feat: live deployment with automated acceptance checklist (phase 13)

- APP_INTERNAL_URL: in-network base URL for §5.2 callbacks and signed
  attachment URLs handed to the external services (compose: http://app:8787)
- work-performer image runs as the node user with ~/.claude mounted into
  /home/node — the claude CLI refuses --dangerously-skip-permissions as root
- scripts/acceptance.sh: re-run-safe live verification of the §13 checklist
  (demo import within one poll, subdivide sum=1 + editable, extend sibling,
  publish/bounty math, decline/claim/approve, changes-requested loop,
  approval award in metrics, unassign, AI job through real Claude Code with
  signed idempotent callback, breaker independence between the two services)
- README/DECISIONS: sudo HOME gotcha, internal URL, non-root performer

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
etalon
2026-06-12 21:06:23 +02:00
parent c69c028028
commit 6265ffa894
10 changed files with 230 additions and 8 deletions
+168
View File
@@ -0,0 +1,168 @@
#!/usr/bin/env bash
# Live acceptance checklist (§13) against a running, seeded stack with the
# mocks profile. Exercises: demo ticket import → subdivide → extend →
# publish → claim/decline/approve → work → review → award → AI assignment →
# breaker independence.
set -euo pipefail
BASE="${BASE_URL:-http://localhost:8787}"
PASS="demo-pass-123"
TMP=$(mktemp -d)
trap 'rm -rf "$TMP"' EXIT
fail() { echo "ACCEPTANCE FAIL: $*" >&2; exit 1; }
ok() { echo "$*"; }
jqr() { python3 -c "import sys,json;d=json.load(sys.stdin);print(eval(sys.argv[1]))" "$1"; }
login() { # $1 email → jar at $TMP/$1.jar, csrf in $TMP/$1.csrf
local jar="$TMP/$1.jar"
curl -fsS -c "$jar" -H 'Content-Type: application/json' \
-d "{\"email\":\"$1\",\"password\":\"$PASS\"}" "$BASE/api/v1/auth/login" -o /dev/null \
|| fail "login $1"
awk '$6=="bb_csrf" {print $7}' "$jar" > "$TMP/$1.csrf"
}
api() { # $1 user, $2 method, $3 path, [$4 json body] → stdout
local jar="$TMP/$1.jar" csrf
csrf=$(cat "$TMP/$1.csrf")
if [ $# -ge 4 ]; then
curl -fsS -b "$jar" -X "$2" -H "X-CSRF-Token: $csrf" \
-H 'Content-Type: application/json' -d "$4" "$BASE$3"
else
curl -fsS -b "$jar" -X "$2" -H "X-CSRF-Token: $csrf" "$BASE$3"
fi
}
echo "1. consultant login + demo tickets imported within one poll interval"
login clara@example.com
for i in $(seq 1 24); do
COUNT=$(api clara@example.com GET /api/v1/consultant/board | jqr "len(d['tasks'])")
[ "$COUNT" -ge 5 ] && break
sleep 5
done
[ "$COUNT" -ge 5 ] || fail "expected ≥5 imported demo tickets, got $COUNT"
ok "demo sync imported $COUNT tickets"
BOARD=$(api clara@example.com GET /api/v1/consultant/board)
ROOT=$(echo "$BOARD" | jqr "[t for t in d['tasks'] if t['status']=='imported'][0]['id']")
ROOT_BUDGET=$(echo "$BOARD" | jqr "[t for t in d['tasks'] if t['id']=='$ROOT'][0]['budget']")
ok "picked imported root $ROOT (budget $ROOT_BUDGET)"
echo "2. subdivide → N children, coefficients sum to 1, editable"
api clara@example.com POST "/api/v1/tasks/$ROOT/subdivide" \
'{"note":"split it","constraints":{"minTasks":3,"maxTasks":3}}' > /dev/null
for i in $(seq 1 30); do
KIDS=$(api clara@example.com GET "/api/v1/consultant/board" | \
jqr "len([t for t in d['tasks'] if t.get('parentId')=='$ROOT'])")
[ "$KIDS" -ge 3 ] && break
sleep 2
done
[ "$KIDS" -ge 3 ] || fail "subdivision produced $KIDS children"
SUM=$(api clara@example.com GET "/api/v1/consultant/board" | \
jqr "round(sum(t['effortCoefficient'] for t in d['tasks'] if t.get('parentId')=='$ROOT' and t['origin']=='subdivided'),4)")
[ "$SUM" = "1.0" ] || fail "children coefficients sum to $SUM"
ok "3 children, coefficient sum exactly 1.0"
CHILD1=$(api clara@example.com GET "/api/v1/consultant/board" | \
jqr "[t for t in d['tasks'] if t.get('parentId')=='$ROOT'][0]['id']")
CHILD1V=$(api clara@example.com GET "/api/v1/tasks/$CHILD1" | jqr "d['task']['version']")
api clara@example.com PATCH "/api/v1/tasks/$CHILD1" \
"{\"version\":$CHILD1V,\"effortCoefficient\":0.5,\"budget\":2000}" > /dev/null
B=$(api clara@example.com GET "/api/v1/tasks/$CHILD1" | jqr "float(d['task']['bounty'])")
[ "$B" = "1000.0" ] || fail "edited bounty = $B, want 1000 (0.5 × 2000)"
ok "edit recomputed bounty = coefficient × budget"
echo "3. extend creates exactly one sibling"
BEFORE=$(api clara@example.com GET /api/v1/consultant/board | \
jqr "len([t for t in d['tasks'] if t['origin']=='extended'])")
api clara@example.com POST "/api/v1/tasks/$ROOT/extend" '{"note":"add CSV presets"}' > /dev/null
for i in $(seq 1 30); do
AFTER=$(api clara@example.com GET /api/v1/consultant/board | \
jqr "len([t for t in d['tasks'] if t['origin']=='extended'])")
[ "$AFTER" -eq $((BEFORE + 1)) ] && break
sleep 2
done
[ "$AFTER" -eq $((BEFORE + 1)) ] || fail "extension count $AFTER (was $BEFORE)"
ok "extension created exactly one sibling"
echo "4. publish → developer board with bounty = coefficient × budget"
api clara@example.com POST "/api/v1/tasks/$CHILD1/publish" '{}' > /dev/null
login dev1@example.com
DEVB=$(api dev1@example.com GET /api/v1/board)
DB=$(echo "$DEVB" | jqr "float([t for t in d['tasks'] if t['id']=='$CHILD1'][0]['bounty'])")
[ "$DB" = "1000.0" ] || fail "published task not on dev board with bounty 1000 (got $DB)"
ok "developer sees published task, bounty 1000"
echo "5. claim → decline → claim → approve → work → changes → approve → award"
api dev1@example.com POST "/api/v1/tasks/$CHILD1/claim" '{"note":"mine!"}' > /dev/null
api clara@example.com POST "/api/v1/tasks/$CHILD1/decline-claim" "{\"developerId\":\"$(api dev1@example.com GET /api/v1/auth/me | jqr "d['user']['id']")\"}" > /dev/null
ST=$(api clara@example.com GET "/api/v1/tasks/$CHILD1" | jqr "d['task']['status']")
[ "$ST" = "published" ] || fail "after decline: $ST"
ok "decline returned task to published"
TOTAL_BEFORE=$(api dev1@example.com GET /api/v1/developer/metrics | jqr "float(d['totalBounty'])")
api dev1@example.com POST "/api/v1/tasks/$CHILD1/claim" '{"note":"please"}' > /dev/null
DEVID=$(api dev1@example.com GET /api/v1/auth/me | jqr "d['user']['id']")
api clara@example.com POST "/api/v1/tasks/$CHILD1/approve-claim" "{\"developerId\":\"$DEVID\"}" > /dev/null
api dev1@example.com POST "/api/v1/tasks/$CHILD1/start" '{}' > /dev/null
api dev1@example.com POST "/api/v1/tasks/$CHILD1/comments" '{"body":"<p>done, see <b>notes</b></p>"}' > /dev/null
api dev1@example.com POST "/api/v1/tasks/$CHILD1/time" '{"minutes":45,"note":"impl"}' > /dev/null
api dev1@example.com POST "/api/v1/tasks/$CHILD1/submit-review" '{}' > /dev/null
api clara@example.com POST "/api/v1/tasks/$CHILD1/review" '{"decision":"request_changes","note":"edge cases"}' > /dev/null
api dev1@example.com POST "/api/v1/tasks/$CHILD1/start" '{}' > /dev/null
api dev1@example.com POST "/api/v1/tasks/$CHILD1/submit-review" '{}' > /dev/null
api clara@example.com POST "/api/v1/tasks/$CHILD1/review" \
'{"decision":"approve","note":"good","checklist":[{"criterion":"works","ok":true}]}' > /dev/null
ST=$(api clara@example.com GET "/api/v1/tasks/$CHILD1" | jqr "d['task']['status']")
[ "$ST" = "approved" ] || fail "after approve: $ST"
TOTAL=$(api dev1@example.com GET /api/v1/developer/metrics | jqr "float(d['totalBounty'])")
DELTA=$(python3 -c "print($TOTAL - $TOTAL_BEFORE)")
[ "$DELTA" = "1000.0" ] || fail "developer metrics delta $DELTA, want 1000"
ok "full lifecycle approved; bountyAwards +1000 reflected in metrics"
echo "6. unassign returns an assigned task to the board"
CHILD2=$(api clara@example.com GET "/api/v1/consultant/board" | \
jqr "[t for t in d['tasks'] if t.get('parentId')=='$ROOT' and t['status']=='atomized'][0]['id']")
api clara@example.com POST "/api/v1/tasks/$CHILD2/publish" '{}' > /dev/null
api dev1@example.com POST "/api/v1/tasks/$CHILD2/claim" '{}' > /dev/null
api clara@example.com POST "/api/v1/tasks/$CHILD2/approve-claim" "{\"developerId\":\"$DEVID\"}" > /dev/null
api clara@example.com POST "/api/v1/tasks/$CHILD2/unassign" '{}' > /dev/null
ST=$(api clara@example.com GET "/api/v1/tasks/$CHILD2" | jqr "d['task']['status']")
[ "$ST" = "published" ] || fail "after unassign: $ST"
ok "unassign returned task to published"
echo "7. AI assignment → §5.2 job → signed callback → in_review"
api clara@example.com POST "/api/v1/tasks/$CHILD2/assign-ai" \
'{"context":{"instructions":"create SUMMARY.md only; do not write code"}}' > /dev/null
for i in $(seq 1 90); do
ST=$(api clara@example.com GET "/api/v1/tasks/$CHILD2" | jqr "d['task']['status']")
[ "$ST" = "in_review" ] && break
sleep 5
done
[ "$ST" = "in_review" ] || fail "AI task status after wait: $ST"
ok "work performer callback moved the task to in_review"
api clara@example.com POST "/api/v1/tasks/$CHILD2/review" '{"decision":"approve","note":"AI ok"}' > /dev/null
ok "consultant reviewed AI work like a human's"
echo "8. breaker independence: stopping the atomizer must not affect the work performer"
sudo -n docker compose --profile mocks stop atomizer-mock > /dev/null 2>&1 \
|| docker compose --profile mocks stop atomizer-mock > /dev/null
CHILD3=$(api clara@example.com GET "/api/v1/consultant/board" | \
jqr "[t for t in d['tasks'] if t['status']=='atomized'][0]['id']")
for i in 1 2 3; do
api clara@example.com POST "/api/v1/tasks/$CHILD3/subdivide" '{"note":"x","confirmReplace":true}' > /dev/null || true
sleep 16
done
HEALTH=$(api clara@example.com GET /api/v1/service-health)
A_OK=$(echo "$HEALTH" | jqr "d['atomizer']['healthy']")
W_OK=$(echo "$HEALTH" | jqr "d['workPerformer']['healthy']")
[ "$A_OK" = "False" ] || fail "atomizer should be down"
[ "$W_OK" = "True" ] || fail "work performer must be unaffected"
BREAKER=$(echo "$HEALTH" | jqr "d['atomizer']['breaker']")
ok "atomizer down (breaker: $BREAKER), work performer healthy — independent"
sudo -n docker compose --profile mocks start atomizer-mock > /dev/null 2>&1 \
|| docker compose --profile mocks start atomizer-mock > /dev/null
ok "atomizer restarted"
echo
echo "ACCEPTANCE PASS"