yoke/src/templates/saga/yoke.conf

# Yoke configuration (saga mode)
# Lines starting with # are comments. Blank lines are ignored.

# ── Backend ────────────────────────────────────────────────────────────
# Model to use for the agent. If unset, defaults to Claude CLI.
# Use provider/model format for OpenRouter or other opencode providers.
# model      openrouter/anthropic/claude-sonnet-4
# model      openai/gpt-4o
# model      anthropic/claude-sonnet-4

# ── Sandbox ──────────────────────────────────────────────────────────
# Docker image to run the agent inside. Required unless you pass --no-sandbox.
# Note: sandbox is not currently supported with the 'model' directive.
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 stream-json output per iteration.
# log-dir   .loop/logs

# ── Scope rules (diff boundary enforcement) ──────────────────────────
# Controls what files the agent 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 agent iteration. If any guard
# exits non-zero the iteration fails and results are fed back.
#
# NOTE: avoid "cargo check" as the sole guard — its type-error output
# can confuse the agent into chasing compiler noise instead of finishing
# the task. Prefer a test suite or linter that validates behaviour.

# guard     cargo check

# ── Judge cadence ─────────────────────────────────────────────────────
# By default the judge runs only after the worker signals DONE.
# Set judge-every to fire the judge as a quality checkpoint every N
# worker iterations (it still always fires on DONE too).
#
# judge-every   5

# Max consecutive judge failures before bailing out (default: 3).
# The counter resets to 0 after any passing verdict.
#
# max-judge-failures  3

# ── Periodic agents (cadence-based supplementary agents) ──────────────
# Invoke an additional agent protocol at a fixed cadence (every N
# worker iterations). Useful for code cleanup, review passes, etc.
# The agent name is derived from the filename (cleaner.md → "cleaner").
#
#   periodic  <protocol-path>  <every-N-iterations>
#
# periodic  .loop/cleaner.md  10

# Guards that run after a specific periodic agent completes. Results
# are written to .loop/periodic-<name>-results.md (separate from the
# worker's guard-results.md so the worker isn't confused).
#
#   guard-after  <periodic-name>  <command>
#
# guard-after  cleaner  cargo test