@xyd-js/opensdk-python 0.0.0-build-f0c10f6-20260703195526

package/__fixtures__/-2.complex.openai/realtime__sessions__create/input.json

@@ -0,0 +1,1400 @@
+{
+  "opensdk": "1.0.0",
+  "info": {
+    "title": "openai",
+    "version": "2.3.0"
+  },
+  "servers": [
+    "https://api.openai.com/v1"
+  ],
+  "security": [
+    {
+      "type": "http",
+      "kind": "bearer",
+      "schemeName": "ApiKeyAuth",
+      "envVar": "OPENAI_API_KEY",
+      "scheme": "bearer"
+    },
+    {
+      "type": "http",
+      "kind": "bearer",
+      "schemeName": "AdminApiKeyAuth",
+      "envVar": "OPENAI_API_KEY",
+      "scheme": "bearer"
+    }
+  ],
+  "types": [
+    {
+      "name": "RealtimeSessionCreateRequest",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "client_secret",
+          "type": {
+            "kind": "ref",
+            "name": "RealtimeSessionCreateRequestClientSecret"
+          },
+          "required": true,
+          "description": "Ephemeral key returned by the API."
+        },
+        {
+          "name": "modalities",
+          "type": {
+            "kind": "any"
+          },
+          "required": false,
+          "description": "The set of modalities the model can respond with. To disable audio,\nset this to [\"text\"].\n"
+        },
+        {
+          "name": "instructions",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. \"be extremely succinct\", \"act friendly\", \"here are examples of good responses\") and on audio behavior (e.g. \"talk quickly\", \"inject emotion into your voice\", \"laugh frequently\"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.\nNote that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session.\n"
+        },
+        {
+          "name": "voice",
+          "type": {
+            "kind": "ref",
+            "name": "VoiceIdsOrCustomVoice"
+          },
+          "required": false
+        },
+        {
+          "name": "input_audio_format",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.\n"
+        },
+        {
+          "name": "output_audio_format",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.\n"
+        },
+        {
+          "name": "input_audio_transcription",
+          "type": {
+            "kind": "ref",
+            "name": "RealtimeSessionCreateRequestInputAudioTranscription"
+          },
+          "required": false,
+          "description": "Configuration for input audio transcription, defaults to off and can be\nset to `null` to turn off once on. Input audio transcription is not native\nto the model, since the model consumes audio directly. Transcription runs\nasynchronously and should be treated as rough guidance\nrather than the representation understood by the model.\n"
+        },
+        {
+          "name": "speed",
+          "type": {
+            "kind": "scalar",
+            "scalar": "number"
+          },
+          "required": false,
+          "default": 1,
+          "description": "The speed of the model's spoken response. 1.0 is the default speed. 0.25 is\nthe minimum speed. 1.5 is the maximum speed. This value can only be changed\nin between model turns, not while a response is in progress.\n"
+        },
+        {
+          "name": "tracing",
+          "type": {
+            "kind": "ref",
+            "name": "RealtimeSessionCreateRequestTracing"
+          },
+          "required": false,
+          "description": "Configuration options for tracing. Set to null to disable tracing. Once\ntracing is enabled for a session, the configuration cannot be modified.\n\n`auto` will create a trace for the session with default values for the\nworkflow name, group id, and metadata.\n"
+        },
+        {
+          "name": "turn_detection",
+          "type": {
+            "kind": "ref",
+            "name": "RealtimeSessionCreateRequestTurnDetection"
+          },
+          "required": false,
+          "description": "Configuration for turn detection. Can be set to `null` to turn off. Server\nVAD means that the model will detect the start and end of speech based on\naudio volume and respond at the end of user speech.\n"
+        },
+        {
+          "name": "tools",
+          "type": {
+            "kind": "array",
+            "items": {
+              "kind": "ref",
+              "name": "RealtimeSessionCreateRequestToolsItem"
+            }
+          },
+          "required": false,
+          "description": "Tools (functions) available to the model."
+        },
+        {
+          "name": "tool_choice",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "How the model chooses tools. Options are `auto`, `none`, `required`, or\nspecify a function.\n"
+        },
+        {
+          "name": "temperature",
+          "type": {
+            "kind": "scalar",
+            "scalar": "number"
+          },
+          "required": false,
+          "description": "Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.\n"
+        },
+        {
+          "name": "max_response_output_tokens",
+          "type": {
+            "kind": "ref",
+            "name": "RealtimeSessionCreateRequestMaxResponseOutputTokens"
+          },
+          "required": false,
+          "description": "Maximum number of output tokens for a single assistant response,\ninclusive of tool calls. Provide an integer between 1 and 4096 to\nlimit output tokens, or `inf` for the maximum available tokens for a\ngiven model. Defaults to `inf`.\n"
+        },
+        {
+          "name": "truncation",
+          "type": {
+            "kind": "ref",
+            "name": "RealtimeTruncation"
+          },
+          "required": false
+        },
+        {
+          "name": "prompt",
+          "type": {
+            "kind": "ref",
+            "name": "Prompt"
+          },
+          "required": false
+        }
+      ],
+      "description": "A new Realtime session configuration, with an ephemeral key. Default TTL\nfor keys is one minute.\n"
+    },
+    {
+      "name": "RealtimeSessionCreateRequestClientSecret",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "value",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": true,
+          "description": "Ephemeral key usable in client environments to authenticate connections\nto the Realtime API. Use this in client-side environments rather than\na standard API token, which should only be used server-side.\n"
+        },
+        {
+          "name": "expires_at",
+          "type": {
+            "kind": "scalar",
+            "scalar": "integer",
+            "format": "unixtime"
+          },
+          "required": true,
+          "description": "Timestamp for when the token expires. Currently, all tokens expire\nafter one minute.\n"
+        }
+      ],
+      "description": "Ephemeral key returned by the API."
+    },
+    {
+      "name": "VoiceIdsOrCustomVoice",
+      "kind": "union",
+      "semantics": "anyOf",
+      "variants": [
+        {
+          "kind": "ref",
+          "name": "VoiceIdsShared"
+        },
+        {
+          "kind": "ref",
+          "name": "VoiceIdsOrCustomVoiceVariant1"
+        }
+      ],
+      "description": "A built-in voice name or a custom voice reference.\n"
+    },
+    {
+      "name": "VoiceIdsShared",
+      "kind": "union",
+      "semantics": "anyOf",
+      "variants": [
+        {
+          "kind": "scalar",
+          "scalar": "string"
+        },
+        {
+          "kind": "ref",
+          "name": "VoiceIdsSharedString"
+        }
+      ]
+    },
+    {
+      "name": "VoiceIdsSharedString",
+      "kind": "enum",
+      "base": "string",
+      "values": [
+        {
+          "value": "alloy"
+        },
+        {
+          "value": "ash"
+        },
+        {
+          "value": "ballad"
+        },
+        {
+          "value": "coral"
+        },
+        {
+          "value": "echo"
+        },
+        {
+          "value": "sage"
+        },
+        {
+          "value": "shimmer"
+        },
+        {
+          "value": "verse"
+        },
+        {
+          "value": "marin"
+        },
+        {
+          "value": "cedar"
+        }
+      ]
+    },
+    {
+      "name": "VoiceIdsOrCustomVoiceVariant1",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "id",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": true,
+          "description": "The custom voice ID, e.g. `voice_1234`."
+        }
+      ],
+      "description": "Custom voice reference."
+    },
+    {
+      "name": "RealtimeSessionCreateRequestInputAudioTranscription",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "model",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "The model to use for transcription.\n"
+        }
+      ],
+      "description": "Configuration for input audio transcription, defaults to off and can be\nset to `null` to turn off once on. Input audio transcription is not native\nto the model, since the model consumes audio directly. Transcription runs\nasynchronously and should be treated as rough guidance\nrather than the representation understood by the model.\n"
+    },
+    {
+      "name": "RealtimeSessionCreateRequestTracing",
+      "kind": "union",
+      "semantics": "oneOf",
+      "variants": [
+        {
+          "kind": "scalar",
+          "scalar": "string",
+          "const": "auto"
+        },
+        {
+          "kind": "ref",
+          "name": "RealtimeSessionCreateRequestTracingTracingConfiguration"
+        }
+      ],
+      "description": "Configuration options for tracing. Set to null to disable tracing. Once\ntracing is enabled for a session, the configuration cannot be modified.\n\n`auto` will create a trace for the session with default values for the\nworkflow name, group id, and metadata.\n"
+    },
+    {
+      "name": "RealtimeSessionCreateRequestTracingTracingConfiguration",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "workflow_name",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "The name of the workflow to attach to this trace. This is used to\nname the trace in the traces dashboard.\n"
+        },
+        {
+          "name": "group_id",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "The group id to attach to this trace to enable filtering and\ngrouping in the traces dashboard.\n"
+        },
+        {
+          "name": "metadata",
+          "type": {
+            "kind": "map",
+            "values": {
+              "kind": "any"
+            }
+          },
+          "required": false,
+          "description": "The arbitrary metadata to attach to this trace to enable\nfiltering in the traces dashboard.\n"
+        }
+      ],
+      "description": "Granular configuration for tracing.\n"
+    },
+    {
+      "name": "RealtimeSessionCreateRequestTurnDetection",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "type",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "Type of turn detection, only `server_vad` is currently supported.\n"
+        },
+        {
+          "name": "threshold",
+          "type": {
+            "kind": "scalar",
+            "scalar": "number"
+          },
+          "required": false,
+          "description": "Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A\nhigher threshold will require louder audio to activate the model, and\nthus might perform better in noisy environments.\n"
+        },
+        {
+          "name": "prefix_padding_ms",
+          "type": {
+            "kind": "scalar",
+            "scalar": "integer"
+          },
+          "required": false,
+          "description": "Amount of audio to include before the VAD detected speech (in\nmilliseconds). Defaults to 300ms.\n"
+        },
+        {
+          "name": "silence_duration_ms",
+          "type": {
+            "kind": "scalar",
+            "scalar": "integer"
+          },
+          "required": false,
+          "description": "Duration of silence to detect speech stop (in milliseconds). Defaults\nto 500ms. With shorter values the model will respond more quickly,\nbut may jump in on short pauses from the user.\n"
+        }
+      ],
+      "description": "Configuration for turn detection. Can be set to `null` to turn off. Server\nVAD means that the model will detect the start and end of speech based on\naudio volume and respond at the end of user speech.\n"
+    },
+    {
+      "name": "RealtimeSessionCreateRequestToolsItem",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "type",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string",
+            "const": "function"
+          },
+          "required": false,
+          "description": "The type of the tool, i.e. `function`."
+        },
+        {
+          "name": "name",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "The name of the function."
+        },
+        {
+          "name": "description",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "The description of the function, including guidance on when and how\nto call it, and guidance about what to tell the user when calling\n(if anything).\n"
+        },
+        {
+          "name": "parameters",
+          "type": {
+            "kind": "map",
+            "values": {
+              "kind": "any"
+            }
+          },
+          "required": false,
+          "description": "Parameters of the function in JSON Schema."
+        }
+      ]
+    },
+    {
+      "name": "RealtimeSessionCreateRequestMaxResponseOutputTokens",
+      "kind": "union",
+      "semantics": "oneOf",
+      "variants": [
+        {
+          "kind": "scalar",
+          "scalar": "integer"
+        },
+        {
+          "kind": "scalar",
+          "scalar": "string",
+          "const": "inf"
+        }
+      ],
+      "description": "Maximum number of output tokens for a single assistant response,\ninclusive of tool calls. Provide an integer between 1 and 4096 to\nlimit output tokens, or `inf` for the maximum available tokens for a\ngiven model. Defaults to `inf`.\n"
+    },
+    {
+      "name": "RealtimeTruncation",
+      "kind": "union",
+      "semantics": "oneOf",
+      "variants": [
+        {
+          "kind": "ref",
+          "name": "RealtimeTruncationString"
+        },
+        {
+          "kind": "ref",
+          "name": "RealtimeTruncationRetentionRatio"
+        }
+      ],
+      "description": "When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs.\n\nClients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost.\n\nTruncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate.\n\nTruncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit.\n"
+    },
+    {
+      "name": "RealtimeTruncationString",
+      "kind": "enum",
+      "base": "string",
+      "values": [
+        {
+          "value": "auto"
+        },
+        {
+          "value": "disabled"
+        }
+      ],
+      "description": "The truncation strategy to use for the session. `auto` is the default truncation strategy. `disabled` will disable truncation and emit errors when the conversation exceeds the input token limit."
+    },
+    {
+      "name": "RealtimeTruncationRetentionRatio",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "type",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string",
+            "const": "retention_ratio"
+          },
+          "required": true,
+          "description": "Use retention ratio truncation."
+        },
+        {
+          "name": "retention_ratio",
+          "type": {
+            "kind": "scalar",
+            "scalar": "number"
+          },
+          "required": true,
+          "description": "Fraction of post-instruction conversation tokens to retain (`0.0` - `1.0`) when the conversation exceeds the input token limit. Setting this to `0.8` means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates.\n"
+        },
+        {
+          "name": "token_limits",
+          "type": {
+            "kind": "ref",
+            "name": "RealtimeTruncationRetentionRatioTokenLimits"
+          },
+          "required": false,
+          "description": "Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used."
+        }
+      ],
+      "description": "Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage."
+    },
+    {
+      "name": "RealtimeTruncationRetentionRatioTokenLimits",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "post_instructions",
+          "type": {
+            "kind": "scalar",
+            "scalar": "integer"
+          },
+          "required": false,
+          "description": "Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens."
+        }
+      ],
+      "description": "Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used."
+    },
+    {
+      "name": "Prompt",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "id",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": true,
+          "description": "The unique identifier of the prompt template to use."
+        },
+        {
+          "name": "version",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string",
+            "nullable": true
+          },
+          "required": false
+        },
+        {
+          "name": "variables",
+          "type": {
+            "kind": "ref",
+            "name": "ResponsePromptVariables"
+          },
+          "required": false
+        }
+      ],
+      "description": "Reference to a prompt template and its variables.\n[Learn more](/docs/guides/text?api-mode=responses#reusable-prompts).\n"
+    },
+    {
+      "name": "ResponsePromptVariables",
+      "kind": "alias",
+      "of": {
+        "kind": "map",
+        "values": {
+          "kind": "ref",
+          "name": "ResponsePromptVariablesValue"
+        },
+        "nullable": true
+      }
+    },
+    {
+      "name": "ResponsePromptVariablesValue",
+      "kind": "union",
+      "semantics": "oneOf",
+      "variants": [
+        {
+          "kind": "scalar",
+          "scalar": "string"
+        },
+        {
+          "kind": "ref",
+          "name": "InputTextContent"
+        },
+        {
+          "kind": "ref",
+          "name": "InputImageContent"
+        },
+        {
+          "kind": "ref",
+          "name": "InputFileContent"
+        }
+      ]
+    },
+    {
+      "name": "InputTextContent",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "type",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string",
+            "const": "input_text"
+          },
+          "required": true,
+          "default": "input_text",
+          "description": "The type of the input item. Always `input_text`."
+        },
+        {
+          "name": "text",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": true,
+          "description": "The text input to the model."
+        }
+      ],
+      "description": "A text input to the model."
+    },
+    {
+      "name": "InputImageContent",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "type",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string",
+            "const": "input_image"
+          },
+          "required": true,
+          "default": "input_image",
+          "description": "The type of the input item. Always `input_image`."
+        },
+        {
+          "name": "image_url",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string",
+            "format": "uri",
+            "nullable": true
+          },
+          "required": false
+        },
+        {
+          "name": "file_id",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string",
+            "nullable": true
+          },
+          "required": false
+        },
+        {
+          "name": "detail",
+          "type": {
+            "kind": "ref",
+            "name": "ImageDetail"
+          },
+          "required": true
+        }
+      ],
+      "description": "An image input to the model. Learn about [image inputs](/docs/guides/vision)."
+    },
+    {
+      "name": "ImageDetail",
+      "kind": "enum",
+      "base": "string",
+      "values": [
+        {
+          "value": "low"
+        },
+        {
+          "value": "high"
+        },
+        {
+          "value": "auto"
+        },
+        {
+          "value": "original"
+        }
+      ]
+    },
+    {
+      "name": "InputFileContent",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "type",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string",
+            "const": "input_file"
+          },
+          "required": true,
+          "default": "input_file",
+          "description": "The type of the input item. Always `input_file`."
+        },
+        {
+          "name": "file_id",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string",
+            "nullable": true
+          },
+          "required": false
+        },
+        {
+          "name": "filename",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "The name of the file to be sent to the model."
+        },
+        {
+          "name": "file_data",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "The content of the file to be sent to the model.\n"
+        },
+        {
+          "name": "file_url",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string",
+            "format": "uri"
+          },
+          "required": false,
+          "description": "The URL of the file to be sent to the model."
+        },
+        {
+          "name": "detail",
+          "type": {
+            "kind": "ref",
+            "name": "FileInputDetail"
+          },
+          "required": false
+        }
+      ],
+      "description": "A file input to the model."
+    },
+    {
+      "name": "FileInputDetail",
+      "kind": "enum",
+      "base": "string",
+      "values": [
+        {
+          "value": "low"
+        },
+        {
+          "value": "high"
+        }
+      ]
+    },
+    {
+      "name": "RealtimeSessionCreateResponse",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "id",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "Unique identifier for the session that looks like `sess_1234567890abcdef`.\n"
+        },
+        {
+          "name": "object",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "The object type. Always `realtime.session`."
+        },
+        {
+          "name": "expires_at",
+          "type": {
+            "kind": "scalar",
+            "scalar": "integer",
+            "format": "unixtime"
+          },
+          "required": false,
+          "description": "Expiration timestamp for the session, in seconds since epoch."
+        },
+        {
+          "name": "include",
+          "type": {
+            "kind": "array",
+            "items": {
+              "kind": "scalar",
+              "scalar": "string",
+              "const": "item.input_audio_transcription.logprobs"
+            }
+          },
+          "required": false,
+          "description": "Additional fields to include in server outputs.\n- `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription.\n"
+        },
+        {
+          "name": "model",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "The Realtime model used for this session."
+        },
+        {
+          "name": "output_modalities",
+          "type": {
+            "kind": "any"
+          },
+          "required": false,
+          "description": "The set of modalities the model can respond with. To disable audio,\nset this to [\"text\"].\n"
+        },
+        {
+          "name": "instructions",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "The default system instructions (i.e. system message) prepended to model\ncalls. This field allows the client to guide the model on desired\nresponses. The model can be instructed on response content and format,\n(e.g. \"be extremely succinct\", \"act friendly\", \"here are examples of good\nresponses\") and on audio behavior (e.g. \"talk quickly\", \"inject emotion\ninto your voice\", \"laugh frequently\"). The instructions are not guaranteed\nto be followed by the model, but they provide guidance to the model on the\ndesired behavior.\n\nNote that the server sets default instructions which will be used if this\nfield is not set and are visible in the `session.created` event at the\nstart of the session.\n"
+        },
+        {
+          "name": "audio",
+          "type": {
+            "kind": "ref",
+            "name": "RealtimeSessionCreateResponseAudio"
+          },
+          "required": false,
+          "description": "Configuration for input and output audio for the session.\n"
+        },
+        {
+          "name": "tracing",
+          "type": {
+            "kind": "ref",
+            "name": "RealtimeSessionCreateRequestTracing"
+          },
+          "required": false,
+          "description": "Configuration options for tracing. Set to null to disable tracing. Once\ntracing is enabled for a session, the configuration cannot be modified.\n\n`auto` will create a trace for the session with default values for the\nworkflow name, group id, and metadata.\n"
+        },
+        {
+          "name": "turn_detection",
+          "type": {
+            "kind": "ref",
+            "name": "RealtimeSessionCreateRequestTurnDetection"
+          },
+          "required": false,
+          "description": "Configuration for turn detection. Can be set to `null` to turn off. Server\nVAD means that the model will detect the start and end of speech based on\naudio volume and respond at the end of user speech.\n"
+        },
+        {
+          "name": "tools",
+          "type": {
+            "kind": "array",
+            "items": {
+              "kind": "ref",
+              "name": "RealtimeFunctionTool"
+            }
+          },
+          "required": false,
+          "description": "Tools (functions) available to the model."
+        },
+        {
+          "name": "tool_choice",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "How the model chooses tools. Options are `auto`, `none`, `required`, or\nspecify a function.\n"
+        },
+        {
+          "name": "max_output_tokens",
+          "type": {
+            "kind": "ref",
+            "name": "RealtimeSessionCreateRequestMaxResponseOutputTokens"
+          },
+          "required": false,
+          "description": "Maximum number of output tokens for a single assistant response,\ninclusive of tool calls. Provide an integer between 1 and 4096 to\nlimit output tokens, or `inf` for the maximum available tokens for a\ngiven model. Defaults to `inf`.\n"
+        }
+      ],
+      "description": "A Realtime session configuration object.\n"
+    },
+    {
+      "name": "RealtimeSessionCreateResponseAudio",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "input",
+          "type": {
+            "kind": "ref",
+            "name": "RealtimeSessionCreateResponseAudioInput"
+          },
+          "required": false
+        },
+        {
+          "name": "output",
+          "type": {
+            "kind": "ref",
+            "name": "RealtimeSessionCreateResponseAudioOutput"
+          },
+          "required": false
+        }
+      ],
+      "description": "Configuration for input and output audio for the session.\n"
+    },
+    {
+      "name": "RealtimeSessionCreateResponseAudioInput",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "format",
+          "type": {
+            "kind": "ref",
+            "name": "RealtimeAudioFormats"
+          },
+          "required": false
+        },
+        {
+          "name": "transcription",
+          "type": {
+            "kind": "ref",
+            "name": "AudioTranscriptionResponse"
+          },
+          "required": false
+        },
+        {
+          "name": "noise_reduction",
+          "type": {
+            "kind": "ref",
+            "name": "RealtimeSessionCreateResponseAudioInputNoiseReduction"
+          },
+          "required": false,
+          "description": "Configuration for input audio noise reduction.\n"
+        },
+        {
+          "name": "turn_detection",
+          "type": {
+            "kind": "ref",
+            "name": "RealtimeSessionCreateResponseAudioInputTurnDetection"
+          },
+          "required": false,
+          "description": "Configuration for turn detection.\n"
+        }
+      ]
+    },
+    {
+      "name": "RealtimeAudioFormats",
+      "kind": "union",
+      "semantics": "anyOf",
+      "variants": [
+        {
+          "kind": "ref",
+          "name": "RealtimeAudioFormatsAudioPcm"
+        },
+        {
+          "kind": "ref",
+          "name": "RealtimeAudioFormatsAudioPcmu"
+        },
+        {
+          "kind": "ref",
+          "name": "RealtimeAudioFormatsAudioPcma"
+        }
+      ]
+    },
+    {
+      "name": "RealtimeAudioFormatsAudioPcm",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "type",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string",
+            "const": "audio/pcm"
+          },
+          "required": false,
+          "description": "The audio format. Always `audio/pcm`."
+        },
+        {
+          "name": "rate",
+          "type": {
+            "kind": "scalar",
+            "scalar": "integer",
+            "const": 24000
+          },
+          "required": false,
+          "description": "The sample rate of the audio. Always `24000`."
+        }
+      ],
+      "description": "The PCM audio format. Only a 24kHz sample rate is supported."
+    },
+    {
+      "name": "RealtimeAudioFormatsAudioPcmu",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "type",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string",
+            "const": "audio/pcmu"
+          },
+          "required": false,
+          "description": "The audio format. Always `audio/pcmu`."
+        }
+      ],
+      "description": "The G.711 μ-law format."
+    },
+    {
+      "name": "RealtimeAudioFormatsAudioPcma",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "type",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string",
+            "const": "audio/pcma"
+          },
+          "required": false,
+          "description": "The audio format. Always `audio/pcma`."
+        }
+      ],
+      "description": "The G.711 A-law format."
+    },
+    {
+      "name": "AudioTranscriptionResponse",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "model",
+          "type": {
+            "kind": "ref",
+            "name": "AudioTranscriptionResponseModel"
+          },
+          "required": false,
+          "description": "The model used for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`.\n"
+        },
+        {
+          "name": "language",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "The language of the input audio.\n"
+        },
+        {
+          "name": "prompt",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "The prompt configured for input audio transcription, when present.\n"
+        }
+      ]
+    },
+    {
+      "name": "AudioTranscriptionResponseModel",
+      "kind": "union",
+      "semantics": "anyOf",
+      "variants": [
+        {
+          "kind": "scalar",
+          "scalar": "string"
+        },
+        {
+          "kind": "ref",
+          "name": "AudioTranscriptionResponseModelString"
+        }
+      ],
+      "description": "The model used for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`.\n"
+    },
+    {
+      "name": "AudioTranscriptionResponseModelString",
+      "kind": "enum",
+      "base": "string",
+      "values": [
+        {
+          "value": "whisper-1"
+        },
+        {
+          "value": "gpt-4o-mini-transcribe"
+        },
+        {
+          "value": "gpt-4o-mini-transcribe-2025-12-15"
+        },
+        {
+          "value": "gpt-4o-transcribe"
+        },
+        {
+          "value": "gpt-4o-transcribe-diarize"
+        },
+        {
+          "value": "gpt-realtime-whisper"
+        }
+      ]
+    },
+    {
+      "name": "RealtimeSessionCreateResponseAudioInputNoiseReduction",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "type",
+          "type": {
+            "kind": "ref",
+            "name": "NoiseReductionType"
+          },
+          "required": false
+        }
+      ],
+      "description": "Configuration for input audio noise reduction.\n"
+    },
+    {
+      "name": "NoiseReductionType",
+      "kind": "enum",
+      "base": "string",
+      "values": [
+        {
+          "value": "near_field"
+        },
+        {
+          "value": "far_field"
+        }
+      ],
+      "description": "Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones.\n"
+    },
+    {
+      "name": "RealtimeSessionCreateResponseAudioInputTurnDetection",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "type",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "Type of turn detection, only `server_vad` is currently supported.\n"
+        },
+        {
+          "name": "threshold",
+          "type": {
+            "kind": "scalar",
+            "scalar": "number"
+          },
+          "required": false
+        },
+        {
+          "name": "prefix_padding_ms",
+          "type": {
+            "kind": "scalar",
+            "scalar": "integer"
+          },
+          "required": false
+        },
+        {
+          "name": "silence_duration_ms",
+          "type": {
+            "kind": "scalar",
+            "scalar": "integer"
+          },
+          "required": false
+        }
+      ],
+      "description": "Configuration for turn detection.\n"
+    },
+    {
+      "name": "RealtimeSessionCreateResponseAudioOutput",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "format",
+          "type": {
+            "kind": "ref",
+            "name": "RealtimeAudioFormats"
+          },
+          "required": false
+        },
+        {
+          "name": "voice",
+          "type": {
+            "kind": "ref",
+            "name": "VoiceIdsShared"
+          },
+          "required": false
+        },
+        {
+          "name": "speed",
+          "type": {
+            "kind": "scalar",
+            "scalar": "number"
+          },
+          "required": false
+        }
+      ]
+    },
+    {
+      "name": "RealtimeFunctionTool",
+      "kind": "struct",
+      "fields": [
+        {
+          "name": "type",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string",
+            "const": "function"
+          },
+          "required": false,
+          "description": "The type of the tool, i.e. `function`."
+        },
+        {
+          "name": "name",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "The name of the function."
+        },
+        {
+          "name": "description",
+          "type": {
+            "kind": "scalar",
+            "scalar": "string"
+          },
+          "required": false,
+          "description": "The description of the function, including guidance on when and how\nto call it, and guidance about what to tell the user when calling\n(if anything).\n"
+        },
+        {
+          "name": "parameters",
+          "type": {
+            "kind": "map",
+            "values": {
+              "kind": "any"
+            }
+          },
+          "required": false,
+          "description": "Parameters of the function in JSON Schema."
+        }
+      ]
+    }
+  ],
+  "resources": [
+    {
+      "name": "realtime",
+      "resources": [
+        {
+          "name": "sessions",
+          "methods": [
+            {
+              "action": "create",
+              "httpMethod": "post",
+              "path": "/realtime/sessions",
+              "operationId": "create-realtime-session",
+              "description": "Create an ephemeral API token for use in client-side applications with the\nRealtime API. Can be configured with the same session parameters as the\n`session.update` client event.\n\nIt responds with a session object, plus a `client_secret` key which contains\na usable ephemeral API token that can be used to authenticate browser clients\nfor the Realtime API.\n\nReturns the created Realtime session object, plus an ephemeral key.\n",
+              "requestBody": {
+                "contentType": "application/json",
+                "type": {
+                  "kind": "ref",
+                  "name": "RealtimeSessionCreateRequest"
+                },
+                "required": true,
+                "encoding": "json",
+                "description": "Create an ephemeral API key with the given session configuration."
+              },
+              "responses": [
+                {
+                  "status": "200",
+                  "description": "Session created successfully.",
+                  "contentType": "application/json",
+                  "type": {
+                    "kind": "ref",
+                    "name": "RealtimeSessionCreateResponse"
+                  }
+                }
+              ],
+              "primaryResponse": {
+                "kind": "ref",
+                "name": "RealtimeSessionCreateResponse"
+              }
+            }
+          ]
+        }
+      ]
+    }
+  ],
+  "sdk": {
+    "retry": {
+      "maxRetries": 2,
+      "retryableStatusCodes": [
+        408,
+        429,
+        500,
+        502,
+        503,
+        504
+      ],
+      "retryConnectionErrors": true,
+      "honorRetryAfterHeader": true,
+      "backoff": {
+        "initialDelayMs": 500,
+        "maxDelayMs": 8000,
+        "multiplier": 2,
+        "jitter": 0.25
+      }
+    },
+    "timeout": {
+      "defaultTimeoutMs": 60000
+    },
+    "errors": {
+      "statusCodeMap": {
+        "400": "BadRequest",
+        "401": "Unauthorized",
+        "403": "PermissionDenied",
+        "404": "NotFound",
+        "409": "Conflict",
+        "422": "UnprocessableEntity",
+        "429": "RateLimited"
+      },
+      "clientErrorKind": "API",
+      "serverErrorKind": "Internal"
+    },
+    "userAgent": {
+      "sdkIdentifierTemplate": "{package}-{language}/{version}",
+      "includeRuntimeVersion": false,
+      "aiAgentEnvVars": {
+        "CLAUDE_CODE": "claude-code",
+        "CURSOR_AGENT": "cursor",
+        "CLINE_ACTIVE": "cline",
+        "WINDSURF_ACTIVE": "windsurf",
+        "COPILOT_AGENT": "copilot"
+      }
+    },
+    "telemetry": {
+      "requestIdHeader": "X-Request-ID",
+      "headerName": "X-Client-Telemetry",
+      "enabledByDefault": false
+    },
+    "logging": {
+      "events": [
+        "request.start",
+        "request.success",
+        "request.retry",
+        "request.rate_limited",
+        "request.error",
+        "request.connection_error"
+      ]
+    },
+    "idempotency": {
+      "headerName": "Idempotency-Key",
+      "autoGenerateForPost": true
+    },
+    "pagination": {
+      "autoPageDelayMs": 0
+    },
+    "requestGuard": {
+      "optionKeys": [
+        "api_key",
+        "apiKey",
+        "idempotency_key",
+        "idempotencyKey",
+        "extra_headers",
+        "extraHeaders",
+        "max_retries",
+        "maxRetries",
+        "base_url",
+        "baseUrl",
+        "timeout"
+      ]
+    }
+  }
+}