> ## Documentation Index > Fetch the complete documentation index at: https://docs.syllable.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create Prompt > Create a new prompt ## OpenAPI ````yaml https://spec.speakeasy.com/syllable/syllable/syllable-sdk-oas-with-code-samples post /api/v1/prompts/ openapi: 3.1.0 info: title: SyllableSDK description: > # Syllable Platform SDK Syllable SDK gives you the power of awesome AI agentry. 🚀 ## Overview The Syllable SDK provides a comprehensive set of tools and APIs to integrate powerful AI capabilities into your communication applications. Whether you're building phone agents, chatbots, virtual assistants, or any other AI-driven solutions, Syllable SDK has got you covered. ## Features - **Agent Configuration**: Create and manage agents that can interact with users across various channels. - **Channel Management**: Configure channels like SMS, web chat, and more to connect agents with users. - **Custom Messages**: Set up custom messages that agents can deliver as greetings or responses. - **Conversations**: Track and manage conversations between users and agents, including session management. - **Tools and Workflows**: Leverage tools and workflows to enhance agent capabilities, such as data processing and API calls. - **Data Sources**: Integrate data sources to provide agents with additional context and information. - **Insights and Analytics**: Analyze conversations and sessions to gain insights into user interactions. - **Permissions and Security**: Manage permissions to control access to various features and functionalities. - **Language Support**: Define language groups to enable multilingual support for agents. - **Outbound Campaigns**: Create and manage outbound communication campaigns to reach users effectively. - **Session Labels**: Label sessions with evaluations of quality and descriptions of issues encountered. - **Incident Management**: Track and manage incidents related to agent interactions. version: 0.0.3 servers: - url: https://api.syllable.cloud description: API server security: [] tags: - name: agents description: >- Operations related to agent configuration. When a user interacts with the Syllable system, they do so by communicating with an agent. An agent is linked to a prompt, a custom message, and one or more channel targets to define its behavior and capabilities. For more information, see [Console docs](https://docs.syllable.ai/workspaces/Agents). - name: agents.test description: >- Operations for testing agents with live text. These endpoints allow sending messages to an agent and receiving its responses. - name: channels description: >- Operations related to channel configuration. A channel is an organization-level point of communication, like a phone number or a web chat. A channel can be associated with an agent by creating a channel target linking them. - name: channels.twilio description: Operations related to Twilio channel configuration. - name: channels.twilio.numbers description: >- Operations related to setting up phone numbers in Twilio for use in channels. - name: channels.targets description: >- Operations related to channel target configuration. A channel target links a channel to an agent, allowing users to communicate with the agent through that channel. For more information, see [Console docs](https://docs.syllable.ai/Resources/Channels). - name: conversations description: >- Operations related to conversations. A conversation is a record of messages between a user and an agent, and is composed of one or more sessions. - name: custom_messages description: >- Operations related to custom message configuration. A custom message is a pre-configured message delivered by an agent as a greeting at the beginning of a conversation. Multiple agents can use the same custom mesasage. A custom message has one or more rules defined, which allow for different messages to be dynamically selected and delivered at runtime based on the current time and either date or day of the week. For more information, see [Console docs](https://docs.syllable.ai/Resources/Messages). - name: dashboards description: >- Operations related to dashboards. Currently the API/SDK only supports fetching basic information about dashboards. - name: data_sources description: >- Operations related to data sources. A data source is a blob of text that can be made available to an agent's general info tools to provide more context to the agent when generating its responses. For more information, see [Console docs](https://docs.syllable.ai/Resources/DataSources). - name: directory description: Operations related to directory - name: events description: >- Operations related to events. An event represents a specific occurrence during a session. Currently the API/SDK only supports fetching logged events. - name: incidents description: Operations related to incidents. - name: insights description: >- Operations related to insights results. An insight is a tool that processes conversation data to extract information and generate reports. - name: insights.folders description: >- Operations related to insights upload folders. An insight folder is used to upload call recordings for insight workflow analysis. - name: insights.tools description: >- Operations related to insights tool configurationss. An insight is a tool that processes conversation data to extract information and generate reports. - name: insights.workflows description: >- Operations related to insights workflows. An workflow is series of tool invocations that processes conversation data to extract information and generate reports. - name: language_groups description: >- Operations related to language groups. A language group is a collection of language, voice, and DTMF configuration that can be linked to an agent to define the languages and voices it supports. For more information, see [Console docs](https://docs.syllable.ai/Resources/LanguageGroups). - name: organizations description: Operations related to organizations. - name: outbound.campaigns description: Operations related to outbound message campaigns - name: outbound.batches description: Operations related to outbound campaign batches - name: permissions description: >- Operations related to permissions. A permission is a specific capability or access level granted to a user within the Syllable system. Permissions are used to control access to various features and functionalities. - name: prompts description: >- Operations related to prompts. A prompt defines the behavior of an agent by delivering instructions to the LLM about how the agent should behave. A prompt can be linked to one or more agents. A prompt can also be linked to tools to allow an agent using the prompt to use them. For more information, see [Console docs](https://docs.syllable.ai/Resources/Prompts). - name: roles description: >- Operations related to roles. A role is a collection of permissions that can be assigned to users to control their access to various features within the Syllable system. - name: services description: >- Operations related to service configuration. A service is a collection of tools. You can specify an authentication method and values on a service, and any linked tools will use that auth information to generate headers for HTTP calls. - name: sessions description: >- Operations related to sessions. A session is a building block of a conversation. For more information, see [Console docs](https://docs.syllable.ai/workspaces/Sessions). - name: session_labels description: >- Operations related to labeling sessions with evaluations of quality and descriptions of issues the user encountered or other details. For more information, see [Console docs](https://docs.syllable.ai/workspaces/Sessions). - name: tools description: >- Operations related to tool configuration. A tool is a function that an agent can call to perform actions like accessing databases, making API calls, or processing data. For an agent to have access to a tool, the prompt associated with that agent should be linked to the tool and include instructions to use it. For more information, see [Console docs](https://docs.syllable.ai/Resources/Tools). paths: /api/v1/prompts/: post: tags: - prompts summary: Create Prompt description: Create a new prompt operationId: prompts_create requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/PromptCreateRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/PromptResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - APIKeyHeader: [] x-codeSamples: - lang: typescript label: Typescript (SDK) source: |- import { SyllableSDK } from "syllable-sdk"; const syllableSDK = new SyllableSDK({ apiKeyHeader: process.env["SYLLABLESDK_API_KEY_HEADER"] ?? "", }); async function run() { const result = await syllableSDK.prompts.create({ name: "Weather Agent Prompt", description: "Prompt for a weather agent.", type: "prompt_v1", context: "You are a weather agent. Answer the user's questions about weather and nothing else.", tools: [], llmConfig: { version: "2024-05-13", apiVersion: "2024-06-01", temperature: 1, seed: 123, }, sessionEndToolId: 1, editComments: "Updated prompt text to include requirement to not answer questions that aren't about weather.", }); console.log(result); } run(); - lang: python label: Python (SDK) source: |- import os from syllable_sdk import SyllableSDK with SyllableSDK( api_key_header=os.getenv("SYLLABLESDK_API_KEY_HEADER", ""), ) as ss_client: res = ss_client.prompts.create(request={ "name": "Weather Agent Prompt", "description": "Prompt for a weather agent.", "type": "prompt_v1", "context": "You are a weather agent. Answer the user's questions about weather and nothing else.", "tools": [], "llm_config": { "version": "2024-05-13", "api_version": "2024-06-01", "temperature": 1, "seed": 123, }, "session_end_tool_id": 1, "edit_comments": "Updated prompt text to include requirement to not answer questions that aren't about weather.", }) # Handle response print(res) components: schemas: PromptCreateRequest: properties: name: type: string title: Name description: The prompt name examples: - Weather Agent Prompt description: anyOf: - type: string - type: 'null' title: Description description: The description of the prompt examples: - Prompt for a weather agent. type: type: string title: Type description: The type of the prompt examples: - prompt_v1 context: anyOf: - type: string - type: 'null' title: Context description: >- The prompt text that will be sent to the LLM at the beginning of the conversation examples: - >- You are a weather agent. Answer the user's questions about weather and nothing else. tools: items: type: string type: array title: Tools description: Names of tools to which the prompt has access default: [] examples: - [] llm_config: $ref: '#/components/schemas/PromptLlmConfig' description: The configuration for the LLM that the prompt uses examples: - model: gpt-4o provider: openai version: '2024-08-06' session_end_enabled: type: boolean title: Session End Enabled description: Whether session end functionality is enabled for this prompt default: false examples: - false session_end_tool_id: anyOf: - type: integer - type: 'null' title: Session End Tool Id description: ID of the optional session end tool associated with the prompt examples: - 1 edit_comments: anyOf: - type: string - type: 'null' title: Edit Comments description: The comments for the most recent edit to the prompt examples: - >- Updated prompt text to include requirement to not answer questions that aren't about weather. include_default_tools: type: boolean title: Include Default Tools description: >- Whether to include the default tools (`hangup`) in the list of tools for the prompt (also includes set_current_language if any of the agents assigned to the prompt have Dynamic Language Switching enabled). If you disable this during creation, you might want to disable it during updates as well; otherwise the default tools will be added when updating the prompt. default: true examples: - true type: object required: - name - type - llm_config title: PromptCreateRequest description: Request model to create a prompt. PromptResponse: properties: name: type: string title: Name description: The prompt name examples: - Weather Agent Prompt description: anyOf: - type: string - type: 'null' title: Description description: The description of the prompt examples: - Prompt for a weather agent. type: type: string title: Type description: The type of the prompt examples: - prompt_v1 context: anyOf: - type: string - type: 'null' title: Context description: >- The prompt text that will be sent to the LLM at the beginning of the conversation examples: - >- You are a weather agent. Answer the user's questions about weather and nothing else. tools: items: type: string type: array title: Tools description: >- Names of the tools to which the prompt has access (DEPRECATED - use information from full tools field instead) default: [] deprecated: true examples: - hangup - summary llm_config: $ref: '#/components/schemas/PromptLlmConfig' description: The configuration for the LLM that the prompt uses examples: - model: gpt-4o provider: openai version: '2024-08-06' session_end_enabled: type: boolean title: Session End Enabled description: Whether session end functionality is enabled for this prompt default: false examples: - false session_end_tool_id: anyOf: - type: integer - type: 'null' title: Session End Tool Id description: ID of the optional session end tool associated with the prompt examples: - 1 edit_comments: anyOf: - type: string - type: 'null' title: Edit Comments description: The comments for the most recent edit to the prompt examples: - >- Updated prompt text to include requirement to not answer questions that aren't about weather. id: type: integer title: Id description: The internal ID of the prompt examples: - 1 last_updated: anyOf: - type: string - type: 'null' title: Last Updated description: The last updated date of the prompt examples: - '2024-01-01T12:00:00Z' last_updated_by: anyOf: - type: string - type: 'null' title: Last Updated By description: Email address of the user who most recently updated the prompt examples: - user@email.com session_end_tool: anyOf: - $ref: '#/components/schemas/DaoToolResponse' - type: 'null' description: The session end tool associated with the prompt examples: [] agent_count: anyOf: - type: integer - type: 'null' title: Agent Count description: The number of agents using the prompt examples: - 5 version_number: anyOf: - type: integer - type: 'null' title: Version Number description: The version number of the current version of the prompt examples: - 1 tools_full: anyOf: - items: $ref: '#/components/schemas/ToolResponse' type: array - type: 'null' title: Tools Full description: Full definitions of tools to which the prompt has access examples: [] type: object required: - name - type - llm_config - id - last_updated title: PromptResponse description: >- Response model for prompt operations. A prompt defines the behavior of an agent by delivering instructions to the LLM about how the agent should behave. A prompt can be linked to one or more agents. A prompt can also be linked to tools to allow an agent using it to use those tools. For more information, see [Console docs](https://docs.syllable.ai/Resources/Prompts). HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError PromptLlmConfig: properties: provider: $ref: '#/components/schemas/PromptLlmProvider' description: Provider of the LLM model. default: azure_openai examples: - anthropic - azure_openai - google - openai model: type: string title: Model description: >- Name of the model. Must match the deployment name in Azure AI Studio. default: gpt-4o examples: - gpt-4o version: anyOf: - type: string - type: 'null' title: Version description: Optional model version. examples: - '2024-05-13' api_version: anyOf: - type: string - type: 'null' title: Api Version description: Version of the provider's API. examples: - '2024-06-01' temperature: anyOf: - type: number - type: 'null' title: Temperature description: >- Temperature parameter for the model. Determines randomness of responses - higher is more random, lower is more focused. Must be between 0.0 and 2.0, inclusive. examples: - 1 seed: anyOf: - type: integer - type: 'null' title: Seed description: >- Controls the reproducibility of the job. The LLM will give the same or similar responses given the same inputs in multiple conversations with the same seed. examples: - 123 type: object title: PromptLlmConfig description: LLM configuration for a prompt. DaoToolResponse: properties: name: type: string title: Name description: The name of the tool examples: - Weather Fetcher definition: $ref: '#/components/schemas/ToolDefinition' description: The definition of the tool examples: - endpoint: argument_location: query method: get url: https://api.open-meteo.com/v1/forecast static_parameters: - default: fahrenheit description: >- Whether the temperature information should be fetched in Celsius or Fahrenheit name: temperature_unit required: false type: string tool: function: description: Get the weather for a city name: get_weather parameters: properties: latitude: description: Latitude of the city type: number longitude: description: Longitude of the city type: number current: default: >- temperature_2m,relative_humidity_2m,precipitation,rain,showers description: >- Information to retrieve from the open-meteo API, comma-separated type: string required: - latitude - longitude - current type: object type: function type: endpoint service_id: type: integer title: Service Id description: Internal ID of the service to which the tool belongs examples: - 1 id: type: integer title: Id description: The internal ID of the tool examples: - 1 last_updated_comments: anyOf: - type: string - type: 'null' title: Last Updated Comments description: Comments for the most recent edit to the tool. examples: - Updated to use new API endpoint service_name: anyOf: - type: string - type: 'null' title: Service Name description: The name of the service to which the tool belongs prompts_info: anyOf: - items: $ref: '#/components/schemas/ToolPromptInfo' type: array - type: 'null' title: Prompts Info description: IDs and names of the prompts linked to the tool agents_info: anyOf: - items: $ref: '#/components/schemas/ToolAgentInfo' type: array - type: 'null' title: Agents Info description: IDs and names of the agents linked to the tool via a prompt last_updated: type: string format: date-time title: Last Updated description: The timestamp of the most recent update to the tool last_updated_by: type: string title: Last Updated By description: The email of the user who last updated the tool examples: - user@email.com version_number: type: integer title: Version Number description: >- Highest tools_history snapshot version for this tool; the tools row defaults to 1. examples: - 1 type: object required: - name - definition - service_id - id - last_updated - last_updated_by - version_number title: DaoToolResponse ToolResponse: properties: name: type: string title: Name description: The name of the tool examples: - Weather Fetcher definition: $ref: '#/components/schemas/ToolDefinition' description: The definition of the tool examples: - endpoint: argument_location: query method: get url: https://api.open-meteo.com/v1/forecast static_parameters: - default: fahrenheit description: >- Whether the temperature information should be fetched in Celsius or Fahrenheit name: temperature_unit required: false type: string tool: function: description: Get the weather for a city name: get_weather parameters: properties: latitude: description: Latitude of the city type: number longitude: description: Longitude of the city type: number current: default: >- temperature_2m,relative_humidity_2m,precipitation,rain,showers description: >- Information to retrieve from the open-meteo API, comma-separated type: string required: - latitude - longitude - current type: object type: function type: endpoint service_id: type: integer title: Service Id description: Internal ID of the service to which the tool belongs examples: - 1 id: type: integer title: Id description: The internal ID of the tool examples: - 1 last_updated_comments: anyOf: - type: string - type: 'null' title: Last Updated Comments description: Comments for the most recent edit to the tool. examples: - Updated to use new API endpoint service_name: anyOf: - type: string - type: 'null' title: Service Name description: The name of the service to which the tool belongs prompts_info: anyOf: - items: $ref: '#/components/schemas/ToolPromptInfo' type: array - type: 'null' title: Prompts Info description: IDs and names of the prompts linked to the tool agents_info: anyOf: - items: $ref: '#/components/schemas/ToolAgentInfo' type: array - type: 'null' title: Agents Info description: IDs and names of the agents linked to the tool via a prompt last_updated: type: string format: date-time title: Last Updated description: The timestamp of the most recent update to the tool last_updated_by: type: string title: Last Updated By description: The email of the user who last updated the tool examples: - user@email.com version_number: type: integer title: Version Number description: >- Highest tools_history snapshot version for this tool; the tools row defaults to 1. examples: - 1 validation_issues: anyOf: - items: $ref: '#/components/schemas/ValidationIssue' type: array - type: 'null' title: Validation Issues description: >- Validation issues found in the tool definition. Warnings and infos are informational; errors block the save. type: object required: - name - definition - service_id - id - last_updated - last_updated_by - version_number title: ToolResponse description: >- Response model for tool operations. A tool is a function that an agent can call to perform actions like accessing databases, making API calls, or processing data. For an agent to have access to a tool, the prompt associated with that agent should be linked to the tool and include instructions to use it. For more information, see [Console docs](https://docs.syllable.ai/Resources/Tools). 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 PromptLlmProvider: type: string enum: - anthropic - azure_openai - google - openai title: PromptLlmProvider description: LLM API provider. ToolDefinition: properties: type: anyOf: - type: string enum: - action - endpoint - context - log - type: 'null' title: Type description: The action to take when the LLM calls the tool. examples: - endpoint tool: $ref: '#/components/schemas/InternalTool' description: The tool definition to be used by the OpenAI API. examples: [] endpoint: anyOf: - $ref: '#/components/schemas/ToolHttpEndpoint' - type: 'null' description: The configuration for an HTTP API call. examples: [] context: anyOf: - $ref: '#/components/schemas/Context' - type: 'null' description: The configuration for a context tool. defaults: anyOf: - {} - additionalProperties: $ref: '#/components/schemas/ToolParameterDefault' type: object - type: 'null' title: Defaults description: The default values for the parameters of the function/tool call. examples: [] static_parameters: anyOf: - items: $ref: '#/components/schemas/StaticToolParameter' type: array - type: 'null' title: Static Parameters description: >- Parameters for the tool whose values should be set at config time (i.e., not provided by the LLM). examples: - - default: fahrenheit description: >- Whether the temperature information should be fetched in Celsius or Fahrenheit name: temperature_unit required: false type: string result: anyOf: - {} - type: 'null' title: Result description: The optional result of the tool call. examples: [] options: anyOf: - $ref: '#/components/schemas/ToolOptions' - type: 'null' description: >- The options for the tool. Ie allows to propagate the tool result to the caller via propagate_tool_result flag. examples: [] type: object required: - tool title: ToolDefinition description: >- A tool that can be called from an LLM during the conversation. See https://docs.syllable.ai/Resources/Tools. ToolPromptInfo: properties: id: type: integer title: Id description: The ID of the prompt examples: - 1 name: type: string title: Name description: The name of the prompt examples: - Test Prompt type: object required: - id - name title: ToolPromptInfo description: Information about a prompt linked to a tool. ToolAgentInfo: properties: id: type: integer title: Id description: The internal ID of the agent examples: - 1 name: type: string title: Name description: The name of the agent examples: - Test Agent type: object required: - id - name title: ToolAgentInfo description: Information about an agent linked to a tool via a prompt. ValidationIssue: properties: id: type: string title: Id description: Stable machine-readable identifier (kebab-case) severity: type: string enum: - info - warning - error title: Severity default: error message: type: string title: Message description: Human-readable description path: anyOf: - type: string - type: 'null' title: Path description: JSONPath-style location (e.g. $.context.task.steps[2]) value: anyOf: - type: string - type: 'null' title: Value description: The offending value, when it adds clarity type: object required: - id - message title: ValidationIssue description: A single validation finding with severity, location, and description. InternalTool: properties: type: type: string const: function title: Type description: Always `function`. default: function examples: - function function: $ref: '#/components/schemas/ToolFunction' description: >- The tool function definition, including the JSON Schema of its parameters. examples: [] type: object required: - function title: InternalTool description: A tool definition to be used by the OpenAI API. ToolHttpEndpoint: properties: url: type: string title: Url description: The endpoint URL of the external service to call. examples: - https://api.example.com method: $ref: '#/components/schemas/ToolHttpMethod' description: The HTTP method to use for the service call. examples: - get argument_location: $ref: '#/components/schemas/ToolArgumentLocation' description: How to pass the arguments to the request. examples: - query timeout: anyOf: - type: number maximum: 120 minimum: 1 - type: 'null' title: Timeout description: >- Timeout in seconds for the HTTP request. Default 20 seconds when not set. examples: - 45 type: object required: - url - method - argument_location title: ToolHttpEndpoint description: The configuration for an HTTP API call by a tool. Context: properties: task: anyOf: - oneOf: - $ref: '#/components/schemas/ExpressionTask' - $ref: '#/components/schemas/LoadToolFromFileTask' - $ref: '#/components/schemas/EventTask' - $ref: '#/components/schemas/StepsTask' discriminator: propertyName: type mapping: event: $ref: '#/components/schemas/EventTask' expression: $ref: '#/components/schemas/ExpressionTask' import: $ref: '#/components/schemas/LoadToolFromFileTask' steps: $ref: '#/components/schemas/StepsTask' - items: oneOf: - $ref: '#/components/schemas/ExpressionTask' - $ref: '#/components/schemas/LoadToolFromFileTask' - $ref: '#/components/schemas/EventTask' - $ref: '#/components/schemas/StepsTask' discriminator: propertyName: type mapping: event: $ref: '#/components/schemas/EventTask' expression: $ref: '#/components/schemas/ExpressionTask' import: $ref: '#/components/schemas/LoadToolFromFileTask' steps: $ref: '#/components/schemas/StepsTask' type: array - type: 'null' title: Task description: Task implementation details type: object title: Context ToolParameterDefault: properties: transform: $ref: '#/components/schemas/ToolParameterTransform' description: The transform to apply to the value before using it as the default. examples: [] type: object required: - transform title: ToolParameterDefault description: The default value for a parameter of a tool call. StaticToolParameter: properties: name: type: string title: Name description: The name of the parameter - must be unique within the tool. examples: - temperature_unit description: anyOf: - type: string - type: 'null' title: Description description: The description of the parameter. examples: - >- Whether the temperature information should be fetched in celsius or fahrenheit. required: type: boolean title: Required description: Whether the parameter is required to have a value assigned. examples: - true type: $ref: '#/components/schemas/StaticToolParameterType' description: The expected type for the parameter. examples: - string default: anyOf: - {} - type: 'null' title: Default description: >- The default value for the parameter. If `type` is string, must be a string. If `type` is int, must be an int. If `type` is boolean, must be a boolean. If `type` is data_source_list, must be a list of strings (data source names). examples: - fahrenheit type: object required: - name - required - type title: StaticToolParameter description: A parameter for the tool whose value should be set at config time. ToolOptions: properties: propagate_tool_result: type: boolean title: Propagate Tool Result description: Whether the tool call result should be propagated to the caller. default: false type: object title: ToolOptions description: The options for a tool call. ToolFunction: properties: name: type: string title: Name description: The name of the function/tool call. examples: - get_weather description: type: string title: Description description: The description of the tool. examples: - Get the weather for a city parameters: title: Parameters description: The JSON Schema of parameters of the function/tool call. examples: - {} type: object required: - name - description - parameters title: ToolFunction description: >- A function available to an agent. See: - https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/function-calling ToolHttpMethod: type: string enum: - get - post - put - delete title: ToolHttpMethod description: The HTTP method to use for a tool HTTP request. ToolArgumentLocation: type: string enum: - body - form - path - query title: ToolArgumentLocation description: |- The location of the argument in a tool HTTP request. 'body' is used for JSON data in the POST request body. 'form' is used for form data in the POST request body. 'path' is used for URL path parameters. 'query' is used for query parameters in the URL. ExpressionTask: properties: id: anyOf: - type: string - type: 'null' title: Id description: A unique identifier for the task. config: anyOf: - additionalProperties: $ref: '#/components/schemas/JsonValue' type: object - type: 'null' title: Config variables: anyOf: - items: $ref: '#/components/schemas/Variable' type: array - type: 'null' title: Variables metadata: anyOf: - $ref: '#/components/schemas/ContextTaskMetadata' - type: 'null' tool: anyOf: - $ref: '#/components/schemas/ContextToolInfo' - type: 'null' type: type: string const: expression title: Type default: expression version: type: string const: v1alpha title: Version default: v1alpha inputs: items: $ref: '#/components/schemas/InputParameter' type: array title: Inputs expression: anyOf: - oneOf: - $ref: '#/components/schemas/CelExpression' - $ref: '#/components/schemas/JMESPathExpression' discriminator: propertyName: type mapping: cel: $ref: '#/components/schemas/CelExpression' jmespath: $ref: '#/components/schemas/JMESPathExpression' jp: $ref: '#/components/schemas/JMESPathExpression' - $ref: '#/components/schemas/CaseExpression' - type: string - type: 'null' title: Expression description: >- Expression for task output/logic. Supported expression forms: (1) JMESPath string (default for plain strings), (2) typed JMESPath object {"type":"jp"|"jmespath","expression":"..."}, or (3) typed CEL object {"type":"cel","expression":"..."}. examples: - inputs.can_sign_consent == `true` - expression: inputs.can_sign_consent == `true` type: jp - expression: inputs.can_sign_consent == true type: cel output: anyOf: - $ref: '#/components/schemas/JsonValue' - type: 'null' 'on': $ref: '#/components/schemas/ExpressionTaskEvents' description: Actions to execute when the configured events occur. type: object title: ExpressionTask LoadToolFromFileTask: properties: id: anyOf: - type: string - type: 'null' title: Id description: A unique identifier for the task. config: anyOf: - additionalProperties: $ref: '#/components/schemas/JsonValue' type: object - type: 'null' title: Config variables: anyOf: - items: $ref: '#/components/schemas/Variable' type: array - type: 'null' title: Variables metadata: anyOf: - $ref: '#/components/schemas/ContextTaskMetadata' - type: 'null' tool: anyOf: - $ref: '#/components/schemas/ContextToolInfo' - type: 'null' type: type: string const: import title: Type default: import version: type: string const: v1alpha title: Version default: v1alpha file: anyOf: - type: string - items: type: string type: array title: File description: The local path of the tool definition JSON file. type: object required: - file title: LoadToolFromFileTask description: >- Bootstraps a tool from a file (for internal developer use only if ENV.local=True). EventTask: properties: id: anyOf: - type: string - type: 'null' title: Id description: A unique identifier for the task. config: anyOf: - additionalProperties: $ref: '#/components/schemas/JsonValue' type: object - type: 'null' title: Config variables: anyOf: - items: $ref: '#/components/schemas/Variable' type: array - type: 'null' title: Variables metadata: anyOf: - $ref: '#/components/schemas/ContextTaskMetadata' - type: 'null' tool: anyOf: - $ref: '#/components/schemas/ContextToolInfo' - type: 'null' type: type: string const: event title: Type default: event version: type: string const: v1alpha title: Version default: v1alpha 'on': $ref: '#/components/schemas/EventTaskEvents' description: Actions to execute when the configured events occur. type: object title: EventTask StepsTask: properties: id: anyOf: - type: string - type: 'null' title: Id description: A unique identifier for the task. config: anyOf: - additionalProperties: $ref: '#/components/schemas/JsonValue' type: object - type: 'null' title: Config variables: anyOf: - items: $ref: '#/components/schemas/Variable' type: array - type: 'null' title: Variables metadata: anyOf: - $ref: '#/components/schemas/ContextTaskMetadata' - type: 'null' tool: anyOf: - $ref: '#/components/schemas/ContextToolInfo' - type: 'null' type: type: string const: steps title: Type default: steps version: type: string const: v1alpha title: Version default: v1alpha start: type: string enum: - auto - manual title: Start description: >- Controls when the workflow activation lifecycle runs. `auto` activates at session start; `manual` activates on first invocation. default: auto steps: items: $ref: '#/components/schemas/Step' type: array title: Steps type: object title: StepsTask ToolParameterTransform: properties: action: type: string enum: - default - override - remove title: Action description: >- The action to perform on the tool parameter value: `default` means only set the value (using the `format` field) if the parameter doesn't exist or is empty, `override` means always set the value," and `remove` means "remove the parameter value." default: default examples: [] when: anyOf: - $ref: '#/components/schemas/ToolParameterTransformCondition' - type: 'null' description: Only apply the transform if the condition is met. examples: [] value: anyOf: - {} - type: 'null' title: Value description: The default value to use for the parameter. examples: [] format: anyOf: - type: string - type: 'null' title: Format description: >- The string value to use for the parameter. The value will be evaluated with the Python `str.format` method, for example, `Hello, {name}!` examples: [] type: object title: ToolParameterTransform description: >- A transform to be applied to the value of a tool parameter. Either `value` or `format` must be set: - `value` is any arbitrary value: string, list or dictionary. - `format` is a string composed of other parameters or context variables. StaticToolParameterType: type: string enum: - string - int - boolean - data_source_list title: StaticToolParameterType description: The expected type for a static tool parameter. JsonValue: {} Variable: properties: value: anyOf: - $ref: '#/components/schemas/JsonValue' - type: 'null' description: Initial value of the variable. valueFrom: anyOf: - oneOf: - $ref: '#/components/schemas/CelExpression' - $ref: '#/components/schemas/JMESPathExpression' discriminator: propertyName: type mapping: cel: $ref: '#/components/schemas/CelExpression' jmespath: $ref: '#/components/schemas/JMESPathExpression' jp: $ref: '#/components/schemas/JMESPathExpression' - $ref: '#/components/schemas/CaseExpression' - type: string - type: 'null' title: Valuefrom description: >- Expression that computes the value. Supported expression forms: (1) JMESPath string (default for plain strings), (2) typed JMESPath object {"type":"jp"|"jmespath","expression":"..."}, or (3) typed CEL object {"type":"cel","expression":"..."}. Mutually exclusive with value. examples: - inputs.provided_dob == patient_dob - expression: inputs.provided_dob == patient_dob type: jmespath - expression: inputs.count + 1 type: cel name: type: string title: Name description: The name of the property. type: anyOf: - type: string enum: - string - number - integer - boolean - object - array - 'null' - type: 'null' title: Type description: anyOf: - type: string - type: 'null' title: Description title: anyOf: - type: string - type: 'null' title: Title format: anyOf: - type: string - type: 'null' title: Format pattern: anyOf: - type: string - type: 'null' title: Pattern enum: anyOf: - items: type: string type: array - type: 'null' title: Enum examples: anyOf: - items: $ref: '#/components/schemas/JsonValue' type: array - type: 'null' title: Examples type: object required: - name title: Variable ContextTaskMetadata: properties: priority: anyOf: - type: integer - type: 'null' title: Priority type: object title: ContextTaskMetadata ContextToolInfo: properties: name: anyOf: - type: string - type: 'null' title: Name description: The name of the generated tool. description: anyOf: - type: string - type: 'null' title: Description description: The description of the tool. type: object title: ContextToolInfo InputParameter: properties: name: type: string title: Name description: The name of the property. type: anyOf: - type: string enum: - string - number - integer - boolean - object - array - 'null' - type: 'null' title: Type description: anyOf: - type: string - type: 'null' title: Description title: anyOf: - type: string - type: 'null' title: Title format: anyOf: - type: string - type: 'null' title: Format pattern: anyOf: - type: string - type: 'null' title: Pattern enum: anyOf: - items: type: string type: array - type: 'null' title: Enum examples: anyOf: - items: $ref: '#/components/schemas/JsonValue' type: array - type: 'null' title: Examples required: type: boolean title: Required default: true type: object required: - name title: InputParameter CelExpression: properties: expression: type: string title: Expression description: CEL expression string. examples: - inputs.can_sign_consent == true type: type: string const: cel title: Type description: >- CEL expression language selector. Use with object form {"type":"cel","expression":"..."}. default: cel type: object required: - expression title: CelExpression description: |- Google CEL expression object. Use this object form when you want CEL syntax: {"type": "cel", "expression": "inputs.count + 1"} See https://github.com/google/cel-spec/blob/master/doc/langdef.md JMESPathExpression: properties: expression: type: string title: Expression description: JMESPath expression string. examples: - inputs.can_sign_consent == `true` type: type: string enum: - jp - jmespath title: Type description: >- JMESPath expression language selector. Use with object form {"type":"jp"|"jmespath","expression":"..."}. default: jp type: object required: - expression title: JMESPathExpression description: |- JMESPath expression object. Use this object form to explicitly mark JMESPath syntax: {"type": "jp", "expression": "inputs.can_sign_consent == `true`"} See https://jmespath.org/specification.html#grammar CaseExpression: properties: case: items: $ref: '#/components/schemas/ConditionalValue' type: array title: Case description: Ordered conditional branches (reserved for future runtime support). type: object required: - case title: CaseExpression description: >- Conditional branch expression. Note: CaseExpression is currently reserved and not yet executed at runtime. ExpressionTaskEvents: properties: start: anyOf: - items: oneOf: - $ref: '#/components/schemas/SetValueAction' - $ref: '#/components/schemas/IncrementAction' - $ref: '#/components/schemas/CallAction' - $ref: '#/components/schemas/SayAction' discriminator: propertyName: action mapping: call: $ref: '#/components/schemas/CallAction' inc: $ref: '#/components/schemas/IncrementAction' say: $ref: '#/components/schemas/SayAction' set: $ref: '#/components/schemas/SetValueAction' type: array - type: 'null' title: Start description: Actions to execute on the first input from the user. submit: anyOf: - items: oneOf: - $ref: '#/components/schemas/SetValueAction' - $ref: '#/components/schemas/IncrementAction' - $ref: '#/components/schemas/SaveAction' - $ref: '#/components/schemas/CallAction' - $ref: '#/components/schemas/SayAction' discriminator: propertyName: action mapping: call: $ref: '#/components/schemas/CallAction' inc: $ref: '#/components/schemas/IncrementAction' save: $ref: '#/components/schemas/SaveAction' say: $ref: '#/components/schemas/SayAction' set: $ref: '#/components/schemas/SetValueAction' type: array - type: 'null' title: Submit description: Actions to execute when the tool/step is submitted by the LLM. type: object title: ExpressionTaskEvents description: Actions to perform when events occur (start, submit). EventTaskEvents: properties: start: anyOf: - items: oneOf: - $ref: '#/components/schemas/SetValueAction' - $ref: '#/components/schemas/IncrementAction' - $ref: '#/components/schemas/CallAction' - $ref: '#/components/schemas/SayAction' discriminator: propertyName: action mapping: call: $ref: '#/components/schemas/CallAction' inc: $ref: '#/components/schemas/IncrementAction' say: $ref: '#/components/schemas/SayAction' set: $ref: '#/components/schemas/SetValueAction' type: array - type: 'null' title: Start description: Actions to execute on the first input from the user. type: object title: EventTaskEvents Step: properties: id: type: string title: Id description: The unique identifier of the step. goal: type: string title: Goal description: The goal of the step. instructions: items: anyOf: - $ref: '#/components/schemas/ConditionalText' - type: string type: array title: Instructions description: The instructions for the step. tools: $ref: '#/components/schemas/StepTools' description: The tools configuration for the step. inputs: items: $ref: '#/components/schemas/InputParameter' type: array title: Inputs description: The inputs for the step. 'on': $ref: '#/components/schemas/StepEventActions' description: The events that trigger the actions to be executed. next: items: anyOf: - $ref: '#/components/schemas/NextStep' - type: string type: array title: Next description: The next steps to execute. type: object required: - id - goal title: Step ToolParameterTransformCondition: properties: key: type: string title: Key description: The name of the parameter to check. examples: - key value: type: string title: Value description: The value to check against the parameter. examples: - value operator: anyOf: - type: string const: eq - type: 'null' title: Operator description: The operator to use for the comparison. Currently only supports "eq" default: eq examples: - eq type: object required: - key - value title: ToolParameterTransformCondition description: >- A condition to be met for a transform to be applied to the value of a tool parameter. ConditionalValue: properties: value: anyOf: - $ref: '#/components/schemas/JsonValue' - type: 'null' description: Initial value of the variable. valueFrom: anyOf: - oneOf: - $ref: '#/components/schemas/CelExpression' - $ref: '#/components/schemas/JMESPathExpression' discriminator: propertyName: type mapping: cel: $ref: '#/components/schemas/CelExpression' jmespath: $ref: '#/components/schemas/JMESPathExpression' jp: $ref: '#/components/schemas/JMESPathExpression' - $ref: '#/components/schemas/CaseExpression' - type: string - type: 'null' title: Valuefrom description: >- Expression that computes the value. Supported expression forms: (1) JMESPath string (default for plain strings), (2) typed JMESPath object {"type":"jp"|"jmespath","expression":"..."}, or (3) typed CEL object {"type":"cel","expression":"..."}. Mutually exclusive with value. examples: - inputs.provided_dob == patient_dob - expression: inputs.provided_dob == patient_dob type: jmespath - expression: inputs.count + 1 type: cel if: anyOf: - oneOf: - $ref: '#/components/schemas/CelExpression' - $ref: '#/components/schemas/JMESPathExpression' discriminator: propertyName: type mapping: cel: $ref: '#/components/schemas/CelExpression' jmespath: $ref: '#/components/schemas/JMESPathExpression' jp: $ref: '#/components/schemas/JMESPathExpression' - $ref: '#/components/schemas/CaseExpression' - type: string - type: 'null' title: If description: >- Condition to decide whether this item executes. Supported expression forms: (1) JMESPath string (default for plain strings), (2) typed JMESPath object {"type":"jp"|"jmespath","expression":"..."}, or (3) typed CEL object {"type":"cel","expression":"..."}. Example JMESPath string: "inputs.can_sign_consent == `true`". examples: - inputs.can_sign_consent == `true` - expression: inputs.can_sign_consent == `true` type: jp - expression: inputs.can_sign_consent == true type: cel type: object title: ConditionalValue SetValueAction: properties: value: anyOf: - $ref: '#/components/schemas/JsonValue' - type: 'null' description: Initial value of the variable. valueFrom: anyOf: - oneOf: - $ref: '#/components/schemas/CelExpression' - $ref: '#/components/schemas/JMESPathExpression' discriminator: propertyName: type mapping: cel: $ref: '#/components/schemas/CelExpression' jmespath: $ref: '#/components/schemas/JMESPathExpression' jp: $ref: '#/components/schemas/JMESPathExpression' - $ref: '#/components/schemas/CaseExpression' - type: string - type: 'null' title: Valuefrom description: >- Expression that computes the value. Supported expression forms: (1) JMESPath string (default for plain strings), (2) typed JMESPath object {"type":"jp"|"jmespath","expression":"..."}, or (3) typed CEL object {"type":"cel","expression":"..."}. Mutually exclusive with value. examples: - inputs.provided_dob == patient_dob - expression: inputs.provided_dob == patient_dob type: jmespath - expression: inputs.count + 1 type: cel if: anyOf: - oneOf: - $ref: '#/components/schemas/CelExpression' - $ref: '#/components/schemas/JMESPathExpression' discriminator: propertyName: type mapping: cel: $ref: '#/components/schemas/CelExpression' jmespath: $ref: '#/components/schemas/JMESPathExpression' jp: $ref: '#/components/schemas/JMESPathExpression' - $ref: '#/components/schemas/CaseExpression' - type: string - type: 'null' title: If description: >- Condition to decide whether this item executes. Supported expression forms: (1) JMESPath string (default for plain strings), (2) typed JMESPath object {"type":"jp"|"jmespath","expression":"..."}, or (3) typed CEL object {"type":"cel","expression":"..."}. Example JMESPath string: "inputs.can_sign_consent == `true`". examples: - inputs.can_sign_consent == `true` - expression: inputs.can_sign_consent == `true` type: jp - expression: inputs.can_sign_consent == true type: cel action: type: string const: set title: Action default: set name: type: string title: Name description: Destination path to mutate (e.g. output.foo). type: object required: - name title: SetValueAction IncrementAction: properties: if: anyOf: - oneOf: - $ref: '#/components/schemas/CelExpression' - $ref: '#/components/schemas/JMESPathExpression' discriminator: propertyName: type mapping: cel: $ref: '#/components/schemas/CelExpression' jmespath: $ref: '#/components/schemas/JMESPathExpression' jp: $ref: '#/components/schemas/JMESPathExpression' - $ref: '#/components/schemas/CaseExpression' - type: string - type: 'null' title: If description: >- Condition to decide whether this item executes. Supported expression forms: (1) JMESPath string (default for plain strings), (2) typed JMESPath object {"type":"jp"|"jmespath","expression":"..."}, or (3) typed CEL object {"type":"cel","expression":"..."}. Example JMESPath string: "inputs.can_sign_consent == `true`". examples: - inputs.can_sign_consent == `true` - expression: inputs.can_sign_consent == `true` type: jp - expression: inputs.can_sign_consent == true type: cel action: type: string const: inc title: Action default: inc name: type: string title: Name description: Numeric destination path to increment. by: type: integer title: By description: Increment amount (defaults to 1). default: 1 type: object required: - name title: IncrementAction CallAction: properties: if: anyOf: - oneOf: - $ref: '#/components/schemas/CelExpression' - $ref: '#/components/schemas/JMESPathExpression' discriminator: propertyName: type mapping: cel: $ref: '#/components/schemas/CelExpression' jmespath: $ref: '#/components/schemas/JMESPathExpression' jp: $ref: '#/components/schemas/JMESPathExpression' - $ref: '#/components/schemas/CaseExpression' - type: string - type: 'null' title: If description: >- Condition to decide whether this item executes. Supported expression forms: (1) JMESPath string (default for plain strings), (2) typed JMESPath object {"type":"jp"|"jmespath","expression":"..."}, or (3) typed CEL object {"type":"cel","expression":"..."}. Example JMESPath string: "inputs.can_sign_consent == `true`". examples: - inputs.can_sign_consent == `true` - expression: inputs.can_sign_consent == `true` type: jp - expression: inputs.can_sign_consent == true type: cel action: type: string const: call title: Action default: call name: type: string title: Name description: The name of the tool to call. arguments: anyOf: - additionalProperties: $ref: '#/components/schemas/JsonValue' type: object - type: 'null' title: Arguments description: Optional arguments to pass to the tool (supports template strings) type: object required: - name title: CallAction SayAction: properties: if: anyOf: - oneOf: - $ref: '#/components/schemas/CelExpression' - $ref: '#/components/schemas/JMESPathExpression' discriminator: propertyName: type mapping: cel: $ref: '#/components/schemas/CelExpression' jmespath: $ref: '#/components/schemas/JMESPathExpression' jp: $ref: '#/components/schemas/JMESPathExpression' - $ref: '#/components/schemas/CaseExpression' - type: string - type: 'null' title: If description: >- Condition to decide whether this item executes. Supported expression forms: (1) JMESPath string (default for plain strings), (2) typed JMESPath object {"type":"jp"|"jmespath","expression":"..."}, or (3) typed CEL object {"type":"cel","expression":"..."}. Example JMESPath string: "inputs.can_sign_consent == `true`". examples: - inputs.can_sign_consent == `true` - expression: inputs.can_sign_consent == `true` type: jp - expression: inputs.can_sign_consent == true type: cel text: type: string title: Text description: Text to apply if the condition is true. action: type: string const: say title: Action default: say role: type: string enum: - user - assistant title: Role description: The role of the message. default: assistant type: object required: - text title: SayAction SaveAction: properties: if: anyOf: - oneOf: - $ref: '#/components/schemas/CelExpression' - $ref: '#/components/schemas/JMESPathExpression' discriminator: propertyName: type mapping: cel: $ref: '#/components/schemas/CelExpression' jmespath: $ref: '#/components/schemas/JMESPathExpression' jp: $ref: '#/components/schemas/JMESPathExpression' - $ref: '#/components/schemas/CaseExpression' - type: string - type: 'null' title: If description: >- Condition to decide whether this item executes. Supported expression forms: (1) JMESPath string (default for plain strings), (2) typed JMESPath object {"type":"jp"|"jmespath","expression":"..."}, or (3) typed CEL object {"type":"cel","expression":"..."}. Example JMESPath string: "inputs.can_sign_consent == `true`". examples: - inputs.can_sign_consent == `true` - expression: inputs.can_sign_consent == `true` type: jp - expression: inputs.can_sign_consent == true type: cel action: type: string const: save title: Action default: save name: anyOf: - type: string - type: 'null' title: Name description: Target name to save (defaults to global variable). inputs: anyOf: - items: type: string type: array - type: 'null' title: Inputs description: Input field names to persist; None saves all collected inputs. type: object title: SaveAction ConditionalText: properties: if: anyOf: - oneOf: - $ref: '#/components/schemas/CelExpression' - $ref: '#/components/schemas/JMESPathExpression' discriminator: propertyName: type mapping: cel: $ref: '#/components/schemas/CelExpression' jmespath: $ref: '#/components/schemas/JMESPathExpression' jp: $ref: '#/components/schemas/JMESPathExpression' - $ref: '#/components/schemas/CaseExpression' - type: string - type: 'null' title: If description: >- Condition to decide whether this item executes. Supported expression forms: (1) JMESPath string (default for plain strings), (2) typed JMESPath object {"type":"jp"|"jmespath","expression":"..."}, or (3) typed CEL object {"type":"cel","expression":"..."}. Example JMESPath string: "inputs.can_sign_consent == `true`". examples: - inputs.can_sign_consent == `true` - expression: inputs.can_sign_consent == `true` type: jp - expression: inputs.can_sign_consent == true type: cel text: type: string title: Text description: Text to apply if the condition is true. type: object required: - text title: ConditionalText StepTools: properties: call: anyOf: - type: boolean - type: 'null' title: Call description: Whether to force immediate tool call without user interaction. allow: anyOf: - items: type: string type: array - type: 'null' title: Allow description: List of allowed tool names for this step. allowGoToStep: anyOf: - type: boolean - type: 'null' title: Allowgotostep description: >- Whether to expose the go_to_step escape hatch to the LLM. Defaults to disabled. type: object title: StepTools description: Configuration for tools available in a step. StepEventActions: properties: start: anyOf: - items: oneOf: - $ref: '#/components/schemas/SetValueAction' - $ref: '#/components/schemas/IncrementAction' - $ref: '#/components/schemas/CallAction' - $ref: '#/components/schemas/SayAction' discriminator: propertyName: action mapping: call: $ref: '#/components/schemas/CallAction' inc: $ref: '#/components/schemas/IncrementAction' say: $ref: '#/components/schemas/SayAction' set: $ref: '#/components/schemas/SetValueAction' type: array - type: 'null' title: Start description: Actions to execute on the first input from the user. enter: anyOf: - items: oneOf: - $ref: '#/components/schemas/GetValueAction' - $ref: '#/components/schemas/SetValueAction' - $ref: '#/components/schemas/IncrementAction' - $ref: '#/components/schemas/CallAction' - $ref: '#/components/schemas/SayAction' discriminator: propertyName: action mapping: call: $ref: '#/components/schemas/CallAction' get: $ref: '#/components/schemas/GetValueAction' inc: $ref: '#/components/schemas/IncrementAction' load: $ref: '#/components/schemas/GetValueAction' say: $ref: '#/components/schemas/SayAction' set: $ref: '#/components/schemas/SetValueAction' type: array - type: 'null' title: Enter description: Actions to execute when entering a step (before collecting inputs). presubmit: anyOf: - items: oneOf: - $ref: '#/components/schemas/GetValueAction' - $ref: '#/components/schemas/SetValueAction' - $ref: '#/components/schemas/IncrementAction' - $ref: '#/components/schemas/SaveAction' discriminator: propertyName: action mapping: get: $ref: '#/components/schemas/GetValueAction' inc: $ref: '#/components/schemas/IncrementAction' load: $ref: '#/components/schemas/GetValueAction' save: $ref: '#/components/schemas/SaveAction' set: $ref: '#/components/schemas/SetValueAction' type: array - type: 'null' title: Presubmit description: >- Actions to execute before validation (data-mutation only: set, inc, save). Use this to set default values for required fields that would otherwise fail validation. submit: anyOf: - items: oneOf: - $ref: '#/components/schemas/SetValueAction' - $ref: '#/components/schemas/IncrementAction' - $ref: '#/components/schemas/SaveAction' - $ref: '#/components/schemas/CallAction' - $ref: '#/components/schemas/SayAction' discriminator: propertyName: action mapping: call: $ref: '#/components/schemas/CallAction' inc: $ref: '#/components/schemas/IncrementAction' save: $ref: '#/components/schemas/SaveAction' say: $ref: '#/components/schemas/SayAction' set: $ref: '#/components/schemas/SetValueAction' type: array - type: 'null' title: Submit description: Actions to execute when the tool/step is submitted by the LLM. type: object title: StepEventActions description: Actions to perform when events occur (enter, presubmit, submit). NextStep: properties: if: anyOf: - oneOf: - $ref: '#/components/schemas/CelExpression' - $ref: '#/components/schemas/JMESPathExpression' discriminator: propertyName: type mapping: cel: $ref: '#/components/schemas/CelExpression' jmespath: $ref: '#/components/schemas/JMESPathExpression' jp: $ref: '#/components/schemas/JMESPathExpression' - $ref: '#/components/schemas/CaseExpression' - type: string - type: 'null' title: If description: >- Condition to decide whether this item executes. Supported expression forms: (1) JMESPath string (default for plain strings), (2) typed JMESPath object {"type":"jp"|"jmespath","expression":"..."}, or (3) typed CEL object {"type":"cel","expression":"..."}. Example JMESPath string: "inputs.can_sign_consent == `true`". examples: - inputs.can_sign_consent == `true` - expression: inputs.can_sign_consent == `true` type: jp - expression: inputs.can_sign_consent == true type: cel id: type: string title: Id description: The identifier of the next step. requires: anyOf: - items: type: string type: array - type: 'null' title: Requires description: >- List of input field names required for this transition. Validates that specified inputs are collected before allowing transition. type: object required: - id title: NextStep description: Represents a conditional transition to the next step. GetValueAction: properties: value: anyOf: - $ref: '#/components/schemas/JsonValue' - type: 'null' description: Initial value of the variable. valueFrom: anyOf: - oneOf: - $ref: '#/components/schemas/CelExpression' - $ref: '#/components/schemas/JMESPathExpression' discriminator: propertyName: type mapping: cel: $ref: '#/components/schemas/CelExpression' jmespath: $ref: '#/components/schemas/JMESPathExpression' jp: $ref: '#/components/schemas/JMESPathExpression' - $ref: '#/components/schemas/CaseExpression' - type: string - type: 'null' title: Valuefrom description: >- Expression that computes the value. Supported expression forms: (1) JMESPath string (default for plain strings), (2) typed JMESPath object {"type":"jp"|"jmespath","expression":"..."}, or (3) typed CEL object {"type":"cel","expression":"..."}. Mutually exclusive with value. examples: - inputs.provided_dob == patient_dob - expression: inputs.provided_dob == patient_dob type: jmespath - expression: inputs.count + 1 type: cel if: anyOf: - oneOf: - $ref: '#/components/schemas/CelExpression' - $ref: '#/components/schemas/JMESPathExpression' discriminator: propertyName: type mapping: cel: $ref: '#/components/schemas/CelExpression' jmespath: $ref: '#/components/schemas/JMESPathExpression' jp: $ref: '#/components/schemas/JMESPathExpression' - $ref: '#/components/schemas/CaseExpression' - type: string - type: 'null' title: If description: >- Condition to decide whether this item executes. Supported expression forms: (1) JMESPath string (default for plain strings), (2) typed JMESPath object {"type":"jp"|"jmespath","expression":"..."}, or (3) typed CEL object {"type":"cel","expression":"..."}. Example JMESPath string: "inputs.can_sign_consent == `true`". examples: - inputs.can_sign_consent == `true` - expression: inputs.can_sign_consent == `true` type: jp - expression: inputs.can_sign_consent == true type: cel action: type: string enum: - get - load title: Action description: Populate default input values. default: get inputs: anyOf: - items: type: string type: array - type: 'null' title: Inputs description: Input field names to populate; None populates all step inputs. overwrite: type: boolean title: Overwrite description: >- If False (default), only populate empty inputs. If True, always overwrite. default: false type: object title: GetValueAction securitySchemes: APIKeyHeader: type: apiKey in: header name: Syllable-API-Key ````