+ Uie Ra0t$^RIHt^RIt^RIt^RIHt^RIHt^RIH t H t H t H t H t HtHtHtHtHt^RIHt^RIHtHt^RIt^RIHt^R IHt^R IHtHtH t H!t!H"t"H#t#H$t$H%t%H&t&^R I'H(t(H)t)H*t*H+t+H,t,^R I-H.t.^R I/H0t0^RI1H2t2H3t3^RI4H5t5H6t6^RI7H8t8H9t9H:t:H;t;HH?t?H@t@^RIAHBtBHCtC^RIDHEtEHFtFHGtGHHtHHItIHJtJ^RIKHLtL^RIMHNtNHOtO^RIPHQtQHRtRHStSHTtT^RIUHVtVHWtWHXtY^RIZH[t[^RI\H]t]H^t^^RI_H`t`^RIaHbtb^RIcHdtd^RIeHftfHgtg^RIhHiti^RIjHktk^R IlHmtm^R!InHoto^R"IpHqtq^R#IrHsts^R$ItHutu^R%IvHwtw^R&IxHyty^R'IzH{t{^R(I|H}t}^R)I~Ht] 'd^R*IHt^R*IHt^R+IHtHtR,R-.t]EP!]4tR.]R/&!R0R,]24t!R1R-]34t!R2R34t!R4R54t!R6R74t!R8R94tR:R;lt!R<R=4t!R>R?4t!R@RA4t!RBRC4t!RDRE4t!RFRG]4t!RHRI4t!RJRK]4tR#)L) annotationsN)copy) TracebackType) TYPE_CHECKINGAnyListTypeUnionIterableIteratorOptional AsyncIteratorcast)partial)Literaloverload) BaseModel)_legacy_response) NOT_GIVENBodyOmitQueryHeadersNoneTypeNotGivenomit not_given)is_given path_templatemaybe_transformstrip_not_givenasync_maybe_transform)cached_property)construct_type_unchecked)SyncAPIResourceAsyncAPIResource)to_streamed_response_wrapper"async_to_streamed_response_wrapper) InputItemsAsyncInputItemsInputItemsWithRawResponseAsyncInputItemsWithRawResponseInputItemsWithStreamingResponse$AsyncInputItemsWithStreamingResponse)Stream AsyncStream)PydanticFunctionToolResponsesPydanticFunctionTool) InputTokensAsyncInputTokensInputTokensWithRawResponseAsyncInputTokensWithRawResponse InputTokensWithStreamingResponse%AsyncInputTokensWithStreamingResponse) OpenAIError)_merge_mappingsmake_request_options)response_create_paramsresponse_compact_paramsresponse_retrieve_paramsresponses_client_event_param) TextFormatTparse_responsetype_to_text_format_param)Response) ToolParamParseableToolParam)Metadata) Reasoning)ParsedResponse)ResponseStreamManagerAsyncResponseStreamManager)CompactedResponse)WebSocketConnectionOptions)ResponseIncludable)ResponsesModel)ResponseInputParam)ResponsePromptParam)ResponseStreamEvent)ResponsesClientEvent)ResponsesServerEvent)ResponseInputItemParam)ResponseTextConfigParam)ResponsesClientEventParam)ClientConnection)OpenAI AsyncOpenAI ResponsesAsyncResponseszlogging.LoggerlogcF]tRt^Tt]RRl4t]RRl4t]RRl4t]RRl4t] R ] R ] R ] R ] R ] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R ] R!] R"] R#] R$] R%] R&R'R(R'R)R'R*] /!R+R,ll4t ] R ] R ] R ] R ] R ] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R ] R!] R"] R#] R$] R%] R&R'R(R'R)R'R*] / R-R.ll4t ] R ] R ] R ] R ] R ] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R ] R!] R"] R#] R$] R%] R&R'R(R'R)R'R*] / R/R0ll4t R ] R ] R ] R ] R ] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R ] R!] R"] R#] R$] R%] R&R'R(R'R)R'R*] /!R1R2llt ] R3] R4] R!] R&R'R(R'R)R'R*] /R5R6ll4t] R ] R ] R3] R!] R ] R ] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R ] R"] R#] R$] R%] R&R'R(R'R)R'R*] /R7R8ll4tR9] R ] R] R ] R ] R3] R!] R ] R ] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R ] R"] R#] R$] R%] R4] R&R'R(R'R)R'R*] /#R:R;lltR3] R ] R ] R ] R ] R ] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R] R ] R!] R"] R#] R$] R%] R<] R&R'R(R'R)R'R*] /#R=R>llt] R ] R?] R4] R] R&R'R(R'R)R'R*] /R@RAll4t] R ] R4] R&R'R(R'R)R'R*] /RBRCll4t] R ] R4] R&R'R(R'R)R'R*] /RDREll4t] RRFR ] R4] R&R'R(R'R)R'R*] /RGRHll4t] R ] R?] R4] R&R'R(R'R)R'R*] /RIRJll4t] R ] R?] R4] R&R'R(R'R)R'R*] /RKRLll4tR ] R?] R4] R] R&R'R(R'R)R'R*] /RMRNlltR&R'R(R'R)R'R*] /RORPlltR&R'R(R'R)R'R*] /RQRRlltR ] R] R] R] R&R'R(R'R)R'R*] /RSRTllt///3RURVlltRWtR'#)XrZcV^8dQhRR/#)returnr))formats"c/home/ubuntu/hermes-agent/venv/lib/python3.14/site-packages/openai/resources/responses/responses.py __annotate__Responses.__annotate__Vs((Z(c ,\VP4#N)r)_clientselfs&rc input_itemsResponses.input_itemsUs$,,''rfcV^8dQhRR/#)r_r`r3ra)rbs"rcrdreZs))k)rfc ,\VP4#rh)r3rirjs&rc input_tokensResponses.input_tokensYs4<<((rfcV^8dQhRR/#)r_r`ResponsesWithRawResponsera)rbs"rcrdre^s..#;.rfc \V4#z This property can be used as a prefix for any HTTP method call to return the raw response object instead of the parsed content. For more information, see https://www.github.com/openai/openai-python#accessing-raw-response-data-eg-headers )rsrjs&rcwith_raw_responseResponses.with_raw_response]s(--rfcV^8dQhRR/#)r_r`ResponsesWithStreamingResponsera)rbs"rcrdrehs44)G4rfc \V4#z An alternative to `.with_raw_response` that doesn't eagerly read the response body. For more information, see https://www.github.com/openai/openai-python#with_streaming_response )ryrjs&rcwith_streaming_response!Responses.with_streaming_responsegs.d33rf backgroundcontext_management conversationincludeinput instructionsmax_output_tokensmax_tool_callsmetadatamodelparallel_tool_callsprevious_response_idpromptprompt_cache_keyprompt_cache_retention reasoningsafety_identifier service_tierstorestreamstream_options temperaturetext tool_choicetools top_logprobstop_p truncationuser extra_headersN extra_query extra_bodytimeoutcDV^8dQhRRRRRRRRR R R R R RRRRRRRRRRR RRRRRRRRRRRR R!RR"R#R$R%R&R'R(R)R*R+R,R-R.RR/R'R0R1R2RR3R4R5R6R7R8R9R:R;R5v 6*7v 8+9v :&;v <A=v >?v D&Ev F"Gv H Iv J9Kv L Mv rfc! R#aK+Creates a model response. Provide [text](https://platform.openai.com/docs/guides/text) or [image](https://platform.openai.com/docs/guides/images) inputs to generate [text](https://platform.openai.com/docs/guides/text) or [JSON](https://platform.openai.com/docs/guides/structured-outputs) outputs. Have the model call your own [custom code](https://platform.openai.com/docs/guides/function-calling) or use built-in [tools](https://platform.openai.com/docs/guides/tools) like [web search](https://platform.openai.com/docs/guides/tools-web-search) or [file search](https://platform.openai.com/docs/guides/tools-file-search) to use your own data as input for the model's response. Args: background: Whether to run the model response in the background. [Learn more](https://platform.openai.com/docs/guides/background). context_management: Context management configuration for this request. conversation: The conversation that this response belongs to. Items from this conversation are prepended to `input_items` for this response request. Input items and output items from this response are automatically added to this conversation after this response completes. include: Specify additional output data to include in the model response. Currently supported values are: - `web_search_call.action.sources`: Include the sources of the web search tool call. - `code_interpreter_call.outputs`: Includes the outputs of python code execution in code interpreter tool call items. - `computer_call_output.output.image_url`: Include image urls from the computer call output. - `file_search_call.results`: Include the search results of the file search tool call. - `message.input_image.image_url`: Include image urls from the input message. - `message.output_text.logprobs`: Include logprobs with assistant messages. - `reasoning.encrypted_content`: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the `store` parameter is set to `false`, or when an organization is enrolled in the zero data retention program). input: Text, image, or file inputs to the model, used to generate a response. Learn more: - [Text inputs and outputs](https://platform.openai.com/docs/guides/text) - [Image inputs](https://platform.openai.com/docs/guides/images) - [File inputs](https://platform.openai.com/docs/guides/pdf-files) - [Conversation state](https://platform.openai.com/docs/guides/conversation-state) - [Function calling](https://platform.openai.com/docs/guides/function-calling) instructions: A system (or developer) message inserted into the model's context. When using along with `previous_response_id`, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses. max_output_tokens: An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](https://platform.openai.com/docs/guides/reasoning). max_tool_calls: The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. metadata: Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters. model: Model ID used to generate the response, like `gpt-4o` or `o3`. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the [model guide](https://platform.openai.com/docs/models) to browse and compare available models. parallel_tool_calls: Whether to allow the model to run tool calls in parallel. previous_response_id: The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](https://platform.openai.com/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. prompt: Reference to a prompt template and its variables. [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). prompt_cache_key: Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](https://platform.openai.com/docs/guides/prompt-caching). prompt_cache_retention: The retention policy for the prompt cache. Set to `24h` to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. [Learn more](https://platform.openai.com/docs/guides/prompt-caching#prompt-cache-retention). reasoning: **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). safety_identifier: A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers). service_tier: Specifies the processing type used for serving the request. - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'. - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model. - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or '[priority](https://openai.com/api-priority-processing/)', then the request will be processed with the corresponding service tier. - When not set, the default behavior is 'auto'. When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter. store: Whether to store the generated model response for later retrieval via API. stream: If set to true, the model response data will be streamed to the client as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). See the [Streaming section below](https://platform.openai.com/docs/api-reference/responses-streaming) for more information. stream_options: Options for streaming responses. Only set this when you set `stream: true`. temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. text: Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - [Text inputs and outputs](https://platform.openai.com/docs/guides/text) - [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs) tool_choice: How the model should select which tool (or tools) to use when generating a response. See the `tools` parameter to see how to specify which tools the model can call. tools: An array of tools the model may call while generating a response. You can specify which tool to use by setting the `tool_choice` parameter. We support the following categories of tools: - **Built-in tools**: Tools that are provided by OpenAI that extend the model's capabilities, like [web search](https://platform.openai.com/docs/guides/tools-web-search) or [file search](https://platform.openai.com/docs/guides/tools-file-search). Learn more about [built-in tools](https://platform.openai.com/docs/guides/tools). - **MCP Tools**: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about [MCP Tools](https://platform.openai.com/docs/guides/tools-connectors-mcp). - **Function calls (custom tools)**: Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling). You can also use custom tools to call your own code. top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. top_p: An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both. truncation: The truncation strategy to use for the model response. - `auto`: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. - `disabled` (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error. user: This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers). extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Nra"rkr~rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrs"&$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$rccreateResponses.createpn rfcDV^8dQhRRRRRRRRR R R R R RRRRRRRRRRRRRRRRRRRRRR RR!R"R#RR$R%R&R'R(R)R*R+R,R-R.RR/R'R0R1R2RR3R4R5R6R7R8R9R:R;R5v 6*7v 8+9v :&;v <A=v >?v D&Ev F"Gv H Iv J9Kv L %Mv rfc! R#aK+Creates a model response. Provide [text](https://platform.openai.com/docs/guides/text) or [image](https://platform.openai.com/docs/guides/images) inputs to generate [text](https://platform.openai.com/docs/guides/text) or [JSON](https://platform.openai.com/docs/guides/structured-outputs) outputs. Have the model call your own [custom code](https://platform.openai.com/docs/guides/function-calling) or use built-in [tools](https://platform.openai.com/docs/guides/tools) like [web search](https://platform.openai.com/docs/guides/tools-web-search) or [file search](https://platform.openai.com/docs/guides/tools-file-search) to use your own data as input for the model's response. Args: stream: If set to true, the model response data will be streamed to the client as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). See the [Streaming section below](https://platform.openai.com/docs/api-reference/responses-streaming) for more information. background: Whether to run the model response in the background. [Learn more](https://platform.openai.com/docs/guides/background). context_management: Context management configuration for this request. conversation: The conversation that this response belongs to. Items from this conversation are prepended to `input_items` for this response request. Input items and output items from this response are automatically added to this conversation after this response completes. include: Specify additional output data to include in the model response. Currently supported values are: - `web_search_call.action.sources`: Include the sources of the web search tool call. - `code_interpreter_call.outputs`: Includes the outputs of python code execution in code interpreter tool call items. - `computer_call_output.output.image_url`: Include image urls from the computer call output. - `file_search_call.results`: Include the search results of the file search tool call. - `message.input_image.image_url`: Include image urls from the input message. - `message.output_text.logprobs`: Include logprobs with assistant messages. - `reasoning.encrypted_content`: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the `store` parameter is set to `false`, or when an organization is enrolled in the zero data retention program). input: Text, image, or file inputs to the model, used to generate a response. Learn more: - [Text inputs and outputs](https://platform.openai.com/docs/guides/text) - [Image inputs](https://platform.openai.com/docs/guides/images) - [File inputs](https://platform.openai.com/docs/guides/pdf-files) - [Conversation state](https://platform.openai.com/docs/guides/conversation-state) - [Function calling](https://platform.openai.com/docs/guides/function-calling) instructions: A system (or developer) message inserted into the model's context. When using along with `previous_response_id`, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses. max_output_tokens: An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](https://platform.openai.com/docs/guides/reasoning). max_tool_calls: The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. metadata: Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters. model: Model ID used to generate the response, like `gpt-4o` or `o3`. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the [model guide](https://platform.openai.com/docs/models) to browse and compare available models. parallel_tool_calls: Whether to allow the model to run tool calls in parallel. previous_response_id: The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](https://platform.openai.com/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. prompt: Reference to a prompt template and its variables. [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). prompt_cache_key: Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](https://platform.openai.com/docs/guides/prompt-caching). prompt_cache_retention: The retention policy for the prompt cache. Set to `24h` to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. [Learn more](https://platform.openai.com/docs/guides/prompt-caching#prompt-cache-retention). reasoning: **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). safety_identifier: A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers). service_tier: Specifies the processing type used for serving the request. - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'. - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model. - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or '[priority](https://openai.com/api-priority-processing/)', then the request will be processed with the corresponding service tier. - When not set, the default behavior is 'auto'. When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter. store: Whether to store the generated model response for later retrieval via API. stream_options: Options for streaming responses. Only set this when you set `stream: true`. temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. text: Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - [Text inputs and outputs](https://platform.openai.com/docs/guides/text) - [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs) tool_choice: How the model should select which tool (or tools) to use when generating a response. See the `tools` parameter to see how to specify which tools the model can call. tools: An array of tools the model may call while generating a response. You can specify which tool to use by setting the `tool_choice` parameter. We support the following categories of tools: - **Built-in tools**: Tools that are provided by OpenAI that extend the model's capabilities, like [web search](https://platform.openai.com/docs/guides/tools-web-search) or [file search](https://platform.openai.com/docs/guides/tools-file-search). Learn more about [built-in tools](https://platform.openai.com/docs/guides/tools). - **MCP Tools**: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about [MCP Tools](https://platform.openai.com/docs/guides/tools-connectors-mcp). - **Function calls (custom tools)**: Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling). You can also use custom tools to call your own code. top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. top_p: An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both. truncation: The truncation strategy to use for the model response. - `auto`: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. - `disabled` (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error. user: This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers). extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Nra"rkrr~rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrs"&$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$rcrrirrfcDV^8dQhRRRRRRRRR R R R R RRRRRRRRRRRRRRRRRRRRRR RR!R"R#RR$R%R&R'R(R)R*R+R,R-R.RR/R'R0R1R2RR3R4R5R6R7R8R9R:R;R5v 6*7v 8+9v :&;v <A=v >?v D&Ev F"Gv H Iv J9Kv L 0Mv rfc! R#rrars"&$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$rcrrbrrfcDV^8dQhRRRRRRRRR R R R R RRRRRRRRRRR RRRRRRRRRRRR R!RR"R#R$R%R&R'R(R)R*R+R,R-R.RR/R'R0R1R2RR3R4R5R6R7R8R9R:R;R5S 6*7S 8+9S :&;S <A=S >?S D&ES F"GS H IS J9KS L 0MS rfc! ~TPR\/RVbRVbRVbRVbRVbRVbRVbRVbR V bR V bR V bR V bR V bRVbRVbRVbRVbRVRVRVRVRVRVRVRVRVRVRVRV/ CV'd\PM\P4\ VVV V!R7\ T;'gR\\,R 7#)! /responsesr~rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrFbodyoptionscast_tor stream_cls) _postr r<ResponseCreateParamsStreaming ResponseCreateParamsNonStreamingr;rCr/rQrs"&$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$rcrr[sNzz   *(*<#Lw  U  #L ():%nU*+>+,@f'(8-.D  !"():#$#LUf$n!;D!;U"LU *D;@'DD+LLE#H)+Q[el??U12W, , rf text_formatstarting_afterc<V^8dQhRRRRRRRRR R R R R RRRRR/ #)r_ response_idstrrtype[TextFormatT] | Omitr int | Omitr#Iterable[ParseableToolParam] | Omitrrrrrrrrr`"ResponseStreamManager[TextFormatT]ra)rbs"rcrdresf 1 1 1. 1 # 1 3 1& 1" 1  19 1 , 1rfc R#rhra rkrrrrrrrrs &$$$$$$$$rcrResponses.streams.1rfcDV^8dQhRRRRRRRRR R R R R RRRRRRRRRRRRRRRRRRRRRR R!R"RR#R$R%RR&R'R(R)R*R+R,R-R.RR/R)R0R1R2RR3R4R5R6R7R8R9R:R;R7&18+9&1:&;&1<A=&1>?&1D&E&1F"G&1H I&1J9K&1L ,M&1rfc! R#rhra"rkrrr~rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrs"&$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$rcrrsN.1rfrcHV^8dQhRRRRRRRRR R R R R RRRRRRRRRRRRRRRRRRRRRRR R!R"R#RR$R%R&RR'R(R)R*R+R,R-R.R/RR0R*R1R2R3RR4R5R6R7R8R9R:R;RR?/$#)@r_rrrrrrr~rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrr`rra)rbs"rcrdresWW W5 W % W * W`W.W3WKW;W+W0W-W,W 3!W"3#W$5%W&%'W(!M)W*.+W,&-W._/W0%1W2N3W4,5W6-7W8>9W:+;W<&=W>A?W@AWB#CWH&IWJ"KWL MWN9OWP ,QWrfc# aaa a a!a"a#/RVbRVbRVbRVbRS bRV bRV bRV bRV bR VbR VbR VbR VbR VbRVbRVbRVbRVRVRVRVRVRVRVRVRVRV/ Cp$V$P4U%U&u.uFwp%p&\V&4'gKV%NK p'p%p&\S4'g\V4'd2\V'4^8d"\RRP V'4,4h\ V4p\V'4^8Ed\V4'g \R4h\V4'g \R4h\V4'd6V'g/pRV9d \ R 4h\V4p\V4VR&\SP3/RVbRVbR!VbRVbRVbRS bRV bRV bRV bRV bR VbR VbR VbR VbR VbRVbRVbR"R#bRVbRVbRVbRVbRVbRVbRVbRVbRVbRVbRVbR$S bR%S!bR&S"bR'S#bp(\V(WgR(R)7#\S4'g \R*4h\V"V V!V VVV#3R+lTT\V4'dVR)7#R(R)7#uup&p%i),rrrrrrrrrrrrrrrrrrrrrrrrrrr~OCannot provide both response_id/starting_after can't be provided together with , 3input must be provided when creating a new response3model must be provided when creating a new responserb1Cannot mix and match text.format with text_formatrrTrrrrNr input_toolsrz7id must be provided when streaming an existing responsec R<SPSRS;'g.SSS\SR7#)T)rrrrrrrr)retriever)rrrrrrkrsrc"Responses.stream..rs1 +#MMr"/ +)#'#& rf) itemsrlen ValueErrorjoin _make_tools TypeErrorr_type_to_text_format_paramrrrI)rkrrrr~rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrnew_response_argskvnew_response_args_names api_requests)fd$$$$$$$d$$$$$$$$$$$$$$$$$$$$$$dddd rcrrsR U U  !"4  L  w  L   !2  n    "#6  #$8  f   0  %&<   !2! " L# $ U n ; D ; L U * D *7 :2C1H1H1J"Z1JAhWXk111J"Z [ ! !Xn%=%=3G^C_bcCca))345 E" & '! +E?? !VWWE?? !VWW $$Dt##$WXXDz!;K!HX@G #A#A#A #A $6 #A * #A #A*#A#4#A .#A"#A%8#A&:#A#A"2#A (>!#A"##A$ .%#A&'#A(()#A*+#A,(-#A.$/#A0#41#A2*3#A4*5#A67#A8&9#A:;#A<&=#A>,?#A@(A#AB&C#AD E#AKJ)+quv vK(( !Z[[(  (!19.1I1I~ PT G#[s &I I  verbositycHV^8dQhRRRRRRRRR R R R R RRRRRRRRRRRRRRRRRRRRRR RR!R"R#RR$R%R&R'R(R)R*R+R,R-R.R/R0RR1R)R2R3R4RR5R6R7R8R9R:R;RR?R@/$#Ar_rrr~rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrz1Optional[Literal['low', 'medium', 'high']] | Omitrrrrrrrrr`ParsedResponse[TextFormatT]ra)rbs"rcrdrej j .j * j ` j K j ;j 5j +j 0j -j ,j %j 3j 3j 5!j "%#j $!M%j &.'j (&)j *_+j ,%-j .@/j 0N1j 2,3j 4-5j 6>7j 839j :+;j <&=j >A?j @Aj BECj H&Ij J"Kj L Mj N9Oj P %Qj rfc#  aa\S4'd6V'g/pRV9d \R4h\V4p\S4VR&\ S4oRVV3Rllp$VP R\ /RVbRVbRVbRVbR VbR VbR VbR V bR V bRV bRV bRV bRVbRVbRVbRVbRVbRVRVRVRVRVRVRVRSRVRVR VR!VR"V/ C\P4\V V!V"V#V$R#7\\\\,,\4R$7#)%rbrc V^8dQhRRRR/#r_ raw_responserCr`rra)rbs"rcrd%Responses.parse..__annotate__   .I rfc <\SSVR7#)rrresponserAr rrs&rcparserResponses.parse..parser!!'% rfrr~rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrr post_parserrrrrrrrrrr r<ResponseCreateParamsr;rr rHr@rC%rkrr~rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrs%&d$$$$$$$$$$$$$$$$$$$$$$$$d$$$$$$$$$ rcparseResponses.parsesR K 4 STT:D7 DDNE"  zz   *(*<#Lw  U  #L ():%nU*+>+,@f'(8-.D  !"():#$#LUf$n!;D!;U"LU *D=@';;C"F)+'%" n[9:HE]/ / rfinclude_obfuscationc@V^8dQhRRRRRRRRR R R R R RRRRRRR/ #r_rrrList[ResponseIncludable] | Omitr bool | OmitrrrzLiteral[False] | Omitrrrrrrrrr`rCra)rbs"rcrdren1  )  # &&" 9 rfc R#rhra rkrrrrrrrrrs &&$$$$$$$$rcrResponses.retrievesrfc<V^8dQhRRRRRRRRR R R R R RRRRR/ #)r_rrrrrrrrrrrrrrrrr`rra)rbs"rcrdresd * * * * 1 * # *& *" *  *9 * % *rfc R#rhra rkrrrrrrrrs &&$$$$$$$rcrr$s'*rfc<V^8dQhRRRRRRRRR R R R R RRRRR/ #r_rrrrrrrrrrrrrrrrr`rra)rbs"rcrdresd 5 5 5 5 1 5 # 5& 5" 5  59 5 0 5rfc R#rhrar's &&$$$$$$$rcrr$s25rfFc<V^8dQhRRRRRRRRR R R R R RRRRR/ #r)ra)rbs"rcrdresd- - -  - 1 - # - &- "-  - 9-  0- rfc R#a Retrieves a model response with the given ID. Args: include: Additional fields to include in the response. See the `include` parameter for Response creation above for more information. include_obfuscation: When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an `obfuscation` field on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can set `include_obfuscation` to false to optimize for bandwidth if you trust the network links between your application and the OpenAI API. starting_after: The sequence number of the event after which to start streaming. stream: If set to true, the model response data will be streamed to the client as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). See the [Streaming section below](https://platform.openai.com/docs/api-reference/responses-streaming) for more information. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Nrar's &&$$$$$$$rcrr$s\ rfc@V^8dQhRRRRRRRRR R R R R RRRRRRR/ #)r_rrrrrrrr rrrrrrrrrrr`rra)rbs"rcrdreOsn. . .  . 1 . ) . #. &. ".  . 9.  %. rfc R#a Retrieves a model response with the given ID. Args: stream: If set to true, the model response data will be streamed to the client as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). See the [Streaming section below](https://platform.openai.com/docs/api-reference/responses-streaming) for more information. include: Additional fields to include in the response. See the `include` parameter for Response creation above for more information. include_obfuscation: When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an `obfuscation` field on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can set `include_obfuscation` to false to optimize for bandwidth if you trust the network links between your application and the OpenAI API. starting_after: The sequence number of the event after which to start streaming. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Nra rkrrrrrrrrrs &&$$$$$$$$rcrr$N^ rfc@V^8dQhRRRRRRRRR R R R R RRRRRRR/ #)r_rrrrrrrr rrrrrrrrrrr`rra)rbs"rcrdresn. . .  . 1 . ) . #. &. ".  . 9.  0. rfc R#r0rar1s &&$$$$$$$$rcrr$r2rfc@V^8dQhRRRRRRRRR R R R R RRRRRRR/ #)r_rrrrrr rrr%Literal[False] | Literal[True] | Omitrrrrrrrrr`rra)rbs"rcrdresn% % % 1 % ) % # % 6% &% "%  % 9%  0% rfc V'g\RV: 24hTP\RVR7\VVVV \ RVRVRVRV/\ P 4R7\T;'gR\\,R 7#) :Expected a non-empty value for `response_id` but received /responses/{response_id}rrrrrrrrrqueryFrrrr) r_getrr;r r>ResponseRetrieveParamsrCr/rQr#s &&$$$$$$$$rcrr$sYZeYhij jyy 4+ N(+'%%!7-/B(. &  -CC ??U12'  rfc 0V^8dQhRRRRRRRRR R R R /# r_rrrrrrrrrrr`Nonera)rbs"rcrdreF     &  "     9     rfc  V'g\RV: 24hRR/T;'g/CpVP\RVR7\W#WER7\R7#)' Deletes a model response with the given ID. Args: extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds r8Accept*/*r9r:rrrr_deleterr;rrkrrrrrs&&$$$$rcdeleteResponses.deletesg.YZeYhij j!5B]-@-@bB || 4+ N(+Q[   rfc 0V^8dQhRRRRRRRRR R R R /# r_rrrrrrrrrrr`rCra)rbs"rcrdreF" " " & " ""  " 9"  " rfc  V'g\RV: 24hVP\RVR7\W#WER7\R7#)Cancels a model response with the given ID. Only responses created with the `background` parameter set to `true` can be cancelled. [Learn more](https://platform.openai.com/docs/guides/background). Args: extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds r8/responses/{response_id}/cancelr:rrHrrrr;rCrKs&&$$$$rccancelResponses.cancelsP4YZeYhij jzz ; U(+Q[   rfc@V^8dQhRRRRRRRRRRR R R R R RRRRR/ #r_raUnion[Literal['gpt-5.4', 'gpt-5.4-mini', 'gpt-5.4-nano', 'gpt-5.4-mini-2026-03-17', 'gpt-5.4-nano-2026-03-17', 'gpt-5.3-chat-latest', 'gpt-5.2', 'gpt-5.2-2025-12-11', 'gpt-5.2-chat-latest', 'gpt-5.2-pro', 'gpt-5.2-pro-2025-12-11', 'gpt-5.1', 'gpt-5.1-2025-11-13', 'gpt-5.1-codex', 'gpt-5.1-mini', 'gpt-5.1-chat-latest', 'gpt-5', 'gpt-5-mini', 'gpt-5-nano', 'gpt-5-2025-08-07', 'gpt-5-mini-2025-08-07', 'gpt-5-nano-2025-08-07', 'gpt-5-chat-latest', 'gpt-4.1', 'gpt-4.1-mini', 'gpt-4.1-nano', 'gpt-4.1-2025-04-14', 'gpt-4.1-mini-2025-04-14', 'gpt-4.1-nano-2025-04-14', 'o4-mini', 'o4-mini-2025-04-16', 'o3', 'o3-2025-04-16', 'o3-mini', 'o3-mini-2025-01-31', 'o1', 'o1-2024-12-17', 'o1-preview', 'o1-preview-2024-09-12', 'o1-mini', 'o1-mini-2024-09-12', 'gpt-4o', 'gpt-4o-2024-11-20', 'gpt-4o-2024-08-06', 'gpt-4o-2024-05-13', 'gpt-4o-audio-preview', 'gpt-4o-audio-preview-2024-10-01', 'gpt-4o-audio-preview-2024-12-17', 'gpt-4o-audio-preview-2025-06-03', 'gpt-4o-mini-audio-preview', 'gpt-4o-mini-audio-preview-2024-12-17', 'gpt-4o-search-preview', 'gpt-4o-mini-search-preview', 'gpt-4o-search-preview-2025-03-11', 'gpt-4o-mini-search-preview-2025-03-11', 'chatgpt-4o-latest', 'codex-mini-latest', 'gpt-4o-mini', 'gpt-4o-mini-2024-07-18', 'gpt-4-turbo', 'gpt-4-turbo-2024-04-09', 'gpt-4-0125-preview', 'gpt-4-turbo-preview', 'gpt-4-1106-preview', 'gpt-4-vision-preview', 'gpt-4', 'gpt-4-0314', 'gpt-4-0613', 'gpt-4-32k', 'gpt-4-32k-0314', 'gpt-4-32k-0613', 'gpt-3.5-turbo', 'gpt-3.5-turbo-16k', 'gpt-3.5-turbo-0301', 'gpt-3.5-turbo-0613', 'gpt-3.5-turbo-1106', 'gpt-3.5-turbo-0125', 'gpt-3.5-turbo-16k-0613', 'o1-pro', 'o1-pro-2025-03-19', 'o3-pro', 'o3-pro-2025-06-10', 'o3-deep-research', 'o3-deep-research-2025-06-26', 'o4-mini-deep-research', 'o4-mini-deep-research-2025-06-26', 'computer-use-preview', 'computer-use-preview-2025-03-11', 'gpt-5-codex', 'gpt-5-pro', 'gpt-5-pro-2025-10-06', 'gpt-5.1-codex-max'], str, None]rz9Union[str, Iterable[ResponseInputItemParam], None] | Omitrrrrrrrrrrrrr`rKra)rbs"rcrdref f a f JIKf L+Mf N3Of P/Qf V&Wf X"Yf Z [f \9]f ^ _f rfc  VPR\RVRVRVRVRV/\P4\ WgWR7\ R7#) Compact a conversation. Returns a compacted response object. Learn when and how to compact long-running conversations in the [conversation state guide](https://platform.openai.com/docs/guides/conversation-state#managing-the-context-window). For ZDR-compatible compaction details, see [Compaction (advanced)](https://platform.openai.com/docs/guides/conversation-state#compaction-advanced). Args: model: Model ID used to generate the response, like `gpt-5` or `o3`. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the [model guide](https://platform.openai.com/docs/models) to browse and compare available models. input: Text, image, or file inputs to the model, used to generate a response instructions: A system (or developer) message inserted into the model's context. When used along with `previous_response_id`, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses. previous_response_id: The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](https://platform.openai.com/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. prompt_cache_key: A key to use when reading from or writing to the prompt cache. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds /responses/compactrrrrrrr)rr r=ResponseCompactParamsr;rK rkrrrrrrrrrs &$$$$$$$$$rccompactResponses.compactsflzz  UU"L*,@&(8 (== )+Q[&  rfc(V^8dQhRRRRRRRR/#) r_rrrrwebsocket_connection_optionsrLr`ResponsesConnectionManagerra)rbs"rcrdres3    'A  $  rfc 4\VPVVVR7#zConnect to a persistent Responses API WebSocket. Send `response.create` events and receive response stream events over the socket. )clientrrrb)rcrirkrrrbs&&&&rcconnectResponses.connects!*<<#')E   rfra__name__ __module__ __qualname____firstlineno__r#rlrprvr|rrrrrrrrrLrUr_rh__static_attributes__rarfrcrZrZTs(())..44v -1v cg v NR v >B v 8<v .2v 37v 04v /3v (,v 6:v 6:v 8<v (,!v "PT#v $15%v &)-'v (bf)v *(,+v ,37-v .QU/v 0/31v 2043v 4AE5v 6-17v 8.29v :)-;v <DH=v > ?v D)-Ev F%)Gv H#'Iv JBv 8<v .2v 37v 04v /3v (,v 6:v 6:v 8 ?v D)-Ev F%)Gv H#'Iv JBv 8<v .2v 37v 04v /3v (,v 6:v 6:v 8 ?v D)-Ev F%)Gv H#'Iv JB S 8<S .2S 37S 04S /3S (,S 6:S 6:S 8<S (,!S "PT#S $15%S &)-'S (bf)S *(,+S ,CG-S .QU/S 0/31S 2043S 4AE5S 6-17S 8.29S :)-;S <DH=S > ?S D)-ES F%)GS H#'IS JB&1.2&137&104&1/3&16:&1 6:!&1"8<#&1$(,%&1&PT'&1(15)&1*)-+&1,bf-&1.(,/&10QU1&12/33&14045&16AE7&18.29&1:)-;&1<DH=&1> ?&1D)-E&1F%)G&1H#'I&1JBW.2W37W04W/3W 6:!W"6:#W$8<%W&(,'W(PT)W*15+W,)--W.bf/W0(,1W2QU3W4/35W6047W8AE9W:.2;W<)-=W>DH?W@ AWB&*CWH)-IWJ%)KWL#'MWNBj 8<j .2j 37j 04j /3j (,j 6:j 6:j 8DH?j @ Aj BHLCj H)-Ij J%)Kj L#'Mj NR?llt] R ] R@] R5] R] R'R(R)R(R*R(R+] /RARBll4t] R ] R5] R'R(R)R(R*R(R+] /RCRDll4t] R ] R5] R'R(R)R(R*R(R+] /RERFll4t] RRGR ] R5] R'R(R)R(R*R(R+] /RHRIll4t] R ] R@] R5] R'R(R)R(R*R(R+] /RJRKll4t] R ] R@] R5] R'R(R)R(R*R(R+] /RLRMll4tR ] R@] R5] R] R'R(R)R(R*R(R+] /RNROlltR'R(R)R(R*R(R+] /RPRQlltR'R(R)R(R*R(R+] /RRRSlltR] R] R] R] R'R(R)R(R*R(R+] /RTRUllt///3RVRWlltRXtR(#)Yr[icV^8dQhRR/#)r_r`r*ra)rbs"rcrdAsyncResponses.__annotate__s--_-rfc ,\VP4#rh)r*rirjs&rcrlAsyncResponses.input_itemsst||,,rfcV^8dQhRR/#)r_r`r4ra)rbs"rcrdrrs....rfc ,\VP4#rh)r4rirjs&rcrpAsyncResponses.input_tokenss --rfcV^8dQhRR/#)r_r`AsyncResponsesWithRawResponsera)rbs"rcrdrrs33#@3rfc \V4#ru)ryrjs&rcrv AsyncResponses.with_raw_responses-T22rfcV^8dQhRR/#)r_r`#AsyncResponsesWithStreamingResponsera)rbs"rcrdrrs99)L9rfc \V4#r{)r}rjs&rcr|&AsyncResponses.with_streaming_responses3488rfr~rrrrrrrrrrrrrrrrrrrrrrrrrrrrrNrrrcDV^8dQhRRRRRRRRR R R R R RRRRRRRRRRR RRRRRRRRRRRR R!RR"R#R$R%R&R'R(R)R*R+R,R-R.RR/R'R0R1R2RR3R4R5R6R7R8R9R:R;R5v 6*7v 8+9v :&;v <A=v >?v D&Ev F"Gv H Iv J9Kv L *Mv rfc! "R#5irrars"&$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$rcrrrrcDV^8dQhRRRRRRRRR R R R R RRRRRRRRRRRRRRRRRRRRRR RR!R"R#RR$R%R&R'R(R)R*R+R,R-R.RR/R'R0R1R2RR3R4R5R6R7R8R9R:R;R5v 6*7v 8+9v :&;v <A=v >?v D&Ev F"Gv H Iv J9Kv L 5Mv rfc! "R#5irrars"&$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$rcrrrrcDV^8dQhRRRRRRRRR R R R R RRRRRRRRRRR RRRRRRRRRRRR R!RR"R#R$R%R&R'R(R)R*R+R,R-R.RR/R'R0R1R2RR3R4R5R6R7R8R9R:R;R5S 6*7S 8+9S :&;S <A=S >?S D&ES F"GS H IS J9KS L 5MS rfc! "TPR\/RVbRVbRVbRVbRVbRVbRVbRVbR V bR V bR V bR V bR V bRVbRVbRVbRVbRVRVRVRVRVRVRVRVRVRVRVRV/ CV'd\PM\P4GRjxL \ VVV V!R7\ T;'gR \\,R!7GRjxL #L?L5i)"rr~rrrrrrrrrrrrrrrrrrrrrrrrrrrrNrFr) rr"r<rrr;rCr0rQrs"&$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$rcrr sNZZ , *(*<#Lw  U  #L ():%nU*+>+,@f'(8-.D  !"():#$#LUf$n!;D!;U"LU *D;@'DD+LLE##H)+Q[el??U"#67W , , , #, s*BCC C1C C CCrrc<V^8dQhRRRRRRRRR R R R R RRRRR/ #)r_rrrrrrrrrrrrrrrrr`'AsyncResponseStreamManager[TextFormatT]ra)rbs"rcrdrr4 sf 6 6 6. 6 # 6 3 6& 6" 6  69 6 1 6rfc R#rhrars &$$$$$$$$rcrAsyncResponses.stream3 s36rfcDV^8dQhRRRRRRRRR R R R R RRRRRRRRRRRRRRRRRRRRRR R!R"RR#R$R%RR&R'R(R)R*R+R,R-R.RR/R)R0R1R2RR3R4R5R6R7R8R9R:R;R7&68+9&6:&;&6<A=&6>?&6D&E&6F"G&6H I&6J9K&6L 1M&6rfc! R#rhrars"&$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$rcrrB sN36rfrcHV^8dQhRRRRRRRRR R R R R RRRRRRRRRRRRRRRRRRRRRRR R!R"R#RR$R%R&RR'R(R)R*R+R,R-R.R/RR0R*R1R2R3RR4R5R6R7R8R9R:R;RR?/$#)@r_rrrrrrr~rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrr`rra)rbs"rcrdrrk s[[ [5 [ % [ * [`[.[3[K[;[+[0[-[,[ 3!["3#[$5%[&%'[(!M)[*.+[,&-[._/[0%1[2N3[4,5[6-7[8>9[:+;[<&=[>A?[@A[B#C[H&I[J"K[L M[N9O[P 1Q[rfc# /RVbRVbRVbRVbRV bRV bRV bRV bRV bR VbR VbR VbR VbR VbRVbRVbRVbRVRVRVRVRVRVRVRVRVRV/ Cp$V$P4U%U&u.uFwp%p&\V&4'gKV%NK p'p%p&\V4'g\V4'd2\V'4^8d"\RRP V'4,4h\ V4p\V'4^8Ed\ V\4'd \R4h\V4'g \R4h\V4'd6V'g/pRV9d \R 4h\V4p\V4VR&VP!R,/RVbRVbR!R"bR#VbRVbRVbRV bRV bRV bRV bRV bR VbR VbR VbR VbR VbRVbRVbRVbRVbRVbRVbRVbRVbRVbRVbRVbRVbRVbR$V bR%V!bR&V"bR'V#bp(\V(VVR(R)7#\ V\4'd \R*4hTPTR"T ;'g.V V!V"V#R+7p(\T(TT\V4'dVR)7#R(R)7#uup&p%i)-rrrrrrrrrrrrrrrrrrrrrrrrrrr~rrrrrbrrTrrrrrNrz@response_id must be provided when streaming an existing response)rrrrrrra)rrrrrr isinstancerrrrrrJrrrs)&$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$ rcrrk sR U U  !"4  L  w  L   !2  n    "#6  #$8  f   0  %&<   !2! " L# $ U n ; D ; L U * D *7 :2C1H1H1J"Z1JAhWXk111J"Z [ ! !Xn%=%=3G^C_bcCca))345  E" & '! +%** !VWWE?? !VWW $$Dt##$WXXDz!;K!HX++"""" " $6 " * " "*"#4" ."""%8"&:"""2" (>!""#"$ .%"&('"()"*(+",$-".#4/"0*1"2*3"45"6&7"89":&;"<,=">(?"@&A"B C"KH.'!#  +t,, !cdd-- 2+'%(K.'!19.1I1I~  PT  a#[s I!:I!rcHV^8dQhRRRRRRRRR R R R R RRRRRRRRRRRRRRRRRRRRRR RR!R"R#RR$R%R&R'R(R)R*R+R,R-R.R/R0RR1R)R2R3R4RR5R6R7R8R9R:R;RR?R@/$#rra)rbs"rcrdrr rrfc# <aa"\S4'd6V'g/pRV9d \R4h\V4p\S4VR&\ S4oRVV3Rllp$VP R\ /RVbRVbRVbRVbR VbR VbR VbR V bR V bRV bRV bRV bRVbRVbRVbRVbRVbRVRVRVRVRVRVRVRSRVRVR VR!VR"V/ C\P4\V V!V"V#V$R#7\\\\,,\4R$7GR%jxL #L5i)&rbrc V^8dQhRRRR/#rra)rbs"rcrd*AsyncResponses.parse..__annotate__< r rfc <\SSVR7#r rrs&rcr$AsyncResponses.parse..parser< rrfrr~rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrNrrs%&d$$$$$$$$$$$$$$$$$$$$$$$$d$$$$$$$$$ rcrAsyncResponses.parse sR K 4 STT:D7 DDNE"  ZZ   *(*<#Lw  U  #L ():%nU*+>+,@f'(8-.D  !"():#$#LUf$n!;D!;U"LU *D=@';;C"F)+'%" n[9:HE] / / / / sDC7DDDrc@V^8dQhRRRRRRRRR R R R R RRRRRRR/ #rra)rbs"rcrdrru r!rfc "R#5irhrar#s &&$$$$$$$$rcrAsyncResponses.retrievet s rc<V^8dQhRRRRRRRRR R R R R RRRRR/ #)r_rrrrrrrrrrrrrrrrr`rra)rbs"rcrdrr sd / / / / 1 / # /& /" /  /9 / * /rfc "R#5irhrar's &&$$$$$$$rcrr s ,/rc<V^8dQhRRRRRRRRR R R R R RRRRR/ #r_rrrrrrrrrrrrrrrrr`rra)rbs"rcrdrr sd : : : : 1 : # :& :" :  :9 : 5 :rfc "R#5irhrar's &&$$$$$$$rcrr s 7:rFc<V^8dQhRRRRRRRRR R R R R RRRRR/ #rra)rbs"rcrdrr sd- - -  - 1 - # - &- "-  - 9-  5- rfc "R#5ir-rar's &&$$$$$$$rcrr s \ rc@V^8dQhRRRRRRRRR R R R R RRRRRRR/ #)r_rrrrrrrr rrrrrrrrrrr`rra)rbs"rcrdrr sn. . .  . 1 . ) . #. &. ".  . 9.  *. rfc "R#5ir0rar1s &&$$$$$$$$rcrr ^ rc@V^8dQhRRRRRRRRR R R R R RRRRRRR/ #)r_rrrrrrrr rrrrrrrrrrr`rra)rbs"rcrdrr sn. . .  . 1 . ) . #. &. ".  . 9.  5. rfc "R#5ir0rar1s &&$$$$$$$$rcrr rrc@V^8dQhRRRRRRRRR R R R R RRRRRRR/ #)r_rrrrrr rrrr6rrrrrrrrr`rra)rbs"rcrdrr7 sn% % % 1 % ) % # % 6% &% "%  % 9%  5% rfc 8"V'g\RV: 24hTP\RVR7\TTTT \ RVRVRVRV/\ P 4GRjxL R7\T;'gR \\,R 7GRjxL #L6L5i) r8r9r:rrrrNr;Fr=) rr>rr;r"r>r?rCr0rQr#s &&$$$$$$$$rcrr7 sYZeYhij jYY 4+ N(+'%1!7-/B(. &  -CC ??U"#67'    s*ABB B6BBBBc 0V^8dQhRRRRRRRRR R R R /#rAra)rbs"rcrdrr^ rCrfc "V'g\RV: 24hRR/T;'g/CpVP\RVR7\W#WER7\R7GRjxL #L5i) rEr8rFrGr9r:rrHNrIrKs&&$$$$rcrLAsyncResponses.delete^ st.YZeYhij j!5B]-@-@bB \\ 4+ N(+Q[ "    s#A"5A"A A"c 0V^8dQhRRRRRRRRR R R R /#rOra)rbs"rcrdrr rPrfc "V'g\RV: 24hVP\RVR7\W#WER7\R7GRjxL #L5i)rRr8rSr:rrHNrTrKs&&$$$$rcrUAsyncResponses.cancel s]4YZeYhij jZZ ; U(+Q[      sA A A Ac@V^8dQhRRRRRRRRRRR R R R R RRRRR/ #rXra)rbs"rcrdrr rYrfc  "TPR\RVRVRVRVRV/\P4GRjxL \ WgWR7\ R 7GRjxL #L"L5i) r[r\rrrrrNrr)rr"r=r]r;rKr^s &$$$$$$$$$rcr_AsyncResponses.compact s}lZZ ,UU"L*,@&(8 (==  )+Q[&      s!4AA AAAAc(V^8dQhRRRRRRRR/#) r_rrrrrbrLr`AsyncResponsesConnectionManagerra)rbs"rcrdrrL s3    'A  )  rfc 4\VPVVVR7#re)rrirgs&&&&rcrhAsyncResponses.connectL s!/<<#')E   rfrarjrarfrcr[r[s--..3399v -1v cg v NR v >B v 8<v .2v 37v 04v /3v (,v 6:v 6:v 8<v (,!v "PT#v $15%v &)-'v (bf)v *(,+v ,37-v .QU/v 0/31v 2043v 4AE5v 6-17v 8.29v :)-;v <DH=v > ?v D)-Ev F%)Gv H#'Iv JBv 8<v .2v 37v 04v /3v (,v 6:v 6:v 8 ?v D)-Ev F%)Gv H#'Iv JBv 8<v .2v 37v 04v /3v (,v 6:v 6:v 8 ?v D)-Ev F%)Gv H#'Iv JB S 8<S .2S 37S 04S /3S (,S 6:S 6:S 8<S (,!S "PT#S $15%S &)-'S (bf)S *(,+S ,CG-S .QU/S 0/31S 2043S 4AE5S 6-17S 8.29S :)-;S <DH=S > ?S D)-ES F%)GS H#'IS JB&6.2&637&604&6/3&66:&6 6:!&6"8<#&6$(,%&6&PT'&6(15)&6*)-+&6,bf-&6.(,/&60QU1&62/33&64045&66AE7&68.29&6:)-;&6<DH=&6> ?&6D)-E&6F%)G&6H#'I&6JB[.2[37[04[/3[ 6:!["6:#[$8<%[&(,'[(PT)[*15+[,)--[.bf/[0(,1[2QU3[4/35[6047[8AE9[:.2;[<)-=[>DH?[@ A[B&*C[H)-I[J%)K[L#'M[NBj 8<j .2j 37j 04j /3j (,j 6:j 6:j 8DH?j @ Aj BHLCj H)-Ij J%)Kj L#'Mj N>     )@@     '>>     '>>     (??     &== OO  rfcV^8dQhRR/#)r_r`r+ra)rbs"rcrdrv sFF6Frfc @\VPP4#rh)r+rrlrjs&rcrl$ResponsesWithRawResponse.input_itemsu s()D)DEErfcV^8dQhRR/#)r_r`r5ra)rbs"rcrdrz sHH8Hrfc @\VPP4#rh)r5rrprjs&rcrp%ResponsesWithRawResponse.input_tokensy s)$//*F*FGGrfrrUr_rrLrrN rkrlrmrnrr#rlrprorarfrcrsrs^ s3 ,FFHHrfrscN]tRtRtRRlt]RRl4t]RRl4tRtR #) ryi~ c V^8dQhRRRR/#r_rr[r`rBra)rbs"rcrd*AsyncResponsesWithRawResponse.__annotate__ s  . T rfc Wn\P!VP4Vn\P!VP4Vn\P!VP 4Vn\P!VP 4Vn\P!VP4Vn\P!VP4VnR#rh) rrasync_to_raw_response_wrapperrrrLrUr_rrs&&rcr&AsyncResponsesWithRawResponse.__init__ s#&DD     )FF     'DD     'DD     (EE     &CC OO  rfcV^8dQhRR/#)r_r`r,ra)rbs"rcrdr sKK;Krfc @\VPP4#rh)r,rrlrjs&rcrl)AsyncResponsesWithRawResponse.input_items s-doo.I.IJJrfcV^8dQhRR/#)r_r`r6ra)rbs"rcrdr sMM=Mrfc @\VPP4#rh)r6rrprjs&rcrp*AsyncResponsesWithRawResponse.input_tokens s.t/K/KLLrfrNrrarfrcryry~ s3 ,KKMMrfrycN]tRtRtRRlt]RRl4t]RRl4tRtR #) ryi c V^8dQhRRRR/#rra)rbs"rcrd+ResponsesWithStreamingResponse.__annotate__ s  )  rfc Wn\VP4Vn\VP4Vn\VP4Vn\VP 4Vn\VP 4VnR#rh)rr'rrrLrUr_rs&&rcr'ResponsesWithStreamingResponse.__init__ sx#2     5     3     3     4     rfcV^8dQhRR/#)r_r`r-ra)rbs"rcrdr sLL<Lrfc @\VPP4#rh)r-rrlrjs&rcrl*ResponsesWithStreamingResponse.input_items s.t/J/JKKrfcV^8dQhRR/#)r_r`r7ra)rbs"rcrdr sNN>Nrfc @\VPP4#rh)r7rrprjs&rcrp+ResponsesWithStreamingResponse.input_tokens s/0L0LMMrfrrUr_rrLrNrrarfrcryry s3 &LLNNrfrycN]tRtRtRRlt]RRl4t]RRl4tRtR #) r}i c V^8dQhRRRR/#rra)rbs"rcrd0AsyncResponsesWithStreamingResponse.__annotate__ s  . T rfc Wn\VP4Vn\VP4Vn\VP4Vn\VP 4Vn\VP 4VnR#rh)rr(rrrLrUr_rs&&rcr,AsyncResponsesWithStreamingResponse.__init__ sx#8     ;     9     9     :     rfcV^8dQhRR/#)r_r`r.ra)rbs"rcrdr sQQAQrfc @\VPP4#rh)r.rrlrjs&rcrl/AsyncResponsesWithStreamingResponse.input_items s3DOO4O4OPPrfcV^8dQhRR/#)r_r`r8ra)rbs"rcrdr sSSCSrfc @\VPP4#rh)r8rrprjs&rcrp0AsyncResponsesWithStreamingResponse.input_tokens s4T__5Q5QRRrfrNrrarfrcr}r} s3 &QQSSrfr}c V^8dQhRRRR/#)r_rrr`zList[ToolParam] | Omitra)rbs"rcrdrd s##:#?U#rfc,\V4'g\#.pVFpVR,R8wdVPV4K$RV9dVPV4K>\\V4R,p\ V\ 4'g \R4hRV9gQh\RRRVR,RVPR4RVR,RVPR4;'gR/VP4pVPVP44K V#)typefunctionzcExpected Chat Completions function tool shape to be created using `openai.pydantic_function_tool()` parametersname descriptionstrictF) rrappendrrrr1 Exceptionr2getr)rconverted_toolstoolrnew_tools& rcrr s E?? ')O <: %  " "4 (  T !  " "4 ( T?:.($899u x'''0 (x||M:h|4(,,x099E   NN   x}}/9< rfc]tRtRt$RtR]R&R]R&RRltR R ltR R ltR Rlt RRlt RRRR/RRllt RRlt Rt R#)AsyncResponsesConnectioni ;Represents a live WebSocket connection to the Responses APIAsyncResponsesResponseResourcerAsyncWebSocketConnection _connectionc V^8dQhRRRR/#)r_ connectionrr`rBra)rbs"rcrd%AsyncResponsesConnection.__annotate__s==#;==rfc 2Wn\V4VnR#rh)rrrrkrs&&rcr!AsyncResponsesConnection.__init__s%6t< rfcV^8dQhRR/#)r_r`z#AsyncIterator[ResponsesServerEvent]ra)rbs"rcrdr s  !D rfc t"^RIHpVP4GRjxL 5xKL TdR#i;i5izY An infinite-iterator that will continue to yield events until the connection is closed. )ConnectionClosedOKNwebsockets.exceptionsrrecvrkrs& rc __aiter__"AsyncResponsesConnection.__aiter__ s5 =  IIK'''!   s 8*( *5858cV^8dQhRR/#r_r`rSra)rbs"rcrdrs9909rfc \"TPVP4GRjxL 4#L5i) Receive the next message from the connection and parses it into a `ResponsesServerEvent` object. Canceling this method is safe. There's no risk of losing data. N parse_event recv_bytesrjs&rcrAsyncResponsesConnection.recvs% doo&7 788 7s ,* ,cV^8dQhRR/#r_r`bytesra)rbs"rcrdrs  % rfc "VPPRR7GRjxL p\PRV4V#L5i)Receive the next message from the connection as raw bytes. Canceling this method is safe. There's no risk of losing data. If you want to parse the message into a `ResponsesServerEvent` object like `.recv()` does, then you can call `.parse_event(data)`. FdecodeNReceived WebSocket message: %srrr\debugrkmessages& rcr#AsyncResponsesConnection.recv_bytess<((--U-;; 2W=&B7B8BBcodereasonc$V^8dQhRRRRRR/#r_r:intr<rr`rBra)rbs"rcrdr3s!??3?s?D?rfc Z"VPPWR7GRjxL R#L5i)r:r<Nrcloserkr:r<s&$$rcrDAsyncResponsesConnection.close3s"$$$$>>>s +)+c V^8dQhRRRR/#r_r8z str | bytesr`rSra)rbs"rcrdr6    0D  rfc  \\\\P!V4\\ \4R74#z Converts a raw `str` or `bytes` message into a `ResponsesServerEvent` object. This is helpful if you're using `.recv_bytes()`. )valuetype_rrSr$r4loadsrrkr8s&&rcr$AsyncResponsesConnection.parse_event6/  $4::d+;4MaCb c  rfrrN)rkrlrmrn__doc____annotations__rrrrr6rDrrorarfrcrr sGE,,))= 9 *??R?   rfrcN]tRtRtRtRRltRRlt]tRRltR R lt R t R #) riBa Context manager over a `AsyncResponsesConnection` that is returned by `responses.connect()` This context manager ensures that the connection will be closed when it exits. --- Note that if your application doesn't work well with the context manager approach then you can call the `.enter()` method directly to initiate a connection. **Warning**: You must remember to close the connection with `.close()`. ```py connection = await client.responses.connect(...).enter() # ... await connection.close() ``` c ,V^8dQhRRRRRRRRR R /#) r_rfrYrrrrrbrLr`rBra)rbs"rcrd,AsyncResponsesConnectionManager.__annotate__VsF K K K K  K 'A K  Krfc DWnRVnW nW0nW@nR#rh)(_AsyncResponsesConnectionManager__client,_AsyncResponsesConnectionManager__connection-_AsyncResponsesConnectionManager__extra_query/_AsyncResponsesConnectionManager__extra_headers>_AsyncResponsesConnectionManager__websocket_connection_optionsrkrfrrrbs&$$$$rcr(AsyncResponsesConnectionManager.__init__Vs# =A(,.J+rfcV^8dQhRR/#)r_r`rra)rbs"rcrdrXds*!*!":*!rfc "^RIHpTP 4P /TP PPCTPCR7p\PRT4TP'd!\PRTP4\T!\T43RTP PR\!/TP P"CTP$4/TPBGRjxL 4TnTP&# \dp\R4ThRp?ii;iL85i) u; 👋 If your application doesn't work well with the context manager approach then you can call this method directly to initiate a connection. **Warning**: You must remember to close the connection with `.close()`. ```py connection = await client.responses.connect(...).enter() # ... await connection.close() ``` rh9You need to install `openai[realtime]` to use this methodNparamsConnecting to %sConnection options: %suser_agent_headeradditional_headers)websockets.asyncio.clientrh ImportErrorr9 _prepare_url copy_withrZbase_urlrfr\r\r'r^rr user_agentr: auth_headersr]r[rkrhexcurls& rc __aenter__*AsyncResponsesConnectionManager.__aenter__ds5 d 9!++--((//$$,  $c*  . . . II.0S0S T4C "&--":": $3--44(( $ 55       7 dYZ`c c d s;D?DA3D?>BD?D=D? D:) D55D::D?cV^8dQhRR/#r_r`z httpx.URLra)rbs"rcrdrX ; ;i ;rfc VPPe,\P!VPP4pMQVPPP pVR8XdRMRpVPPP VR7pVPPR4R,pVP VR7#Nhttpwswss)scheme/s /responses)raw_path) rZwebsocket_base_urlhttpxURL _base_urlrrnrrstriprkror ws_schememerge_raw_paths& rcrm,AsyncResponsesConnectionManager._prepare_url == + + 7yy!A!ABH]],,33F && 0eI}}..88 8JH!**11$7-G!!>!::rfc(V^8dQhRRRRRRRR/# r_exc_typeztype[BaseException] | NonerszBaseException | Noneexc_tbzTracebackType | Noner`rBra)rbs"rcrdrXs,,,2,9M,Wk, ,rfc v"VPe%VPP4GRjxL R#R#L5irh)r[rDrkrrsrs&&&&rc __aexit__)AsyncResponsesConnectionManager.__aexit__s3    (##))+ + + ) +s ,97 9__client __connection__extra_headers __extra_query__websocket_connection_optionsN) rkrlrmrnrTrruenterrmrrorarfrcrrBs)& K*!X E ;,,rfrc]tRtRt$RtR]R&R]R&RRltR R ltR R ltR Rlt RRlt RRRR/RRllt RRlt Rt R#)ResponsesConnectionirResponsesResponseResourcerWebSocketConnectionrc V^8dQhRRRR/#)r_rrr`rBra)rbs"rcrd ResponsesConnection.__annotate__s88#6848rfc 2Wn\V4VnR#rh)rrrr s&&rcrResponsesConnection.__init__s%1$7 rfcV^8dQhRR/#)r_r`zIterator[ResponsesServerEvent]ra)rbs"rcrdrs  8 rfc# ^"^RIHpVP4xK TdR#i;i5irrrs& rc__iter__ResponsesConnection.__iter__s/ = iik!!   s-*-*-cV^8dQhRR/#rra)rbs"rcrdrs33*3rfc @VPVP44#)rrrjs&rcrResponsesConnection.recvs  122rfcV^8dQhRR/#rra)rbs"rcrdrs  E rfc jVPPRR7p\PRV4V#)r"Fr#r%r&r(s& rcrResponsesConnection.recv_bytess1""''u'5 2W=rfc V^8dQhRRRR/#r,ra)rbs"rcrdrs$$J$t$rfc \V\4'dVPRRRR7M#\P!\ V\ 44pVPPV4R#r/) rrr3r4r5r rVrr6r7s&& rcr6ResponsesConnection.sendsU%++ MMtSWM XOE3LMN d#rfr:r;r<r=c$V^8dQhRRRRRR/#r?ra)rbs"rcrdrs!99S99d9rfc >VPPWR7R#rBrCrEs&$$rcrDResponsesConnection.closes D8rfc V^8dQhRRRR/#rHra)rbs"rcrdrrIrfc  \\\\P!V4\\ \4R74#rKrNrPs&&rcrResponsesConnection.parse_eventrRrfrSN)rkrlrmrnrTrUrrrrr6rDrrorarfrcrrsGE''$$8 3 $949r9   rfrcN]tRtRtRtRRltRRlt]tRRltR R lt R t R #) rcia Context manager over a `ResponsesConnection` that is returned by `responses.connect()` This context manager ensures that the connection will be closed when it exits. --- Note that if your application doesn't work well with the context manager approach then you can call the `.enter()` method directly to initiate a connection. **Warning**: You must remember to close the connection with `.close()`. ```py connection = client.responses.connect(...).enter() # ... connection.close() ``` c ,V^8dQhRRRRRRRRR R /#) r_rfrXrrrrrbrLr`rBra)rbs"rcrd'ResponsesConnectionManager.__annotate__sF K K K K  K 'A K  Krfc DWnRVnW nW0nW@nR#rh)#_ResponsesConnectionManager__client'_ResponsesConnectionManager__connection(_ResponsesConnectionManager__extra_query*_ResponsesConnectionManager__extra_headers9_ResponsesConnectionManager__websocket_connection_optionsr_s&$$$$rcr#ResponsesConnectionManager.__init__s# 8<(,.J+rfcV^8dQhRR/#)r_r`rra)rbs"rcrdr s*!*!.*!rfc  f^RIHpTP 4P /TP PPCTPCR7p\PRT4TP'd!\PRTP4\T!\T43RTP PR\!/TP P"CTP$4/TPB4TnTP&# \dp\R4ThRp?ii;i) u/ 👋 If your application doesn't work well with the context manager approach then you can call this method directly to initiate a connection. **Warning**: You must remember to close the connection with `.close()`. ```py connection = client.responses.connect(...).enter() # ... connection.close() ``` rcrdNrergrhrirj)websockets.sync.clientrhrlr9rmrnrrorfrr\r'rrrrpr:rqrrrrs& rc __enter__$ResponsesConnectionManager.__enter__ s( d 6!++--((//$$,  $c*  . . . II.0S0S T/ C "&--":": $3--44(( $ 55      7 dYZ`c c dsD D0 D++D0cV^8dQhRR/#rxra)rbs"rcrdr8ryrfc VPPe,\P!VPP4pMQVPPP pVR8XdRMRpVPPP VR7pVPPR4R,pVP VR7#r{) rrrrrrrnrrrs& rcrm'ResponsesConnectionManager._prepare_url8rrfc(V^8dQhRRRRRRRR/#rra)rbs"rcrdrCs,&&2&9M&Wk& &rfc ZVPeVPP4R#R#rh)rrDrs&&&&rc__exit__#ResponsesConnectionManager.__exit__Cs'    (    # # % )rfrN) rkrlrmrnrTrrrrmrrorarfrcrcrcs)& K*!X E ;&&rfrcc"]tRtRtRRltRtR#)BaseResponsesConnectionResourceiJc V^8dQhRRRR/#)r_rrr`rBra)rbs"rcrd,BaseResponsesConnectionResource.__annotate__Ks&&4&rfc WnR#rhrr s&&rcr(BaseResponsesConnectionResource.__init__K%rfrNrkrlrmrnrrorarfrcrrJ &&rfrc:]tRtRtR]R]R]R]R]R]R]R ]R ]R ]R ]R ]R]R]R]R]R]R]R]R]R]R]R]R]R]R]R]R]R]/RR lltR!tR"#)#riOr~rrrrrrrrrrrrrrrrrrrrrrrrrrrrc<V^8dQhRRRRRRRRR R R R R RRRRRRRRRRR RRRRRRRRRRRR R!RR"RR#R$R%R&R'R(R)R*R+R,R-RR.R&R/R0R1RR2R3/#4r_r~rrzIOptional[Iterable[responses_client_event_param.ContextManagement]] | Omitrz:Optional[responses_client_event_param.Conversation] | Omitrrrrrrrrrrrrrrrrrrrrrrrrrrrrrz;Optional[responses_client_event_param.StreamOptions] | Omitrrrrrz.responses_client_event_param.ToolChoice | Omitrrrrrrrr`rBra)rbs"rcrd&ResponsesResponseResource.__annotate__PaG G *G f G Q G ; G 5G +G 0G -G ,G %G 3G 3G 5G %!G "!M#G $.%G &&'G (_)G *%+G ,&-G .T/G 0,1G 2-3G 4D5G 6*7G 8+9G :&;G <A=G >?G @ AG rfc" VPP\\\ /RRbRVbRVbRVbRVbRVbRVbRVbR VbR V bR V bR V bR V bRV bRVbRVbRVbRVRVRVRVRVRVRVRVRVRVRVRVRV/ C444R# rzresponse.creater~rrrrrrrrrrrrrrrrrrrrrrrrrrrrNrr6rrVr!rkr~rrrrrrrrrrrrrrrrrrrrrrrrrrrrs&$$$$$$$$$$$$$$$$$$$$$$$$$$$$$rcr ResponsesResponseResource.createPsIB  ) 1$j-.@'  "7    ' ,->).#H ./B/0D!&+,< 12H!"$Y#$,->&  &(.%{%{& $j=!$ & rfraNrkrlrmrnrrrorarfrcrrO\G -1G im G TX G >B G 8<G .2G 37G 04G /3G (,G 6:G 6:G 8<G (,!G "PT#G $15%G &)-'G (bf)G *(,+G ,)--G .W[/G 0/31G 2043G 4GK5G 6-17G 8.29G :)-;G <DH=G > ?G G rfrc"]tRtRtRRltRtR#)$BaseAsyncResponsesConnectionResourceic V^8dQhRRRR/#)r_rrr`rBra)rbs"rcrd1BaseAsyncResponsesConnectionResource.__annotate__s&&#;&&rfc WnR#rhrr s&&rcr-BaseAsyncResponsesConnectionResource.__init__rrfrNrrarfrcrrrrfrc:]tRtRtR]R]R]R]R]R]R]R ]R ]R ]R ]R ]R]R]R]R]R]R]R]R]R]R]R]R]R]R]R]R]R]/RR lltR!tR"#)#rir~rrrrrrrrrrrrrrrrrrrrrrrrrrrrc<V^8dQhRRRRRRRRR R R R R RRRRRRRRRRR RRRRRRRRRRRR R!RR"RR#R$R%R&R'R(R)R*R+R,R-RR.R&R/R0R1RR2R3/#rra)rbs"rcrd+AsyncResponsesResponseResource.__annotate__rrfc" $"VPP\\\ /RRbRVbRVbRVbRVbRVbRVbRVbR VbR V bR V bR V bR V bRV bRVbRVbRVbRVRVRVRVRVRVRVRVRVRVRVRVRV/ C444GRjxL R#L5irrrs&$$$$$$$$$$$$$$$$$$$$$$$$$$$$$rcr%AsyncResponsesResponseResource.createsVB## ) 1$j-.@'  "7    ' ,->).#H ./B/0D!&+,< 12H!"$Y#$,->&  &(.%{%{& $j=!$ & & & sBBBBraNrrarfrcrrrrfr)__conditional_annotations__ __future__rr4loggingrtypesrtypingrrrr r r r r rr functoolsrtyping_extensionsrrrpydanticrr=r_typesrrrrrrrrr_utilsrrr r!r"_compatr#_modelsr$ _resourcer%r& _responser'r(rlr)r*r+r,r-r. _streamingr/r0 lib._toolsr1r2rpr3r4r5r6r7r8 _exceptionsr9 _base_clientr:r;types.responsesr<r=r>r?lib._parsing._responsesr@rArBrtypes.responses.responserCtypes.responses.tool_paramrDrEtypes.shared_params.metadatarFtypes.shared_params.reasoningrGtypes.responses.parsed_responserH"lib.streaming.responses._responsesrIrJ"types.responses.compacted_responserK"types.websocket_connection_optionsrL#types.responses.response_includablerM#types.shared_params.responses_modelrN$types.responses.response_input_paramrO%types.responses.response_prompt_paramrP%types.responses.response_stream_eventrQ&types.responses.responses_client_eventrR&types.responses.responses_server_eventrS)types.responses.response_input_item_paramrT*types.responses.response_text_config_paramrU,types.responses.responses_client_event_paramrVrrWrrkrrirXrY__all__ getLoggerrkr\rUrZr[rsryryr}rrrrrcrrrr)rs@rcrs#" kkk/  ```ff&/:Y.M'A  1G46=cCLEAFHHJJOQUNV. ( )''1^1@ @ F4D %D N4HH@MM@NN:SS:#LA A H_,_,DA A H_&_&D&& H ?H V&& H %IH rf