@swarmclawai/swarmclaw 1.9.6 → 1.9.8

package/README.md

@@ -399,6 +399,25 @@ Operational docs: https://swarmclaw.ai/docs/observability
 
 ## Releases
 
+### v1.9.8 Highlights
+
+Bundled release-readiness release: a single operator report that combines eval gates, operations blockers, approvals, and runtime readiness.
+
+- **Release readiness report.** `/api/quality/release-readiness` returns a scored ready/warning/blocked report built from eval regression gates and Operations Pulse evidence.
+- **Quality Center ship gate.** The Quality overview now shows readiness score, blockers, warnings, checks, and next actions before operators cut a release.
+- **CLI readiness checks.** `swarmclaw operations readiness` exposes the same report for scripts and CI.
+- **Browser coverage.** The e2e smoke now verifies the release-readiness panel on `/quality`.
+
+### v1.9.7 Highlights
+
+Bundled eval-gate release: approved baselines, regression checks, and Quality Center release gates for repeatable eval evidence.
+
+- **Eval regression baselines.** Operators can snapshot the latest scenario or suite score as an approved baseline with minimum score and regression allowance settings.
+- **Release gate API.** `/api/eval/gate` compares current eval evidence against thresholds and baselines, while `/api/eval/baselines` lists and updates approved baselines.
+- **CLI gate checks.** `swarmclaw eval gate`, `swarmclaw eval baselines`, and `swarmclaw eval baseline-set` expose the same release-gate workflow from automation.
+- **Quality Center gate panel.** Eval Lab now shows pass/warn/fail status, latest-run coverage, current score, baseline score, regression points, and actionable checks.
+- **Public-source hygiene.** Generic implementation comments now describe SwarmClaw behavior without naming internal comparison sources.
+
 ### v1.9.6 Highlights
 
 Bundled eval-environment release: validation preflights, deterministic eval workspaces, and clearer operator readiness before spending run budget.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@swarmclawai/swarmclaw",
-  "version": "1.9.6",
+  "version": "1.9.8",
   "description": "Build and run autonomous AI agents with OpenClaw, Hermes, multiple model providers, orchestration, delegation, memory, skills, schedules, and chat connectors.",
   "main": "electron-dist/main.js",
   "license": "MIT",
@@ -87,7 +87,7 @@
     "test:cli": "node --test src/cli/*.test.js bin/*.test.js scripts/electron-after-pack.test.mjs scripts/ensure-sandbox-browser-image.test.mjs scripts/postinstall.test.mjs scripts/run-next-build.test.mjs scripts/run-next-typegen.test.mjs",
     "test:setup": "tsx --test src/app/api/setup/check-provider/route.test.ts src/lib/server/provider-model-discovery.test.ts src/components/auth/setup-wizard/utils.test.ts src/components/auth/setup-wizard/types.test.ts src/hooks/setup-done-detection.test.ts src/lib/setup-defaults.test.ts src/lib/server/storage-auth.test.ts src/lib/server/storage-auth-docker.test.ts",
     "test:openclaw": "tsx --test src/lib/openclaw/openclaw-agent-id.test.ts src/lib/openclaw/openclaw-endpoint.test.ts src/lib/server/agents/agent-runtime-config.test.ts src/lib/server/build-llm.test.ts src/lib/server/connectors/connector-routing.test.ts src/lib/server/connectors/openclaw.test.ts src/lib/server/connectors/swarmdock.test.ts src/lib/server/gateway/protocol.test.ts src/lib/server/gateways/gateway-topology.test.ts src/lib/server/llm-response-cache.test.ts src/lib/server/mcp-conformance.test.ts src/lib/server/openclaw/agent-resolver.test.ts src/lib/server/openclaw/deploy.test.ts src/lib/server/openclaw/skills-normalize.test.ts src/lib/server/session-tools/openclaw-nodes.test.ts src/lib/server/session-tools/swarmdock.test.ts src/lib/server/tasks/task-quality-gate.test.ts src/lib/server/tasks/task-validation.test.ts src/lib/server/tool-capability-policy.test.ts src/lib/providers/openai.test.ts src/lib/providers/openclaw-exports.test.ts src/app/api/gateways/topology-route.test.ts src/app/api/openclaw/dashboard-url/route.test.ts",
-    "test:runtime": "tsx --test src/lib/a2a/agent-card.test.ts src/lib/strip-internal-metadata.test.ts src/lib/provider-sets.test.ts src/lib/providers/opencode-cli.test.ts src/lib/providers/cli-provider-metadata.test.ts src/lib/providers/cli-utils.test.ts src/lib/providers/generic-cli.test.ts src/lib/server/agents/delegation-advisory.test.ts src/lib/server/cli-provider-readiness.test.ts src/lib/server/provider-health.test.ts src/lib/server/mcp-gateway-runtime.test.ts src/lib/server/mcp-connection-pool.test.ts src/lib/server/knowledge-sources.test.ts src/lib/server/extension-managed-resources.test.ts src/lib/server/eval/environment-plan.test.ts src/lib/server/chat-execution/chat-execution-grounding.test.ts src/lib/server/chat-execution/chat-turn-preparation.test.ts src/lib/server/chat-execution/iteration-timers.test.ts src/lib/server/chat-execution/post-stream-finalization.test.ts src/lib/server/chat-execution/reasoning-tag-scrubber.test.ts src/lib/server/chats/clear-undo-snapshots.test.ts src/lib/server/connectors/email.test.ts src/lib/server/protocols/protocol-service.test.ts src/lib/server/runtime/run-ledger.test.ts src/lib/server/runtime/queue-retry-policy.test.ts src/lib/server/runs/run-brief.test.ts src/lib/server/operations/operation-pulse.test.ts src/lib/server/artifacts/artifact-resolver.test.ts src/lib/server/observability/otel-config.test.ts src/lib/server/safe-parse-body.test.ts src/lib/server/missions/mission-templates.test.ts src/lib/server/sharing/share-link-repository.test.ts src/lib/server/sharing/share-resolver.test.ts src/lib/server/tasks/task-execution-workspace.test.ts src/lib/server/tasks/task-service.test.ts src/lib/server/session-tools/execute.test.ts src/lib/server/session-tools/manage-tasks.test.ts src/lib/app/view-constants.test.ts src/lib/quality/quality-summary.test.ts src/app/api/approvals/route.test.ts src/app/api/agents/agents-route.test.ts src/app/api/tasks/tasks-route.test.ts src/app/api/tasks/task-workspace-route.test.ts src/app/api/chats/chat-route.test.ts src/app/api/chats/clear-route.test.ts src/app/api/chats/compact-route.test.ts src/app/api/chats/context-status-route.test.ts src/app/api/connectors/connector-doctor-route.test.ts src/app/api/extensions/managed-resources/route.test.ts src/app/api/healthz/route.test.ts src/app/api/logs/route.test.ts src/app/api/portability/export/route.test.ts src/app/api/portability/import/route.test.ts src/app/api/providers/[id]/route.test.ts src/app/api/tts/route.test.ts",
+    "test:runtime": "tsx --test src/lib/a2a/agent-card.test.ts src/lib/strip-internal-metadata.test.ts src/lib/provider-sets.test.ts src/lib/providers/opencode-cli.test.ts src/lib/providers/cli-provider-metadata.test.ts src/lib/providers/cli-utils.test.ts src/lib/providers/generic-cli.test.ts src/lib/server/agents/delegation-advisory.test.ts src/lib/server/cli-provider-readiness.test.ts src/lib/server/provider-health.test.ts src/lib/server/mcp-gateway-runtime.test.ts src/lib/server/mcp-connection-pool.test.ts src/lib/server/knowledge-sources.test.ts src/lib/server/extension-managed-resources.test.ts src/lib/server/eval/baseline.test.ts src/lib/server/eval/environment-plan.test.ts src/lib/server/chat-execution/chat-execution-grounding.test.ts src/lib/server/chat-execution/chat-turn-preparation.test.ts src/lib/server/chat-execution/iteration-timers.test.ts src/lib/server/chat-execution/post-stream-finalization.test.ts src/lib/server/chat-execution/reasoning-tag-scrubber.test.ts src/lib/server/chats/clear-undo-snapshots.test.ts src/lib/server/connectors/email.test.ts src/lib/server/protocols/protocol-service.test.ts src/lib/server/runtime/run-ledger.test.ts src/lib/server/runtime/queue-retry-policy.test.ts src/lib/server/runs/run-brief.test.ts src/lib/server/operations/operation-pulse.test.ts src/lib/quality/release-readiness.test.ts src/lib/server/artifacts/artifact-resolver.test.ts src/lib/server/observability/otel-config.test.ts src/lib/server/safe-parse-body.test.ts src/lib/server/missions/mission-templates.test.ts src/lib/server/sharing/share-link-repository.test.ts src/lib/server/sharing/share-resolver.test.ts src/lib/server/tasks/task-execution-workspace.test.ts src/lib/server/tasks/task-service.test.ts src/lib/server/session-tools/execute.test.ts src/lib/server/session-tools/manage-tasks.test.ts src/lib/app/view-constants.test.ts src/lib/quality/quality-summary.test.ts src/app/api/approvals/route.test.ts src/app/api/agents/agents-route.test.ts src/app/api/tasks/tasks-route.test.ts src/app/api/tasks/task-workspace-route.test.ts src/app/api/chats/chat-route.test.ts src/app/api/chats/clear-route.test.ts src/app/api/chats/compact-route.test.ts src/app/api/chats/context-status-route.test.ts src/app/api/connectors/connector-doctor-route.test.ts src/app/api/extensions/managed-resources/route.test.ts src/app/api/healthz/route.test.ts src/app/api/logs/route.test.ts src/app/api/portability/export/route.test.ts src/app/api/portability/import/route.test.ts src/app/api/providers/[id]/route.test.ts src/app/api/tts/route.test.ts",
     "test:builder": "tsx --test src/features/protocols/builder/utils/nodes-to-template.test.ts src/features/protocols/builder/utils/template-to-nodes.test.ts src/features/protocols/builder/validators/dag-validator.test.ts",
     "test:e2e": "node --import tsx scripts/browser-e2e-smoke.ts",
     "test:mcp:conformance": "node --import tsx ./scripts/mcp-conformance-check.ts",

package/src/app/api/eval/baselines/route.ts

@@ -0,0 +1,55 @@
+import { NextResponse } from 'next/server'
+import { z } from 'zod'
+import { evaluateEvalGate, listEvalBaselinesForAgent, setEvalBaseline } from '@/lib/server/eval/baseline'
+import { errorMessage } from '@/lib/shared-utils'
+
+const BaselineSchema = z.object({
+  agentId: z.string().min(1),
+  scenarioId: z.string().min(1).nullable().optional(),
+  suite: z.string().min(1).nullable().optional(),
+  minPercent: z.number().min(0).max(100).nullable().optional(),
+  maxRegressionPoints: z.number().min(0).max(100).nullable().optional(),
+  label: z.string().max(160).nullable().optional(),
+  notes: z.string().max(1_000).nullable().optional(),
+})
+
+export async function GET(req: Request) {
+  try {
+    const { searchParams } = new URL(req.url)
+    const agentId = searchParams.get('agentId')
+    return NextResponse.json(listEvalBaselinesForAgent(agentId))
+  } catch (err: unknown) {
+    return NextResponse.json(
+      { error: errorMessage(err) },
+      { status: 500 },
+    )
+  }
+}
+
+export async function POST(req: Request) {
+  try {
+    const body: unknown = await req.json()
+    const parsed = BaselineSchema.safeParse(body)
+    if (!parsed.success) {
+      return NextResponse.json(
+        { error: parsed.error.issues.map((issue) => issue.message).join(', ') },
+        { status: 400 },
+      )
+    }
+
+    const baseline = setEvalBaseline(parsed.data)
+    const gate = evaluateEvalGate({
+      agentId: parsed.data.agentId,
+      scenarioId: parsed.data.scenarioId,
+      suite: parsed.data.suite,
+      minPercent: parsed.data.minPercent,
+      maxRegressionPoints: parsed.data.maxRegressionPoints,
+    })
+    return NextResponse.json({ baseline, gate })
+  } catch (err: unknown) {
+    return NextResponse.json(
+      { error: errorMessage(err) },
+      { status: 500 },
+    )
+  }
+}

package/src/app/api/eval/gate/route.ts

@@ -0,0 +1,36 @@
+import { NextResponse } from 'next/server'
+import { evaluateEvalGate } from '@/lib/server/eval/baseline'
+import { errorMessage } from '@/lib/shared-utils'
+
+function parseNumberParam(value: string | null): number | null {
+  if (value == null || value.trim() === '') return null
+  const parsed = Number(value)
+  return Number.isFinite(parsed) ? parsed : null
+}
+
+export async function GET(req: Request) {
+  try {
+    const { searchParams } = new URL(req.url)
+    const agentId = searchParams.get('agentId') || ''
+    if (!agentId) {
+      return NextResponse.json(
+        { error: 'agentId is required' },
+        { status: 400 },
+      )
+    }
+
+    const result = evaluateEvalGate({
+      agentId,
+      scenarioId: searchParams.get('scenarioId'),
+      suite: searchParams.get('suite'),
+      minPercent: parseNumberParam(searchParams.get('minPercent')),
+      maxRegressionPoints: parseNumberParam(searchParams.get('maxRegressionPoints')),
+    })
+    return NextResponse.json(result)
+  } catch (err: unknown) {
+    return NextResponse.json(
+      { error: errorMessage(err) },
+      { status: 500 },
+    )
+  }
+}

package/src/app/api/quality/release-readiness/route.ts

@@ -0,0 +1,38 @@
+import { NextResponse } from 'next/server'
+import { evaluateEvalGate } from '@/lib/server/eval/baseline'
+import { getOperationPulse, normalizeOperationPulseRange } from '@/lib/server/operations/operation-pulse'
+import { buildReleaseReadinessReport } from '@/lib/quality/release-readiness'
+import { errorMessage } from '@/lib/shared-utils'
+
+export const dynamic = 'force-dynamic'
+
+function parseNumberParam(value: string | null): number | null {
+  if (value == null || value.trim() === '') return null
+  const parsed = Number(value)
+  return Number.isFinite(parsed) ? parsed : null
+}
+
+export async function GET(req: Request) {
+  try {
+    const { searchParams } = new URL(req.url)
+    const range = normalizeOperationPulseRange(searchParams.get('range'))
+    const agentId = searchParams.get('agentId') || ''
+    const pulse = getOperationPulse(range)
+    const evalGate = agentId
+      ? evaluateEvalGate({
+        agentId,
+        scenarioId: searchParams.get('scenarioId'),
+        suite: searchParams.get('suite'),
+        minPercent: parseNumberParam(searchParams.get('minPercent')),
+        maxRegressionPoints: parseNumberParam(searchParams.get('maxRegressionPoints')),
+      })
+      : null
+
+    return NextResponse.json(buildReleaseReadinessReport({ pulse, evalGate }))
+  } catch (err: unknown) {
+    return NextResponse.json(
+      { error: errorMessage(err) },
+      { status: 500 },
+    )
+  }
+}

package/src/cli/index.js

@@ -210,6 +210,7 @@ const COMMAND_GROUPS = [
     description: 'Operator triage and readiness summaries',
     commands: [
       cmd('pulse', 'GET', '/operations/pulse', 'Get Operations Pulse summary (use --query range=24h or --query range=7d)'),
+      cmd('readiness', 'GET', '/quality/release-readiness', 'Get release readiness report (use --query agentId=... and --query suite=core for eval gate coverage)'),
     ],
   },
   {
@@ -232,9 +233,12 @@ const COMMAND_GROUPS = [
       cmd('suites', 'GET', '/eval/suites', 'List available eval suites (core, swe-bench-lite, gaia-l1, ...)'),
       cmd('status', 'GET', '/eval/run', 'Get eval run status'),
       cmd('environment', 'GET', '/eval/environments', 'Preview validation environment readiness for an eval'),
+      cmd('baselines', 'GET', '/eval/baselines', 'List eval regression baselines'),
+      cmd('gate', 'GET', '/eval/gate', 'Check the latest eval score against thresholds and baseline'),
       cmd('run', 'POST', '/eval/run', 'Run an eval scenario against an agent', { expectsJsonBody: true }),
       cmd('suite', 'POST', '/eval/suite', 'Run a full eval suite against an agent (pass { suite: "swe-bench-lite" } in body)', { expectsJsonBody: true }),
       cmd('environment-prepare', 'POST', '/eval/environments', 'Prepare validation environment readiness for an eval', { expectsJsonBody: true }),
+      cmd('baseline-set', 'POST', '/eval/baselines', 'Set an eval regression baseline from latest completed runs', { expectsJsonBody: true }),
     ],
   },
   {

package/src/components/quality/quality-workspace.tsx

@@ -15,9 +15,10 @@ import {
   summarizeEvalRuns,
   summarizeRunHealth,
 } from '@/lib/quality/quality-summary'
+import type { ReleaseReadinessReport, ReleaseReadinessStatus } from '@/lib/quality/release-readiness'
 import { cn } from '@/lib/utils'
 import { useAppStore } from '@/stores/use-app-store'
-import type { EvalEnvironmentPlan, EvalRun, EvalSuiteResult } from '@/lib/server/eval/types'
+import type { EvalEnvironmentPlan, EvalGateResult, EvalRun, EvalSuiteResult } from '@/lib/server/eval/types'
 import type { Agent, ApprovalRequest, SessionRunRecord } from '@/types'
 
 type QualityTab = 'overview' | 'evals' | 'approvals' | 'runs'
@@ -117,6 +118,142 @@ function checkClass(level: 'info' | 'warn' | 'error'): string {
   return 'border-white/[0.06] bg-white/[0.025] text-text-3'
 }
 
+function gateStatusClass(status: EvalGateResult['status']): string {
+  if (status === 'pass') return 'border-emerald-500/25 bg-emerald-500/10 text-emerald-200'
+  if (status === 'warn') return 'border-amber-500/25 bg-amber-500/10 text-amber-200'
+  return 'border-rose-500/25 bg-rose-500/10 text-rose-200'
+}
+
+function gateCheckClass(status: EvalGateResult['status']): string {
+  if (status === 'fail') return 'border-rose-500/20 bg-rose-500/[0.05] text-rose-200'
+  if (status === 'warn') return 'border-amber-500/20 bg-amber-500/[0.05] text-amber-200'
+  return 'border-emerald-500/20 bg-emerald-500/[0.05] text-emerald-200'
+}
+
+function readinessStatusClass(status: ReleaseReadinessStatus): string {
+  if (status === 'ready') return 'border-emerald-500/25 bg-emerald-500/10 text-emerald-200'
+  if (status === 'warning') return 'border-amber-500/25 bg-amber-500/10 text-amber-200'
+  return 'border-rose-500/25 bg-rose-500/10 text-rose-200'
+}
+
+function readinessScoreTone(status: ReleaseReadinessStatus): string {
+  if (status === 'ready') return 'text-emerald-300'
+  if (status === 'warning') return 'text-amber-300'
+  return 'text-rose-300'
+}
+
+function ReleaseReadinessPanel({
+  report,
+  loading,
+  onRefresh,
+  onOpenHref,
+}: {
+  report: ReleaseReadinessReport | null
+  loading: boolean
+  onRefresh: () => void
+  onOpenHref: (href: string) => void
+}) {
+  return (
+    <section className="rounded-[16px] border border-white/[0.06] bg-white/[0.025] p-4">
+      <div className="flex flex-col gap-3 lg:flex-row lg:items-start lg:justify-between">
+        <div>
+          <div className="text-[11px] font-700 uppercase tracking-[0.12em] text-accent-bright/70">Release Readiness</div>
+          <h2 className="mt-1 font-display text-[17px] font-700 text-text">Ship gate report</h2>
+          <p className="mt-1 max-w-[680px] text-[12px] leading-relaxed text-text-3/65">
+            Combines eval regression gates, operations pulse blockers, pending approvals, active runs, budgets, connectors, and gateway readiness.
+          </p>
+        </div>
+        <button
+          type="button"
+          onClick={onRefresh}
+          disabled={loading}
+          className="shrink-0 rounded-[10px] border border-white/[0.08] bg-white/[0.04] px-3 py-2 text-[12px] font-800 text-text-2 transition-colors hover:bg-white/[0.08] disabled:opacity-40"
+        >
+          {loading ? 'Checking' : 'Refresh gate'}
+        </button>
+      </div>
+
+      {!report ? (
+        <div className="mt-4 rounded-[12px] border border-dashed border-white/[0.08] bg-white/[0.02] px-4 py-5 text-[12px] text-text-3/65">
+          {loading ? 'Building release readiness report...' : 'No release readiness report is available yet.'}
+        </div>
+      ) : (
+        <div className="mt-4 grid gap-4 xl:grid-cols-[260px_1fr]">
+          <div className="rounded-[14px] border border-white/[0.06] bg-white/[0.025] p-4">
+            <span className={cn('inline-flex rounded-full border px-2.5 py-1 text-[10px] font-800 uppercase tracking-[0.1em]', readinessStatusClass(report.status))}>
+              {report.status}
+            </span>
+            <div className={cn('mt-4 font-display text-[42px] font-700 tracking-[-0.04em]', readinessScoreTone(report.status))}>{report.score}</div>
+            <div className="mt-1 text-[12px] text-text-3/65">readiness score</div>
+            <div className="mt-4 grid grid-cols-2 gap-2">
+              <div className="rounded-[10px] bg-white/[0.035] px-3 py-2">
+                <div className="text-[10px] font-700 uppercase tracking-[0.1em] text-text-3/50">Blockers</div>
+                <div className="mt-1 text-[18px] font-800 text-text">{report.blockerCount}</div>
+              </div>
+              <div className="rounded-[10px] bg-white/[0.035] px-3 py-2">
+                <div className="text-[10px] font-700 uppercase tracking-[0.1em] text-text-3/50">Warnings</div>
+                <div className="mt-1 text-[18px] font-800 text-text">{report.warningCount}</div>
+              </div>
+            </div>
+          </div>
+
+          <div className="grid gap-3 lg:grid-cols-2">
+            <div className="rounded-[14px] border border-white/[0.06] bg-white/[0.02] p-3">
+              <div className="text-[12px] font-800 text-text">Checks</div>
+              <div className="mt-3 flex flex-col gap-2">
+                {report.checks.slice(0, 6).map((check) => (
+                  <button
+                    key={check.code}
+                    type="button"
+                    onClick={() => check.href && onOpenHref(check.href)}
+                    className={cn(
+                      'rounded-[10px] border px-3 py-2 text-left transition-colors',
+                      readinessStatusClass(check.status),
+                      check.href ? 'hover:bg-white/[0.08]' : '',
+                    )}
+                  >
+                    <div className="text-[11px] font-800 uppercase tracking-[0.08em]">{check.status}</div>
+                    <div className="mt-1 text-[12px] font-700 text-text">{check.title}</div>
+                    <div className="mt-0.5 text-[11px] leading-relaxed text-text-3/70">{check.summary}</div>
+                  </button>
+                ))}
+              </div>
+            </div>
+
+            <div className="rounded-[14px] border border-white/[0.06] bg-white/[0.02] p-3">
+              <div className="text-[12px] font-800 text-text">Next actions</div>
+              <div className="mt-3 flex flex-col gap-2">
+                {report.nextActions.length === 0 ? (
+                  <div className="rounded-[10px] border border-white/[0.06] bg-white/[0.025] px-3 py-4 text-[12px] text-text-3/65">
+                    No triage actions are open in the selected window.
+                  </div>
+                ) : (
+                  report.nextActions.slice(0, 5).map((action) => (
+                    <button
+                      key={action.id}
+                      type="button"
+                      onClick={() => onOpenHref(action.href)}
+                      className="rounded-[10px] border border-white/[0.06] bg-white/[0.025] px-3 py-2 text-left transition-colors hover:bg-white/[0.06]"
+                    >
+                      <div className="flex items-center justify-between gap-2">
+                        <div className="text-[12px] font-800 text-text">{action.title}</div>
+                        <span className={cn('rounded-full border px-2 py-0.5 text-[9px] font-800 uppercase tracking-[0.08em]', action.severity === 'high' ? 'border-rose-500/25 text-rose-200' : action.severity === 'medium' ? 'border-amber-500/25 text-amber-200' : 'border-emerald-500/25 text-emerald-200')}>
+                          {action.severity}
+                        </span>
+                      </div>
+                      <div className="mt-1 line-clamp-2 text-[11px] leading-relaxed text-text-3/65">{action.summary}</div>
+                    </button>
+                  ))
+                )}
+              </div>
+            </div>
+          </div>
+        </div>
+      )}
+    </section>
+  )
+}
+
 function EvalEnvironmentPanel({ plan, loading, onRefresh }: {
   plan: EvalEnvironmentPlan | null
   loading: boolean
@@ -195,6 +332,115 @@ function EvalEnvironmentPanel({ plan, loading, onRefresh }: {
   )
 }
 
+function EvalGatePanel({
+  gate,
+  loading,
+  busy,
+  scope,
+  onScopeChange,
+  onRefresh,
+  onSetBaseline,
+}: {
+  gate: EvalGateResult | null
+  loading: boolean
+  busy: boolean
+  scope: 'scenario' | 'suite'
+  onScopeChange: (scope: 'scenario' | 'suite') => void
+  onRefresh: () => void
+  onSetBaseline: () => void
+}) {
+  return (
+    <div className="rounded-[12px] border border-white/[0.06] bg-white/[0.025] px-3 py-3">
+      <div className="flex items-start justify-between gap-3">
+        <div>
+          <div className="text-[13px] font-800 text-text">Regression gate</div>
+          <p className="mt-1 text-[11px] leading-relaxed text-text-3/65">
+            Compare latest eval evidence against thresholds and an approved baseline.
+          </p>
+        </div>
+        <button
+          type="button"
+          onClick={onRefresh}
+          disabled={loading}
+          className="shrink-0 rounded-[8px] border border-white/[0.08] px-2 py-1 text-[10px] font-800 text-text-2 transition-colors hover:bg-white/[0.06] disabled:opacity-40"
+        >
+          {loading ? 'Checking' : 'Refresh'}
+        </button>
+      </div>
+
+      <div className="mt-3 flex rounded-[10px] border border-white/[0.06] bg-white/[0.025] p-1">
+        {(['scenario', 'suite'] as const).map((item) => (
+          <button
+            key={item}
+            type="button"
+            onClick={() => onScopeChange(item)}
+            className={cn(
+              'flex-1 rounded-[8px] px-2 py-1.5 text-[10px] font-800 uppercase tracking-[0.08em] transition-colors',
+              scope === item ? 'bg-white/[0.1] text-text' : 'text-text-3 hover:bg-white/[0.05]',
+            )}
+          >
+            {item}
+          </button>
+        ))}
+      </div>
+
+      {!gate ? (
+        <div className="mt-3 text-[11px] text-text-3/60">{loading ? 'Checking gate...' : 'Run evals to build gate evidence.'}</div>
+      ) : (
+        <div className="mt-3 flex flex-col gap-3">
+          <div className="flex flex-wrap items-center gap-2">
+            <span className={cn('rounded-full border px-2 py-1 text-[10px] font-800 uppercase tracking-[0.08em]', gateStatusClass(gate.status))}>
+              {gate.status}
+            </span>
+            <span className="rounded-full bg-white/[0.05] px-2 py-1 text-[10px] font-700 text-text-3">
+              {gate.scope.label}
+            </span>
+            <span className="rounded-full bg-white/[0.05] px-2 py-1 text-[10px] font-700 text-text-3">
+              {gate.latestRuns.length}/{gate.scope.scenarioIds.length} latest runs
+            </span>
+          </div>
+
+          <div className="grid grid-cols-3 gap-2">
+            <div className="rounded-[10px] border border-white/[0.06] bg-white/[0.02] px-2 py-2">
+              <div className="text-[9px] font-800 uppercase tracking-[0.08em] text-text-3/50">Current</div>
+              <div className="mt-1 text-[14px] font-800 text-text">{formatPercent(gate.currentPercent)}</div>
+            </div>
+            <div className="rounded-[10px] border border-white/[0.06] bg-white/[0.02] px-2 py-2">
+              <div className="text-[9px] font-800 uppercase tracking-[0.08em] text-text-3/50">Baseline</div>
+              <div className="mt-1 text-[14px] font-800 text-text">{gate.baseline ? `${gate.baseline.baselinePercent}%` : 'none'}</div>
+            </div>
+            <div className="rounded-[10px] border border-white/[0.06] bg-white/[0.02] px-2 py-2">
+              <div className="text-[9px] font-800 uppercase tracking-[0.08em] text-text-3/50">Regression</div>
+              <div className="mt-1 text-[14px] font-800 text-text">{gate.regressionPoints == null ? 'n/a' : `${gate.regressionPoints}pt`}</div>
+            </div>
+          </div>
+
+          <div className="flex flex-col gap-1.5">
+            {gate.checks.slice(0, 4).map((check) => (
+              <div key={`${check.code}:${check.message}`} className={cn('rounded-[9px] border px-2.5 py-2 text-[11px] leading-relaxed', gateCheckClass(check.status))}>
+                <span className="font-800 uppercase tracking-[0.08em]">{check.status}</span>
+                <span className="ml-2">{check.message}</span>
+              </div>
+            ))}
+            {gate.checks.length > 4 && (
+              <div className="text-[10px] text-text-3/55">+{gate.checks.length - 4} more check{gate.checks.length - 4 === 1 ? '' : 's'}</div>
+            )}
+          </div>
+
+          <button
+            type="button"
+            onClick={onSetBaseline}
+            disabled={busy || gate.latestRuns.length === 0 || gate.checks.some((check) => check.code === 'missing_scope_runs')}
+            className="rounded-[9px] border border-white/[0.08] bg-white/[0.04] px-3 py-2 text-[11px] font-800 text-text-2 transition-colors hover:bg-white/[0.08] disabled:cursor-not-allowed disabled:opacity-40"
+          >
+            {busy ? 'Saving baseline' : gate.baseline ? 'Update baseline' : 'Set baseline'}
+          </button>
+        </div>
+      )}
+    </div>
+  )
+}
+
 export function QualityWorkspace() {
   const router = useRouter()
   const searchParams = useSearchParams()
@@ -219,6 +465,12 @@ export function QualityWorkspace() {
   const [evalBusy, setEvalBusy] = useState<string | null>(null)
   const [evalEnvironmentPlan, setEvalEnvironmentPlan] = useState<EvalEnvironmentPlan | null>(null)
   const [evalEnvironmentLoading, setEvalEnvironmentLoading] = useState(false)
+  const [evalGate, setEvalGate] = useState<EvalGateResult | null>(null)
+  const [evalGateScope, setEvalGateScope] = useState<'scenario' | 'suite'>('scenario')
+  const [evalGateLoading, setEvalGateLoading] = useState(false)
+  const [evalBaselineBusy, setEvalBaselineBusy] = useState(false)
+  const [releaseReadiness, setReleaseReadiness] = useState<ReleaseReadinessReport | null>(null)
+  const [releaseReadinessLoading, setReleaseReadinessLoading] = useState(false)
   const [approvalBusy, setApprovalBusy] = useState<string | null>(null)
 
   useEffect(() => {
@@ -283,6 +535,49 @@ export function QualityWorkspace() {
     }
   }, [selectedAgentId, selectedScenarioId, selectedSuite])
 
+  const loadEvalGate = useCallback(async () => {
+    if (!selectedAgentId) {
+      setEvalGate(null)
+      return
+    }
+    if (evalGateScope === 'scenario' && !selectedScenarioId) {
+      setEvalGate(null)
+      return
+    }
+    const params = new URLSearchParams({ agentId: selectedAgentId })
+    if (evalGateScope === 'scenario') params.set('scenarioId', selectedScenarioId)
+    else params.set('suite', selectedSuite)
+    setEvalGateLoading(true)
+    try {
+      const gate = await api<EvalGateResult>('GET', `/eval/gate?${params.toString()}`)
+      setEvalGate(gate)
+    } catch (err) {
+      setEvalGate(null)
+      toast.error(err instanceof Error ? err.message : 'Unable to check eval gate')
+    } finally {
+      setEvalGateLoading(false)
+    }
+  }, [evalGateScope, selectedAgentId, selectedScenarioId, selectedSuite])
+
+  const loadReleaseReadiness = useCallback(async () => {
+    const params = new URLSearchParams({ range: '7d' })
+    if (selectedAgentId) {
+      params.set('agentId', selectedAgentId)
+      if (evalGateScope === 'scenario' && selectedScenarioId) params.set('scenarioId', selectedScenarioId)
+      if (evalGateScope === 'suite') params.set('suite', selectedSuite)
+    }
+    setReleaseReadinessLoading(true)
+    try {
+      const report = await api<ReleaseReadinessReport>('GET', `/quality/release-readiness?${params.toString()}`)
+      setReleaseReadiness(report)
+    } catch (err) {
+      setReleaseReadiness(null)
+      toast.error(err instanceof Error ? err.message : 'Unable to check release readiness')
+    } finally {
+      setReleaseReadinessLoading(false)
+    }
+  }, [evalGateScope, selectedAgentId, selectedScenarioId, selectedSuite])
+
   useEffect(() => {
     void loadQualityData()
   }, [loadQualityData])
@@ -301,6 +596,14 @@ export function QualityWorkspace() {
     void loadEvalEnvironmentPlan()
   }, [loadEvalEnvironmentPlan])
 
+  useEffect(() => {
+    void loadEvalGate()
+  }, [loadEvalGate])
+
+  useEffect(() => {
+    void loadReleaseReadiness()
+  }, [loadReleaseReadiness])
+
   useEffect(() => {
     if (!suites.some((suite) => suite.name === selectedSuite) && suites[0]) {
       setSelectedSuite(suites[0].name)
@@ -341,12 +644,14 @@ export function QualityWorkspace() {
       toast.success('Eval scenario completed')
       await loadQualityData({ silent: true })
       await loadEvalEnvironmentPlan()
+      await loadEvalGate()
+      await loadReleaseReadiness()
     } catch (err) {
       toast.error(err instanceof Error ? err.message : 'Eval scenario failed')
     } finally {
       setEvalBusy(null)
     }
-  }, [evalEnvironmentPlan, loadEvalEnvironmentPlan, loadQualityData, selectedAgentId, selectedScenarioId])
+  }, [evalEnvironmentPlan, loadEvalEnvironmentPlan, loadEvalGate, loadQualityData, loadReleaseReadiness, selectedAgentId, selectedScenarioId])
 
   const runSuite = useCallback(async (suiteName: string) => {
     if (!selectedAgentId) {
@@ -369,12 +674,39 @@ export function QualityWorkspace() {
       toast.success(`Suite completed at ${Math.round(result.percentage)}%`)
       await loadQualityData({ silent: true })
       await loadEvalEnvironmentPlan()
+      await loadEvalGate()
+      await loadReleaseReadiness()
     } catch (err) {
       toast.error(err instanceof Error ? err.message : 'Eval suite failed')
     } finally {
       setEvalBusy(null)
     }
-  }, [evalEnvironmentPlan, loadEvalEnvironmentPlan, loadQualityData, selectedAgentId])
+  }, [evalEnvironmentPlan, loadEvalEnvironmentPlan, loadEvalGate, loadQualityData, loadReleaseReadiness, selectedAgentId])
+
+  const setEvalBaseline = useCallback(async () => {
+    if (!selectedAgentId) {
+      toast.error('Choose an agent first')
+      return
+    }
+    if (evalGateScope === 'scenario' && !selectedScenarioId) {
+      toast.error('Choose a scenario first')
+      return
+    }
+    setEvalBaselineBusy(true)
+    try {
+      const body = evalGateScope === 'scenario'
+        ? { agentId: selectedAgentId, scenarioId: selectedScenarioId, minPercent: evalGate?.minPercent ?? 80, maxRegressionPoints: evalGate?.maxRegressionPoints ?? 5 }
+        : { agentId: selectedAgentId, suite: selectedSuite, minPercent: evalGate?.minPercent ?? 80, maxRegressionPoints: evalGate?.maxRegressionPoints ?? 5 }
+      const result = await api<{ gate: EvalGateResult }>('POST', '/eval/baselines', body)
+      setEvalGate(result.gate)
+      await loadReleaseReadiness()
+      toast.success('Eval baseline saved')
+    } catch (err) {
+      toast.error(err instanceof Error ? err.message : 'Unable to save eval baseline')
+    } finally {
+      setEvalBaselineBusy(false)
+    }
+  }, [evalGate, evalGateScope, loadReleaseReadiness, selectedAgentId, selectedScenarioId, selectedSuite])
 
   const actOnApproval = useCallback(async (approval: ApprovalRequest, approved: boolean) => {
     setApprovalBusy(approval.id)
@@ -382,12 +714,13 @@ export function QualityWorkspace() {
       await api('POST', '/approvals', { id: approval.id, approved })
       toast.success(approved ? 'Approval granted' : 'Approval denied')
       await loadQualityData({ silent: true })
+      await loadReleaseReadiness()
     } catch (err) {
       toast.error(err instanceof Error ? err.message : 'Unable to update approval')
     } finally {
       setApprovalBusy(null)
     }
-  }, [loadQualityData])
+  }, [loadQualityData, loadReleaseReadiness])
 
   if (loading) {
     return (
@@ -451,6 +784,12 @@ export function QualityWorkspace() {
           {activeTab === 'overview' && (
             <div className="flex flex-col gap-6">
               <OperationsPulsePanel defaultRange="7d" compact />
+              <ReleaseReadinessPanel
+                report={releaseReadiness}
+                loading={releaseReadinessLoading}
+                onRefresh={() => void loadReleaseReadiness()}
+                onOpenHref={(href) => router.push(href)}
+              />
 
               <div className="grid gap-3 md:grid-cols-2 xl:grid-cols-4">
                 <StatTile
@@ -600,6 +939,15 @@ export function QualityWorkspace() {
                     loading={evalEnvironmentLoading}
                     onRefresh={() => void loadEvalEnvironmentPlan({ refreshGateway: true })}
                   />
+                  <EvalGatePanel
+                    gate={evalGate}
+                    loading={evalGateLoading}
+                    busy={evalBaselineBusy}
+                    scope={evalGateScope}
+                    onScopeChange={setEvalGateScope}
+                    onRefresh={() => void loadEvalGate()}
+                    onSetBaseline={() => void setEvalBaseline()}
+                  />
                   <button
                     type="button"
                     onClick={() => openMissionTemplate('release-candidate-qa')}