o i^@sZdZddlZddlZddlmZmZmZmZmZm Z ddl m Z m Z m Z ddlmZedZGddde ZGd d d eZGd d d eZGd ddeZGddde ZGddde ZGddde ZGddde ZGddde ZGddde ZGddde ZGddde Ze eeeeeeeffZedZGd d!d!e Z Gd"d#d#e Z!Gd$d%d%e Z"Gd&d'd'e Z#Gd(d)d)e Z$Gd*d+d+e Z%Gd,d-d-e Z&Gd.d/d/e&Z'Gd0d1d1e&Z(Gd2d3d3e&Z)Gd4d5d5e&Z*Gd6d7d7e&Z+Gd8d9d9e&Z,Gd:d;d;e&Z-Gdd?d?e.Z/Gd@dAdAe.Z0GdBdCdCe.Z1GdDdEdEe.Z2GdFdGdGe.Z3GdHdIdIe.Z4GdJdKdKe.Z5GdLdMdMe.Z6GdNdOdOe.Z7GdPdQdQe.Z8GdRdSdSe.Z9GdTdUdUe.Z:GdVdWdWe.Z;GdXdYdYe.ZGd^d_d_e Z?Gd`dadae Z@GdbdOdOe.Z7Gdcdddde.ZAGdedfdfe.ZBGdgdhdhe ZCGdidjdje.ZDGdkdldle.ZEGdmdndne.ZFGdodpdpe.ZGidqeGdreFdse/dte0due1dve2dwe3dxe4dye5dze6d{e7d|e8d}eBd~eDdeEde9de:e;eeAdZHdefddZIdS)zEvent models and data structures for Grok Voice Agent API communication. Based on xAI's Grok Voice Agent API documentation: https://docs.x.ai/docs/guides/voice/agent N)AnyDictListLiteralOptionalUnion) BaseModel ConfigDictField) ToolsSchema)i@i>i:R]i}iDic@seZdZUdZeed<dS) AudioFormatz*Base class for audio format configuration.typeN)__name__ __module__ __qualname____doc__str__annotations__rrY/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/grok/realtime/events.pyr s  r c@s.eZdZUdZdZeded<dZeed<dS)PCMAudioFormataPCM audio format configuration with configurable sample rate. Grok supports: 8000, 16000, 21050, 24000, 32000, 44100, 48000 Hz Parameters: type: Audio format type, always "audio/pcm". rate: Sample rate in Hz. Defaults to 24000. z audio/pcmrr rateN) rrrrrrrrSUPPORTED_SAMPLE_RATESrrrrr#s  rc@"eZdZUdZdZeded<dS)PCMUAudioFormatuPCMU (G.711 μ-law) audio format configuration. Fixed at 8000 Hz sample rate. Parameters: type: Audio format type, always "audio/pcmu". z audio/pcmurNrrrrrrrrrrrr1 rc@r)PCMAAudioFormatzPCMA (G.711 A-law) audio format configuration. Fixed at 8000 Hz sample rate. Parameters: type: Audio format type, always "audio/pcma". z audio/pcmarNrrrrrr=rrc@s&eZdZUdZdZeeded<dS) TurnDetectionzServer-side voice activity detection configuration. Parameters: type: Detection type, must be "server_vad" or None for manual. server_vadrN)rrrrrrrrrrrrrNs rc@,eZdZUdZdZeeeee fe d<dS) AudioInputzjAudio input configuration. Parameters: format: The format configuration for input audio. Nformat rrrrr#rrrrrrrrrrr"] r"c@r!) AudioOutputzlAudio output configuration. Parameters: format: The format configuration for output audio. Nr#r$rrrrr&gr%r&c@s2eZdZUdZdZeeed<dZee ed<dS)AudioConfigurationzAudio configuration for input and output. Parameters: input: Configuration for input audio. output: Configuration for output audio. Ninputoutput) rrrrr(rr"rr)r&rrrrr'q r'c@r) WebSearchToolzkWeb search tool configuration. Enables the voice agent to search the web for current information. web_searchrNrrrrrr+s r+c@s6eZdZUdZdZeded<dZee e ed<dS) XSearchToolzX (Twitter) search tool configuration. Enables the voice agent to search X for posts and information. Parameters: type: Tool type, always "x_search". allowed_x_handles: Optional list of X handles to filter search results. x_searchrNallowed_x_handles) rrrrrrrr/rrrrrrrr-s  r-c@s>eZdZUdZdZeded<eeed<dZ e e ed<dS)FileSearchToola7File/Collection search tool configuration. Enables the voice agent to search through uploaded document collections. Parameters: type: Tool type, always "file_search". vector_store_ids: List of collection IDs to search. max_num_results: Maximum number of results to return. file_searchrvector_store_ids max_num_resultsN) rrrrrrrrrr4rintrrrrr0s  r0c@sBeZdZUdZdZeded<eed<eed<eee fed<dS) FunctionToolzCustom function tool configuration. Parameters: type: Tool type, always "function". name: Name of the function. description: Description of what the function does. parameters: JSON schema for function parameters. functionrname description parametersN) rrrrrrrrrrrrrrr6s  r6)AraRexSalEveLeoc@seZdZUdZeddZdZeee d<dZ ee eBe d<e dd d Z eee d <dZeee d <dZeeeeBe d <dS)SessionPropertiesa#Configuration properties for a Grok Voice Agent session. Parameters: instructions: System instructions for the assistant. voice: The voice the model uses to respond. Options: Ara, Rex, Sal, Eve, Leo. Defaults to "Ara". turn_detection: Configuration for turn detection. Defaults to server-side VAD. Set to None for manual turn detection. audio: Configuration for input and output audio. tools: Available tools for the assistant (web_search, x_search, file_search, function). Tarbitrary_types_allowedN instructionsr;voicecCs tddS)Nr )r)rrrrrs zSessionProperties.default_factoryturn_detectionaudiotools)rrrrr model_configrCrrrrD GrokVoicer rHrrIr'rJr rGrokToolrrrrr@s  r@c@sNeZdZUdZeded<dZeeed<dZ eeed<dZ eeed<dS) ItemContentaContent within a conversation item. Parameters: type: Content type (input_text, input_audio, text, audio). text: Text content for text-based items. audio: Base64-encoded audio data for audio items. transcript: Transcribed text for audio items. )textrI input_text input_audio output_text output_audiorNrOrI transcript) rrrrrrrOrrrIrTrrrrrNs  rNc@seZdZUdZedddZeed<dZe e ded<e d ed <dZ e e d ed <dZ e e d ed<dZ e eeed<dZe eed<dZe eed<dZe eed<dZe eed<dS)ConversationItemaA conversation item in the realtime session. Parameters: id: Unique identifier for the item, auto-generated if not provided. object: Object type identifier for the realtime API. type: Item type (message, function_call, or function_call_output). status: Current status of the item. role: Speaker role for message items (user, assistant, or system). content: Content list for message items. call_id: Function call identifier for function_call items. name: Function name for function_call items. arguments: Function arguments as JSON string for function_call items. output: Function output as JSON string for function_call_output items. cCsttjSN)ruuiduuid4hexrrrrrE szConversationItem.rFidNz realtime.itemobject)message function_callfunction_call_outputr) completed in_progress incompletestatus)user assistantsystemtoolrolecontentcall_idr8 argumentsr))rrrrr rZrrr[rrrbrgrhrrNrir8rjr)rrrrrUs  rUc@s&eZdZUdZeed<eded<dS)RealtimeConversationzA realtime conversation session. Parameters: id: Unique identifier for the conversation. object: Object type identifier, always "realtime.conversation". rZzrealtime.conversationr[N)rrrrrrrrrrrrks rkc@s.eZdZUdZddgZeeeded<dS)ResponsePropertieszProperties for configuring assistant responses. Parameters: modalities: Output modalities for the response (text, audio, or both). rOrI)rOrI modalitiesN) rrrrrmrrrrrrrrrl!s  rlc@sZeZdZUdZdZeeed<dZeeed<eed<dZ eeed<dZ eeed<dS) RealtimeErrora>Error information from the realtime API. Parameters: type: Error type identifier. code: Specific error code. message: Human-readable error message. param: Parameter name that caused the error, if applicable. event_id: Event ID associated with the error, if applicable. Nrcoder\paramevent_id) rrrrrrrrrprqrrrrrrrn0s  rnc@s(eZdZUdZedddZeed<dS) ClientEventzBase class for client events sent to the realtime API. Parameters: event_id: Unique identifier for the event, auto-generated if not provided. cCs ttSrV)rrWrXrrrrrENs zClientEvent.rFrrN)rrrrr rrrrrrrrrsGs rsc@*eZdZUdZdZeded<eed<dS)SessionUpdateEventzEvent to update session properties. Parameters: type: Event type, always "session.update". session: Updated session properties. zsession.updatersessionN)rrrrrrrr@rrrrruQ  ruc@rt)InputAudioBufferAppendEventzEvent to append audio data to the input buffer. Parameters: type: Event type, always "input_audio_buffer.append". audio: Base64-encoded audio data to append. zinput_audio_buffer.appendrrIN)rrrrrrrrrrrrrx]rwrxc@r)InputAudioBufferCommitEventzEvent to commit the current input audio buffer. Used when turn_detection is null (manual mode). Parameters: type: Event type, always "input_audio_buffer.commit". zinput_audio_buffer.commitrNrrrrrryirryc@r)InputAudioBufferClearEventzyEvent to clear the input audio buffer. Parameters: type: Event type, always "input_audio_buffer.clear". zinput_audio_buffer.clearrNrrrrrrzu rzc@s:eZdZUdZdZeded<dZee ed<e ed<dS)ConversationItemCreateEventzEvent to create a new conversation item. Parameters: type: Event type, always "conversation.item.create". previous_item_id: ID of the item to insert after, if any. item: The conversation item to create. zconversation.item.createrNprevious_item_iditem) rrrrrrrr}rrrUrrrrr|s  r|c@s2eZdZUdZdZeded<dZee ed<dS)ResponseCreateEventzEvent to create a new assistant response. Parameters: type: Event type, always "response.create". response: Optional response configuration properties. zresponse.createrNresponse) rrrrrrrrrrlrrrrrr*rc@r)ResponseCancelEventzyEvent to cancel the current assistant response. Parameters: type: Event type, always "response.cancel". zresponse.cancelrNrrrrrrr{rc@s,eZdZUdZeddZeed<eed<dS) ServerEventzBase class for server events received from the realtime API. Parameters: event_id: Unique identifier for the event. type: Type of the server event. TrArrrN)rrrrr rKrrrrrrrs   rc@&eZdZUdZeded<eed<dS)SessionUpdatedEventzEvent indicating a session has been updated. Parameters: type: Event type, always "session.updated". session: The updated session properties. session.updatedrrvN)rrrrrrr@rrrrr   rc@r)ConversationCreatedzEvent indicating a conversation has been created. This is the first message received after connecting. Parameters: type: Event type, always "conversation.created". conversation: The created conversation. conversation.createdr conversationN)rrrrrrrkrrrrr  rc@s6eZdZUdZeded<dZeeed<e ed<dS)ConversationItemAddedzEvent indicating a conversation item has been added. Parameters: type: Event type, always "conversation.item.added". previous_item_id: ID of the previous item, if any. item: The added conversation item. conversation.item.addedrNr}r~) rrrrrrr}rrrUrrrrr   rc@.eZdZUdZeded<eed<eed<dS)0ConversationItemInputAudioTranscriptionCompletedaEvent indicating input audio transcription is complete. Parameters: type: Event type, always "conversation.item.input_audio_transcription.completed". item_id: ID of the conversation item that was transcribed. transcript: Complete transcription text. 5conversation.item.input_audio_transcription.completedritem_idrTNrrrrrrrrrrrr   rc@r)InputAudioBufferSpeechStartedaEvent indicating speech has started in the input audio buffer. Only sent when turn_detection is "server_vad". Parameters: type: Event type, always "input_audio_buffer.speech_started". item_id: ID of the associated conversation item. !input_audio_buffer.speech_startedrrNrrrrrrrrc@r)InputAudioBufferSpeechStoppedaEvent indicating speech has stopped in the input audio buffer. Only sent when turn_detection is "server_vad". Parameters: type: Event type, always "input_audio_buffer.speech_stopped". item_id: ID of the associated conversation item. !input_audio_buffer.speech_stoppedrrNrrrrrrrrc@s6eZdZUdZeded<dZeeed<eed<dS)InputAudioBufferCommittedaEvent indicating the input audio buffer has been committed. Parameters: type: Event type, always "input_audio_buffer.committed". previous_item_id: ID of the previous item, if any. item_id: ID of the committed conversation item. input_audio_buffer.committedrNr}r) rrrrrrr}rrrrrrrrrc@seZdZUdZeded<dS)InputAudioBufferClearedzEvent indicating the input audio buffer has been cleared. Parameters: type: Event type, always "input_audio_buffer.cleared". input_audio_buffer.clearedrNrrrrrrrrrrrs rc@s&eZdZUdZeded<ded<dS)ResponseCreatedEvent indicating an assistant response has been created. Parameters: type: Event type, always "response.created". response: The created response object. response.createdrResponserNrrrrrr rrc@6eZdZUdZeded<eed<eed<eed<dS)ResponseOutputItemAddedaEvent indicating an output item has been added to a response. Parameters: type: Event type, always "response.output_item.added". response_id: ID of the response. output_index: Index of the output item. item: The added conversation item. response.output_item.addedr response_id output_indexr~N rrrrrrrr5rUrrrrr,   rc@6eZdZUdZeded<eed<eed<eed<dS)ResponseAudioTranscriptDeltaa"Event containing incremental audio transcript from a response. Parameters: type: Event type, always "response.output_audio_transcript.delta". response_id: ID of the response. item_id: ID of the conversation item. delta: Incremental transcript text. &response.output_audio_transcript.deltarrrdeltaNrrrrrr<rrc@r)ResponseAudioTranscriptDonezEvent indicating audio transcript is complete. Parameters: type: Event type, always "response.output_audio_transcript.done". response_id: ID of the response. item_id: ID of the conversation item. %response.output_audio_transcript.donerrrNrrrrrrLrrc@sFeZdZUdZeded<eed<eed<eed<eed<eed<d S) ResponseAudioDeltaa}Event containing incremental audio data from a response. Parameters: type: Event type, always "response.output_audio.delta". response_id: ID of the response. item_id: ID of the conversation item. output_index: Index of the output item. content_index: Index of the content part. delta: Base64-encoded incremental audio data. response.output_audio.deltarrrr content_indexrNrrrrrrrr5rrrrrZ   rc@r)ResponseAudioDonezEvent indicating audio content is complete. Parameters: type: Event type, always "response.output_audio.done". response_id: ID of the response. item_id: ID of the conversation item. response.output_audio.donerrrNrrrrrrnrrc@s^eZdZUdZeded<dZeeed<dZ eeed<eed<eed<dZ eeed <dS) "ResponseFunctionCallArgumentsDeltaaEvent containing incremental function call arguments. Parameters: type: Event type, always "response.function_call_arguments.delta". response_id: ID of the response. item_id: ID of the conversation item. call_id: ID of the function call. delta: Incremental function arguments as JSON. previous_item_id: ID of the previous item, if any. &response.function_call_arguments.deltarNrrrirr}) rrrrrrrrrrr}rrrrr|s  rc@r)!ResponseFunctionCallArgumentsDonea0Event indicating function call arguments are complete. Parameters: type: Event type, always "response.function_call_arguments.done". call_id: ID of the function call. name: Name of the function being called. arguments: Complete function arguments as JSON string. %response.function_call_arguments.donerrir8rjNrrrrrrrrc@sBeZdZUdZdZeeed<dZeeed<dZ eeed<dS)Usagea#Token usage statistics for a response. All fields are optional because Grok sends empty usage in some events. Parameters: total_tokens: Total number of tokens used. input_tokens: Number of input tokens used. output_tokens: Number of output tokens used. N total_tokens input_tokens output_tokens) rrrrrrr5rrrrrrrrs  rc@s^eZdZUdZeed<eded<eded<dZee ed<e e ed <dZ ee ed <dS) raAA complete assistant response. Parameters: id: Unique identifier for the response. object: Object type, always "realtime.response". status: Current status of the response. output: List of conversation items in the response. usage: Token usage statistics for the response. rZzrealtime.responser[)r_r`ra cancelledfailedrbNstatus_detailsr)usage)rrrrrrrrrrrrUrrrrrrrs    rc@r)rrrrrN)rrrrrrrrrrrrrc@s6eZdZUdZeded<eed<dZee ed<dS) ResponseDonezEvent indicating an assistant response is complete. Parameters: type: Event type, always "response.done". response: The completed response object. usage: Token usage (also available at top level in Grok). response.donerrNr) rrrrrrrrrrrrrrrs  rc@r)ResponseOutputItemDoneaEvent indicating an output item is complete. Parameters: type: Event type, always "response.output_item.done". response_id: ID of the response. output_index: Index of the output item. item: The completed conversation item. response.output_item.donerrrr~Nrrrrrrrrc@s*eZdZUdZeed<dZeeed<dS) ContentPartzA content part within a response. Parameters: type: Type of the content part (audio, text). transcript: Transcript text if applicable. rNrT)rrrrrrrTrrrrrrs rc@sFeZdZUdZeded<eed<eed<eed<eed<eed<d S) ResponseContentPartAddedarEvent indicating a content part has been added to a response. Parameters: type: Event type, always "response.content_part.added". response_id: ID of the response. item_id: ID of the conversation item. content_index: Index of the content part. output_index: Index of the output item. part: The added content part. response.content_part.addedrrrrrpartN) rrrrrrrr5rrrrrrrrc@s>eZdZUdZeded<eed<eed<eed<eed<dS) ResponseContentPartDonea:Event indicating a content part is complete. Parameters: type: Event type, always "response.content_part.done". response_id: ID of the response. item_id: ID of the conversation item. content_index: Index of the content part. output_index: Index of the output item. response.content_part.donerrrrrNrrrrrr s   rc@r) PingEventzKeep-alive ping event from the server. Parameters: type: Event type, always "ping". timestamp: Server timestamp in milliseconds. pingr timestampN)rrrrrrr5rrrrrrrc@s&eZdZUdZeded<eed<dS) ErrorEventzEvent indicating an error occurred. Parameters: type: Event type, always "error". error: Error details. errorrN)rrrrrrrnrrrrr+rrrrrrrrrrrrrrrrrrr)rrrrrdatac Csdzt|}|d}|tvrtd|t||WSty1}z t|d|d}~ww)a Parse a server event from JSON string. Args: data: JSON string containing the server event. Returns: Parsed server event object of the appropriate type. Raises: Exception: If the event type is unimplemented or parsing fails. rz!Unimplemented server event type: z N)jsonloads_server_event_types Exceptionmodel_validate)revent event_typeerrrparse_server_eventUs r)JrrrWtypingrrrrrrpydanticrr r %pipecat.adapters.schemas.tools_schemar rr rrrrr"r&r'r+r-r0r6rrMrLr@rNrUrkrlrnrsrurxryrzr|rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrs