feat(phased-execution): harness commits each completed phase atomically

Children never commit (their prompts forbid git add/commit, overriding
project instructions) so the commit is deterministic. At the phase commit
point (00_phase.md final pass) the harness makes ONE atomic commit: the
phase's code changes, the todo→complete file move, and the executor
reports, together.

- Scoped staging: a worktree snapshot taken at the phase's first unit
  (phase-sessions/dirty-<phase>, always kept) is subtracted, so the
  owner's pre-existing uncommitted work is left alone; runtime artifacts
  are never staged. The commit prints exactly what went in.
- Verified: the moved phase file (and report, unless gitignored) must be
  in the index before committing.
- Loud on failure: a commit failure prints the git error + hand-fix and
  stops the run; the phase stays complete, the miss is never swept into a
  later phase.
- PHASE_COMMIT_SUBJECT (default 'phase: <phase>'); the executor's final
  report becomes the commit body; --no-gpg-sign always passed.
- PHASE_COMMIT defaults to 1: completed phases are committed by default.
  Explicit PHASE_COMMIT=0 opts out with a loud warning that the phase is
  complete but uncommitted — a completed phase is never left uncommitted
  silently (that gap let four phases pile up uncommitted in
  brain_of_reese).
This commit is contained in:
2026-09-07 12:42:59 -04:00
parent e505df62e8
commit f6cbb2d664
8 changed files with 209 additions and 17 deletions
+4 -2
View File
@@ -29,8 +29,10 @@ delivered=()
while unit="$(next_unit)"; do
[[ -n "$unit" ]] || break
if ! execute_unit "$unit"; then
echo "✗ ERROR: pipeline stopped — $unit FAILED after $MAX_FIX_ATTEMPTS attempts" >&2
echo " fix the issues above, then re-run this script to continue where it stopped" >&2
# execute_unit printed the failure detail (task failure: errors, logs,
# resume command — or phase-commit failure: the hand-fix command).
echo "✗ ERROR: pipeline stopped — $unit did not complete (see the error output above)" >&2
echo " re-run this script to continue where it stopped" >&2
exit 1
fi
delivered+=("$unit")
+163 -7
View File
@@ -17,7 +17,10 @@
# report, and validation passes. When all of a phase's tasks are done,
# 00_phase.md runs as the phase's final pass (any remaining inline work +
# completion criteria + phase-level verification); moving it completes the
# phase and is the PHASE_COMMIT commit point.
# phase and is the commit point. Children never commit — by default
# (PHASE_COMMIT=1) the harness makes ONE atomic commit per completed phase
# (code changes + the file move + the executor reports), scoped so the
# owner's pre-existing worktree changes are left alone (see commit_phase).
SKILL_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
EXECUTOR_PROMPT_FILE="$SKILL_DIR/assets/executor-prompt.md"
@@ -300,6 +303,147 @@ run_validation() {
bash .agents/validate.sh >"$1" 2>&1
}
# --- phase commit -------------------------------------------------------------
# Commit ownership: child executors NEVER commit (their prompts forbid it,
# overriding any project instruction to commit per task/phase). By default
# (PHASE_COMMIT=1) the harness therefore makes ONE atomic commit per
# completed phase — the phase's code changes, the todo→complete file move,
# and the executor reports, together — at the phase's commit point.
#
# Staging is scoped so the owner's unrelated work is not swept in:
# stage = (everything dirty now)
# − (what was already dirty when the phase's first unit started —
# snapshot $PHASE_SESSIONS/dirty-<phase>, taken once per phase)
# − (pipeline runtime artifacts: phase-sessions/, pipeline.log)
# Work the owner dirtied mid-phase is indistinguishable from phase work and
# IS committed — the commit output prints exactly what went in.
# Snapshot the worktree's dirty state at the phase's first unit (no-op
# outside a git work tree, and when the phase already has a snapshot — a
# resumed phase keeps the one taken at its start).
phase_dirty_snapshot() {
local phase="$1" f
git rev-parse --is-inside-work-tree >/dev/null 2>&1 || return 0
f="$PHASE_SESSIONS/dirty-$phase"
if [[ ! -f "$f" ]]; then
git status --porcelain >"$f" 2>/dev/null || : >"$f"
fi
}
# commit_phase <unit> <report-file>
# Returns 0 on success, when there is nothing left to commit, or outside a
# git work tree. Returns 1 (after printing a ✗ ERROR block with the git
# error and the hand-fix command) when the phase's own artifacts could not
# be committed. The phase stays COMPLETE either way — the work passed
# validation; the caller stops the run so a commit miss is visible, never
# retried as a task and never swept into a later phase's commit.
commit_phase() {
local unit="$1" report="${2:-}"
local phase pre curf paths lits moved staged addout commitout subject msgf
phase="$(unit_phase "$unit")"
if ! git rev-parse --is-inside-work-tree >/dev/null 2>&1; then
warn "not a git work tree — no phase commit for $phase"
return 0
fi
pre="$PHASE_SESSIONS/dirty-$phase"
# Everything dirty now: tracked changes vs HEAD + untracked non-ignored.
curf="$(mktemp)"
{ git diff --name-only HEAD; git ls-files --others --exclude-standard; } | sort -u >"$curf"
# Quick exit: the phase's artifacts are already committed (moved file
# tracked and clean — e.g. a duplicate commit attempt after the snapshot
# was cleaned up) — never stage again, owner WIP stays untouched.
if git ls-files --error-unmatch -- "$PHASE_DONE/$unit" >/dev/null 2>&1 \
&& ! grep -qx -- "$PHASE_DONE/$unit" "$curf"; then
rm -f "$curf"
echo " (nothing to commit — the phase is already fully committed)"
return 0
fi
# Subtract pre-phase owner WIP (porcelain lines are "XY <path>") and the
# pipeline's own runtime artifacts.
paths="$(mktemp)"
if [[ -f "$pre" ]]; then
comm -23 "$curf" <(cut -c4- "$pre" | grep -v '^[[:space:]]*$' | sort -u) \
| grep -vE '^\.agents/(phase-sessions/|pipeline\.log$)' >"$paths" || true
else
grep -vE '^\.agents/(phase-sessions/|pipeline\.log$)' "$curf" >"$paths" || true
fi
rm -f "$curf"
if [[ ! -s "$paths" ]]; then
rm -f "$paths" "$pre"
echo " (nothing to commit — the phase is already fully committed)"
return 0
fi
# :(literal) keeps file names with glob characters ([?* ) from being read
# as pathspec patterns.
lits="$(mktemp)"
sed 's|^|:(literal)|' "$paths" >"$lits"
if ! addout="$(git add -A --pathspec-from-file="$lits" 2>&1)"; then
rm -f "$paths" "$lits"
echo "✗ ERROR: phase commit for $phase — staging failed:" >&2
printf '%s\n' "$addout" | sed 's/^/ /' >&2
return 1
fi
rm -f "$lits"
# Verify the artifacts that used to go missing: the moved phase file must
# be in the index (hard fail), and the executor report unless the project
# deliberately gitignores reports.
moved="$PHASE_DONE/$unit"
staged="$(git -c core.quotepath=off diff --cached --name-only -z | tr '\0' '\n')"
if ! grep -qx -- "$moved" <<<"$staged"; then
git reset -q
rm -f "$paths"
echo "✗ ERROR: phase commit for $phase — the moved phase file is not in the index ($moved)." >&2
if git check-ignore -q -- "$moved" 2>/dev/null; then
echo " your .gitignore excludes it — .agents/phases must be tracked (SKILL.md setup notes)." >&2
fi
echo " the work is complete and uncommitted; stage and commit it by hand." >&2
return 1
fi
if [[ -n "$report" && -f "$report" ]] && ! grep -qx -- "$report" <<<"$staged" \
&& ! git check-ignore -q -- "$report" 2>/dev/null; then
git reset -q
rm -f "$paths"
echo "✗ ERROR: phase commit for $phase — the executor report is not in the index ($report)." >&2
echo " the work is complete and uncommitted; stage and commit it by hand." >&2
return 1
fi
rm -f "$paths"
# Subject: PHASE_COMMIT_SUBJECT with {{PHASE}} substituted (default
# "phase: <phase>"); the executor's final report becomes the body.
# The default subject lives in a variable: a brace literal inside the
# ${var:-default} word would terminate the expansion early (bash does not
# nest plain braces).
local default_subject="phase: {{PHASE}}"
subject="${PHASE_COMMIT_SUBJECT:-$default_subject}"
subject="${subject//\{\{PHASE\}\}/$phase}"
msgf="$(mktemp)"
{
printf '%s\n' "$subject"
printf '\n'
[[ -n "$report" && -f "$report" ]] && sed -n '1,40p' "$report"
} >"$msgf"
if ! commitout="$(git commit --no-gpg-sign -F "$msgf" 2>&1)"; then
rm -f "$msgf"
echo "✗ ERROR: phase commit for $phase FAILED — the phase is complete but UNCOMMITTED (the scoped changes are still staged)." >&2
printf '%s\n' "$commitout" | sed 's/^/ /' >&2
echo " finish by hand: git commit --no-gpg-sign -m 'phase: $phase'" >&2
echo " re-running the pipeline will NOT commit this phase — fix the commit first." >&2
return 1
fi
rm -f "$msgf" "$pre"
echo " (committed: $(git log -1 --oneline))"
return 0
}
# --- notifications ------------------------------------------------------------
# Send a push notification via ntfy after a unit completes. Reads
# ~/.env/pi-ntfy.env (see the ntfy skill). No-ops (silently) when notifications
@@ -337,7 +481,9 @@ notify_task() {
# --- one unit (task, phase final pass, or legacy phase), with retries ---------
# execute_unit <unit>
# Returns 0 and moves the unit to complete/ on success; returns 1 after
# MAX_FIX_ATTEMPTS failed attempts (unit file is left in todo/).
# MAX_FIX_ATTEMPTS failed attempts (unit file is left in todo/), or 1 when
# the phase commit fails at a phase's commit point (unit stays in
# complete/ — the work is done; the commit must be finished by hand).
execute_unit() {
local unit="$1"
local base attempt=1 errors=""
@@ -346,6 +492,9 @@ execute_unit() {
command -v node >/dev/null 2>&1 || die "node not found on PATH (needed to render task progress)"
mkdir -p "$PHASE_DONE" "$PHASE_REPORTS" "$PHASE_SESSIONS" "$(unit_report_dir "$unit")"
ensure_validate
# First unit of the phase: freeze the owner's pre-existing dirty state so
# the phase commit (commit_phase) can exclude it from staging.
phase_dirty_snapshot "$(unit_phase "$unit")"
while (( attempt <= MAX_FIX_ATTEMPTS )); do
echo "━━ $unit — attempt $attempt/$MAX_FIX_ATTEMPTS ━━"
@@ -390,12 +539,19 @@ execute_unit() {
move_unit "$unit"
if is_phase_end "$unit"; then
echo "✓ $unit → complete (phase $(unit_phase "$unit") done)"
if [[ "${PHASE_COMMIT:-0}" == "1" ]]; then
if git add -A 2>/dev/null && git commit --no-gpg-sign -m "phase: $(unit_phase "$unit")" >/dev/null 2>&1; then
echo " (committed)"
else
warn "git commit failed (continuing)"
if [[ "${PHASE_COMMIT:-1}" == "1" ]]; then
if ! commit_phase "$unit" "$(unit_report "$unit" "$attempt" md)"; then
# The work is done and validated; the unit stays in complete/ and
# re-running will NOT re-execute this phase. Stop the run so the
# commit miss is visible — commit_phase printed the hand-fix.
echo " phase work is UNCOMMITTED — fix the commit first (see above); re-running continues at the next phase" >&2
return 1
fi
else
# Explicit opt-out (PHASE_COMMIT=0): respect it, but never let the
# miss be silent — a completed phase with uncommitted work used to
# pile up in the worktree unnoticed.
warn "PHASE_COMMIT=0 — phase $(unit_phase "$unit") is COMPLETE but UNCOMMITTED; its work is left in the worktree — commit it by hand"
fi
else
echo "✓ $unit → complete"
+3 -3
View File
@@ -44,9 +44,9 @@ while unit="$(phase_next_unit "$phase")"; do
execute_unit "$unit" || { failed=1; break; }
done
if (( failed )); then
echo "✗ ERROR: phase $phase FAILED — see error above" >&2
echo " reports: $(unit_report_dir "$unit")/$(unit_base "$unit").a*.{md,err,validate}" >&2
echo " resume: re-run this script — the failed executor session is resumed automatically" >&2
# execute_unit printed the failure detail (task failure: errors, logs,
# resume command — or phase-commit failure: the hand-fix command).
echo "✗ ERROR: phase $phase did not complete — see the error output above" >&2
exit 1
fi
echo "✓ phase $phase complete"
+3 -3
View File
@@ -40,7 +40,7 @@ build_pi_args
if execute_unit "$unit"; then
exit 0
fi
echo "✗ ERROR: task $unit FAILED after $MAX_FIX_ATTEMPTS attempts" >&2
echo " reports: $(unit_report_dir "$unit")/$(unit_base "$unit").a*.{md,err,validate}" >&2
echo " resume: re-run this script — the failed executor session is resumed automatically" >&2
# execute_unit printed the failure detail (task failure: errors, logs,
# resume command — or phase-commit failure: the hand-fix command).
echo "✗ ERROR: $unit did not complete — see the error output above" >&2
exit 1