Context Length Exceeded Issue - Difference between Official SWE-agent and Mini SWE-agent
Hi team,
I’m trying to reproduce the evaluation results of your model, but encountering some issues regarding context length management.
My Setup:
Using mini swe-agent framework (only bash tool available)
Set context length to 128k
Still frequently hitting “exceed context limit” errors
Official Setup (from your repo):
Using full SWE-agent (bash, str_replace_editor, submit tools)
Only used 85k context length
Achieved good results without context issues
Questions:
Why does the official setup with 85k context work better than my 128k setup?
Is the difference mainly due to the additional tools (str_replace_editor, submit)?
Do these tools help reduce context consumption?
Are there any specific context management strategies used in the official evaluation?
Could you share more details about the context window management in your evaluation setup?
Any guidance would be greatly appreciated!