Thinking Phrases are extremely unprofessional and should not be enabled by default!

Type: Bug

I was just working on a project and saw GPT agent display "Bribing the hamster" in its reasoning chain of thought. I immediately freaked out the model reasoning got somehow derailed and I am wasting expensive tokens on something useless.

These kind of stupid gimmicks don't belong into a professional paid service, or at the very least they should be off by default.

VS Code version: Code 1.138.0 (7debcd0e2acdea1c52de81bf9ee1620444407dda, 2026-09-15T07:24:32Z)
OS version: Windows_NT x64 10.0.26200
Modes:

System Info

|Item|Value|
|---|---|
|CPUs|AMD Ryzen 9 3900X 12-Core Processor (24 x 3800)|
|GPU Status|2d_canvas: enabled
GPU0: VENDOR= 0x10de, DEVICE=0x2705 [NVIDIA GeForce RTX 4070 Ti SUPER], DRIVER_VENDOR=NVIDIA, DRIVER_VERSION=32.0.15.9649 *ACTIVE*
GPU1: VENDOR= 0x1414, DEVICE=0x008c [Microsoft Basic Render Driver], DRIVER_VERSION=10.0.26100.9278
Machine model name:
Machine model version:
direct_rendering_display_compositor: disabled_off_ok
gpu_compositing: enabled
multiple_raster_threads: enabled_on
opengl: enabled_on
rasterization: enabled
raw_draw: disabled_off_ok
skia_graphite: disabled_off
trees_in_viz: disabled_off
video_decode: enabled
video_encode: enabled
webgl: enabled
webgpu: enabled
webnn: disabled_off|
|Load (avg)|undefined|
|Memory (System)|63.91GB (38.53GB free)|
|Process Argv|D:\\Projects\\Games\\IncarnusWarfare\\IncarnusWarfare.code-workspace --crash-reporter-id 7a6c2507-c44b-4e8f-8d06-918d5883f16a|
|Screen Reader|no|
|VM|0%|
Extensions (6)

Name|Identifier|Author|Version
---|---|---|---
Unreal Angelscript|hazelight.unreal-angelscript|Hazelight|1.9.4
Unreal AngelScript Clang-Format|hazelight.unreal-angelscript-clang-format|Hazelight|3.1.0
clangd|llvm-vs-code-extensions.vscode-clangd|llvm-vs-code-extensions|0.6.0
UE Clangd Helper|ludvikkoutny.ue-clangd-helper|ludvikkoutny|1.0.7
C/C++ DevTools|ms-vscode.cpp-devtools|ms-vscode|0.7.1
C/C++|ms-vscode.cpptools|ms-vscode|1.34.4