33 lines
1.7 KiB
Text
33 lines
1.7 KiB
Text
# Yoke guard configuration (brute mode)
|
|
# Lines starting with # are comments. Blank lines are ignored.
|
|
|
|
# ── Sandbox ──────────────────────────────────────────────────────────
|
|
# Docker image to run Claude inside. Required unless you pass --no-sandbox.
|
|
image claude-code-sandbox:latest
|
|
|
|
# ── Output ───────────────────────────────────────────────────────────
|
|
# Max lines of tail output kept per guard in guard-results.md.
|
|
max-tail 200
|
|
|
|
# Uncomment to save raw Claude stream-json output per iteration.
|
|
# log-dir .loop/logs
|
|
|
|
# ── Scope rules (diff boundary enforcement) ──────────────────────────
|
|
# Controls what files Claude is allowed to change. Most-specific
|
|
# (longest prefix) match wins.
|
|
#
|
|
# allow <prefix> — any change permitted (add, modify, delete)
|
|
# add-only <prefix> — new files only; existing files cannot be modified
|
|
# no-modify <prefix> — no changes at all (adds or modifications rejected)
|
|
|
|
allow .
|
|
|
|
# ── Guards (run after each plan stage, fail-fast) ────────────────────
|
|
# Shell commands executed after each Claude iteration. If any guard
|
|
# exits non-zero the iteration fails and results are fed back to Claude.
|
|
#
|
|
# NOTE: avoid "cargo check" as the sole guard — its type-error output
|
|
# can confuse Claude into chasing compiler noise instead of finishing
|
|
# the task. Prefer a test suite or linter that validates behaviour.
|
|
|
|
# guard cargo check
|