whylisted

# Your machine, or your code — decide that first The expensive mistake is not picking the wrong fix. It is spending two hours in the code when the problem was a version, or two hours on the environment when the problem was a line somebody changed. One decision comes before any debugging, and this repository holds evidence for both sides of it. ## 1 · The machine ``` chamnan-env ``` What this repository has declared about the environments it runs in — the constraints nobody writes down and everybody re-learns. A shell alias that hangs without a terminal, a binary that is not on this platform, a Python whose certificate bundle is broken. **If the failure matches one of these, stop: there is nothing wrong with the code.** An error that mentions a command not found, a version mismatch, a certificate, a path separator or a permission is a machine failure until something rules that out. ## 2 · The code ``` chamnan-impact <the file the failure points at> ``` Who imports it, **which tests cover it**, and what this repository has recorded about it. If the failing test is in that list, the change and the failure are connected. If it is not, the error's file and the failure's cause are probably different files. ## 3 · What this cannot tell you, and do not pretend otherwise **chamnan does not know when the test last passed.** A Bash tool response carries no exit code — only stdout, stderr and whether it was interrupted — and the `stderr` field was measured to be a constant rath