helixevo 0.6.1 → 0.8.0

package/dashboard/app/guide/page.tsx

@@ -18,7 +18,7 @@ const TOC = [
   { id: 'judges', label: 'Multi-Judge System', icon: '⚖' },
   { id: 'networkhealth', label: 'Network Health', icon: '♺' },
   { id: 'autogen', label: 'Auto-Generalization', icon: '↑' },
-  { id: 'metrics', label: 'Closed-Loop Metrics', icon: '📊' },
+  { id: 'metrics', label: 'Proof & Metrics', icon: '📊' },
   { id: 'frontier', label: 'Pareto Frontier', icon: '▲' },
   { id: 'regression', label: 'Regression Testing', icon: '✓' },
   { id: 'research', label: 'Proactive Research', icon: '◎' },
@@ -286,13 +286,13 @@ export default function GuidePage() {
           <div className="grid-3" style={{ marginTop: 24, marginBottom: 24 }}>
             <div className="card" style={{ padding: '18px 18px 16px' }}>
               <div style={{ fontSize: 10, fontWeight: 700, color: 'var(--text-muted)', textTransform: 'uppercase', letterSpacing: 0.7, marginBottom: 8 }}>Start operating</div>
-              <div style={{ fontSize: 15, fontWeight: 700, color: 'var(--text)', marginBottom: 6 }}>Project setup → Watch / Capture → Co-Evolution → Topology</div>
-              <div style={{ fontSize: 12.5, color: 'var(--text-dim)', lineHeight: 1.6 }}>This is the shortest path to seeing pressure, governed response, and structural control in the live product.</div>
+              <div style={{ fontSize: 15, fontWeight: 700, color: 'var(--text)', marginBottom: 6 }}>Project setup → Watch / Capture → Co-Evolution → Topology → Proof</div>
+              <div style={{ fontSize: 12.5, color: 'var(--text-dim)', lineHeight: 1.6 }}>This is the shortest path to seeing pressure, governed response, structural control, and the new bounded prove stage in the live product.</div>
             </div>
             <div className="card" style={{ padding: '18px 18px 16px' }}>
               <div style={{ fontSize: 10, fontWeight: 700, color: 'var(--text-muted)', textTransform: 'uppercase', letterSpacing: 0.7, marginBottom: 8 }}>Understand the brain</div>
               <div style={{ fontSize: 15, fontWeight: 700, color: 'var(--text)', marginBottom: 6 }}>Read the stack, then trace one signal through the loop</div>
-              <div style={{ fontSize: 12.5, color: 'var(--text-dim)', lineHeight: 1.6 }}>The current system is best understood as layered cognition: semantic kernel → observation → pressure → response → transfer → governance → topology.</div>
+              <div style={{ fontSize: 12.5, color: 'var(--text-dim)', lineHeight: 1.6 }}>The current system is best understood as layered cognition: semantic kernel → observation → pressure → response → transfer → governance → topology → proof.</div>
             </div>
             <div className="card" style={{ padding: '18px 18px 16px' }}>
               <div style={{ fontSize: 10, fontWeight: 700, color: 'var(--text-muted)', textTransform: 'uppercase', letterSpacing: 0.7, marginBottom: 8 }}>Fast jumps</div>
@@ -319,11 +319,11 @@ export default function GuidePage() {
           <p className="guide-text">
             HelixEvo still captures failures, proposes skill mutations, evaluates them with judges, and deploys improvements carefully.
             What changed over the recent milestone arc is that these mutation mechanics now live inside a larger architecture that senses pressure,
-            routes intervention under governance, records transfer evidence, reviews topology, and can execute a safe reviewed subset of structural change with rollback.
+            routes intervention under governance, records transfer evidence, reviews topology, executes a safe reviewed subset of structural change with rollback, and now exposes bounded proof review over what appears to have worked.
           </p>
           <p className="guide-text">
             That means the current product should not be explained as only “capture → evolve → validate.” The more truthful frame is:
-            <strong> semantic kernel → observation → pressure → response → transfer → governance → topology review → topology execution → operator surfaces.</strong>
+            <strong> semantic kernel → observation → pressure → response → transfer → governance → topology review → topology execution → proof → operator surfaces.</strong>
           </p>
           <div className="guide-directions">
             <div className="guide-direction">
@@ -359,6 +359,7 @@ export default function GuidePage() {
           <Callout type="info">
             <strong>Prerequisites:</strong> Node.js 18+, <a href="https://bun.sh">Bun</a> (for building),
             and <a href="https://docs.anthropic.com/en/docs/claude-code">Claude CLI</a> with a Claude Max plan.
+            Claude Code remains the default provider. Codex and Ollama are optional providers for shared prompt-in / text-out paths once enabled in <code>~/.helix/config.json</code>.
             Prefer <code>claude auth login</code> managed credentials over exporting a hardcoded <code>CLAUDE_CODE_OAUTH_TOKEN</code>.
           </Callout>
 
@@ -403,7 +404,7 @@ helixevo evolve --verbose
 helixevo graph --optimize
 helixevo topology --status`}</Code>
             <p className="guide-text-sm">
-              <code>evolve</code> mutates skills directly, while <code>graph --optimize</code> and <code>topology</code> expose the higher-level structural review and execution loop.
+              <code>evolve</code> mutates skills directly, while <code>graph --optimize</code> and <code>topology</code> expose the higher-level structural review and execution loop. Optimize now refreshes the review queue first and then reports whether conflict enrichment completed fully or only partially.
             </p>
           </Step>
 
@@ -488,9 +489,14 @@ helixevo topology --status`}</Code>
               },
               {
                 cmd: 'helixevo metrics',
-                desc: 'Measure whether evolution actually reduces corrections over time. This is the primary proof command.',
+                desc: 'Measure correction-rate and evolution-impact trends over time. This remains the quantitative metrics surface inside the broader prove stage.',
                 flags: ['--verbose'],
               },
+              {
+                cmd: 'helixevo proof',
+                desc: 'Review bounded outcome attribution across interventions, transfer, topology execution, semantic adoption, and evolution impact; then verify, defer, or contest proof records explicitly.',
+                flags: ['--status', '--review <recordId>', '--decision <verify|defer|contest>', '--rationale <text>', '--verbose'],
+              },
               {
                 cmd: 'helixevo dashboard',
                 desc: 'Open the premium operator dashboard. It prefers localhost:3847, reuses a known managed dashboard, falls forward if needed, and can auto-update before launch.',
@@ -522,7 +528,7 @@ helixevo topology --status`}</Code>
           <Callout type="tip">
             A good mental grouping is: <strong>observe</strong> with <code>project-setup</code>, <code>watch</code>, and <code>capture</code>;
             <strong>respond</strong> with <code>research</code>, <code>specialize</code>, <code>evolve</code>, and <code>generalize</code>;
-            <strong>restructure</strong> with <code>graph --optimize</code> plus <code>topology</code>; and <strong>prove</strong> with <code>metrics</code>, <code>health</code>, and <code>report</code>.
+            <strong>restructure</strong> with <code>graph --optimize</code> plus <code>topology</code>; and <strong>prove</strong> with <code>proof</code> first, supported by <code>metrics</code>, <code>health</code>, and <code>report</code>.
           </Callout>
         </Section>
 
@@ -729,11 +735,12 @@ helixevo ontology --deprecate <conceptId>`}</Code>
         <Section id="surfaces" title="Dashboard Surface Map" subtitle="Each tab is a different control or observability surface for the same brain.">
           <div className="grid-2" style={{ gap: 12 }}>
             {[
-              ['Overview', 'var(--blue)', 'Top-level cockpit for frontier state, brain foundation, pressure totals, topology review counts, and prepared/applied structural state.'],
+              ['Overview', 'var(--blue)', 'Top-level cockpit for frontier state, brain foundation, pressure totals, topology review counts, prepared/applied structural state, and proof review visibility.'],
               ['Co-Evolution', 'var(--purple)', 'The response cockpit. Use it to inspect routed pressure, governance mode, promotion queue, transfer evidence, and where approved ontology concepts are influencing live route rationale.'],
               ['Skill Network', 'var(--green)', 'Graph-level understanding: relationships, co-evolution signals, inspector context, and structural handoff links.'],
               ['Ontology', 'var(--blue)', 'Semantic control surface for kernel visibility, frontier review, approved extensions, semantic adoption coverage, consumer summaries, and ontology change events.'],
               ['Topology', 'var(--yellow)', 'Governed plasticity surface for review decisions, accepted-ready queue, prepared plans, apply, rollback, and execution history.'],
+              ['Proof', 'var(--text-secondary)', 'Outcome-attribution cockpit for bounded review across interventions, transfer, topology execution, semantic adoption, and evolution impact.'],
               ['Projects', 'var(--blue)', 'Project intake and project-aware pressure surface. Best for capability gaps, activation traces, and promotion feeders.'],
               ['Research', 'var(--purple)', 'Discovery-oriented view grounded in current pressure and routed recommendations rather than disconnected idea generation.'],
               ['Evolution', 'var(--green)', 'Proposal-centric evidence view: judge scores, artifact provenance, and iteration history.'],
@@ -746,8 +753,8 @@ helixevo ontology --deprecate <conceptId>`}</Code>
             ))}
           </div>
           <Callout type="tip">
-            If you are debugging current state, the best sequence is usually: <strong>Overview → Co-Evolution → Ontology → Topology → Skill Network → Projects / Research</strong>.
-            That path mirrors the stack from summary → routed demand → semantic interpretation → structural review/execution → graph context → project or discovery detail.
+            If you are debugging current state, the best sequence is usually: <strong>Overview → Co-Evolution → Ontology → Topology → Proof → Skill Network → Projects / Research</strong>.
+            That path mirrors the stack from summary → routed demand → semantic interpretation → structural review/execution → bounded outcome review → graph context → project or discovery detail.
           </Callout>
         </Section>
 
@@ -851,25 +858,32 @@ Project B: "Use FlashList not FlatList" (React Native perf)
         </Section>
 
         {/* ─── Closed-Loop Metrics ─── */}
-        <Section id="metrics" title="Closed-Loop Metrics" subtitle="Proving that HelixEvo actually makes the agent better — with data, not just LLM scores.">
+        <Section id="metrics" title="Proof & Closed-Loop Metrics" subtitle="The prove stage is now first-class: metrics remain useful, but proof now unifies bounded outcome review across the newer brain loop.">
           <p className="guide-text">
-            The <code>helixevo metrics</code> command answers the most important question: <strong>&ldquo;Is HelixEvo actually
-            reducing corrections?&rdquo;</strong> It tracks correction rates per skill over time and measures the real
-            impact of each evolution.
+            The <code>helixevo proof</code> command is now the primary operator surface for the <strong>prove</strong> stage. It reviews bounded outcome attribution across interventions,
+            transfer, topology execution, semantic adoption, and legacy evolution impact without pretending to know more than the evidence supports.
           </p>
-          <Code title="Terminal">{`helixevo metrics --verbose`}</Code>
+          <Code title="Terminal">{`helixevo proof --status --verbose
+helixevo metrics --verbose`}</Code>
+
+          <h3 className="guide-h3">What Proof Adds</h3>
+          <ul className="guide-list">
+            <li><strong>Unified proof targets:</strong> interventions, realized transfers, topology execution, semantic-adoption effectiveness, and existing evolution impact</li>
+            <li><strong>Bounded outcome states:</strong> effective, mixed, regressed, measuring, and insufficient-evidence</li>
+            <li><strong>Operator review:</strong> verify, defer, or contest proof records explicitly instead of trusting derived heuristics blindly</li>
+            <li><strong>Dedicated dashboard route:</strong> the Prove stage now lands on <code>/proof</code> instead of only the Guide metrics section</li>
+          </ul>
 
-          <h3 className="guide-h3">What It Tracks</h3>
+          <h3 className="guide-h3">What Metrics Still Tracks</h3>
           <ul className="guide-list">
             <li><strong>Per-skill correction rates:</strong> 7-day rolling windows showing how often each skill leads to corrections</li>
             <li><strong>Trend detection:</strong> Each skill is marked as improving (↓), stable (→), or degrading (↑)</li>
             <li><strong>Evolution impact:</strong> Before/after comparison for each evolution — failures/day in the 7 days before vs. after</li>
-            <li><strong>Verdict:</strong> &ldquo;X/Y evolutions reduced corrections&rdquo; — the bottom line</li>
+            <li><strong>Quantitative baseline:</strong> legacy correction reduction remains an important proof input even though it is no longer the whole prove layer</li>
           </ul>
 
           <Callout type="warning">
-            Metrics need time to accumulate. The system needs at least 7 days of data after an evolution to produce
-            a reliable before/after comparison. Results shown as &ldquo;Measuring&rdquo; during the first 3 days.
+            Proof remains bounded. Recent changes should stay <strong>measuring</strong>, weak evidence should stay <strong>insufficient-evidence</strong>, and semantic-adoption proof should be treated as correlational evidence rather than strong direct causality. Treat <strong>regressed</strong> as explicit negative evidence that should trigger route/structure review before retry, and treat <strong>verified</strong> as stronger operator trust in the review state rather than magical proof of causality.
           </Callout>
         </Section>
 
@@ -1077,10 +1091,19 @@ generation: 3
 
         {/* ─── Configuration ─── */}
         <Section id="config" title="Configuration" subtitle="All configurable parameters and their defaults.">
+          <h3 className="guide-h3">Provider control</h3>
+          <div className="guide-params">
+            <Param name="model" type="string" desc="Backward-compatible top-level model alias. It stays in sync with the current default provider model." def='"sonnet"' />
+            <Param name="judgeModel" type="string" desc="Backward-compatible top-level judge model alias. It stays in sync with the current default provider judge model." def='"sonnet"' />
+            <Param name="llm.defaultProvider" type="string" desc="Default provider for shared prompt-in / text-out operations." def='"claude-code"' />
+            <Param name="llm.fallbackPolicy" type="string" desc="Fallback policy for shared provider-eligible operations. Keep disabled unless you want explicit on-failure fallback." def='"disabled"' />
+            <Param name="llm.providers.claudeCode.enabled" type="boolean" desc="Keep Claude Code enabled as the default provider unless you intentionally move the default elsewhere." def="true" />
+            <Param name="llm.providers.codex.enabled" type="boolean" desc="Enable GPT Codex for shared chat / JSON / judge-style paths." def="false" />
+            <Param name="llm.providers.ollama.enabled" type="boolean" desc="Enable Ollama for shared local-model chat / JSON / judge-style paths." def="false" />
+          </div>
+
           <h3 className="guide-h3">Evolution</h3>
           <div className="guide-params">
-            <Param name="model" type="string" desc="LLM model for proposals and clustering." def='"sonnet"' />
-            <Param name="judgeModel" type="string" desc="LLM model for judge evaluations." def='"sonnet"' />
             <Param name="evolution.schedule" type="cron" desc="When to run automatic evolution." def='"0 2 * * *"' />
             <Param name="evolution.minFailuresForEvolution" type="number" desc="Minimum unresolved failures before evolve runs." def="5" />
             <Param name="evolution.maxFailuresPerRun" type="number" desc="Max failures to process per run." def="20" />
@@ -1102,6 +1125,32 @@ generation: 3
           <Code title="~/.helix/config.json">{`{
   "model": "sonnet",
   "judgeModel": "sonnet",
+  "llm": {
+    "defaultProvider": "claude-code",
+    "fallbackPolicy": "disabled",
+    "fallbackOrder": [],
+    "providers": {
+      "claudeCode": {
+        "enabled": true,
+        "command": "claude",
+        "model": "sonnet",
+        "judgeModel": "sonnet"
+      },
+      "codex": {
+        "enabled": false,
+        "command": "codex",
+        "model": "gpt-5-codex",
+        "judgeModel": "gpt-5-codex"
+      },
+      "ollama": {
+        "enabled": false,
+        "command": "ollama",
+        "host": "http://127.0.0.1:11434",
+        "model": "qwen3-coder:latest",
+        "judgeModel": "qwen3-coder:latest"
+      }
+    }
+  },
   "evolution": {
     "schedule": "0 2 * * *",
     "minFailuresForEvolution": 5,
@@ -1131,8 +1180,10 @@ generation: 3
 ├── pressure-interventions.jsonl # Routed intervention ledger across response lanes
 ├── transfer-events.jsonl    # Promotion / transfer evidence across motifs and projects
 ├── governance-state.json    # Operator-selected governance steering state
+├── llm-runtime-state.json   # Default provider, per-provider health, last execution, and fallback truth
 ├── topology-review-candidates.json # Persisted structural review queue
 ├── topology-review-decisions.jsonl # Accept / reject / defer decision ledger
+├── topology-optimize-status.json # Last full/partial optimize refresh status + queue/enrichment summary
 ├── topology-overrides.json   # Applied safe structural topology overrides
 ├── topology-snapshots.json   # Snapshot refs for reviewed execution and rollback
 ├── topology-apply-plans.json # Prepared reviewed topology plans
@@ -1163,7 +1214,8 @@ generation: 3
               ['Observation memory', 'var(--blue)', 'failures.jsonl + activation-traces.jsonl capture what happened, where it happened, and which skills were active.'],
               ['Pressure & response memory', 'var(--yellow)', 'pressure-signals.jsonl + pressure-interventions.jsonl + transfer-events.jsonl describe demand, routing, and reusable promotion evidence.'],
               ['Ontology frontier memory', 'var(--blue)', 'ontology/kernel.json + ontology/frontier.json + ontology/extensions.json + ontology/reviews.jsonl + ontology/change-log.jsonl preserve semantic kernel state, provisional concepts, approved extensions, and review/change lineage while semantic adoption is derived from active runtime/control objects rather than a parallel ontology-usage ledger.'],
-              ['Governance & review memory', 'var(--purple)', 'governance-state.json + topology-review-candidates.json + topology-review-decisions.jsonl preserve why structural decisions are being made.'],
+              ['Governance & provider memory', 'var(--purple)', 'governance-state.json + llm-runtime-state.json preserve adaptation steering plus the truthful backend ledger: default provider, per-provider health, last execution, and fallback state.'],
+              ['Structural review memory', 'var(--purple)', 'topology-review-candidates.json + topology-review-decisions.jsonl + topology-optimize-status.json preserve why structural decisions are being made and whether the last optimize pass was full or degraded.'],
               ['Topology execution memory', 'var(--green)', 'topology-overrides.json + topology-snapshots.json + topology-apply-plans.json + topology-executions.jsonl + topology-artifacts.jsonl preserve reviewed structural execution and rollback.'],
               ['Evaluation & frontier memory', 'var(--blue)', 'evolution-history.json + evolution-artifacts.jsonl + skill-tests.jsonl + canary-registry.json + frontier.json preserve proof, guardrails, and best configurations.'],
               ['Discovery memory', 'var(--purple)', 'knowledge-buffer.json keeps research discoveries and drafts so failed experiments can be iterated instead of lost.'],
@@ -1359,7 +1411,7 @@ generation: 3
             A transfer event is evidence that reusable knowledge was actually promoted or reused across layers or projects. This is how HelixEvo distinguishes a recommendation from a realized knowledge transfer.
           </FAQItem>
           <FAQItem q="How do I prove HelixEvo's brain is working?">
-            Use multiple proof surfaces together: <code>metrics</code> for correction reduction, Co-Evolution for routed interventions and transfer evidence, Topology for reviewed structural execution state, and the verification reports under <code>reports/verification/</code> for milestone-level backtesting.
+            Start with <code>helixevo proof --status</code> or the <code>/proof</code> dashboard route, then use supporting proof surfaces together: <code>metrics</code> for correction reduction, Co-Evolution for routed interventions and transfer evidence, Topology for reviewed structural execution state, and the verification reports under <code>reports/verification/</code> for milestone-level backtesting.
           </FAQItem>
           <FAQItem q="How many failures do I need before evolution works?">
             By default, 5 unresolved failures are required (<code>minFailuresForEvolution</code>) for the standard evolution trigger.

package/dashboard/app/ontology/client.tsx

@@ -10,6 +10,7 @@ import { OperatorLoopTrail } from '@/components/operator-loop-trail'
 import { SurfaceJumpLinks } from '@/components/surface-jump-links'
 import { NextStepEmptyState } from '@/components/next-step-empty-state'
 import type { OntologyControlDashboardSummary, OntologyReviewDecisionStatus } from '@/lib/data'
+import type { ProofDashboardSummary } from '@/lib/proof'
 
 type RunState = 'idle' | 'running' | 'success' | 'error'
 
@@ -35,7 +36,7 @@ function formatMode(value: string) {
   return value.replace(/-/g, ' ')
 }
 
-export default function OntologyClient({ initialDashboard }: { initialDashboard: OntologyControlDashboardSummary }) {
+export default function OntologyClient({ initialDashboard, proof }: { initialDashboard: OntologyControlDashboardSummary; proof: ProofDashboardSummary }) {
   const [dashboard, setDashboard] = useState(initialDashboard)
   const [runState, setRunState] = useState<RunState>('idle')
   const [output, setOutput] = useState('')
@@ -80,6 +81,7 @@ export default function OntologyClient({ initialDashboard }: { initialDashboard:
           { label: `${dashboard.summary.extensions} approved extensions`, tone: dashboard.summary.extensions > 0 ? 'blue' : 'neutral' },
           { label: `${dashboard.adoption.activeConcepts} active concepts`, tone: dashboard.adoption.activeConcepts > 0 ? 'green' : 'neutral' },
           { label: `${dashboard.adoption.routesInfluenced} semantically influenced routes`, tone: dashboard.adoption.routesInfluenced > 0 ? 'purple' : 'neutral' },
+          { label: `${proof.summary.reviewOpen} proof review`, tone: proof.summary.reviewOpen > 0 ? 'yellow' : proof.summary.effective > 0 ? 'green' : 'neutral' },
           { label: formatMode(dashboard.governance.activeMode), tone: dashboard.governance.activeMode === 'transfer-focused' ? 'purple' : dashboard.governance.activeMode === 'project-critical' ? 'yellow' : 'blue' },
         ]}
         actions={
@@ -88,6 +90,10 @@ export default function OntologyClient({ initialDashboard }: { initialDashboard:
               <div className="hero-note-label">Native ontology state</div>
               <div className="hero-note-title">Kernel + review + semantic adoption</div>
               <div className="hero-note-copy">Use this surface to move from frontier hypotheses into approved extensions, inspect active semantic consumers, and manage deprecation with operator-visible risk rather than hidden drift.</div>
+              <div style={{ marginTop: 8, display: 'flex', gap: 6, flexWrap: 'wrap' }}>
+                <Link href="/proof" className="badge badge-gray" style={{ textDecoration: 'none' }}>open proof</Link>
+                <span className="badge badge-gray">{proof.summary.effective} effective records live</span>
+              </div>
             </div>
             <div style={{ display: 'grid', gap: 10 }}>
               <div style={{ display: 'flex', gap: 10, flexWrap: 'wrap', justifyContent: 'flex-end' }}>
@@ -107,6 +113,7 @@ export default function OntologyClient({ initialDashboard }: { initialDashboard:
         <MetricCard label="Approved extensions" value={dashboard.summary.extensions} sublabel={`${dashboard.summary.deprecated} deprecated • ${dashboard.adoption.unusedExtensions} unused`} tone={dashboard.summary.extensions > 0 ? 'blue' : 'neutral'} icon="↑" />
         <MetricCard label="Active semantic concepts" value={dashboard.adoption.activeConcepts} sublabel={`${dashboard.adoption.totalBindings} bindings • ${dashboard.adoption.routesInfluenced} routed influences`} tone={dashboard.adoption.activeConcepts > 0 ? 'green' : 'neutral'} icon="⇄" />
         <MetricCard label="Deprecation-sensitive" value={dashboard.adoption.conceptsAtDeprecationRisk} sublabel="approved concepts with live consumers" tone={dashboard.adoption.conceptsAtDeprecationRisk > 0 ? 'yellow' : 'neutral'} icon="!" />
+        <MetricCard label="Semantic proof review" value={proof.summary.reviewOpen} sublabel={`${proof.summary.effective} effective • ${proof.summary.mixed} mixed`} tone={proof.summary.reviewOpen > 0 ? 'yellow' : proof.summary.effective > 0 ? 'green' : 'neutral'} icon="◇" />
         <MetricCard label="Concept changes" value={dashboard.summary.changeEvents} sublabel={`${dashboard.summary.promoted} promoted • ${dashboard.summary.rejected} rejected`} tone={dashboard.summary.changeEvents > 0 ? 'green' : 'neutral'} icon="⇄" />
       </div>
 

package/dashboard/app/ontology/page.tsx

@@ -1,9 +1,11 @@
 import OntologyClient from './client'
 import { loadOntologyControlSummary } from '@/lib/data'
+import { loadProofDashboardSummary } from '@/lib/proof'
 
 export const dynamic = 'force-dynamic'
 
 export default function OntologyPage() {
   const dashboard = loadOntologyControlSummary()
-  return <OntologyClient initialDashboard={dashboard} />
+  const proof = loadProofDashboardSummary()
+  return <OntologyClient initialDashboard={dashboard} proof={proof} />
 }

package/dashboard/app/page.tsx

@@ -1,5 +1,6 @@
 import Link from 'next/link'
-import { getDashboardSummary, getOntologyDashboardSummary, loadCoEvolutionSummary, loadFailures, loadFrontier, loadGraph, loadHistory, listProjects } from '@/lib/data'
+import { getDashboardSummary, getOntologyDashboardSummary, loadCoEvolutionSummary, loadFailures, loadFrontier, loadGraph, loadHistory, listProjects, loadTopologyDashboardSummary, loadLlmRuntimeState } from '@/lib/data'
+import { loadProofDashboardSummary } from '@/lib/proof'
 import { OverviewActions } from '@/components/overview-actions'
 import { PageHero } from '@/components/page-hero'
 import { MetricCard } from '@/components/metric-card'
@@ -16,10 +17,95 @@ function scoreColor(score: number) {
   return 'var(--red)'
 }
 
+function providerLabel(provider: 'claude-code' | 'codex' | 'ollama') {
+  if (provider === 'claude-code') return 'Claude Code'
+  if (provider === 'codex') return 'GPT Codex'
+  return 'Ollama'
+}
+
+function providerTone(status: 'healthy' | 'degraded' | 'unavailable' | 'unknown') {
+  if (status === 'healthy') return 'green' as const
+  if (status === 'degraded') return 'yellow' as const
+  if (status === 'unavailable') return 'red' as const
+  return 'neutral' as const
+}
+
+function getPriorityActions(params: {
+  unresolved: number
+  proofOpen: number
+  topologyOpen: number
+  optimizeStatus: 'idle' | 'healthy' | 'partial' | 'failed'
+  optimizeNextStep?: string
+  providerStatus: 'healthy' | 'degraded' | 'unavailable' | 'unknown'
+  providerSummary: string
+  providerNextStep?: string
+}) {
+  const actions: Array<{ href: string; title: string; description: string; tone: 'blue' | 'green' | 'purple' | 'yellow' }> = []
+
+  if (params.providerStatus === 'degraded' || params.providerStatus === 'unavailable') {
+    actions.push({
+      href: '/commands',
+      title: 'Stabilize provider control',
+      description: params.providerNextStep ?? params.providerSummary,
+      tone: 'yellow',
+    })
+  }
+
+  if (params.optimizeStatus === 'partial' || params.optimizeStatus === 'failed') {
+    actions.push({
+      href: '/topology',
+      title: 'Review degraded optimize state',
+      description: params.optimizeNextStep ?? 'The review queue refreshed, but structural enrichment did not complete fully. Inspect topology control before treating the queue as fully enriched.',
+      tone: 'yellow',
+    })
+  }
+
+  if (params.proofOpen > 0) {
+    actions.push({
+      href: '/proof',
+      title: 'Review open proof records',
+      description: `${params.proofOpen} proof record${params.proofOpen === 1 ? '' : 's'} currently need operator review before the prove layer becomes more trustworthy.`,
+      tone: 'blue',
+    })
+  }
+
+  if (params.topologyOpen > 0) {
+    actions.push({
+      href: '/topology',
+      title: 'Triage structural backlog',
+      description: `${params.topologyOpen} topology review item${params.topologyOpen === 1 ? '' : 's'} are waiting for accept/defer/reject decisions.`,
+      tone: 'purple',
+    })
+  }
+
+  if (params.unresolved > 0) {
+    actions.push({
+      href: '/coevolution',
+      title: 'Route live pressure',
+      description: `${params.unresolved} unresolved correction${params.unresolved === 1 ? '' : 's'} still need to be routed back into the learning loop.`,
+      tone: 'green',
+    })
+  }
+
+  if (actions.length === 0) {
+    actions.push({
+      href: '/projects',
+      title: 'Setup a project',
+      description: 'Analyze a folder or GitHub repo, match skills, and identify capability gaps to seed the next loop.',
+      tone: 'green',
+    })
+  }
+
+  return actions.slice(0, 3)
+}
+
 export default function Overview() {
   const summary = getDashboardSummary()
   const ontology = getOntologyDashboardSummary()
   const coevolution = loadCoEvolutionSummary()
+  const topologyControl = loadTopologyDashboardSummary()
+  const llmRuntime = loadLlmRuntimeState()
+  const proof = loadProofDashboardSummary()
   const frontier = loadFrontier()
   const history = loadHistory()
   const graph = loadGraph()
@@ -27,6 +113,18 @@ export default function Overview() {
   const unresolved = failures.filter((failure) => !failure.resolved)
   const recentRuns = history.iterations.slice(-4).reverse()
   const topSkills = [...graph.nodes].sort((a, b) => b.score - a.score).slice(0, 10)
+  const defaultProvider = llmRuntime.providers[llmRuntime.defaultProvider]
+  const priorityActions = getPriorityActions({
+    unresolved: summary.failures.unresolved,
+    proofOpen: proof.summary.reviewOpen,
+    topologyOpen: topologyControl.summary.open,
+    optimizeStatus: topologyControl.optimizeStatus.status,
+    optimizeNextStep: topologyControl.optimizeStatus.nextStep,
+    providerStatus: defaultProvider.status,
+    providerSummary: defaultProvider.summary,
+    providerNextStep: defaultProvider.nextStep,
+  })
+  const primaryAction = priorityActions[0]
 
   return (
     <div className="overview-grid">
@@ -42,19 +140,21 @@ export default function Overview() {
           { label: `${coevolution.pressureMotifs.promotionReady} promotion-ready motifs`, tone: coevolution.pressureMotifs.promotionReady > 0 ? 'purple' : 'neutral' },
           { label: `${coevolution.topologyReviews.open} topology reviews`, tone: coevolution.topologyReviews.open > 0 ? 'yellow' : 'green' },
           { label: `${coevolution.topologyExecution.prepared} prepared structural plans`, tone: coevolution.topologyExecution.prepared > 0 ? 'blue' : 'neutral' },
+          { label: `${proof.summary.reviewOpen} proof reviews`, tone: proof.summary.reviewOpen > 0 ? 'yellow' : proof.summary.effective > 0 ? 'green' : 'neutral' },
+          { label: `${providerLabel(llmRuntime.defaultProvider)} ${defaultProvider.status}`, tone: providerTone(defaultProvider.status) },
           { label: `mode: ${coevolution.governance.activeMode.replace(/-/g, ' ')}`, tone: coevolution.governance.activeMode === 'transfer-focused' ? 'purple' : coevolution.governance.activeMode === 'project-critical' ? 'yellow' : 'blue' },
         ]}
         actions={
-          <Link href="/projects" className="metric-card-anchor" style={{ minWidth: 240, display: 'block' }}>
-            <div className="metric-card metric-card-green metric-card-link">
+          <Link href={primaryAction.href} className="metric-card-anchor" style={{ minWidth: 260, display: 'block' }}>
+            <div className={`metric-card metric-card-${primaryAction.tone} metric-card-link`}>
               <div className="metric-card-header">
                 <div>
-                  <div className="metric-card-label">Next workflow</div>
-                  <div className="metric-card-value" style={{ fontSize: 24 }}>Setup a project</div>
+                  <div className="metric-card-label">Priority now</div>
+                  <div className="metric-card-value" style={{ fontSize: 24 }}>{primaryAction.title}</div>
                 </div>
                 <div className="metric-card-icon">↗</div>
               </div>
-              <div className="metric-card-sublabel">Analyze a folder or GitHub repo, match skills, and identify capability gaps.</div>
+              <div className="metric-card-sublabel">{primaryAction.description}</div>
             </div>
           </Link>
         }
@@ -68,6 +168,7 @@ export default function Overview() {
         <MetricCard label="Unresolved corrections" value={summary.failures.unresolved} sublabel={`out of ${summary.failures.total} captured failures`} tone={summary.failures.unresolved > 0 ? 'yellow' : 'green'} href={summary.failures.unresolved > 0 ? '#attention' : '/evolution'} icon="!" />
         <MetricCard label="Discoveries" value={summary.buffer.discoveries} sublabel={`${summary.buffer.drafts} drafts in progress`} tone="blue" href="/research" icon="◎" />
         <MetricCard label="Frontier candidates" value={frontier.programs.length} sublabel={`${summary.canaries} active canaries`} tone="neutral" href="/frontier" icon="▲" />
+        <MetricCard label="Proof review" value={proof.summary.reviewOpen} sublabel={`${proof.summary.effective} effective • ${proof.summary.regressed} regressed`} tone={proof.summary.reviewOpen > 0 ? 'yellow' : proof.summary.effective > 0 ? 'green' : 'neutral'} href="/proof" icon="◇" />
       </div>
 
       <SectionFrame
@@ -108,6 +209,69 @@ export default function Overview() {
         />
       </SectionFrame>
 
+      <SectionFrame
+        eyebrow="Provider control"
+        title="Live backend truth"
+        description="Claude Code remains the default provider, while Codex and Ollama are optional for shared prompt-in/text-out paths. Claude-only web-search and research tooling stay explicitly Claude-scoped."
+        tone="blue"
+      >
+        <div className="grid-2" style={{ gap: 16 }}>
+          <div className="summary-list">
+            {(['claude-code', 'codex', 'ollama'] as const).map((provider) => {
+              const snapshot = llmRuntime.providers[provider]
+              return (
+                <div key={provider} className="summary-row">
+                  <div className="summary-row-main">
+                    <div className="summary-row-title">{providerLabel(provider)}</div>
+                    <div className="summary-row-meta">{snapshot.summary}</div>
+                    {snapshot.nextStep ? <div className="summary-row-meta" style={{ marginTop: 6 }}>Next: {snapshot.nextStep}</div> : null}
+                  </div>
+                  <span className={`hero-chip hero-chip-${providerTone(snapshot.status)}`}>{snapshot.status}</span>
+                </div>
+              )
+            })}
+          </div>
+          <div style={{ display: 'grid', gap: 12 }}>
+            <MetricCard
+              label="Default provider"
+              value={providerLabel(llmRuntime.defaultProvider)}
+              sublabel={`fallback: ${llmRuntime.fallbackPolicy}${llmRuntime.fallbackOrder.length > 0 ? ` • ${llmRuntime.fallbackOrder.map((provider) => providerLabel(provider)).join(' → ')}` : ''}`}
+              tone={providerTone(defaultProvider.status)}
+              href="/commands"
+              icon="☍"
+            />
+            <MetricCard
+              label="Last provider run"
+              value={llmRuntime.lastExecution?.usedProvider ? providerLabel(llmRuntime.lastExecution.usedProvider) : 'None'}
+              sublabel={llmRuntime.lastExecution ? llmRuntime.lastExecution.summary : 'No provider-backed execution has been recorded yet.'}
+              tone={llmRuntime.lastExecution?.success ? 'green' : llmRuntime.lastExecution ? 'yellow' : 'neutral'}
+              href="/commands"
+              icon="↺"
+            />
+            <div className="signal-text">Commands, status, and dashboard surfaces now track whether execution stayed on the selected provider, degraded, or used an explicit fallback path.</div>
+          </div>
+        </div>
+      </SectionFrame>
+
+      <SectionFrame
+        eyebrow="Priority now"
+        title="Top ranked next actions"
+        description="This layer compresses the live loop into the most important operator moves right now instead of leaving everything as flat dashboard signal."
+        tone="blue"
+      >
+        <div className="summary-list">
+          {priorityActions.map((action, index) => (
+            <Link key={`${action.href}-${index}`} href={action.href} className="summary-row">
+              <div className="summary-row-main">
+                <div className="summary-row-title">{index + 1}. {action.title}</div>
+                <div className="summary-row-meta">{action.description}</div>
+              </div>
+              <span className={`hero-chip hero-chip-${action.tone}`}>open</span>
+            </Link>
+          ))}
+        </div>
+      </SectionFrame>
+
       <SectionFrame
         eyebrow="Brain foundation"
         title="Semantic backbone"
@@ -215,8 +379,10 @@ export default function Overview() {
           <span className="badge badge-gray">deprecation risk → {ontology.ontologyLoop.adoption.conceptsAtDeprecationRisk} concepts • {ontology.ontologyLoop.adoption.unusedExtensions} unused extensions</span>
           <span className="badge badge-gray">topology → {ontology.topologyReviews.open} open • {ontology.topologyReviews.accepted} accepted • {ontology.topologyReviews.generatedFromManualReview} manual-route</span>
           <span className="badge badge-gray">execution → {ontology.topologyExecution.prepared} prepared • {ontology.topologyExecution.applied} applied • {ontology.topologyExecution.rolledBack} rolled back</span>
+          <span className="badge badge-gray">proof → {proof.summary.total} total • {proof.summary.effective} effective • {proof.summary.reviewOpen} open review</span>
           <Link href="/ontology" className="badge badge-blue" style={{ textDecoration: 'none' }}>Open ontology control</Link>
           <Link href="/topology" className="badge badge-blue" style={{ textDecoration: 'none' }}>Open topology control</Link>
+          <Link href="/proof" className="badge badge-blue" style={{ textDecoration: 'none' }}>Open proof control</Link>
           <span className="badge badge-gray">governance: {ontology.governance.activeMode.replace(/-/g, ' ')} ({ontology.governance.source})</span>
           <span className="badge badge-gray">routes → research {ontology.governedRoutes.research} • specialize {ontology.governedRoutes.specialize} • evolve {ontology.governedRoutes.evolve} • generalize {ontology.governedRoutes.generalize} • manual-review {ontology.governedRoutes['manual-review']}</span>
           <span className="badge badge-gray">{ontology.enrichedSkillNodes} skills carry explicit brain metadata</span>