Test-Iterate Loop — Autonomous Bug Fix Cycle

Autonomous loop: run tests → root-cause failures → apply minimal fix → retry. Bounded by iteration cap and same-error-repeat detector. Never commits — leaves clean working tree + markdown report. Generic across Python (pytest), R (testthat), Julia (Pkg.test), and HPC pipelines (mock-Avon Docker).

Hard Rules

Existential — block proceed

1. Never git commit, git push, or modify .git/ state. All changes go into the working tree only. The user reviews the final clean tree + report and decides what to commit. Enforced via the standard forbid-list per subagent-write-guard.md if dispatching sub-agents.
2. Bounded iteration: max 10 iterations OR 3-same-error-repeat — whichever first. Hardcoded ceiling. Past that, stop and summarise. Don't ask "continue?" — exhaustion is the signal.
3. Each iteration must change ≥1 file. A no-op iteration (Claude couldn't propose a fix) counts as a same-error-repeat.
4. Memory bug detector: flag any iteration that adds a model load, env var change, or version pin without a corresponding test — these are common failure-cause patterns from past HPC sessions.

Format — catch in review

5. Every iteration logged to log/test-iterate/<project>-YYYY-MM-DD-HHMM.md with: hypothesis, fix applied, result.
6. Final report at the same path summarises iterations, terminal state, and remaining failures (if any).
7. Use TaskCreate/TaskUpdate for live progress tracking — the user can see what iteration is running and why.