Kimi 2.6 custom model - Provider returned error: {"error":{"message":"thinking is enabled but reasoning_content is missing

Support Bug Reports
1

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

When tried to use Kimi 2.6 API as a custom model inside Cursor IDE , after the first tool call, i got this error:

Provider returned error: {“error”:{“message”:“thinking is enabled but reasoning_content is missing in assistant tool call message at index 3”,“type”:“invalid_request_error”}}

Steps to Reproduce

Add Kimi api key and “kimi-2.5” as a custom model and try to send a message requiring tool calls

Operating System

Linux

Version Information

Version: 3.2.16
VSCode Version: 1.105.1
Commit: 3e548838cf824b70851dd3ef27d0c6aae371b3f0
Date: 2026-04-28T21:07:47.682Z
Layout: editor
Build Type: Stable
Release Track: Default
Electron: 39.8.1
Chromium: 142.0.7444.265
Node.js: 22.22.1
V8: 14.2.231.22-electron.0
OS: Linux x64 6.17.0-20-generic

For AI issues: which model did you use?

Kimi 2.6

For AI issues: add Request ID with privacy disabled

Request ID: f6b2f1e2-6541-4958-9651-98650cb128f1
{“error”:“ERROR_PROVIDER_ERROR”,“details”:{“title”:“Provider Error”,“detail”:“Provider returned error: {"error":{"message":"thinking is enabled but reasoning_content is missing in assistant tool call message at index 3","type":"invalid_request_error"}}”,“isRetryable”:false,“additionalInfo”:{},“buttons”:,“planChoices”:},“isExpected”:true}
Provider Error Provider returned error: {“error”:{“message”:“thinking is enabled but reasoning_content is missing in assistant tool call message at index 3”,“type”:“invalid_request_error”}}
Svs: Provider Error Provider returned error: {“error”:{“message”:“thinking is enabled but reasoning_content is missing in assistant tool call message at index 3”,“type”:“invalid_request_error”}}
at mg_ (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:29432:24260)
at dg_ (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:29432:23144)
at wg_ (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:29433:6490)
at nCh.run (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:29433:11307)
at async lQi.runAgentLoop (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:41749:12418)
at async mim.streamFromAgentBackend (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:41817:12344)
at async mim.getAgentStreamResponse (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:41817:19567)
at async hCt.submitChatMaybeAbortCurrent (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:29548:16906)
at async Object.Xa [as onSubmit] (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:40804:4244)
at async vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:40803:102189

Does this stop you from using Cursor

Sometimes - I can sometimes use Cursor

5

Hey, this is a known limitation of the BYOK path for thinking models like Kimi and DeepSeek. After the first tool call, reasoning_content gets dropped from the history, and the provider Moonshot rejects the next request.

The same symptom is discussed here: Kimi/kimi-k2.5 cannot be called to execute tool calls in cursor and here for DeepSeek with the same root cause: Compatibility with DeepSeek model's design to return reasoning content after tool calls?.

We’re tracking the issue, but I can’t share an ETA for a fix yet. I’m going to close this thread as a duplicate. For updates, please follow the DeepSeek thread since it’s more active.

Workaround for now: if you can, turn off thinking mode in Moonshot for this model, or use a non-reasoning model. Tool calls should work fine then.