code_puppy
code_puppy copied to clipboard
mpfaffenberger
Agentic AI for writing code
## Summary Fixes a bug where excessively long command strings or path tokens could crash the attachment detection logic with `OSError` (ENAMETOOLONG) or cause unexpected behavior during file path resolution....
Support for fully localized AI with ollama Let me know if you want to collab.
Added ability to pause code puppy to use shell commands /shell to switch to a shell 
When setting the VQA model to claude-sonnet-4-5-20250929 Screenshot saved: /tmp/code_puppy_screenshots_a64xtocn/screenshot_20251122_114721.png Visual question answering failed: status_code: 400, model_name: claude-sonnet-4-5-20250929, body: {'type': 'error', 'error': {'type': 'invalid_request_error', 'message': 'This credential is only authorized...
I typically run VERY long running tasks .... and there should be a option to override the Usage limit. In a 5-6h run (of one prompt) of it i see...
* feat: add comprehensive code execution sandboxing Implements sandboxing for shell command execution inspired by Anthropic's Claude Code approach. Provides dual-layer isolation: filesystem and network. ## Features **Filesystem Isolation:** -...
this is for support for `--continue`
Add a shell mode to puppy. Just like major coding agent CLI. Instead of going to another terminal to execute a trivial shell command that you don't need LLM to...
