Agent Safety

The Debugger in the autonomous engineering pipeline now routes each failure to the stage that owns the fix. Half the original destinations no longer exist.

Swarm parallelism is a throughput solution applied to a reliability problem. Probabilistic verification of probabilistic output does not converge.

When a ticket has two equally-plausible interpretations, a deterministic stage stops the pipeline and asks before any Coder agent runs.

How per-stage retry budgets, wall-clock timeouts, and a global token cap keep any stage from running indefinitely, with the Debugger as the most complex case.

The mechanics behind a binding validator: why synchronous pre-commit timing, structured rejections, and retry folding are each individually load-bearing.

When the model has a strong prior, naming the failure mode in the prompt doesn't prevent it. Prompt rules are advisory; validators are binding.

The Coder added a new function to an existing file. The pipeline reported success. All seven existing functions were gone.

The pipeline committed code before branch isolation existed. The risk was real, named, given a close condition. That is what makes it different from a shortcut.

When the pipeline detects zero test files, logging a warning and continuing produces output that looks correct but cannot be caught by any downstream gate.

On attempt 3, the Coder tried to write a file that was not in the manifest. The write gate stopped it before anything hit disk. This is what it is for.

The Debugger receives the test failure and the code on disk, not the Coder's reasoning. That isolation is not a constraint. It is the design.