@jonit-dev/night-watch-cli 1.8.8-beta.0 → 1.8.8-beta.10

package/dist/scripts/night-watch-qa-cron.sh

@@ -25,6 +25,7 @@ PROVIDER_CMD="${NW_PROVIDER_CMD:-claude}"
 PROVIDER_LABEL="${NW_PROVIDER_LABEL:-}"
 BRANCH_PATTERNS_RAW="${NW_BRANCH_PATTERNS:-feat/,night-watch/}"
 SKIP_LABEL="${NW_QA_SKIP_LABEL:-skip-qa}"
+VALIDATED_LABEL="${NW_QA_VALIDATED_LABEL:-e2e-validated}"
 QA_ARTIFACTS="${NW_QA_ARTIFACTS:-both}"
 QA_AUTO_INSTALL_PLAYWRIGHT="${NW_QA_AUTO_INSTALL_PLAYWRIGHT:-1}"
 SCRIPT_START_TIME=$(date +%s)
@@ -55,6 +56,16 @@ emit_result() {
   fi
 }
 
+LABEL_ENSURED=0
+ensure_validated_label() {
+  if [ "${LABEL_ENSURED}" -eq 1 ]; then return 0; fi
+  gh label create "${VALIDATED_LABEL}" \
+    --description "PR acceptance requirements validated by e2e/integration tests" \
+    --color "0e8a16" \
+    --force 2>/dev/null || true
+  LABEL_ENSURED=1
+}
+
 # ── Global Job Queue Gate ────────────────────────────────────────────────────
 # Atomically claim a DB slot or enqueue for later dispatch — no flock needed.
 if [ "${NW_QUEUE_ENABLED:-0}" = "1" ]; then
@@ -330,8 +341,8 @@ validate_qa_evidence() {
   fi
 
   if ! pr_has_qa_generated_files "${pr_number}"; then
-    log "FAIL-QA-EVIDENCE: PR #${pr_number} has QA marker comment but no qa-artifacts/ or tests/*/qa/ files"
-    return 1
+    log "WARN-QA-EVIDENCE: PR #${pr_number} has QA marker comment but no qa-artifacts/ or tests/*/qa/ files"
+    return 2
   fi
 
   if [ "${QA_ARTIFACTS}" = "screenshot" ] || [ "${QA_ARTIFACTS}" = "both" ]; then
@@ -487,13 +498,16 @@ fi
 EXIT_CODE=0
 PROCESSED_PRS_CSV=""
 PASSING_PRS_CSV=""
+VALIDATED_PRS_CSV=""
 ISSUES_FOUND_PRS_CSV=""
 NO_TESTS_PRS_CSV=""
 UNCLASSIFIED_PRS_CSV=""
+WARNING_PRS_CSV=""
 FAILED_AUTOMATION_PRS_CSV=""
 FAILED_PR=""
 FAILED_REASON="unknown"
 QA_SCREENSHOT_SUMMARY=""
+QA_WARNING_SUMMARY=""
 
 # Process each PR that needs QA
 for pr_ref in ${PRS_NEEDING_QA}; do
@@ -595,34 +609,56 @@ for pr_ref in ${PRS_NEEDING_QA}; do
       FAILED_PR="#${pr_num}"
       FAILED_REASON="invalid_provider_output"
       EXIT_CODE=1
-    elif ! validate_qa_evidence "${pr_num}"; then
-      FAILED_AUTOMATION_PRS_CSV=$(append_csv "${FAILED_AUTOMATION_PRS_CSV}" "#${pr_num}")
-      FAILED_PR="#${pr_num}"
-      FAILED_REASON="qa_evidence_validation_failed"
-      EXIT_CODE=1
     else
-      QA_OUTCOME=$(classify_qa_comment_outcome "${pr_num}")
-      case "${QA_OUTCOME}" in
-        passing)
-          PASSING_PRS_CSV=$(append_csv "${PASSING_PRS_CSV}" "#${pr_num}")
-          ;;
-        issues_found)
-          ISSUES_FOUND_PRS_CSV=$(append_csv "${ISSUES_FOUND_PRS_CSV}" "#${pr_num}")
-          ;;
-        no_tests_needed)
-          NO_TESTS_PRS_CSV=$(append_csv "${NO_TESTS_PRS_CSV}" "#${pr_num}")
-          ;;
-        *)
-          UNCLASSIFIED_PRS_CSV=$(append_csv "${UNCLASSIFIED_PRS_CSV}" "#${pr_num}")
-          ;;
-      esac
-
-      PR_FIRST_SCREENSHOT=$(get_qa_screenshot_links "${pr_num}" | head -n 1 || true)
-      if [ -n "${PR_FIRST_SCREENSHOT}" ]; then
-        QA_SCREENSHOT_SUMMARY="${QA_SCREENSHOT_SUMMARY}${QA_SCREENSHOT_SUMMARY:+$'\n'}#${pr_num}: ${PR_FIRST_SCREENSHOT}"
+      if validate_qa_evidence "${pr_num}"; then
+        QA_EVIDENCE_STATUS=0
+      else
+        QA_EVIDENCE_STATUS=$?
+      fi
+      if [ ${QA_EVIDENCE_STATUS} -eq 2 ]; then
+        WARNING_PRS_CSV=$(append_csv "${WARNING_PRS_CSV}" "#${pr_num}")
+        QA_WARNING_SUMMARY="${QA_WARNING_SUMMARY}${QA_WARNING_SUMMARY:+$'\n'}#${pr_num}: no qa-artifacts/ or tests/*/qa/ files"
+        log "QA: PR #${pr_num} — provider completed with warning-only QA evidence"
+      elif [ ${QA_EVIDENCE_STATUS} -ne 0 ]; then
+        FAILED_AUTOMATION_PRS_CSV=$(append_csv "${FAILED_AUTOMATION_PRS_CSV}" "#${pr_num}")
+        FAILED_PR="#${pr_num}"
+        FAILED_REASON="qa_evidence_validation_failed"
+        EXIT_CODE=1
+      else
+        QA_OUTCOME=$(classify_qa_comment_outcome "${pr_num}")
+        case "${QA_OUTCOME}" in
+          passing)
+            PASSING_PRS_CSV=$(append_csv "${PASSING_PRS_CSV}" "#${pr_num}")
+            # Apply e2e-validated label
+            ensure_validated_label
+            gh pr edit "${pr_num}" --add-label "${VALIDATED_LABEL}" 2>/dev/null || true
+            VALIDATED_PRS_CSV=$(append_csv "${VALIDATED_PRS_CSV}" "#${pr_num}")
+            log "QA: PR #${pr_num} — added '${VALIDATED_LABEL}' label (tests passing)"
+            ;;
+          issues_found)
+            ISSUES_FOUND_PRS_CSV=$(append_csv "${ISSUES_FOUND_PRS_CSV}" "#${pr_num}")
+            # Remove e2e-validated label if present
+            gh pr edit "${pr_num}" --remove-label "${VALIDATED_LABEL}" 2>/dev/null || true
+            log "QA: PR #${pr_num} — removed '${VALIDATED_LABEL}' label (issues found)"
+            ;;
+          no_tests_needed)
+            NO_TESTS_PRS_CSV=$(append_csv "${NO_TESTS_PRS_CSV}" "#${pr_num}")
+            # Remove e2e-validated label — no tests doesn't prove acceptance
+            gh pr edit "${pr_num}" --remove-label "${VALIDATED_LABEL}" 2>/dev/null || true
+            log "QA: PR #${pr_num} — removed '${VALIDATED_LABEL}' label (no tests needed)"
+            ;;
+          *)
+            UNCLASSIFIED_PRS_CSV=$(append_csv "${UNCLASSIFIED_PRS_CSV}" "#${pr_num}")
+            ;;
+        esac
+
+        PR_FIRST_SCREENSHOT=$(get_qa_screenshot_links "${pr_num}" | head -n 1 || true)
+        if [ -n "${PR_FIRST_SCREENSHOT}" ]; then
+          QA_SCREENSHOT_SUMMARY="${QA_SCREENSHOT_SUMMARY}${QA_SCREENSHOT_SUMMARY:+$'\n'}#${pr_num}: ${PR_FIRST_SCREENSHOT}"
+        fi
+
+        log "QA: PR #${pr_num} — provider completed with verifiable QA evidence"
       fi
-
-      log "QA: PR #${pr_num} — provider completed with verifiable QA evidence"
     fi
   fi
 
@@ -633,9 +669,11 @@ cleanup_worktrees "${PROJECT_DIR}"
 
 FINAL_PROCESSED_PRS_CSV="${PROCESSED_PRS_CSV:-${PRS_NEEDING_QA_CSV}}"
 PASSING_PRS_SUMMARY=$(csv_or_none "${PASSING_PRS_CSV}")
+VALIDATED_PRS_SUMMARY=$(csv_or_none "${VALIDATED_PRS_CSV}")
 ISSUES_FOUND_PRS_SUMMARY=$(csv_or_none "${ISSUES_FOUND_PRS_CSV}")
 NO_TESTS_PRS_SUMMARY=$(csv_or_none "${NO_TESTS_PRS_CSV}")
 UNCLASSIFIED_PRS_SUMMARY=$(csv_or_none "${UNCLASSIFIED_PRS_CSV}")
+WARNING_PRS_SUMMARY=$(csv_or_none "${WARNING_PRS_CSV}")
 FAILED_AUTOMATION_PRS_SUMMARY=$(csv_or_none "${FAILED_AUTOMATION_PRS_CSV}")
 FAILED_PR_SUMMARY=$(csv_or_none "${FAILED_PR}")
 
@@ -643,25 +681,56 @@ QA_TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START_TIME ))
 log "OUTCOME: exit_code=${EXIT_CODE} total_elapsed=${QA_TOTAL_ELAPSED}s processed_prs=${FINAL_PROCESSED_PRS_CSV:-none}"
 
 if [ ${EXIT_CODE} -eq 0 ]; then
-  log "DONE: QA runner completed successfully"
-  TELEGRAM_SUCCESS_BODY="Project: ${PROJECT_NAME}
+  if [ -n "${WARNING_PRS_CSV}" ]; then
+    log "DONE-WARN: QA runner completed with warnings"
+    TELEGRAM_WARNING_BODY="Project: ${PROJECT_NAME}
 Provider (model): ${PROVIDER_MODEL_DISPLAY}
 Artifacts: ${QA_ARTIFACTS_DESC} (mode=${QA_ARTIFACTS})
 Processed PRs: ${FINAL_PROCESSED_PRS_CSV}
 Passing tests: ${PASSING_PRS_SUMMARY}
+E2E validated: ${VALIDATED_PRS_SUMMARY}
 Issues found by tests: ${ISSUES_FOUND_PRS_SUMMARY}
 No tests needed: ${NO_TESTS_PRS_SUMMARY}
-Reported (unclassified): ${UNCLASSIFIED_PRS_SUMMARY}"
-  if [ -n "${QA_SCREENSHOT_SUMMARY}" ]; then
-    TELEGRAM_SUCCESS_BODY="${TELEGRAM_SUCCESS_BODY}
+Reported (unclassified): ${UNCLASSIFIED_PRS_SUMMARY}
+Warnings: ${WARNING_PRS_SUMMARY}"
+    if [ -n "${QA_WARNING_SUMMARY}" ]; then
+      TELEGRAM_WARNING_BODY="${TELEGRAM_WARNING_BODY}
+Warning details:
+${QA_WARNING_SUMMARY}"
+    fi
+    if [ -n "${QA_SCREENSHOT_SUMMARY}" ]; then
+      TELEGRAM_WARNING_BODY="${TELEGRAM_WARNING_BODY}
 Screenshot links:
 ${QA_SCREENSHOT_SUMMARY}"
-  fi
-  send_telegram_status_message "🧪 Night Watch QA: completed" "${TELEGRAM_SUCCESS_BODY}"
-  if [ -n "${REPO}" ]; then
-    emit_result "success_qa" "prs=${FINAL_PROCESSED_PRS_CSV}|passing=${PASSING_PRS_SUMMARY}|issues=${ISSUES_FOUND_PRS_SUMMARY}|no_tests=${NO_TESTS_PRS_SUMMARY}|unclassified=${UNCLASSIFIED_PRS_SUMMARY}|repo=${REPO}"
+    fi
+    send_telegram_status_message "🧪 Night Watch QA: warning" "${TELEGRAM_WARNING_BODY}"
+    if [ -n "${REPO}" ]; then
+      emit_result "warning_qa" "prs=${FINAL_PROCESSED_PRS_CSV}|passing=${PASSING_PRS_SUMMARY}|validated=${VALIDATED_PRS_SUMMARY}|issues=${ISSUES_FOUND_PRS_SUMMARY}|no_tests=${NO_TESTS_PRS_SUMMARY}|unclassified=${UNCLASSIFIED_PRS_SUMMARY}|warnings=${WARNING_PRS_SUMMARY}|repo=${REPO}"
+    else
+      emit_result "warning_qa" "prs=${FINAL_PROCESSED_PRS_CSV}|passing=${PASSING_PRS_SUMMARY}|validated=${VALIDATED_PRS_SUMMARY}|issues=${ISSUES_FOUND_PRS_SUMMARY}|no_tests=${NO_TESTS_PRS_SUMMARY}|unclassified=${UNCLASSIFIED_PRS_SUMMARY}|warnings=${WARNING_PRS_SUMMARY}"
+    fi
   else
-    emit_result "success_qa" "prs=${FINAL_PROCESSED_PRS_CSV}|passing=${PASSING_PRS_SUMMARY}|issues=${ISSUES_FOUND_PRS_SUMMARY}|no_tests=${NO_TESTS_PRS_SUMMARY}|unclassified=${UNCLASSIFIED_PRS_SUMMARY}"
+    log "DONE: QA runner completed successfully"
+    TELEGRAM_SUCCESS_BODY="Project: ${PROJECT_NAME}
+Provider (model): ${PROVIDER_MODEL_DISPLAY}
+Artifacts: ${QA_ARTIFACTS_DESC} (mode=${QA_ARTIFACTS})
+Processed PRs: ${FINAL_PROCESSED_PRS_CSV}
+Passing tests: ${PASSING_PRS_SUMMARY}
+E2E validated: ${VALIDATED_PRS_SUMMARY}
+Issues found by tests: ${ISSUES_FOUND_PRS_SUMMARY}
+No tests needed: ${NO_TESTS_PRS_SUMMARY}
+Reported (unclassified): ${UNCLASSIFIED_PRS_SUMMARY}"
+    if [ -n "${QA_SCREENSHOT_SUMMARY}" ]; then
+      TELEGRAM_SUCCESS_BODY="${TELEGRAM_SUCCESS_BODY}
+Screenshot links:
+${QA_SCREENSHOT_SUMMARY}"
+    fi
+    send_telegram_status_message "🧪 Night Watch QA: completed" "${TELEGRAM_SUCCESS_BODY}"
+    if [ -n "${REPO}" ]; then
+      emit_result "success_qa" "prs=${FINAL_PROCESSED_PRS_CSV}|passing=${PASSING_PRS_SUMMARY}|validated=${VALIDATED_PRS_SUMMARY}|issues=${ISSUES_FOUND_PRS_SUMMARY}|no_tests=${NO_TESTS_PRS_SUMMARY}|unclassified=${UNCLASSIFIED_PRS_SUMMARY}|repo=${REPO}"
+    else
+      emit_result "success_qa" "prs=${FINAL_PROCESSED_PRS_CSV}|passing=${PASSING_PRS_SUMMARY}|validated=${VALIDATED_PRS_SUMMARY}|issues=${ISSUES_FOUND_PRS_SUMMARY}|no_tests=${NO_TESTS_PRS_SUMMARY}|unclassified=${UNCLASSIFIED_PRS_SUMMARY}"
+    fi
   fi
 elif [ ${EXIT_CODE} -eq 124 ]; then
   log "TIMEOUT: QA runner killed after ${MAX_RUNTIME}s"

package/dist/scripts/test-helpers.bats

@@ -75,3 +75,48 @@ teardown() {
 
   [ "${result}" = "02-test-prd.md" ]
 }
+
+# ── pr-resolver lock acquisition ─────────────────────────────────────────────
+
+@test "pr-resolver lock acquisition: acquire_lock succeeds when no lock exists" {
+  local test_lock="/tmp/nw-test-resolver-$$.lock"
+
+  # Ensure clean state
+  rm -f "${test_lock}"
+
+  run acquire_lock "${test_lock}"
+  [ "$status" -eq 0 ]
+  [ -f "${test_lock}" ]
+
+  # PID written to lock file must be the current test process
+  local lock_pid
+  lock_pid=$(cat "${test_lock}")
+  [ -n "${lock_pid}" ]
+
+  rm -f "${test_lock}"
+}
+
+@test "pr-resolver lock acquisition: acquire_lock fails when active lock exists" {
+  local test_lock="/tmp/nw-test-resolver-active-$$.lock"
+
+  # Write current PID as an active lock holder
+  echo $$ > "${test_lock}"
+
+  run acquire_lock "${test_lock}"
+  [ "$status" -eq 1 ]
+
+  rm -f "${test_lock}"
+}
+
+@test "pr-resolver lock acquisition: acquire_lock removes stale lock and succeeds" {
+  local test_lock="/tmp/nw-test-resolver-stale-$$.lock"
+
+  # Write a PID that does not exist (use a very high number unlikely to be running)
+  echo "999999999" > "${test_lock}"
+
+  run acquire_lock "${test_lock}"
+  [ "$status" -eq 0 ]
+  [ -f "${test_lock}" ]
+
+  rm -f "${test_lock}"
+}

package/dist/templates/night-watch-pr-reviewer.md

@@ -21,7 +21,8 @@ If current PR code or review feedback conflicts with the PRD context, call out t
 ## Important: Early Exit
 
 - If there are **no open PRs** on `night-watch/` or `feat/` branches, **stop immediately** and report "No PRs to review."
-- If all open PRs have **no merge conflicts**, **passing CI**, and **review score >= 80** (or no review score yet), **stop immediately** and report "All PRs are in good shape."
+- If all open PRs have **no merge conflicts**, **passing CI**, and **review score >= 80**, **stop immediately** and report "All PRs are in good shape."
+- If a PR has no review score yet, it needs a first review — do NOT skip it.
 - Do **NOT** loop or retry. Process each PR **once** per run. After processing all PRs, stop.
 - Do **NOT** re-check PRs after pushing fixes -- the CI will re-run automatically on the next push.
 

package/dist/templates/pr-reviewer.md

@@ -21,7 +21,8 @@ If current PR code or review feedback conflicts with the PRD context, call out t
 ## Important: Early Exit
 
 - If there are **no open PRs** on `night-watch/` or `feat/` branches, **stop immediately** and report "No PRs to review."
-- If all open PRs have **no merge conflicts**, **passing CI**, and **review score >= 80** (or no review score yet), **stop immediately** and report "All PRs are in good shape."
+- If all open PRs have **no merge conflicts**, **passing CI**, and **review score >= 80**, **stop immediately** and report "All PRs are in good shape."
+- If a PR has no review score yet, it needs a first review — do NOT skip it.
 - Do **NOT** loop or retry. Process each PR **once** per run. After processing all PRs, stop.
 - Do **NOT** re-check PRs after pushing fixes -- the CI will re-run automatically on the next push.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jonit-dev/night-watch-cli",
-  "version": "1.8.8-beta.0",
+  "version": "1.8.8-beta.10",
   "description": "AI agent that implements your specs, opens PRs, and reviews code overnight. Queue GitHub issues or PRDs, wake up to pull requests.",
   "type": "module",
   "bin": {