From 7f245b0968b8455edbcbdbe8d71c9a11e44b142b Mon Sep 17 00:00:00 2001
From: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
Date: Thu, 24 Sep 2026 13:42:10 -0500
Subject: [PATCH] fix(ai): fit OpenRouter reasoning budgets to the output limit
 (#51189)

---
 packages/ai/src/providers/openrouter.ts      | 15 ++++++++++----
 packages/ai/test/provider/openrouter.test.ts | 21 ++++++++++++++++++++
 2 files changed, 32 insertions(+), 4 deletions(-)

diff --git a/packages/ai/src/providers/openrouter.ts b/packages/ai/src/providers/openrouter.ts
index 5cc2f0ce6eb..3a09c0826e5 100644
--- a/packages/ai/src/providers/openrouter.ts
+++ b/packages/ai/src/providers/openrouter.ts
@@ -8,7 +8,7 @@ import type { ProviderPackage } from "../provider-package.js"
 import { SystemOne } from "../experimental/system-one.js"
 import { OpenAIChat } from "../protocols/openai-chat.js"
 import { newBreakpoints, ttlBucket } from "../protocols/utils/cache.js"
-import { isRecord } from "../protocols/shared.js"
+import { isRecord, ProviderShared } from "../protocols/shared.js"
 
 export const id = ProviderID.make("openrouter")
 const baseURL = "https://openrouter.ai/api/v1"
@@ -123,7 +123,7 @@ export const protocol = Protocol.make({
           return {
             ...body,
             messages,
-            ...bodyOptions(request.providerOptions),
+            ...bodyOptions(request.providerOptions, request.generation?.maxTokens),
           } as OpenRouterBody
         }),
       ),
@@ -143,7 +143,14 @@ const cacheControl = () => {
   }
 }
 
-const bodyOptions = (input: unknown) => {
+// OpenRouter forwards `reasoning.max_tokens` as the upstream thinking budget. Upstreams such as Anthropic and Alibaba
+// reject one that is not below the output limit; 1,024 is Anthropic's minimum budget.
+const fitReasoning = (reasoning: Record<string, unknown>, maxTokens: number | undefined) =>
+  typeof reasoning.max_tokens === "number"
+    ? { ...reasoning, max_tokens: ProviderShared.fitThinkingBudget(reasoning.max_tokens, maxTokens, 1_024) }
+    : reasoning
+
+const bodyOptions = (input: unknown, maxTokens: number | undefined) => {
   const openrouter = isRecord(input) ? input : {}
   const { usage, models, provider, plugins, web_search_options, debug, user, reasoning, promptCacheKey, ...options } =
     openrouter
@@ -162,7 +169,7 @@ const bodyOptions = (input: unknown) => {
     ...(isRecord(web_search_options) ? { web_search_options } : {}),
     ...(isRecord(debug) ? { debug } : {}),
     ...(typeof user === "string" ? { user } : {}),
-    ...(isRecord(reasoning) ? { reasoning } : {}),
+    ...(isRecord(reasoning) ? { reasoning: fitReasoning(reasoning, maxTokens) } : {}),
   }
 }
 
diff --git a/packages/ai/test/provider/openrouter.test.ts b/packages/ai/test/provider/openrouter.test.ts
index 7c320df3420..7e717b96bde 100644
--- a/packages/ai/test/provider/openrouter.test.ts
+++ b/packages/ai/test/provider/openrouter.test.ts
@@ -152,6 +152,27 @@ describe("OpenRouter", () => {
     }),
   )
 
+  it.effect("fits the reasoning budget to half the output limit", () =>
+    Effect.gen(function* () {
+      const reasoning = (maxTokens: number | undefined, value: Record<string, unknown>) =>
+        compileRequest(
+          LLM.request({
+            model: OpenRouter.configure({ apiKey: "test-key" }).model("qwen/qwen3.8-flash"),
+            cache: "none",
+            prompt: "Hello",
+            ...(maxTokens === undefined ? {} : { generation: { maxTokens } }),
+            providerOptions: { reasoning: value },
+          }),
+        ).pipe(Effect.map((prepared) => prepared.body.reasoning))
+
+      expect(yield* reasoning(32_000, { max_tokens: 131_071 })).toEqual({ max_tokens: 16_000 })
+      expect(yield* reasoning(131_072, { max_tokens: 65_536 })).toEqual({ max_tokens: 65_536 })
+      expect(yield* reasoning(1_500, { max_tokens: 65_536 })).toEqual({ max_tokens: 1_024 })
+      expect(yield* reasoning(undefined, { max_tokens: 131_071 })).toEqual({ max_tokens: 131_071 })
+      expect(yield* reasoning(32_000, { effort: "high" })).toEqual({ effort: "high" })
+    }),
+  )
+
   it.effect("applies OpenRouter payload options from the model helper", () =>
     Effect.gen(function* () {
       const prepared = yield* compileRequest(