@hebo-ai/gateway 0.10.7 → 0.11.1

package/dist/endpoints/responses/handler.js

@@ -23,7 +23,7 @@ export const responses = (config) => {
             throw new GatewayError("Method Not Allowed", 405);
         }
         // Parse + validate input (handles Content-Encoding decompression + body size limits).
-        ctx.body = (await parseRequestBody(ctx.request, cfg.maxBodySize));
+        ctx.body = (await parseRequestBody(ctx.request, cfg.advanced.maxBodySize));
         logger.trace({ requestId: ctx.requestId, body: ctx.body }, "[responses] ResponsesBody");
         addSpanEvent("hebo.request.deserialized");
         const parsed = ResponsesBodySchema.safeParse(ctx.body);
@@ -71,10 +71,12 @@ export const responses = (config) => {
             let ttft = 0;
             const result = streamText({
                 model: languageModelWithMiddleware,
-                headers: prepareForwardHeaders(ctx.request),
+                headers: prepareForwardHeaders(ctx.request, cfg.advanced.forwardHeaders),
                 abortSignal: ctx.request.signal,
                 timeout: {
-                    totalMs: ctx.body.service_tier === "flex" ? cfg.timeouts.flex : cfg.timeouts.normal,
+                    totalMs: ctx.body.service_tier === "flex"
+                        ? cfg.advanced.timeouts.flex
+                        : cfg.advanced.timeouts.normal,
                 },
                 onAbort: () => {
                     throw new DOMException("The operation was aborted.", "AbortError");
@@ -112,9 +114,11 @@ export const responses = (config) => {
         addSpanEvent("hebo.ai-sdk.started");
         const result = await generateText({
             model: languageModelWithMiddleware,
-            headers: prepareForwardHeaders(ctx.request),
+            headers: prepareForwardHeaders(ctx.request, cfg.advanced.forwardHeaders),
             abortSignal: ctx.request.signal,
-            timeout: ctx.body.service_tier === "flex" ? cfg.timeouts.flex : cfg.timeouts.normal,
+            timeout: ctx.body.service_tier === "flex"
+                ? cfg.advanced.timeouts.flex
+                : cfg.advanced.timeouts.normal,
             experimental_include: {
                 requestBody: false,
                 responseBody: false,

package/dist/index.d.ts

@@ -10,3 +10,4 @@ export * from "./models/catalog";
 export * from "./models/types";
 export * from "./providers/registry";
 export * from "./providers/types";
+export { FORWARD_HEADER_ALLOWLIST } from "./utils";

package/dist/index.js

@@ -9,3 +9,4 @@ export * from "./models/catalog";
 export * from "./models/types";
 export * from "./providers/registry";
 export * from "./providers/types";
+export { FORWARD_HEADER_ALLOWLIST } from "./utils";

package/dist/models/alibaba/index.d.ts

@@ -0,0 +1,2 @@
+export * from "./presets";
+export * from "./middleware";

package/dist/models/alibaba/index.js

@@ -0,0 +1,2 @@
+export * from "./presets";
+export * from "./middleware";

package/dist/models/alibaba/middleware.d.ts

@@ -0,0 +1,2 @@
+import type { LanguageModelMiddleware } from "ai";
+export declare const qwenReasoningMiddleware: LanguageModelMiddleware;

package/dist/models/alibaba/middleware.js

@@ -0,0 +1,31 @@
+import { modelMiddlewareMatcher } from "../../middleware/matcher";
+import { calculateReasoningBudgetFromEffort } from "../../middleware/utils";
+const QWEN_DEFAULT_MAX_OUTPUT_TOKENS = 16384;
+export const qwenReasoningMiddleware = {
+    specificationVersion: "v3",
+    // oxlint-disable-next-line require-await
+    transformParams: async ({ params }) => {
+        const unknown = params.providerOptions?.["unknown"];
+        if (!unknown)
+            return params;
+        const reasoning = unknown["reasoning"];
+        if (!reasoning)
+            return params;
+        const target = (params.providerOptions["alibaba"] ??= {});
+        if (!reasoning.enabled || reasoning.effort === "none") {
+            target.enableThinking = false;
+            delete target.thinkingBudget;
+        }
+        else {
+            target.enableThinking = true;
+            target.thinkingBudget =
+                reasoning.max_tokens ??
+                    calculateReasoningBudgetFromEffort(reasoning.effort ?? "medium", params.maxOutputTokens ?? QWEN_DEFAULT_MAX_OUTPUT_TOKENS);
+        }
+        delete unknown["reasoning"];
+        return params;
+    },
+};
+modelMiddlewareMatcher.useForModel("alibaba/qwen*", {
+    language: [qwenReasoningMiddleware],
+});