@pencil-agent/nano-pencil 2.0.0-beta.2 → 2.0.0-beta.3

package/dist/node_modules/@pencil-agent/ai/dist/providers/openai-responses-shared.d.ts

@@ -0,0 +1,22 @@
+/**
+ * [WHO]: OpenAIResponsesStreamOptions, ConvertResponsesMessagesOptions, ConvertResponsesToolsOptions, convertResponsesMessages, convertResponsesTools
+ * [FROM]: Depends on ../models.js, ../utils/json-parse.js, ../utils/sanitize-unicode.js, ./transform-messages.js
+ * [TO]: Consumed by core/lib/ai/src/index.ts
+ * [HERE]: core/lib/ai/src/providers/openai-responses-shared.ts -
+ */
+import type { Tool as OpenAITool, ResponseCreateParamsStreaming, ResponseInput, ResponseStreamEvent } from "openai/resources/responses/responses.js";
+import type { Api, AssistantMessage, Context, Model, Tool, Usage } from "../types.js";
+import type { AssistantMessageEventStream } from "../utils/event-stream.js";
+export interface OpenAIResponsesStreamOptions {
+    serviceTier?: ResponseCreateParamsStreaming["service_tier"];
+    applyServiceTierPricing?: (usage: Usage, serviceTier: ResponseCreateParamsStreaming["service_tier"] | undefined) => void;
+}
+export interface ConvertResponsesMessagesOptions {
+    includeSystemPrompt?: boolean;
+}
+export interface ConvertResponsesToolsOptions {
+    strict?: boolean | null;
+}
+export declare function convertResponsesMessages<TApi extends Api>(model: Model<TApi>, context: Context, allowedToolCallProviders: ReadonlySet<string>, options?: ConvertResponsesMessagesOptions): ResponseInput;
+export declare function convertResponsesTools(tools: Tool[], options?: ConvertResponsesToolsOptions): OpenAITool[];
+export declare function processResponsesStream<TApi extends Api>(openaiStream: AsyncIterable<ResponseStreamEvent>, output: AssistantMessage, stream: AssistantMessageEventStream, model: Model<TApi>, options?: OpenAIResponsesStreamOptions): Promise<void>;

package/dist/node_modules/@pencil-agent/ai/dist/providers/openai-responses-shared.js

@@ -0,0 +1,432 @@
+/**
+ * [WHO]: OpenAIResponsesStreamOptions, ConvertResponsesMessagesOptions, ConvertResponsesToolsOptions, convertResponsesMessages, convertResponsesTools
+ * [FROM]: Depends on ../models.js, ../utils/json-parse.js, ../utils/sanitize-unicode.js, ./transform-messages.js
+ * [TO]: Consumed by core/lib/ai/src/index.ts
+ * [HERE]: core/lib/ai/src/providers/openai-responses-shared.ts -
+ */
+import { calculateCost } from "../models.js";
+import { parseStreamingJson } from "../utils/json-parse.js";
+import { sanitizeSurrogates } from "../utils/sanitize-unicode.js";
+import { transformMessages } from "./transform-messages.js";
+// =============================================================================
+// Utilities
+// =============================================================================
+/** Fast deterministic hash to shorten long strings */
+function shortHash(str) {
+    let h1 = 0xdeadbeef;
+    let h2 = 0x41c6ce57;
+    for (let i = 0; i < str.length; i++) {
+        const ch = str.charCodeAt(i);
+        h1 = Math.imul(h1 ^ ch, 2654435761);
+        h2 = Math.imul(h2 ^ ch, 1597334677);
+    }
+    h1 = Math.imul(h1 ^ (h1 >>> 16), 2246822507) ^ Math.imul(h2 ^ (h2 >>> 13), 3266489909);
+    h2 = Math.imul(h2 ^ (h2 >>> 16), 2246822507) ^ Math.imul(h1 ^ (h1 >>> 13), 3266489909);
+    return (h2 >>> 0).toString(36) + (h1 >>> 0).toString(36);
+}
+// =============================================================================
+// Message conversion
+// =============================================================================
+export function convertResponsesMessages(model, context, allowedToolCallProviders, options) {
+    const messages = [];
+    const normalizeToolCallId = (id) => {
+        if (!allowedToolCallProviders.has(model.provider))
+            return id;
+        if (!id.includes("|"))
+            return id;
+        const [callId, itemId] = id.split("|");
+        const sanitizedCallId = callId.replace(/[^a-zA-Z0-9_-]/g, "_");
+        let sanitizedItemId = itemId.replace(/[^a-zA-Z0-9_-]/g, "_");
+        // OpenAI Responses API requires item id to start with "fc"
+        if (!sanitizedItemId.startsWith("fc")) {
+            sanitizedItemId = `fc_${sanitizedItemId}`;
+        }
+        // Truncate to 64 chars and strip trailing underscores (OpenAI Codex rejects them)
+        let normalizedCallId = sanitizedCallId.length > 64 ? sanitizedCallId.slice(0, 64) : sanitizedCallId;
+        let normalizedItemId = sanitizedItemId.length > 64 ? sanitizedItemId.slice(0, 64) : sanitizedItemId;
+        normalizedCallId = normalizedCallId.replace(/_+$/, "");
+        normalizedItemId = normalizedItemId.replace(/_+$/, "");
+        return `${normalizedCallId}|${normalizedItemId}`;
+    };
+    const transformedMessages = transformMessages(context.messages, model, normalizeToolCallId);
+    const includeSystemPrompt = options?.includeSystemPrompt ?? true;
+    if (includeSystemPrompt && context.systemPrompt) {
+        const role = model.reasoning ? "developer" : "system";
+        messages.push({
+            role,
+            content: sanitizeSurrogates(context.systemPrompt),
+        });
+    }
+    let msgIndex = 0;
+    for (const msg of transformedMessages) {
+        if (msg.role === "user") {
+            if (typeof msg.content === "string") {
+                messages.push({
+                    role: "user",
+                    content: [{ type: "input_text", text: sanitizeSurrogates(msg.content) }],
+                });
+            }
+            else {
+                const content = msg.content.map((item) => {
+                    if (item.type === "text") {
+                        return {
+                            type: "input_text",
+                            text: sanitizeSurrogates(item.text),
+                        };
+                    }
+                    return {
+                        type: "input_image",
+                        detail: "auto",
+                        image_url: `data:${item.mimeType};base64,${item.data}`,
+                    };
+                });
+                const filteredContent = !model.input.includes("image")
+                    ? content.filter((c) => c.type !== "input_image")
+                    : content;
+                if (filteredContent.length === 0)
+                    continue;
+                messages.push({
+                    role: "user",
+                    content: filteredContent,
+                });
+            }
+        }
+        else if (msg.role === "assistant") {
+            const output = [];
+            const assistantMsg = msg;
+            const isDifferentModel = assistantMsg.model !== model.id &&
+                assistantMsg.provider === model.provider &&
+                assistantMsg.api === model.api;
+            for (const block of msg.content) {
+                if (block.type === "thinking") {
+                    if (block.thinkingSignature) {
+                        const reasoningItem = JSON.parse(block.thinkingSignature);
+                        output.push(reasoningItem);
+                    }
+                }
+                else if (block.type === "text") {
+                    const textBlock = block;
+                    // OpenAI requires id to be max 64 characters
+                    let msgId = textBlock.textSignature;
+                    if (!msgId) {
+                        msgId = `msg_${msgIndex}`;
+                    }
+                    else if (msgId.length > 64) {
+                        msgId = `msg_${shortHash(msgId)}`;
+                    }
+                    output.push({
+                        type: "message",
+                        role: "assistant",
+                        content: [{ type: "output_text", text: sanitizeSurrogates(textBlock.text), annotations: [] }],
+                        status: "completed",
+                        id: msgId,
+                    });
+                }
+                else if (block.type === "toolCall") {
+                    const toolCall = block;
+                    const [callId, itemIdRaw] = toolCall.id.split("|");
+                    let itemId = itemIdRaw;
+                    // For different-model messages, set id to undefined to avoid pairing validation.
+                    // OpenAI tracks which fc_xxx IDs were paired with rs_xxx reasoning items.
+                    // By omitting the id, we avoid triggering that validation (like cross-provider does).
+                    if (isDifferentModel && itemId?.startsWith("fc_")) {
+                        itemId = undefined;
+                    }
+                    output.push({
+                        type: "function_call",
+                        id: itemId,
+                        call_id: callId,
+                        name: toolCall.name,
+                        arguments: JSON.stringify(toolCall.arguments),
+                    });
+                }
+            }
+            if (output.length === 0)
+                continue;
+            messages.push(...output);
+        }
+        else if (msg.role === "toolResult") {
+            // Extract text and image content
+            const textResult = msg.content
+                .filter((c) => c.type === "text")
+                .map((c) => c.text)
+                .join("\n");
+            const hasImages = msg.content.some((c) => c.type === "image");
+            // Always send function_call_output with text (or placeholder if only images)
+            const hasText = textResult.length > 0;
+            const [callId] = msg.toolCallId.split("|");
+            messages.push({
+                type: "function_call_output",
+                call_id: callId,
+                output: sanitizeSurrogates(hasText ? textResult : "(see attached image)"),
+            });
+            // If there are images and model supports them, send a follow-up user message with images
+            if (hasImages && model.input.includes("image")) {
+                const contentParts = [];
+                // Add text prefix
+                contentParts.push({
+                    type: "input_text",
+                    text: "Attached image(s) from tool result:",
+                });
+                // Add images
+                for (const block of msg.content) {
+                    if (block.type === "image") {
+                        contentParts.push({
+                            type: "input_image",
+                            detail: "auto",
+                            image_url: `data:${block.mimeType};base64,${block.data}`,
+                        });
+                    }
+                }
+                messages.push({
+                    role: "user",
+                    content: contentParts,
+                });
+            }
+        }
+        msgIndex++;
+    }
+    return messages;
+}
+// =============================================================================
+// Tool conversion
+// =============================================================================
+export function convertResponsesTools(tools, options) {
+    const strict = options?.strict === undefined ? false : options.strict;
+    return tools.map((tool) => ({
+        type: "function",
+        name: tool.name,
+        description: tool.description,
+        parameters: tool.parameters, // TypeBox already generates JSON Schema
+        strict,
+    }));
+}
+// =============================================================================
+// Stream processing
+// =============================================================================
+export async function processResponsesStream(openaiStream, output, stream, model, options) {
+    let currentItem = null;
+    let currentBlock = null;
+    const blocks = output.content;
+    const blockIndex = () => blocks.length - 1;
+    for await (const event of openaiStream) {
+        if (event.type === "response.output_item.added") {
+            const item = event.item;
+            if (item.type === "reasoning") {
+                currentItem = item;
+                currentBlock = { type: "thinking", thinking: "" };
+                output.content.push(currentBlock);
+                stream.push({ type: "thinking_start", contentIndex: blockIndex(), partial: output });
+            }
+            else if (item.type === "message") {
+                currentItem = item;
+                currentBlock = { type: "text", text: "" };
+                output.content.push(currentBlock);
+                stream.push({ type: "text_start", contentIndex: blockIndex(), partial: output });
+            }
+            else if (item.type === "function_call") {
+                currentItem = item;
+                currentBlock = {
+                    type: "toolCall",
+                    id: `${item.call_id}|${item.id}`,
+                    name: item.name,
+                    arguments: {},
+                    partialJson: item.arguments || "",
+                };
+                output.content.push(currentBlock);
+                stream.push({ type: "toolcall_start", contentIndex: blockIndex(), partial: output });
+            }
+        }
+        else if (event.type === "response.reasoning_summary_part.added") {
+            if (currentItem && currentItem.type === "reasoning") {
+                currentItem.summary = currentItem.summary || [];
+                currentItem.summary.push(event.part);
+            }
+        }
+        else if (event.type === "response.reasoning_summary_text.delta") {
+            if (currentItem?.type === "reasoning" && currentBlock?.type === "thinking") {
+                currentItem.summary = currentItem.summary || [];
+                const lastPart = currentItem.summary[currentItem.summary.length - 1];
+                if (lastPart) {
+                    currentBlock.thinking += event.delta;
+                    lastPart.text += event.delta;
+                    stream.push({
+                        type: "thinking_delta",
+                        contentIndex: blockIndex(),
+                        delta: event.delta,
+                        partial: output,
+                    });
+                }
+            }
+        }
+        else if (event.type === "response.reasoning_summary_part.done") {
+            if (currentItem?.type === "reasoning" && currentBlock?.type === "thinking") {
+                currentItem.summary = currentItem.summary || [];
+                const lastPart = currentItem.summary[currentItem.summary.length - 1];
+                if (lastPart) {
+                    currentBlock.thinking += "\n\n";
+                    lastPart.text += "\n\n";
+                    stream.push({
+                        type: "thinking_delta",
+                        contentIndex: blockIndex(),
+                        delta: "\n\n",
+                        partial: output,
+                    });
+                }
+            }
+        }
+        else if (event.type === "response.content_part.added") {
+            if (currentItem?.type === "message") {
+                currentItem.content = currentItem.content || [];
+                // Filter out ReasoningText, only accept output_text and refusal
+                if (event.part.type === "output_text" || event.part.type === "refusal") {
+                    currentItem.content.push(event.part);
+                }
+            }
+        }
+        else if (event.type === "response.output_text.delta") {
+            if (currentItem?.type === "message" && currentBlock?.type === "text") {
+                if (!currentItem.content || currentItem.content.length === 0) {
+                    continue;
+                }
+                const lastPart = currentItem.content[currentItem.content.length - 1];
+                if (lastPart?.type === "output_text") {
+                    currentBlock.text += event.delta;
+                    lastPart.text += event.delta;
+                    stream.push({
+                        type: "text_delta",
+                        contentIndex: blockIndex(),
+                        delta: event.delta,
+                        partial: output,
+                    });
+                }
+            }
+        }
+        else if (event.type === "response.refusal.delta") {
+            if (currentItem?.type === "message" && currentBlock?.type === "text") {
+                if (!currentItem.content || currentItem.content.length === 0) {
+                    continue;
+                }
+                const lastPart = currentItem.content[currentItem.content.length - 1];
+                if (lastPart?.type === "refusal") {
+                    currentBlock.text += event.delta;
+                    lastPart.refusal += event.delta;
+                    stream.push({
+                        type: "text_delta",
+                        contentIndex: blockIndex(),
+                        delta: event.delta,
+                        partial: output,
+                    });
+                }
+            }
+        }
+        else if (event.type === "response.function_call_arguments.delta") {
+            if (currentItem?.type === "function_call" && currentBlock?.type === "toolCall") {
+                currentBlock.partialJson += event.delta;
+                currentBlock.arguments = parseStreamingJson(currentBlock.partialJson);
+                stream.push({
+                    type: "toolcall_delta",
+                    contentIndex: blockIndex(),
+                    delta: event.delta,
+                    partial: output,
+                });
+            }
+        }
+        else if (event.type === "response.function_call_arguments.done") {
+            if (currentItem?.type === "function_call" && currentBlock?.type === "toolCall") {
+                currentBlock.partialJson = event.arguments;
+                currentBlock.arguments = parseStreamingJson(currentBlock.partialJson);
+            }
+        }
+        else if (event.type === "response.output_item.done") {
+            const item = event.item;
+            if (item.type === "reasoning" && currentBlock?.type === "thinking") {
+                currentBlock.thinking = item.summary?.map((s) => s.text).join("\n\n") || "";
+                currentBlock.thinkingSignature = JSON.stringify(item);
+                stream.push({
+                    type: "thinking_end",
+                    contentIndex: blockIndex(),
+                    content: currentBlock.thinking,
+                    partial: output,
+                });
+                currentBlock = null;
+            }
+            else if (item.type === "message" && currentBlock?.type === "text") {
+                currentBlock.text = item.content.map((c) => (c.type === "output_text" ? c.text : c.refusal)).join("");
+                currentBlock.textSignature = item.id;
+                stream.push({
+                    type: "text_end",
+                    contentIndex: blockIndex(),
+                    content: currentBlock.text,
+                    partial: output,
+                });
+                currentBlock = null;
+            }
+            else if (item.type === "function_call") {
+                const args = currentBlock?.type === "toolCall" && currentBlock.partialJson
+                    ? parseStreamingJson(currentBlock.partialJson)
+                    : parseStreamingJson(item.arguments || "{}");
+                const toolCall = {
+                    type: "toolCall",
+                    id: `${item.call_id}|${item.id}`,
+                    name: item.name,
+                    arguments: args,
+                };
+                currentBlock = null;
+                stream.push({ type: "toolcall_end", contentIndex: blockIndex(), toolCall, partial: output });
+            }
+        }
+        else if (event.type === "response.completed") {
+            const response = event.response;
+            if (response?.usage) {
+                const cachedTokens = response.usage.input_tokens_details?.cached_tokens || 0;
+                output.usage = {
+                    // OpenAI includes cached tokens in input_tokens, so subtract to get non-cached input
+                    input: (response.usage.input_tokens || 0) - cachedTokens,
+                    output: response.usage.output_tokens || 0,
+                    cacheRead: cachedTokens,
+                    cacheWrite: 0,
+                    totalTokens: response.usage.total_tokens || 0,
+                    cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },
+                };
+            }
+            calculateCost(model, output.usage);
+            if (options?.applyServiceTierPricing) {
+                const serviceTier = response?.service_tier ?? options.serviceTier;
+                options.applyServiceTierPricing(output.usage, serviceTier);
+            }
+            // Map status to stop reason
+            output.stopReason = mapStopReason(response?.status);
+            if (output.content.some((b) => b.type === "toolCall") && output.stopReason === "stop") {
+                output.stopReason = "toolUse";
+            }
+        }
+        else if (event.type === "error") {
+            throw new Error(`Error Code ${event.code}: ${event.message}` || "Unknown error");
+        }
+        else if (event.type === "response.failed") {
+            throw new Error("Unknown error");
+        }
+    }
+}
+function mapStopReason(status) {
+    if (!status)
+        return "stop";
+    switch (status) {
+        case "completed":
+            return "stop";
+        case "incomplete":
+            return "length";
+        case "failed":
+        case "cancelled":
+            return "error";
+        // These two are wonky ...
+        case "in_progress":
+        case "queued":
+            return "stop";
+        default: {
+            const _exhaustive = status;
+            throw new Error(`Unhandled stop reason: ${_exhaustive}`);
+        }
+    }
+}

package/dist/node_modules/@pencil-agent/ai/dist/providers/openai-responses.d.ts

@@ -0,0 +1,19 @@
+/**
+ * [WHO]: OpenAIResponsesOptions, streamOpenAIResponses, streamSimpleOpenAIResponses
+ * [FROM]: Depends on openai, ../env-api-keys.js, ../models.js, ../utils/event-stream.js, ./github-copilot-headers.js
+ * [TO]: Consumed by core/lib/ai/src/index.ts
+ * [HERE]: core/lib/ai/src/providers/openai-responses.ts -
+ */
+import type { ResponseCreateParamsStreaming } from "openai/resources/responses/responses.js";
+import type { SimpleStreamOptions, StreamFunction, StreamOptions } from "../types.js";
+export interface OpenAIResponsesOptions extends StreamOptions {
+    reasoningEffort?: "minimal" | "low" | "medium" | "high" | "xhigh";
+    reasoningSummary?: "auto" | "detailed" | "concise" | null;
+    serviceTier?: ResponseCreateParamsStreaming["service_tier"];
+    toolChoice?: unknown;
+}
+/**
+ * Generate function for OpenAI Responses API
+ */
+export declare const streamOpenAIResponses: StreamFunction<"openai-responses", OpenAIResponsesOptions>;
+export declare const streamSimpleOpenAIResponses: StreamFunction<"openai-responses", SimpleStreamOptions>;

package/dist/node_modules/@pencil-agent/ai/dist/providers/openai-responses.js

@@ -0,0 +1,207 @@
+/**
+ * [WHO]: OpenAIResponsesOptions, streamOpenAIResponses, streamSimpleOpenAIResponses
+ * [FROM]: Depends on openai, ../env-api-keys.js, ../models.js, ../utils/event-stream.js, ./github-copilot-headers.js
+ * [TO]: Consumed by core/lib/ai/src/index.ts
+ * [HERE]: core/lib/ai/src/providers/openai-responses.ts -
+ */
+import OpenAI from "openai";
+import { getEnvApiKey } from "../env-api-keys.js";
+import { supportsXhigh } from "../models.js";
+import { AssistantMessageEventStream } from "../utils/event-stream.js";
+import { buildCopilotDynamicHeaders, hasCopilotVisionInput } from "./github-copilot-headers.js";
+import { convertResponsesMessages, convertResponsesTools, processResponsesStream } from "./openai-responses-shared.js";
+import { buildBaseOptions, clampReasoning } from "./simple-options.js";
+const OPENAI_TOOL_CALL_PROVIDERS = new Set(["openai", "openai-codex", "opencode"]);
+/**
+ * Resolve cache retention preference.
+ * Defaults to "short" and uses NANOPENCIL_CACHE_RETENTION for backward compatibility.
+ */
+function resolveCacheRetention(cacheRetention) {
+    if (cacheRetention) {
+        return cacheRetention;
+    }
+    if (typeof process !== "undefined" && process.env.NANOPENCIL_CACHE_RETENTION === "long") {
+        return "long";
+    }
+    return "short";
+}
+/**
+ * Get prompt cache retention based on cacheRetention and base URL.
+ * Only applies to direct OpenAI API calls (api.openai.com).
+ */
+function getPromptCacheRetention(baseUrl, cacheRetention) {
+    if (cacheRetention !== "long") {
+        return undefined;
+    }
+    if (baseUrl.includes("api.openai.com")) {
+        return "24h";
+    }
+    return undefined;
+}
+/**
+ * Generate function for OpenAI Responses API
+ */
+export const streamOpenAIResponses = (model, context, options) => {
+    const stream = new AssistantMessageEventStream();
+    // Start async processing
+    (async () => {
+        const output = {
+            role: "assistant",
+            content: [],
+            api: model.api,
+            provider: model.provider,
+            model: model.id,
+            usage: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+                totalTokens: 0,
+                cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },
+            },
+            stopReason: "stop",
+            timestamp: Date.now(),
+        };
+        try {
+            // Create OpenAI client
+            const apiKey = options?.apiKey || getEnvApiKey(model.provider) || "";
+            const client = createClient(model, context, apiKey, options?.headers);
+            const params = buildParams(model, context, options);
+            options?.onPayload?.(params);
+            const openaiStream = await client.responses.create(params, options?.signal ? { signal: options.signal } : undefined);
+            stream.push({ type: "start", partial: output });
+            await processResponsesStream(openaiStream, output, stream, model, {
+                serviceTier: options?.serviceTier,
+                applyServiceTierPricing,
+            });
+            if (options?.signal?.aborted) {
+                throw new Error("Request was aborted");
+            }
+            if (output.stopReason === "aborted" || output.stopReason === "error") {
+                throw new Error("An unknown error occurred");
+            }
+            stream.push({ type: "done", reason: output.stopReason, message: output });
+            stream.end();
+        }
+        catch (error) {
+            for (const block of output.content)
+                delete block.index;
+            output.stopReason = options?.signal?.aborted ? "aborted" : "error";
+            output.errorMessage = error instanceof Error ? error.message : JSON.stringify(error);
+            stream.push({ type: "error", reason: output.stopReason, error: output });
+            stream.end();
+        }
+    })();
+    return stream;
+};
+export const streamSimpleOpenAIResponses = (model, context, options) => {
+    const apiKey = options?.apiKey || getEnvApiKey(model.provider);
+    if (!apiKey) {
+        throw new Error(`No API key for provider: ${model.provider}`);
+    }
+    const base = buildBaseOptions(model, options, apiKey);
+    const reasoningEffort = supportsXhigh(model) ? options?.reasoning : clampReasoning(options?.reasoning);
+    return streamOpenAIResponses(model, context, {
+        ...base,
+        reasoningEffort,
+        toolChoice: options?.toolChoice,
+    });
+};
+function createClient(model, context, apiKey, optionsHeaders) {
+    if (!apiKey) {
+        if (!process.env.OPENAI_API_KEY) {
+            throw new Error("OpenAI API key is required. Set OPENAI_API_KEY environment variable or pass it as an argument.");
+        }
+        apiKey = process.env.OPENAI_API_KEY;
+    }
+    const headers = { ...model.headers };
+    if (model.provider === "github-copilot") {
+        const hasImages = hasCopilotVisionInput(context.messages);
+        const copilotHeaders = buildCopilotDynamicHeaders({
+            messages: context.messages,
+            hasImages,
+        });
+        Object.assign(headers, copilotHeaders);
+    }
+    // Merge options headers last so they can override defaults
+    if (optionsHeaders) {
+        Object.assign(headers, optionsHeaders);
+    }
+    return new OpenAI({
+        apiKey,
+        baseURL: model.baseUrl,
+        dangerouslyAllowBrowser: true,
+        defaultHeaders: headers,
+    });
+}
+function buildParams(model, context, options) {
+    const messages = convertResponsesMessages(model, context, OPENAI_TOOL_CALL_PROVIDERS);
+    const cacheRetention = resolveCacheRetention(options?.cacheRetention);
+    const params = {
+        model: model.id,
+        input: messages,
+        stream: true,
+        prompt_cache_key: cacheRetention === "none" ? undefined : options?.sessionId,
+        prompt_cache_retention: getPromptCacheRetention(model.baseUrl, cacheRetention),
+        store: false,
+    };
+    if (options?.maxTokens) {
+        params.max_output_tokens = options?.maxTokens;
+    }
+    if (options?.temperature !== undefined) {
+        params.temperature = options?.temperature;
+    }
+    if (options?.serviceTier !== undefined) {
+        params.service_tier = options.serviceTier;
+    }
+    if (context.tools) {
+        params.tools = convertResponsesTools(context.tools);
+    }
+    if (options?.toolChoice !== undefined) {
+        params.tool_choice = options.toolChoice;
+    }
+    if (model.reasoning) {
+        if (options?.reasoningEffort || options?.reasoningSummary) {
+            params.reasoning = {
+                effort: options?.reasoningEffort || "medium",
+                summary: options?.reasoningSummary || "auto",
+            };
+            params.include = ["reasoning.encrypted_content"];
+        }
+        else {
+            if (model.name.startsWith("gpt-5")) {
+                // Jesus Christ, see https://community.openai.com/t/need-reasoning-false-option-for-gpt-5/1351588/7
+                messages.push({
+                    role: "developer",
+                    content: [
+                        {
+                            type: "input_text",
+                            text: "# Juice: 0 !important",
+                        },
+                    ],
+                });
+            }
+        }
+    }
+    return params;
+}
+function getServiceTierCostMultiplier(serviceTier) {
+    switch (serviceTier) {
+        case "flex":
+            return 0.5;
+        case "priority":
+            return 2;
+        default:
+            return 1;
+    }
+}
+function applyServiceTierPricing(usage, serviceTier) {
+    const multiplier = getServiceTierCostMultiplier(serviceTier);
+    if (multiplier === 1)
+        return;
+    usage.cost.input *= multiplier;
+    usage.cost.output *= multiplier;
+    usage.cost.cacheRead *= multiplier;
+    usage.cost.cacheWrite *= multiplier;
+    usage.cost.total = usage.cost.input + usage.cost.output + usage.cost.cacheRead + usage.cost.cacheWrite;
+}