What happened
CugaLite sometimes halts mid-execution on certain models (e.g. gpt-4.1) and produces a natural-language announcement such as:
"I am going to perform X."
without writing any Python code. The agent does not proceed autonomously — it waits for the user to explicitly instruct it to continue, at which point it resumes normally and completes the task.
How to reproduce
- Run CugaLite with a
gpt-4.1 (or similarly affected) model backend.
- Trigger a multi-step task that requires tool/code execution.
- Observe that at some step the agent outputs a verbal intent message instead of generating a code block.
- Instruct the agent to continue — it will proceed correctly.
Environment
- Model:
gpt-4.1 (and potentially other models)
- Component: CugaLite agent loop
Logs, screenshots, or config
No code block generated at the stopping step — the agent outputs plain text intent instead of a python fenced block. Execution resumes normally after user prompt.
What happened
CugaLite sometimes halts mid-execution on certain models (e.g.
gpt-4.1) and produces a natural-language announcement such as:without writing any Python code. The agent does not proceed autonomously — it waits for the user to explicitly instruct it to continue, at which point it resumes normally and completes the task.
How to reproduce
gpt-4.1(or similarly affected) model backend.Environment
gpt-4.1(and potentially other models)Logs, screenshots, or config
No code block generated at the stopping step — the agent outputs plain text intent instead of a
pythonfenced block. Execution resumes normally after user prompt.