shipwright-cli 3.0.0 → 3.1.0

package/config/event-schema.json

@@ -15,12 +15,15 @@
       "required": ["job_id"],
       "optional": ["error", "stage"]
     },
-    "stage.started": { "required": ["job_id", "stage"], "optional": [] },
+    "stage.started": { "required": ["stage"], "optional": ["issue", "job_id"] },
     "stage.completed": {
-      "required": ["job_id", "stage"],
-      "optional": ["duration_s"]
+      "required": ["stage"],
+      "optional": ["issue", "job_id", "duration_s", "result"]
+    },
+    "stage.failed": {
+      "required": ["stage"],
+      "optional": ["issue", "job_id", "error", "error_class", "duration_s"]
     },
-    "stage.failed": { "required": ["job_id", "stage"], "optional": ["error"] },
     "daemon.started": { "required": [], "optional": ["pid", "mode"] },
     "daemon.stopped": { "required": [], "optional": ["reason"] },
     "daemon.claimed": { "required": ["issue"], "optional": ["repo", "title"] },
@@ -76,6 +79,140 @@
       "required": ["session_id"],
       "optional": ["template", "agents"]
     },
-    "session.ended": { "required": ["session_id"], "optional": ["duration_s"] }
+    "session.ended": { "required": ["session_id"], "optional": ["duration_s"] },
+    "memory.fix_outcome": {
+      "required": ["pattern"],
+      "optional": ["outcome", "repo"]
+    },
+    "memory.global_aggregated": {
+      "required": [],
+      "optional": ["repo", "patterns_promoted"]
+    },
+    "memory.not_available": {
+      "required": ["path"],
+      "optional": ["action"]
+    },
+    "memory.export": {
+      "required": [],
+      "optional": ["repo"]
+    },
+    "cost.budget_unconfigured": {
+      "required": ["status"],
+      "optional": []
+    },
+    "scale.recommendation": {
+      "required": [],
+      "optional": ["iterations", "coverage", "modules", "has_recommendations"]
+    },
+    "pr.skipped": {
+      "required": ["issue"],
+      "optional": ["reason"]
+    },
+    "pr.rejected": {
+      "required": ["issue"],
+      "optional": ["reason"]
+    },
+    "intelligence.compose": {
+      "required": [],
+      "optional": ["stage_count", "complexity"]
+    },
+    "intelligence.synthesize": {
+      "required": [],
+      "optional": ["fix_count", "cause_count"]
+    },
+    "simulation.complete": {
+      "required": [],
+      "optional": ["issue", "concerns"]
+    },
+    "daemon.hard_limit": {
+      "required": ["issue"],
+      "optional": ["elapsed_s", "limit_s", "pid"]
+    },
+    "daemon.stalled": {
+      "required": ["issue"],
+      "optional": ["no_progress", "elapsed_s", "pid"]
+    },
+    "daemon.nudge": {
+      "required": ["issue"],
+      "optional": ["no_progress", "stage", "elapsed_s"]
+    },
+    "daemon.stuck_kill": {
+      "required": ["issue"],
+      "optional": [
+        "no_progress",
+        "repeated_errors",
+        "stage",
+        "elapsed_s",
+        "pid",
+        "reason"
+      ]
+    },
+    "convergence.tests_passed": {
+      "required": [],
+      "optional": ["issue", "cycle"]
+    },
+    "vitals.snapshot": {
+      "required": [],
+      "optional": [
+        "issue",
+        "stage",
+        "iteration",
+        "diff_count",
+        "files_changed",
+        "error"
+      ]
+    },
+    "retry.classified": {
+      "required": ["stage"],
+      "optional": ["issue", "attempt", "error_class"]
+    },
+    "retry.escalated": {
+      "required": ["stage"],
+      "optional": ["issue", "reason"]
+    },
+    "retry.skipped": {
+      "required": ["stage"],
+      "optional": ["issue", "reason"]
+    },
+    "pipeline.anomaly": {
+      "required": ["stage"],
+      "optional": ["metric", "value", "severity"]
+    },
+    "pipeline.cost": {
+      "required": [],
+      "optional": ["issue", "stage", "cost_usd", "model"]
+    },
+    "pipeline.cleanup": {
+      "required": [],
+      "optional": ["issue", "reason"]
+    },
+    "pipeline.comment_failed": {
+      "required": [],
+      "optional": ["issue"]
+    },
+    "loop.iteration_start": {
+      "required": ["iteration"],
+      "optional": ["issue", "goal"]
+    },
+    "loop.iteration_complete": {
+      "required": ["iteration"],
+      "optional": ["issue", "test_result", "duration_s"]
+    },
+    "loop.restart": {
+      "required": [],
+      "optional": ["issue", "restart_count", "reason"]
+    },
+    "loop.stuckness_detected": {
+      "required": [],
+      "optional": ["issue", "iteration", "reason"]
+    },
+    "stage.skipped": {
+      "required": ["stage"],
+      "optional": ["issue", "reason"]
+    },
+    "stage.artifact_miss": {
+      "required": ["stage"],
+      "optional": ["issue"]
+    }
   }
 }

package/config/policy.json

@@ -222,5 +222,13 @@
     "default_model": "sonnet",
     "promote_threshold_tasks": 10,
     "promote_threshold_success_rate": 85
+  },
+  "decision": {
+    "enabled": false,
+    "cycle_interval_seconds": 1800,
+    "tiers_file": "config/decision-tiers.json",
+    "outcome_learning_enabled": true,
+    "outcome_min_samples": 10,
+    "dedup_window_days": 7
   }
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "shipwright-cli",
-  "version": "3.0.0",
+  "version": "3.1.0",
   "description": "Orchestrate autonomous Claude Code agent teams in tmux",
   "bin": {
     "shipwright": "scripts/sw",
@@ -36,9 +36,9 @@
     "dashboard:test": "vitest run --config dashboard/vitest.config.ts",
     "dashboard:test:watch": "vitest --config dashboard/vitest.config.ts",
     "dashboard:test:coverage": "vitest run --config dashboard/vitest.config.ts --coverage",
-    "test": "bash scripts/sw-agi-roadmap-test.sh && bash scripts/sw-activity-test.sh && bash scripts/sw-adaptive-test.sh && bash scripts/sw-adversarial-test.sh && bash scripts/sw-architecture-enforcer-test.sh && bash scripts/sw-auth-test.sh && bash scripts/sw-autonomous-test.sh && bash scripts/sw-changelog-test.sh && bash scripts/sw-checkpoint-test.sh && bash scripts/sw-ci-test.sh && bash scripts/sw-cleanup-test.sh && bash scripts/sw-code-review-test.sh && bash scripts/sw-connect-test.sh && bash scripts/sw-context-test.sh && bash scripts/sw-cost-test.sh && bash scripts/sw-daemon-test.sh && bash scripts/sw-dashboard-test.sh && bash scripts/sw-db-test.sh && bash scripts/sw-decompose-test.sh && bash scripts/sw-deps-test.sh && bash scripts/sw-developer-simulation-test.sh && bash scripts/sw-discovery-test.sh && bash scripts/sw-doc-fleet-test.sh && bash scripts/sw-docs-agent-test.sh && bash scripts/sw-docs-test.sh && bash scripts/sw-doctor-test.sh && bash scripts/sw-dora-test.sh && bash scripts/sw-durable-test.sh && bash scripts/sw-e2e-orchestrator-test.sh && bash scripts/sw-eventbus-test.sh && bash scripts/sw-feedback-test.sh && bash scripts/sw-fix-test.sh && bash scripts/sw-fleet-discover-test.sh && bash scripts/sw-fleet-test.sh && bash scripts/sw-fleet-viz-test.sh && bash scripts/sw-frontier-test.sh && bash scripts/sw-github-app-test.sh && bash scripts/sw-github-checks-test.sh && bash scripts/sw-github-deploy-test.sh && bash scripts/sw-github-graphql-test.sh && bash scripts/sw-guild-test.sh && bash scripts/sw-heartbeat-test.sh && bash scripts/sw-hygiene-test.sh && bash scripts/sw-incident-test.sh && bash scripts/sw-init-test.sh && bash scripts/sw-instrument-test.sh && bash scripts/sw-intelligence-test.sh && bash scripts/sw-jira-test.sh && bash scripts/sw-launchd-test.sh && bash scripts/sw-linear-test.sh && bash scripts/sw-logs-test.sh && bash scripts/sw-loop-test.sh && bash scripts/sw-memory-test.sh && bash scripts/sw-mission-control-test.sh && bash scripts/sw-model-router-test.sh && bash scripts/sw-otel-test.sh && bash scripts/sw-oversight-test.sh && bash scripts/sw-patrol-meta-test.sh && bash scripts/sw-pipeline-composer-test.sh && bash scripts/sw-pipeline-test.sh && bash scripts/sw-pipeline-vitals-test.sh && bash scripts/sw-pm-test.sh && bash scripts/sw-pr-lifecycle-test.sh && bash scripts/sw-predictive-test.sh && bash scripts/sw-prep-test.sh && bash scripts/sw-ps-test.sh && bash scripts/sw-public-dashboard-test.sh && bash scripts/sw-quality-test.sh && bash scripts/sw-reaper-test.sh && bash scripts/sw-recruit-test.sh && bash scripts/sw-regression-test.sh && bash scripts/sw-release-manager-test.sh && bash scripts/sw-release-test.sh && bash scripts/sw-remote-test.sh && bash scripts/sw-replay-test.sh && bash scripts/sw-retro-test.sh && bash scripts/sw-scale-test.sh && bash scripts/sw-security-audit-test.sh && bash scripts/sw-self-optimize-test.sh && bash scripts/sw-session-test.sh && bash scripts/sw-setup-test.sh && bash scripts/sw-standup-test.sh && bash scripts/sw-status-test.sh && bash scripts/sw-strategic-test.sh && bash scripts/sw-stream-test.sh && bash scripts/sw-swarm-test.sh && bash scripts/sw-team-stages-test.sh && bash scripts/sw-templates-test.sh && bash scripts/sw-testgen-test.sh && bash scripts/sw-tmux-pipeline-test.sh && bash scripts/sw-tmux-test.sh && bash scripts/sw-trace-test.sh && bash scripts/sw-tracker-test.sh && bash scripts/sw-triage-test.sh && bash scripts/sw-upgrade-test.sh && bash scripts/sw-ux-test.sh && bash scripts/sw-webhook-test.sh && bash scripts/sw-widgets-test.sh && bash scripts/sw-worktree-test.sh && bash scripts/sw-policy-e2e-test.sh && bash scripts/sw-e2e-smoke-test.sh && bash scripts/sw-dashboard-e2e-test.sh",
+    "test": "bash scripts/sw-agi-roadmap-test.sh && bash scripts/sw-activity-test.sh && bash scripts/sw-adaptive-test.sh && bash scripts/sw-adversarial-test.sh && bash scripts/sw-architecture-enforcer-test.sh && bash scripts/sw-auth-test.sh && bash scripts/sw-autonomous-test.sh && bash scripts/sw-changelog-test.sh && bash scripts/sw-checkpoint-test.sh && bash scripts/sw-ci-test.sh && bash scripts/sw-cleanup-test.sh && bash scripts/sw-code-review-test.sh && bash scripts/sw-connect-test.sh && bash scripts/sw-context-test.sh && bash scripts/sw-cost-test.sh && bash scripts/sw-daemon-test.sh && bash scripts/sw-dashboard-test.sh && bash scripts/sw-db-test.sh && bash scripts/sw-decompose-test.sh && bash scripts/sw-decide-test.sh && bash scripts/sw-deps-test.sh && bash scripts/sw-developer-simulation-test.sh && bash scripts/sw-discovery-test.sh && bash scripts/sw-doc-fleet-test.sh && bash scripts/sw-docs-agent-test.sh && bash scripts/sw-docs-test.sh && bash scripts/sw-doctor-test.sh && bash scripts/sw-dora-test.sh && bash scripts/sw-durable-test.sh && bash scripts/sw-e2e-orchestrator-test.sh && bash scripts/sw-eventbus-test.sh && bash scripts/sw-feedback-test.sh && bash scripts/sw-fix-test.sh && bash scripts/sw-fleet-discover-test.sh && bash scripts/sw-fleet-test.sh && bash scripts/sw-fleet-viz-test.sh && bash scripts/sw-frontier-test.sh && bash scripts/sw-github-app-test.sh && bash scripts/sw-github-checks-test.sh && bash scripts/sw-github-deploy-test.sh && bash scripts/sw-github-graphql-test.sh && bash scripts/sw-guild-test.sh && bash scripts/sw-heartbeat-test.sh && bash scripts/sw-hygiene-test.sh && bash scripts/sw-incident-test.sh && bash scripts/sw-init-test.sh && bash scripts/sw-instrument-test.sh && bash scripts/sw-intelligence-test.sh && bash scripts/sw-jira-test.sh && bash scripts/sw-launchd-test.sh && bash scripts/sw-linear-test.sh && bash scripts/sw-logs-test.sh && bash scripts/sw-loop-test.sh && bash scripts/sw-memory-test.sh && bash scripts/sw-mission-control-test.sh && bash scripts/sw-model-router-test.sh && bash scripts/sw-otel-test.sh && bash scripts/sw-oversight-test.sh && bash scripts/sw-patrol-meta-test.sh && bash scripts/sw-pipeline-composer-test.sh && bash scripts/sw-pipeline-test.sh && bash scripts/sw-pipeline-vitals-test.sh && bash scripts/sw-pm-test.sh && bash scripts/sw-pr-lifecycle-test.sh && bash scripts/sw-predictive-test.sh && bash scripts/sw-prep-test.sh && bash scripts/sw-ps-test.sh && bash scripts/sw-public-dashboard-test.sh && bash scripts/sw-quality-test.sh && bash scripts/sw-reaper-test.sh && bash scripts/sw-recruit-test.sh && bash scripts/sw-regression-test.sh && bash scripts/sw-release-manager-test.sh && bash scripts/sw-release-test.sh && bash scripts/sw-remote-test.sh && bash scripts/sw-replay-test.sh && bash scripts/sw-retro-test.sh && bash scripts/sw-scale-test.sh && bash scripts/sw-security-audit-test.sh && bash scripts/sw-self-optimize-test.sh && bash scripts/sw-session-test.sh && bash scripts/sw-setup-test.sh && bash scripts/sw-standup-test.sh && bash scripts/sw-status-test.sh && bash scripts/sw-strategic-test.sh && bash scripts/sw-stream-test.sh && bash scripts/sw-swarm-test.sh && bash scripts/sw-team-stages-test.sh && bash scripts/sw-templates-test.sh && bash scripts/sw-testgen-test.sh && bash scripts/sw-tmux-pipeline-test.sh && bash scripts/sw-tmux-test.sh && bash scripts/sw-trace-test.sh && bash scripts/sw-tracker-test.sh && bash scripts/sw-triage-test.sh && bash scripts/sw-upgrade-test.sh && bash scripts/sw-ux-test.sh && bash scripts/sw-webhook-test.sh && bash scripts/sw-widgets-test.sh && bash scripts/sw-worktree-test.sh && bash scripts/sw-lib-compat-test.sh && bash scripts/sw-lib-helpers-test.sh && bash scripts/sw-lib-daemon-dispatch-test.sh && bash scripts/sw-lib-daemon-failure-test.sh && bash scripts/sw-lib-daemon-poll-test.sh && bash scripts/sw-lib-daemon-state-test.sh && bash scripts/sw-lib-daemon-triage-test.sh && bash scripts/sw-lib-pipeline-detection-test.sh && bash scripts/sw-lib-pipeline-intelligence-test.sh && bash scripts/sw-lib-pipeline-quality-checks-test.sh && bash scripts/sw-lib-pipeline-stages-test.sh && bash scripts/sw-lib-pipeline-state-test.sh && bash scripts/sw-adapters-test.sh && bash scripts/sw-evidence-test.sh && bash scripts/sw-review-rerun-test.sh && bash scripts/sw-tracker-providers-test.sh && bash scripts/sw-budget-chaos-test.sh && bash scripts/sw-autonomous-e2e-test.sh && bash scripts/sw-memory-discovery-e2e-test.sh && bash scripts/sw-policy-e2e-test.sh && bash scripts/sw-e2e-smoke-test.sh && bash scripts/sw-dashboard-e2e-test.sh",
     "test:smoke": "bash scripts/sw-e2e-smoke-test.sh",
-    "test:integration": "bash scripts/sw-e2e-integration-test.sh",
+    "test:integration": "bash scripts/sw-e2e-integration-test.sh && bash scripts/sw-e2e-system-test.sh && bash scripts/sw-server-api-test.sh && bash scripts/sw-integration-claude-test.sh",
     "harness:evidence:capture": "bash scripts/sw-evidence.sh capture",
     "harness:evidence:verify": "bash scripts/sw-evidence.sh verify",
     "harness:evidence:pre-pr": "bash scripts/sw-evidence.sh pre-pr",

package/scripts/lib/architecture.sh

@@ -45,7 +45,8 @@ $(find "$repo_root" -type f \( -name '*.ts' -o -name '*.js' -o -name '*.py' -o -
             while IFS= read -r f; do
                 [[ -f "$f" ]] || continue
                 local exports=0
-                exports=$(grep -c "^export " "$f" 2>/dev/null || echo "0")
+                exports=$(grep -c "^export " "$f" 2>/dev/null || true)
+                exports="${exports:-0}"
                 [[ "$exports" -gt 2 ]] 2>/dev/null && context="${context}  $(basename "$f"): $exports exports
 "
             done < <(find "$repo_root/src" "$repo_root/lib" -name "*.ts" -o -name "*.js" 2>/dev/null | head -30)

package/scripts/lib/daemon-dispatch.sh

@@ -282,7 +282,30 @@ daemon_reap_completed() {
 
         # Check if process is still running
         if kill -0 "$pid" 2>/dev/null; then
-            continue
+            # Guard against PID reuse: if job has been running > 6 hours and
+            # the process tree doesn't contain sw-pipeline/sw-loop, it's stale
+            local _started_at _start_e _age_s
+            _started_at=$(echo "$job" | jq -r '.started_at // empty')
+            if [[ -n "$_started_at" ]]; then
+                _start_e=$(TZ=UTC date -j -f "%Y-%m-%dT%H:%M:%SZ" "$_started_at" +%s 2>/dev/null || date -d "$_started_at" +%s 2>/dev/null || echo "0")
+                _age_s=$(( $(now_epoch) - ${_start_e:-0} ))
+                if [[ "$_age_s" -gt 21600 ]]; then  # 6 hours
+                    # Verify this PID is actually our pipeline (not a reused PID)
+                    local _proc_cmd
+                    _proc_cmd=$(ps -p "$pid" -o command= 2>/dev/null || true)
+                    if [[ -z "$_proc_cmd" ]] || ! echo "$_proc_cmd" | grep -qE 'sw-pipeline|sw-loop|claude' 2>/dev/null; then
+                        daemon_log WARN "Stale job #${issue_num}: PID $pid running ${_age_s}s but not a pipeline process — force-reaping"
+                        emit_event "daemon.stale_dead" "issue=$issue_num" "pid=$pid" "elapsed_s=$_age_s"
+                        # Fall through to reap logic
+                    else
+                        continue
+                    fi
+                else
+                    continue
+                fi
+            else
+                continue
+            fi
         fi
 
         # Process is dead — determine exit code

package/scripts/lib/daemon-patrol.sh

@@ -3,6 +3,28 @@
 [[ -n "${_DAEMON_PATROL_LOADED:-}" ]] && return 0
 _DAEMON_PATROL_LOADED=1
 
+# ─── Decision Engine Signal Mode ─────────────────────────────────────────────
+# When DECISION_ENGINE_ENABLED=true, patrol writes candidates to the pending
+# signals file instead of creating GitHub issues directly. The decision engine
+# collects, scores, and acts on these signals with tiered autonomy.
+SIGNALS_PENDING_FILE="${HOME}/.shipwright/signals/pending.jsonl"
+
+_patrol_emit_signal() {
+    local id="$1" signal="$2" category="$3" title="$4" description="$5"
+    local risk="${6:-50}" confidence="${7:-0.80}" dedup_key="$8"
+    mkdir -p "$(dirname "$SIGNALS_PENDING_FILE")"
+    local ts
+    ts=$(now_iso)
+    local candidate
+    candidate=$(jq -n \
+        --arg id "$id" --arg signal "$signal" --arg category "$category" \
+        --arg title "$title" --arg desc "$description" \
+        --argjson risk "$risk" --arg conf "$confidence" \
+        --arg dedup "$dedup_key" --arg ts "$ts" \
+        '{id:$id, signal:$signal, category:$category, title:$title, description:$desc, evidence:{}, risk_score:$risk, confidence:$conf, dedup_key:$dedup, collected_at:$ts}')
+    echo "$candidate" >> "$SIGNALS_PENDING_FILE"
+}
+
 patrol_build_labels() {
     local check_label="$1"
     local labels="${PATROL_LABEL},${check_label}"
@@ -76,8 +98,16 @@ daemon_patrol() {
                     findings=$((findings + 1))
                     emit_event "patrol.finding" "check=security" "severity=$severity" "package=$name"
 
-                    # Check if issue already exists
-                    if [[ "$NO_GITHUB" != "true" ]] && [[ "$dry_run" != "true" ]]; then
+                    # Route to decision engine or create issue directly
+                    if [[ "${DECISION_ENGINE_ENABLED:-false}" == "true" ]]; then
+                        local _cat="security_patch"
+                        [[ "$severity" == "critical" ]] && _cat="security_critical"
+                        _patrol_emit_signal "sec-${name}" "security" "$_cat" \
+                            "Security: ${title} in ${name}" \
+                            "Fix ${severity} vulnerability in ${name}" \
+                            "$([[ "$severity" == "critical" ]] && echo 80 || echo 50)" \
+                            "0.95" "security:${name}:${title}"
+                    elif [[ "$NO_GITHUB" != "true" ]] && [[ "$dry_run" != "true" ]]; then
                         local existing
                         existing=$(gh issue list --label "$PATROL_LABEL" --label "security" \
                             --search "Security: $name" --json number -q 'length' 2>/dev/null || echo "0")
@@ -202,8 +232,13 @@ Auto-detected by \`shipwright daemon patrol\`." \
                     fi
                 done < <(echo "$outdated_json" | jq -c 'to_entries[]' 2>/dev/null)
 
-                # Create a single issue for all stale deps
-                if [[ "$findings" -gt 0 ]] && [[ "$NO_GITHUB" != "true" ]] && [[ "$dry_run" != "true" ]]; then
+                # Route to decision engine or create issue
+                if [[ "$findings" -gt 0 ]] && [[ "${DECISION_ENGINE_ENABLED:-false}" == "true" ]]; then
+                    _patrol_emit_signal "deps-stale-${findings}" "deps" "deps_major" \
+                        "Update ${findings} stale dependencies" \
+                        "Packages 2+ major versions behind" \
+                        45 "0.90" "deps:stale:${findings}"
+                elif [[ "$findings" -gt 0 ]] && [[ "$NO_GITHUB" != "true" ]] && [[ "$dry_run" != "true" ]]; then
                     local existing
                     existing=$(gh issue list --label "$PATROL_LABEL" --label "dependencies" \
                         --search "Stale dependencies" --json number -q 'length' 2>/dev/null || echo "0")
@@ -814,7 +849,7 @@ Auto-detected by \`shipwright daemon patrol\` on $(now_iso)." \
             if [[ ! -f "$scripts_dir/sw-${name}-test.sh" ]]; then
                 # Count usage across other scripts
                 local usage_count
-                usage_count=$(grep -rl "sw-${name}" "$scripts_dir"/sw-*.sh 2>/dev/null | grep -cv "$basename" 2>/dev/null || echo "0")
+                usage_count=$(grep -rl "sw-${name}" "$scripts_dir"/sw-*.sh 2>/dev/null | grep -cv "$basename" 2>/dev/null || true)
                 usage_count=${usage_count:-0}
 
                 local line_count

package/scripts/lib/daemon-poll.sh

@@ -1196,6 +1196,23 @@ daemon_poll_loop() {
                 daemon_patrol --once || daemon_log WARN "daemon_patrol failed — continuing"
                 LAST_PATROL_EPOCH=$now_e
             fi
+
+            # Decision engine cycle (if enabled)
+            local _decision_enabled
+            _decision_enabled=$(policy_get ".decision.enabled" "false" 2>/dev/null || echo "false")
+            if [[ "$_decision_enabled" == "true" ]]; then
+                local _decision_interval
+                _decision_interval=$(policy_get ".decision.cycle_interval_seconds" "1800" 2>/dev/null || echo "1800")
+                local _last_decision_epoch="${_LAST_DECISION_EPOCH:-0}"
+                if [[ $((now_e - _last_decision_epoch)) -ge "$_decision_interval" ]]; then
+                    daemon_log INFO "Running decision engine cycle"
+                    if [[ -f "$SCRIPT_DIR/sw-decide.sh" ]]; then
+                        DECISION_ENGINE_ENABLED=true bash "$SCRIPT_DIR/sw-decide.sh" run --once 2>/dev/null || \
+                            daemon_log WARN "Decision engine cycle failed — continuing"
+                    fi
+                    _LAST_DECISION_EPOCH=$now_e
+                fi
+            fi
         fi
 
         # ── Adaptive poll interval: adjust sleep based on queue state ──

package/scripts/lib/daemon-state.sh

@@ -390,6 +390,16 @@ init_state() {
             atomic_write_state "$init_json"
         ) 200>"$lock_file"
     else
+        # Validate existing state file JSON before using it
+        if ! jq '.' "$STATE_FILE" >/dev/null 2>&1; then
+            daemon_log WARN "Corrupted state file detected — backing up and resetting"
+            cp "$STATE_FILE" "${STATE_FILE}.corrupted.$(date +%s)" 2>/dev/null || true
+            rm -f "$STATE_FILE"
+            # Re-initialize as fresh state (recursive call with file removed)
+            init_state
+            return
+        fi
+
         # Update PID and start time in existing state
         locked_state_update \
             --arg pid "$$" \

package/scripts/lib/daemon-triage.sh

@@ -250,7 +250,7 @@ select_pipeline_template() {
         _dora_events=$(tail -500 "${EVENTS_FILE:-$HOME/.shipwright/events.jsonl}" \
             | grep '"type":"pipeline.completed"' 2>/dev/null \
             | tail -5 || true)
-        _dora_total=$(echo "$_dora_events" | grep -c '.' 2>/dev/null || echo "0")
+        _dora_total=$(echo "$_dora_events" | grep -c '.' 2>/dev/null || true)
         _dora_total="${_dora_total:-0}"
         if [[ "$_dora_total" -ge 3 ]]; then
             _dora_failures=$(echo "$_dora_events" | grep -c '"result":"failure"' 2>/dev/null || true)