Cline error
Cline: [ERROR] You did not use a tool in your previous response!
[ERROR] You did not use a tool in your previous response! Please retry with a tool use.Status: WorkaroundLast verified 3 documented fixes2 sources
What it means
The model replied with plain text instead of one of Cline's tool calls, so Cline asks it to retry with a tool.
Causes
- Models with weak tool-calling support, especially local Ollama models; maintainers consolidated it into #4362 (Improve Ollama Local Model Compatibility).
- Too-small context window on local models.
How to fix it
- Fix 1.
Increase the Ollama context window (maintainer workaround): run the model, set num_ctx, and save it.
Terminalollama run your-model /set parameter num_ctx 32768 /save model-name - Fix 2.
Use tool-optimized models such as hhao/qwen2.5-coder-tools or acidtib/qwen2.5-coder-cline:7b, or qwen2.5-coder:7b with increased context.
- Fix 3.
Consider the OpenAI Compatible provider instead of the direct Ollama integration.
More Cline errors
All 17 Cline errorsShell Integration Unavailable. Cline may have trouble viewing the command's output. Please update VSCode (CMD/CTRL + Shift + P → "Update") and make sure you're using a supported shell: zsh, bash, fish, or PowerShell (CMD/CTRL + Shift + P → "Terminal: Select Default Profile").Status: WorkaroundError executing command: The command ran successfully, but we couldn't capture its output. Please proceed accordingly.Status: Fixed in releaseCommand failed with exit code 1: powershell (Get-CimInstance -ClassName Win32_OperatingSystem).caption 'powershell' is not recognized as an internal or external command, operable program or batch file.Status: WorkaroundUnexpected API Response: The language model did not provide any assistant messages. This may indicate an issue with the API or the model's output.Status: WorkaroundInvalid API Response: The provider returned an empty or unparsable response. This is a provider-side issue where the model failed to generate valid output or returned tool calls that Cline cannot process. Retrying the request may help resolve this issue.Status: OpenModel returned empty responseStatus: OpenFunction call is missing a thought_signature in functionCall parts. This is required for tools to work correctly, and missing thought_signature may lead to degraded model performance.Status: Fixed in release429 {"type":"error","error":{"type":"rate_limit_error","message":"Number of request tokens has exceeded your per-minute rate limit (https://docs.anthropic.com/en/api/rate-limits); see the response headers for current usage. Please reduce the prompt length or the maximum tokens requested, or try again later. You may also contact sales at https://www.anthropic.com/contact-sales to discuss your options for a rate limit increase."}}Status: Workaround
Related reading
- What Is Cline? The Open-Source AI Coding Agent for VS CodeCline is a free, open-source VS Code extension for agentic AI coding. Bring your own model, a cloud API or a local one via Ollama, with no vendor lock-in.
- Every AI Coding Tool Compared: The 2026 MatrixEvery AI coding tool compared: 15 terminal, IDE, cloud and browser tools side by side on pricing, model surface, strengths, weaknesses and best use cases.
FAQ
What does "[ERROR] You did not use a tool in your previous response!" mean in Cline?
The model replied with plain text instead of one of Cline's tool calls, so Cline asks it to retry with a tool.
How do I fix "[ERROR] You did not use a tool in your previous response!"?
There are 3 documented fixes. Start with the first: Increase the Ollama context window (maintainer workaround): run the model, set num_ctx, and save it.
Is this Cline error fixed?
Status: Workaround. No release removes the cause. The documented fixes work around it. Affected versions: Reported on 3.1.5, 3.2.5, 3.3.1
Sources
Last verified against 2 sources: official docs, maintainer replies and release notes.
Newsletter
Fixes for the tools you use, weekly
One email per week. New coding agent releases, what broke, and how developers are working around it.