shipwright-cli 3.0.0 → 3.2.0

package/config/decision-tiers.json

@@ -0,0 +1,55 @@
+{
+  "$schema": "https://shipwright.dev/schemas/decision-tiers-v1.json",
+  "description": "Autonomy tiers for Shipwright decision engine. Controls which actions the engine takes automatically vs proposing for human review.",
+  "version": "1",
+  "tiers": {
+    "auto": {
+      "description": "Create issue and auto-spawn pipeline — no human approval needed",
+      "labels": ["shipwright", "shipwright:auto", "ready-to-build"],
+      "pipeline_template": "fast"
+    },
+    "propose": {
+      "description": "Create issue with proposed label — human approves before build",
+      "labels": ["shipwright", "shipwright:proposed"],
+      "pipeline_template": "standard"
+    },
+    "draft": {
+      "description": "Write to decision-drafts directory only — human reviews offline",
+      "labels": [],
+      "pipeline_template": null
+    }
+  },
+  "category_rules": {
+    "deps_patch": { "tier": "auto", "risk_ceiling": 30 },
+    "deps_minor": { "tier": "auto", "risk_ceiling": 40 },
+    "deps_major": { "tier": "propose", "risk_ceiling": 60 },
+    "security_patch": { "tier": "auto", "risk_ceiling": 50 },
+    "security_critical": { "tier": "propose", "risk_ceiling": 80 },
+    "test_coverage": { "tier": "auto", "risk_ceiling": 30 },
+    "doc_sync": { "tier": "auto", "risk_ceiling": 20 },
+    "dead_code": { "tier": "auto", "risk_ceiling": 35 },
+    "refactor_hotspot": { "tier": "propose", "risk_ceiling": 60 },
+    "architecture_drift": { "tier": "propose", "risk_ceiling": 70 },
+    "performance_regression": { "tier": "propose", "risk_ceiling": 60 },
+    "recurring_failure": { "tier": "propose", "risk_ceiling": 50 },
+    "dora_regression": { "tier": "propose", "risk_ceiling": 55 },
+    "new_feature": { "tier": "draft", "risk_ceiling": 90 },
+    "breaking_change": { "tier": "draft", "risk_ceiling": 95 },
+    "business_logic": { "tier": "draft", "risk_ceiling": 90 },
+    "api_change": { "tier": "draft", "risk_ceiling": 85 },
+    "data_model_change": { "tier": "draft", "risk_ceiling": 90 }
+  },
+  "limits": {
+    "max_issues_per_day": 15,
+    "max_cost_per_day_usd": 25,
+    "cooldown_seconds": 300,
+    "halt_after_consecutive_failures": 3
+  },
+  "scoring_weights": {
+    "impact": 0.3,
+    "urgency": 0.25,
+    "effort": 0.2,
+    "confidence": 0.15,
+    "risk": 0.1
+  }
+}

package/config/defaults.json

@@ -25,6 +25,7 @@
     "build_test_retries": 3,
     "claude_timeout": 1800,
     "heartbeat_interval": 30,
+    "composed_cache_ttl": 3600,
     "branch_pattern": "shipwright/issue-{issue}",
     "stage_order": [
       "intake",
@@ -47,7 +48,12 @@
     "max_restarts": 0,
     "fast_test_interval": 5,
     "convergence_threshold": 3,
-    "multi_agent_sleep": 5
+    "multi_agent_sleep": 5,
+    "context_budget_chars": 180000,
+    "context_trim_memory_chars": 20000,
+    "context_trim_git_entries": 10,
+    "context_trim_hotspot_files": 5,
+    "context_trim_test_lines": 50
   },
   "dashboard": {
     "port": 8767,
@@ -77,12 +83,29 @@
     "ab_test_ratio": 0.2,
     "claude_timeout": 60
   },
+  "predictive": {
+    "default_risk_score": 50,
+    "keyword_risk_score": 70
+  },
+  "api_optimization": {
+    "programmatic_tool_calling": true,
+    "tool_search_enabled": true,
+    "tool_search_type": "bm25",
+    "defer_unused_tools": true,
+    "web_search_version": "web_search_20260209",
+    "web_fetch_version": "web_fetch_20260209",
+    "dynamic_filtering": true,
+    "code_execution_sandbox": true,
+    "beta_header": "code-execution-web-tools-2026-02-09"
+  },
   "quality": {
     "gate_score_threshold": 70,
     "secret_threshold": 3,
     "min_file_count": 10,
     "score_weight_per_file": 25,
-    "pass_rate_threshold": 5.0
+    "pass_rate_threshold": 5.0,
+    "bundle_growth_legacy_pct": 20,
+    "perf_regression_legacy_pct": 30
   },
   "cleanup": {
     "artifact_age_days": 7,

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": true,
+    "cycle_interval_seconds": 1800,
+    "tiers_file": "config/decision-tiers.json",
+    "outcome_learning_enabled": true,
+    "outcome_min_samples": 10,
+    "dedup_window_days": 7
   }
 }

package/dashboard/public/index.html

@@ -516,6 +516,12 @@
             id="cost-trend-container"
           ></div>
 
+          <!-- Context efficiency -->
+          <div
+            class="metric-card metric-card-wide"
+            id="context-efficiency-container"
+          ></div>
+
           <!-- DORA trend -->
           <div
             class="metric-card metric-card-wide"

package/dashboard/public/styles.css

@@ -3634,6 +3634,82 @@ body::-webkit-scrollbar-thumb {
   text-align: center;
 }
 
+/* Context efficiency widget */
+.ctx-eff-grid {
+  display: grid;
+  grid-template-columns: repeat(4, 1fr);
+  gap: 16px;
+}
+
+.ctx-eff-card {
+  background: var(--glass-bg);
+  border: 1px solid var(--glass-border);
+  border-radius: 10px;
+  padding: 12px;
+  display: flex;
+  flex-direction: column;
+  gap: 6px;
+}
+
+.ctx-eff-card-label {
+  font-family: var(--font-mono);
+  font-size: 0.65rem;
+  font-weight: 600;
+  letter-spacing: 0.08em;
+  color: var(--text-muted);
+  text-transform: uppercase;
+}
+
+.ctx-eff-gauge {
+  height: 8px;
+  border-radius: 4px;
+  background: var(--glass-border);
+  overflow: hidden;
+}
+
+.ctx-eff-gauge-fill {
+  height: 100%;
+  border-radius: 4px;
+  transition: width 0.5s ease;
+}
+
+.ctx-eff-gauge-fill.ctx-eff-high {
+  background: #4ade80;
+}
+
+.ctx-eff-gauge-fill.ctx-eff-mid {
+  background: #00d4ff;
+}
+
+.ctx-eff-gauge-fill.ctx-eff-low {
+  background: #f43f5e;
+}
+
+.ctx-eff-gauge-fill.ctx-eff-trim {
+  background: #7c3aed;
+}
+
+.ctx-eff-value {
+  font-family: var(--font-mono);
+  font-size: 0.85rem;
+  font-weight: 700;
+  color: var(--text-primary);
+}
+
+.ctx-eff-big {
+  font-family: var(--font-mono);
+  font-size: 1.4rem;
+  font-weight: 700;
+  color: var(--text-primary);
+  line-height: 1;
+}
+
+.ctx-eff-sub {
+  font-family: var(--font-mono);
+  font-size: 0.65rem;
+  color: var(--text-muted);
+}
+
 .dora-trend-grid {
   display: grid;
   grid-template-columns: repeat(4, 1fr);

package/dashboard/server.ts

@@ -3690,6 +3690,57 @@ const server = Bun.serve({
       });
     }
 
+    // REST: Context efficiency metrics (from loop.context_efficiency events)
+    if (pathname === "/api/context-efficiency") {
+      const period = parseInt(url.searchParams.get("period") || "7");
+      const events = readEvents();
+      const now = Math.floor(Date.now() / 1000);
+      const cutoff = now - period * 86400;
+
+      let totalUtil = 0;
+      let totalRatio = 0;
+      let totalRaw = 0;
+      let totalTrimmed = 0;
+      let trimEvents = 0;
+      let count = 0;
+
+      for (const e of events) {
+        if ((e.ts_epoch || 0) < cutoff) continue;
+        if (e.type !== "loop.context_efficiency") continue;
+
+        const util = parseFloat(String(e.budget_utilization || 0));
+        const ratio = parseFloat(String(e.trim_ratio || 0));
+        const raw = parseInt(String(e.raw_prompt_chars || 0), 10);
+        const trimmed = parseInt(String(e.trimmed_prompt_chars || 0), 10);
+
+        totalUtil += util;
+        totalRatio += ratio;
+        totalRaw += raw;
+        totalTrimmed += trimmed;
+        if (ratio > 0) trimEvents++;
+        count++;
+      }
+
+      const avgUtilization =
+        count > 0 ? Math.round((totalUtil / count) * 10) / 10 : 0;
+      const avgTrimRatio =
+        count > 0 ? Math.round((totalRatio / count) * 10) / 10 : 0;
+      const totalDiscarded = totalRaw - totalTrimmed;
+
+      return new Response(
+        JSON.stringify({
+          avg_utilization: avgUtilization,
+          avg_trim_ratio: avgTrimRatio,
+          total_raw_chars: totalRaw,
+          total_trimmed_chars: totalTrimmed,
+          total_discarded_chars: totalDiscarded,
+          trim_events: trimEvents,
+          total_iterations: count,
+        }),
+        { headers: { "Content-Type": "application/json", ...CORS_HEADERS } },
+      );
+    }
+
     // REST: DORA trend (weekly sliding windows)
     if (pathname === "/api/metrics/dora-trend") {
       const period = parseInt(url.searchParams.get("period") || "30");

package/dashboard/src/core/api.ts

@@ -7,6 +7,7 @@ import type {
   MachineInfo,
   JoinToken,
   CostBreakdown,
+  ContextEfficiency,
   DaemonConfig,
   AlertInfo,
   InsightsData,
@@ -113,6 +114,10 @@ export const fetchCostTrend = (period = 30) =>
     `/api/costs/trend?period=${period}`,
   );
 
+// Context efficiency
+export const fetchContextEfficiency = (period = 7) =>
+  request<ContextEfficiency>(`/api/context-efficiency?period=${period}`);
+
 // Daemon
 export const fetchDaemonConfig = () =>
   request<DaemonConfig>("/api/daemon/config");

package/dashboard/src/types/api.ts

@@ -255,6 +255,16 @@ export interface HeatmapData {
   heatmap: Record<string, Record<string, number>>;
 }
 
+export interface ContextEfficiency {
+  avg_utilization: number;
+  avg_trim_ratio: number;
+  total_raw_chars: number;
+  total_trimmed_chars: number;
+  total_discarded_chars: number;
+  trim_events: number;
+  total_iterations: number;
+}
+
 export interface DaemonConfig {
   paused?: boolean;
   config?: Record<string, unknown>;

package/dashboard/src/views/metrics.ts

@@ -82,10 +82,12 @@ function renderMetrics(data: MetricsData): void {
     doraContainer.style.display = "none";
   }
 
-  // Cost breakdown/trend
+  // Cost breakdown/trend/context efficiency
   if (document.getElementById("cost-breakdown-container"))
     renderCostBreakdown();
   if (document.getElementById("cost-trend-container")) renderCostTrend();
+  if (document.getElementById("context-efficiency-container"))
+    renderContextEfficiency();
   if (document.getElementById("dora-trend-container")) renderDoraTrend();
   if (document.getElementById("stage-performance-container"))
     renderStagePerformance();
@@ -256,6 +258,72 @@ function renderCostTrend(): void {
     });
 }
 
+function renderContextEfficiency(): void {
+  const container = document.getElementById("context-efficiency-container");
+  if (!container) return;
+  api
+    .fetchContextEfficiency()
+    .then((data) => {
+      if (!data.total_iterations) {
+        container.innerHTML =
+          '<div class="empty-state"><p>No context efficiency data</p></div>';
+        return;
+      }
+      const utilPct = Math.min(data.avg_utilization, 100);
+      const utilClass =
+        utilPct >= 90
+          ? "ctx-eff-high"
+          : utilPct >= 60
+            ? "ctx-eff-mid"
+            : "ctx-eff-low";
+      const trimPct = Math.min(data.avg_trim_ratio, 100);
+
+      let html =
+        '<span class="metric-label">CONTEXT EFFICIENCY</span>' +
+        '<div class="ctx-eff-grid">';
+
+      // Budget utilization gauge
+      html +=
+        '<div class="ctx-eff-card">' +
+        '<span class="ctx-eff-card-label">Budget Utilization</span>' +
+        `<div class="ctx-eff-gauge"><div class="ctx-eff-gauge-fill ${utilClass}" style="width:${utilPct.toFixed(0)}%"></div></div>` +
+        `<span class="ctx-eff-value">${data.avg_utilization.toFixed(1)}%</span>` +
+        "</div>";
+
+      // Trim ratio
+      html +=
+        '<div class="ctx-eff-card">' +
+        '<span class="ctx-eff-card-label">Avg Trim Ratio</span>' +
+        `<div class="ctx-eff-gauge"><div class="ctx-eff-gauge-fill ctx-eff-trim" style="width:${trimPct.toFixed(0)}%"></div></div>` +
+        `<span class="ctx-eff-value">${data.avg_trim_ratio.toFixed(1)}%</span>` +
+        "</div>";
+
+      // Chars saved
+      const savedK = Math.round(data.total_discarded_chars / 1000);
+      const totalK = Math.round(data.total_raw_chars / 1000);
+      html +=
+        '<div class="ctx-eff-card">' +
+        '<span class="ctx-eff-card-label">Chars Discarded</span>' +
+        `<span class="ctx-eff-big">${fmtNum(savedK)}K</span>` +
+        `<span class="ctx-eff-sub">of ${fmtNum(totalK)}K generated</span>` +
+        "</div>";
+
+      // Trim events
+      html +=
+        '<div class="ctx-eff-card">' +
+        '<span class="ctx-eff-card-label">Trim Events</span>' +
+        `<span class="ctx-eff-big">${data.trim_events}</span>` +
+        `<span class="ctx-eff-sub">of ${data.total_iterations} iterations</span>` +
+        "</div>";
+
+      html += "</div>";
+      container.innerHTML = html;
+    })
+    .catch((err) => {
+      container.innerHTML = `<div class="empty-state"><p>Failed to load: ${escapeHtml(String(err))}</p></div>`;
+    });
+}
+
 function renderDoraTrend(): void {
   const container = document.getElementById("dora-trend-container");
   if (!container) return;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "shipwright-cli",
-  "version": "3.0.0",
+  "version": "3.2.0",
   "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-adaptive.sh

@@ -223,10 +223,12 @@ daemon_collect_snapshot() {
     if [[ -d "$worktree/.git" ]] || [[ -f "$worktree/.git" ]]; then
         diff_lines=$(cd "$worktree" && git diff --stat 2>/dev/null | tail -1 | grep -o '[0-9]* insertion' | grep -o '[0-9]*' || echo "0")
         [[ -z "$diff_lines" ]] && diff_lines=0
-        files_changed=$(cd "$worktree" && git diff --name-only 2>/dev/null | wc -l | tr -d ' ' || echo "0")
+        files_changed=$(cd "$worktree" && git diff --name-only 2>/dev/null | wc -l | tr -d ' ' || true)
+        files_changed="${files_changed:-0}"
         # Also count untracked files the agent has created
         local untracked
-        untracked=$(cd "$worktree" && git ls-files --others --exclude-standard 2>/dev/null | wc -l | tr -d ' ' || echo "0")
+        untracked=$(cd "$worktree" && git ls-files --others --exclude-standard 2>/dev/null | wc -l | tr -d ' ' || true)
+        untracked="${untracked:-0}"
         files_changed=$((files_changed + untracked))
     fi