From 1191e8416a161b5ec4c80ac07f972fcaf8635ac4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marc-Andr=C3=A9=20Bombeck?= <mbombeck@gmail.com>
Date: Sat, 24 Oct 2026 18:47:03 +0200
Subject: [PATCH] test(labs): expect the minimum's thinking room on wires that
 cannot promise off

The lab-scan read asks every provider for no reasoning. On an
OpenAI-compatible gateway or a local server that "none" is a request the
model behind it may ignore, so these wires now add the low thinking budget on
top, the same rule the file already holds for a model that always thinks:
the answer keeps its full allowance either way.

Refs #1276
---
 src/lib/labs/__tests__/ocr-output-budget.test.ts | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/src/lib/labs/__tests__/ocr-output-budget.test.ts b/src/lib/labs/__tests__/ocr-output-budget.test.ts
index fd5d17cd9..b57abe8c9 100644
--- a/src/lib/labs/__tests__/ocr-output-budget.test.ts
+++ b/src/lib/labs/__tests__/ocr-output-budget.test.ts
@@ -115,8 +115,12 @@ describe("OpenAI", () => {
   });
 });
 
+// #1276 — a gateway or local server cannot promise that `none` is honoured
+// (a model behind it may reason anyway), so these wires add the minimum's
+// thinking budget on top like a model that always thinks: the answer keeps
+// its full allowance either way.
 describe("an OpenAI-compatible gateway (Gemini, OpenRouter, LiteLLM)", () => {
-  it("asks for no reasoning on the endpoint's own dialect", async () => {
+  it("asks for no reasoning on the endpoint's own dialect, with the minimum's budget on top", async () => {
     const body = await sentBody(
       new OpenAIClient({
         apiKey: "k",
@@ -126,12 +130,14 @@ describe("an OpenAI-compatible gateway (Gemini, OpenRouter, LiteLLM)", () => {
       }),
     );
     expect(body.reasoning_effort).toBe("none");
-    expect(body.max_tokens ?? body.max_completion_tokens).toBe(ANSWER);
+    expect(body.max_tokens ?? body.max_completion_tokens).toBe(
+      ANSWER + REASONING_THINKING_BUDGET.low,
+    );
   });
 });
 
 describe("a local server", () => {
-  it("asks for no reasoning and keeps the answer budget", async () => {
+  it("asks for no reasoning and keeps the answer budget, with the minimum's on top", async () => {
     const body = await sentBody(
       new LocalOpenAICompatibleClient({
         apiKey: null,
@@ -140,7 +146,7 @@ describe("a local server", () => {
       }),
     );
     expect(body.reasoning_effort).toBe("none");
-    expect(body.max_tokens).toBe(ANSWER);
+    expect(body.max_tokens).toBe(ANSWER + REASONING_THINKING_BUDGET.low);
   });
 });