h B8SSKJr SSKrSSKJrJrJrJr SSKJ r SSKJ r J r SSK r SSK Jr SS KJrJrJrJrJrJr SS KJrJrJrJrJr SS KJrJrJrJ r SS K!J"r" SS K#J$r$J%r% SSK&J'r'J(r( SSK)J*r*J+r+ SSK,J-r-J.r. SSK/J0r0J1r1 SSK2J3r3J4r4J5r5J6r6J7r7J8r8 SSK9J:r:J;r;JJ?r? SSK@JArA SSKBJCrC SSKDJErE SSKFJGrG SSKHJIrI SSKJJKrK SSKLJMrM SSKNJOrO SS/rP"SS\$5rQ"S S\%5rR"S!S"5rS"S#S$5rT"S%S&5rU"S'S(5rVg))) annotationsN)ListUnionIterableOptional)partial)Literaloverload)_legacy_response)Steps AsyncStepsStepsWithRawResponseAsyncStepsWithRawResponseStepsWithStreamingResponseAsyncStepsWithStreamingResponse) NOT_GIVENBodyQueryHeadersNotGiven)is_given required_argsmaybe_transformasync_maybe_transform)cached_property)SyncAPIResourceAsyncAPIResource)to_streamed_response_wrapper"async_to_streamed_response_wrapper)Stream AsyncStream)SyncCursorPageAsyncCursorPage)AsyncPaginatormake_request_options)AssistantEventHandlerAssistantEventHandlerTAssistantStreamManagerAsyncAssistantEventHandlerAsyncAssistantEventHandlerTAsyncAssistantStreamManager)run_list_paramsrun_create_paramsrun_update_paramsrun_submit_tool_outputs_params)Run) ChatModel)Metadata)ReasoningEffort)AssistantToolParam)AssistantStreamEvent)RunStepInclude)AssistantToolChoiceOptionParam)"AssistantResponseFormatOptionParamRuns AsyncRunsc \rSrSr\S1Sj5r\S2Sj5r\S3Sj5r\\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ SSS\ S.S4S jj5r \\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ SSS\ S .S5S jj5r \\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ SSS\ S .S6S jj5r \ "S/SS /5\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ SSS\ S.S7Sjj5r SSS\ S.S8Sjjr \ SSS\ S.S9Sjjr \ \ \ \ SSS\ S.S:SjjrSSS\ S.S8Sjjr\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ SSS\ S.S;Sjjr\\R$"S5\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ SSS\ S.SSjj5rSSS\ \ 4S?Sjjr\\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ SSS\ S .S@Sjj5r\\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ SSS\ S .SAS jj5r\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ SSSS\ S!.SBS"jjr\\ SSS\ S#.SCS%jj5r\SSS\ S.SDS&jj5r\SSS\ S.SES'jj5r\ "SS$//S(Q5\ SSS\ S#.SFS)jj5r\ SSS\ S*.SGS+jjr\SSS\ S.SHS,jj5r\SSS\ S.SIS-jj5rSSSS\ S..SJS/jjrS0rg)Kr;=c,[UR5$N)r_clientselfs Y/var/www/html/env/lib/python3.13/site-packages/openai/resources/beta/threads/runs/runs.pysteps Runs.steps>sT\\""c[U5$z This property can be used as a prefix for any HTTP method call to return the raw response object instead of the parsed content. For more information, see https://www.github.com/openai/openai-python#accessing-raw-response-data-eg-headers )RunsWithRawResponserBs rDwith_raw_responseRuns.with_raw_responseBs#4((rGc[U5$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 )RunsWithStreamingResponserBs rDwith_streaming_responseRuns.with_streaming_responseLs)..rGNincludeadditional_instructionsadditional_messages instructionsmax_completion_tokensmax_prompt_tokensmetadatamodelparallel_tool_callsreasoning_effortresponse_formatstream temperature tool_choicetoolstop_ptruncation_strategy extra_headers extra_query extra_bodytimeout thread_id assistant_idr^cga Create a run. Args: assistant_id: The ID of the [assistant](https://platform.openai.com/docs/api-reference/assistants) to use to execute this run. include: A list of additional fields to include in the response. Currently the only supported value is `step_details.tool_calls[*].file_search.results[*].content` to fetch the file search result content. See the [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings) for more information. additional_instructions: Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions. additional_messages: Adds additional messages to the thread before creating the run. instructions: Overrides the [instructions](https://platform.openai.com/docs/api-reference/assistants/createAssistant) of the assistant. This is useful for modifying the behavior on a per-run basis. max_completion_tokens: The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. max_prompt_tokens: The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. 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: The ID of the [Model](https://platform.openai.com/docs/api-reference/models) to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used. parallel_tool_calls: Whether to enable [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. reasoning_effort: **o-series models only** Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently supported values are `low`, `medium`, and `high`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. response_format: Specifies the format that the model must output. Compatible with [GPT-4o](https://platform.openai.com/docs/models#gpt-4o), [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs). Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the message the model generates is valid JSON. **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. stream: If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message. 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. tool_choice: Controls which (if any) tool is called by the model. `none` means the model will not call any tools and instead generates a message. `auto` is the default value and means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools before responding to the user. Specifying a particular tool like `{"type": "file_search"}` or `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. tools: Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis. 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_strategy: Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run. 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 NrCrhrirSrTrUrVrWrXrYrZr[r\r]r^r_r`rarbrcrdrerfrgs rDcreate Runs.createUh rGrSrTrUrVrWrXrYrZr[r\r]r_r`rarbrcrdrerfrgcga Create a run. Args: assistant_id: The ID of the [assistant](https://platform.openai.com/docs/api-reference/assistants) to use to execute this run. stream: If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message. include: A list of additional fields to include in the response. Currently the only supported value is `step_details.tool_calls[*].file_search.results[*].content` to fetch the file search result content. See the [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings) for more information. additional_instructions: Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions. additional_messages: Adds additional messages to the thread before creating the run. instructions: Overrides the [instructions](https://platform.openai.com/docs/api-reference/assistants/createAssistant) of the assistant. This is useful for modifying the behavior on a per-run basis. max_completion_tokens: The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. max_prompt_tokens: The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. 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: The ID of the [Model](https://platform.openai.com/docs/api-reference/models) to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used. parallel_tool_calls: Whether to enable [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. reasoning_effort: **o-series models only** Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently supported values are `low`, `medium`, and `high`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. response_format: Specifies the format that the model must output. Compatible with [GPT-4o](https://platform.openai.com/docs/models#gpt-4o), [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs). Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the message the model generates is valid JSON. **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. 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. tool_choice: Controls which (if any) tool is called by the model. `none` means the model will not call any tools and instead generates a message. `auto` is the default value and means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools before responding to the user. Specifying a particular tool like `{"type": "file_search"}` or `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. tools: Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis. 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_strategy: Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run. 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 NrlrCrhrir^rSrTrUrVrWrXrYrZr[r\r]r_r`rarbrcrdrerfrgs rDrnrorprGcgrsrlrts rDrnrorprGcU(d[SU<35eSS0U=(d 0EnURSUS3[0SU_SU_SU_S U_S U_S U_S U _S U _SU _SU _SU _SU_SU_SU_SU_SU_SU_U(a[RO[R 5[ UUUU[SU0[R5S9[U=(d S[[S9$N8Expected a non-empty value for `thread_id` but received OpenAI-Beta assistants=v2 /threads//runsrirTrUrVrWrXrYrZr[r\r]r^r_r`rarbrcrSrdrerfrgqueryFbodyoptionscast_tor^ stream_cls) ValueError_postrr/RunCreateParamsStreamingRunCreateParamsNonStreamingr'RunCreateParamsr2r"r7rms rDrnros<WXaWdef f&QM#L  ,-B  (): U*+>'(8&f";";U U!"*+>#&?E!::J[JwJw),)+'%%y'&: rG)rTrUrVrWrXrYrZr[r\r]r_r`rarbrcrrdrerfrgc U(d[SU<35eSSU(aSOSS.U=(d 0En[URSUS3[0S U_S U_S U_S U_S U_SU_SU_SU_SU _SU _SU _SS_SU_SU_SU _SU _SU_[R 5[ UUUUS9[S[[S9n[UU=(d [5S9$)rrxrzthreads.runs.create_and_streamtruefalseryzX-Stainless-Stream-Helperz X-Stainless-Custom-Event-Handlerr{r|rirTrUrVrWrXrYrZr]r_r`r^Trarcr[r\rbrrr rrrrr/rr'r2r"r7r*r()rCrirTrUrVrWrXrYrZr[r\r]r_r`rarbrcrhrrdrerfrg make_requests rDrrs<WXaWdef f+)I:GW "   JJ {% ( "L-/F*+>#L  ,-B  (): U&";";dU*+>*+> '(8!"U#&"11),)+Q[el23= @&l-BjShSjkkrGc SS0U=(d 0En[U5(a[U5US'1SknURRUUUUUUS9n U R 5n U R U;aU $[U5(d,U R RS5n U b [U 5nOSnURUS- 5 M) A helper to poll a run status until it reaches a terminal state. More information on Run lifecycles can be found here: https://platform.openai.com/docs/assistants/how-it-works/runs-and-run-steps X-Stainless-Poll-Helperr X-Stainless-Custom-Poll-Interval>failedexpired cancelled completed incompleterequires_actionrhrrdrfrergopenai-poll-after-ms rstrrKrparsestatusheadersgetint_sleep rCrrhrdrerfrgrterminal_statesresponser from_headers rDr Runs.polls3FT}?RPRT $ % %@CDT@UM< =j--66#+%' 7H.."Czz_, ,--&..223IJ *'*;'7$'+$ KK(4/ 0-rGcgrrl)rCrirSrTrUrVrWrXrYrZr[r\r]r_r`rarbrcrhrdrerfrgs rDr^ Runs.streamrrGcgrrlrCrirSrTrUrVrWrXrYrZr[r\r]r_r`rarbrcrhrrdrerfrgs rDr^r4rrGrSrTrUrVrWrXrYrZr[r\r]r_r`rarbrcrrdrerfrgcU(d[SU<35eSSU(aSOSS.U=(d 0En[URSUS3[0S U_S U_S U_S U_S U_SU_SU_SU _SU _SU _SU_SS_SU_SU _SU _SU_SU_[R 5[ UUUU[SU0[R 5S9[S[[S9n[UU=(d [5S9$rrxrzrrrrr{r|rirTrUrVrWrXrYrZr]r_r`r^Trar[r\rcrbrSr}rrr)rCrirSrTrUrVrWrXrYrZr[r\r]r_r`rarbrcrhrrdrerfrgrs rDr^rUs<WXaWdef f+)I:GW "   JJ {% ( "L-/F*+>#L  ,-B  (): U&";";dU*+>'(8 *+>!"U#&"11),)+'%%y'&:)0rirrSr rTr!rUr"rVr!rWr#rXr#rYr$rZr%r[r&r\r'r]r(r_r*r`r+rar,rbr*rcr-rhrrr?rdr.rer/rfr0rgr1rr@rrrhrr3Iterable[run_submit_tool_outputs_params.ToolOutput]r^r)rdr.rer/rfr0rgr1rr2)rrrhrr^r2rrCrdr.rer/rfr0rgr1rr3)rrrhrr^r4rrCrdr.rer/rfr0rgr1rr5)rrrhrrrCr^r6rdr.rer/rfr0rgr1rr5rrCrrrhrrr:rdr.rer/rfr0rgr1rr2)rrCrrrhrrdr.rer/rfr0rgr1rr=)rrCrrrhrrr)rdr.rer/rfr0rgr1rr>)rrCrrrhrrr?rdr.rer/rfr0rgr1rr@__name__ __module__ __qualname____firstlineno__rrErKrPr rrnrrrrrrtyping_extensions deprecatedrrr^rr r__static_attributes__rlrGrDr;r;=sC##))// 4=!!"89 =Fbk1::C6?2;8A/8AJS\2;KTCL,5Yb7;)-$("&;D5FlFl": Fl ` Fl / Fl 8Fl4Fl0Fl6Fl-Fl?FlQFl0FlIFl A!Fl"*#Fl$W%Fl&'Fl(5)Fl.&/Fl0"1Fl2 3Fl495Fl6 h7Fl:FlX)-$("&;D+4+1+1+1& +1 " +1  +19+1)+1 +1Z 4= 4=Sjj55r\R$"S5\ \ \ \ \ \ \ \ \ \ \ \ \ \ SSSS\ S.S?Sjj5rSSS\ \ 4S@Sjjr\\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ SSS\ S.SAS jj5r\\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ SSS\ S .SBS!jj5r\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ SSSS\ S".SCS#jjr\\ SSS\ S$.SDS&jj5r\SSS\ S.SES'jj5r\SSS\ S.SFS(jj5r\ "SS%//S)Q5\ SSS\ S$.SGS*jj5r\ SSS\ S+.SHS,jjr\SSS\ S.SIS-jj5r\SSS\ S.SJS.jj5rSSSS\ S/.SKS0jjrS1rg)Lr<ic,[UR5$r@)rrArBs rDrEAsyncRuns.stepss$,,''rGc[U5$rI)AsyncRunsWithRawResponserBs rDrKAsyncRuns.with_raw_responses(--rGc[U5$rN)AsyncRunsWithStreamingResponserBs rDrP!AsyncRuns.with_streaming_responses.d33rGNrRrhrir^c # g7frkrlrms rDrnAsyncRuns.create h rqc # g7frsrlrts rDrnrWnrXrYc # g7frsrlrts rDrnrWrXrYc# U(d[SU<35eSS0U=(d 0EnURSUS3[0SU_SU_SU_S U_S U_S U_S U _S U _SU _SU _SU _SU_SU_SU_SU_SU_SU_U(a[RO[R 5IShvN [ UUUU[SU0[R5IShvN S9[U=(d S[[S9IShvN $NWN-N7frw) rrrr/rrr'rr2r#r7rms rDrnrWs<WXaWdef f&QM#L  ,-B  (): U*+>'(8&f";";U U!"*+>#&?E!::J[JwJw),)+'%19g2FHYHiHijj ?U"#78C " " " 6k;" s6BC=C7 +C= C9 &C=2C;3C=9C=;C=rc # U(d[SU<35eU(d[SU<35eSS0U=(d 0EnURSUSU3[X4XVS9[S9IS hvN $N7f) rrxrryrzr{rrrNrrs rDrAsyncRuns.retrieves0WXaWdef fTU[T^_` `&QM#L  ,-B  (): U&";";dU*+>U *+>!$"11'*)+Q[el"#789 <+7-BoSmSopprGc # SS0U=(d 0En[U5(a[U5US'1SknURRUUUUUUS9IShvN n U R 5n U R U;aU $[U5(d,U R RS5n U b [U 5nOSnURUS- 5IShvN MNN7f) rrrr>rrrrrrrNrrrrs rDrAsyncRuns.pollh s3FT}?RPRT $ % %@CDT@UM< =j!33<<#+%' =H.."Czz_, ,--&..223IJ *'*;'7$'+$++.56 6 6-* 7s%ACCA9CCCCrcgrrlrs rDr^AsyncRuns.stream rirGcgrrlrs rDr^rp rrGrcU(d[SU<35eSSU(aSOSS.U=(d 0EnURSUS3[0S U_S U_S U_S U_S U_SU_SU_SU _SU _SU _SU_SS_SU_SU _SU _SU_SU_[R5[ UUUU[SU0[R5S9[ S[[S9n[UU=(d [5S9$rrl)rCrirSrTrUrVrWrXrYrZr[r\r]r_r`rarbrcrhrrdrerfrgrs rDr^rp sBWXaWdef f+)I:GW "  ** {% ( "L-/F*+>#L  ,-B  (): U&";";dU*+>'(8 *+>!"U#&"11),)+'%%y'&:> KK  )@@ MM  '>> KK  %<< II  '>> KK  $4#K#K  $ $$  rGc@[URR5$r@)rrrErBs rDrERunsWithRawResponse.steps[ s#DJJ$4$455rGrrrnrrrrNrr;rNone)rrrFrGrHrIrrrErLrlrGrDrJrJD s ,66rGrJc2\rSrSrSSjr\SSj5rSrg)rQi` cXl[R"UR5Ul[R"UR5Ul[R"UR 5Ul[R"UR 5Ul[R"UR5Ul[R"UR5Ulgr@) rr async_to_raw_response_wrapperrnrrrrrrs rDr!AsyncRunsWithRawResponse.__init__a s &DD KK  )FF MM  'DD KK  %BB II  'DD KK  $4#Q#Q  $ $$  rGc@[URR5$r@)rrrErBs rDrEAsyncRunsWithRawResponse.stepsw s()9)9::rGrNrr<rr)rrrrlrGrDrQrQ` s ,;;rGrQc2\rSrSrSSjr\SSj5rSrg)rOi| cHXl[UR5Ul[UR5Ul[UR5Ul[UR 5Ul[UR 5Ul[UR5Ulgr@)rr rnrrrrrrs rDr"RunsWithStreamingResponse.__init__} s 2 KK  5 MM  3 KK  1 II  3 KK  $@  $ $$  rGc@[URR5$r@)rrrErBs rDrERunsWithStreamingResponse.steps s)$***:*:;;rGrNr)rrrrlrGrDrOrO| s ,<rs#22/ "BA )<[/;B ,26>CGH]e ; @g?@gF,Aq AqH,668;;8<<8AArG