving system (e.g. an SBC or contact center) should not hear it. When disabled the caller hears silence until the transfer completes. SIP REFER transfers only. default: true uui: anyOf: - $ref: '#/components/schemas/UUITransferConfig' - type: 'null' description: >- User-to-User Information (RFC 7433) to attach to SIP REFER transfers. Carries call context such as CRM identifiers or escalation reason across the transfer boundary. post_dial_digits: anyOf: - oneOf: - $ref: '#/components/schemas/PostDialDigitsStatic' - $ref: '#/components/schemas/PostDialDigitsDynamicVariable' discriminator: propertyName: type mapping: dynamic: $ref: '#/components/schemas/PostDialDigitsDynamicVariable' static: $ref: '#/components/schemas/PostDialDigitsStatic' - type: 'null' title: Post Dial Digits description: >- DTMF digits to send after call connects (e.g., 'ww1234' for extension). Can be either a static value or a dynamic variable reference. Use 'w' for 0.5s pause. Only supported for Twilio transfers. type: type: string const: phone_number title: Type default: phone_number position: $ref: '#/components/schemas/Position-Output' description: Position of the node in the workflow. edge_order: items: type: string type: array title: Edge Order description: The ids of outgoing edges in the order they should be evaluated. type: object required: - custom_sip_headers - transfer_destination - transfer_type - sip_refer_play_dialtone - uui - post_dial_digits - type - position - edge_order title: WorkflowPhoneNumberNodeModel WorkflowOverrideAgentNodeModel-Output: properties: type: type: string const: override_agent title: Type default: override_agent position: $ref: '#/components/schemas/Position-Output' description: Position of the node in the workflow. edge_order: items: type: string type: array title: Edge Order description: The ids of outgoing edges in the order they should be evaluated. conversation_config: $ref: >- #/components/schemas/ConversationalConfigAPIModelWorkflowOverride-Output description: >- Configuration overrides applied while the subagent is conducting the conversation. additional_prompt: type: string title: Additional Prompt description: >- Specific goal for this subagent. It will be added to the system prompt and can be used to further refine the agent's behavior in this specific context. additional_knowledge_base: items: $ref: '#/components/schemas/KnowledgeBaseLocator' type: array title: Additional Knowledge Base description: >- Additional knowledge base documents that the subagent has access to. These will be used in addition to the main agent's documents. additional_tool_ids: items: type: string type: array title: Additional Tool Ids description: >- IDs of additional tools that the subagent has access to. These will be used in addition to the main agent's tools. label: type: string title: Label description: Human-readable label for the node used throughout the UI. entry_behavior: $ref: '#/components/schemas/EntryBehavior' description: >- Dictates whether this node should immediately generate a response upon entry or wait for the user input. When set to "auto", the behavior will be decided based on the type of the preceding node: "wait_for_user" after the "say" and "start" nodes and "generate_immediately" otherwise. default: auto type: object required: - type - position - edge_order - conversation_config - additional_prompt - additional_knowledge_base - additional_tool_ids - label - entry_behavior title: WorkflowOverrideAgentNodeModel WorkflowStandaloneAgentNodeModel-Output: properties: type: type: string const: standalone_agent title: Type default: standalone_agent position: $ref: '#/components/schemas/Position-Output' description: Position of the node in the workflow. edge_order: items: type: string type: array title: Edge Order description: The ids of outgoing edges in the order they should be evaluated. agent_id: type: string title: Agent Id description: The ID of the agent to transfer the conversation to. delay_ms: type: integer title: Delay Ms description: >- Artificial delay in milliseconds applied before transferring the conversation. default: 0 transfer_message: anyOf: - type: string - type: 'null' title: Transfer Message description: Optional message sent to the user before the transfer is initiated. enable_transferred_agent_first_message: type: boolean title: Enable Transferred Agent First Message description: >- Whether to enable the transferred agent to send its configured first message after the transfer. default: false type: object required: - type - position - edge_order - agent_id - delay_ms - transfer_message - enable_transferred_agent_first_message title: WorkflowStandaloneAgentNodeModel WorkflowToolNodeModel-Output: properties: type: type: string const: tool title: Type default: tool position: $ref: '#/components/schemas/Position-Output' description: Position of the node in the workflow. edge_order: items: type: string type: array title: Edge Order description: The ids of outgoing edges in the order they should be evaluated. tools: items: $ref: '#/components/schemas/WorkflowToolLocator' type: array title: Tools description: >- List of tools to execute in parallel. The entire node is considered successful if all tools are executed successfully. type: object required: - type - position - edge_order - tools title: WorkflowToolNodeModel TurnMode: type: string enum: - silence - turn title: TurnMode TurnEagerness: type: string enum: - patient - normal - eager title: TurnEagerness SpellingPatience: type: string enum: - auto - 'off' title: SpellingPatience TurnModel: type: string enum: - turn_v2 - turn_v3 title: TurnModel SoftTimeoutConfigWorkflowOverride: properties: timeout_seconds: anyOf: - type: number - type: 'null' title: Timeout Seconds description: >- Time in seconds before showing the predefined message while waiting for LLM response. Set to -1 to disable. message: anyOf: - type: string - type: 'null' title: Message description: >- Message to show when the first soft timeout is reached while waiting for LLM response. Supports dynamic variables (e.g., {{system__time}}, {{custom_variable}}). x-convai-client-override: true x-convai-language-override: true additional_soft_timeout_messages: anyOf: - items: type: string type: array - type: 'null' title: Additional Soft Timeout Messages description: >- Extra static filler messages for subsequent soft timeouts in the same LLM generation. The first timeout uses `message`. If fewer messages are configured than `max_soft_timeouts_per_generation`, the last configured message is repeated; otherwise a built-in filler is used. x-convai-client-override: true x-convai-language-override: true use_llm_generated_message: anyOf: - type: boolean - type: 'null' title: Use Llm Generated Message description: >- If enabled, the soft timeout message will be generated dynamically instead of using the static message. randomize_fillers: anyOf: - type: boolean - type: 'null' title: Randomize Fillers description: >- If enabled, shuffle the order of static soft timeout messages once at the start of each turn. Only applies when use_llm_generated_message is false. max_soft_timeouts_per_generation: anyOf: - type: integer - type: 'null' title: Max Soft Timeouts Per Generation description: >- Maximum filler messages while waiting for a single LLM response. Fires every timeout_seconds until the LLM streams content or this limit is reached. llm_generated_message_prompt_override: anyOf: - type: string - type: 'null' title: Llm Generated Message Prompt Override description: >- Custom prompt for generating the soft timeout filler message when use_llm_generated_message is enabled. Recent conversation context is provided as a separate user message. If not set, the default prompt will be used. Supports dynamic variables (e.g., {{system__time}}, {{custom_variable}}). examples: - >- Output a SHORT neutral filler phrase (1-4 words MAX) acknowledging you heard the user. disable_until_first_user_message: anyOf: - type: boolean - type: 'null' title: Disable Until First User Message description: >- When true, soft timeout fillers are suppressed until the conversation has at least one real user message. Prevents fillers during the agent's opening turn (e.g. workflow generate-immediately / tool calls before the user speaks). type: object title: SoftTimeoutConfigWorkflowOverride example: message: Hhmmmm...yeah. timeout_seconds: -1 use_llm_generated_message: false TTSPerformance: type: string enum: - latency - quality title: TTSPerformance description: |- User-facing TTS performance tier. Decouples the UI from vendor names. latency -> optimized for response speed (currently Cartesia Sonic). quality -> optimized for expressiveness (currently ElevenLabs v3). PydanticPronunciationDictionaryVersionLocator: properties: pronunciation_dictionary_id: type: string title: Pronunciation Dictionary Id description: The ID of the pronunciation dictionary version_id: anyOf: - type: string - type: 'null' title: Version Id description: The ID of the version of the pronunciation dictionary type: object required: - pronunciation_dictionary_id - version_id title: PydanticPronunciationDictionaryVersionLocator description: >- A locator for other documents to be able to reference a specific dictionary and it's version. This is a pydantic version of PronunciationDictionaryVersionLocatorDBModel. Required to ensure compat with the rest of the agent data models. CartesiaSonic36LiveKitInferenceTTSOptions: properties: adapter_contract: type: string const: livekit_inference_cartesia_sonic_3_6_2026_08_27_v1 title: Adapter Contract default: livekit_inference_cartesia_sonic_3_6_2026_08_27_v1 speed: anyOf: - $ref: '#/components/schemas/CartesiaSpeedPreset' - type: number maximum: 1.5 minimum: 0.6 - type: 'null' title: Speed volume: anyOf: - type: number maximum: 2 minimum: 0.5 - type: 'null' title: Volume emotion: anyOf: - $ref: '#/components/schemas/CartesiaEmotion' - type: 'null' duration_seconds: anyOf: - type: number exclusiveMinimum: 0 - type: 'null' title: Duration Seconds max_buffer_delay_ms: anyOf: - type: integer minimum: 0 - type: 'null' title: Max Buffer Delay Ms add_timestamps: anyOf: - type: boolean - type: 'null' title: Add Timestamps add_phoneme_timestamps: anyOf: - type: boolean - type: 'null' title: Add Phoneme Timestamps use_normalized_timestamps: anyOf: - type: boolean - type: 'null' title: Use Normalized Timestamps additionalProperties: false type: object title: CartesiaSonic36LiveKitInferenceTTSOptions description: Options for the pinned Sonic 3.6 LiveKit Inference variant. SarvamBulbulV3LiveKitPluginTTSOptions: properties: adapter_contract: type: string const: livekit_plugin_python_sarvam_bulbul_v3_v1 title: Adapter Contract default: livekit_plugin_python_sarvam_bulbul_v3_v1 pace: anyOf: - type: number maximum: 2 minimum: 0.5 - type: 'null' title: Pace temperature: anyOf: - type: number maximum: 1 minimum: 0.01 - type: 'null' title: Temperature min_buffer_size: anyOf: - type: integer maximum: 200 minimum: 30 - type: 'null' title: Min Buffer Size max_chunk_length: anyOf: - type: integer maximum: 500 minimum: 50 - type: 'null' title: Max Chunk Length additionalProperties: false type: object title: SarvamBulbulV3LiveKitPluginTTSOptions description: User-facing Bulbul v3 controls compiled to the LiveKit Python plugin. ClientEvent: type: string enum: - conversation_initiation_metadata - asr_initiation_metadata - ping - audio - interruption - user_transcript - tentative_user_transcript - agent_response - agent_response_correction - client_tool_call - mcp_tool_call - mcp_connection_status - agent_tool_request - agent_tool_response - agent_tool_response_full_payload - agent_response_metadata - vad_score - agent_chat_response_part - client_error - guardrail_triggered - dtmf_request - agent_response_complete - context_usage - internal_turn_probability - internal_tentative_agent_response title: ClientEvent FileInputConfigWorkflowOverride: properties: enabled: anyOf: - type: boolean - type: 'null' title: Enabled description: >- When enabled, users may attach images or PDFs in chat when the LLM supports multimodal input. max_files_in_memory: anyOf: - type: integer - type: 'null' title: Max Files In Memory description: >- Number of most-recent files kept in memory during a conversation. Older files are summarized and their bytes freed. max_files_per_conversation: anyOf: - type: integer - type: 'null' title: Max Files Per Conversation description: >- Total files a user can upload in one conversation. Uploads are billed per file. Use -1 for no limit, or a value >= max_files_in_memory. type: object title: FileInputConfigWorkflowOverride DTMFInputConfig: properties: dtmf_input_timeout: type: number maximum: 10 minimum: 0.5 title: Dtmf Input Timeout description: Timeout in seconds to wait for additional DTMF digits default: 2 hash_terminator: type: boolean title: Hash Terminator description: 'If true, pressing # immediately completes DTMF input' default: true redact_input: type: boolean title: Redact Input description: >- If true, replace the caller's DTMF (keypad) entries with a redaction marker in the transcript, conversation log and analysis. Digits the agent repeats back or passes to a tool are not affected. default: false type: object title: DTMFInputConfig description: Configuration for DTMF (keypad) input collection during phone calls. BackgroundSoundConfigWorkflowOverride: properties: source_type: anyOf: - $ref: '#/components/schemas/BackgroundSoundSourceType' - type: 'null' description: The type of background sound source. source_id: anyOf: - $ref: '#/components/schemas/BackgroundSoundPresetId' - type: 'null' description: Identifier for the sound source. volume: anyOf: - type: number - type: 'null' title: Volume description: Volume level for background sound (0.01 to 1.0). crossfade_loop: anyOf: - type: boolean - type: 'null' title: Crossfade Loop description: >- Apply a crossfade at the loop boundary to avoid audible pops when the sound loops. type: object title: BackgroundSoundConfigWorkflowOverride ConversationConfigClientOverride: properties: turn: anyOf: - $ref: '#/components/schemas/TurnConfigOverride' - type: 'null' description: Configuration for turn detection tts: anyOf: - $ref: '#/components/schemas/TTSConversationalConfigOverride' - type: 'null' description: Configuration for conversational text to speech conversation: anyOf: - $ref: '#/components/schemas/ConversationConfigOverride' - type: 'null' description: Configuration for conversational events agent: anyOf: - $ref: '#/components/schemas/AgentConfigOverride' - type: 'null' description: Agent specific configuration type: object title: ConversationConfigClientOverride example: agent: first_message: Hello, how can I help you today? language: en prompt: knowledge_base: [] llm: gemini-2.0-flash-001 prompt: >- You are a helpful assistant that can answer questions about the topic of the conversation. tool_ids: [] tts: performance: latency voice_id: ME9RtCnWp5vX2LhJdF3k LanguagePresetTranslation: properties: source_hash: type: string title: Source Hash text: type: string title: Text type: object required: - source_hash - text title: LanguagePresetTranslation DynamicVariablesConfigWorkflowOverride-Input: properties: dynamic_variable_placeholders: anyOf: - additionalProperties: $ref: '#/components/schemas/DynamicVariableValueType-Input' type: object - type: 'null' title: Dynamic Variable Placeholders description: A dictionary of dynamic variable placeholders and their values type: object title: DynamicVariablesConfigWorkflowOverride example: dynamic_variable_placeholders: user_name: John Doe BehaviorOverride: properties: verbosity: anyOf: - $ref: '#/components/schemas/Verbosity' - type: 'null' description: Verbosity override. Underlying default applies when unset. output_format: anyOf: - $ref: '#/components/schemas/OutputFormat' - type: 'null' description: Output format override. Underlying default applies when unset. interaction_budget: anyOf: - $ref: '#/components/schemas/InteractionBudget' - type: 'null' description: Interaction budget override. Underlying default applies when unset. type: object title: BehaviorOverride PromptAgentAPIModelWorkflowOverride-Input: properties: prompt: anyOf: - type: string - type: 'null' title: Prompt description: The prompt for the agent x-convai-client-override: true llm: anyOf: - $ref: '#/components/schemas/LLM' - type: 'null' description: >- The LLM to query with the prompt and the chat history. If using data residency, the LLM must be supported in the data residency environment x-convai-client-override: true reasoning_effort: anyOf: - $ref: '#/components/schemas/LLMReasoningEffort' - type: 'null' description: Reasoning effort of the model. Only available for some models. thinking_budget: anyOf: - type: integer - type: 'null' title: Thinking Budget description: >- Max number of tokens used for thinking. Use 0 to turn off if supported by the model. enable_reasoning_summary: anyOf: - type: boolean - type: 'null' title: Enable Reasoning Summary description: >- Enable model reasoning summaries. When disabled, we do not request summaries from provider if possible for faster TTFB. Not ZRM compatible. temperature: anyOf: - type: number - type: 'null' title: Temperature description: >- The temperature for the LLM. Defaults to 0. Set to null to omit the parameter from the LLM request entirely (useful for custom LLMs that reject the temperature field). max_tokens: anyOf: - type: integer - type: 'null' title: Max Tokens description: If greater than 0, maximum number of tokens the LLM can predict tool_ids: anyOf: - items: type: string type: array - type: 'null' title: Tool Ids description: A list of IDs of tools used by the agent x-convai-client-override: true built_in_tools: anyOf: - $ref: '#/components/schemas/BuiltInToolsWorkflowOverride' - type: 'null' description: Built-in system tools to be used by the agent mcp_server_ids: anyOf: - items: type: string type: array - type: 'null' title: Mcp Server Ids description: A list of MCP server ids to be used by the agent native_mcp_server_ids: anyOf: - items: type: string type: array - type: 'null' title: Native Mcp Server Ids description: A list of Native MCP server ids to be used by the agent x-convai-client-override: true knowledge_base: anyOf: - items: $ref: '#/components/schemas/KnowledgeBaseLocator' type: array - type: 'null' title: Knowledge Base description: A list of knowledge bases to be used by the agent x-convai-client-override: true custom_llm: anyOf: - $ref: '#/components/schemas/CustomLLM' - type: 'null' description: Definition for a custom LLM if LLM field is set to 'CUSTOM_LLM' ignore_default_personality: anyOf: - type: boolean - type: 'null' title: Ignore Default Personality description: >- Whether to remove the default personality lines from the system prompt rag: anyOf: - $ref: '#/components/schemas/RagConfigWorkflowOverride' - type: 'null' description: Configuration for RAG timezone: anyOf: - type: string - type: 'null' title: Timezone description: >- Timezone for displaying current time in system prompt. If set, the current time will be included in the system prompt using this timezone. Must be a valid timezone name (e.g., 'America/New_York', 'Europe/London', 'UTC'). Recommended for accurate time-aware responses; without this, the agent has no knowledge of the current date/time unless you provide it via dynamic variables or tools, which can lead to incorrect or hallucinated time references. backup_llm_config: anyOf: - $ref: '#/components/schemas/BackupLLMDefault' - $ref: '#/components/schemas/BackupLLMDisabled' - $ref: '#/components/schemas/BackupLLMOverride' - type: 'null' title: Backup Llm Config description: >- Configuration for backup LLM cascading. Can be disabled, use system defaults, or specify custom order. cascade_timeout_seconds: anyOf: - type: number - type: 'null' title: Cascade Timeout Seconds description: >- Time in seconds before cascading to backup LLM. Must be between 2 and 15 seconds. tools: anyOf: - items: oneOf: - $ref: '#/components/schemas/WebhookToolConfig-Input' - $ref: '#/components/schemas/ClientToolConfig-Input' - $ref: '#/components/schemas/SystemToolConfig' - $ref: '#/components/schemas/MCPToolConfig-Input' - $ref: '#/components/schemas/ApiIntegrationWebhookToolConfig-Input' - $ref: '#/components/schemas/SMBToolConfig' description: The type of tool discriminator: propertyName: type mapping: api_integration_webhook: $ref: >- #/components/schemas/ApiIntegrationWebhookToolConfig-Input client: $ref: '#/components/schemas/ClientToolConfig-Input' mcp: $ref: '#/components/schemas/MCPToolConfig-Input' smb: $ref: '#/components/schemas/SMBToolConfig' system: $ref: '#/components/schemas/SystemToolConfig' webhook: $ref: '#/components/schemas/WebhookToolConfig-Input' type: array - type: 'null' title: Tools description: >- A list of tools that the agent can use over the course of the conversation, use tool_ids instead type: object title: PromptAgentAPIModelWorkflowOverride example: knowledge_base: [] llm: gemini-2.0-flash-001 max_tokens: -1 prompt: >- You are a helpful assistant that can answer questions about the topic of the conversation. temperature: 0 tool_ids: [] tools: [] ASRFixedRecognition: properties: mode: type: string const: fixed title: Mode default: fixed additionalProperties: false type: object title: ASRFixedRecognition description: Recognize the agent's configured base language. ASRAutomaticAgentLanguagesRecognition: properties: mode: type: string const: automatic_agent_languages title: Mode default: automatic_agent_languages additionalProperties: false type: object title: ASRAutomaticAgentLanguagesRecognition description: Detect only among the base language and configured language presets. ASRAutomaticProviderLanguagesRecognition: properties: mode: type: string const: automatic_provider_languages title: Mode default: automatic_provider_languages additionalProperties: false type: object title: ASRAutomaticProviderLanguagesRecognition description: Allow detection across every language supported by the resolved route. ASRTranscriptTask: type: string enum: - transcribe - translate - verbatim - transliterate - code_mixed title: ASRTranscriptTask CartesiaInk2LiveKitInferenceASROptions: properties: adapter_contract: type: string const: livekit_inference_cartesia_ink_2_v1 title: Adapter Contract default: livekit_inference_cartesia_ink_2_v1 turn_start_threshold: anyOf: - type: number maximum: 0.9 minimum: 0.5 - type: 'null' title: Turn Start Threshold turn_eager_end_threshold: anyOf: - type: number maximum: 0.6 minimum: 0.3 - type: 'null' title: Turn Eager End Threshold turn_end_threshold: anyOf: - type: number maximum: 0.5 minimum: 0.05 - type: 'null' title: Turn End Threshold turn_end_timeout_ms: anyOf: - type: integer maximum: 11200 minimum: 640 - type: 'null' title: Turn End Timeout Ms additionalProperties: false type: object title: CartesiaInk2LiveKitInferenceASROptions description: Options for Cartesia Ink 2 through LiveKit Inference. CartesiaInkWhisperLiveKitInferenceASROptions: properties: adapter_contract: type: string const: livekit_inference_cartesia_ink_whisper_v1 title: Adapter Contract default: livekit_inference_cartesia_ink_whisper_v1 min_volume: anyOf: - type: number maximum: 1 minimum: 0 - type: 'null' title: Min Volume max_silence_duration_secs: anyOf: - type: number exclusiveMinimum: 0 - type: 'null' title: Max Silence Duration Secs additionalProperties: false type: object title: CartesiaInkWhisperLiveKitInferenceASROptions description: Options for Cartesia Ink Whisper through LiveKit Inference. SarvamSaarasV4DirectRealtimeASROptions: properties: adapter_contract: type: string const: sarvam_direct_realtime_saaras_v4_2026_09_v1 title: Adapter Contract default: sarvam_direct_realtime_saaras_v4_2026_09_v1 stream_type: $ref: '#/components/schemas/SarvamStreamType' default: balanced endpointing: $ref: '#/components/schemas/ASREndpointingMode' default: vad threshold: anyOf: - type: number maximum: 1 minimum: 0 - type: 'null' title: Threshold silence_duration_ms: anyOf: - type: integer minimum: 0 - type: 'null' title: Silence Duration Ms min_speech_duration_ms: anyOf: - type: integer minimum: 0 - type: 'null' title: Min Speech Duration Ms return_timestamps: type: boolean title: Return Timestamps default: false prompt: anyOf: - type: string - type: 'null' title: Prompt additionalProperties: false type: object title: SarvamSaarasV4DirectRealtimeASROptions description: Options for Saaras v4 on Sarvam's direct realtime WebSocket API. WorkflowUnconditionalModel: properties: label: anyOf: - type: string - type: 'null' title: Label description: >- Optional human-readable label for the condition used throughout the UI. type: type: string const: unconditional title: Type default: unconditional type: object title: WorkflowUnconditionalModel WorkflowLLMConditionModel: properties: label: anyOf: - type: string - type: 'null' title: Label description: >- Optional human-readable label for the condition used throughout the UI. type: type: string const: llm title: Type default: llm condition: type: string title: Condition description: Condition to evaluate examples: - User's last message contains a question about our pricing. - User provided their email address. type: object required: - condition title: WorkflowLLMConditionModel WorkflowResultConditionModel: properties: label: anyOf: - type: string - type: 'null' title: Label description: >- Optional human-readable label for the condition used throughout the UI. type: type: string const: result title: Type default: result successful: type: boolean title: Successful description: >- Whether all tools in the previously executed tool node were executed successfully. type: object required: - successful title: WorkflowResultConditionModel WorkflowExpressionConditionModel-Input: properties: label: anyOf: - type: string - type: 'null' title: Label description: >- Optional human-readable label for the condition used throughout the UI. type: type: string const: expression title: Type default: expression expression: $ref: '#/components/schemas/ASTNode-Input' description: Expression to evaluate. type: object required: - expression title: WorkflowExpressionConditionModel Position-Input: properties: x: type: number title: X default: 0 'y': type: number title: 'Y' default: 0 type: object title: Position CustomSIPHeader: properties: type: type: string const: static title: Type default: static key: type: string maxLength: 64 minLength: 1 pattern: ^[A-Za-z0-9]+(-[A-Za-z0-9]+)*$ title: Key description: The SIP header name (e.g., 'X-Customer-ID') value: type: string maxLength: 512 minLength: 1 pattern: ^[\x09\x20-\x7E]+$ title: Value description: The header value additionalProperties: false type: object required: - key - value title: CustomSIPHeader CustomSIPHeaderWithDynamicVariable: properties: type: type: string const: dynamic title: Type key: type: string maxLength: 64 minLength: 1 pattern: ^[A-Za-z0-9]+(-[A-Za-z0-9]+)*$ title: Key description: The SIP header name (e.g., 'X-Customer-ID') value: type: string minLength: 1 title: Value description: The dynamic variable name to resolve additionalProperties: false type: object required: - type - key - value title: CustomSIPHeaderWithDynamicVariable PhoneNumberTransferDestination: properties: type: type: string const: phone title: Type default: phone phone_number: type: string title: Phone Number additionalProperties: false type: object required: - phone_number title: PhoneNumberTransferDestination SIPUriTransferDestination: properties: type: type: string const: sip_uri title: Type default: sip_uri sip_uri: type: string title: Sip Uri additionalProperties: false type: object required: - sip_uri title: SIPUriTransferDestination PhoneNumberDynamicVariableTransferDestination: properties: type: type: string const: phone_dynamic_variable title: Type default: phone_dynamic_variable phone_number: type: string title: Phone Number additionalProperties: false type: object required: - phone_number title: PhoneNumberDynamicVariableTransferDestination SIPUriDynamicVariableTransferDestination: properties: type: type: string const: sip_uri_dynamic_variable title: Type default: sip_uri_dynamic_variable sip_uri: type: string title: Sip Uri additionalProperties: false type: object required: - sip_uri title: SIPUriDynamicVariableTransferDestination TransferTypeEnum: type: string enum: - blind - conference - sip_refer title: TransferTypeEnum UUITransferConfig: properties: data: type: string maxLength: 8192 title: Data description: >- UUI payload to send on SIP REFER transfers. Supports inline dynamic variables and is hex-encoded at transfer time. protocol_discriminator: anyOf: - type: string pattern: ^[0-9A-Fa-f]{2}$ - type: 'null' title: Protocol Discriminator description: >- Optional one-octet protocol discriminator (two hex digits, e.g. '00'). Required by platforms such as Genesys Cloud, which otherwise strip the first octet of the payload. Leave unset for platforms like Talkdesk that expect a bare hex payload. protocol_discriminator_mode: type: string enum: - prefix - pd_parameter title: Protocol Discriminator Mode description: >- How to attach protocol_discriminator. 'prefix' prepends the octet to the hex payload (User-to-User=XX;encoding=hex). 'pd_parameter' sends it as a separate parameter (User-to-User=;pd=XX;encoding=hex). Ignored when protocol_discriminator is unset. default: prefix additionalProperties: false type: object required: - data title: UUITransferConfig description: >- User-to-User Information envelope for SIP REFER transfers (RFC 7433). Outbound payloads are hex-encoded (the only encoding RFC 7433 defines). The protocol discriminator axis lets per-platform formats (Talkdesk, Genesys, ...) be expressed by configuration rather than scattered transfer flags. Further axes (ASCII encoding, header name, purpose/content parameters) can be added here without touching the transfer model. PostDialDigitsStatic: properties: type: type: string const: static title: Type default: static value: type: string minLength: 1 pattern: ^[0-9*#wW]*$ title: Value description: >- DTMF digits to send after call connects (e.g., 'ww1234' for extension) additionalProperties: false type: object required: - value title: PostDialDigitsStatic PostDialDigitsDynamicVariable: properties: type: type: string const: dynamic title: Type default: dynamic value: type: string minLength: 1 title: Value description: The dynamic variable name to resolve additionalProperties: false type: object required: - value title: PostDialDigitsDynamicVariable ConversationalConfigAPIModelWorkflowOverride-Input: properties: turn: anyOf: - $ref: '#/components/schemas/TurnConfigWorkflowOverride' - type: 'null' description: Configuration for turn detection tts: anyOf: - $ref: '#/components/schemas/TTSConversationalConfigWorkflowOverride' - type: 'null' description: Configuration for conversational text to speech conversation: anyOf: - $ref: '#/components/schemas/ConversationConfigWorkflowOverride' - type: 'null' description: Configuration for conversational events language_presets: anyOf: - additionalProperties: $ref: '#/components/schemas/LanguagePreset' type: object - type: 'null' title: Language Presets description: Language presets for conversations vad: anyOf: - $ref: '#/components/schemas/VADConfigWorkflowOverride' - type: 'null' description: Configuration for voice activity detection agent: anyOf: - $ref: '#/components/schemas/AgentConfigAPIModelWorkflowOverride-Input' - type: 'null' description: Agent specific configuration type: object title: ConversationalConfigAPIModelWorkflowOverride example: agent: disable_first_message_interruptions: false dynamic_variables: dynamic_variable_placeholders: user_name: John Doe first_message: Hello, how can I help you today? language: en prompt: knowledge_base: [] llm: gemini-2.0-flash-001 max_tokens: -1 prompt: >- You are a helpful assistant that can answer questions about the topic of the conversation. temperature: 0 tool_ids: [] conversation: client_events: - audio - interruption max_duration_seconds: 600 tts: performance: latency voice_id: ME9RtCnWp5vX2LhJdF3k turn: interruption_ignore_term_languages: [] interruption_ignore_terms: [] merge_with_default_ignore_terms: false mode: turn retranscribe_on_turn_timeout: false silence_end_call_timeout: -1 soft_timeout_config: message: Hhmmmm...yeah. timeout_seconds: -1 use_llm_generated_message: false speculative_turn: false spelling_patience: auto transcribe_on_disabled_interruptions: false turn_eagerness: normal turn_model: turn_v3 turn_timeout: 7 KnowledgeBaseLocator: properties: type: $ref: '#/components/schemas/KnowledgeBaseDocumentType' description: The type of the knowledge base name: type: string title: Name description: The name of the knowledge base id: type: string title: Id description: The ID of the knowledge base usage_mode: $ref: '#/components/schemas/DocumentUsageModeEnum' description: The usage mode of the knowledge base default: auto type: object required: - type - name - id title: KnowledgeBaseLocator example: id: '123' name: My Knowledge Base type: file usage_mode: auto EntryBehavior: type: string enum: - generate_immediately - wait_for_user - auto title: EntryBehavior default: auto WorkflowToolLocator: properties: tool_id: type: string title: Tool Id schema_overrides: anyOf: - additionalProperties: oneOf: - $ref: '#/components/schemas/ConstantSchemaOverride' - $ref: '#/components/schemas/DynamicVariableSchemaOverride' - $ref: '#/components/schemas/LLMSchemaOverride' - $ref: '#/components/schemas/OmitSchemaOverride' discriminator: propertyName: source mapping: constant: $ref: '#/components/schemas/ConstantSchemaOverride' dynamic_variable: $ref: '#/components/schemas/DynamicVariableSchemaOverride' llm: $ref: '#/components/schemas/LLMSchemaOverride' omit: $ref: '#/components/schemas/OmitSchemaOverride' type: object - type: 'null' title: Schema Overrides description: >- Per-node parameter overrides applied on top of the tool's own configuration. Keys are dotted parameter paths (webhook tools prefix keys with path_params./query_params./request_body.). These take precedence over any overrides already defined on the tool itself. type: object required: - tool_id title: WorkflowToolLocator SoftTimeoutConfig: properties: timeout_seconds: type: number title: Timeout Seconds description: >- Time in seconds before showing the predefined message while waiting for LLM response. Set to -1 to disable. default: -1 message: type: string maxLength: 200 minLength: 1 title: Message description: >- Message to show when the first soft timeout is reached while waiting for LLM response. Supports dynamic variables (e.g., {{system__time}}, {{custom_variable}}). default: Hhmmmm...yeah. x-convai-client-override: true x-convai-language-override: true additional_soft_timeout_messages: items: type: string type: array maxItems: 7 title: Additional Soft Timeout Messages description: >- Extra static filler messages for subsequent soft timeouts in the same LLM generation. The first timeout uses `message`. If fewer messages are configured than `max_soft_timeouts_per_generation`, the last configured message is repeated; otherwise a built-in filler is used. x-convai-client-override: true x-convai-language-override: true use_llm_generated_message: type: boolean title: Use Llm Generated Message description: >- If enabled, the soft timeout message will be generated dynamically instead of using the static message. default: false randomize_fillers: type: boolean title: Randomize Fillers description: >- If enabled, shuffle the order of static soft timeout messages once at the start of each turn. Only applies when use_llm_generated_message is false. default: false max_soft_timeouts_per_generation: type: integer maximum: 8 minimum: 1 title: Max Soft Timeouts Per Generation description: >- Maximum filler messages while waiting for a single LLM response. Fires every timeout_seconds until the LLM streams content or this limit is reached. default: 1 llm_generated_message_prompt_override: anyOf: - type: string maxLength: 1000 minLength: 1 - type: 'null' title: Llm Generated Message Prompt Override description: >- Custom prompt for generating the soft timeout filler message when use_llm_generated_message is enabled. Recent conversation context is provided as a separate user message. If not set, the default prompt will be used. Supports dynamic variables (e.g., {{system__time}}, {{custom_variable}}). examples: - >- Output a SHORT neutral filler phrase (1-4 words MAX) acknowledging you heard the user. disable_until_first_user_message: type: boolean title: Disable Until First User Message description: >- When true, soft timeout fillers are suppressed until the conversation has at least one real user message. Prevents fillers during the agent's opening turn (e.g. workflow generate-immediately / tool calls before the user speaks). default: false type: object title: SoftTimeoutConfig description: >- Configuration for soft timeout functionality during LLM response generation. example: message: Hhmmmm...yeah. timeout_seconds: 2 use_llm_generated_message: false FileInputConfig: properties: enabled: type: boolean title: Enabled description: >- When enabled, users may attach images or PDFs in chat when the LLM supports multimodal input. default: true max_files_in_memory: type: integer maximum: 30 minimum: 1 title: Max Files In Memory description: >- Number of most-recent files kept in memory during a conversation. Older files are summarized and their bytes freed. default: 10 max_files_per_conversation: type: integer title: Max Files Per Conversation description: >- Total files a user can upload in one conversation. Uploads are billed per file. Use -1 for no limit, or a value >= max_files_in_memory. default: 10 type: object title: FileInputConfig BackgroundSoundConfig: properties: source_type: anyOf: - $ref: '#/components/schemas/BackgroundSoundSourceType' - type: 'null' description: The type of background sound source. source_id: anyOf: - $ref: '#/components/schemas/BackgroundSoundPresetId' - type: 'null' description: Identifier for the sound source. volume: type: number maximum: 1 minimum: 0.01 title: Volume description: Volume level for background sound (0.01 to 1.0). default: 0.15 crossfade_loop: type: boolean title: Crossfade Loop description: >- Apply a crossfade at the loop boundary to avoid audible pops when the sound loops. default: true type: object title: BackgroundSoundConfig DynamicVariablesConfig-Output: properties: dynamic_variable_placeholders: additionalProperties: $ref: '#/components/schemas/DynamicVariableValueType-Output' type: object title: Dynamic Variable Placeholders description: A dictionary of dynamic variable placeholders and their values type: object title: DynamicVariablesConfig example: dynamic_variable_placeholders: user_name: John Doe PromptAgentAPIModel: properties: prompt: type: string title: Prompt description: The prompt for the agent default: '' x-convai-client-override: true llm: $ref: '#/components/schemas/LLM' description: >- The LLM to query with the prompt and the chat history. If using data residency, the LLM must be supported in the data residency environment default: gemini-2.5-flash x-convai-client-override: true reasoning_effort: anyOf: - $ref: '#/components/schemas/LLMReasoningEffort' - type: 'null' description: Reasoning effort of the model. Only available for some models. thinking_budget: anyOf: - type: integer - type: 'null' title: Thinking Budget description: >- Max number of tokens used for thinking. Use 0 to turn off if supported by the model. enable_reasoning_summary: type: boolean title: Enable Reasoning Summary description: >- Enable model reasoning summaries. When disabled, we do not request summaries from provider if possible for faster TTFB. Not ZRM compatible. default: false temperature: anyOf: - type: number - type: 'null' title: Temperature description: >- The temperature for the LLM. Defaults to 0. Set to null to omit the parameter from the LLM request entirely (useful for custom LLMs that reject the temperature field). default: 0 max_tokens: type: integer title: Max Tokens description: If greater than 0, maximum number of tokens the LLM can predict default: -1 tool_ids: items: type: string type: array title: Tool Ids description: A list of IDs of tools used by the agent x-convai-client-override: true built_in_tools: $ref: '#/components/schemas/BuiltInTools' description: Built-in system tools to be used by the agent mcp_server_ids: items: type: string type: array maxItems: 10 title: Mcp Server Ids description: A list of MCP server ids to be used by the agent native_mcp_server_ids: items: type: string type: array maxItems: 10 title: Native Mcp Server Ids description: A list of Native MCP server ids to be used by the agent x-convai-client-override: true knowledge_base: items: $ref: '#/components/schemas/KnowledgeBaseLocator' type: array title: Knowledge Base description: A list of knowledge bases to be used by the agent x-convai-client-override: true custom_llm: anyOf: - $ref: '#/components/schemas/CustomLLM' - type: 'null' description: Definition for a custom LLM if LLM field is set to 'CUSTOM_LLM' ignore_default_personality: anyOf: - type: boolean - type: 'null' title: Ignore Default Personality description: >- Whether to remove the default personality lines from the system prompt default: false rag: $ref: '#/components/schemas/RagConfig' description: Configuration for RAG timezone: anyOf: - type: string - type: 'null' title: Timezone description: >- Timezone for displaying current time in system prompt. If set, the current time will be included in the system prompt using this timezone. Must be a valid timezone name (e.g., 'America/New_York', 'Europe/London', 'UTC'). Recommended for accurate time-aware responses; without this, the agent has no knowledge of the current date/time unless you provide it via dynamic variables or tools, which can lead to incorrect or hallucinated time references. backup_llm_config: oneOf: - $ref: '#/components/schemas/BackupLLMDefault' - $ref: '#/components/schemas/BackupLLMDisabled' - $ref: '#/components/schemas/BackupLLMOverride' title: Backup Llm Config description: >- Configuration for backup LLM cascading. Can be disabled, use system defaults, or specify custom order. discriminator: propertyName: preference mapping: default: $ref: '#/components/schemas/BackupLLMDefault' disabled: $ref: '#/components/schemas/BackupLLMDisabled' override: $ref: '#/components/schemas/BackupLLMOverride' cascade_timeout_seconds: type: number maximum: 15 minimum: 2 title: Cascade Timeout Seconds description: >- Time in seconds before cascading to backup LLM. Must be between 2 and 15 seconds. default: 4 type: object title: PromptAgentAPIModel example: knowledge_base: [] llm: gemini-2.0-flash-001 max_tokens: -1 prompt: >- You are a helpful assistant that can answer questions about the topic of the conversation. temperature: 0 tool_ids: [] PromptEvaluationCriteria: properties: id: type: string title: Id description: The unique identifier for the evaluation criteria name: type: string title: Name type: type: string const: prompt title: Type description: The type of evaluation criteria default: prompt conversation_goal_prompt: type: string maxLength: 2000 title: Conversation Goal Prompt description: The prompt that the agent should use to evaluate the conversation use_knowledge_base: type: boolean title: Use Knowledge Base description: >- When evaluating the prompt, should the agent's knowledge base be used. default: false scope: $ref: '#/components/schemas/AnalysisScope' description: >- The scope of transcript context used when evaluating this criterion. 'conversation' uses the full transcript; 'agent' uses only the portion where the defining agent was active. llm: anyOf: - $ref: '#/components/schemas/LLM' - type: 'null' description: >- LLM model to use for this evaluation criteria. If not set, uses agent's analysis_llm default. scoring_mode: $ref: '#/components/schemas/CriteriaScoringMode' description: >- How this criterion is scored. 'binary' resolves to success/failure/unknown. 'numeric_uniform' returns a number on the [0, max_score] scale which is normalized into the aggregate conversation success percentage. default: binary max_score: type: integer title: Max Score description: >- Maximum value of the numeric score scale (minimum is always 0). Only used when scoring_mode is 'numeric_uniform'. default: 100 score_instructions: anyOf: - type: string maxLength: 2000 - type: 'null' title: Score Instructions description: >- Optional free-text instructions describing how to assign values on the numeric scale. Only used when scoring_mode is 'numeric_uniform'. type: object required: - id - name - conversation_goal_prompt title: PromptEvaluationCriteria description: >- An evaluation using the transcript and a prompt for a yes/no achieved answer examples: - conversation_goal_prompt: Determine whether the agent fully resolved the user's issue. id: criterion_binary_001 max_score: 100 name: Issue resolved scope: conversation scoring_mode: binary use_knowledge_base: false - conversation_goal_prompt: Rate how completely and correctly the issue was resolved. id: criterion_numeric_001 max_score: 100 name: Resolution quality scope: conversation score_instructions: >- 0 means unresolved, 50 means partially resolved, 100 means fully resolved with correct details. scoring_mode: numeric_uniform use_knowledge_base: false EmbedVariant: type: string enum: - tiny - compact - full - expandable title: EmbedVariant default: full WidgetPlacement: type: string enum: - top-left - top - top-right - bottom-left - bottom - bottom-right title: WidgetPlacement default: bottom-right WidgetExpandable: type: string enum: - never - mobile - desktop - always title: WidgetExpandable default: never OrbAvatar: properties: type: type: string const: orb title: Type description: The type of the avatar default: orb color_1: type: string title: Color 1 description: The first color of the avatar default: '#2792dc' color_2: type: string title: Color 2 description: The second color of the avatar default: '#9ce6e6' type: object title: OrbAvatar example: color_1: '#2792dc' color_2: '#9ce6e6' type: orb URLAvatar: properties: type: type: string const: url title: Type description: The type of the avatar default: url custom_url: type: string title: Custom Url description: The custom URL of the avatar default: '' type: object title: URLAvatar ImageAvatar: properties: type: type: string const: image title: Type description: The type of the avatar default: image url: type: string title: Url description: The URL of the avatar default: '' type: object title: ImageAvatar WidgetFeedbackMode: type: string enum: - none - during - end title: WidgetFeedbackMode default: none WidgetEndFeedbackConfig: properties: type: $ref: '#/components/schemas/WidgetEndFeedbackType' description: The type of feedback to collect at the end of the conversation default: rating type: object title: WidgetEndFeedbackConfig AllowlistItem: properties: hostname: type: string title: Hostname description: The hostname of the allowed origin type: object required: - hostname title: AllowlistItem WidgetTextContents: properties: main_label: anyOf: - type: string - type: 'null' title: Main Label description: Call to action displayed inside the compact and full variants. start_call: anyOf: - type: string - type: 'null' title: Start Call description: Text and ARIA label for the start call button. start_chat: anyOf: - type: string - type: 'null' title: Start Chat description: Text and ARIA label for the start chat button (text only) new_call: anyOf: - type: string - type: 'null' title: New Call description: >- Text and ARIA label for the new call button. Displayed when the caller already finished at least one call in order ot start the next one. end_call: anyOf: - type: string - type: 'null' title: End Call description: Text and ARIA label for the end call button. mute_microphone: anyOf: - type: string - type: 'null' title: Mute Microphone description: ARIA label for the mute microphone button. change_language: anyOf: - type: string - type: 'null' title: Change Language description: ARIA label for the change language dropdown. collapse: anyOf: - type: string - type: 'null' title: Collapse description: ARIA label for the collapse button. expand: anyOf: - type: string - type: 'null' title: Expand description: ARIA label for the expand button. copied: anyOf: - type: string - type: 'null' title: Copied description: Text displayed when the user copies a value using the copy button. accept_terms: anyOf: - type: string - type: 'null' title: Accept Terms description: Text and ARIA label for the accept terms button. dismiss_terms: anyOf: - type: string - type: 'null' title: Dismiss Terms description: Text and ARIA label for the cancel terms button. listening_status: anyOf: - type: string - type: 'null' title: Listening Status description: Status displayed when the agent is listening. speaking_status: anyOf: - type: string - type: 'null' title: Speaking Status description: Status displayed when the agent is speaking. connecting_status: anyOf: - type: string - type: 'null' title: Connecting Status description: Status displayed when the agent is connecting. chatting_status: anyOf: - type: string - type: 'null' title: Chatting Status description: Status displayed when the agent is chatting (text only) input_label: anyOf: - type: string - type: 'null' title: Input Label description: ARIA label for the text message input. input_placeholder: anyOf: - type: string - type: 'null' title: Input Placeholder description: Placeholder text for the text message input. input_placeholder_text_only: anyOf: - type: string - type: 'null' title: Input Placeholder Text Only description: Placeholder text for the text message input (text only) input_placeholder_new_conversation: anyOf: - type: string - type: 'null' title: Input Placeholder New Conversation description: >- Placeholder text for the text message input when starting a new conversation (text only) user_ended_conversation: anyOf: - type: string - type: 'null' title: User Ended Conversation description: Information message displayed when the user ends the conversation. agent_ended_conversation: anyOf: - type: string - type: 'null' title: Agent Ended Conversation description: Information message displayed when the agent ends the conversation. conversation_id: anyOf: - type: string - type: 'null' title: Conversation Id description: Text label used next to the conversation ID. error_occurred: anyOf: - type: string - type: 'null' title: Error Occurred description: Text label used when an error occurs. copy_id: anyOf: - type: string - type: 'null' title: Copy Id description: Text and ARIA label used for the copy ID button. initiate_feedback: anyOf: - type: string - type: 'null' title: Initiate Feedback description: Text displayed to prompt the user for feedback. request_follow_up_feedback: anyOf: - type: string - type: 'null' title: Request Follow Up Feedback description: Text displayed to request additional feedback details. thanks_for_feedback: anyOf: - type: string - type: 'null' title: Thanks For Feedback description: Text displayed to thank the user for providing feedback. thanks_for_feedback_details: anyOf: - type: string - type: 'null' title: Thanks For Feedback Details description: Additional text displayed explaining the value of user feedback. follow_up_feedback_placeholder: anyOf: - type: string - type: 'null' title: Follow Up Feedback Placeholder description: Placeholder text for the follow-up feedback input field. submit: anyOf: - type: string - type: 'null' title: Submit description: Text and ARIA label for the submit button. go_back: anyOf: - type: string - type: 'null' title: Go Back description: Text and ARIA label for the go back button. send_message: anyOf: - type: string - type: 'null' title: Send Message description: Text and ARIA label for the send message button. text_mode: anyOf: - type: string - type: 'null' title: Text Mode description: Text and ARIA label for the switch to text mode button. voice_mode: anyOf: - type: string - type: 'null' title: Voice Mode description: Text and ARIA label for the switch to voice mode button. switched_to_text_mode: anyOf: - type: string - type: 'null' title: Switched To Text Mode description: Toast notification displayed when switching to text mode. switched_to_voice_mode: anyOf: - type: string - type: 'null' title: Switched To Voice Mode description: Toast notification displayed when switching to voice mode. copy: anyOf: - type: string - type: 'null' title: Copy description: Text and ARIA label for the copy button. download: anyOf: - type: string - type: 'null' title: Download description: Text and ARIA label for the download button. wrap: anyOf: - type: string - type: 'null' title: Wrap description: Text and ARIA label for the wrap toggle button. agent_working: anyOf: - type: string - type: 'null' title: Agent Working description: Status text displayed when the agent is processing a tool call. agent_done: anyOf: - type: string - type: 'null' title: Agent Done description: >- Status text displayed when the agent finishes processing a tool call. agent_error: anyOf: - type: string - type: 'null' title: Agent Error description: >- Status text displayed when the agent encounters an error during a tool call. attach_file: anyOf: - type: string - type: 'null' title: Attach File description: Text and ARIA label for the attach file button. remove_file: anyOf: - type: string - type: 'null' title: Remove File description: ARIA label for the remove file button. file_upload_error: anyOf: - type: string - type: 'null' title: File Upload Error description: Error message displayed when a file fails to upload. file_type_unsupported: anyOf: - type: string - type: 'null' title: File Type Unsupported description: >- Error message displayed when an unsupported file type is selected. Followed by the list of accepted types. file_too_large: anyOf: - type: string - type: 'null' title: File Too Large description: Error message displayed when a file exceeds the maximum size limit. file_limit_reached: anyOf: - type: string - type: 'null' title: File Limit Reached description: >- Error message displayed when the maximum number of files for a conversation is reached. typing_indicator: anyOf: - type: string - type: 'null' title: Typing Indicator description: Status text displayed while the agent is typing. type: object title: WidgetTextContents WidgetStyles: properties: base: anyOf: - type: string - type: 'null' title: Base description: The base background color. base_hover: anyOf: - type: string - type: 'null' title: Base Hover description: The color of the base background when hovered. base_active: anyOf: - type: string - type: 'null' title: Base Active description: The color of the base background when active (clicked). base_border: anyOf: - type: string - type: 'null' title: Base Border description: The color of the border against the base background. base_subtle: anyOf: - type: string - type: 'null' title: Base Subtle description: The color of subtle text against the base background. base_primary: anyOf: - type: string - type: 'null' title: Base Primary description: The color of primary text against the base background. base_error: anyOf: - type: string - type: 'null' title: Base Error description: The color of error text against the base background. accent: anyOf: - type: string - type: 'null' title: Accent description: The accent background color. accent_hover: anyOf: - type: string - type: 'null' title: Accent Hover description: The color of the accent background when hovered. accent_active: anyOf: - type: string - type: 'null' title: Accent Active description: The color of the accent background when active (clicked). accent_border: anyOf: - type: string - type: 'null' title: Accent Border description: The color of the border against the accent background. accent_subtle: anyOf: - type: string - type: 'null' title: Accent Subtle description: The color of subtle text against the accent background. accent_primary: anyOf: - type: string - type: 'null' title: Accent Primary description: The color of primary text against the accent background. overlay_padding: anyOf: - type: number - type: 'null' title: Overlay Padding description: The padding around the edges of the viewport. button_radius: anyOf: - type: number - type: 'null' title: Button Radius description: The radius of the buttons. input_radius: anyOf: - type: number - type: 'null' title: Input Radius description: The radius of the input fields. bubble_radius: anyOf: - type: number - type: 'null' title: Bubble Radius description: The radius of the chat bubbles. sheet_radius: anyOf: - type: number - type: 'null' title: Sheet Radius description: The default radius of sheets. compact_sheet_radius: anyOf: - type: number - type: 'null' title: Compact Sheet Radius description: The radius of the sheet in compact mode. dropdown_sheet_radius: anyOf: - type: number - type: 'null' title: Dropdown Sheet Radius description: The radius of the dropdown sheet. type: object title: WidgetStyles WidgetLanguagePreset: properties: text_contents: anyOf: - $ref: '#/components/schemas/WidgetTextContents' - type: 'null' description: The text contents for the selected language text_contents_translation: anyOf: - $ref: '#/components/schemas/WidgetTextContentsTranslation' - type: 'null' description: The translation cache for the text contents terms_text: anyOf: - type: string - type: 'null' title: Terms Text description: The text to display for terms and conditions in this language terms_html: anyOf: - type: string - type: 'null' title: Terms Html description: The HTML to display for terms and conditions in this language terms_key: anyOf: - type: string - type: 'null' title: Terms Key description: The key to display for terms and conditions in this language terms_translation: anyOf: - $ref: '#/components/schemas/WidgetTermsTranslation' - type: 'null' description: The translation cache for the terms type: object title: WidgetLanguagePreset AttachedUserEvaluationRef: properties: source: type: string const: user title: Source analysis_item_id: type: string title: Analysis Item Id description: Id of the referenced user evaluation item. version_id: anyOf: - type: string - type: 'null' title: Version Id description: >- Primary item version whose result feeds scoring. None tracks the item's latest published version. additional_version_ids: items: type: string type: array title: Additional Version Ids description: >- Extra item versions to also run for comparison (A/B). These are executed and stored but excluded from scoring; the primary version_id is the one that scores. scope: $ref: '#/components/schemas/AnalysisScope' description: >- Transcript context ('conversation' or 'agent') used when running this item. default: conversation weight: anyOf: - type: number - type: 'null' title: Weight description: Optional relative weight for aggregate scoring. type: object required: - source - analysis_item_id title: AttachedUserEvaluationRef AttachedSystemEvaluationRef: properties: source: type: string const: system title: Source analysis_item_id: type: string enum: - __system_eval_criteria_sentiment - __system_eval_criteria_frustration title: Analysis Item Id description: Id of the referenced built-in system evaluation. scope: $ref: '#/components/schemas/AnalysisScope' description: >- Transcript context ('conversation' or 'agent') used when running this item. default: conversation weight: anyOf: - type: number - type: 'null' title: Weight description: Optional relative weight for aggregate scoring. type: object required: - source - analysis_item_id title: AttachedSystemEvaluationRef AttachedUserDataCollectionRef: properties: source: type: string const: user title: Source analysis_item_id: type: string title: Analysis Item Id description: Id of the referenced user data-collection item. version_id: anyOf: - type: string - type: 'null' title: Version Id description: >- Pinned item version. None tracks the item's latest published version. scope: $ref: '#/components/schemas/AnalysisScope' description: >- Transcript context ('conversation' or 'agent') used when running this item. default: conversation type: object required: - source - analysis_item_id title: AttachedUserDataCollectionRef AttachedSystemDataCollectionRef: properties: source: type: string const: system title: Source analysis_item_id: type: string const: __system_data_collection_topic title: Analysis Item Id description: Id of the referenced built-in system data-collection item. scope: $ref: '#/components/schemas/AnalysisScope' description: >- Transcript context ('conversation' or 'agent') used when running this item. default: conversation type: object required: - source - analysis_item_id title: AttachedSystemDataCollectionRef ConversationConfigClientOverrideConfig: properties: turn: $ref: '#/components/schemas/TurnConfigOverrideConfig' description: Configures overrides for nested fields. tts: $ref: '#/components/schemas/TTSConversationalConfigOverrideConfig' description: Configures overrides for nested fields. conversation: $ref: '#/components/schemas/ConversationConfigOverrideConfig' description: Configures overrides for nested fields. agent: $ref: '#/components/schemas/AgentConfigOverrideConfig' description: Configures overrides for nested fields. type: object title: ConversationConfigClientOverrideConfig ConversationInitiationClientDataWebhook: properties: url: type: string title: Url description: The URL to send the webhook to request_headers: additionalProperties: anyOf: - type: string - $ref: '#/components/schemas/ConvAISecretLocator' type: object title: Request Headers description: The headers to send with the webhook request type: object required: - url - request_headers title: ConversationInitiationClientDataWebhook example: request_headers: Content-Type: application/json url: https://example.com/webhook ConvAIWebhooks: properties: post_call_webhook_id: anyOf: - type: string - type: 'null' title: Post Call Webhook Id events: items: $ref: '#/components/schemas/WebhookEventType' type: array title: Events description: >- List of event types to send via webhook. Options: transcript, audio, call_initiation_failure, unredacted_transcript, unredacted_audio. Unredacted events contain sensitive conversation data and must only be sent to explicitly authorized endpoints. transcript_format: $ref: '#/components/schemas/WebhookTranscriptFormat' description: Format for transcript webhooks. default: json type: object title: ConvAIWebhooks AttachedTestModel: properties: test_id: type: string title: Test Id workflow_node_id: anyOf: - type: string - type: 'null' title: Workflow Node Id type: object required: - test_id title: AttachedTestModel FocusGuardrail: properties: is_enabled: type: boolean title: Is Enabled default: false type: object title: FocusGuardrail PromptInjectionGuardrail: properties: is_enabled: type: boolean title: Is Enabled default: false type: object title: PromptInjectionGuardrail ContentGuardrail: properties: execution_mode: $ref: '#/components/schemas/GuardrailExecutionMode' default: streaming config: $ref: '#/components/schemas/ContentConfig' trigger_action: oneOf: - $ref: '#/components/schemas/EndCallTriggerAction' - $ref: '#/components/schemas/RetryTriggerAction' title: Trigger Action discriminator: propertyName: type mapping: end_call: $ref: '#/components/schemas/EndCallTriggerAction' retry: $ref: '#/components/schemas/RetryTriggerAction' type: object title: ContentGuardrail ModerationGuardrail: properties: execution_mode: $ref: '#/components/schemas/GuardrailExecutionMode' default: streaming config: $ref: '#/components/schemas/ModerationConfig' type: object title: ModerationGuardrail CustomGuardrail: properties: config: $ref: '#/components/schemas/CustomGuardrailsConfig' type: object title: CustomGuardrail description: Container for custom guardrails, matching ModerationGuardrail pattern. ConversationHistoryRedactionConfig: properties: enabled: type: boolean title: Enabled description: Whether conversation history redaction is enabled default: false entities: items: $ref: '#/components/schemas/ConfigEntityType' type: array title: Entities description: >- The entities to redact from the conversation transcript, audio and analysis. Use top-level types like 'name', 'email_address', or dot notation for specific subtypes like 'name.name_given'. type: object title: ConversationHistoryRedactionConfig AlertingMonitorConfig: properties: threshold: anyOf: - type: number maximum: 1 minimum: 0 - type: 'null' title: Threshold description: Failure rate threshold at which this monitor can notify. relative_increase_threshold: anyOf: - type: number maximum: 10 minimum: 0 - type: 'null' title: Relative Increase Threshold description: >- Relative increase over the trailing baseline at which this monitor can notify (0.2 = 20% above baseline, 0 = any failure). min_failure_count: anyOf: - type: integer minimum: 1 - type: 'null' title: Min Failure Count description: Minimum failures in the window before this monitor can fire. min_history_bucket_count: anyOf: - type: integer minimum: 1 - type: 'null' title: Min History Bucket Count description: >- Minimum trailing buckets with traffic before spike detection can fire. min_sample_count: anyOf: - type: integer minimum: 1 - type: 'null' title: Min Sample Count description: Minimum samples in the window before this monitor can fire. suspect_trigger_threshold: anyOf: - type: integer maximum: 10 minimum: 1 - type: 'null' title: Suspect Trigger Threshold description: >- How many suspect buckets within the lookback window are required to promote a suspect to an alert. auto_resolve_after_inactive_minutes: anyOf: - type: integer minimum: 1 - type: 'null' title: Auto Resolve After Inactive Minutes description: >- How many minutes an alert can stay inactive before it is auto-resolved. type: object title: AlertingMonitorConfig AlertingWebhookNotifierResponse: properties: type: type: string const: webhook title: Type default: webhook webhook_id: type: string title: Webhook Id type: object required: - webhook_id title: AlertingWebhookNotifierResponse AlertingIntegrationNotifierResponse: properties: type: type: string const: integration title: Type default: integration connection_id: type: string title: Connection Id type: object required: - connection_id title: AlertingIntegrationNotifierResponse SIPTrunkTransportEnum: type: string enum: - auto - udp - tcp - tls title: SIPTrunkTransportEnum SIPMediaEncryptionEnum: type: string enum: - disabled - allowed - required title: SIPMediaEncryptionEnum MediaCodec: type: string enum: - G722/8000 - PCMU/8000 - PCMA/8000 title: MediaCodec WorkflowExpressionConditionModel-Output: properties: label: anyOf: - type: string - type: 'null' title: Label description: >- Optional human-readable label for the condition used throughout the UI. type: type: string const: expression title: Type default: expression expression: $ref: '#/components/schemas/ASTNode-Output' description: Expression to evaluate. type: object required: - expression title: WorkflowExpressionConditionModel Position-Output: properties: x: type: number title: X default: 0 'y': type: number title: 'Y' default: 0 type: object required: - x - 'y' title: Position ConversationalConfigAPIModelWorkflowOverride-Output: properties: turn: anyOf: - $ref: '#/components/schemas/TurnConfigWorkflowOverride' - type: 'null' description: Configuration for turn detection tts: anyOf: - $ref: '#/components/schemas/TTSConversationalConfigWorkflowOverride' - type: 'null' description: Configuration for conversational text to speech conversation: anyOf: - $ref: '#/components/schemas/ConversationConfigWorkflowOverride' - type: 'null' description: Configuration for conversational events language_presets: anyOf: - additionalProperties: $ref: '#/components/schemas/LanguagePreset' type: object - type: 'null' title: Language Presets description: Language presets for conversations vad: anyOf: - $ref: '#/components/schemas/VADConfigWorkflowOverride' - type: 'null' description: Configuration for voice activity detection agent: anyOf: - $ref: '#/components/schemas/AgentConfigAPIModelWorkflowOverride-Output' - type: 'null' description: Agent specific configuration type: object title: ConversationalConfigAPIModelWorkflowOverride example: agent: disable_first_message_interruptions: false dynamic_variables: dynamic_variable_placeholders: user_name: John Doe first_message: Hello, how can I help you today? language: en prompt: knowledge_base: [] llm: gemini-2.0-flash-001 max_tokens: -1 prompt: >- You are a helpful assistant that can answer questions about the topic of the conversation. temperature: 0 tool_ids: [] conversation: client_events: - audio - interruption max_duration_seconds: 600 tts: performance: latency voice_id: ME9RtCnWp5vX2LhJdF3k turn: interruption_ignore_term_languages: [] interruption_ignore_terms: [] merge_with_default_ignore_terms: false mode: turn retranscribe_on_turn_timeout: false silence_end_call_timeout: -1 soft_timeout_config: message: Hhmmmm...yeah. timeout_seconds: -1 use_llm_generated_message: false speculative_turn: false spelling_patience: auto transcribe_on_disabled_interruptions: false turn_eagerness: normal turn_model: turn_v3 turn_timeout: 7 CartesiaSpeedPreset: type: string enum: - slow - normal - fast title: CartesiaSpeedPreset CartesiaEmotion: type: string enum: - happy - excited - enthusiastic - elated - euphoric - triumphant - amazed - surprised - flirtatious - joking/comedic - curious - content - peaceful - serene - calm - grateful - affectionate - trust - sympathetic - anticipation - mysterious - angry - mad - outraged - frustrated - agitated - threatened - disgusted - contempt - envious - sarcastic - ironic - sad - dejected - melancholic - disappointed - hurt - guilty - bored - tired - rejected - nostalgic - wistful - apologetic - hesitant - insecure - confused - resigned - anxious - panicked - alarmed - scared - neutral - proud - confident - distant - skeptical - contemplative - determined title: CartesiaEmotion BackgroundSoundSourceType: type: string enum: - preset title: BackgroundSoundSourceType description: The type of background sound source. BackgroundSoundPresetId: type: string enum: - office2 - office1 - restaurant - city - typing - elevator1 - elevator2 - elevator3 - elevator4 title: BackgroundSoundPresetId description: Predefined background sound preset identifiers. TurnConfigOverride: properties: soft_timeout_config: anyOf: - $ref: '#/components/schemas/SoftTimeoutConfigOverride' - type: 'null' description: >- Configuration for soft timeout functionality. Provides immediate feedback during longer LLM responses. type: object title: TurnConfigOverride example: soft_timeout_config: message: Hhmmmm...yeah. TTSConversationalConfigOverride: properties: voice_id: type: string title: Voice Id description: The voice ID to use for TTS performance: $ref: '#/components/schemas/TTSPerformance' description: >- User-facing TTS performance tier (latency or quality). The concrete provider/model is selected by the voice-server based on this value. pronunciation_dictionary_locators: anyOf: - items: $ref: >- #/components/schemas/PydanticPronunciationDictionaryVersionLocator type: array - type: 'null' title: Pronunciation Dictionary Locators description: The pronunciation dictionary locators x-convai-client-override: true type: object title: TTSConversationalConfigOverride ConversationConfigOverride: properties: text_only: anyOf: - type: boolean - type: 'null' title: Text Only description: >- If enabled audio will not be processed and only text will be used, use to avoid audio pricing. x-convai-client-override: true max_duration_seconds: anyOf: - type: integer - type: 'null' title: Max Duration Seconds description: The maximum duration of a conversation in seconds x-convai-client-override: true type: object title: ConversationConfigOverride example: max_duration_seconds: 600 AgentConfigOverride: properties: first_message: anyOf: - type: string - type: 'null' title: First Message description: >- If non-empty, the first message the agent will say. If empty, the agent waits for the user to start the discussion. x-convai-client-override: true x-convai-language-override: true language: anyOf: - type: string - type: 'null' title: Language description: Language of the agent - used for ASR and TTS x-convai-client-override: true max_conversation_duration_message: anyOf: - type: string - type: 'null' title: Max Conversation Duration Message description: >- If non-empty, the message the agent will send when max conversation duration is reached. x-convai-client-override: true x-convai-language-override: true prompt: anyOf: - $ref: '#/components/schemas/PromptAgentAPIModelOverride' - type: 'null' description: The prompt for the agent type: object title: AgentConfigOverride example: first_message: Hello, how can I help you today? language: en prompt: knowledge_base: [] llm: gemini-2.0-flash-001 prompt: >- You are a helpful assistant that can answer questions about the topic of the conversation. tool_ids: [] DynamicVariableValueType-Input: anyOf: - type: string - type: number - type: integer - type: boolean - items: $ref: '#/components/schemas/DynamicVariableNestedValueType-Input' type: array - type: 'null' Verbosity: type: string enum: - auto - concise - thorough title: Verbosity OutputFormat: type: string enum: - plain_text - markdown title: OutputFormat InteractionBudget: type: string enum: - realtime - 5_minutes - 10_minutes - 1_hour title: InteractionBudget LLMReasoningEffort: type: string enum: - none - minimal - low - medium - high - xhigh - max title: LLMReasoningEffort BuiltInToolsWorkflowOverride: properties: end_call: anyOf: - $ref: '#/components/schemas/SystemToolConfig' - type: 'null' description: The end call tool language_detection: anyOf: - $ref: '#/components/schemas/SystemToolConfig' - type: 'null' description: The language detection tool transfer_to_agent: anyOf: - $ref: '#/components/schemas/SystemToolConfig' - type: 'null' description: The transfer to agent tool transfer_to_number: anyOf: - $ref: '#/components/schemas/SystemToolConfig' - type: 'null' description: The transfer to number tool skip_turn: anyOf: - $ref: '#/components/schemas/SystemToolConfig' - type: 'null' description: The skip turn tool play_keypad_touch_tone: anyOf: - $ref: '#/components/schemas/SystemToolConfig' - type: 'null' description: The play DTMF tool voicemail_detection: anyOf: - $ref: '#/components/schemas/SystemToolConfig' - type: 'null' description: The voicemail detection tool additionalProperties: false type: object title: BuiltInToolsWorkflowOverride CustomLLM: properties: url: type: string title: Url description: The URL of the Chat Completions compatible endpoint model_id: anyOf: - type: string - type: 'null' title: Model Id description: The model ID to be used if URL serves multiple models api_key: anyOf: - $ref: '#/components/schemas/ConvAISecretLocator' - $ref: '#/components/schemas/ConvAIEnvVarLocator' - type: 'null' title: Api Key description: >- The API key for authentication. Either a workspace secret reference {'secret_id': '...'} or an environment variable reference {'env_var_label': '...'}. request_headers: additionalProperties: anyOf: - type: string - $ref: '#/components/schemas/ConvAISecretLocator' - $ref: '#/components/schemas/ConvAIDynamicVariable' - $ref: '#/components/schemas/ConvAIEnvVarLocator' type: object title: Request Headers description: Headers that should be included in the request api_version: anyOf: - type: string - type: 'null' title: Api Version description: The API version to use for the request api_type: $ref: '#/components/schemas/CustomLLMAPIType' description: The API type to use (chat_completions, responses or websocket) default: chat_completions type: object required: - url title: CustomLLM RagConfigWorkflowOverride: properties: enabled: anyOf: - type: boolean - type: 'null' title: Enabled embedding_model: anyOf: - $ref: '#/components/schemas/EmbeddingModelEnum' - type: 'null' max_vector_distance: anyOf: - type: number - type: 'null' title: Max Vector Distance description: Maximum vector distance of retrieved chunks. examples: - 0.5 max_documents_length: anyOf: - type: integer - type: 'null' title: Max Documents Length description: Maximum total length of document chunks retrieved from RAG. examples: - '50000' max_retrieved_rag_chunks_count: anyOf: - type: integer - type: 'null' title: Max Retrieved Rag Chunks Count description: >- Maximum number of RAG document chunks to initially retrieve from the vector store. These are then further filtered by vector distance and total length. examples: - 5 num_candidates: anyOf: - type: integer - type: 'null' title: Num Candidates description: >- Number of candidates evaluated in ANN vector search. Higher number means better results, but higher latency. Minimum recommended value is 100. If disabled, the default value is used. examples: - 300 query_rewrite_prompt_override: anyOf: - type: string - type: 'null' title: Query Rewrite Prompt Override description: >- Custom prompt for rewriting user queries before RAG retrieval. The conversation history will be automatically appended at the end. If not set, the default prompt will be used. examples: - >- You are given a conversation between a user and an assistant. Rewrite the last question to be self-contained and clear. type: object title: RagConfigWorkflowOverride BackupLLMDefault: properties: preference: type: string const: default title: Preference default: default type: object title: BackupLLMDefault BackupLLMDisabled: properties: preference: type: string const: disabled title: Preference default: disabled type: object title: BackupLLMDisabled BackupLLMOverride: properties: preference: type: string const: override title: Preference default: override order: items: $ref: '#/components/schemas/LLM' type: array title: Order type: object required: - order title: BackupLLMOverride WebhookToolConfig-Input: properties: type: type: string const: webhook title: Type description: The type of tool default: webhook name: type: string minLength: 0 pattern: ^[a-zA-Z0-9_-]{1,64}$ title: Name description: type: string minLength: 0 title: Description description: Description of when the tool should be used and what it does. response_timeout_secs: type: integer maximum: 300 minimum: 5 title: Response Timeout Secs description: >- The maximum time in seconds to wait for the tool call to complete. Must be between 5 and 300 seconds (inclusive). default: 20 interruption_mode: $ref: '#/components/schemas/ToolInterruptionMode' description: >- Controls whether the user can interrupt the agent around this tool call. 'allow' (default) lets the user interrupt at any time, 'disable_during_tool' suppresses interruptions only while the tool is running, 'disable_during_tool_and_turn' suppresses interruptions while the tool runs and for the agent response that follows it. default: allow pre_tool_speech: $ref: '#/components/schemas/PreToolSpeechMode' description: >- Controls whether the agent speaks before this tool is called. 'auto' (default) decides based on recent tool latency, 'force' always asks the agent to speak, 'off' fully opts out regardless of latency. default: auto assignments: items: $ref: '#/components/schemas/DynamicVariableAssignment' type: array title: Assignments description: >- Configuration for extracting values from tool responses and assigning them to dynamic variables tool_call_sound: anyOf: - $ref: '#/components/schemas/ToolCallSoundType' - type: 'null' description: >- Predefined tool call sound type to play during tool execution. If not specified, no tool call sound will be played. x-convai-client-override: true tool_call_sound_behavior: $ref: '#/components/schemas/ToolCallSoundBehavior' description: >- Determines when the tool call sound should play. 'auto' only plays when there's pre-tool speech, 'always' plays for every tool call. default: auto tool_error_handling_mode: $ref: '#/components/schemas/ToolErrorHandlingMode' description: >- Controls how tool errors are processed before being shared with the agent. 'auto' determines handling based on tool type (summarized for native integrations, hide for others), 'summarized' sends an LLM-generated summary, 'passthrough' sends the raw error, 'hide' does not share the error with the agent. default: auto dynamic_variables: $ref: '#/components/schemas/DynamicVariablesConfig-Input' description: Configuration for dynamic variables execution_mode: $ref: '#/components/schemas/ToolExecutionMode' description: >- Determines when and how the tool executes: 'immediate' executes the tool right away when requested by the LLM, 'post_tool_speech' waits for the agent to finish speaking before executing, 'async' runs the tool in the background without blocking - best for long-running operations. default: immediate api_schema: $ref: '#/components/schemas/WebhookToolApiSchemaConfig-Input' description: >- The schema for the outgoing webhook, including parameters and URL specification type: object required: - name - description - api_schema title: WebhookToolConfig description: A webhook tool is a tool that calls an external webhook from our server example: response_timeout_secs: 20 type: webhook ClientToolConfig-Input: properties: type: type: string const: client title: Type description: The type of tool default: client name: type: string minLength: 0 pattern: ^[a-zA-Z0-9_-]{1,64}$ title: Name description: type: string minLength: 0 title: Description description: Description of when the tool should be used and what it does. response_timeout_secs: type: integer maximum: 120 minimum: 1 title: Response Timeout Secs description: >- The maximum time in seconds to wait for the tool call to complete. Must be between 1 and 120 seconds (inclusive). default: 20 interruption_mode: $ref: '#/components/schemas/ToolInterruptionMode' description: >- Controls whether the user can interrupt the agent around this tool call. 'allow' (default) lets the user interrupt at any time, 'disable_during_tool' suppresses interruptions only while the tool is running, 'disable_during_tool_and_turn' suppresses interruptions while the tool runs and for the agent response that follows it. default: allow pre_tool_speech: $ref: '#/components/schemas/PreToolSpeechMode' description: >- Controls whether the agent speaks before this tool is called. 'auto' (default) decides based on recent tool latency, 'force' always asks the agent to speak, 'off' fully opts out regardless of latency. default: auto assignments: items: $ref: '#/components/schemas/DynamicVariableAssignment' type: array title: Assignments description: >- Configuration for extracting values from tool responses and assigning them to dynamic variables tool_call_sound: anyOf: - $ref: '#/components/schemas/ToolCallSoundType' - type: 'null' description: >- Predefined tool call sound type to play during tool execution. If not specified, no tool call sound will be played. x-convai-client-override: true tool_call_sound_behavior: $ref: '#/components/schemas/ToolCallSoundBehavior' description: >- Determines when the tool call sound should play. 'auto' only plays when there's pre-tool speech, 'always' plays for every tool call. default: auto tool_error_handling_mode: $ref: '#/components/schemas/ToolErrorHandlingMode' description: >- Controls how tool errors are processed before being shared with the agent. 'auto' determines handling based on tool type (summarized for native integrations, hide for others), 'summarized' sends an LLM-generated summary, 'passthrough' sends the raw error, 'hide' does not share the error with the agent. default: auto parameters: anyOf: - $ref: '#/components/schemas/ObjectJsonSchemaProperty-Input' - type: 'null' description: Schema for any parameters to pass to the client expects_response: type: boolean title: Expects Response description: >- If true, calling this tool should block the conversation until the client responds with some response which is passed to the llm. If false then we will continue the conversation without waiting for the client to respond, this is useful to show content to a user but not block the conversation default: false dynamic_variables: $ref: '#/components/schemas/DynamicVariablesConfig-Input' description: Configuration for dynamic variables execution_mode: $ref: '#/components/schemas/ToolExecutionMode' description: >- Determines when and how the tool executes: 'immediate' executes the tool right away when requested by the LLM, 'post_tool_speech' waits for the agent to finish speaking before executing, 'async' runs the tool in the background without blocking - best for long-running operations. default: immediate type: object required: - name - description title: ClientToolConfig description: >- A client tool is one that sends an event to the user's client to trigger something client side example: expects_response: false type: client SystemToolConfig: properties: type: type: string const: system title: Type description: The type of tool default: system name: type: string minLength: 0 pattern: ^[a-zA-Z0-9_-]{1,64}$ title: Name description: type: string minLength: 0 title: Description description: >- Description of when the tool should be used and what it does. Leave empty to use the default description that's optimized for the specific tool type. default: '' response_timeout_secs: type: integer title: Response Timeout Secs description: The maximum time in seconds to wait for the tool call to complete. default: 20 interruption_mode: $ref: '#/components/schemas/ToolInterruptionMode' description: >- Controls whether the user can interrupt the agent around this tool call. 'allow' (default) lets the user interrupt at any time, 'disable_during_tool' suppresses interruptions only while the tool is running, 'disable_during_tool_and_turn' suppresses interruptions while the tool runs and for the agent response that follows it. default: allow pre_tool_speech: $ref: '#/components/schemas/PreToolSpeechMode' description: >- Controls whether the agent speaks before this tool is called. 'auto' (default) decides based on recent tool latency, 'force' always asks the agent to speak, 'off' fully opts out regardless of latency. default: auto assignments: items: $ref: '#/components/schemas/DynamicVariableAssignment' type: array title: Assignments description: >- Configuration for extracting values from tool responses and assigning them to dynamic variables tool_call_sound: anyOf: - $ref: '#/components/schemas/ToolCallSoundType' - type: 'null' description: >- Predefined tool call sound type to play during tool execution. If not specified, no tool call sound will be played. x-convai-client-override: true tool_call_sound_behavior: $ref: '#/components/schemas/ToolCallSoundBehavior' description: >- Determines when the tool call sound should play. 'auto' only plays when there's pre-tool speech, 'always' plays for every tool call. default: auto tool_error_handling_mode: $ref: '#/components/schemas/ToolErrorHandlingMode' description: >- Controls how tool errors are processed before being shared with the agent. 'auto' determines handling based on tool type (summarized for native integrations, hide for others), 'summarized' sends an LLM-generated summary, 'passthrough' sends the raw error, 'hide' does not share the error with the agent. default: auto params: oneOf: - $ref: '#/components/schemas/EndCallToolConfig' - $ref: '#/components/schemas/LanguageDetectionToolConfig' - $ref: '#/components/schemas/TransferToAgentToolConfig' - $ref: '#/components/schemas/TransferToNumberToolConfig' - $ref: '#/components/schemas/SkipTurnToolConfig' - $ref: '#/components/schemas/PlayDTMFToolConfig' - $ref: '#/components/schemas/VoicemailDetectionToolConfig' - $ref: '#/components/schemas/KnowledgeBaseRagToolConfig' - $ref: '#/components/schemas/KnowledgeBaseToolConfig' - $ref: '#/components/schemas/StartProcedureToolConfig' - $ref: '#/components/schemas/EndProcedureToolConfig' title: Params discriminator: propertyName: system_tool_type mapping: end_call: $ref: '#/components/schemas/EndCallToolConfig' end_procedure: $ref: '#/components/schemas/EndProcedureToolConfig' knowledge_base: $ref: '#/components/schemas/KnowledgeBaseToolConfig' knowledge_base_rag: $ref: '#/components/schemas/KnowledgeBaseRagToolConfig' language_detection: $ref: '#/components/schemas/LanguageDetectionToolConfig' play_keypad_touch_tone: $ref: '#/components/schemas/PlayDTMFToolConfig' skip_turn: $ref: '#/components/schemas/SkipTurnToolConfig' start_procedure: $ref: '#/components/schemas/StartProcedureToolConfig' transfer_to_agent: $ref: '#/components/schemas/TransferToAgentToolConfig' transfer_to_number: $ref: '#/components/schemas/TransferToNumberToolConfig' voicemail_detection: $ref: '#/components/schemas/VoicemailDetectionToolConfig' additionalProperties: false type: object required: - name - params title: SystemToolConfig description: >- A system tool is a tool that is used to call a system method in the server examples: - description: '' name: end_call params: system_tool_type: end_call type: system - description: Custom description for specific use case name: transfer_to_agent params: system_tool_type: transfer_to_agent transfers: [] type: system MCPToolConfig-Input: properties: type: type: string const: mcp title: Type default: mcp name: type: string minLength: 0 pattern: ^[a-zA-Z0-9_-]{1,64}$ title: Name description: type: string minLength: 0 title: Description description: Description of when the tool should be used and what it does. response_timeout_secs: type: integer maximum: 300 minimum: 5 title: Response Timeout Secs description: >- The maximum time in seconds to wait for the MCP tool call to complete. Must be between 5 and 300 seconds (inclusive). default: 30 interruption_mode: $ref: '#/components/schemas/ToolInterruptionMode' description: >- Controls whether the user can interrupt the agent around this tool call. 'allow' (default) lets the user interrupt at any time, 'disable_during_tool' suppresses interruptions only while the tool is running, 'disable_during_tool_and_turn' suppresses interruptions while the tool runs and for the agent response that follows it. default: allow pre_tool_speech: $ref: '#/components/schemas/PreToolSpeechMode' description: >- Controls whether the agent speaks before this tool is called. 'auto' (default) decides based on recent tool latency, 'force' always asks the agent to speak, 'off' fully opts out regardless of latency. default: auto assignments: items: $ref: '#/components/schemas/DynamicVariableAssignment' type: array title: Assignments description: >- Configuration for extracting values from tool responses and assigning them to dynamic variables tool_call_sound: anyOf: - $ref: '#/components/schemas/ToolCallSoundType' - type: 'null' description: >- Predefined tool call sound type to play during tool execution. If not specified, no tool call sound will be played. x-convai-client-override: true tool_call_sound_behavior: $ref: '#/components/schemas/ToolCallSoundBehavior' description: >- Determines when the tool call sound should play. 'auto' only plays when there's pre-tool speech, 'always' plays for every tool call. default: auto tool_error_handling_mode: $ref: '#/components/schemas/ToolErrorHandlingMode' description: >- Controls how tool errors are processed before being shared with the agent. 'auto' determines handling based on tool type (summarized for native integrations, hide for others), 'summarized' sends an LLM-generated summary, 'passthrough' sends the raw error, 'hide' does not share the error with the agent. default: auto integration_type: $ref: '#/components/schemas/IntegrationType' description: The type of MCP tool parameters: anyOf: - $ref: '#/components/schemas/ObjectJsonSchemaProperty-Input' - type: 'null' description: Schema for any parameters the LLM needs to provide to the MCP tool. approval_policy: $ref: '#/components/schemas/MCPApprovalPolicy' description: The approval policy for the MCP tool default: require_approval_all mcp_tool_name: type: string title: Mcp Tool Name description: The name of the MCP tool to call mcp_tool_description: type: string title: Mcp Tool Description description: The description of the MCP tool to call mcp_server_id: type: string title: Mcp Server Id description: The id of the MCP server to call mcp_server_name: type: string title: Mcp Server Name description: The name of the MCP server to call mcp_input_schema: anyOf: - additionalProperties: true type: object - type: 'null' title: Mcp Input Schema description: Original inputSchema dict for consistent hashing execution_mode: $ref: '#/components/schemas/ToolExecutionMode' description: >- Determines when and how the tool executes: 'immediate' executes the tool right away when requested by the LLM, 'post_tool_speech' waits for the agent to finish speaking before executing, 'async' runs the tool in the background without blocking - best for long-running operations. default: immediate input_overrides: anyOf: - additionalProperties: oneOf: - $ref: '#/components/schemas/ConstantSchemaOverride' - $ref: '#/components/schemas/DynamicVariableSchemaOverride' - $ref: '#/components/schemas/LLMSchemaOverride' - $ref: '#/components/schemas/OmitSchemaOverride' discriminator: propertyName: source mapping: constant: $ref: '#/components/schemas/ConstantSchemaOverride' dynamic_variable: $ref: '#/components/schemas/DynamicVariableSchemaOverride' llm: $ref: '#/components/schemas/LLMSchemaOverride' omit: $ref: '#/components/schemas/OmitSchemaOverride' type: object - type: 'null' title: Input Overrides description: Input parameter overrides for this tool type: object required: - name - description - integration_type - mcp_tool_name - mcp_tool_description - mcp_server_id - mcp_server_name title: MCPToolConfig description: An MCP tool configuration that can be used to call MCP servers. x-fern-ignore: true ApiIntegrationWebhookToolConfig-Input: properties: type: type: string const: api_integration_webhook title: Type default: api_integration_webhook name: type: string minLength: 0 pattern: ^[a-zA-Z0-9_-]{1,64}$ title: Name description: type: string minLength: 0 title: Description description: Description of when the tool should be used and what it does. response_timeout_secs: type: integer maximum: 300 minimum: 5 title: Response Timeout Secs description: >- The maximum time in seconds to wait for the tool call to complete. Must be between 5 and 300 seconds (inclusive). default: 20 interruption_mode: $ref: '#/components/schemas/ToolInterruptionMode' description: >- Controls whether the user can interrupt the agent around this tool call. 'allow' (default) lets the user interrupt at any time, 'disable_during_tool' suppresses interruptions only while the tool is running, 'disable_during_tool_and_turn' suppresses interruptions while the tool runs and for the agent response that follows it. default: allow pre_tool_speech: $ref: '#/components/schemas/PreToolSpeechMode' description: >- Controls whether the agent speaks before this tool is called. 'auto' (default) decides based on recent tool latency, 'force' always asks the agent to speak, 'off' fully opts out regardless of latency. default: auto assignments: items: $ref: '#/components/schemas/DynamicVariableAssignment' type: array title: Assignments description: >- Configuration for extracting values from tool responses and assigning them to dynamic variables tool_call_sound: anyOf: - $ref: '#/components/schemas/ToolCallSoundType' - type: 'null' description: >- Predefined tool call sound type to play during tool execution. If not specified, no tool call sound will be played. x-convai-client-override: true tool_call_sound_behavior: $ref: '#/components/schemas/ToolCallSoundBehavior' description: >- Determines when the tool call sound should play. 'auto' only plays when there's pre-tool speech, 'always' plays for every tool call. default: auto tool_error_handling_mode: $ref: '#/components/schemas/ToolErrorHandlingMode' description: >- Controls how tool errors are processed before being shared with the agent. 'auto' determines handling based on tool type (summarized for native integrations, hide for others), 'summarized' sends an LLM-generated summary, 'passthrough' sends the raw error, 'hide' does not share the error with the agent. default: auto dynamic_variables: $ref: '#/components/schemas/DynamicVariablesConfig-Input' description: Configuration for dynamic variables execution_mode: $ref: '#/components/schemas/ToolExecutionMode' description: >- Determines when and how the tool executes: 'immediate' executes the tool right away when requested by the LLM, 'post_tool_speech' waits for the agent to finish speaking before executing, 'async' runs the tool in the background without blocking - best for long-running operations. default: immediate tool_version: type: string title: Tool Version description: The version of the API integration tool default: 1.0.0 api_integration_id: type: string title: Api Integration Id api_integration_connection_id: type: string title: Api Integration Connection Id api_schema_overrides: anyOf: - $ref: '#/components/schemas/ApiIntegrationWebhookOverrides' - type: 'null' title: Api Schema Overrides description: User overrides applied on top of the base api_schema type: object required: - name - description - api_integration_id - api_integration_connection_id title: ApiIntegrationWebhookToolConfig SMBToolConfig: properties: type: type: string const: smb title: Type description: Tool type identifier default: smb name: type: string minLength: 0 pattern: ^[a-zA-Z0-9_-]{1,64}$ title: Name description: type: string minLength: 0 title: Description description: Description of when the tool should be used and what it does. default: '' response_timeout_secs: type: integer title: Response Timeout Secs description: The maximum time in seconds to wait for the tool call to complete. default: 20 interruption_mode: $ref: '#/components/schemas/ToolInterruptionMode' description: >- Controls whether the user can interrupt the agent around this tool call. 'allow' (default) lets the user interrupt at any time, 'disable_during_tool' suppresses interruptions only while the tool is running, 'disable_during_tool_and_turn' suppresses interruptions while the tool runs and for the agent response that follows it. default: allow pre_tool_speech: $ref: '#/components/schemas/PreToolSpeechMode' description: >- Controls whether the agent speaks before this tool is called. 'auto' (default) decides based on recent tool latency, 'force' always asks the agent to speak, 'off' fully opts out regardless of latency. default: auto assignments: items: $ref: '#/components/schemas/DynamicVariableAssignment' type: array title: Assignments description: >- Configuration for extracting values from tool responses and assigning them to dynamic variables tool_call_sound: anyOf: - $ref: '#/components/schemas/ToolCallSoundType' - type: 'null' description: >- Predefined tool call sound type to play during tool execution. If not specified, no tool call sound will be played. x-convai-client-override: true tool_call_sound_behavior: $ref: '#/components/schemas/ToolCallSoundBehavior' description: >- Determines when the tool call sound should play. 'auto' only plays when there's pre-tool speech, 'always' plays for every tool call. default: auto tool_error_handling_mode: $ref: '#/components/schemas/ToolErrorHandlingMode' description: >- Controls how tool errors are processed before being shared with the agent. 'auto' determines handling based on tool type (summarized for native integrations, hide for others), 'summarized' sends an LLM-generated summary, 'passthrough' sends the raw error, 'hide' does not share the error with the agent. default: auto human_description: type: string minLength: 0 title: Human Description description: >- User-facing tooltip for the procedure reference picker. Not sent to the LLM. default: '' enabled: type: boolean title: Enabled description: Whether this tool is enabled for the agent default: true params: oneOf: - $ref: '#/components/schemas/SearchClientsParams' - $ref: '#/components/schemas/ListClientsParams' - $ref: '#/components/schemas/GetClientByPhoneParams' - $ref: '#/components/schemas/CreateClientParams' - $ref: '#/components/schemas/UpdateClientParams' - $ref: '#/components/schemas/DeleteClientParams' - $ref: '#/components/schemas/ListStaffParams' - $ref: '#/components/schemas/CreateStaffParams' - $ref: '#/components/schemas/UpdateStaffParams' - $ref: '#/components/schemas/DeleteStaffParams' - $ref: '#/components/schemas/ListAssetsParams' - $ref: '#/components/schemas/CreateAssetParams' - $ref: '#/components/schemas/UpdateAssetParams' - $ref: '#/components/schemas/DeleteAssetParams' - $ref: '#/components/schemas/ListServicesParams' - $ref: '#/components/schemas/CreateServiceParams' - $ref: '#/components/schemas/UpdateServiceParams' - $ref: '#/components/schemas/DeleteServiceParams' - $ref: '#/components/schemas/ListProductsParams' - $ref: '#/components/schemas/CreateProductParams' - $ref: '#/components/schemas/UpdateProductParams' - $ref: '#/components/schemas/DeleteProductParams' - $ref: '#/components/schemas/CheckServiceAvailabilityParams' - $ref: '#/components/schemas/CreateClientAppointmentParams' - $ref: '#/components/schemas/GetClientAppointmentsParams' - $ref: '#/components/schemas/GetAppointmentByConfirmationNumberParams' - $ref: '#/components/schemas/CreateOrderParams' - $ref: '#/components/schemas/GetOrderByConfirmationNumberParams' - $ref: '#/components/schemas/GetClientOrdersParams' - $ref: '#/components/schemas/UpdateOrderParams' - $ref: '#/components/schemas/CancelOrderParams' - $ref: '#/components/schemas/ListGroupSessionsParams' - $ref: '#/components/schemas/ScheduleGroupSessionParams' - $ref: '#/components/schemas/RegisterForGroupSessionParams' - $ref: '#/components/schemas/CancelGroupSessionRegistrationParams' - $ref: '#/components/schemas/UpdateGroupSessionSeatsParams' - $ref: '#/components/schemas/CancelGroupSessionForAllParams' - $ref: '#/components/schemas/DeleteGroupSessionParams' - $ref: '#/components/schemas/ListCalendarEventsParams' - $ref: '#/components/schemas/UpdateCalendarEventParams' - $ref: '#/components/schemas/CancelCalendarEventParams' - $ref: '#/components/schemas/RestoreCalendarEventParams' - $ref: '#/components/schemas/DeleteCalendarEventParams' - $ref: '#/components/schemas/ListCustomerFacingAgentsParams' - $ref: '#/components/schemas/ListAgentRulesParams' - $ref: '#/components/schemas/CreateAgentRuleParams' - $ref: '#/components/schemas/UpdateAgentRuleParams' - $ref: '#/components/schemas/DeleteAgentRuleParams' - $ref: '#/components/schemas/ListTransferRulesParams' - $ref: '#/components/schemas/CreateTransferRuleParams' - $ref: '#/components/schemas/UpdateTransferRuleParams' - $ref: '#/components/schemas/DeleteTransferRuleParams' - $ref: '#/components/schemas/ListAgentProceduresParams' - $ref: '#/components/schemas/ListAgentReferencesParams' - $ref: '#/components/schemas/CreateAgentProcedureParams' - $ref: '#/components/schemas/UpdateAgentProcedureParams' - $ref: '#/components/schemas/DeleteAgentProcedureParams' - $ref: '#/components/schemas/ListHolidaysParams' - $ref: '#/components/schemas/CreateHolidayParams' - $ref: '#/components/schemas/UpdateHolidayParams' - $ref: '#/components/schemas/DeleteHolidayParams' - $ref: '#/components/schemas/GetScheduleParams' - $ref: '#/components/schemas/SubmitBusinessInfoParams' - $ref: '#/components/schemas/UpdateBusinessInfoParams' - $ref: '#/components/schemas/UpdateCustomerFacingConfigParams' - $ref: '#/components/schemas/GetAnalyticsSummaryParams' - $ref: '#/components/schemas/GetBookingPageSettingsParams' - $ref: '#/components/schemas/UpdateBookingPageSettingsParams' - $ref: '#/components/schemas/UpdateBookingPageAppearanceParams' - $ref: '#/components/schemas/GetBookingSlugStatusParams' - $ref: '#/components/schemas/SetBookingSlugParams' - $ref: '#/components/schemas/ListClientInteractionsParams' - $ref: '#/components/schemas/CreateClientInteractionParams' - $ref: '#/components/schemas/DeleteClientInteractionParams' - $ref: '#/components/schemas/ListLocationsParams' - $ref: '#/components/schemas/CreateLocationParams' - $ref: '#/components/schemas/UpdateLocationParams' - $ref: '#/components/schemas/DeleteLocationParams' - $ref: '#/components/schemas/LeaveMessageParams' - $ref: '#/components/schemas/ReportKnowledgeGapParams' - $ref: '#/components/schemas/OptInSmsReminderParams' - $ref: '#/components/schemas/OptOutSmsReminderParams' - $ref: '#/components/schemas/TriggerUserVerificationParams' - $ref: '#/components/schemas/ValidateUserVerificationCodeParams' title: Params discriminator: propertyName: smb_tool_type mapping: cancel_calendar_event: $ref: '#/components/schemas/CancelCalendarEventParams' cancel_group_session_for_all: $ref: '#/components/schemas/CancelGroupSessionForAllParams' cancel_group_session_registration: $ref: '#/components/schemas/CancelGroupSessionRegistrationParams' cancel_order: $ref: '#/components/schemas/CancelOrderParams' check_service_availability: $ref: '#/components/schemas/CheckServiceAvailabilityParams' create_agent_procedure: $ref: '#/components/schemas/CreateAgentProcedureParams' create_agent_rule: $ref: '#/components/schemas/CreateAgentRuleParams' create_asset: $ref: '#/components/schemas/CreateAssetParams' create_client: $ref: '#/components/schemas/CreateClientParams' create_client_appointment: $ref: '#/components/schemas/CreateClientAppointmentParams' create_client_interaction: $ref: '#/components/schemas/CreateClientInteractionParams' create_holiday: $ref: '#/components/schemas/CreateHolidayParams' create_location: $ref: '#/components/schemas/CreateLocationParams' create_order: $ref: '#/components/schemas/CreateOrderParams' create_product: $ref: '#/components/schemas/CreateProductParams' create_service: $ref: '#/components/schemas/CreateServiceParams' create_staff: $ref: '#/components/schemas/CreateStaffParams' create_transfer_rule: $ref: '#/components/schemas/CreateTransferRuleParams' delete_agent_procedure: $ref: '#/components/schemas/DeleteAgentProcedureParams' delete_agent_rule: $ref: '#/components/schemas/DeleteAgentRuleParams' delete_asset: $ref: '#/components/schemas/DeleteAssetParams' delete_calendar_event: $ref: '#/components/schemas/DeleteCalendarEventParams' delete_client: $ref: '#/components/schemas/DeleteClientParams' delete_client_interaction: $ref: '#/components/schemas/DeleteClientInteractionParams' delete_group_session: $ref: '#/components/schemas/DeleteGroupSessionParams' delete_holiday: $ref: '#/components/schemas/DeleteHolidayParams' delete_location: $ref: '#/components/schemas/DeleteLocationParams' delete_product: $ref: '#/components/schemas/DeleteProductParams' delete_service: $ref: '#/components/schemas/DeleteServiceParams' delete_staff: $ref: '#/components/schemas/DeleteStaffParams' delete_transfer_rule: $ref: '#/components/schemas/DeleteTransferRuleParams' get_analytics_summary: $ref: '#/components/schemas/GetAnalyticsSummaryParams' get_appointment_by_confirmation_number: $ref: '#/components/schemas/GetAppointmentByConfirmationNumberParams' get_booking_page_settings: $ref: '#/components/schemas/GetBookingPageSettingsParams' get_booking_slug_status: $ref: '#/components/schemas/GetBookingSlugStatusParams' get_client_appointments: $ref: '#/components/schemas/GetClientAppointmentsParams' get_client_by_phone: $ref: '#/components/schemas/GetClientByPhoneParams' get_client_orders: $ref: '#/components/schemas/GetClientOrdersParams' get_order_by_confirmation_number: $ref: '#/components/schemas/GetOrderByConfirmationNumberParams' get_schedule: $ref: '#/components/schemas/GetScheduleParams' leave_message: $ref: '#/components/schemas/LeaveMessageParams' list_agent_procedures: $ref: '#/components/schemas/ListAgentProceduresParams' list_agent_references: $ref: '#/components/schemas/ListAgentReferencesParams' list_agent_rules: $ref: '#/components/schemas/ListAgentRulesParams' list_assets: $ref: '#/components/schemas/ListAssetsParams' list_calendar_events: $ref: '#/components/schemas/ListCalendarEventsParams' list_client_interactions: $ref: '#/components/schemas/ListClientInteractionsParams' list_clients: $ref: '#/components/schemas/ListClientsParams' list_customer_facing_agents: $ref: '#/components/schemas/ListCustomerFacingAgentsParams' list_group_sessions: $ref: '#/components/schemas/ListGroupSessionsParams' list_holidays: $ref: '#/components/schemas/ListHolidaysParams' list_locations: $ref: '#/components/schemas/ListLocationsParams' list_products: $ref: '#/components/schemas/ListProductsParams' list_services: $ref: '#/components/schemas/ListServicesParams' list_staff: $ref: '#/components/schemas/ListStaffParams' list_transfer_rules: $ref: '#/components/schemas/ListTransferRulesParams' opt_in_sms_reminder: $ref: '#/components/schemas/OptInSmsReminderParams' opt_out_sms_reminder: $ref: '#/components/schemas/OptOutSmsReminderParams' register_for_group_session: $ref: '#/components/schemas/RegisterForGroupSessionParams' report_knowledge_gap: $ref: '#/components/schemas/ReportKnowledgeGapParams' restore_calendar_event: $ref: '#/components/schemas/RestoreCalendarEventParams' schedule_group_session: $ref: '#/components/schemas/ScheduleGroupSessionParams' search_clients: $ref: '#/components/schemas/SearchClientsParams' set_booking_slug: $ref: '#/components/schemas/SetBookingSlugParams' submit_business_info: $ref: '#/components/schemas/SubmitBusinessInfoParams' trigger_user_verification: $ref: '#/components/schemas/TriggerUserVerificationParams' update_agent_procedure: $ref: '#/components/schemas/UpdateAgentProcedureParams' update_agent_rule: $ref: '#/components/schemas/UpdateAgentRuleParams' update_asset: $ref: '#/components/schemas/UpdateAssetParams' update_booking_page_appearance: $ref: '#/components/schemas/UpdateBookingPageAppearanceParams' update_booking_page_settings: $ref: '#/components/schemas/UpdateBookingPageSettingsParams' update_business_info: $ref: '#/components/schemas/UpdateBusinessInfoParams' update_calendar_event: $ref: '#/components/schemas/UpdateCalendarEventParams' update_client: $ref: '#/components/schemas/UpdateClientParams' update_customer_facing_config: $ref: '#/components/schemas/UpdateCustomerFacingConfigParams' update_group_session_seats: $ref: '#/components/schemas/UpdateGroupSessionSeatsParams' update_holiday: $ref: '#/components/schemas/UpdateHolidayParams' update_location: $ref: '#/components/schemas/UpdateLocationParams' update_order: $ref: '#/components/schemas/UpdateOrderParams' update_product: $ref: '#/components/schemas/UpdateProductParams' update_service: $ref: '#/components/schemas/UpdateServiceParams' update_staff: $ref: '#/components/schemas/UpdateStaffParams' update_transfer_rule: $ref: '#/components/schemas/UpdateTransferRuleParams' validate_user_verification_code: $ref: '#/components/schemas/ValidateUserVerificationCodeParams' type: object required: - name - params title: SMBToolConfig description: SMB tool configuration that wraps SMB tool parameters. examples: - description: '' enabled: true name: search_clients params: smb_tool_type: search_clients type: smb x-fern-ignore: true SarvamStreamType: type: string enum: - fast - balanced - simulated title: SarvamStreamType ASREndpointingMode: type: string enum: - vad - manual title: ASREndpointingMode ASTNode-Input: oneOf: - $ref: '#/components/schemas/ASTStringNode-Input' description: String literal. - $ref: '#/components/schemas/ASTNumberNode-Input' description: Number literal. - $ref: '#/components/schemas/ASTBooleanNode-Input' description: Boolean literal. - $ref: '#/components/schemas/ASTNullNode-Input' description: Null literal. - $ref: '#/components/schemas/ASTLLMNode-Input' description: Value extracted by an LLM according to the given schema. - $ref: '#/components/schemas/ASTDynamicVariableNode-Input' description: Reference to a dynamic variable. - $ref: '#/components/schemas/ASTOrOperatorNode-Input' description: Evaluates to true if any child is true. - $ref: '#/components/schemas/ASTAndOperatorNode-Input' description: Evaluates to true if all children are true. - $ref: '#/components/schemas/ASTEqualsOperatorNode-Input' description: Evaluates to true if the left value equals the right. - $ref: '#/components/schemas/ASTNotEqualsOperatorNode-Input' description: Evaluates to true if the left value does not equal the right. - $ref: '#/components/schemas/ASTGreaterThanOperatorNode-Input' description: Evaluates to true if the left value is greater than the right. - $ref: '#/components/schemas/ASTLessThanOperatorNode-Input' description: Evaluates to true if the left value is less than the right. - $ref: '#/components/schemas/ASTGreaterThanOrEqualsOperatorNode-Input' description: >- Evaluates to true if the left value is greater than or equal to the right. - $ref: '#/components/schemas/ASTLessThanOrEqualsOperatorNode-Input' description: >- Evaluates to true if the left value is less than or equal to the right. - $ref: '#/components/schemas/ASTAdditionOperatorNode-Input' description: Adds the left and right values. - $ref: '#/components/schemas/ASTSubtractionOperatorNode-Input' description: Subtracts the right value from the left. - $ref: '#/components/schemas/ASTMultiplicationOperatorNode-Input' description: Multiplies the left value times the right. - $ref: '#/components/schemas/ASTDivisionOperatorNode-Input' description: Divides the left value by the right. - $ref: '#/components/schemas/ASTConditionalOperatorNode-Input' description: >- Selects one of two expressions based on whether the given condition evaluates to true. discriminator: propertyName: type mapping: add_operator: $ref: '#/components/schemas/ASTAdditionOperatorNode-Input' and_operator: $ref: '#/components/schemas/ASTAndOperatorNode-Input' boolean_literal: $ref: '#/components/schemas/ASTBooleanNode-Input' conditional_operator: $ref: '#/components/schemas/ASTConditionalOperatorNode-Input' div_operator: $ref: '#/components/schemas/ASTDivisionOperatorNode-Input' dynamic_variable: $ref: '#/components/schemas/ASTDynamicVariableNode-Input' eq_operator: $ref: '#/components/schemas/ASTEqualsOperatorNode-Input' gt_operator: $ref: '#/components/schemas/ASTGreaterThanOperatorNode-Input' gte_operator: $ref: '#/components/schemas/ASTGreaterThanOrEqualsOperatorNode-Input' llm: $ref: '#/components/schemas/ASTLLMNode-Input' lt_operator: $ref: '#/components/schemas/ASTLessThanOperatorNode-Input' lte_operator: $ref: '#/components/schemas/ASTLessThanOrEqualsOperatorNode-Input' mul_operator: $ref: '#/components/schemas/ASTMultiplicationOperatorNode-Input' neq_operator: $ref: '#/components/schemas/ASTNotEqualsOperatorNode-Input' null_literal: $ref: '#/components/schemas/ASTNullNode-Input' number_literal: $ref: '#/components/schemas/ASTNumberNode-Input' or_operator: $ref: '#/components/schemas/ASTOrOperatorNode-Input' string_literal: $ref: '#/components/schemas/ASTStringNode-Input' sub_operator: $ref: '#/components/schemas/ASTSubtractionOperatorNode-Input' TTSConversationalConfigWorkflowOverride: properties: voice_id: anyOf: - type: string - type: 'null' title: Voice Id description: The voice ID to use for TTS performance: anyOf: - $ref: '#/components/schemas/TTSPerformance' - type: 'null' description: >- User-facing TTS performance tier (latency or quality). The concrete provider/model is selected by the voice-server based on this value. pronunciation_dictionary_locators: anyOf: - items: $ref: >- #/components/schemas/PydanticPronunciationDictionaryVersionLocator type: array - type: 'null' title: Pronunciation Dictionary Locators description: The pronunciation dictionary locators x-convai-client-override: true enable_phoneme_tags: anyOf: - type: boolean - type: 'null' title: Enable Phoneme Tags description: >- Opt-in to SSML phoneme tag handling. When enabled, phoneme tags from inline content and pronunciation dictionaries may be normalized before synthesis when the selected provider supports them. type: object title: TTSConversationalConfigWorkflowOverride example: performance: latency voice_id: ME9RtCnWp5vX2LhJdF3k KnowledgeBaseDocumentType: type: string enum: - file - url - text - folder title: KnowledgeBaseDocumentType DocumentUsageModeEnum: type: string enum: - prompt - auto title: DocumentUsageModeEnum default: auto ConstantSchemaOverride: properties: source: type: string const: constant title: Source default: constant constant_value: anyOf: - type: string - type: integer - type: number - type: boolean - items: {} type: array - additionalProperties: true type: object - type: 'null' title: Constant Value description: The constant value to use type: object required: - constant_value title: ConstantSchemaOverride DynamicVariableSchemaOverride: properties: source: type: string const: dynamic_variable title: Source default: dynamic_variable dynamic_variable: type: string minLength: 1 title: Dynamic Variable description: The name of the dynamic variable to use type: object required: - dynamic_variable title: DynamicVariableSchemaOverride LLMSchemaOverride: properties: source: type: string const: llm title: Source default: llm prompt: anyOf: - type: string - type: 'null' title: Prompt description: >- Prompt override for the LLM. If not provided, the original schema description is used. type: object title: LLMSchemaOverride OmitSchemaOverride: properties: source: type: string const: omit title: Source default: omit type: object title: OmitSchemaOverride DynamicVariableValueType-Output: anyOf: - type: string - type: number - type: integer - type: boolean - items: $ref: '#/components/schemas/DynamicVariableNestedValueType-Output' type: array - type: 'null' BuiltInTools: properties: end_call: anyOf: - $ref: '#/components/schemas/SystemToolConfig' - type: 'null' description: The end call tool language_detection: anyOf: - $ref: '#/components/schemas/SystemToolConfig' - type: 'null' description: The language detection tool transfer_to_agent: anyOf: - $ref: '#/components/schemas/SystemToolConfig' - type: 'null' description: The transfer to agent tool transfer_to_number: anyOf: - $ref: '#/components/schemas/SystemToolConfig' - type: 'null' description: The transfer to number tool skip_turn: anyOf: - $ref: '#/components/schemas/SystemToolConfig' - type: 'null' description: The skip turn tool play_keypad_touch_tone: anyOf: - $ref: '#/components/schemas/SystemToolConfig' - type: 'null' description: The play DTMF tool voicemail_detection: anyOf: - $ref: '#/components/schemas/SystemToolConfig' - type: 'null' description: The voicemail detection tool additionalProperties: false type: object title: BuiltInTools RagConfig: properties: enabled: type: boolean title: Enabled description: Whether RAG is enabled default: false embedding_model: $ref: '#/components/schemas/EmbeddingModelEnum' description: The embedding model to use for RAG default: multilingual_e5_large_instruct max_vector_distance: type: number exclusiveMaximum: 1 exclusiveMinimum: 0 title: Max Vector Distance description: Maximum vector distance of retrieved chunks. default: 0.6 max_documents_length: type: integer exclusiveMaximum: 10000000 exclusiveMinimum: 0 title: Max Documents Length description: Maximum total length of document chunks retrieved from RAG. default: 50000 max_retrieved_rag_chunks_count: type: integer maximum: 20 exclusiveMinimum: 0 title: Max Retrieved Rag Chunks Count description: >- Maximum number of RAG document chunks to initially retrieve from the vector store. These are then further filtered by vector distance and total length. default: 20 num_candidates: anyOf: - type: integer maximum: 10000 exclusiveMinimum: 0 - type: 'null' title: Num Candidates description: >- Number of candidates evaluated in ANN vector search. Higher number means better results, but higher latency. Minimum recommended value is 100. If disabled, the default value is used. query_rewrite_prompt_override: anyOf: - type: string maxLength: 1000 minLength: 1 - type: 'null' title: Query Rewrite Prompt Override description: >- Custom prompt for rewriting user queries before RAG retrieval. The conversation history will be automatically appended at the end. If not set, the default prompt will be used. type: object title: RagConfig example: embedding_model: multilingual_e5_large_instruct enabled: false max_documents_length: 50000 max_retrieved_rag_chunks_count: 5 max_vector_distance: 0.5 num_candidates: 300 CriteriaScoringMode: type: string enum: - binary - numeric_uniform title: CriteriaScoringMode WidgetEndFeedbackType: type: string enum: - rating title: WidgetEndFeedbackType default: rating WidgetTextContentsTranslation: properties: source: additionalProperties: type: string type: object title: Source description: The source text each translated field was derived from text: additionalProperties: type: string type: object title: Text description: The last auto-translated output for each translated field type: object title: WidgetTextContentsTranslation WidgetTermsTranslation: properties: source_hash: type: string title: Source Hash text: type: string title: Text type: object required: - source_hash - text title: WidgetTermsTranslation TurnConfigOverrideConfig: properties: soft_timeout_config: $ref: '#/components/schemas/SoftTimeoutConfigOverrideConfig' description: Configures overrides for nested fields. type: object title: TurnConfigOverrideConfig TTSConversationalConfigOverrideConfig: properties: voice_id: type: boolean title: Voice Id description: Whether to allow overriding the voice_id field. default: false performance: type: boolean title: Performance description: Whether to allow overriding the performance field. default: false pronunciation_dictionary_locators: type: boolean title: Pronunciation Dictionary Locators description: >- Whether to allow overriding the pronunciation_dictionary_locators field. default: false type: object title: TTSConversationalConfigOverrideConfig ConversationConfigOverrideConfig: properties: text_only: type: boolean title: Text Only description: Whether to allow overriding the text_only field. default: false max_duration_seconds: type: boolean title: Max Duration Seconds description: Whether to allow overriding the max_duration_seconds field. default: false type: object title: ConversationConfigOverrideConfig AgentConfigOverrideConfig: properties: first_message: type: boolean title: First Message description: Whether to allow overriding the first_message field. default: false language: type: boolean title: Language description: Whether to allow overriding the language field. default: false max_conversation_duration_message: type: boolean title: Max Conversation Duration Message description: >- Whether to allow overriding the max_conversation_duration_message field. default: false prompt: $ref: '#/components/schemas/PromptAgentAPIModelOverrideConfig' description: Configures overrides for nested fields. type: object title: AgentConfigOverrideConfig ConvAISecretLocator: properties: secret_id: type: string title: Secret Id type: object required: - secret_id title: ConvAISecretLocator description: Used to reference a secret from the agent's secret store. WebhookEventType: type: string enum: - transcript - audio - call_initiation_failure - unredacted_transcript - unredacted_audio title: WebhookEventType WebhookTranscriptFormat: type: string enum: - json - opentelemetry title: WebhookTranscriptFormat default: json GuardrailExecutionMode: type: string enum: - streaming - blocking title: GuardrailExecutionMode ContentConfig: properties: sexual: $ref: '#/components/schemas/ContentThresholdGuardrail' violence: $ref: '#/components/schemas/ContentThresholdGuardrail' harassment: $ref: '#/components/schemas/ContentThresholdGuardrail' self_harm: $ref: '#/components/schemas/ContentThresholdGuardrail' profanity: $ref: '#/components/schemas/ContentThresholdGuardrail' religion_or_politics: $ref: '#/components/schemas/ContentThresholdGuardrail' medical_and_legal_information: $ref: '#/components/schemas/ContentThresholdGuardrail' type: object title: ContentConfig EndCallTriggerAction: properties: type: type: string const: end_call title: Type default: end_call type: object title: EndCallTriggerAction RetryTriggerAction: properties: type: type: string const: retry title: Type default: retry feedback: type: string title: Feedback description: >- Custom feedback to inject into the agent when retrying after guardrail trigger. default: >- Your response was blocked by a guardrail that blocks content that matches this condition/category: '{{trigger_reason}}' During your next turn you must tell the user "I'm sorry but I can't answer that question, would you like to know something else?". type: object title: RetryTriggerAction ModerationConfig: properties: sexual: $ref: '#/components/schemas/ThresholdGuardrail' violence: $ref: '#/components/schemas/ThresholdGuardrail' violence_graphic: $ref: '#/components/schemas/ThresholdGuardrail' harassment: $ref: '#/components/schemas/ThresholdGuardrail' harassment_threatening: $ref: '#/components/schemas/ThresholdGuardrail' hate: $ref: '#/components/schemas/ThresholdGuardrail' hate_threatening: $ref: '#/components/schemas/ThresholdGuardrail' self_harm_instructions: $ref: '#/components/schemas/ThresholdGuardrail' self_harm: $ref: '#/components/schemas/ThresholdGuardrail' self_harm_intent: $ref: '#/components/schemas/ThresholdGuardrail' sexual_minors: $ref: '#/components/schemas/ThresholdGuardrail' type: object title: ModerationConfig CustomGuardrailsConfig: properties: configs: items: $ref: '#/components/schemas/CustomGuardrailConfig' type: array title: Configs type: object title: CustomGuardrailsConfig description: Config container for custom guardrails list. ConfigEntityType: type: string enum: - name - name.name_given - name.name_family - name.name_other - email_address - contact_number - dob - age - religious_belief - political_opinion - sexual_orientation - ethnicity_race - marital_status - occupation - physical_attribute - language - username - password - url - organization - financial_id - financial_id.payment_card - financial_id.payment_card.payment_card_number - financial_id.payment_card.payment_card_expiration_date - financial_id.payment_card.payment_card_cvv - financial_id.bank_account - financial_id.bank_account.bank_account_number - financial_id.bank_account.bank_routing_number - financial_id.bank_account.swift_bic_code - financial_id.financial_id_other - location - location.location_address - location.location_city - location.location_postal_code - location.location_coordinate - location.location_state - location.location_country - location.location_other - date - date_interval - unique_id - unique_id.government_issued_id - unique_id.account_number - unique_id.vehicle_id - unique_id.healthcare_number - unique_id.healthcare_number.medical_record_number - unique_id.healthcare_number.health_plan_beneficiary_number - unique_id.device_id - unique_id.unique_id_other - medical - medical.medical_condition - medical.medication - medical.medical_procedure - medical.medical_measurement - medical.medical_other title: ConfigEntityType description: >- Entity types for the API configuration. This enum contains all valid entity type configurations that users can specify: - Parent types (e.g., "name", "financial_id") that expand to all subtypes - Specific subtypes using dot notation (e.g., "name.full_name") - Standalone terminal types (e.g., "email_address") When converted for service use, parent types expand to all their terminal subtypes. ASTNode-Output: oneOf: - $ref: '#/components/schemas/ASTStringNode-Output' description: String literal. - $ref: '#/components/schemas/ASTNumberNode-Output' description: Number literal. - $ref: '#/components/schemas/ASTBooleanNode-Output' description: Boolean literal. - $ref: '#/components/schemas/ASTNullNode-Output' description: Null literal. - $ref: '#/components/schemas/ASTLLMNode-Output' description: Value extracted by an LLM according to the given schema. - $ref: '#/components/schemas/ASTDynamicVariableNode-Output' description: Reference to a dynamic variable. - $ref: '#/components/schemas/ASTOrOperatorNode-Output' description: Evaluates to true if any child is true. - $ref: '#/components/schemas/ASTAndOperatorNode-Output' description: Evaluates to true if all children are true. - $ref: '#/components/schemas/ASTEqualsOperatorNode-Output' description: Evaluates to true if the left value equals the right. - $ref: '#/components/schemas/ASTNotEqualsOperatorNode-Output' description: Evaluates to true if the left value does not equal the right. - $ref: '#/components/schemas/ASTGreaterThanOperatorNode-Output' description: Evaluates to true if the left value is greater than the right. - $ref: '#/components/schemas/ASTLessThanOperatorNode-Output' description: Evaluates to true if the left value is less than the right. - $ref: '#/components/schemas/ASTGreaterThanOrEqualsOperatorNode-Output' description: >- Evaluates to true if the left value is greater than or equal to the right. - $ref: '#/components/schemas/ASTLessThanOrEqualsOperatorNode-Output' description: >- Evaluates to true if the left value is less than or equal to the right. - $ref: '#/components/schemas/ASTAdditionOperatorNode-Output' description: Adds the left and right values. - $ref: '#/components/schemas/ASTSubtractionOperatorNode-Output' description: Subtracts the right value from the left. - $ref: '#/components/schemas/ASTMultiplicationOperatorNode-Output' description: Multiplies the left value times the right. - $ref: '#/components/schemas/ASTDivisionOperatorNode-Output' description: Divides the left value by the right. - $ref: '#/components/schemas/ASTConditionalOperatorNode-Output' description: >- Selects one of two expressions based on whether the given condition evaluates to true. discriminator: propertyName: type mapping: add_operator: $ref: '#/components/schemas/ASTAdditionOperatorNode-Output' and_operator: $ref: '#/components/schemas/ASTAndOperatorNode-Output' boolean_literal: $ref: '#/components/schemas/ASTBooleanNode-Output' conditional_operator: $ref: '#/components/schemas/ASTConditionalOperatorNode-Output' div_operator: $ref: '#/components/schemas/ASTDivisionOperatorNode-Output' dynamic_variable: $ref: '#/components/schemas/ASTDynamicVariableNode-Output' eq_operator: $ref: '#/components/schemas/ASTEqualsOperatorNode-Output' gt_operator: $ref: '#/components/schemas/ASTGreaterThanOperatorNode-Output' gte_operator: $ref: '#/components/schemas/ASTGreaterThanOrEqualsOperatorNode-Output' llm: $ref: '#/components/schemas/ASTLLMNode-Output' lt_operator: $ref: '#/components/schemas/ASTLessThanOperatorNode-Output' lte_operator: $ref: '#/components/schemas/ASTLessThanOrEqualsOperatorNode-Output' mul_operator: $ref: '#/components/schemas/ASTMultiplicationOperatorNode-Output' neq_operator: $ref: '#/components/schemas/ASTNotEqualsOperatorNode-Output' null_literal: $ref: '#/components/schemas/ASTNullNode-Output' number_literal: $ref: '#/components/schemas/ASTNumberNode-Output' or_operator: $ref: '#/components/schemas/ASTOrOperatorNode-Output' string_literal: $ref: '#/components/schemas/ASTStringNode-Output' sub_operator: $ref: '#/components/schemas/ASTSubtractionOperatorNode-Output' AgentConfigAPIModelWorkflowOverride-Output: properties: first_message: anyOf: - type: string - type: 'null' title: First Message description: >- If non-empty, the first message the agent will say. If empty, the agent waits for the user to start the discussion. x-convai-client-override: true x-convai-language-override: true language: anyOf: - type: string - type: 'null' title: Language description: Language of the agent - used for ASR and TTS x-convai-client-override: true dynamic_variables: anyOf: - $ref: >- #/components/schemas/DynamicVariablesConfigWorkflowOverride-Output - type: 'null' description: Configuration for dynamic variables disable_first_message_interruptions: anyOf: - type: boolean - type: 'null' title: Disable First Message Interruptions description: >- If true, the user will not be able to interrupt the agent while the first message is being delivered. max_conversation_duration_message: anyOf: - type: string - type: 'null' title: Max Conversation Duration Message description: >- If non-empty, the message the agent will send when max conversation duration is reached. x-convai-client-override: true x-convai-language-override: true text_behavior_overrides: anyOf: - additionalProperties: $ref: '#/components/schemas/BehaviorOverride' propertyNames: $ref: '#/components/schemas/ConversationInitiationSource' type: object - type: 'null' title: Text Behavior Overrides description: >- Per-channel response behavior overrides for text conversations. Built-in channel defaults apply when unset. prompt: anyOf: - $ref: '#/components/schemas/PromptAgentAPIModelWorkflowOverride-Output' - type: 'null' description: The prompt for the agent type: object title: AgentConfigAPIModelWorkflowOverride example: disable_first_message_interruptions: false dynamic_variables: dynamic_variable_placeholders: user_name: John Doe first_message: Hello, how can I help you today? language: en prompt: knowledge_base: [] llm: gemini-2.0-flash-001 max_tokens: -1 prompt: >- You are a helpful assistant that can answer questions about the topic of the conversation. temperature: 0 tool_ids: [] SoftTimeoutConfigOverride: properties: message: anyOf: - type: string - type: 'null' title: Message description: >- Message to show when the first soft timeout is reached while waiting for LLM response. Supports dynamic variables (e.g., {{system__time}}, {{custom_variable}}). x-convai-client-override: true x-convai-language-override: true additional_soft_timeout_messages: anyOf: - items: type: string type: array - type: 'null' title: Additional Soft Timeout Messages description: >- Extra static filler messages for subsequent soft timeouts in the same LLM generation. The first timeout uses `message`. If fewer messages are configured than `max_soft_timeouts_per_generation`, the last configured message is repeated; otherwise a built-in filler is used. x-convai-client-override: true x-convai-language-override: true type: object title: SoftTimeoutConfigOverride example: message: Hhmmmm...yeah. PromptAgentAPIModelOverride: properties: prompt: anyOf: - type: string - type: 'null' title: Prompt description: The prompt for the agent x-convai-client-override: true llm: anyOf: - $ref: '#/components/schemas/LLM' - type: 'null' description: >- The LLM to query with the prompt and the chat history. If using data residency, the LLM must be supported in the data residency environment x-convai-client-override: true tool_ids: anyOf: - items: type: string type: array - type: 'null' title: Tool Ids description: A list of IDs of tools used by the agent x-convai-client-override: true native_mcp_server_ids: anyOf: - items: type: string type: array - type: 'null' title: Native Mcp Server Ids description: A list of Native MCP server ids to be used by the agent x-convai-client-override: true knowledge_base: anyOf: - items: $ref: '#/components/schemas/KnowledgeBaseLocator' type: array - type: 'null' title: Knowledge Base description: A list of knowledge bases to be used by the agent x-convai-client-override: true type: object title: PromptAgentAPIModelOverride example: knowledge_base: [] llm: gemini-2.0-flash-001 prompt: >- You are a helpful assistant that can answer questions about the topic of the conversation. tool_ids: [] DynamicVariableNestedValueType-Input: anyOf: - type: string - type: number - type: integer - type: boolean - items: $ref: '#/components/schemas/DynamicVariableNestedValueType-Input' type: array - type: 'null' ConvAIEnvVarLocator: properties: env_var_label: type: string title: Env Var Label type: object required: - env_var_label title: ConvAIEnvVarLocator description: Used to reference an environment variable by label. ConvAIDynamicVariable: properties: variable_name: type: string title: Variable Name type: object required: - variable_name title: ConvAIDynamicVariable description: Used to reference a dynamic variable. CustomLLMAPIType: type: string enum: - chat_completions - responses - websocket title: CustomLLMAPIType EmbeddingModelEnum: type: string enum: - e5_mistral_7b_instruct - multilingual_e5_large_instruct title: EmbeddingModelEnum default: e5_mistral_7b_instruct ToolInterruptionMode: type: string enum: - allow - disable_during_tool - disable_during_tool_and_turn title: ToolInterruptionMode default: allow PreToolSpeechMode: type: string enum: - auto - force - 'off' title: PreToolSpeechMode DynamicVariableAssignment: properties: source: type: string const: response title: Source description: >- The source to extract the value from. Currently only 'response' is supported. default: response dynamic_variable: type: string title: Dynamic Variable description: The name of the dynamic variable to assign the extracted value to value_path: type: string title: Value Path description: >- Dot notation path to extract the value from the source (e.g., 'user.name' or 'data.0.id') sanitize: type: boolean title: Sanitize description: >- If true, this assignment's value will be removed from the tool response before sending to the LLM and transcript, but still processed for variable assignment. default: false preserve_native_type: type: boolean title: Preserve Native Type description: >- If true, non-scalar values (lists, objects) extracted from the tool response are stored as their native type instead of being stringified to JSON. Enable this to use extracted arrays directly as list dynamic variables. default: false additionalProperties: false type: object required: - dynamic_variable - value_path title: DynamicVariableAssignment description: >- Configuration for extracting values from tool responses and assigning them to dynamic variables. example: dynamic_variable: user_name preserve_native_type: false sanitize: false source: response value_path: user.name ToolCallSoundType: type: string enum: - typing - elevator1 - elevator2 - elevator3 - elevator4 title: ToolCallSoundType description: Predefined tool call sound types. ToolCallSoundBehavior: type: string enum: - auto - always title: ToolCallSoundBehavior description: Determines how the tool call sound should be played. ToolErrorHandlingMode: type: string enum: - auto - summarized - passthrough - hide title: ToolErrorHandlingMode description: >- Controls how tool errors are processed before being shared with the agent. DynamicVariablesConfig-Input: properties: dynamic_variable_placeholders: additionalProperties: $ref: '#/components/schemas/DynamicVariableValueType-Input' type: object title: Dynamic Variable Placeholders description: A dictionary of dynamic variable placeholders and their values type: object title: DynamicVariablesConfig example: dynamic_variable_placeholders: user_name: John Doe ToolExecutionMode: type: string enum: - immediate - post_tool_speech - async title: ToolExecutionMode WebhookToolApiSchemaConfig-Input: properties: request_headers: additionalProperties: anyOf: - type: string - $ref: '#/components/schemas/ConvAISecretLocator' - $ref: '#/components/schemas/ConvAIDynamicVariable' - $ref: '#/components/schemas/ConvAIEnvVarLocator' type: object title: Request Headers description: Headers that should be included in the request url: type: string title: Url description: >- The URL that the webhook will be sent to. May include path parameters, e.g. https://example.com/agents/{agent_id} method: type: string enum: - GET - POST - PUT - PATCH - DELETE title: Method description: The HTTP method to use for the webhook default: GET path_params_schema: additionalProperties: $ref: '#/components/schemas/LiteralJsonSchemaProperty' type: object title: Path Params Schema description: >- Schema for path parameters, if any. The keys should match the placeholders in the URL. query_params_schema: anyOf: - $ref: '#/components/schemas/QueryParamsJsonSchema' - type: 'null' description: >- Schema for any query params, if any. These will be added to end of the URL as query params. Note: properties in a query param must all be literal types request_body_schema: anyOf: - $ref: '#/components/schemas/ObjectJsonSchemaProperty-Input' - type: 'null' description: >- Schema for the body parameters, if any. Used for POST/PATCH/PUT requests. The schema should be an object which will be sent as the json body response_body_schema: anyOf: - $ref: '#/components/schemas/ObjectJsonSchemaProperty-Input' - type: 'null' description: >- Schema describing the expected response body structure. For documentation only; not surfaced to the LLM. response_filter: anyOf: - $ref: '#/components/schemas/ResponseFilter' - type: 'null' description: >- Optional allow-list filter applied to the response before the LLM sees it, so large responses don't pollute the context. Defaults to the full response. content_type: type: string enum: - application/json - application/x-www-form-urlencoded title: Content Type description: >- Content type for the request body. Only applies to POST/PUT/PATCH requests. default: application/json auth_resolved_params: items: type: string type: array uniqueItems: true title: Auth Resolved Params description: >- URL placeholders resolved from the auth connection (e.g. secrets injected via UrlSecretAuthConnection) rather than from path_params_schema. auth_connection: anyOf: - $ref: '#/components/schemas/AuthConnectionLocator' - $ref: '#/components/schemas/EnvironmentAuthConnectionLocator' - type: 'null' title: Auth Connection description: Optional auth connection to use for authentication with this webhook type: object required: - url title: WebhookToolApiSchemaConfig example: method: GET path_params_schema: agent_id: type: string query_params_schema: param1: type: string request_body_schema: param1: type: string request_headers: Authorization: Bearer {api_key} url: https://example.com/agents/{agent_id} ObjectJsonSchemaProperty-Input: properties: property_kind: type: string enum: - array - object title: Property Kind default: object description: type: string title: Description default: '' dynamic_variable: type: string title: Dynamic Variable description: >- When set, the entire parameter is populated from this dynamic variable at runtime. Mutually exclusive with description (LLM-provided value), constant_value, and is_omitted. default: '' constant_value: anyOf: - additionalProperties: true type: object - type: 'null' title: Constant Value description: >- When set, the entire object uses this constant JSON value at runtime. Mutually exclusive with description (LLM-provided object), dynamic_variable, and is_omitted. is_omitted: type: boolean title: Is Omitted description: >- If true, this parameter will be completely omitted from the request. Only valid for optional parameters. Mutually exclusive with description, dynamic_variable, and constant_value. default: false type: type: string const: object title: Type default: object required: items: type: string type: array title: Required properties: additionalProperties: oneOf: - $ref: '#/components/schemas/LiteralJsonSchemaProperty' - $ref: '#/components/schemas/ObjectJsonSchemaProperty-Input' - $ref: '#/components/schemas/ArrayJsonSchemaProperty-Input' type: object title: Properties required_constraints: anyOf: - $ref: '#/components/schemas/RequiredConstraints' - type: 'null' additionalProperties: false type: object title: ObjectJsonSchemaProperty EndCallToolConfig: properties: system_tool_type: type: string const: end_call title: System Tool Type default: end_call additionalProperties: false type: object title: EndCallToolConfig LanguageDetectionToolConfig: properties: system_tool_type: type: string const: language_detection title: System Tool Type default: language_detection only_at_conversation_start: type: boolean title: Only At Conversation Start description: >- If no language switch happens in the first 2 user turns, later attempts fail and the conversation stays in the current language. If the language switches during those turns, later switching stays available. Enable to reduce the possibility of false switching. default: false additionalProperties: false type: object title: LanguageDetectionToolConfig TransferToAgentToolConfig: properties: system_tool_type: type: string const: transfer_to_agent title: System Tool Type default: transfer_to_agent transfers: items: $ref: '#/components/schemas/AgentTransfer' type: array title: Transfers additionalProperties: false type: object required: - transfers title: TransferToAgentToolConfig TransferToNumberToolConfig: properties: system_tool_type: type: string const: transfer_to_number title: System Tool Type default: transfer_to_number transfers: items: $ref: '#/components/schemas/PhoneNumberTransfer' type: array title: Transfers enable_client_message: type: boolean title: Enable Client Message description: >- Whether to play a message to the client while they wait for transfer. Defaults to true. default: true additionalProperties: false type: object required: - transfers title: TransferToNumberToolConfig SkipTurnToolConfig: properties: system_tool_type: type: string const: skip_turn title: System Tool Type default: skip_turn additionalProperties: false type: object title: SkipTurnToolConfig PlayDTMFToolConfig: properties: system_tool_type: type: string const: play_keypad_touch_tone title: System Tool Type default: play_keypad_touch_tone use_out_of_band_dtmf: type: boolean title: Use Out Of Band Dtmf description: >- Send DTMF tones as out-of-band RTP events (RFC 4733) instead of in-band audio. Only effective for SIP trunk imported numbers. default: true suppress_turn_after_dtmf: type: boolean title: Suppress Turn After Dtmf description: >- If true, the agent will not generate further speech after playing DTMF tones. This prevents the agent's speech from interfering with IVR systems. default: false additionalProperties: false type: object title: PlayDTMFToolConfig VoicemailDetectionToolConfig: properties: system_tool_type: type: string const: voicemail_detection title: System Tool Type default: voicemail_detection voicemail_message: anyOf: - type: string - type: 'null' title: Voicemail Message description: >- Optional message to leave on voicemail when detected. If not provided, the call will end immediately when voicemail is detected. Supports dynamic variables (e.g., {{system__time}}, {{system__call_duration_secs}}, {{custom_variable}}). additionalProperties: false type: object title: VoicemailDetectionToolConfig KnowledgeBaseRagToolConfig: properties: system_tool_type: type: string const: knowledge_base_rag title: System Tool Type default: knowledge_base_rag additionalProperties: false type: object title: KnowledgeBaseRagToolConfig KnowledgeBaseToolConfig: properties: system_tool_type: type: string const: knowledge_base title: System Tool Type default: knowledge_base enabled_strategies: items: $ref: '#/components/schemas/SearchStrategy' type: array title: Enabled Strategies additionalProperties: false type: object title: KnowledgeBaseToolConfig StartProcedureToolConfig: properties: system_tool_type: type: string const: start_procedure title: System Tool Type default: start_procedure procedures: additionalProperties: anyOf: - $ref: '#/components/schemas/ProcedureVersionRef' - $ref: '#/components/schemas/ProcedureDraftRef' type: object title: Procedures additionalProperties: false type: object title: StartProcedureToolConfig EndProcedureToolConfig: properties: system_tool_type: type: string const: end_procedure title: System Tool Type default: end_procedure procedures: additionalProperties: anyOf: - $ref: '#/components/schemas/ProcedureVersionRef' - $ref: '#/components/schemas/ProcedureDraftRef' type: object title: Procedures additionalProperties: false type: object title: EndProcedureToolConfig IntegrationType: type: string enum: - mcp_server - mcp_integration title: IntegrationType MCPApprovalPolicy: type: string enum: - auto_approve_all - require_approval_all - require_approval_per_tool title: MCPApprovalPolicy description: Defines the MCP server-level approval policy for tool execution. default: require_approval_all ApiIntegrationWebhookOverrides: properties: schema_overrides: anyOf: - additionalProperties: oneOf: - $ref: '#/components/schemas/ConstantSchemaOverride' - $ref: '#/components/schemas/DynamicVariableSchemaOverride' - $ref: '#/components/schemas/LLMSchemaOverride' - $ref: '#/components/schemas/OmitSchemaOverride' discriminator: propertyName: source mapping: constant: $ref: '#/components/schemas/ConstantSchemaOverride' dynamic_variable: $ref: '#/components/schemas/DynamicVariableSchemaOverride' llm: $ref: '#/components/schemas/LLMSchemaOverride' omit: $ref: '#/components/schemas/OmitSchemaOverride' type: object - type: 'null' title: Schema Overrides request_headers: anyOf: - additionalProperties: anyOf: - type: string - $ref: '#/components/schemas/ConvAIDynamicVariable' type: object - type: 'null' title: Request Headers response_filter_mode: anyOf: - $ref: '#/components/schemas/ResponseFilterMode' - type: 'null' response_filters: anyOf: - items: type: string type: array - type: 'null' title: Response Filters type: object title: ApiIntegrationWebhookOverrides description: |- A whitelist of fields that can be overridden by users when configuring an API Integration Webhook Tool. SearchClientsParams: properties: smb_tool_type: type: string const: search_clients title: Smb Tool Type default: search_clients type: object title: SearchClientsParams description: Search for clients by name, phone number, or email. ListClientsParams: properties: smb_tool_type: type: string const: list_clients title: Smb Tool Type default: list_clients type: object title: ListClientsParams description: List clients ordered by most recently updated, with an optional limit. GetClientByPhoneParams: properties: smb_tool_type: type: string const: get_client_by_phone title: Smb Tool Type default: get_client_by_phone type: object title: GetClientByPhoneParams description: Look up a client by their exact phone number. CreateClientParams: properties: smb_tool_type: type: string const: create_client title: Smb Tool Type default: create_client type: object title: CreateClientParams description: Create a new client in the system. UpdateClientParams: properties: smb_tool_type: type: string const: update_client title: Smb Tool Type default: update_client type: object title: UpdateClientParams description: Update an existing client's information. DeleteClientParams: properties: smb_tool_type: type: string const: delete_client title: Smb Tool Type default: delete_client type: object title: DeleteClientParams description: Delete a client, cascading deletion of all their appointments first. ListStaffParams: properties: list_kwargs: additionalProperties: true type: object title: List Kwargs smb_tool_type: type: string const: list_staff title: Smb Tool Type default: list_staff type: object title: ListStaffParams CreateStaffParams: properties: smb_tool_type: type: string const: create_staff title: Smb Tool Type default: create_staff type: object title: CreateStaffParams description: Create a new staff member in the system. UpdateStaffParams: properties: smb_tool_type: type: string const: update_staff title: Smb Tool Type default: update_staff type: object title: UpdateStaffParams description: Update an existing staff member's information. DeleteStaffParams: properties: smb_tool_type: type: string const: delete_staff title: Smb Tool Type default: delete_staff type: object title: DeleteStaffParams description: Delete an existing staff member from the system. ListAssetsParams: properties: list_kwargs: additionalProperties: true type: object title: List Kwargs smb_tool_type: type: string const: list_assets title: Smb Tool Type default: list_assets type: object title: ListAssetsParams CreateAssetParams: properties: smb_tool_type: type: string const: create_asset title: Smb Tool Type default: create_asset type: object title: CreateAssetParams UpdateAssetParams: properties: smb_tool_type: type: string const: update_asset title: Smb Tool Type default: update_asset type: object title: UpdateAssetParams DeleteAssetParams: properties: smb_tool_type: type: string const: delete_asset title: Smb Tool Type default: delete_asset type: object title: DeleteAssetParams ListServicesParams: properties: list_kwargs: additionalProperties: true type: object title: List Kwargs smb_tool_type: type: string const: list_services title: Smb Tool Type default: list_services type: object title: ListServicesParams CreateServiceParams: properties: smb_tool_type: type: string const: create_service title: Smb Tool Type default: create_service type: object title: CreateServiceParams description: Create a new service (classic, rental, or group) in the system. UpdateServiceParams: properties: smb_tool_type: type: string const: update_service title: Smb Tool Type default: update_service type: object title: UpdateServiceParams description: Update an existing service's information. DeleteServiceParams: properties: smb_tool_type: type: string const: delete_service title: Smb Tool Type default: delete_service type: object title: DeleteServiceParams description: Delete an existing service from the system. ListProductsParams: properties: list_kwargs: additionalProperties: true type: object title: List Kwargs smb_tool_type: type: string const: list_products title: Smb Tool Type default: list_products type: object title: ListProductsParams CreateProductParams: properties: smb_tool_type: type: string const: create_product title: Smb Tool Type default: create_product type: object title: CreateProductParams UpdateProductParams: properties: smb_tool_type: type: string const: update_product title: Smb Tool Type default: update_product type: object title: UpdateProductParams DeleteProductParams: properties: smb_tool_type: type: string const: delete_product title: Smb Tool Type default: delete_product type: object title: DeleteProductParams CheckServiceAvailabilityParams: properties: smb_tool_type: type: string const: check_service_availability title: Smb Tool Type default: check_service_availability type: object title: CheckServiceAvailabilityParams CreateClientAppointmentParams: properties: smb_tool_type: type: string const: create_client_appointment title: Smb Tool Type default: create_client_appointment type: object title: CreateClientAppointmentParams GetClientAppointmentsParams: properties: smb_tool_type: type: string const: get_client_appointments title: Smb Tool Type default: get_client_appointments include_cancelled: type: boolean title: Include Cancelled default: false type: object title: GetClientAppointmentsParams GetAppointmentByConfirmationNumberParams: properties: smb_tool_type: type: string const: get_appointment_by_confirmation_number title: Smb Tool Type default: get_appointment_by_confirmation_number type: object title: GetAppointmentByConfirmationNumberParams description: >- Look up an appointment by the booking confirmation number the caller quotes. The confirmation number is the 8-character code shown on the booking confirmation page (e.g. ``#01ABCDEF``). Callers may read it back with or without the leading ``#`` and with varied spacing; the tool normalizes the input and does a prefix match on the stored calendar item id. CreateOrderParams: properties: smb_tool_type: type: string const: create_order title: Smb Tool Type default: create_order type: object title: CreateOrderParams GetOrderByConfirmationNumberParams: properties: smb_tool_type: type: string const: get_order_by_confirmation_number title: Smb Tool Type default: get_order_by_confirmation_number type: object title: GetOrderByConfirmationNumberParams GetClientOrdersParams: properties: smb_tool_type: type: string const: get_client_orders title: Smb Tool Type default: get_client_orders include_cancelled: type: boolean title: Include Cancelled default: false type: object title: GetClientOrdersParams UpdateOrderParams: properties: smb_tool_type: type: string const: update_order title: Smb Tool Type default: update_order type: object title: UpdateOrderParams CancelOrderParams: properties: smb_tool_type: type: string const: cancel_order title: Smb Tool Type default: cancel_order type: object title: CancelOrderParams ListGroupSessionsParams: properties: smb_tool_type: type: string const: list_group_sessions title: Smb Tool Type default: list_group_sessions type: object title: ListGroupSessionsParams description: >- List scheduled group sessions for a group service in a date range. Group services are scheduled in advance (e.g. yoga classes, workshops) and callers register against an existing session. Use this for group services; use ``check_service_availability`` for appointment / rental services. ScheduleGroupSessionParams: properties: smb_tool_type: type: string const: schedule_group_session title: Smb Tool Type default: schedule_group_session type: object title: ScheduleGroupSessionParams description: >- Schedule a single instance of a group service. The session's duration is derived from the parent service so the assistant only has to pin start time, the (optional) instructor / room, and the location. Participants register separately via ``register_for_group_session``. RegisterForGroupSessionParams: properties: smb_tool_type: type: string const: register_for_group_session title: Smb Tool Type default: register_for_group_session type: object title: RegisterForGroupSessionParams description: Register a client for a scheduled group session. CancelGroupSessionRegistrationParams: properties: smb_tool_type: type: string const: cancel_group_session_registration title: Smb Tool Type default: cancel_group_session_registration type: object title: CancelGroupSessionRegistrationParams description: Cancel a single client's registration for a group session. UpdateGroupSessionSeatsParams: properties: smb_tool_type: type: string const: update_group_session_seats title: Smb Tool Type default: update_group_session_seats type: object title: UpdateGroupSessionSeatsParams description: Change the seat count of an existing group session registration. CancelGroupSessionForAllParams: properties: smb_tool_type: type: string const: cancel_group_session_for_all title: Smb Tool Type default: cancel_group_session_for_all type: object title: CancelGroupSessionForAllParams description: >- Cancel an entire group session and notify every registered participant. Destructive -- prefer ``cancel_group_session_registration`` for cancelling a single attendee. DeleteGroupSessionParams: properties: smb_tool_type: type: string const: delete_group_session title: Smb Tool Type default: delete_group_session type: object title: DeleteGroupSessionParams description: |- Permanently remove a previously-cancelled group session. Group analogue of ``delete_calendar_event``: cancel (``cancel_group_session_for_all``) is the soft, history-preserving step; this tool is the irreversible follow-up that drops the row from Mongo and the staff Google Calendar entirely. The backend rejects the call (422) if the session hasn't been cancelled yet, so the only safe path is cancel-then-delete. ListCalendarEventsParams: properties: smb_tool_type: type: string const: list_calendar_events title: Smb Tool Type default: list_calendar_events include_cancelled: type: boolean title: Include Cancelled default: false type: object title: ListCalendarEventsParams UpdateCalendarEventParams: properties: smb_tool_type: type: string const: update_calendar_event title: Smb Tool Type default: update_calendar_event type: object title: UpdateCalendarEventParams CancelCalendarEventParams: properties: smb_tool_type: type: string const: cancel_calendar_event title: Smb Tool Type default: cancel_calendar_event type: object title: CancelCalendarEventParams RestoreCalendarEventParams: properties: smb_tool_type: type: string const: restore_calendar_event title: Smb Tool Type default: restore_calendar_event type: object title: RestoreCalendarEventParams DeleteCalendarEventParams: properties: smb_tool_type: type: string const: delete_calendar_event title: Smb Tool Type default: delete_calendar_event type: object title: DeleteCalendarEventParams description: |- Permanently remove a previously-cancelled calendar event. This delete tool is the irreversible follow-up to cancel_calendar_event. The backend rejects the call (422) if the event hasn't been cancelled yet, so the only safe path is cancel-then-delete. ListCustomerFacingAgentsParams: properties: smb_tool_type: type: string const: list_customer_facing_agents title: Smb Tool Type default: list_customer_facing_agents type: object title: ListCustomerFacingAgentsParams description: >- List every customer-facing agent on the workspace. The assistant uses this whenever it needs to act on a specific customer-facing agent (rules, config edits, etc.) so it can pick the right ``agent_id`` to pass to mutating tools. Mirrors the ``list_services`` / ``list_clients`` pattern: read once, then mutate by id. ListAgentRulesParams: properties: smb_tool_type: type: string const: list_agent_rules title: Smb Tool Type default: list_agent_rules type: object title: ListAgentRulesParams CreateAgentRuleParams: properties: smb_tool_type: type: string const: create_agent_rule title: Smb Tool Type default: create_agent_rule type: object title: CreateAgentRuleParams UpdateAgentRuleParams: properties: smb_tool_type: type: string const: update_agent_rule title: Smb Tool Type default: update_agent_rule type: object title: UpdateAgentRuleParams DeleteAgentRuleParams: properties: smb_tool_type: type: string const: delete_agent_rule title: Smb Tool Type default: delete_agent_rule type: object title: DeleteAgentRuleParams ListTransferRulesParams: properties: smb_tool_type: type: string const: list_transfer_rules title: Smb Tool Type default: list_transfer_rules type: object title: ListTransferRulesParams CreateTransferRuleParams: properties: smb_tool_type: type: string const: create_transfer_rule title: Smb Tool Type default: create_transfer_rule post_dial_digits_enabled: type: boolean title: Post Dial Digits Enabled description: >- Whether to offer the post_dial_digits parameter, set from the receptionists' enable_play_keypad_touch_tone_tool config. Digits saved while that is off are dropped when the receptionist is built, so the parameter is hidden rather than accepted and ignored. default: false type: object title: CreateTransferRuleParams UpdateTransferRuleParams: properties: smb_tool_type: type: string const: update_transfer_rule title: Smb Tool Type default: update_transfer_rule post_dial_digits_enabled: type: boolean title: Post Dial Digits Enabled description: >- Whether to offer the post_dial_digits parameter, set from the receptionists' enable_play_keypad_touch_tone_tool config. Digits saved while that is off are dropped when the receptionist is built, so the parameter is hidden rather than accepted and ignored. default: false type: object title: UpdateTransferRuleParams DeleteTransferRuleParams: properties: smb_tool_type: type: string const: delete_transfer_rule title: Smb Tool Type default: delete_transfer_rule type: object title: DeleteTransferRuleParams ListAgentProceduresParams: properties: smb_tool_type: type: string const: list_agent_procedures title: Smb Tool Type default: list_agent_procedures type: object title: ListAgentProceduresParams ListAgentReferencesParams: properties: smb_tool_type: type: string const: list_agent_references title: Smb Tool Type default: list_agent_references type: object title: ListAgentReferencesParams CreateAgentProcedureParams: properties: smb_tool_type: type: string const: create_agent_procedure title: Smb Tool Type default: create_agent_procedure type: object title: CreateAgentProcedureParams UpdateAgentProcedureParams: properties: smb_tool_type: type: string const: update_agent_procedure title: Smb Tool Type default: update_agent_procedure type: object title: UpdateAgentProcedureParams DeleteAgentProcedureParams: properties: smb_tool_type: type: string const: delete_agent_procedure title: Smb Tool Type default: delete_agent_procedure type: object title: DeleteAgentProcedureParams ListHolidaysParams: properties: smb_tool_type: type: string const: list_holidays title: Smb Tool Type default: list_holidays type: object title: ListHolidaysParams CreateHolidayParams: properties: smb_tool_type: type: string const: create_holiday title: Smb Tool Type default: create_holiday type: object title: CreateHolidayParams UpdateHolidayParams: properties: smb_tool_type: type: string const: update_holiday title: Smb Tool Type default: update_holiday type: object title: UpdateHolidayParams DeleteHolidayParams: properties: smb_tool_type: type: string const: delete_holiday title: Smb Tool Type default: delete_holiday type: object title: DeleteHolidayParams GetScheduleParams: properties: smb_tool_type: type: string const: get_schedule title: Smb Tool Type default: get_schedule include_location_filter: type: boolean title: Include Location Filter default: false type: object title: GetScheduleParams SubmitBusinessInfoParams: properties: smb_tool_type: type: string const: submit_business_info title: Smb Tool Type default: submit_business_info type: object title: SubmitBusinessInfoParams description: >- Finalize the onboarding interview: create a text knowledge source and mark done. UpdateBusinessInfoParams: properties: smb_tool_type: type: string const: update_business_info title: Smb Tool Type default: update_business_info type: object title: UpdateBusinessInfoParams UpdateCustomerFacingConfigParams: properties: smb_tool_type: type: string const: update_customer_facing_config title: Smb Tool Type default: update_customer_facing_config type: object title: UpdateCustomerFacingConfigParams GetAnalyticsSummaryParams: properties: smb_tool_type: type: string const: get_analytics_summary title: Smb Tool Type default: get_analytics_summary type: object title: GetAnalyticsSummaryParams description: Get a summary of key business analytics for a time period. GetBookingPageSettingsParams: properties: smb_tool_type: type: string const: get_booking_page_settings title: Smb Tool Type default: get_booking_page_settings type: object title: GetBookingPageSettingsParams UpdateBookingPageSettingsParams: properties: smb_tool_type: type: string const: update_booking_page_settings title: Smb Tool Type default: update_booking_page_settings type: object title: UpdateBookingPageSettingsParams UpdateBookingPageAppearanceParams: properties: smb_tool_type: type: string const: update_booking_page_appearance title: Smb Tool Type default: update_booking_page_appearance type: object title: UpdateBookingPageAppearanceParams GetBookingSlugStatusParams: properties: smb_tool_type: type: string const: get_booking_slug_status title: Smb Tool Type default: get_booking_slug_status type: object title: GetBookingSlugStatusParams SetBookingSlugParams: properties: smb_tool_type: type: string const: set_booking_slug title: Smb Tool Type default: set_booking_slug type: object title: SetBookingSlugParams ListClientInteractionsParams: properties: smb_tool_type: type: string const: list_client_interactions title: Smb Tool Type default: list_client_interactions type: object title: ListClientInteractionsParams CreateClientInteractionParams: properties: smb_tool_type: type: string const: create_client_interaction title: Smb Tool Type default: create_client_interaction type: object title: CreateClientInteractionParams DeleteClientInteractionParams: properties: smb_tool_type: type: string const: delete_client_interaction title: Smb Tool Type default: delete_client_interaction type: object title: DeleteClientInteractionParams ListLocationsParams: properties: smb_tool_type: type: string const: list_locations title: Smb Tool Type default: list_locations type: object title: ListLocationsParams description: Params + Reception-proxied ``run()`` for list_locations. CreateLocationParams: properties: smb_tool_type: type: string const: create_location title: Smb Tool Type default: create_location type: object title: CreateLocationParams UpdateLocationParams: properties: smb_tool_type: type: string const: update_location title: Smb Tool Type default: update_location type: object title: UpdateLocationParams DeleteLocationParams: properties: smb_tool_type: type: string const: delete_location title: Smb Tool Type default: delete_location type: object title: DeleteLocationParams LeaveMessageParams: properties: smb_tool_type: type: string const: leave_message title: Smb Tool Type default: leave_message type: object title: LeaveMessageParams ReportKnowledgeGapParams: properties: smb_tool_type: type: string const: report_knowledge_gap title: Smb Tool Type default: report_knowledge_gap type: object title: ReportKnowledgeGapParams OptInSmsReminderParams: properties: smb_tool_type: type: string const: opt_in_sms_reminder title: Smb Tool Type default: opt_in_sms_reminder type: object title: OptInSmsReminderParams OptOutSmsReminderParams: properties: smb_tool_type: type: string const: opt_out_sms_reminder title: Smb Tool Type default: opt_out_sms_reminder type: object title: OptOutSmsReminderParams TriggerUserVerificationParams: properties: smb_tool_type: type: string const: trigger_user_verification title: Smb Tool Type default: trigger_user_verification type: object title: TriggerUserVerificationParams ValidateUserVerificationCodeParams: properties: smb_tool_type: type: string const: validate_user_verification_code title: Smb Tool Type default: validate_user_verification_code type: object title: ValidateUserVerificationCodeParams ASTStringNode-Input: properties: type: type: string const: string_literal title: Type default: string_literal value: type: string title: Value description: Value of this literal. type: object required: - value title: ASTStringNode ASTNumberNode-Input: properties: type: type: string const: number_literal title: Type default: number_literal value: anyOf: - type: number - type: integer title: Value description: Value of this literal. type: object required: - value title: ASTNumberNode ASTBooleanNode-Input: properties: type: type: string const: boolean_literal title: Type default: boolean_literal value: type: boolean title: Value description: Value of this literal. type: object required: - value title: ASTBooleanNode ASTNullNode-Input: properties: type: type: string const: null_literal title: Type default: null_literal type: object title: ASTNullNode ASTLLMNode-Input: properties: type: type: string const: llm title: Type default: llm value_schema: $ref: '#/components/schemas/LLMLiteralJsonSchemaProperty' description: JSON schema describing the value that the LLM should extract. examples: - description: User's last message contains a question about our pricing. type: boolean - description: User provided their email address. type: boolean type: object required: - value_schema title: ASTLLMNode ASTDynamicVariableNode-Input: properties: type: type: string const: dynamic_variable title: Type default: dynamic_variable name: type: string title: Name description: The name of the dynamic variable. type: object required: - name title: ASTDynamicVariableNode ASTOrOperatorNode-Input: properties: type: type: string const: or_operator title: Type default: or_operator children: items: $ref: '#/components/schemas/ASTNode-Input' type: array minItems: 2 title: Children description: Child nodes of the logical operator. type: object required: - children title: ASTOrOperatorNode ASTAndOperatorNode-Input: properties: type: type: string const: and_operator title: Type default: and_operator children: items: $ref: '#/components/schemas/ASTNode-Input' type: array minItems: 2 title: Children description: Child nodes of the logical operator. type: object required: - children title: ASTAndOperatorNode ASTEqualsOperatorNode-Input: properties: type: type: string const: eq_operator title: Type default: eq_operator left: $ref: '#/components/schemas/ASTNode-Input' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Input' description: Right operand of the binary operator. type: object required: - left - right title: ASTEqualsOperatorNode ASTNotEqualsOperatorNode-Input: properties: type: type: string const: neq_operator title: Type default: neq_operator left: $ref: '#/components/schemas/ASTNode-Input' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Input' description: Right operand of the binary operator. type: object required: - left - right title: ASTNotEqualsOperatorNode ASTGreaterThanOperatorNode-Input: properties: type: type: string const: gt_operator title: Type default: gt_operator left: $ref: '#/components/schemas/ASTNode-Input' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Input' description: Right operand of the binary operator. type: object required: - left - right title: ASTGreaterThanOperatorNode ASTLessThanOperatorNode-Input: properties: type: type: string const: lt_operator title: Type default: lt_operator left: $ref: '#/components/schemas/ASTNode-Input' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Input' description: Right operand of the binary operator. type: object required: - left - right title: ASTLessThanOperatorNode ASTGreaterThanOrEqualsOperatorNode-Input: properties: type: type: string const: gte_operator title: Type default: gte_operator left: $ref: '#/components/schemas/ASTNode-Input' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Input' description: Right operand of the binary operator. type: object required: - left - right title: ASTGreaterThanOrEqualsOperatorNode ASTLessThanOrEqualsOperatorNode-Input: properties: type: type: string const: lte_operator title: Type default: lte_operator left: $ref: '#/components/schemas/ASTNode-Input' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Input' description: Right operand of the binary operator. type: object required: - left - right title: ASTLessThanOrEqualsOperatorNode ASTAdditionOperatorNode-Input: properties: type: type: string const: add_operator title: Type default: add_operator left: $ref: '#/components/schemas/ASTNode-Input' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Input' description: Right operand of the binary operator. type: object required: - left - right title: ASTAdditionOperatorNode ASTSubtractionOperatorNode-Input: properties: type: type: string const: sub_operator title: Type default: sub_operator left: $ref: '#/components/schemas/ASTNode-Input' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Input' description: Right operand of the binary operator. type: object required: - left - right title: ASTSubtractionOperatorNode ASTMultiplicationOperatorNode-Input: properties: type: type: string const: mul_operator title: Type default: mul_operator left: $ref: '#/components/schemas/ASTNode-Input' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Input' description: Right operand of the binary operator. type: object required: - left - right title: ASTMultiplicationOperatorNode ASTDivisionOperatorNode-Input: properties: type: type: string const: div_operator title: Type default: div_operator left: $ref: '#/components/schemas/ASTNode-Input' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Input' description: Right operand of the binary operator. type: object required: - left - right title: ASTDivisionOperatorNode ASTConditionalOperatorNode-Input: properties: type: type: string const: conditional_operator title: Type default: conditional_operator condition: $ref: '#/components/schemas/ASTNode-Input' description: Condition deciding which expression should be selected. trueExpression: $ref: '#/components/schemas/ASTNode-Input' description: Expression selected if the condition is true. falseExpression: $ref: '#/components/schemas/ASTNode-Input' description: Expression selected if the condition is false. type: object required: - condition - trueExpression - falseExpression title: ASTConditionalOperatorNode DynamicVariableNestedValueType-Output: anyOf: - type: string - type: number - type: integer - type: boolean - items: $ref: '#/components/schemas/DynamicVariableNestedValueType-Output' type: array - type: 'null' SoftTimeoutConfigOverrideConfig: properties: message: type: boolean title: Message description: Whether to allow overriding the message field. default: false additional_soft_timeout_messages: type: boolean title: Additional Soft Timeout Messages description: >- Whether to allow overriding the additional_soft_timeout_messages field. default: false type: object title: SoftTimeoutConfigOverrideConfig PromptAgentAPIModelOverrideConfig: properties: prompt: type: boolean title: Prompt description: Whether to allow overriding the prompt field. default: false llm: type: boolean title: Llm description: Whether to allow overriding the llm field. default: false tool_ids: type: boolean title: Tool Ids description: Whether to allow overriding the tool_ids field. default: false native_mcp_server_ids: type: boolean title: Native Mcp Server Ids description: Whether to allow overriding the native_mcp_server_ids field. default: false knowledge_base: type: boolean title: Knowledge Base description: Whether to allow overriding the knowledge_base field. default: false type: object title: PromptAgentAPIModelOverrideConfig ContentThresholdGuardrail: properties: is_enabled: type: boolean title: Is Enabled default: false threshold: anyOf: - type: number - type: string enum: - low - medium - high title: Threshold default: 0.3 type: object title: ContentThresholdGuardrail ThresholdGuardrail: properties: is_enabled: type: boolean title: Is Enabled default: false threshold: type: number maximum: 1 minimum: 0 title: Threshold default: 0.3 type: object title: ThresholdGuardrail CustomGuardrailConfig: properties: is_enabled: type: boolean title: Is Enabled default: false name: type: string maxLength: 500 minLength: 1 title: Name description: User-facing name for this guardrail prompt: type: string maxLength: 10000 minLength: 1 title: Prompt description: >- Instruction describing what to block, e.g. 'don't talk about politics' execution_mode: $ref: '#/components/schemas/GuardrailExecutionMode' default: streaming model: type: string enum: - gemini-2.5-flash-lite - gemini-2.5-flash - gemini-3.1-flash-lite - gemini-3.5-flash - claude-haiku-4-5 - claude-sonnet-4-6 - gpt-5.4-nano - gpt-5.4-mini title: Model description: LLM model to use for custom guardrail evaluation default: gemini-2.5-flash-lite history_message_count: type: integer maximum: 100 minimum: 0 title: History Message Count description: >- How many recent customer messages to include in the guardrail's history, plus the agent replies that follow them (and tool calls and results when history_include_tool_calls is enabled). Only customer messages count toward the limit. 0 (default) shows none; 1 shows the customer's latest message onward. When > 0, the guardrail prompt can refer to this history as ; the reply under evaluation appears as and may repeat at the end of the history. default: 0 history_include_tool_calls: type: boolean title: History Include Tool Calls description: >- When history is on (history_message_count > 0), also render interleaved tool calls and results in the window. Off by default: history shows only customer and agent text. Tool payloads can be large, so enabling this increases evaluation token cost. default: false x-fern-ignore: true trigger_action: oneOf: - $ref: '#/components/schemas/EndCallTriggerAction' - $ref: '#/components/schemas/RetryTriggerAction' title: Trigger Action discriminator: propertyName: type mapping: end_call: $ref: '#/components/schemas/EndCallTriggerAction' retry: $ref: '#/components/schemas/RetryTriggerAction' evaluate_full_response_only: type: boolean title: Evaluate Full Response Only description: >- Evaluate once against the complete non-TTS response instead of cumulative partials. Requires blocking mode. default: false type: object required: - name - prompt title: CustomGuardrailConfig description: Single custom guardrail configuration. ASTStringNode-Output: properties: type: type: string const: string_literal title: Type default: string_literal value: type: string title: Value description: Value of this literal. type: object required: - type - value title: ASTStringNode ASTNumberNode-Output: properties: type: type: string const: number_literal title: Type default: number_literal value: anyOf: - type: number - type: integer title: Value description: Value of this literal. type: object required: - type - value title: ASTNumberNode ASTBooleanNode-Output: properties: type: type: string const: boolean_literal title: Type default: boolean_literal value: type: boolean title: Value description: Value of this literal. type: object required: - type - value title: ASTBooleanNode ASTNullNode-Output: properties: type: type: string const: null_literal title: Type default: null_literal type: object required: - type title: ASTNullNode ASTLLMNode-Output: properties: type: type: string const: llm title: Type default: llm value_schema: $ref: '#/components/schemas/LLMLiteralJsonSchemaProperty' description: JSON schema describing the value that the LLM should extract. examples: - description: User's last message contains a question about our pricing. type: boolean - description: User provided their email address. type: boolean type: object required: - type - value_schema title: ASTLLMNode ASTDynamicVariableNode-Output: properties: type: type: string const: dynamic_variable title: Type default: dynamic_variable name: type: string title: Name description: The name of the dynamic variable. type: object required: - type - name title: ASTDynamicVariableNode ASTOrOperatorNode-Output: properties: type: type: string const: or_operator title: Type default: or_operator children: items: $ref: '#/components/schemas/ASTNode-Output' type: array minItems: 2 title: Children description: Child nodes of the logical operator. type: object required: - type - children title: ASTOrOperatorNode ASTAndOperatorNode-Output: properties: type: type: string const: and_operator title: Type default: and_operator children: items: $ref: '#/components/schemas/ASTNode-Output' type: array minItems: 2 title: Children description: Child nodes of the logical operator. type: object required: - type - children title: ASTAndOperatorNode ASTEqualsOperatorNode-Output: properties: type: type: string const: eq_operator title: Type default: eq_operator left: $ref: '#/components/schemas/ASTNode-Output' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Output' description: Right operand of the binary operator. type: object required: - type - left - right title: ASTEqualsOperatorNode ASTNotEqualsOperatorNode-Output: properties: type: type: string const: neq_operator title: Type default: neq_operator left: $ref: '#/components/schemas/ASTNode-Output' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Output' description: Right operand of the binary operator. type: object required: - type - left - right title: ASTNotEqualsOperatorNode ASTGreaterThanOperatorNode-Output: properties: type: type: string const: gt_operator title: Type default: gt_operator left: $ref: '#/components/schemas/ASTNode-Output' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Output' description: Right operand of the binary operator. type: object required: - type - left - right title: ASTGreaterThanOperatorNode ASTLessThanOperatorNode-Output: properties: type: type: string const: lt_operator title: Type default: lt_operator left: $ref: '#/components/schemas/ASTNode-Output' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Output' description: Right operand of the binary operator. type: object required: - type - left - right title: ASTLessThanOperatorNode ASTGreaterThanOrEqualsOperatorNode-Output: properties: type: type: string const: gte_operator title: Type default: gte_operator left: $ref: '#/components/schemas/ASTNode-Output' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Output' description: Right operand of the binary operator. type: object required: - type - left - right title: ASTGreaterThanOrEqualsOperatorNode ASTLessThanOrEqualsOperatorNode-Output: properties: type: type: string const: lte_operator title: Type default: lte_operator left: $ref: '#/components/schemas/ASTNode-Output' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Output' description: Right operand of the binary operator. type: object required: - type - left - right title: ASTLessThanOrEqualsOperatorNode ASTAdditionOperatorNode-Output: properties: type: type: string const: add_operator title: Type default: add_operator left: $ref: '#/components/schemas/ASTNode-Output' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Output' description: Right operand of the binary operator. type: object required: - type - left - right title: ASTAdditionOperatorNode ASTSubtractionOperatorNode-Output: properties: type: type: string const: sub_operator title: Type default: sub_operator left: $ref: '#/components/schemas/ASTNode-Output' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Output' description: Right operand of the binary operator. type: object required: - type - left - right title: ASTSubtractionOperatorNode ASTMultiplicationOperatorNode-Output: properties: type: type: string const: mul_operator title: Type default: mul_operator left: $ref: '#/components/schemas/ASTNode-Output' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Output' description: Right operand of the binary operator. type: object required: - type - left - right title: ASTMultiplicationOperatorNode ASTDivisionOperatorNode-Output: properties: type: type: string const: div_operator title: Type default: div_operator left: $ref: '#/components/schemas/ASTNode-Output' description: Left operand of the binary operator. right: $ref: '#/components/schemas/ASTNode-Output' description: Right operand of the binary operator. type: object required: - type - left - right title: ASTDivisionOperatorNode ASTConditionalOperatorNode-Output: properties: type: type: string const: conditional_operator title: Type default: conditional_operator condition: $ref: '#/components/schemas/ASTNode-Output' description: Condition deciding which expression should be selected. trueExpression: $ref: '#/components/schemas/ASTNode-Output' description: Expression selected if the condition is true. falseExpression: $ref: '#/components/schemas/ASTNode-Output' description: Expression selected if the condition is false. type: object required: - type - condition - trueExpression - falseExpression title: ASTConditionalOperatorNode DynamicVariablesConfigWorkflowOverride-Output: properties: dynamic_variable_placeholders: anyOf: - additionalProperties: $ref: '#/components/schemas/DynamicVariableValueType-Output' type: object - type: 'null' title: Dynamic Variable Placeholders description: A dictionary of dynamic variable placeholders and their values type: object title: DynamicVariablesConfigWorkflowOverride example: dynamic_variable_placeholders: user_name: John Doe PromptAgentAPIModelWorkflowOverride-Output: properties: prompt: anyOf: - type: string - type: 'null' title: Prompt description: The prompt for the agent x-convai-client-override: true llm: anyOf: - $ref: '#/components/schemas/LLM' - type: 'null' description: >- The LLM to query with the prompt and the chat history. If using data residency, the LLM must be supported in the data residency environment x-convai-client-override: true reasoning_effort: anyOf: - $ref: '#/components/schemas/LLMReasoningEffort' - type: 'null' description: Reasoning effort of the model. Only available for some models. thinking_budget: anyOf: - type: integer - type: 'null' title: Thinking Budget description: >- Max number of tokens used for thinking. Use 0 to turn off if supported by the model. enable_reasoning_summary: anyOf: - type: boolean - type: 'null' title: Enable Reasoning Summary description: >- Enable model reasoning summaries. When disabled, we do not request summaries from provider if possible for faster TTFB. Not ZRM compatible. temperature: anyOf: - type: number - type: 'null' title: Temperature description: >- The temperature for the LLM. Defaults to 0. Set to null to omit the parameter from the LLM request entirely (useful for custom LLMs that reject the temperature field). max_tokens: anyOf: - type: integer - type: 'null' title: Max Tokens description: If greater than 0, maximum number of tokens the LLM can predict tool_ids: anyOf: - items: type: string type: array - type: 'null' title: Tool Ids description: A list of IDs of tools used by the agent x-convai-client-override: true built_in_tools: anyOf: - $ref: '#/components/schemas/BuiltInToolsWorkflowOverride' - type: 'null' description: Built-in system tools to be used by the agent mcp_server_ids: anyOf: - items: type: string type: array - type: 'null' title: Mcp Server Ids description: A list of MCP server ids to be used by the agent native_mcp_server_ids: anyOf: - items: type: string type: array - type: 'null' title: Native Mcp Server Ids description: A list of Native MCP server ids to be used by the agent x-convai-client-override: true knowledge_base: anyOf: - items: $ref: '#/components/schemas/KnowledgeBaseLocator' type: array - type: 'null' title: Knowledge Base description: A list of knowledge bases to be used by the agent x-convai-client-override: true custom_llm: anyOf: - $ref: '#/components/schemas/CustomLLM' - type: 'null' description: Definition for a custom LLM if LLM field is set to 'CUSTOM_LLM' ignore_default_personality: anyOf: - type: boolean - type: 'null' title: Ignore Default Personality description: >- Whether to remove the default personality lines from the system prompt rag: anyOf: - $ref: '#/components/schemas/RagConfigWorkflowOverride' - type: 'null' description: Configuration for RAG timezone: anyOf: - type: string - type: 'null' title: Timezone description: >- Timezone for displaying current time in system prompt. If set, the current time will be included in the system prompt using this timezone. Must be a valid timezone name (e.g., 'America/New_York', 'Europe/London', 'UTC'). Recommended for accurate time-aware responses; without this, the agent has no knowledge of the current date/time unless you provide it via dynamic variables or tools, which can lead to incorrect or hallucinated time references. backup_llm_config: anyOf: - $ref: '#/components/schemas/BackupLLMDefault' - $ref: '#/components/schemas/BackupLLMDisabled' - $ref: '#/components/schemas/BackupLLMOverride' - type: 'null' title: Backup Llm Config description: >- Configuration for backup LLM cascading. Can be disabled, use system defaults, or specify custom order. cascade_timeout_seconds: anyOf: - type: number - type: 'null' title: Cascade Timeout Seconds description: >- Time in seconds before cascading to backup LLM. Must be between 2 and 15 seconds. tools: anyOf: - items: oneOf: - $ref: '#/components/schemas/WebhookToolConfig-Output' - $ref: '#/components/schemas/ClientToolConfig-Output' - $ref: '#/components/schemas/SystemToolConfig' - $ref: '#/components/schemas/MCPToolConfig-Output' - $ref: >- #/components/schemas/ApiIntegrationWebhookToolConfig-Output - $ref: '#/components/schemas/SMBToolConfig' description: The type of tool discriminator: propertyName: type mapping: api_integration_webhook: $ref: >- #/components/schemas/ApiIntegrationWebhookToolConfig-Output client: $ref: '#/components/schemas/ClientToolConfig-Output' mcp: $ref: '#/components/schemas/MCPToolConfig-Output' smb: $ref: '#/components/schemas/SMBToolConfig' system: $ref: '#/components/schemas/SystemToolConfig' webhook: $ref: '#/components/schemas/WebhookToolConfig-Output' type: array - type: 'null' title: Tools description: >- A list of tools that the agent can use over the course of the conversation, use tool_ids instead type: object title: PromptAgentAPIModelWorkflowOverride example: knowledge_base: [] llm: gemini-2.0-flash-001 max_tokens: -1 prompt: >- You are a helpful assistant that can answer questions about the topic of the conversation. temperature: 0 tool_ids: [] tools: [] LiteralJsonSchemaProperty: properties: type: anyOf: - type: string enum: - boolean - string - integer - number - items: type: string type: array maxItems: 2 minItems: 2 title: Type description: type: string title: Description description: >- The description of the property. When set, the LLM will provide the value based on this description. Mutually exclusive with dynamic_variable, is_system_provided, constant_value, and is_omitted. default: '' enum: anyOf: - items: type: string type: array - type: 'null' title: Enum description: List of allowed string values for string type parameters is_system_provided: type: boolean title: Is System Provided description: >- If true, the value will be populated by the system at runtime. Used by API Integration Webhook tools for templating. Mutually exclusive with description, dynamic_variable, constant_value, and is_omitted. default: false dynamic_variable: type: string title: Dynamic Variable description: >- The name of the dynamic variable to use for this property's value. Mutually exclusive with description, is_system_provided, constant_value, and is_omitted. default: '' allowed_values_dynamic_variable: type: string title: Allowed Values Dynamic Variable description: >- When set, the LLM provides the value but the runtime rejects any value not present in the list held by this dynamic variable. Use to let the LLM pick from a server-verified set (e.g. the IDs the current user is allowed to access). Requires description; mutually exclusive with dynamic_variable, is_system_provided, constant_value, and is_omitted. default: '' constant_value: anyOf: - type: string - type: integer - type: number - type: boolean - type: 'null' title: Constant Value description: >- A constant value to use for this property. Mutually exclusive with description, dynamic_variable, is_system_provided, and is_omitted. default: '' is_omitted: type: boolean title: Is Omitted description: >- If true, this parameter will be completely omitted from the request. Only valid for optional parameters. Mutually exclusive with description, dynamic_variable, is_system_provided, and constant_value. default: false type: object required: - type title: LiteralJsonSchemaProperty description: >- Schema property for literal JSON types. IMPORTANT: Only ONE of the following fields can be set: description (LLM provides value), dynamic_variable (value from variable), is_system_provided (system provides value), constant_value (fixed value), or is_omitted (parameter is omitted). These are mutually exclusive. example: description: A user-provided message type: string QueryParamsJsonSchema: properties: properties: additionalProperties: $ref: '#/components/schemas/LiteralJsonSchemaProperty' type: object minProperties: 1 title: Properties required: items: type: string type: array title: Required additionalProperties: false type: object required: - properties title: QueryParamsJsonSchema ResponseFilter: properties: mode: $ref: '#/components/schemas/ResponseFilterMode' description: >- Controls how tool responses are filtered. 'all' returns entire response, 'allow' returns only specified paths, 'hide_all' hides the entire response. default: all filters: items: type: string type: array title: Filters description: >- Dot notation paths to include when mode is 'allow' (e.g., ['ticket.id', 'ticket.status']). content_type: type: string const: application/json title: Content Type description: >- Content type for response filtering. Only 'application/json' responses are filtered. default: application/json type: object title: ResponseFilter description: >- Configuration for filtering tool responses before they are visible to the agent. AuthConnectionLocator: properties: auth_connection_id: type: string title: Auth Connection Id type: object required: - auth_connection_id title: AuthConnectionLocator description: >- Used to reference an auth connection from the workspace's auth connection store. EnvironmentAuthConnectionLocator: properties: env_var_label: type: string title: Env Var Label type: object required: - env_var_label title: EnvironmentAuthConnectionLocator description: |- References an environment variable of type 'auth_connection' by label. At runtime, resolves to the auth connection for the current environment, falling back to the default environment. ArrayJsonSchemaProperty-Input: properties: property_kind: type: string enum: - array - object title: Property Kind default: array description: type: string title: Description default: '' dynamic_variable: type: string title: Dynamic Variable description: >- When set, the entire parameter is populated from this dynamic variable at runtime. Mutually exclusive with description (LLM-provided value), constant_value, and is_omitted. default: '' constant_value: anyOf: - items: {} type: array - type: 'null' title: Constant Value description: >- When set, the entire array uses this constant value at runtime. Mutually exclusive with description (LLM-provided array), dynamic_variable, and is_omitted. is_omitted: type: boolean title: Is Omitted description: >- If true, this parameter will be completely omitted from the request. Only valid for optional parameters. Mutually exclusive with description, dynamic_variable, and constant_value. default: false type: type: string const: array title: Type default: array items: oneOf: - $ref: '#/components/schemas/LiteralJsonSchemaProperty' - $ref: '#/components/schemas/ObjectJsonSchemaProperty-Input' - $ref: '#/components/schemas/ArrayJsonSchemaProperty-Input' title: Items description: Schema for array elements. default: type: string description: Array element is_system_provided: false dynamic_variable: '' allowed_values_dynamic_variable: '' constant_value: '' is_omitted: false additionalProperties: false type: object title: ArrayJsonSchemaProperty RequiredConstraints: properties: any_of: items: $ref: '#/components/schemas/RequiredConstraint' type: array title: Any Of all_of: items: $ref: '#/components/schemas/RequiredConstraint' type: array title: All Of type: object title: RequiredConstraints description: >- Wrapper for anyOf/allOf composition constraints scoped to required fields. AgentTransfer: properties: agent_id: anyOf: - type: string - type: 'null' title: Agent Id node_id: anyOf: - type: string - type: 'null' title: Node Id condition: type: string title: Condition delay_ms: type: integer title: Delay Ms default: 0 transfer_message: anyOf: - type: string - type: 'null' title: Transfer Message enable_transferred_agent_first_message: type: boolean title: Enable Transferred Agent First Message default: false is_workflow_node_transfer: type: boolean title: Is Workflow Node Transfer default: false preserve_client_tts_overrides: type: boolean title: Preserve Client Tts Overrides description: >- Defines whether TTS client overrides should be carried over to the transferred agent. default: false additionalProperties: false type: object required: - condition title: AgentTransfer PhoneNumberTransfer: properties: custom_sip_headers: items: oneOf: - $ref: '#/components/schemas/CustomSIPHeader' - $ref: '#/components/schemas/CustomSIPHeaderWithDynamicVariable' discriminator: propertyName: type mapping: dynamic: $ref: '#/components/schemas/CustomSIPHeaderWithDynamicVariable' static: $ref: '#/components/schemas/CustomSIPHeader' type: array maxItems: 20 title: Custom Sip Headers description: >- Custom SIP headers to include when transferring the call. Each header can be either a static value or a dynamic variable reference. transfer_destination: oneOf: - $ref: '#/components/schemas/PhoneNumberTransferDestination' - $ref: '#/components/schemas/SIPUriTransferDestination' - $ref: >- #/components/schemas/PhoneNumberDynamicVariableTransferDestination - $ref: '#/components/schemas/SIPUriDynamicVariableTransferDestination' title: Transfer Destination discriminator: propertyName: type mapping: phone: $ref: '#/components/schemas/PhoneNumberTransferDestination' phone_dynamic_variable: $ref: >- #/components/schemas/PhoneNumberDynamicVariableTransferDestination sip_uri: $ref: '#/components/schemas/SIPUriTransferDestination' sip_uri_dynamic_variable: $ref: '#/components/schemas/SIPUriDynamicVariableTransferDestination' transfer_type: $ref: '#/components/schemas/TransferTypeEnum' default: conference sip_refer_play_dialtone: type: boolean title: Sip Refer Play Dialtone description: >- When True, a ringing tone is played on the original call leg while a SIP REFER transfer completes. The tone is carried over RTP to the SIP peer executing the REFER, so disable this if the receiving system (e.g. an SBC or contact center) should not hear it. When disabled the caller hears silence until the transfer completes. SIP REFER transfers only. default: true uui: anyOf: - $ref: '#/components/schemas/UUITransferConfig' - type: 'null' description: >- User-to-User Information (RFC 7433) to attach to SIP REFER transfers. Carries call context such as CRM identifiers or escalation reason across the transfer boundary. post_dial_digits: anyOf: - oneOf: - $ref: '#/components/schemas/PostDialDigitsStatic' - $ref: '#/components/schemas/PostDialDigitsDynamicVariable' discriminator: propertyName: type mapping: dynamic: $ref: '#/components/schemas/PostDialDigitsDynamicVariable' static: $ref: '#/components/schemas/PostDialDigitsStatic' - type: 'null' title: Post Dial Digits description: >- DTMF digits to send after call connects (e.g., 'ww1234' for extension). Can be either a static value or a dynamic variable reference. Use 'w' for 0.5s pause. Only supported for Twilio transfers. condition: type: string title: Condition additionalProperties: false type: object required: - transfer_destination - condition title: PhoneNumberTransfer SearchStrategy: type: string enum: - cat - keyword - semantic - ls title: SearchStrategy ProcedureDraftRef: properties: procedure_id: type: string title: Procedure Id description: Procedure ID version_id: type: 'null' title: Version Id additionalProperties: false type: object required: - procedure_id title: ProcedureDraftRef ResponseFilterMode: type: string enum: - all - allow - hide_all title: ResponseFilterMode description: >- Controls how tool responses are filtered before being visible to the agent. default: all LLMLiteralJsonSchemaProperty: properties: type: anyOf: - type: string enum: - boolean - string - integer - number - items: type: string type: array maxItems: 2 minItems: 2 title: Type description: type: string minLength: 0 title: Description enum: anyOf: - items: type: string type: array - type: 'null' title: Enum description: List of allowed string values for string type parameters type: object required: - type - description title: LLMLiteralJsonSchemaProperty WebhookToolConfig-Output: properties: type: type: string const: webhook title: Type description: The type of tool default: webhook name: type: string minLength: 0 pattern: ^[a-zA-Z0-9_-]{1,64}$ title: Name description: type: string minLength: 0 title: Description description: Description of when the tool should be used and what it does. response_timeout_secs: type: integer maximum: 300 minimum: 5 title: Response Timeout Secs description: >- The maximum time in seconds to wait for the tool call to complete. Must be between 5 and 300 seconds (inclusive). default: 20 interruption_mode: $ref: '#/components/schemas/ToolInterruptionMode' description: >- Controls whether the user can interrupt the agent around this tool call. 'allow' (default) lets the user interrupt at any time, 'disable_during_tool' suppresses interruptions only while the tool is running, 'disable_during_tool_and_turn' suppresses interruptions while the tool runs and for the agent response that follows it. default: allow pre_tool_speech: $ref: '#/components/schemas/PreToolSpeechMode' description: >- Controls whether the agent speaks before this tool is called. 'auto' (default) decides based on recent tool latency, 'force' always asks the agent to speak, 'off' fully opts out regardless of latency. default: auto assignments: items: $ref: '#/components/schemas/DynamicVariableAssignment' type: array title: Assignments description: >- Configuration for extracting values from tool responses and assigning them to dynamic variables tool_call_sound: anyOf: - $ref: '#/components/schemas/ToolCallSoundType' - type: 'null' description: >- Predefined tool call sound type to play during tool execution. If not specified, no tool call sound will be played. x-convai-client-override: true tool_call_sound_behavior: $ref: '#/components/schemas/ToolCallSoundBehavior' description: >- Determines when the tool call sound should play. 'auto' only plays when there's pre-tool speech, 'always' plays for every tool call. default: auto tool_error_handling_mode: $ref: '#/components/schemas/ToolErrorHandlingMode' description: >- Controls how tool errors are processed before being shared with the agent. 'auto' determines handling based on tool type (summarized for native integrations, hide for others), 'summarized' sends an LLM-generated summary, 'passthrough' sends the raw error, 'hide' does not share the error with the agent. default: auto dynamic_variables: $ref: '#/components/schemas/DynamicVariablesConfig-Output' description: Configuration for dynamic variables execution_mode: $ref: '#/components/schemas/ToolExecutionMode' description: >- Determines when and how the tool executes: 'immediate' executes the tool right away when requested by the LLM, 'post_tool_speech' waits for the agent to finish speaking before executing, 'async' runs the tool in the background without blocking - best for long-running operations. default: immediate api_schema: $ref: '#/components/schemas/WebhookToolApiSchemaConfig-Output' description: >- The schema for the outgoing webhook, including parameters and URL specification type: object required: - name - description - api_schema title: WebhookToolConfig description: A webhook tool is a tool that calls an external webhook from our server example: response_timeout_secs: 20 type: webhook ClientToolConfig-Output: properties: type: type: string const: client title: Type description: The type of tool default: client name: type: string minLength: 0 pattern: ^[a-zA-Z0-9_-]{1,64}$ title: Name description: type: string minLength: 0 title: Description description: Description of when the tool should be used and what it does. response_timeout_secs: type: integer maximum: 120 minimum: 1 title: Response Timeout Secs description: >- The maximum time in seconds to wait for the tool call to complete. Must be between 1 and 120 seconds (inclusive). default: 20 interruption_mode: $ref: '#/components/schemas/ToolInterruptionMode' description: >- Controls whether the user can interrupt the agent around this tool call. 'allow' (default) lets the user interrupt at any time, 'disable_during_tool' suppresses interruptions only while the tool is running, 'disable_during_tool_and_turn' suppresses interruptions while the tool runs and for the agent response that follows it. default: allow pre_tool_speech: $ref: '#/components/schemas/PreToolSpeechMode' description: >- Controls whether the agent speaks before this tool is called. 'auto' (default) decides based on recent tool latency, 'force' always asks the agent to speak, 'off' fully opts out regardless of latency. default: auto assignments: items: $ref: '#/components/schemas/DynamicVariableAssignment' type: array title: Assignments description: >- Configuration for extracting values from tool responses and assigning them to dynamic variables tool_call_sound: anyOf: - $ref: '#/components/schemas/ToolCallSoundType' - type: 'null' description: >- Predefined tool call sound type to play during tool execution. If not specified, no tool call sound will be played. x-convai-client-override: true tool_call_sound_behavior: $ref: '#/components/schemas/ToolCallSoundBehavior' description: >- Determines when the tool call sound should play. 'auto' only plays when there's pre-tool speech, 'always' plays for every tool call. default: auto tool_error_handling_mode: $ref: '#/components/schemas/ToolErrorHandlingMode' description: >- Controls how tool errors are processed before being shared with the agent. 'auto' determines handling based on tool type (summarized for native integrations, hide for others), 'summarized' sends an LLM-generated summary, 'passthrough' sends the raw error, 'hide' does not share the error with the agent. default: auto parameters: anyOf: - $ref: '#/components/schemas/ObjectJsonSchemaProperty-Output' - type: 'null' description: Schema for any parameters to pass to the client expects_response: type: boolean title: Expects Response description: >- If true, calling this tool should block the conversation until the client responds with some response which is passed to the llm. If false then we will continue the conversation without waiting for the client to respond, this is useful to show content to a user but not block the conversation default: false dynamic_variables: $ref: '#/components/schemas/DynamicVariablesConfig-Output' description: Configuration for dynamic variables execution_mode: $ref: '#/components/schemas/ToolExecutionMode' description: >- Determines when and how the tool executes: 'immediate' executes the tool right away when requested by the LLM, 'post_tool_speech' waits for the agent to finish speaking before executing, 'async' runs the tool in the background without blocking - best for long-running operations. default: immediate type: object required: - name - description title: ClientToolConfig description: >- A client tool is one that sends an event to the user's client to trigger something client side example: expects_response: false type: client MCPToolConfig-Output: properties: type: type: string const: mcp title: Type default: mcp name: type: string minLength: 0 pattern: ^[a-zA-Z0-9_-]{1,64}$ title: Name description: type: string minLength: 0 title: Description description: Description of when the tool should be used and what it does. response_timeout_secs: type: integer maximum: 300 minimum: 5 title: Response Timeout Secs description: >- The maximum time in seconds to wait for the MCP tool call to complete. Must be between 5 and 300 seconds (inclusive). default: 30 interruption_mode: $ref: '#/components/schemas/ToolInterruptionMode' description: >- Controls whether the user can interrupt the agent around this tool call. 'allow' (default) lets the user interrupt at any time, 'disable_during_tool' suppresses interruptions only while the tool is running, 'disable_during_tool_and_turn' suppresses interruptions while the tool runs and for the agent response that follows it. default: allow pre_tool_speech: $ref: '#/components/schemas/PreToolSpeechMode' description: >- Controls whether the agent speaks before this tool is called. 'auto' (default) decides based on recent tool latency, 'force' always asks the agent to speak, 'off' fully opts out regardless of latency. default: auto assignments: items: $ref: '#/components/schemas/DynamicVariableAssignment' type: array title: Assignments description: >- Configuration for extracting values from tool responses and assigning them to dynamic variables tool_call_sound: anyOf: - $ref: '#/components/schemas/ToolCallSoundType' - type: 'null' description: >- Predefined tool call sound type to play during tool execution. If not specified, no tool call sound will be played. x-convai-client-override: true tool_call_sound_behavior: $ref: '#/components/schemas/ToolCallSoundBehavior' description: >- Determines when the tool call sound should play. 'auto' only plays when there's pre-tool speech, 'always' plays for every tool call. default: auto tool_error_handling_mode: $ref: '#/components/schemas/ToolErrorHandlingMode' description: >- Controls how tool errors are processed before being shared with the agent. 'auto' determines handling based on tool type (summarized for native integrations, hide for others), 'summarized' sends an LLM-generated summary, 'passthrough' sends the raw error, 'hide' does not share the error with the agent. default: auto integration_type: $ref: '#/components/schemas/IntegrationType' description: The type of MCP tool parameters: anyOf: - $ref: '#/components/schemas/ObjectJsonSchemaProperty-Output' - type: 'null' description: Schema for any parameters the LLM needs to provide to the MCP tool. approval_policy: $ref: '#/components/schemas/MCPApprovalPolicy' description: The approval policy for the MCP tool default: require_approval_all mcp_tool_name: type: string title: Mcp Tool Name description: The name of the MCP tool to call mcp_tool_description: type: string title: Mcp Tool Description description: The description of the MCP tool to call mcp_server_id: type: string title: Mcp Server Id description: The id of the MCP server to call mcp_server_name: type: string title: Mcp Server Name description: The name of the MCP server to call mcp_input_schema: anyOf: - additionalProperties: true type: object - type: 'null' title: Mcp Input Schema description: Original inputSchema dict for consistent hashing execution_mode: $ref: '#/components/schemas/ToolExecutionMode' description: >- Determines when and how the tool executes: 'immediate' executes the tool right away when requested by the LLM, 'post_tool_speech' waits for the agent to finish speaking before executing, 'async' runs the tool in the background without blocking - best for long-running operations. default: immediate input_overrides: anyOf: - additionalProperties: oneOf: - $ref: '#/components/schemas/ConstantSchemaOverride' - $ref: '#/components/schemas/DynamicVariableSchemaOverride' - $ref: '#/components/schemas/LLMSchemaOverride' - $ref: '#/components/schemas/OmitSchemaOverride' discriminator: propertyName: source mapping: constant: $ref: '#/components/schemas/ConstantSchemaOverride' dynamic_variable: $ref: '#/components/schemas/DynamicVariableSchemaOverride' llm: $ref: '#/components/schemas/LLMSchemaOverride' omit: $ref: '#/components/schemas/OmitSchemaOverride' type: object - type: 'null' title: Input Overrides description: Input parameter overrides for this tool type: object required: - name - description - integration_type - mcp_tool_name - mcp_tool_description - mcp_server_id - mcp_server_name title: MCPToolConfig description: An MCP tool configuration that can be used to call MCP servers. x-fern-ignore: true ApiIntegrationWebhookToolConfig-Output: properties: type: type: string const: api_integration_webhook title: Type default: api_integration_webhook name: type: string minLength: 0 pattern: ^[a-zA-Z0-9_-]{1,64}$ title: Name description: type: string minLength: 0 title: Description description: Description of when the tool should be used and what it does. response_timeout_secs: type: integer maximum: 300 minimum: 5 title: Response Timeout Secs description: >- The maximum time in seconds to wait for the tool call to complete. Must be between 5 and 300 seconds (inclusive). default: 20 interruption_mode: $ref: '#/components/schemas/ToolInterruptionMode' description: >- Controls whether the user can interrupt the agent around this tool call. 'allow' (default) lets the user interrupt at any time, 'disable_during_tool' suppresses interruptions only while the tool is running, 'disable_during_tool_and_turn' suppresses interruptions while the tool runs and for the agent response that follows it. default: allow pre_tool_speech: $ref: '#/components/schemas/PreToolSpeechMode' description: >- Controls whether the agent speaks before this tool is called. 'auto' (default) decides based on recent tool latency, 'force' always asks the agent to speak, 'off' fully opts out regardless of latency. default: auto assignments: items: $ref: '#/components/schemas/DynamicVariableAssignment' type: array title: Assignments description: >- Configuration for extracting values from tool responses and assigning them to dynamic variables tool_call_sound: anyOf: - $ref: '#/components/schemas/ToolCallSoundType' - type: 'null' description: >- Predefined tool call sound type to play during tool execution. If not specified, no tool call sound will be played. x-convai-client-override: true tool_call_sound_behavior: $ref: '#/components/schemas/ToolCallSoundBehavior' description: >- Determines when the tool call sound should play. 'auto' only plays when there's pre-tool speech, 'always' plays for every tool call. default: auto tool_error_handling_mode: $ref: '#/components/schemas/ToolErrorHandlingMode' description: >- Controls how tool errors are processed before being shared with the agent. 'auto' determines handling based on tool type (summarized for native integrations, hide for others), 'summarized' sends an LLM-generated summary, 'passthrough' sends the raw error, 'hide' does not share the error with the agent. default: auto dynamic_variables: $ref: '#/components/schemas/DynamicVariablesConfig-Output' description: Configuration for dynamic variables execution_mode: $ref: '#/components/schemas/ToolExecutionMode' description: >- Determines when and how the tool executes: 'immediate' executes the tool right away when requested by the LLM, 'post_tool_speech' waits for the agent to finish speaking before executing, 'async' runs the tool in the background without blocking - best for long-running operations. default: immediate tool_version: type: string title: Tool Version description: The version of the API integration tool default: 1.0.0 api_integration_id: type: string title: Api Integration Id api_integration_connection_id: type: string title: Api Integration Connection Id api_schema_overrides: anyOf: - $ref: '#/components/schemas/ApiIntegrationWebhookOverrides' - type: 'null' title: Api Schema Overrides description: User overrides applied on top of the base api_schema type: object required: - type - name - description - response_timeout_secs - interruption_mode - pre_tool_speech - assignments - tool_call_sound - tool_call_sound_behavior - tool_error_handling_mode - dynamic_variables - execution_mode - tool_version - api_integration_id - api_integration_connection_id - api_schema_overrides title: ApiIntegrationWebhookToolConfig RequiredConstraint: properties: required: items: type: string type: array title: Required type: object required: - required title: RequiredConstraint description: A set of fields that must all be present to satisfy this constraint. WebhookToolApiSchemaConfig-Output: properties: request_headers: additionalProperties: anyOf: - type: string - $ref: '#/components/schemas/ConvAISecretLocator' - $ref: '#/components/schemas/ConvAIDynamicVariable' - $ref: '#/components/schemas/ConvAIEnvVarLocator' type: object title: Request Headers description: Headers that should be included in the request url: type: string title: Url description: >- The URL that the webhook will be sent to. May include path parameters, e.g. https://example.com/agents/{agent_id} method: type: string enum: - GET - POST - PUT - PATCH - DELETE title: Method description: The HTTP method to use for the webhook default: GET path_params_schema: additionalProperties: $ref: '#/components/schemas/LiteralJsonSchemaProperty' type: object title: Path Params Schema description: >- Schema for path parameters, if any. The keys should match the placeholders in the URL. query_params_schema: anyOf: - $ref: '#/components/schemas/QueryParamsJsonSchema' - type: 'null' description: >- Schema for any query params, if any. These will be added to end of the URL as query params. Note: properties in a query param must all be literal types request_body_schema: anyOf: - $ref: '#/components/schemas/ObjectJsonSchemaProperty-Output' - type: 'null' description: >- Schema for the body parameters, if any. Used for POST/PATCH/PUT requests. The schema should be an object which will be sent as the json body response_body_schema: anyOf: - $ref: '#/components/schemas/ObjectJsonSchemaProperty-Output' - type: 'null' description: >- Schema describing the expected response body structure. For documentation only; not surfaced to the LLM. response_filter: anyOf: - $ref: '#/components/schemas/ResponseFilter' - type: 'null' description: >- Optional allow-list filter applied to the response before the LLM sees it, so large responses don't pollute the context. Defaults to the full response. content_type: type: string enum: - application/json - application/x-www-form-urlencoded title: Content Type description: >- Content type for the request body. Only applies to POST/PUT/PATCH requests. default: application/json auth_resolved_params: items: type: string type: array uniqueItems: true title: Auth Resolved Params description: >- URL placeholders resolved from the auth connection (e.g. secrets injected via UrlSecretAuthConnection) rather than from path_params_schema. auth_connection: anyOf: - $ref: '#/components/schemas/AuthConnectionLocator' - $ref: '#/components/schemas/EnvironmentAuthConnectionLocator' - type: 'null' title: Auth Connection description: Optional auth connection to use for authentication with this webhook type: object required: - url title: WebhookToolApiSchemaConfig example: method: GET path_params_schema: agent_id: type: string query_params_schema: param1: type: string request_body_schema: param1: type: string request_headers: Authorization: Bearer {api_key} url: https://example.com/agents/{agent_id} ObjectJsonSchemaProperty-Output: properties: description: type: string title: Description default: '' dynamic_variable: type: string title: Dynamic Variable description: >- When set, the entire parameter is populated from this dynamic variable at runtime. Mutually exclusive with description (LLM-provided value), constant_value, and is_omitted. default: '' constant_value: anyOf: - additionalProperties: true type: object - type: 'null' title: Constant Value description: >- When set, the entire object uses this constant JSON value at runtime. Mutually exclusive with description (LLM-provided object), dynamic_variable, and is_omitted. is_omitted: type: boolean title: Is Omitted description: >- If true, this parameter will be completely omitted from the request. Only valid for optional parameters. Mutually exclusive with description, dynamic_variable, and constant_value. default: false type: type: string const: object title: Type default: object required: items: type: string type: array title: Required properties: additionalProperties: oneOf: - $ref: '#/components/schemas/LiteralJsonSchemaProperty' - $ref: '#/components/schemas/ObjectJsonSchemaProperty-Output' - $ref: '#/components/schemas/ArrayJsonSchemaProperty-Output' type: object title: Properties required_constraints: anyOf: - $ref: '#/components/schemas/RequiredConstraints' - type: 'null' additionalProperties: false type: object title: ObjectJsonSchemaProperty ArrayJsonSchemaProperty-Output: properties: description: type: string title: Description default: '' dynamic_variable: type: string title: Dynamic Variable description: >- When set, the entire parameter is populated from this dynamic variable at runtime. Mutually exclusive with description (LLM-provided value), constant_value, and is_omitted. default: '' constant_value: anyOf: - items: {} type: array - type: 'null' title: Constant Value description: >- When set, the entire array uses this constant value at runtime. Mutually exclusive with description (LLM-provided array), dynamic_variable, and is_omitted. is_omitted: type: boolean title: Is Omitted description: >- If true, this parameter will be completely omitted from the request. Only valid for optional parameters. Mutually exclusive with description, dynamic_variable, and constant_value. default: false type: type: string const: array title: Type default: array items: oneOf: - $ref: '#/components/schemas/LiteralJsonSchemaProperty' - $ref: '#/components/schemas/ObjectJsonSchemaProperty-Output' - $ref: '#/components/schemas/ArrayJsonSchemaProperty-Output' title: Items description: Schema for array elements. default: type: string description: Array element is_system_provided: false dynamic_variable: '' allowed_values_dynamic_variable: '' constant_value: '' is_omitted: false additionalProperties: false type: object title: ArrayJsonSchemaProperty ````