{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://jambonz.org/schema/verbs/nova_s2s",
  "minVersion": "11.1.7",
  "title": "Amazon Nova Sonic S2S",
  "description": "Shortcut for 'llm' with vendor automatically set to 'nova'. Connects the caller to Amazon Nova Sonic (Nova 2 / Nova 2.5 Sonic) on Amazon Bedrock for real-time speech-to-speech conversation. auth takes AWS IAM credentials (accessKeyId, secretAccessKey, optional sessionToken) and the Bedrock region; the credentials need bedrock:InvokeModelWithBidirectionalStream on the model. llmOptions is optional: systemPrompt, history, greeting, and sessionStart / promptStart bodies merged into Nova's own events (the audio formats are fixed by jambonz). Requires the mediajam media server.",
  "type": "object",
  "allOf": [
    {
      "$ref": "../components/llm-base"
    }
  ],
  "properties": {
    "verb": {
      "const": "nova_s2s",
      "description": "The verb name."
    },
    "vendor": {
      "type": "string",
      "const": "nova",
      "description": "The LLM vendor (always 'nova' for this shortcut)."
    },
    "model": {
      "type": "string",
      "description": "The Bedrock model id. Defaults to amazon.nova-2-5-sonic.",
      "examples": [
        "amazon.nova-2-5-sonic",
        "amazon.nova-2-sonic-v1:0"
      ]
    },
    "auth": {
      "type": "object",
      "description": "AWS IAM credentials and the Bedrock region.",
      "properties": {
        "accessKeyId": {
          "type": "string",
          "minLength": 1,
          "description": "AWS access key id."
        },
        "secretAccessKey": {
          "type": "string",
          "minLength": 1,
          "description": "AWS secret access key."
        },
        "sessionToken": {
          "type": "string",
          "description": "Session token, for temporary (STS) credentials."
        },
        "region": {
          "type": "string",
          "description": "Bedrock region serving Nova Sonic. Defaults to us-east-1.",
          "examples": [
            "us-east-1",
            "us-west-2",
            "eu-north-1",
            "ap-northeast-1"
          ]
        }
      },
      "required": [
        "accessKeyId",
        "secretAccessKey"
      ],
      "additionalProperties": true
    },
    "llmOptions": {
      "type": "object",
      "description": "Nova session options. A systemPrompt or other text above 50KB is split across several textInput events.",
      "properties": {
        "systemPrompt": {
          "type": "string",
          "description": "System instructions, sent as the SYSTEM text content."
        },
        "speechPrompt": {
          "type": "string",
          "description": "Sent after the system prompt with role SYSTEM_SPEECH. Nova accepts one of three fixed sentences that choose Latin, Devanagari or mixed script for Hindi transcription and responses."
        },
        "history": {
          "type": "array",
          "description": "Prior turns sent before the audio starts. Following Nova's rules, consecutive turns with the same role are merged, leading assistant turns are dropped, and the total is capped at 200KB.",
          "items": {
            "type": "object",
            "properties": {
              "role": {
                "type": "string",
                "enum": [
                  "user",
                  "assistant",
                  "USER",
                  "ASSISTANT"
                ]
              },
              "content": {
                "type": "string"
              }
            },
            "required": [
              "role",
              "content"
            ]
          }
        },
        "greeting": {
          "type": "string",
          "description": "Sent as a user text turn once the audio starts, so Nova speaks first (Nova otherwise waits for the caller)."
        },
        "sessionStart": {
          "type": "object",
          "description": "Merged into Nova's sessionStart event: inferenceConfiguration, turnDetectionConfiguration.endpointingSensitivity (HIGH, MEDIUM, LOW)."
        },
        "promptStart": {
          "type": "object",
          "description": "Merged into Nova's promptStart event: audioOutputConfiguration.voiceId (default matthew), toolConfiguration.tools in Nova's toolSpec shape and toolConfiguration.toolChoice ({auto:{}}, {any:{}} or {tool:{name}}). The audio format fields are set by jambonz."
        },
        "dtmf": {
          "type": "object",
          "description": "Caller keypad input. Nova has no DTMF support, so each completed entry is sent as a user text turn. Takes the gather verb's digit options.",
          "properties": {
            "enable": {
              "type": "boolean"
            },
            "finishOnKey": {
              "type": "string"
            },
            "numDigits": {
              "type": "number"
            },
            "minDigits": {
              "type": "number"
            },
            "maxDigits": {
              "type": "number"
            },
            "interDigitTimeout": {
              "type": "number"
            },
            "timeout": {
              "type": "number"
            }
          },
          "required": [
            "enable"
          ]
        }
      },
      "additionalProperties": true
    }
  },
  "required": [
    "auth"
  ],
  "examples": [
    {
      "verb": "nova_s2s",
      "model": "amazon.nova-2-5-sonic",
      "auth": {
        "accessKeyId": "AKIA...",
        "secretAccessKey": "...",
        "region": "us-east-1"
      },
      "llmOptions": {
        "systemPrompt": "You are a helpful voice assistant. Keep answers short.",
        "greeting": "Greet the caller and ask how you can help.",
        "sessionStart": {
          "turnDetectionConfiguration": {
            "endpointingSensitivity": "MEDIUM"
          }
        },
        "promptStart": {
          "audioOutputConfiguration": {
            "voiceId": "tiffany"
          }
        }
      },
      "toolHook": "/tool-call",
      "actionHook": "/s2s-complete"
    }
  ]
}