Method createMessage

src/api/providers/requesty.ts:125–205

(
		systemPrompt: string,
		messages: Anthropic.Messages.MessageParam[],
		metadata?: ApiHandlerCreateMessageMetadata,
	)

	}

	override async *createMessage(
		systemPrompt: string,
		messages: Anthropic.Messages.MessageParam[],
		metadata?: ApiHandlerCreateMessageMetadata,
	): ApiStream {
		const {
			id: model,
			info,
			maxTokens: max_tokens,
			temperature,
			reasoningEffort: reasoning_effort,
			reasoning: thinking,
		} = await this.fetchModel()

		const openAiMessages: OpenAI.Chat.ChatCompletionMessageParam[] = [
			{ role: "system", content: systemPrompt },
			...convertToOpenAiMessages(messages),
		]

		// Map extended efforts to OpenAI Chat Completions-accepted values (omit unsupported)
		const allowedEffort = (["low", "medium", "high"] as const).includes(reasoning_effort as any)
			? (reasoning_effort as OpenAI.Chat.Completions.ChatCompletionCreateParamsStreaming["reasoning_effort"])
			: undefined

		const completionParams: RequestyChatCompletionParamsStreaming = {
			messages: openAiMessages,
			model,
			max_tokens,
			temperature,
			...(allowedEffort && { reasoning_effort: allowedEffort }),
			...(thinking && { thinking }),
			stream: true,
			stream_options: { include_usage: true },
			requesty: { trace_id: metadata?.taskId, extra: { mode: metadata?.mode } },
			tools: this.convertToolsForOpenAI(metadata?.tools),
			tool_choice: metadata?.tool_choice,
		}

		let stream
		try {
			// With streaming params type, SDK returns an async iterable stream
			stream = await this.client.chat.completions.create(completionParams)
		} catch (error) {
			throw handleOpenAIError(error, this.providerName)
		}
		let lastUsage: any = undefined

		for await (const chunk of stream) {
			const delta = chunk.choices[0]?.delta

			if (delta?.content) {
				yield { type: "text", text: delta.content }
			}

			const reasoningText = extractReasoningFromDelta(delta)
			if (reasoningText) {
				yield { type: "reasoning", text: reasoningText }
			}