diff --git a/.github/workflows/runner-protocol-live-evals.yml b/.github/workflows/runner-protocol-live-evals.yml
index f659f5ec65..e3eafa2da5 100644
--- a/.github/workflows/runner-protocol-live-evals.yml
+++ b/.github/workflows/runner-protocol-live-evals.yml
@@ -213,6 +213,11 @@ jobs:
             --max-parallel "$MAX_PARALLEL" \
             --output runner-protocol-eval-catalog.json
 
+      - name: Require the chat-report renderer before paid execution
+        run: |
+          set -euo pipefail
+          python3 .paperclip-evals/evals/paperclip-runner/tools/eval_program.py report --help | grep -q -- --public-viewer
+
       - name: Upload immutable campaign catalog
         uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         with:
@@ -259,6 +264,9 @@ jobs:
           pnpm --filter @paperclipai/paperclip-runner build:typescript
           pnpm --filter @paperclipai/paperclip-runner build:runner-binaries
           pnpm --filter @paperclipai/paperclip-runner build:issue-thread
+          # Older target refs must fail before paid cells, not publish an empty viewer.
+          grep -q 'paperclip-eval-report' packages/paperclip-runner/dist-issue-thread/assets/*.js
+          grep -q 'evalbook-site' packages/paperclip-runner/dist-issue-thread/assets/*.css
 
       - name: Package a portable provider runtime
         run: |
@@ -290,6 +298,14 @@ jobs:
           compression-level: 0
           if-no-files-found: error
 
+      - name: Upload canonical viewer for publisher byte verification
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: runner-protocol-viewer-${{ github.run_id }}-${{ github.run_attempt }}
+          path: packages/paperclip-runner/dist-issue-thread/
+          retention-days: 30
+          if-no-files-found: error
+
   eval_shard_0:
     name: Direct eval ${{ matrix.rosterId }} / ${{ matrix.caseId }}
     needs: [authorize, catalog, build_runner]
@@ -595,14 +611,28 @@ jobs:
           python3 .paperclip-evals/evals/paperclip-runner/tools/eval_program.py report \
             --runs-root runner-protocol-merged/public-runs \
             --output runner-protocol-merged/public-report \
+            --viewer-root runner-protocol-build/extracted/dist-issue-thread \
+            --public-viewer \
             --inventory .paperclip-evals/evals/paperclip-runner/inventory.json \
             --coverage-matrix .paperclip-evals/evals/paperclip-runner/coverage-matrix.json
           cp runner-protocol-merged/campaign.json runner-protocol-merged/public-report/campaign.json
 
+      - name: Set up report browser verification
+        uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6
+        with:
+          version: 9.15.4
+
+      - name: Verify the actual chat viewer before publication
+        run: |
+          pnpm install --frozen-lockfile --ignore-scripts
+          pnpm --filter @paperclipai/paperclip-runner exec playwright install --with-deps chromium
+          node packages/paperclip-runner/scripts/verify-runner-evalbook-viewer.mjs --report-root runner-protocol-merged/public-report --screenshots runner-protocol-merged/viewer-proof
+          node packages/paperclip-runner/scripts/verify-runner-evalbook-viewer.mjs --report-root runner-protocol-merged/report
+
       - name: Enforce the static public allowlist
         id: public_report
         run: |
-          node --input-type=module -e 'import { validatePublicProtocolEvalReport } from "./packages/paperclip-runner/scripts/publish-runner-protocol-eval-history.mjs"; await validatePublicProtocolEvalReport("runner-protocol-merged/public-report");'
+          node --input-type=module -e 'import { validatePublicProtocolEvalReport } from "./packages/paperclip-runner/scripts/publish-runner-protocol-eval-history.mjs"; await validatePublicProtocolEvalReport("runner-protocol-merged/public-report", { viewerRoot: "runner-protocol-build/extracted/dist-issue-thread" });'
           echo "ready=true" >> "$GITHUB_OUTPUT"
 
       - name: Add campaign result to the workflow summary
@@ -649,6 +679,7 @@ jobs:
       id-token: write
     environment:
       name: runner-e2e-history
+      url: ${{ steps.publish.outputs.report_url }}
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
         with:
@@ -666,6 +697,12 @@ jobs:
           name: runner-protocol-eval-public-${{ github.run_id }}-${{ github.run_attempt }}
           path: runner-protocol-public-report
 
+      - name: Download the same-run canonical viewer for byte verification
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
+        with:
+          name: runner-protocol-viewer-${{ github.run_id }}-${{ github.run_attempt }}
+          path: runner-protocol-trusted-viewer
+
       - name: Exchange GitHub OIDC identity for scoped AWS credentials
         uses: aws-actions/configure-aws-credentials@e6de054238d6b7531b4efff3b6587d9aade6a06c # v6
         with:
@@ -673,8 +710,10 @@ jobs:
           aws-region: ${{ vars.RUNNER_PROTOCOL_EVAL_HISTORY_AWS_REGION || vars.RUNNER_E2E_HISTORY_AWS_REGION }}
 
       - name: Publish versioned report and refresh the root index
+        id: publish
         env:
           PAPERCLIP_RUNNER_PROTOCOL_EVAL_PUBLIC_REPORT_DIR: ${{ github.workspace }}/runner-protocol-public-report
+          PAPERCLIP_RUNNER_PROTOCOL_EVAL_VIEWER_DIR: ${{ github.workspace }}/runner-protocol-trusted-viewer
           RUNNER_PROTOCOL_EVAL_HISTORY_S3_BUCKET: ${{ vars.RUNNER_PROTOCOL_EVAL_HISTORY_S3_BUCKET || vars.RUNNER_E2E_HISTORY_S3_BUCKET }}
           RUNNER_PROTOCOL_EVAL_HISTORY_PREFIX: ${{ vars.RUNNER_PROTOCOL_EVAL_HISTORY_PREFIX || 'runner-protocol-evals' }}
           RUNNER_PROTOCOL_EVAL_HISTORY_PUBLIC_BASE_URL: ${{ vars.RUNNER_PROTOCOL_EVAL_HISTORY_PUBLIC_BASE_URL || vars.RUNNER_E2E_HISTORY_PUBLIC_BASE_URL }}
diff --git a/packages/paperclip-runner/devtools/issue-thread/src/App.tsx b/packages/paperclip-runner/devtools/issue-thread/src/App.tsx
index 5ebeca9d49..c511c631fc 100644
--- a/packages/paperclip-runner/devtools/issue-thread/src/App.tsx
+++ b/packages/paperclip-runner/devtools/issue-thread/src/App.tsx
@@ -12,6 +12,7 @@ import type { CapabilityDevtoolsSnapshot } from "../../../src/devtools";
 import { capabilityDenialCount } from "../../../src/issue-thread/types";
 import { Composer } from "./Composer";
 import { EvidencePanel } from "./EvidencePanel";
+import type { CapabilityDevtoolsTab } from "./DevtoolsInspector";
 import { Icon } from "./Icons";
 import { IssueHeader } from "./IssueHeader";
 import { applyFakeInteractionResponse } from "./fake-store";
@@ -78,6 +79,7 @@ interface EmbeddedEvalCheck {
 }
 
 interface EmbeddedEvalReport {
+  publication?: { schema: string; notice: string };
   attemptId: string;
   caseId: string;
   disposition: string;
@@ -101,7 +103,7 @@ interface EmbeddedEvalReport {
     runnerBuild: string;
     startedAt: string;
     finishedAt: string;
-    durationMs: number;
+    durationMs: number | null;
     initialRevision: number;
     finalRevision: number;
     usage: {
@@ -117,7 +119,7 @@ interface EmbeddedEvalReport {
     } | null;
   };
   view: CapabilityIssueThreadSnapshot;
-  devtools: CapabilityDevtoolsSnapshot;
+  devtools: CapabilityDevtoolsSnapshot | null;
   navigation: { suiteHref: string; previous: { label: string; href: string } | null; next: { label: string; href: string } | null };
 }
 
@@ -332,6 +334,7 @@ export function App() {
   const [panelOpen, setPanelOpen] = useState(() => embeddedEval !== null ||
     readStoredFlag(route.surface === "chat" ? CHAT_PANEL_OPEN_KEY : PANEL_OPEN_KEY, false));
   const [panelWidth, setPanelWidth] = useState(() => readStoredNumber(PANEL_WIDTH_KEY, 384));
+  const [devtoolsTab, setDevtoolsTab] = useState<CapabilityDevtoolsTab>(embeddedEval !== null ? "eval" : "evidence");
   const [segment, setSegment] = useState<"thread" | "evidence">(route.segment);
   const [openSections, setOpenSections] = useState<CapabilityEvidenceSectionId[]>(["tools"]);
   const [selectedTurnId, setSelectedTurnId] = useState<string | "all">("all");
@@ -491,7 +494,7 @@ export function App() {
         await document.fonts.ready;
       }
       if (cancelled) return;
-      if (scroller !== null) scroller.scrollTop = scroller.scrollHeight;
+      if (scroller !== null) scroller.scrollTop = embeddedEval === null ? scroller.scrollHeight : 0;
       await new Promise<void>((resolve) => requestAnimationFrame(() => resolve()));
       if (!cancelled) setSettled(true);
     })();
@@ -501,14 +504,14 @@ export function App() {
   }, [snapshot]);
 
   useEffect(() => {
-    if (!panelOpen || snapshot === null || route.mode !== "live") return;
+    if (embeddedEval !== null || !panelOpen || snapshot === null || route.mode !== "live") return;
     if (historicSessionId !== null) return;
     let cancelled = false;
     void capabilityLiveClient.devtools(snapshot.sessionId)
       .then((next) => { if (!cancelled) setDevtools(next); })
       .catch((cause) => { if (!cancelled) setActionError(describe(cause)); });
     return () => { cancelled = true; };
-  }, [historicSessionId, panelOpen, route.mode, snapshot?.renderedAt, snapshot?.sessionId]);
+  }, [embeddedEval, historicSessionId, panelOpen, route.mode, snapshot?.renderedAt, snapshot?.sessionId]);
 
   useEffect(() => {
     if (!chat || snapshot === null || historicSessionId !== null) return;
@@ -571,6 +574,7 @@ export function App() {
   const openEvidence = useCallback(
     (section: CapabilityEvidenceSectionId, recordId: string) => {
       setPanelOpen(true);
+      setDevtoolsTab("evidence");
       setSegment("evidence");
       setSelectedTurnId("all");
       setOpenSections((current) => (current.includes(section) ? current : [...current, section]));
@@ -1363,7 +1367,7 @@ export function App() {
             >
               <div className="pit-thread">
                 {embeddedEval !== null ? (
-                  <div className="pit-eval-boundary" data-phase="execution"><strong>Eval execution</strong></div>
+                  <div className="pit-eval-boundary" data-phase="execution"><strong>Eval execution</strong>{embeddedEval.publication ? <span>{embeddedEval.publication.notice}</span> : null}</div>
                 ) : null}
                 {snapshot.turns.length === 0 ? (
                   <section className="pit-empty-thread" data-testid="clean-room-empty">
@@ -1404,7 +1408,7 @@ export function App() {
                 {embeddedEval !== null ? (
                   <div className="pit-eval-boundary" data-phase="post-run">
                     <strong>Post-run state</strong>
-                    <span>Final mock control-plane revision {embeddedEval.run.finalRevision}</span>
+                    <span>{embeddedEval.publication ? "Company-state details withheld from public replay" : `Final mock control-plane revision ${embeddedEval.run.finalRevision}`}</span>
                     <EvalAssertions assertions={embeddedEval.checks.filter((check) => check.anchor.kind === "run")} />
                   </div>
                 ) : null}
@@ -1425,7 +1429,7 @@ export function App() {
             ) : null}
           </div>
 
-          <Composer
+          {embeddedEval === null ? <Composer
             model={snapshot.composer}
             sessionId={snapshot.sessionId}
             onSend={send}
@@ -1439,7 +1443,7 @@ export function App() {
                 .getElementById(`interaction-${interactionId}`)
                 ?.scrollIntoView({ block: "center" });
             }}
-          />
+          /> : null}
         </main>
 
         {showPanel && layout === "side" ? (
@@ -1496,6 +1500,8 @@ export function App() {
         {showPanel ? (
           <EvidencePanel
             snapshot={snapshot}
+            devtoolsTab={devtoolsTab}
+            onDevtoolsTabChange={setDevtoolsTab}
             evalReport={embeddedEval}
             {...(embeddedEval !== null || (route.mode === "live" && historicSessionId === null) ? { devtools } : {})}
             onForkRevision={(revision) => {
diff --git a/packages/paperclip-runner/devtools/issue-thread/src/DevtoolsInspector.tsx b/packages/paperclip-runner/devtools/issue-thread/src/DevtoolsInspector.tsx
index acfd180775..ee057682b2 100644
--- a/packages/paperclip-runner/devtools/issue-thread/src/DevtoolsInspector.tsx
+++ b/packages/paperclip-runner/devtools/issue-thread/src/DevtoolsInspector.tsx
@@ -23,6 +23,7 @@ export interface EvalInspectorReport {
   disposition: string;
   passed: boolean;
   checks: EvalAssertion[];
+  publication?: { schema: string; notice: string };
   run: {
     model: string;
     provider: string;
@@ -41,7 +42,7 @@ export interface EvalInspectorReport {
     runnerBuild: string;
     startedAt: string;
     finishedAt: string;
-    durationMs: number;
+    durationMs: number | null;
     initialRevision: number;
     finalRevision: number;
     usage: {
@@ -53,7 +54,7 @@ export interface EvalInspectorReport {
       reasoningTokens: number;
       providerReportedCostNanodollars?: number;
       estimatedCostNanodollars: number;
-      pricingVersion: string;
+      pricingVersion?: string;
     } | null;
   };
 }
@@ -197,6 +198,149 @@ function documentsOf(state: Json): Array<{
   });
 }
 
+export function EvalReportInspector({
+  evalReport,
+}: {
+  evalReport: EvalInspectorReport;
+}) {
+  const isPublic = Boolean(evalReport.publication);
+  return (
+    <div className="pit-devtools-pane pit-eval-inspector">
+      <div className="pit-eval-summary-head">
+        <a href="../../index.html">← Eval suite</a>
+        <strong>
+          {evalReport.passed
+            ? "PASS"
+            : evalReport.disposition.replaceAll("_", " ").toUpperCase()}
+        </strong>
+        <code>{evalReport.attemptId}</code>
+      </div>
+      <dl className="pit-eval-run-facts">
+        <div>
+          <dt>Model</dt>
+          <dd>
+            {evalReport.run.model.startsWith(`${evalReport.run.provider}/`)
+              ? evalReport.run.model
+              : `${evalReport.run.provider}/${evalReport.run.model}`}
+          </dd>
+        </div>
+        <div>
+          <dt>Configuration</dt>
+          <dd>{evalReport.run.configuration}</dd>
+        </div>
+        <div>
+          <dt>Session</dt>
+          <dd>
+            {isPublic
+              ? "Withheld from public replay"
+              : evalReport.run.sessionId}
+          </dd>
+        </div>
+        <div>
+          <dt>Provider session</dt>
+          <dd>
+            {isPublic
+              ? "Withheld from public replay"
+              : (evalReport.run.providerSessionId ?? "unavailable")}
+          </dd>
+        </div>
+        <div>
+          <dt>Driver</dt>
+          <dd>
+            {evalReport.run.driver}
+            {evalReport.run.providerVersion
+              ? ` · ${evalReport.run.providerVersion}`
+              : ""}
+          </dd>
+        </div>
+        {evalReport.run.agentVersion ? (
+          <div>
+            <dt>Agent version</dt>
+            <dd>{evalReport.run.agentVersion}</dd>
+          </div>
+        ) : null}
+        <div>
+          <dt>Retained session</dt>
+          <dd>
+            {isPublic
+              ? "Withheld from public replay"
+              : evalReport.run.retainedSession === true
+                ? (evalReport.run.retainedSessionStatus ?? "retained")
+                : "not applicable"}
+          </dd>
+        </div>
+        <div>
+          <dt>Duration</dt>
+          <dd>
+            {evalReport.run.durationMs == null
+              ? "unavailable"
+              : `${evalReport.run.durationMs} ms`}
+          </dd>
+        </div>
+        <div>
+          <dt>Fixture</dt>
+          <dd>{evalReport.run.fixtureDigest}</dd>
+        </div>
+        <div>
+          <dt>State</dt>
+          <dd>
+            {isPublic
+              ? "Withheld from public replay"
+              : `r${evalReport.run.initialRevision} → r${evalReport.run.finalRevision}`}
+          </dd>
+        </div>
+        <div>
+          <dt>Tokens</dt>
+          <dd>
+            {evalReport.run.usage === null
+              ? "unknown"
+              : `${evalReport.run.usage.inputTokens} in · ${evalReport.run.usage.outputTokens} out · ${evalReport.run.usage.cachedInputTokens} cached`}
+          </dd>
+        </div>
+        <div>
+          <dt>Agent turns</dt>
+          <dd>{evalReport.run.usage?.agentTurns ?? "unknown"}</dd>
+        </div>
+        <div>
+          <dt>Provider requests</dt>
+          <dd>{evalReport.run.usage?.providerRequests ?? "unavailable"}</dd>
+        </div>
+        <div>
+          <dt>Estimated cost</dt>
+          <dd>
+            {evalReport.run.usage === null
+              ? "unknown"
+                  : `$${(evalReport.run.usage.estimatedCostNanodollars / 1_000_000_000).toFixed(6)}${evalReport.run.usage.pricingVersion ? ` · ${evalReport.run.usage.pricingVersion}` : ""}`}
+          </dd>
+        </div>
+        <div>
+          <dt>Provider list cost</dt>
+          <dd>
+            {typeof evalReport.run.usage?.providerReportedCostNanodollars !==
+            "number"
+              ? "unknown"
+              : `$${(evalReport.run.usage.providerReportedCostNanodollars / 1_000_000_000).toFixed(6)}`}
+          </dd>
+        </div>
+        <div>
+          <dt>Runner</dt>
+          <dd>{evalReport.run.runnerPackageDigest}</dd>
+        </div>
+        <div>
+          <dt>Runner build</dt>
+          <dd>{evalReport.run.runnerBuild}</dd>
+        </div>
+        <div>
+          <dt>runnerd</dt>
+          <dd>{evalReport.run.runnerdDigest}</dd>
+        </div>
+      </dl>
+      <h3>Assertions</h3>
+      <EvalAssertions assertions={evalReport.checks} />
+    </div>
+  );
+}
+
 export function DevtoolsInspector({
   snapshot,
   onFork,
@@ -291,6 +435,8 @@ export function DevtoolsInspector({
           className="pit-button"
           type="button"
           onClick={() => onFork(revision)}
+          disabled={evalReport != null}
+          title={evalReport ? "Eval reports are read-only" : undefined}
         >
           <Icon name="branch" /> Fork r{revision}
         </button>
@@ -328,124 +474,7 @@ export function DevtoolsInspector({
         ))}
       </div>
       {tab === "eval" && evalReport ? (
-        <div className="pit-devtools-pane pit-eval-inspector">
-          <div className="pit-eval-summary-head">
-            <a href="../../index.html">← Eval suite</a>
-            <strong>
-              {evalReport.passed
-                ? "PASS"
-                : evalReport.disposition.replaceAll("_", " ").toUpperCase()}
-            </strong>
-            <code>{evalReport.attemptId}</code>
-          </div>
-          <dl className="pit-eval-run-facts">
-            <div>
-              <dt>Model</dt>
-              <dd>
-                {evalReport.run.model.startsWith(`${evalReport.run.provider}/`)
-                  ? evalReport.run.model
-                  : `${evalReport.run.provider}/${evalReport.run.model}`}
-              </dd>
-            </div>
-            <div>
-              <dt>Configuration</dt>
-              <dd>{evalReport.run.configuration}</dd>
-            </div>
-            <div>
-              <dt>Session</dt>
-              <dd>{evalReport.run.sessionId}</dd>
-            </div>
-            <div>
-              <dt>Provider session</dt>
-              <dd>{evalReport.run.providerSessionId ?? "unavailable"}</dd>
-            </div>
-            <div>
-              <dt>Driver</dt>
-              <dd>
-                {evalReport.run.driver}
-                {evalReport.run.providerVersion
-                  ? ` · ${evalReport.run.providerVersion}`
-                  : ""}
-              </dd>
-            </div>
-            {evalReport.run.agentVersion ? (
-              <div>
-                <dt>Agent version</dt>
-                <dd>{evalReport.run.agentVersion}</dd>
-              </div>
-            ) : null}
-            <div>
-              <dt>Retained session</dt>
-              <dd>
-                {evalReport.run.retainedSession === true
-                  ? (evalReport.run.retainedSessionStatus ?? "retained")
-                  : "not applicable"}
-              </dd>
-            </div>
-            <div>
-              <dt>Duration</dt>
-              <dd>{evalReport.run.durationMs} ms</dd>
-            </div>
-            <div>
-              <dt>Fixture</dt>
-              <dd>{evalReport.run.fixtureDigest}</dd>
-            </div>
-            <div>
-              <dt>State</dt>
-              <dd>
-                r{evalReport.run.initialRevision} → r
-                {evalReport.run.finalRevision}
-              </dd>
-            </div>
-            <div>
-              <dt>Tokens</dt>
-              <dd>
-                {evalReport.run.usage === null
-                  ? "unknown"
-                  : `${evalReport.run.usage.inputTokens} in · ${evalReport.run.usage.outputTokens} out · ${evalReport.run.usage.cachedInputTokens} cached`}
-              </dd>
-            </div>
-            <div>
-              <dt>Agent turns</dt>
-              <dd>{evalReport.run.usage?.agentTurns ?? "unknown"}</dd>
-            </div>
-            <div>
-              <dt>Provider requests</dt>
-              <dd>{evalReport.run.usage?.providerRequests ?? "unavailable"}</dd>
-            </div>
-            <div>
-              <dt>Estimated cost</dt>
-              <dd>
-                {evalReport.run.usage === null
-                  ? "unknown"
-                  : `$${(evalReport.run.usage.estimatedCostNanodollars / 1_000_000_000).toFixed(6)} · ${evalReport.run.usage.pricingVersion}`}
-              </dd>
-            </div>
-            <div>
-              <dt>Provider list cost</dt>
-              <dd>
-                {typeof evalReport.run.usage
-                  ?.providerReportedCostNanodollars !== "number"
-                  ? "unknown"
-                  : `$${(evalReport.run.usage.providerReportedCostNanodollars / 1_000_000_000).toFixed(6)}`}
-              </dd>
-            </div>
-            <div>
-              <dt>Runner</dt>
-              <dd>{evalReport.run.runnerPackageDigest}</dd>
-            </div>
-            <div>
-              <dt>Runner build</dt>
-              <dd>{evalReport.run.runnerBuild}</dd>
-            </div>
-            <div>
-              <dt>runnerd</dt>
-              <dd>{evalReport.run.runnerdDigest}</dd>
-            </div>
-          </dl>
-          <h3>Assertions</h3>
-          <EvalAssertions assertions={evalReport.checks} />
-        </div>
+        <EvalReportInspector evalReport={evalReport} />
       ) : null}
       {tab === "timeline" ? (
         <div className="pit-devtools-list">
diff --git a/packages/paperclip-runner/devtools/issue-thread/src/EvidencePanel.tsx b/packages/paperclip-runner/devtools/issue-thread/src/EvidencePanel.tsx
index 61aa2d7373..7c7dd485c4 100644
--- a/packages/paperclip-runner/devtools/issue-thread/src/EvidencePanel.tsx
+++ b/packages/paperclip-runner/devtools/issue-thread/src/EvidencePanel.tsx
@@ -10,7 +10,7 @@ import type {
   CapabilityToolDisposition,
 } from "../../../src/issue-thread/types";
 import type { CapabilityDevtoolsSnapshot } from "../../../src/devtools";
-import { DevtoolsInspector, type CapabilityDevtoolsTab, type EvalInspectorReport } from "./DevtoolsInspector";
+import { DevtoolsInspector, EvalReportInspector, type CapabilityDevtoolsTab, type EvalInspectorReport } from "./DevtoolsInspector";
 import { Icon } from "./Icons";
 import { capabilitySemanticToolDescriptor } from "../../../src/semantic-tools/catalog";
 import {
@@ -114,6 +114,8 @@ export interface EvidencePanelProps {
   snapshot: CapabilityIssueThreadSnapshot;
   devtools?: CapabilityDevtoolsSnapshot | null;
   evalReport?: EvalInspectorReport | null;
+  devtoolsTab: CapabilityDevtoolsTab;
+  onDevtoolsTabChange: (tab: CapabilityDevtoolsTab) => void;
   onForkRevision?: (revision: number) => void;
   layout: "side" | "overlay" | "segment";
   width: number;
@@ -331,11 +333,12 @@ function Section({
 }
 
 export function EvidencePanel(props: EvidencePanelProps) {
-  const [devtoolsTab, setDevtoolsTab] = useState<CapabilityDevtoolsTab>(props.evalReport ? "eval" : "evidence");
   const {
     snapshot,
     devtools,
     evalReport,
+    devtoolsTab,
+    onDevtoolsTabChange,
     onForkRevision = () => undefined,
     layout,
     width,
@@ -392,9 +395,21 @@ export function EvidencePanel(props: EvidencePanelProps) {
       {devtools !== undefined ? (
         <>
           {devtools === null ? (
-            <p className="pit-muted pit-devtools-loading">Loading company state…</p>
+            evalReport ? <section className="pit-devtools">
+              <div className="pit-devtools-tabs" role="tablist" aria-label="Developer tools">
+                {(["eval", "evidence"] as const).map((tab) => <button
+                  key={tab}
+                  type="button"
+                  role="tab"
+                  aria-selected={devtoolsTab === tab}
+                  className="pit-tab"
+                  onClick={() => onDevtoolsTabChange(tab)}
+                ><span className="pit-tab-glyph"><Icon name="evidence" /></span><span>{tab === "eval" ? "Eval" : "Evidence"}</span></button>)}
+              </div>
+              {devtoolsTab === "eval" ? <EvalReportInspector evalReport={evalReport} /> : null}
+            </section> : <p className="pit-muted pit-devtools-loading">Loading company state…</p>
           ) : (
-            <DevtoolsInspector snapshot={devtools} onFork={onForkRevision} tab={devtoolsTab} onTabChange={setDevtoolsTab} evalReport={evalReport} />
+            <DevtoolsInspector snapshot={devtools} onFork={onForkRevision} tab={devtoolsTab} onTabChange={onDevtoolsTabChange} evalReport={evalReport} />
           )}
         </>
       ) : null}
diff --git a/packages/paperclip-runner/devtools/issue-thread/src/evalbook-site.css b/packages/paperclip-runner/devtools/issue-thread/src/evalbook-site.css
new file mode 100644
index 0000000000..cdba55acb8
--- /dev/null
+++ b/packages/paperclip-runner/devtools/issue-thread/src/evalbook-site.css
@@ -0,0 +1,87 @@
+/* Static Evalbook pages share the Runner Lab token/font layer and built asset.
+   Keep every selector scoped so report navigation cannot restyle live chat. */
+.evalbook-site { color-scheme: dark; }
+.evalbook-site main { width: 100%; max-width: 112rem; margin: auto; padding: var(--pit-space-6); }
+.evalbook-site a { color: var(--pit-live); text-underline-offset: var(--pit-space-1); }
+.evalbook-site a:hover { color: var(--pit-foreground); }
+.evalbook-site :is(a, summary, [tabindex]):focus-visible { outline: 2px solid var(--pit-ring); outline-offset: 3px; }
+.evalbook-site .top { display: flex; justify-content: space-between; align-items: center; gap: var(--pit-space-4); padding-bottom: var(--pit-space-4); border-bottom: 1px solid var(--pit-border); }
+.evalbook-site .top > a { color: var(--pit-foreground); font-weight: 700; text-decoration: none; }
+.evalbook-site h1 { margin: var(--pit-space-6) 0 var(--pit-space-3); font-size: var(--pit-text-xl); line-height: var(--pit-leading-tight); overflow-wrap: anywhere; }
+.evalbook-site h2 { margin: var(--pit-space-6) 0 var(--pit-space-3); font-size: var(--pit-text-base); line-height: var(--pit-leading-tight); }
+.evalbook-site p { margin: var(--pit-space-3) 0; }
+.evalbook-site .badge { padding: var(--pit-space-1) var(--pit-space-2); color: var(--pit-live); background: var(--pit-live-surface); border: 1px solid var(--pit-live); border-radius: var(--pit-radius-sm); font-size: var(--pit-text-xs); white-space: nowrap; }
+.evalbook-site :is(.tabs, .pointers, .breadcrumbs) { display: flex; align-items: center; gap: var(--pit-space-4); margin: var(--pit-space-4) 0; overflow-x: auto; }
+.evalbook-site .tabs { border-bottom: 1px solid var(--pit-border); gap: 0; }
+.evalbook-site .tabs a { flex: 0 0 auto; padding: var(--pit-space-3) var(--pit-space-4); color: var(--pit-muted-foreground); text-decoration: none; border-bottom: 2px solid transparent; }
+.evalbook-site .tabs a:hover { background: var(--pit-surface); color: var(--pit-foreground); }
+.evalbook-site .tabs a.active { background: var(--pit-accent-surface); border-color: var(--pit-accent); color: var(--pit-foreground); }
+.evalbook-site .breadcrumbs span { color: var(--pit-muted-foreground); }
+.evalbook-site .spend-summary { display: flex; flex-wrap: wrap; gap: var(--pit-space-6); margin: var(--pit-space-5) 0; }
+.evalbook-site .spend-summary > div { display: flex; flex-direction: column; gap: var(--pit-space-1); }
+.evalbook-site .spend-summary span { color: var(--pit-muted-foreground); font-size: var(--pit-text-xs); }
+.evalbook-site .spend-summary strong { font-size: var(--pit-text-base); font-variant-numeric: tabular-nums; }
+.evalbook-site .lede { color: var(--pit-muted-foreground); margin-bottom: var(--pit-space-5); }
+.evalbook-site :is(.card, .message, .tool, .check) { margin: var(--pit-space-3) 0; padding: var(--pit-space-4); background: var(--pit-surface); border: 1px solid var(--pit-border); border-radius: var(--pit-radius-sm); overflow-wrap: anywhere; }
+.evalbook-site .pass { border-left: 3px solid var(--pit-success); }
+.evalbook-site .fail { border-left: 3px solid var(--pit-danger); }
+.evalbook-site .infra { border-left: 3px solid var(--pit-warning); }
+.evalbook-site .grid { display: grid; grid-template-columns: minmax(0, 1fr) minmax(0, 1.3fr); gap: var(--pit-space-6); }
+.evalbook-site .grid > section { min-width: 0; }
+.evalbook-site :is(.table-shell, .table) { width: 100%; overflow: auto; border: 1px solid var(--pit-border); border-radius: var(--pit-radius-sm); background: var(--pit-surface-sunken); overscroll-behavior-inline: contain; scrollbar-color: var(--pit-border-strong) transparent; }
+.evalbook-site table { width: 100%; border-collapse: separate; border-spacing: 0; font-size: var(--pit-text-xs); }
+.evalbook-site :is(th, td) { padding: var(--pit-space-3); border-bottom: 1px solid var(--pit-border); text-align: left; vertical-align: top; }
+.evalbook-site thead th { background: var(--pit-surface); color: var(--pit-muted-foreground); font-weight: 600; }
+.evalbook-site tbody tr:last-child > :is(th, td) { border-bottom: 0; }
+.evalbook-site tbody tr:hover > :is(th, td) { background: var(--pit-surface-raised); }
+.evalbook-site .matrix { min-width: max(100%, var(--matrix-min-width, 1500px)); }
+.evalbook-site .matrix :is(th, td):not(:first-child) { width: 10rem; text-align: center; }
+.evalbook-site .matrix thead th { position: sticky; top: 0; z-index: 2; }
+.evalbook-site .matrix thead th > div { color: var(--pit-foreground); font-size: var(--pit-text-sm); overflow-wrap: anywhere; }
+.evalbook-site .matrix thead small { display: block; max-width: 11rem; margin: var(--pit-space-1) auto 0; font-size: var(--pit-text-xs); font-weight: 400; overflow-wrap: anywhere; }
+.evalbook-site .matrix th:first-child { position: sticky; left: 0; z-index: 1; width: 18rem; min-width: 14rem; background: var(--pit-surface-sunken); }
+.evalbook-site .matrix thead th:first-child { z-index: 3; background: var(--pit-surface); }
+.evalbook-site .matrix tbody th:first-child a { display: block; color: var(--pit-foreground); font-weight: 500; overflow-wrap: anywhere; text-decoration: none; }
+.evalbook-site .matrix tbody th:first-child a:hover { color: var(--pit-live); text-decoration: underline; }
+.evalbook-site .result { display: flex; align-items: center; justify-content: center; width: 100%; max-width: 10rem; min-height: 2rem; margin-inline: auto; padding: var(--pit-space-1) var(--pit-space-2); border: 1px solid currentColor; border-radius: var(--pit-radius-sm); font-size: var(--pit-text-xs); font-weight: 700; text-decoration: none; }
+.evalbook-site :is(.result-pass, .passed) { background: var(--pit-success-surface); color: var(--pit-success); }
+.evalbook-site :is(.result-fail, .failed) { background: var(--pit-danger-surface); color: var(--pit-danger); }
+.evalbook-site .result-infra { background: var(--pit-warning-surface); color: var(--pit-warning); }
+.evalbook-site :is(.muted, .empty, small, footer) { color: var(--pit-muted-foreground); }
+.evalbook-site .empty { text-align: center; }
+.evalbook-site code { font-family: var(--pit-font-mono); font-size: var(--pit-text-xs); overflow-wrap: anywhere; }
+.evalbook-site pre { max-height: 32rem; padding: var(--pit-space-3); overflow: auto; white-space: pre-wrap; overflow-wrap: anywhere; background: var(--pit-surface-sunken); color: var(--pit-foreground); border: 1px solid var(--pit-border); border-radius: var(--pit-radius-sm); font-family: var(--pit-font-mono); font-size: var(--pit-text-xs); }
+.evalbook-site details { margin: var(--pit-space-4) 0; }
+.evalbook-site summary { cursor: pointer; color: var(--pit-muted-foreground); }
+.evalbook-site .status { display: inline-block; padding: var(--pit-space-1) var(--pit-space-2); border-radius: var(--pit-radius-sm); font-weight: 600; text-transform: uppercase; }
+.evalbook-site small { display: block; margin-top: var(--pit-space-1); }
+.evalbook-site footer { margin-top: var(--pit-space-5); font-size: var(--pit-text-xs); }
+.evalbook-site .trend-group { padding: var(--pit-space-4); border: 1px solid var(--pit-border); border-radius: var(--pit-radius-sm); background: var(--pit-surface-sunken); }
+.evalbook-site .trend-group > summary { color: var(--pit-foreground); font-weight: 600; }
+.evalbook-site .trend-grid { display: grid; grid-template-columns: repeat(2, minmax(0, 1fr)); gap: var(--pit-space-5); }
+.evalbook-site figure { min-width: 0; margin: var(--pit-space-4) 0; }
+.evalbook-site figcaption { color: var(--pit-muted-foreground); font-size: var(--pit-text-xs); }
+.evalbook-site .trend-chart { width: 100%; overflow: visible; }
+.evalbook-site .trend-chart text { fill: var(--pit-muted-foreground); font: var(--pit-text-xs) var(--pit-font-mono); }
+.evalbook-site .trend-axis { fill: none; stroke: var(--pit-border); }
+.evalbook-site .trend-line { fill: none; stroke-width: 2; }
+.evalbook-site :is(.trend-line, .trend-point).pass { stroke: var(--pit-success); }
+.evalbook-site :is(.trend-line, .trend-point).all_attempts { stroke: var(--pit-live); }
+.evalbook-site :is(.trend-line, .trend-point).final_attempts { stroke: var(--pit-accent); stroke-dasharray: 4 3; }
+.evalbook-site .trend-point { fill: var(--pit-surface); stroke-width: 2; }
+.evalbook-site .trend-point:hover { fill: var(--pit-foreground); }
+.evalbook-site .pass-rate { display: block; margin-top: var(--pit-space-2); white-space: nowrap; }
+.evalbook-site .history-table table { min-width: 68rem; }
+.evalbook-site .history-table td:first-child { max-width: 22rem; }
+.evalbook-site .history-table details { margin: var(--pit-space-2) 0; }
+.evalbook-site .history-table li { margin: var(--pit-space-2) 0; }
+.evalbook-site .incomplete { background: var(--pit-warning-surface); color: var(--pit-warning); }
+@media (max-width: 760px) {
+  .evalbook-site main { padding: var(--pit-space-4); }
+  .evalbook-site .grid { grid-template-columns: 1fr; }
+  .evalbook-site .trend-grid { grid-template-columns: 1fr; }
+  .evalbook-site .trend-grid figure { overflow-x: auto; }
+  .evalbook-site .trend-chart { min-width: 30rem; }
+  .evalbook-site .matrix th:first-child { width: 12rem; min-width: 10rem; }
+  .evalbook-site .badge { white-space: normal; text-align: center; }
+}
diff --git a/packages/paperclip-runner/devtools/issue-thread/src/main.tsx b/packages/paperclip-runner/devtools/issue-thread/src/main.tsx
index 0a62fa2ef8..ebe93e307a 100644
--- a/packages/paperclip-runner/devtools/issue-thread/src/main.tsx
+++ b/packages/paperclip-runner/devtools/issue-thread/src/main.tsx
@@ -3,12 +3,25 @@ import { createRoot } from "react-dom/client";
 
 import { App } from "./App";
 import "./issue-thread.css";
+import "./evalbook-site.css";
+
+// Hosted Evalbooks use inert JSON plus the same trusted viewer bundle. No
+// inline executable script or network fetch is needed to load an attempt.
+const reportData = document.getElementById("paperclip-eval-report");
+if (reportData !== null) {
+  window.__PAPERCLIP_EVAL_REPORT__ = JSON.parse(
+    reportData.textContent ?? "null",
+  );
+}
 
 // `?capture=1` freezes animation, caret, and smooth scrolling so the
 // screenshot matrix is byte-stable across runs (contract §10.1).
 const params = new URLSearchParams(window.location.search);
 const hashQuery = window.location.hash.split("?")[1] ?? "";
-if (params.get("capture") === "1" || new URLSearchParams(hashQuery).get("capture") === "1") {
+if (
+  params.get("capture") === "1" ||
+  new URLSearchParams(hashQuery).get("capture") === "1"
+) {
   document.documentElement.dataset.capture = "true";
 }
 
diff --git a/packages/paperclip-runner/docs/images/evalbook-chat/failed.png b/packages/paperclip-runner/docs/images/evalbook-chat/failed.png
new file mode 100644
index 0000000000..21d4be7419
Binary files /dev/null and b/packages/paperclip-runner/docs/images/evalbook-chat/failed.png differ
diff --git a/packages/paperclip-runner/docs/images/evalbook-chat/missing-recording.png b/packages/paperclip-runner/docs/images/evalbook-chat/missing-recording.png
new file mode 100644
index 0000000000..57eba71894
Binary files /dev/null and b/packages/paperclip-runner/docs/images/evalbook-chat/missing-recording.png differ
diff --git a/packages/paperclip-runner/docs/images/evalbook-chat/passed.png b/packages/paperclip-runner/docs/images/evalbook-chat/passed.png
new file mode 100644
index 0000000000..1c28f8f565
Binary files /dev/null and b/packages/paperclip-runner/docs/images/evalbook-chat/passed.png differ
diff --git a/packages/paperclip-runner/docs/runner-protocol-live-evals.md b/packages/paperclip-runner/docs/runner-protocol-live-evals.md
index 809ef86ebd..fe9ee06f6e 100644
--- a/packages/paperclip-runner/docs/runner-protocol-live-evals.md
+++ b/packages/paperclip-runner/docs/runner-protocol-live-evals.md
@@ -1,5 +1,84 @@
 # Direct live Runner protocol evals
 
+## One Evalbook presentation
+
+Every new report uses the canonical Evalbook grid and the existing Runner Lab
+chat viewer for attempt drill-downs. There is no plain-HTML attempt fallback.
+The grid, Latest, test-design, inventory and server-gate pages load the same
+built stylesheet and fonts as the chat viewer. The long-term S3 history index
+references that stylesheet inside an immutable campaign, so every page keeps
+the same dark theme. Static site styles live in
+`devtools/issue-thread/src/evalbook-site.css`, scoped to `.evalbook-site`;
+colors and typography come from the Runner Lab token layer.
+Missing recordings show a notice in the same viewer; missing viewer builds
+fail generation. Build with
+`pnpm --filter @paperclipai/paperclip-runner build:issue-thread` and provide
+`--viewer-root` or `PAPERCLIP_EVAL_VIEWER_ROOT` to the canonical Python renderer.
+
+The Actions artifact contains full evidence. S3 uses the same viewer with a
+closed public DTO: only isolated mock-run conversation text, scrubbed private
+references, named tool outcomes, and checks. Tool arguments/results, reasoning,
+provider identities, and company snapshots stay private. The public notice
+explains these redactions. An unverified isolation boundary yields no public
+conversation, not a guessed reconstruction.
+
+Public attempts use inert JSON and one shared viewer asset directory. The
+publisher verifies each shell and asset against the exact same-run viewer build,
+checks the public payload contract and local links, and rejects other scripts.
+The CSP prohibits network calls, forms and external resources. Supply
+`PAPERCLIP_RUNNER_PROTOCOL_EVAL_VIEWER_DIR` to the publisher. The workflow sends
+a viewer-only artifact to that job; raw attempts and provider secrets stay out.
+After publication succeeds, the publishing job writes **Open this run's
+Evalbook** and **All eval runs** links to the Actions summary. Its deployment
+URL also points to the exact immutable report, not to the downloadable ZIP.
+Failed publication does not advertise a successful deployment.
+
+Before uploading, the report job runs the actual built application in Chromium
+against representative passing, failing and missing-recording pages in both
+reports. It checks initial rendering, tool expansion, read-only controls,
+navigation, reload, a narrow viewport and the public no-API-request boundary.
+In full-evidence reports, a tool's **View in Evidence** link selects the Evidence
+tab and highlights its record, including when reopening that same record after
+switching tabs. The browser check exercises this cross-link too.
+Run the same check locally with
+`node packages/paperclip-runner/scripts/verify-runner-evalbook-viewer.mjs --report-root /path/to/report`.
+Add `--screenshots /path/to/proof` for visual evidence. Public screenshots are
+retained in the aggregate Actions artifact, not added to the public report's
+closed file allowlist.
+
+These screenshots are generated acceptance-test evidence from the scrubbed
+completed campaign, not a separate report design:
+
+![Passing chat replay with expanded tool evidence](images/evalbook-chat/passed.png)
+![Failed chat replay with visible assertions](images/evalbook-chat/failed.png)
+![Missing recording shown in the same viewer](images/evalbook-chat/missing-recording.png)
+
+### Refresh a completed report without calling models
+
+Download the aggregate Actions artifact, then:
+
+```sh
+node packages/paperclip-runner/scripts/refresh-runner-protocol-eval-report.mjs \
+  --source /path/to/downloaded-aggregate \
+  --evals-root /path/to/paperclip-evals \
+  --viewer-root packages/paperclip-runner/dist-issue-thread \
+  --output /path/to/new-refresh-directory \
+  --revision chat-v1
+```
+
+Publish the returned `reportRoot` with the normal history publisher. The new ID
+is `gha-RUN-ATTEMPT-report-chat-v1`. Original reports remain immutable; history
+adds a labeled refresh and retains the source campaign, original measurement
+timestamp, renderer digest, and `providerCalls: 0`. Scores and evaluated source
+revisions do not change. This is not a new model qualification run. Future live
+runs create chat reports automatically.
+Refreshes are ordered by their render time in the history list, but keep the
+original measurement timestamp and never replace the latest or latest-green
+qualification identities. The HTML history links each measurement to its newest
+presentation, while retaining every original bundle and listing refreshes separately.
+Refreshes also recover retry-inclusive estimated and provider-list costs from the
+retained attempt records. They never add another model-cost measurement.
+
 This is the provider-backed, one-turn protocol qualification layer in
 `paperclipai/paperclip-evals/evals/paperclip-runner`. It is intentionally
 separate from both the browser full-stack model E2E and the stress-derived
@@ -149,11 +228,11 @@ read-only Runner issue-thread attempt pages, and raw immutable run records.
 
 Public publishing uses a separate projection and a separate trusted OIDC job.
 The projection retains model/config identity, status, usage totals, and check
-outcomes but removes provider session identifiers, transcripts, semantic-tool
+outcomes and scrubbed mock conversation, but removes provider session identifiers, semantic-tool
 payloads, state revisions, traces, remote profile identities, and raw failure
 text. The same Evalbook `report` command renders that projection, so the public
-grid and test pages have the standard Evalbook layout. The publisher rejects
-scripts, remote resources, symlinks, unknown paths, broken links, raw session
+grid, test pages and chat viewer have the standard Evalbook layout. The publisher rejects
+untrusted scripts, remote resources, symlinks, unknown paths, broken links, raw session
 fields, and credential-shaped values.
 
 S3 publication is additive:
@@ -178,9 +257,27 @@ runner-protocol-evals/
 Campaign files use immutable cache headers and a digest manifest. Reusing a
 campaign ID with different bytes fails closed. Only the root history and
 pointer files are mutable, and the publisher never deletes objects. The root
-history retains at most 200 records, reserving one record for the latest green
-campaign when it would otherwise fall outside that window so its pointer stays
-valid.
+history retains **all** run records; it no longer drops entries after 200 campaigns.
+
+The history index includes:
+
+- Pass-rate and cost timelines, grouped by identical cell/model/driver membership
+  and eval-suite SHA. Different suites and subsets cannot silently share a baseline.
+- Regression and recovery lists against the previous matching run, linking to the
+  affected tests. Infrastructure failures stay distinct from behavior failures.
+- Estimated cost and provider-reported list cost, shown separately, never added.
+  New campaigns include all retained attempts (including retries). Backfilled old
+  campaigns with only final-cell usage are labeled **historical final attempts only**.
+  Missing usage is unknown, not zero; partial totals use `≥` and display coverage.
+- Exact Paperclip and eval-suite commit links (full SHA on hover), the source ref,
+  and the GitHub Actions run. These identify the code **evaluated**, not merely
+  the commit used to render an old report.
+- A separate report-refresh list, excluded from trend points and model-spend totals.
+
+`history.json` stores a versioned, derived `analytics` projection separately from
+immutable campaign records. The publisher backfills missing analytics from each
+original `campaign.json`; a refresh may enrich costs using retained raw attempts
+only when its source metadata and scores still match the original record.
 
 The publishing job uses dedicated `RUNNER_PROTOCOL_EVAL_HISTORY_*` variables
 when present and falls back to the existing Runner E2E history role, region,
diff --git a/packages/paperclip-runner/package.json b/packages/paperclip-runner/package.json
index a133b72024..030fc51505 100644
--- a/packages/paperclip-runner/package.json
+++ b/packages/paperclip-runner/package.json
@@ -115,7 +115,7 @@
     "test:capability-evals": "vitest run src/conformance/capability-eval-suite.test.ts",
     "test:eval-slice": "pnpm run ensure:eval-build-deps && vitest run src/eval",
     "test:runner-workflow-evals": "pnpm run ensure:eval-build-deps && node --test scripts/render-runner-workflow-evalbook.test.mjs && vitest run src/eval/workflow-evals.test.ts src/eval/live-workflow-executor.test.ts",
-    "test:runner-protocol-eval-publish": "node --test scripts/runner-protocol-eval-campaign.test.mjs scripts/publish-runner-protocol-eval-history.test.mjs scripts/runner-protocol-eval-workflow-security.test.mjs",
+    "test:runner-protocol-eval-publish": "node --test scripts/runner-protocol-eval-campaign.test.mjs scripts/publish-runner-protocol-eval-history.test.mjs scripts/runner-protocol-eval-metrics.test.mjs scripts/runner-protocol-eval-workflow-security.test.mjs scripts/public-eval-chat.test.mjs",
     "check:runner-workflow-traceability": "pnpm run build:typescript && node scripts/check-runner-workflow-traceability.mjs",
     "report:capability-evals": "pnpm run build:typescript && node scripts/run-capability-eval-suite.mjs",
     "report:capability-live-evals": "pnpm run build:typescript && cargo build --manifest-path runner/Cargo.toml --locked -p paperclip-runner-core --bin paperclip-runnerd && node scripts/run-capability-live-eval-matrix.mjs",
diff --git a/packages/paperclip-runner/scripts/public-eval-chat.mjs b/packages/paperclip-runner/scripts/public-eval-chat.mjs
new file mode 100644
index 0000000000..d20f998020
--- /dev/null
+++ b/packages/paperclip-runner/scripts/public-eval-chat.mjs
@@ -0,0 +1,217 @@
+// Public replay is a new DTO, never a recursive copy of a provider artifact.
+export const PUBLIC_CHAT_SCHEMA =
+  "paperclip.runner-protocol-eval.public-chat/v1";
+export const PUBLIC_CHAT_NOTICE =
+  "Public replay of an isolated mock eval. Conversation text is scrubbed; provider identities, tool payloads, traces, and company-state snapshots are withheld. Full evidence remains in the access-controlled Actions artifact.";
+
+export const SECRET_TEXT = [
+  /\b(?:AKIA|ASIA)[0-9A-Z]{16}\b/gu,
+  /\bsk-[A-Za-z0-9_-]{16,}\b/gu,
+  /\b(?:gh[pousr]_|github_pat_)[A-Za-z0-9_]{16,}\b/gu,
+  /\bBearer\s+[A-Za-z0-9._~+\/-]{8,}=*/giu,
+  /-----BEGIN [^-]*PRIVATE KEY-----[\s\S]*?-----END [^-]*PRIVATE KEY-----/gu,
+  /\beyJ[A-Za-z0-9_-]+\.[A-Za-z0-9_-]+\.[A-Za-z0-9_-]+\b/gu,
+  /\b(?:https?|file|s3):\/\/[^\s<>"')]+/giu,
+  /\barn:aws[^\s<>"')]+/gu,
+  /(?:\/(?:Users|home|tmp|private|var)\/|[A-Z]:\\)[^\s<>"')]+/gu,
+  /\b(?:api[_-]?key|access[_-]?token|secret|password|authorization|cookie)\s*[=:]\s*[^\s,;]+/giu,
+];
+
+export function publicText(value, privateValues = []) {
+  let text = typeof value === "string" ? value : "";
+  for (const secret of privateValues) {
+    if (typeof secret === "string" && secret.length >= 8)
+      text = text.replaceAll(secret, "[redacted]");
+  }
+  for (const pattern of SECRET_TEXT) text = text.replace(pattern, "[redacted]");
+  return text.length > 40_000 ? `${text.slice(0, 40_000)}\n[truncated]` : text;
+}
+
+function privateIdentities(value, found = new Set()) {
+  if (value && typeof value === "object") {
+    for (const [key, child] of Object.entries(value)) {
+      if (
+        /(?:session|profile|account|runtime|endpoint|memory|agentversion).*id$|arn$|token$|secret$|password$/i.test(
+          key,
+        ) &&
+        typeof child === "string"
+      )
+        found.add(child);
+      else if (child && typeof child === "object")
+        privateIdentities(child, found);
+    }
+  }
+  return [...found];
+}
+
+function timestamp(value) {
+  return typeof value === "string" && /^\d{4}-\d\d-\d\dT[\d:.]+Z$/.test(value)
+    ? value
+    : "1970-01-01T00:00:00.000Z";
+}
+
+function operation(value) {
+  return typeof value === "string" && /^[a-z][a-z_]{0,79}$/.test(value)
+    ? value
+    : "unknown_operation";
+}
+
+export function publicChatView(artifact, evalCase) {
+  const privateValues = privateIdentities(artifact);
+  const scrub = (value) => publicText(value, privateValues);
+  const network = artifact.snapshot?.networkEvidence;
+  // Only the dedicated mock eval boundary can publish recorded conversation.
+  // Early infrastructure failures still receive a viewer with an honest notice.
+  const isolated =
+    network?.realPaperclipRequests === 0 &&
+    Array.isArray(network?.childPaperclipEnvironmentKeys) &&
+    network.childPaperclipEnvironmentKeys.length === 0;
+  const source =
+    isolated &&
+    artifact.issueThread?.schema === "paperclip.capability.issue-thread-view.v1"
+      ? artifact.issueThread
+      : null;
+  const evidence = Object.fromEntries(
+    [
+      "tools",
+      "calls",
+      "authorization",
+      "control_plane",
+      "runner",
+      "state",
+      "traceability",
+      "parity",
+    ].map((key) => [key, []]),
+  );
+  const turns = (source?.turns ?? []).map((turn, turnIndex) => {
+    const turnId = `public-turn-${turnIndex + 1}`;
+    const items = [];
+    for (const item of turn.items ?? []) {
+      const base = {
+        id: `public-item-${turnIndex + 1}-${items.length + 1}`,
+        at: timestamp(item.at),
+      };
+      if (
+        ["user_message", "agent_message", "durable_comment"].includes(item.kind)
+      ) {
+        items.push({
+          ...base,
+          kind: item.kind === "user_message" ? "user_message" : "agent_message",
+          author: item.kind === "user_message" ? "You (eval prompt)" : "Agent",
+          body: scrub(item.body),
+          streaming: false,
+        });
+      } else if (item.kind === "tool_activity") {
+        const operationId = operation(item.operationId);
+        const status = ["ok", "denied", "running"].includes(item.status)
+          ? item.status
+          : "running";
+        const result = {
+          outcome: status,
+          detail: "Tool payload withheld from public replay.",
+        };
+        const recordId = `public-call-${turnIndex + 1}-${items.length + 1}`;
+        items.push({
+          ...base,
+          kind: "tool_activity",
+          operationId,
+          status,
+          summary: `${operationId}: ${status}`,
+          input: { detail: "Arguments withheld from public replay." },
+          result,
+          evidenceRef: { section: "calls", recordId },
+        });
+        if (status !== "running")
+          evidence.calls.push({
+            id: recordId,
+            turnId,
+            operationId,
+            version: 1,
+            providerRequest: operationId,
+            dispatchedCommand: operationId,
+            outcome: status,
+            result,
+            redactions: ["arguments", "result payload", "provider identities"],
+            threadAnchorId: base.id,
+          });
+      }
+      // Provider activity, reasoning, raw events, file refs and unrecognized
+      // future item kinds are deliberately not part of the public contract.
+    }
+    return {
+      id: turnId,
+      ordinal: turnIndex + 1,
+      mode: "replay",
+      toolCallCount: items.filter((item) => item.kind === "tool_activity")
+        .length,
+      at: timestamp(turn.at),
+      stoppedByUser: turn.stoppedByUser === true,
+      items,
+    };
+  });
+  if (!turns.some((turn) => turn.items.length > 0)) {
+    turns.length = 0;
+    turns.push({
+      id: "public-turn-1",
+      ordinal: 1,
+      mode: "replay",
+      toolCallCount: 0,
+      at: timestamp(artifact.snapshot?.createdAt),
+      stoppedByUser: false,
+      items: [
+        {
+          id: "public-notice",
+          at: timestamp(artifact.snapshot?.createdAt),
+          kind: "system_notice",
+          glyph: "–",
+          text: "No publishable conversation was recorded for this attempt. See the checks and the access-controlled artifact for diagnostics.",
+          evidenceRef: { section: "runner", recordId: "public-notice" },
+        },
+      ],
+    });
+  }
+  return {
+    schema: "paperclip.capability.issue-thread-view.v1",
+    sessionId: "public-report",
+    mode: "replay",
+    identity: {
+      agentLabel: "Recorded agent",
+      runnerLabel: "Recorded runner",
+      runnerAttached: false,
+      controlPlaneLabel: "Mock Paperclip",
+      controlPlaneTooltip: PUBLIC_CHAT_NOTICE,
+      replaySource: "live",
+    },
+    issue: {
+      identifier: "EVAL",
+      title: scrub(evalCase.title || evalCase.id),
+      status: [
+        "backlog",
+        "todo",
+        "in_progress",
+        "in_review",
+        "done",
+        "blocked",
+        "cancelled",
+      ].includes(source?.issue?.status)
+        ? source.issue.status
+        : "in_review",
+      priority: "medium",
+      assignee: null,
+      runState: "Read-only public replay",
+      scenarioId: evalCase.id,
+      fixtureProfile: evalCase.id,
+    },
+    turns,
+    composer: {
+      state: "disabled",
+      helper: null,
+      reason: "Read-only eval report",
+      pendingInteractionId: null,
+    },
+    evidence,
+    connection: { state: "closed", attempt: 0 },
+    replay: null,
+    renderedAt: timestamp(source?.renderedAt || artifact.snapshot?.createdAt),
+  };
+}
diff --git a/packages/paperclip-runner/scripts/public-eval-chat.test.mjs b/packages/paperclip-runner/scripts/public-eval-chat.test.mjs
new file mode 100644
index 0000000000..96f8c02fbc
--- /dev/null
+++ b/packages/paperclip-runner/scripts/public-eval-chat.test.mjs
@@ -0,0 +1,273 @@
+import assert from "node:assert/strict";
+import { mkdtemp, mkdir, writeFile, cp, rm, symlink } from "node:fs/promises";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import test from "node:test";
+import {
+  publicChatView,
+  publicText,
+  PUBLIC_CHAT_SCHEMA,
+  PUBLIC_CHAT_NOTICE,
+} from "./public-eval-chat.mjs";
+import {
+  publicViewerShell,
+  validatePublicChatPayload,
+  trustedViewerFiles,
+} from "./public-eval-viewer.mjs";
+import { validatePublicProtocolEvalReport } from "./publish-runner-protocol-eval-history.mjs";
+
+function artifact() {
+  return {
+    providerSessionId: "private-session-canary",
+    snapshot: {
+      networkEvidence: {
+        realPaperclipRequests: 0,
+        childPaperclipEnvironmentKeys: [],
+      },
+    },
+    issueThread: {
+      schema: "paperclip.capability.issue-thread-view.v1",
+      issue: { status: "blocked" },
+      turns: [
+        {
+          items: [
+            { kind: "user_message", body: "Please block this task." },
+            {
+              kind: "agent_message",
+              body: "Blocked. private-session-canary https://private.example/path",
+              privateField: "private-field-canary",
+            },
+            {
+              kind: "tool_activity",
+              operationId: "block_task",
+              status: "ok",
+              input: { secret: "argument-canary" },
+              result: { token: "result-canary" },
+            },
+            { kind: "thinking", body: "reasoning-canary" },
+            { kind: "future_kind", body: "future-canary" },
+          ],
+        },
+      ],
+    },
+  };
+}
+
+function payload() {
+  return {
+    attemptId: "attempt-01",
+    caseId: "block-task",
+    disposition: "pass",
+    passed: true,
+    checks: [],
+    publication: { schema: PUBLIC_CHAT_SCHEMA, notice: PUBLIC_CHAT_NOTICE },
+    view: publicChatView(artifact(), { id: "block-task" }),
+    devtools: null,
+    navigation: { suiteHref: "../../index.html", previous: null, next: null },
+    run: {
+      model: "test",
+      provider: "test",
+      sessionId: "public-report",
+      effectiveModelHistory: [],
+      managedProfile: null,
+      acpxProfile: null,
+      usage: null,
+    },
+  };
+}
+
+test("projects only isolated recorded messages and bounded tool facts", () => {
+  const view = publicChatView(artifact(), { id: "block-task" });
+  assert.equal(view.issue.status, "blocked");
+  assert.deepEqual(
+    view.turns[0].items.map((item) => item.kind),
+    ["user_message", "agent_message", "tool_activity"],
+  );
+  assert.match(view.turns[0].items[1].body, /Blocked/);
+  assert.doesNotMatch(JSON.stringify(view), /canary|private\.example/);
+  assert.deepEqual(view.turns[0].items[2].input, {
+    detail: "Arguments withheld from public replay.",
+  });
+  validatePublicChatPayload(payload());
+  for (const networkEvidence of [
+    undefined,
+    { realPaperclipRequests: 1, childPaperclipEnvironmentKeys: [] },
+    {
+      realPaperclipRequests: 0,
+      childPaperclipEnvironmentKeys: ["PAPERCLIP_API_KEY"],
+    },
+  ]) {
+    const source = artifact();
+    source.snapshot.networkEvidence = networkEvidence;
+    const unavailable = publicChatView(source, { id: "block-task" });
+    assert.equal(unavailable.turns[0].items[0].kind, "system_notice");
+    assert.doesNotMatch(JSON.stringify(unavailable), /Please block|Blocked\./);
+  }
+});
+
+test("scrubs credentials and private references before truncating text", () => {
+  for (const secret of [
+    "sk-" + "a".repeat(32),
+    "ghp_" + "b".repeat(32),
+    "Bearer abcdef123456",
+    "password=secret-canary",
+    "/Users/someone/private.txt",
+    "arn:aws:service:region:account:resource",
+    "-----BEGIN PRIVATE KEY-----\n" +
+      "x".repeat(41_000) +
+      "\n-----END PRIVATE KEY-----",
+  ]) {
+    assert.equal(publicText(secret), "[redacted]");
+  }
+  assert.match(publicText("a".repeat(41_000)), /\[truncated\]$/);
+});
+
+test("turns containing only withheld items still show the missing-recording notice", () => {
+  const source = artifact();
+  source.issueThread.turns = [
+    { items: [{ kind: "thinking", body: "private-reasoning" }] },
+    { items: [] },
+  ];
+  const view = publicChatView(source, { id: "missing" });
+  assert.equal(view.turns.length, 1);
+  assert.equal(view.turns[0].items[0].kind, "system_notice");
+  assert.match(view.turns[0].items[0].text, /No publishable conversation/);
+});
+
+test("trusted viewer rejects index and assets symlinks outside its root", async () => {
+  const root = await mkdtemp(join(tmpdir(), "eval-viewer-symlinks-"));
+  try {
+    const viewer = join(root, "viewer");
+    const outside = join(root, "outside");
+    await mkdir(viewer);
+    await mkdir(outside);
+    await writeFile(
+      join(outside, "index.html"),
+      '<script type="module"></script>',
+    );
+    await mkdir(join(outside, "assets"));
+    await writeFile(join(outside, "assets/app.js"), "// outside canary");
+    await symlink(join(outside, "index.html"), join(viewer, "index.html"));
+    await symlink(join(outside, "assets"), join(viewer, "assets"));
+    await assert.rejects(trustedViewerFiles(viewer), /symlinks/);
+    await rm(join(viewer, "index.html"));
+    await writeFile(
+      join(viewer, "index.html"),
+      '<script type="module"></script>',
+    );
+    await assert.rejects(trustedViewerFiles(viewer), /symlinks/);
+  } finally {
+    await rm(root, { recursive: true, force: true });
+  }
+});
+
+test("fails closed on unknown fields, raw tools, private evidence and identities", () => {
+  for (const mutate of [
+    (p) => {
+      p.view.turns[0].items[0].extra = "unprojected";
+    },
+    (p) => {
+      p.view.turns[0].items[2].input = { password: "oops" };
+    },
+    (p) => {
+      p.view.evidence.calls[0].result.detail = "raw-result";
+    },
+    (p) => {
+      p.view.evidence.state.push({ secret: "raw-state" });
+    },
+    (p) => {
+      p.run.providerSessionId = "private-session";
+    },
+    (p) => {
+      p.view.turns[0].items[1].body = "sk-" + "x".repeat(30);
+    },
+    (p) => {
+      p.devtools = {};
+    },
+    (p) => {
+      p.view.composer.state = "ready";
+    },
+  ]) {
+    const value = payload();
+    mutate(value);
+    assert.throws(() => validatePublicChatPayload(value));
+  }
+});
+
+test("publisher permits only the exact trusted shell/assets and valid local navigation", async () => {
+  const root = await mkdtemp(join(tmpdir(), "eval-chat-contract-"));
+  try {
+    const viewer = join(root, "trusted");
+    const report = join(root, "report");
+    await mkdir(join(viewer, "assets"), { recursive: true });
+    await mkdir(join(report, "attempts/attempt-01"), { recursive: true });
+    const index =
+      '<!doctype html><html><head><script type="module" src="./assets/app.js"></script><link rel="stylesheet" href="./assets/app.css"></head><body><div id="root"></div></body></html>';
+    await writeFile(join(viewer, "index.html"), index);
+    await writeFile(join(viewer, "assets/app.js"), "// trusted build");
+    await writeFile(join(viewer, "assets/app.css"), ":root {}");
+    await cp(join(viewer, "assets"), join(report, "viewer/assets"), {
+      recursive: true,
+    });
+    await writeFile(
+      join(report, "index.html"),
+      '<a href="attempts/attempt-01/index.html">PASS</a>',
+    );
+    await writeFile(
+      join(report, "campaign.json"),
+      JSON.stringify({
+        schema: "paperclip.runner-protocol-eval.campaign/v1",
+        campaignId: "gha-42-1",
+      }),
+    );
+    const page = join(report, "attempts/attempt-01/index.html");
+    const writePayload = async (value) =>
+      writeFile(
+        page,
+        publicViewerShell(
+          index,
+          JSON.stringify(value).replaceAll("<", "\\u003c"),
+        ),
+      );
+    await writePayload(payload());
+    await validatePublicProtocolEvalReport(report, { viewerRoot: viewer });
+    await assert.rejects(validatePublicProtocolEvalReport(report));
+    await writeFile(
+      join(report, "viewer/assets/app.js"),
+      "// substituted build",
+    );
+    await assert.rejects(
+      validatePublicProtocolEvalReport(report, { viewerRoot: viewer }),
+      /trusted/,
+    );
+    await writeFile(join(report, "viewer/assets/app.js"), "// trusted build");
+    await writeFile(
+      page,
+      publicViewerShell(index, JSON.stringify(payload())) +
+        "<script>alert(1)</script>",
+    );
+    await assert.rejects(
+      validatePublicProtocolEvalReport(report, { viewerRoot: viewer }),
+      /trusted shell/,
+    );
+    const escaped = payload();
+    escaped.view.turns[0].items[0].body =
+      '</script><script>alert("not executable")</script>';
+    await writePayload(escaped);
+    await validatePublicProtocolEvalReport(report, { viewerRoot: viewer });
+    const broken = payload();
+    broken.navigation.next = {
+      label: "Next attempt",
+      href: "../missing/index.html",
+    };
+    await writePayload(broken);
+    await assert.rejects(
+      validatePublicProtocolEvalReport(report, { viewerRoot: viewer }),
+      /link|reference/i,
+    );
+    await symlink(viewer, join(root, "symlink"));
+    await assert.rejects(trustedViewerFiles(join(root, "symlink")));
+  } finally {
+    await rm(root, { recursive: true, force: true });
+  }
+});
diff --git a/packages/paperclip-runner/scripts/public-eval-viewer.mjs b/packages/paperclip-runner/scripts/public-eval-viewer.mjs
new file mode 100644
index 0000000000..702f69862d
--- /dev/null
+++ b/packages/paperclip-runner/scripts/public-eval-viewer.mjs
@@ -0,0 +1,234 @@
+import { readFile, readdir, lstat } from "node:fs/promises";
+import { join } from "node:path";
+import { PUBLIC_CHAT_SCHEMA, SECRET_TEXT } from "./public-eval-chat.mjs";
+
+export const PUBLIC_VIEWER_CSP =
+  "default-src 'none'; script-src 'self'; style-src 'self' 'unsafe-inline'; font-src 'self'; img-src 'none'; connect-src 'none'; form-action 'none'; base-uri 'none'";
+export const PUBLIC_VIEWER_DATA =
+  /<script type="application\/json" id="paperclip-eval-report">([^<]*)<\/script>/u;
+const ASSET = /^[A-Za-z0-9][A-Za-z0-9._-]*\.(?:js|css|woff2)$/;
+
+export function publicViewerShell(index, encodedPayload) {
+  return index
+    .replaceAll('"./assets/', '"../../viewer/assets/')
+    .replace(
+      "<head>",
+      `<head>\n    <meta http-equiv="Content-Security-Policy" content="${PUBLIC_VIEWER_CSP}">`,
+    )
+    .replace(
+      '<script type="module"',
+      `<script type="application/json" id="paperclip-eval-report">${encodedPayload}</script>\n    <script type="module"`,
+    );
+}
+
+export async function trustedViewerFiles(viewerRoot) {
+  const rootStat = viewerRoot ? await lstat(viewerRoot) : null;
+  if (!rootStat || rootStat.isSymbolicLink() || !rootStat.isDirectory())
+    throw new Error(
+      "A trusted viewer build is required for public chat reports",
+    );
+  const indexStat = await lstat(join(viewerRoot, "index.html"));
+  const assetsStat = await lstat(join(viewerRoot, "assets"));
+  if (
+    indexStat.isSymbolicLink() ||
+    !indexStat.isFile() ||
+    assetsStat.isSymbolicLink() ||
+    !assetsStat.isDirectory()
+  )
+    throw new Error("Trusted viewer must not use symlinks");
+  const index = await readFile(join(viewerRoot, "index.html"), "utf8");
+  const files = new Map();
+  for (const entry of await readdir(join(viewerRoot, "assets"), {
+    withFileTypes: true,
+  })) {
+    if (!entry.isFile() || entry.isSymbolicLink() || !ASSET.test(entry.name))
+      throw new Error("Unexpected trusted viewer asset");
+    files.set(
+      `viewer/assets/${entry.name}`,
+      await readFile(join(viewerRoot, "assets", entry.name)),
+    );
+  }
+  if (
+    ![...files.keys()].some((name) => name.endsWith(".js")) ||
+    !index.includes('<script type="module"')
+  )
+    throw new Error("Incomplete trusted viewer build");
+  return { index, files };
+}
+
+export function validatePublicChatPayload(payload) {
+  if (
+    payload?.publication?.schema !== PUBLIC_CHAT_SCHEMA ||
+    payload.view?.sessionId !== "public-report" ||
+    payload.view?.composer?.state !== "disabled" ||
+    payload.view?.connection?.state !== "closed" ||
+    payload.devtools !== null
+  )
+    throw new Error(
+      "Public attempt must contain the read-only public chat projection",
+    );
+  const allowed = new Set([
+    "attemptId",
+    "caseId",
+    "disposition",
+    "passed",
+    "checks",
+    "view",
+    "devtools",
+    "navigation",
+    "run",
+    "publication",
+  ]);
+  if (Object.keys(payload).some((key) => !allowed.has(key)))
+    throw new Error("Unknown public chat payload field");
+  const fields = (value, names) => {
+    if (
+      !value ||
+      typeof value !== "object" ||
+      Array.isArray(value) ||
+      Object.keys(value).some((key) => !names.split(" ").includes(key))
+    )
+      throw new Error("Unknown public chat projection field");
+  };
+  fields(payload.publication, "schema notice");
+  fields(payload.navigation, "suiteHref previous next");
+  for (const link of [payload.navigation.previous, payload.navigation.next])
+    if (link !== null) fields(link, "label href");
+  fields(
+    payload.run,
+    "model provider driver providerVersion runnerProvider acpxAgent acpxProfile requestedModel effectiveModelHistory configuration sessionId providerSessionId agentVersion managedProfile retainedSession retainedSessionStatus fixtureDigest runnerPackageDigest runnerdDigest startedAt finishedAt durationMs runnerBuild initialRevision finalRevision usage",
+  );
+  if (
+    payload.run.effectiveModelHistory?.length ||
+    payload.run.managedProfile != null ||
+    payload.run.acpxProfile != null
+  )
+    throw new Error("Public replay contains private provider metadata");
+  if (payload.run.usage !== null)
+    fields(
+      payload.run.usage,
+      "agentTurns providerRequests inputTokens outputTokens cachedInputTokens reasoningTokens providerReportedCostNanodollars estimatedCostNanodollars pricingVersion",
+    );
+  fields(
+    payload.view,
+    "schema sessionId mode identity issue turns composer evidence connection replay renderedAt",
+  );
+  fields(
+    payload.view.identity,
+    "agentLabel runnerLabel runnerAttached controlPlaneLabel controlPlaneTooltip replaySource",
+  );
+  fields(
+    payload.view.issue,
+    "identifier title status priority assignee runState scenarioId fixtureProfile",
+  );
+  fields(payload.view.composer, "state helper reason pendingInteractionId");
+  fields(payload.view.connection, "state attempt");
+  fields(
+    payload.view.evidence,
+    "tools calls authorization control_plane runner state traceability parity",
+  );
+  for (const check of payload.checks) {
+    fields(
+      check,
+      "id kind passed detail evidenceRefs title description definition anchor",
+    );
+    fields(check.definition, "id kind");
+    fields(check.anchor, "kind id");
+    if (check.evidenceRefs.length)
+      throw new Error("Public replay contains raw evidence references");
+  }
+  const visit = (value, key = "") => {
+    if (typeof value === "string") {
+      if (
+        /(?:sessionId|providerSessionId)$/i.test(key) &&
+        !["public-report", "unknown", "redacted"].includes(value)
+      )
+        throw new Error("Public replay contains a private session identity");
+      for (const pattern of SECRET_TEXT) {
+        pattern.lastIndex = 0;
+        if (pattern.test(value))
+          throw new Error(
+            "Public replay contains credential or private reference material",
+          );
+      }
+    } else if (value && typeof value === "object") {
+      for (const [name, child] of Object.entries(value)) {
+        if (
+          /^(?:managedProfile|acpxProfile|providerTrace|mockState|stateHistory|trace|environment|env|apiKey|accessToken|password|secret)$/i.test(
+            name,
+          ) &&
+          child != null
+        )
+          throw new Error("Public replay contains a private field");
+        visit(child, name);
+      }
+    }
+  };
+  visit(payload);
+  for (const section of [
+    "tools",
+    "authorization",
+    "control_plane",
+    "runner",
+    "state",
+    "traceability",
+    "parity",
+  ]) {
+    if (
+      !Array.isArray(payload.view.evidence?.[section]) ||
+      payload.view.evidence[section].length
+    )
+      throw new Error("Public replay contains unprojected evidence");
+  }
+  for (const call of payload.view.evidence.calls) {
+    fields(
+      call,
+      "id turnId operationId version providerRequest dispatchedCommand outcome result redactions threadAnchorId",
+    );
+    fields(call.result, "outcome detail");
+    if (call.result.detail !== "Tool payload withheld from public replay.")
+      throw new Error("Public replay contains raw call evidence");
+  }
+  for (const turn of payload.view.turns ?? []) {
+    fields(turn, "id ordinal mode toolCallCount at stoppedByUser items");
+    for (const item of turn.items ?? []) {
+      if (
+        ![
+          "user_message",
+          "agent_message",
+          "tool_activity",
+          "system_notice",
+        ].includes(item.kind)
+      )
+        throw new Error("Public replay contains an unprojected item");
+      const shapes = {
+        user_message: "kind id at author body streaming",
+        agent_message: "kind id at author body streaming",
+        tool_activity:
+          "kind id at operationId status summary input result evidenceRef",
+        system_notice: "kind id at glyph text evidenceRef",
+      };
+      fields(item, shapes[item.kind]);
+      if (item.evidenceRef) fields(item.evidenceRef, "section recordId");
+      if (
+        item.kind === "tool_activity" &&
+        (JSON.stringify(item.input) !==
+          JSON.stringify({
+            detail: "Arguments withheld from public replay.",
+          }) ||
+          Object.keys(item.result).sort().join(",") !== "detail,outcome" ||
+          item.result.detail !== "Tool payload withheld from public replay.")
+      )
+        throw new Error("Public replay contains a raw tool payload");
+    }
+  }
+}
+
+export function validatePublicViewerPage(content, trustedIndex) {
+  const match = content.match(PUBLIC_VIEWER_DATA);
+  if (!match || publicViewerShell(trustedIndex, match[1]) !== content)
+    throw new Error("Public viewer page differs from the trusted shell");
+  const payload = JSON.parse(match[1]);
+  validatePublicChatPayload(payload);
+  return payload;
+}
diff --git a/packages/paperclip-runner/scripts/publish-runner-protocol-eval-history.mjs b/packages/paperclip-runner/scripts/publish-runner-protocol-eval-history.mjs
index b014d76686..15acc1036c 100644
--- a/packages/paperclip-runner/scripts/publish-runner-protocol-eval-history.mjs
+++ b/packages/paperclip-runner/scripts/publish-runner-protocol-eval-history.mjs
@@ -2,6 +2,7 @@
 import { createHash } from "node:crypto";
 import { execFile } from "node:child_process";
 import {
+  appendFile,
   lstat,
   mkdtemp,
   mkdir,
@@ -13,13 +14,23 @@ import {
 import { tmpdir } from "node:os";
 import { extname, join, relative, resolve, sep } from "node:path";
 import { promisify } from "node:util";
+import { enrichProtocolEvalHistory } from "./runner-protocol-eval-metrics.mjs";
+import { renderProtocolEvalHistoryIndex } from "./runner-protocol-eval-history-view.mjs";
+export { renderProtocolEvalHistoryIndex } from "./runner-protocol-eval-history-view.mjs";
+import {
+  trustedViewerFiles,
+  validatePublicViewerPage,
+} from "./public-eval-viewer.mjs";
 
 const execFileAsync = promisify(execFile);
-const SAFE_CAMPAIGN = /^gha-[1-9][0-9]*-[1-9][0-9]*$/;
+const SAFE_CAMPAIGN =
+  /^gha-[1-9][0-9]*-[1-9][0-9]*(?:-report-[a-z0-9][a-z0-9-]{0,39})?$/;
 const SAFE_REPORT_PATHS = [
   /^(?:index|latest|inventory|real-server)\.html$/,
   /^tests\/[A-Za-z0-9][A-Za-z0-9._-]{0,199}\.html$/,
   /^attempts\/[A-Za-z0-9][A-Za-z0-9._-]{0,199}\.html$/,
+  /^attempts\/[A-Za-z0-9][A-Za-z0-9._-]{0,199}\/index\.html$/,
+  /^viewer\/assets\/[A-Za-z0-9][A-Za-z0-9._-]*\.(?:js|css|woff2)$/,
   /^campaign\.json$/,
 ];
 const CREDENTIAL_PATTERNS = [
@@ -38,21 +49,11 @@ const ACTIVE_HTML_PATTERNS = [
   /javascript\s*:/iu,
   /(?:src|href)\s*=\s*["'](?:https?:)?\/\//iu,
 ];
-const MAX_HISTORY_CAMPAIGNS = 200;
 
 function json(value) {
   return `${JSON.stringify(value, null, 2)}\n`;
 }
 
-function html(value) {
-  return String(value ?? "")
-    .replaceAll("&", "&amp;")
-    .replaceAll("<", "&lt;")
-    .replaceAll(">", "&gt;")
-    .replaceAll('"', "&quot;")
-    .replaceAll("'", "&#39;");
-}
-
 async function loadObject(path) {
   const value = JSON.parse(await readFile(path, "utf8"));
   if (value === null || Array.isArray(value) || typeof value !== "object") {
@@ -136,9 +137,16 @@ function internalHtmlHrefs(content) {
     .filter((href) => href && !href.startsWith("#"));
 }
 
-export async function validatePublicProtocolEvalReport(reportRoot) {
+export async function validatePublicProtocolEvalReport(
+  reportRoot,
+  { viewerRoot } = {},
+) {
   const root = resolve(reportRoot);
   const files = await relativeFiles(root);
+  const hasChat = files.some((file) =>
+    /^attempts\/[^/]+\/index\.html$/.test(file),
+  );
+  const viewer = hasChat ? await trustedViewerFiles(viewerRoot) : null;
   if (!files.includes("index.html") || !files.includes("campaign.json")) {
     throw new Error(
       "Public protocol eval report requires index.html and campaign.json",
@@ -157,21 +165,44 @@ export async function validatePublicProtocolEvalReport(reportRoot) {
         `Public protocol eval file exceeds its size boundary: ${file}`,
       );
     }
+    if (file.startsWith("viewer/")) {
+      const expected = viewer?.files.get(file);
+      if (!expected || !expected.equals(await readFile(absolute)))
+        throw new Error(
+          `Public viewer asset differs from trusted build: ${file}`,
+        );
+      continue;
+    }
     const content = await readFile(absolute, "utf8");
-    for (const pattern of CREDENTIAL_PATTERNS) {
-      if (pattern.test(content))
-        throw new Error(
-          `Public report contains credential/session material: ${file}`,
-        );
+    const richAttempt = /^attempts\/[^/]+\/index\.html$/.test(file);
+    const payload = richAttempt
+      ? validatePublicViewerPage(content, viewer.index)
+      : null;
+    if (!richAttempt) {
+      for (const pattern of CREDENTIAL_PATTERNS) {
+        if (pattern.test(content))
+          throw new Error(
+            `Public report contains credential/session material: ${file}`,
+          );
+      }
+      if (extname(file) !== ".html") continue;
+      for (const pattern of ACTIVE_HTML_PATTERNS) {
+        if (pattern.test(content))
+          throw new Error(
+            `Public report contains active or remote HTML: ${file}`,
+          );
+      }
     }
-    if (extname(file) !== ".html") continue;
-    for (const pattern of ACTIVE_HTML_PATTERNS) {
-      if (pattern.test(content))
-        throw new Error(
-          `Public report contains active or remote HTML: ${file}`,
-        );
-    }
-    for (const href of internalHtmlHrefs(content)) {
+    const navigation = payload
+      ? [
+          payload.navigation?.suiteHref,
+          payload.navigation?.previous?.href,
+          payload.navigation?.next?.href,
+        ].filter(Boolean)
+      : [];
+    for (const href of [...internalHtmlHrefs(content), ...navigation]) {
+      if (typeof href !== "string" || /[?:\\]|^\/|^[a-z]+:/i.test(href))
+        throw new Error(`Unsafe report navigation in ${file}`);
       const clean = href.split("#", 1)[0].split("?", 1)[0];
       const target = resolve(
         root,
@@ -189,6 +220,15 @@ export async function validatePublicProtocolEvalReport(reportRoot) {
       }
     }
   }
+  if (viewer) {
+    for (const file of viewer.files.keys())
+      if (!files.includes(file))
+        throw new Error(`Missing public viewer asset: ${file}`);
+    if (files.some((file) => /^attempts\/[^/]+\.html$/.test(file)))
+      throw new Error(
+        "Chat Evalbook must not mix in legacy plain attempt pages",
+      );
+  }
   const campaign = await loadObject(join(root, "campaign.json"));
   if (
     campaign.schema !== "paperclip.runner-protocol-eval.campaign/v1" ||
@@ -199,11 +239,17 @@ export async function validatePublicProtocolEvalReport(reportRoot) {
   return { files, campaign };
 }
 
-export async function createProtocolEvalBundleManifest(reportRoot, campaignId) {
+export async function createProtocolEvalBundleManifest(
+  reportRoot,
+  campaignId,
+  { viewerRoot } = {},
+) {
   if (!SAFE_CAMPAIGN.test(campaignId))
     throw new Error("Unsafe protocol eval campaign ID");
-  const { files, campaign } =
-    await validatePublicProtocolEvalReport(reportRoot);
+  const { files, campaign } = await validatePublicProtocolEvalReport(
+    reportRoot,
+    { viewerRoot },
+  );
   if (campaign.campaignId !== campaignId)
     throw new Error("Report campaign ID does not match publication target");
   const entries = await Promise.all(
@@ -250,6 +296,9 @@ export function protocolEvalHistoryRecord(campaign, publicRoot) {
     totals: campaign.totals,
     rosters: campaign.rosters,
     source: campaign.source,
+    ...(campaign.reportRevision
+      ? { reportRevision: campaign.reportRevision }
+      : {}),
   };
 }
 
@@ -266,30 +315,29 @@ export function mergeProtocolEvalHistory(history, record) {
     );
   }
   const campaigns = existing
-    ? history.campaigns
+    ? [...history.campaigns]
     : [...history.campaigns, record];
-  campaigns.sort((left, right) =>
-    right.generatedAt.localeCompare(left.generatedAt),
-  );
-  const latest = campaigns[0] ?? null;
+  const activityAt = (campaign) =>
+    campaign.reportRevision?.renderedAt ?? campaign.generatedAt;
+  const activityOrder = (left, right) =>
+    activityAt(right).localeCompare(activityAt(left));
+  campaigns.sort(activityOrder);
+  // Report revisions are discoverable history entries, never qualification runs.
+  const qualifications = campaigns
+    .filter((campaign) => !campaign.reportRevision)
+    .sort((left, right) => right.generatedAt.localeCompare(left.generatedAt));
+  const latest = qualifications[0] ?? null;
   const latestGreen =
-    campaigns.find((campaign) => campaign.complete && campaign.allPassed) ??
-    null;
-  const retained = campaigns.slice(0, MAX_HISTORY_CAMPAIGNS);
-  if (
-    latestGreen &&
-    !retained.some(
-      (campaign) => campaign.campaignId === latestGreen.campaignId,
-    )
-  ) {
-    retained[retained.length - 1] = latestGreen;
-  }
+    qualifications.find(
+      (campaign) => campaign.complete && campaign.allPassed,
+    ) ?? null;
   return {
     schema: history.schema,
     updatedAt: new Date().toISOString(),
     latestCampaignId: latest?.campaignId ?? null,
     latestGreenCampaignId: latestGreen?.campaignId ?? null,
-    campaigns: retained,
+    campaigns,
+    ...(history.analytics ? { analytics: history.analytics } : {}),
   };
 }
 
@@ -323,44 +371,6 @@ export function buildProtocolEvalPointers(history) {
   };
 }
 
-function date(value) {
-  return new Intl.DateTimeFormat("en-US", {
-    dateStyle: "medium",
-    timeStyle: "short",
-    timeZone: "UTC",
-  }).format(new Date(value));
-}
-
-export function renderProtocolEvalHistoryIndex(history) {
-  const rows = history.campaigns.length
-    ? history.campaigns
-        .map((campaign) => {
-          const status =
-            campaign.complete && campaign.allPassed ? "passed" : "failed";
-          const rosters = campaign.rosters
-            .map(
-              (roster) =>
-                `${html(roster.model)} · ${roster.passed}/${roster.selected}`,
-            )
-            .join("<br>");
-          return `<tr><td><a href="${html(campaign.publicUrl)}"><code>${html(campaign.campaignId)}</code></a><small>${html(date(campaign.generatedAt))} UTC</small></td><td><span class="status ${status}">${status}</span></td><td><strong>${html(campaign.totals.passed)}/${html(campaign.totals.selected)}</strong><small>${html(campaign.totals.behaviorFailures)} behavior · ${html(campaign.totals.infrastructureFailures)} infrastructure</small></td><td>${rosters}</td><td><code>${html(campaign.source?.paperclip?.sha?.slice(0, 8) ?? "unknown")}</code><small>evals ${html(campaign.source?.evals?.sha?.slice(0, 8) ?? "unknown")}</small></td><td><a href="${html(campaign.publicUrl)}">Open Evalbook →</a></td></tr>`;
-        })
-        .join("")
-    : '<tr><td colspan="6" class="empty">No campaigns have been published yet.</td></tr>';
-  const latest = history.campaigns.find(
-    (campaign) => campaign.campaignId === history.latestCampaignId,
-  );
-  const latestGreen = history.campaigns.find(
-    (campaign) => campaign.campaignId === history.latestGreenCampaignId,
-  );
-  return `<!doctype html>
-<html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width"><meta name="color-scheme" content="light dark"><title>Runner protocol eval campaigns · Paperclip</title>
-<style>:root{color-scheme:light dark;--bg:#fff;--fg:#172019;--muted:#667069;--line:#dfe3dc;--raised:#f8f9f6;--pass:#17603a;--pass-bg:#e5f3e9;--fail:#942f2b;--fail-bg:#f9e5e3} @media(prefers-color-scheme:dark){:root{--bg:#141413;--fg:#fafafa;--muted:#aaa;--line:#ffffff1f;--raised:#1c1c1b;--pass:#65d58c;--pass-bg:#22c55e1f;--fail:#ff7770;--fail-bg:#dc26262e}} *{box-sizing:border-box}body{margin:0;background:var(--bg);color:var(--fg);font:14px/1.5 ui-sans-serif,system-ui,sans-serif}main{width:min(1560px,calc(100% - 48px));margin:48px auto 72px}h1{margin:0;font-size:clamp(34px,4vw,56px);line-height:1.05;letter-spacing:-.04em}p{max-width:760px;color:var(--muted);font-size:16px}a{color:inherit;text-underline-offset:3px}.pointers{display:flex;gap:10px;margin:28px 0 18px}.pointers a{padding:8px 11px;border:1px solid var(--line);border-radius:8px;background:var(--raised);text-decoration:none}.table{overflow:auto;border:1px solid var(--line);border-radius:12px}table{width:100%;border-collapse:collapse}th,td{padding:13px 14px;border-bottom:1px solid var(--line);text-align:left;vertical-align:top}th{background:var(--raised);color:var(--muted);font-size:10px;text-transform:uppercase;letter-spacing:.06em}tr:last-child td{border:0}small{display:block;margin-top:4px;color:var(--muted);font-size:10px}.status{display:inline-block;padding:3px 8px;border-radius:99px;font-size:10px;font-weight:750;text-transform:uppercase}.passed{color:var(--pass);background:var(--pass-bg)}.failed{color:var(--fail);background:var(--fail-bg)}.empty{padding:48px;text-align:center;color:var(--muted)}footer{margin-top:18px;color:var(--muted);font-size:11px}@media(max-width:700px){main{width:calc(100% - 28px);margin-top:28px}}</style></head>
-<body><main><div><small>Paperclip quality engineering</small><h1>Runner protocol eval campaigns</h1><p>Versioned direct live-runner Evalbook reports. Full provider transcripts, session identifiers, state, and raw tool evidence remain in access-controlled workflow artifacts.</p></div>
-<nav class="pointers">${latest ? `<a href="${html(latest.publicUrl)}">Latest · ${html(latest.campaignId)}</a>` : ""}${latestGreen ? `<a href="${html(latestGreen.publicUrl)}">Latest green · ${html(latestGreen.campaignId)}</a>` : ""}</nav>
-<div class="table"><table><thead><tr><th>Campaign</th><th>Status</th><th>Cells</th><th>Models / rosters</th><th>Source</th><th></th></tr></thead><tbody>${rows}</tbody></table></div><footer>Updated ${html(date(history.updatedAt))} UTC · Immutable campaign bundles · Canonical Evalbook layout with public-safe evidence projections</footer></main></body></html>`;
-}
-
 function awsObject(bucket, key) {
   return `s3://${bucket}/${key}`;
 }
@@ -435,19 +445,31 @@ async function uploadImmutableReport(bucket, prefix, reportRoot) {
   );
 }
 
-export async function publishProtocolEvalHistory({ reportRoot, destination }) {
+export async function publishProtocolEvalHistory({
+  reportRoot,
+  destination,
+  viewerRoot,
+}) {
   const validatedDestination =
     validateProtocolEvalHistoryDestination(destination);
-  const { campaign } = await validatePublicProtocolEvalReport(reportRoot);
+  const { campaign } = await validatePublicProtocolEvalReport(reportRoot, {
+    viewerRoot,
+  });
+  const viewer = await trustedViewerFiles(viewerRoot);
+  const stylesheet = viewer.index.match(/<link rel="stylesheet" crossorigin href="\.\/(assets\/[A-Za-z0-9._-]+\.css)">/)?.[1];
+  if (!stylesheet || !viewer.files.get(`viewer/${stylesheet}`)?.includes(".evalbook-site"))
+    throw new Error("Published history requires the same-run Runner Lab site theme");
+  const stylesheetHref = `campaigns/${campaign.campaignId}/viewer/${stylesheet}`;
   const manifest = await createProtocolEvalBundleManifest(
     reportRoot,
     campaign.campaignId,
+    { viewerRoot },
   );
   const temporary = await mkdtemp(
     join(tmpdir(), "runner-protocol-eval-history-"),
   );
   const historyKey = `${validatedDestination.prefix}/history.json`;
-  const history = mergeProtocolEvalHistory(
+  const mergedHistory = mergeProtocolEvalHistory(
     (await downloadJson(
       validatedDestination.bucket,
       historyKey,
@@ -458,6 +480,15 @@ export async function publishProtocolEvalHistory({ reportRoot, destination }) {
       `${validatedDestination.publicBaseUrl}/${validatedDestination.prefix}`,
     ),
   );
+  const history = await enrichProtocolEvalHistory(mergedHistory, {
+    currentCampaign: campaign,
+    loadCampaign: async (id) => {
+      if (!SAFE_CAMPAIGN.test(id)) throw new Error("Unsafe historical campaign ID");
+      return downloadJson(validatedDestination.bucket,
+        `${validatedDestination.prefix}/campaigns/${id}/campaign.json`,
+        join(temporary, `${id}.json`));
+    },
+  });
   const campaignPrefix = `${validatedDestination.prefix}/campaigns/${campaign.campaignId}`;
   const manifestKey = `${campaignPrefix}/bundle-manifest.json`;
   const existing = await downloadJson(
@@ -502,7 +533,7 @@ export async function publishProtocolEvalHistory({ reportRoot, destination }) {
     );
   }
   const index = join(temporary, "index.html");
-  await writeFile(index, renderProtocolEvalHistoryIndex(history));
+  await writeFile(index, renderProtocolEvalHistoryIndex(history, stylesheetHref));
   await uploadFile(
     validatedDestination.bucket,
     `${validatedDestination.prefix}/index.html`,
@@ -513,11 +544,31 @@ export async function publishProtocolEvalHistory({ reportRoot, destination }) {
     campaignId: campaign.campaignId,
     bundleDigest: manifest.bundleDigest,
     historySize: history.campaigns.length,
+    reportUrl: `${validatedDestination.publicBaseUrl}/${campaignPrefix}/index.html`,
+    historyUrl: `${validatedDestination.publicBaseUrl}/${validatedDestination.prefix}/index.html`,
   };
 }
 
+export async function writeProtocolEvalPublicationLinks(result, environment = process.env) {
+  const { campaignId, reportUrl, historyUrl } = result;
+  if (!SAFE_CAMPAIGN.test(campaignId)) throw new Error("Invalid published campaign ID");
+  const safeUrl = (value) => {
+    const url = new URL(value);
+    if (url.protocol !== "https:" || url.username || url.password || /[\r\n<>]/.test(value))
+      throw new Error("Invalid published report URL");
+    return url.href;
+  };
+  const report = safeUrl(reportUrl);
+  const history = safeUrl(historyUrl);
+  if (environment.GITHUB_OUTPUT)
+    await appendFile(environment.GITHUB_OUTPUT, `report_url=${report}\nhistory_url=${history}\n`);
+  if (environment.GITHUB_STEP_SUMMARY)
+    await appendFile(environment.GITHUB_STEP_SUMMARY, `## Published Runner Evalbook\n\n[Open this run's Evalbook](<${report}>) · [All eval runs](<${history}>)\n\nCampaign: \`${campaignId}\`\n\nPublic replay uses the Runner Lab theme; full evidence is in the workflow artifact.\n`);
+}
+
 async function main() {
   const result = await publishProtocolEvalHistory({
+    viewerRoot: process.env.PAPERCLIP_RUNNER_PROTOCOL_EVAL_VIEWER_DIR,
     reportRoot: resolve(
       process.env.PAPERCLIP_RUNNER_PROTOCOL_EVAL_PUBLIC_REPORT_DIR ??
         "runner-protocol-eval-public-report",
@@ -531,9 +582,11 @@ async function main() {
         process.env.RUNNER_PROTOCOL_EVAL_HISTORY_PUBLIC_BASE_URL ?? "",
     },
   });
+  await writeProtocolEvalPublicationLinks(result);
   console.log(
     `Published immutable protocol eval campaign ${result.campaignId} (${result.bundleDigest}) and ${result.historySize} history record(s)`,
   );
+  console.log(`Evalbook: ${result.reportUrl}\nRun history: ${result.historyUrl}`);
 }
 
 if (
diff --git a/packages/paperclip-runner/scripts/publish-runner-protocol-eval-history.test.mjs b/packages/paperclip-runner/scripts/publish-runner-protocol-eval-history.test.mjs
index 835144fdc5..6ccae9bd9d 100644
--- a/packages/paperclip-runner/scripts/publish-runner-protocol-eval-history.test.mjs
+++ b/packages/paperclip-runner/scripts/publish-runner-protocol-eval-history.test.mjs
@@ -1,5 +1,5 @@
 import assert from "node:assert/strict";
-import { mkdtemp, mkdir, rm, writeFile } from "node:fs/promises";
+import { mkdtemp, mkdir, readFile, rm, writeFile } from "node:fs/promises";
 import { tmpdir } from "node:os";
 import { join } from "node:path";
 import test from "node:test";
@@ -14,9 +14,28 @@ import {
   renderProtocolEvalHistoryIndex,
   validateProtocolEvalHistoryDestination,
   validatePublicProtocolEvalReport,
+  writeProtocolEvalPublicationLinks,
 } from "./publish-runner-protocol-eval-history.mjs";
 
 const roots = [];
+test("successful publication exposes exact report and history links to Actions", async () => {
+  const root = await mkdtemp(join(tmpdir(), "evalbook-publication-links-"));
+  roots.push(root);
+  const environment = { GITHUB_OUTPUT: join(root, "outputs"), GITHUB_STEP_SUMMARY: join(root, "summary") };
+  const result = {
+    campaignId: "gha-42-2",
+    reportUrl: "https://reports.example/runner-protocol-evals/campaigns/gha-42-2/index.html",
+    historyUrl: "https://reports.example/runner-protocol-evals/index.html",
+  };
+  await writeProtocolEvalPublicationLinks(result, environment);
+  assert.equal(await readFile(environment.GITHUB_OUTPUT, "utf8"), `report_url=${result.reportUrl}\nhistory_url=${result.historyUrl}\n`);
+  const summary = await readFile(environment.GITHUB_STEP_SUMMARY, "utf8");
+  assert.ok(summary.includes(`[Open this run's Evalbook](<${result.reportUrl}>)`));
+  assert.ok(summary.includes(`[All eval runs](<${result.historyUrl}>)`));
+  await assert.rejects(writeProtocolEvalPublicationLinks({ ...result, reportUrl: "https://example.test/\nreport_url=bad" }, environment));
+  assert.throws(() => renderProtocolEvalHistoryIndex(emptyProtocolEvalHistory(), "https://untrusted.example/style.css"));
+});
+
 test.afterEach(async () => {
   await Promise.all(
     roots.splice(0).map((root) => rm(root, { recursive: true, force: true })),
@@ -111,12 +130,13 @@ test("keeps publication to the canonical static Evalbook surface", () => {
     "inventory.html",
     "tests/get-context.html",
     "attempts/attempt-01.html",
+    "attempts/attempt-01/index.html",
+    "viewer/assets/index-build.js",
     "campaign.json",
   ]) {
     assert.equal(isPublicProtocolEvalPath(file), true, file);
   }
   for (const file of [
-    "attempts/attempt-01/index.html",
     "runs/attempt/artifact.json",
     "provider-trace.log",
     "../secret",
@@ -177,7 +197,10 @@ test("retains immutable history and independent latest-green pointers", () => {
   const pointers = buildProtocolEvalPointers(history);
   assert.equal(pointers.latest.campaign.campaignId, "gha-43-1");
   assert.equal(pointers.latestGreen.campaign.campaignId, "gha-42-1");
-  const index = renderProtocolEvalHistoryIndex(history);
+  const index = renderProtocolEvalHistoryIndex(history, "campaigns/gha-43-1/viewer/assets/index.css");
+  assert.match(index, /class="evalbook-site"/);
+  assert.match(index, /href="campaigns\/gha-43-1\/viewer\/assets\/index.css"/);
+  assert.doesNotMatch(index, /<style>|color-scheme:light/);
   assert.match(index, /Runner protocol eval campaigns/);
   assert.match(index, /Open Evalbook/);
   assert.match(index, /34\/35/);
@@ -188,7 +211,61 @@ test("retains immutable history and independent latest-green pointers", () => {
   );
 });
 
-test("retains the latest green pointer outside the 200 newest campaigns", () => {
+test("report refreshes never replace qualification pointers or evict older measurements", () => {
+  const record = (value) =>
+    protocolEvalHistoryRecord(
+      value,
+      "https://reports.example/runner-protocol-evals",
+    );
+  let history = mergeProtocolEvalHistory(
+    emptyProtocolEvalHistory(),
+    record(campaign()),
+  );
+  history = mergeProtocolEvalHistory(
+    history,
+    record(
+      campaign({
+        campaignId: "gha-43-1",
+        generatedAt: "2026-09-06T00:00:00.000Z",
+        allPassed: false,
+      }),
+    ),
+  );
+  for (let index = 0; index < 205; index++) {
+    history = mergeProtocolEvalHistory(
+      history,
+      record(
+        campaign({
+          campaignId: `gha-42-1-report-refresh-${index}`,
+          // Defend even against an incorrectly timestamped refresh producer.
+          generatedAt: "2026-09-07T00:00:00.000Z",
+          reportRevision: {
+            sourceCampaignId: "gha-42-1",
+            renderedAt: "2026-09-07T00:00:00.000Z",
+            providerCalls: 0,
+          },
+        }),
+      ),
+    );
+  }
+  assert.equal(history.latestCampaignId, "gha-43-1");
+  assert.equal(history.latestGreenCampaignId, "gha-42-1");
+  assert.equal(
+    buildProtocolEvalPointers(history).latest.campaign.campaignId,
+    "gha-43-1",
+  );
+  assert.equal(
+    buildProtocolEvalPointers(history).latestGreen.campaign.campaignId,
+    "gha-42-1",
+  );
+  assert.equal(history.campaigns.length, 207);
+  assert.match(
+    renderProtocolEvalHistoryIndex(history, "campaigns/gha-42-1-report-chat-v1/viewer/assets/index.css"),
+    /Report refresh · no new model calls/,
+  );
+});
+
+test("retains every run and the latest green pointer beyond 200 campaigns", () => {
   const green = protocolEvalHistoryRecord(
     campaign(),
     "https://reports.example/runner-protocol-evals",
@@ -210,7 +287,7 @@ test("retains the latest green pointer outside the 200 newest campaigns", () =>
     );
   }
 
-  assert.equal(history.campaigns.length, 200);
+  assert.equal(history.campaigns.length, 202);
   assert.equal(history.latestCampaignId, "gha-243-1");
   assert.equal(history.latestGreenCampaignId, "gha-42-1");
   assert.equal(history.campaigns.at(-1).campaignId, "gha-42-1");
diff --git a/packages/paperclip-runner/scripts/refresh-runner-protocol-eval-report.mjs b/packages/paperclip-runner/scripts/refresh-runner-protocol-eval-report.mjs
new file mode 100644
index 0000000000..76bd4d4d32
--- /dev/null
+++ b/packages/paperclip-runner/scripts/refresh-runner-protocol-eval-report.mjs
@@ -0,0 +1,106 @@
+#!/usr/bin/env node
+// Re-render immutable recorded evidence; this command never invokes a model.
+import { execFileSync } from "node:child_process";
+import { createHash } from "node:crypto";
+import { mkdir, readFile, writeFile, lstat, readdir } from "node:fs/promises";
+import { join, resolve } from "node:path";
+import { sanitizeProtocolEvalRuns } from "./runner-protocol-eval-campaign.mjs";
+import { validatePublicProtocolEvalReport } from "./publish-runner-protocol-eval-history.mjs";
+import { sumAttemptCosts } from "./runner-protocol-eval-metrics.mjs";
+
+export async function refreshProtocolEvalReport({
+  sourceRoot,
+  evalsRoot,
+  viewerRoot,
+  outputRoot,
+  revision,
+  selection,
+  renderedAt = new Date().toISOString(),
+}) {
+  if (!/^[a-z0-9][a-z0-9-]{0,39}$/.test(revision ?? ""))
+    throw new Error("A safe, unique --revision is required");
+  if (await lstat(outputRoot).catch(() => null))
+    throw new Error("Report refresh output must be a new directory");
+  const campaign = JSON.parse(
+    await readFile(join(sourceRoot, "campaign.json"), "utf8"),
+  );
+  if (!/^gha-[1-9][0-9]*-[1-9][0-9]*$/.test(campaign.campaignId ?? ""))
+    throw new Error("Expected an original Actions campaign");
+  const program = join(
+    evalsRoot,
+    "evals/paperclip-runner/tools/eval_program.py",
+  );
+  const rendererDigest = createHash("sha256")
+    .update(await readFile(program))
+    .digest("hex");
+  await mkdir(outputRoot, { recursive: true });
+  const runsRoot = join(outputRoot, "public-runs");
+  const reportRoot = join(outputRoot, "report");
+  await sanitizeProtocolEvalRuns({
+    runsRoot: join(sourceRoot, "runs"),
+    publicRunsRoot: runsRoot,
+  });
+  execFileSync(
+    "python3",
+    [
+      program,
+      "report",
+      "--runs-root",
+      runsRoot,
+      "--output",
+      reportRoot,
+      "--viewer-root",
+      viewerRoot,
+      "--public-viewer",
+      "--inventory",
+      join(evalsRoot, "evals/paperclip-runner/inventory.json"),
+      "--coverage-matrix",
+      join(evalsRoot, "evals/paperclip-runner/coverage-matrix.json"),
+    ],
+    { stdio: "inherit" },
+  );
+  const refreshed = {
+    ...campaign,
+    ...(selection ? { selection } : {}),
+    // Recover retry-inclusive cost from retained evidence, not just winning cells.
+    costs: sumAttemptCosts(await Promise.all((await readdir(runsRoot)).map(async (id) =>
+      JSON.parse(await readFile(join(runsRoot, id, "artifact.json"), "utf8")).usage))),
+    campaignId: `${campaign.campaignId}-report-${revision}`,
+    // A presentation refresh is not a new model measurement.
+    generatedAt: campaign.generatedAt,
+    reportRevision: {
+      sourceCampaignId: campaign.campaignId,
+      sourceGeneratedAt: campaign.generatedAt,
+      renderedAt,
+      rendererDigest,
+      providerCalls: 0,
+    },
+  };
+  await writeFile(
+    join(reportRoot, "campaign.json"),
+    `${JSON.stringify(refreshed, null, 2)}\n`,
+  );
+  await validatePublicProtocolEvalReport(reportRoot, { viewerRoot });
+  return { reportRoot, campaignId: refreshed.campaignId, providerCalls: 0 };
+}
+
+if (
+  process.argv[1] &&
+  resolve(process.argv[1]) === resolve(import.meta.filename)
+) {
+  const arg = (name) => {
+    const index = process.argv.indexOf(name);
+    if (index < 0 || !process.argv[index + 1])
+      throw new Error(`Missing ${name}`);
+    return process.argv[index + 1];
+  };
+  console.log(
+    await refreshProtocolEvalReport({
+      sourceRoot: resolve(arg("--source")),
+      evalsRoot: resolve(arg("--evals-root")),
+      viewerRoot: resolve(arg("--viewer-root")),
+      outputRoot: resolve(arg("--output")),
+      revision: arg("--revision"),
+    }),
+  );
+}
diff --git a/packages/paperclip-runner/scripts/render-runner-workflow-evalbook.mjs b/packages/paperclip-runner/scripts/render-runner-workflow-evalbook.mjs
index 9ebafc19a4..df843805b7 100644
--- a/packages/paperclip-runner/scripts/render-runner-workflow-evalbook.mjs
+++ b/packages/paperclip-runner/scripts/render-runner-workflow-evalbook.mjs
@@ -309,6 +309,15 @@ export async function renderRunnerWorkflowWithCanonicalEvalbook({
   environment = process.env,
 }) {
   const program = await resolveCanonicalEvalProgram(packageRoot, environment);
+  const viewerRoot = resolve(
+    environment.PAPERCLIP_EVAL_VIEWER_ROOT ??
+      resolve(packageRoot, "dist-issue-thread"),
+  );
+  await access(resolve(viewerRoot, "index.html")).catch(() => {
+    throw new Error(
+      "Evalbook requires the chat viewer. Run pnpm --filter @paperclipai/paperclip-runner build:issue-thread first.",
+    );
+  });
   const runsRoot = resolve(outputDirectory, "evalbook-runs");
   await rm(runsRoot, { recursive: true, force: true });
   const attempts = await writeRunnerWorkflowEvalbookAttempts({
@@ -331,6 +340,8 @@ export async function renderRunnerWorkflowWithCanonicalEvalbook({
     runsRoot,
     "--output",
     outputDirectory,
+    "--viewer-root",
+    viewerRoot,
   ]);
   const programBytes = await readFile(program);
   const manifest = {
diff --git a/packages/paperclip-runner/scripts/runner-protocol-eval-campaign.mjs b/packages/paperclip-runner/scripts/runner-protocol-eval-campaign.mjs
index 13ccfbb108..5656395b1e 100644
--- a/packages/paperclip-runner/scripts/runner-protocol-eval-campaign.mjs
+++ b/packages/paperclip-runner/scripts/runner-protocol-eval-campaign.mjs
@@ -11,6 +11,12 @@ import {
   writeFile,
 } from "node:fs/promises";
 import { basename, dirname, join, relative, resolve, sep } from "node:path";
+import { sumAttemptCosts } from "./runner-protocol-eval-metrics.mjs";
+import {
+  publicChatView,
+  PUBLIC_CHAT_SCHEMA,
+  PUBLIC_CHAT_NOTICE,
+} from "./public-eval-chat.mjs";
 
 const SAFE_ID = /^[A-Za-z0-9][A-Za-z0-9._-]{0,199}$/;
 const ATTEMPT_FILES = new Set([
@@ -97,7 +103,9 @@ async function maintainedRosterSelection(programRoot) {
       return basename(rosterPath);
     });
   if (selected.length === 0 || new Set(selected).size !== selected.length) {
-    throw new Error("Maintained live campaign must contain unique enabled rosters");
+    throw new Error(
+      "Maintained live campaign must contain unique enabled rosters",
+    );
   }
   return new Set(selected);
 }
@@ -120,8 +128,7 @@ export async function buildProtocolEvalCatalog({
   const programRoot = resolve(evalsRoot, "evals/paperclip-runner");
   const rosterRoot = resolve(programRoot, "rosters");
   const requested = parseRosterSelection(rosterSelection);
-  const selected =
-    requested ?? (await maintainedRosterSelection(programRoot));
+  const selected = requested ?? (await maintainedRosterSelection(programRoot));
   const rosterFiles = (await readdir(rosterRoot, { withFileTypes: true }))
     .filter(
       (entry) =>
@@ -201,6 +208,7 @@ export async function buildProtocolEvalCatalog({
     schema: "paperclip.runner-protocol-eval.catalog/v1",
     campaignId,
     source,
+    selection: { kind: requested === null ? "maintained_full" : "subset", rosters: rosterSelection },
     rosters,
     cells,
     matrices: shards.map((include) => ({ include })),
@@ -432,6 +440,7 @@ export async function aggregateProtocolEvalCampaign({
   }
 
   const results = [];
+  const attemptUsages = [];
   for (const cell of catalog.cells) {
     const retained = retainedByCell.get(cell.cellId);
     const attemptIds = retained?.attemptIds?.length
@@ -445,6 +454,10 @@ export async function aggregateProtocolEvalCampaign({
           }),
         ];
     const finalAttemptId = attemptIds.at(-1);
+    for (const attemptId of attemptIds) {
+      const attempt = await loadObject(join(runsOut, attemptId, "artifact.json"));
+      attemptUsages.push(attempt.usage);
+    }
     const [score, artifact] = await Promise.all([
       loadObject(join(runsOut, finalAttemptId, "score.json")),
       loadObject(join(runsOut, finalAttemptId, "artifact.json")),
@@ -484,6 +497,8 @@ export async function aggregateProtocolEvalCampaign({
     schema: "paperclip.runner-protocol-eval.campaign/v1",
     campaignId: catalog.campaignId,
     generatedAt,
+    selection: catalog.selection,
+    costs: sumAttemptCosts(attemptUsages),
     source: {
       paperclip: source.paperclip,
       evals: source.evals,
@@ -509,7 +524,8 @@ export async function aggregateProtocolEvalCampaign({
   return campaign;
 }
 
-function publicArtifact(artifact) {
+function publicArtifact(artifact, evalCase) {
+  const issueThread = publicChatView(artifact, evalCase);
   const model = artifact.snapshot?.providerModel ?? {};
   const infrastructure = artifact.infrastructureFailure;
   const providerVersion =
@@ -525,12 +541,29 @@ function publicArtifact(artifact) {
     provider: artifact.provider,
     driver: artifact.driver,
     providerVersion,
-    retainedSession: false,
+    retainedSession: null,
     retainedSessionStatus: "redacted from the public report",
     usage: safeUsage(artifact.usage),
-    turn: { status: artifact.turn?.status ?? "failed" },
+    timing: {
+      startedAt:
+        typeof artifact.timing?.startedAt === "string"
+          ? artifact.timing.startedAt
+          : null,
+      finishedAt:
+        typeof artifact.timing?.finishedAt === "string"
+          ? artifact.timing.finishedAt
+          : null,
+      durationMs: Number.isFinite(artifact.timing?.durationMs)
+        ? artifact.timing.durationMs
+        : null,
+    },
+    turn: {
+      status: artifact.turn?.status ?? "failed",
+      turnId: issueThread.turns.at(-1).id,
+    },
     snapshot: {
       createdAt: artifact.snapshot?.createdAt ?? artifact.createdAt,
+      sessionId: "public-report",
       providerModel: {
         id: model.id ?? artifact.requestedModel,
         provider: model.provider ?? artifact.provider,
@@ -539,6 +572,8 @@ function publicArtifact(artifact) {
       evidence: [],
     },
     devtools: { revisions: [] },
+    publication: { schema: PUBLIC_CHAT_SCHEMA, notice: PUBLIC_CHAT_NOTICE },
+    issueThread,
     ...(infrastructure && typeof infrastructure === "object"
       ? {
           infrastructureFailure: {
@@ -622,15 +657,22 @@ export async function sanitizeProtocolEvalRuns({ runsRoot, publicRunsRoot }) {
     await Promise.all([
       writeFile(
         join(destination, "artifact.json"),
-        json(publicArtifact(artifact)),
+        json(publicArtifact(artifact, evalCase)),
         { mode: 0o600 },
       ),
       writeFile(join(destination, "score.json"), json(publicScore(score)), {
         mode: 0o600,
       }),
-      writeFile(join(destination, "case.json"), json(evalCase), {
-        mode: 0o600,
-      }),
+      writeFile(
+        join(destination, "case.json"),
+        json({
+          id: evalCase.id,
+          checks: (evalCase.checks ?? []).map(({ id, kind }) => ({ id, kind })),
+        }),
+        {
+          mode: 0o600,
+        },
+      ),
       writeFile(join(destination, "config.json"), json(publicConfig(config)), {
         mode: 0o600,
       }),
diff --git a/packages/paperclip-runner/scripts/runner-protocol-eval-campaign.test.mjs b/packages/paperclip-runner/scripts/runner-protocol-eval-campaign.test.mjs
index 0703d3de7d..26ca75ea07 100644
--- a/packages/paperclip-runner/scripts/runner-protocol-eval-campaign.test.mjs
+++ b/packages/paperclip-runner/scripts/runner-protocol-eval-campaign.test.mjs
@@ -111,6 +111,7 @@ test("catalogs roster plus case cells and emits bounded balanced shards", async
     maxParallel: 80,
   });
   assert.equal(catalog.cells.length, 1);
+  assert.equal(catalog.selection.kind, "maintained_full");
   assert.equal(catalog.cells[0].credentialName, "OPENROUTER_API_KEY");
   assert.equal(catalog.maxParallelPerShard, 40);
   assert.equal(catalog.matrices[0].include.length, 1);
@@ -185,6 +186,7 @@ test("all selects the maintained enabled campaign and explicit diagnostics can s
     diagnostic.rosters.map((roster) => roster.rosterId),
     ["protocol-live-disabled-model"],
   );
+  assert.equal(diagnostic.selection.kind, "subset");
 });
 
 test("all fails closed when the maintained campaign is missing", async () => {
@@ -252,6 +254,37 @@ test("aggregates retained attempts and synthesizes missing cells as infrastructu
   );
 });
 
+test("campaign cost includes failed attempts before a successful retry", async () => {
+  const { root, config, evalCase } = await fixture();
+  const catalog = await buildProtocolEvalCatalog({ evalsRoot: root, campaignId: "gha-42-1" });
+  const catalogPath = join(root, "catalog.json");
+  const download = join(root, "downloads/cell");
+  await mkdir(download, { recursive: true });
+  await writeFile(catalogPath, JSON.stringify(catalog));
+  await writeFile(join(download, "cell.json"), JSON.stringify({
+    cellId: catalog.cells[0].cellId, caseId: evalCase.id,
+    rosterFile: catalog.cells[0].rosterFile, exitCode: 0,
+  }));
+  for (const [attemptId, amount, passed] of [["attempt-01", 2, false], ["attempt-02", 3, true]]) {
+    const directory = join(download, "runs", attemptId);
+    await mkdir(directory, { recursive: true });
+    for (const [file, value] of Object.entries({
+      "artifact.json": { attemptId, usage: { estimatedCostNanodollars: amount } },
+      "score.json": { attemptId, caseId: evalCase.id, passed, disposition: passed ? "passed" : "infrastructure_failure" },
+      "case.json": evalCase, "config.json": config,
+    })) await writeFile(join(directory, file), JSON.stringify(value));
+  }
+  const result = await aggregateProtocolEvalCampaign({
+    catalogPath, downloadsRoot: join(root, "downloads"), evalsRoot: root,
+    runsOut: join(root, "merged"), campaignOut: join(root, "campaign.json"), source: {},
+  });
+  assert.equal(result.totals.passed, 1);
+  assert.equal(result.results[0].usage.estimatedCostNanodollars, 3);
+  assert.equal(result.costs.estimated.nanodollars, 5);
+  assert.equal(result.costs.attempts, 2);
+  assert.equal(result.selection.kind, "maintained_full");
+});
+
 test("rejects downloaded cells that were not declared by the immutable catalog", async () => {
   const { root } = await fixture();
   const catalog = await buildProtocolEvalCatalog({
@@ -286,7 +319,7 @@ test("rejects downloaded cells that were not declared by the immutable catalog",
   );
 });
 
-test("public run projection removes provider sessions, traces, transcripts, evidence, and state", async () => {
+test("public run projection removes raw evidence and gives unverified recordings an empty chat view", async () => {
   const { root, config, evalCase } = await fixture();
   const attemptId = "get-task-context-opencode-gha-42-1-attempt-01";
   const source = join(root, "raw-runs", attemptId);
@@ -357,12 +390,14 @@ test("public run projection removes provider sessions, traces, transcripts, evid
   );
   assert.doesNotMatch(
     serialized,
-    /private-session|private transcript|private-turn|issueThread|trace/,
+    /private-session|private transcript|private-turn|"trace":/,
   );
   const artifact = JSON.parse(serialized);
   assert.deepEqual(artifact.snapshot.transcript, []);
   assert.deepEqual(artifact.snapshot.evidence, []);
   assert.deepEqual(artifact.devtools.revisions, []);
+  assert.equal(artifact.issueThread.composer.state, "disabled");
+  assert.equal(artifact.issueThread.turns[0].items[0].kind, "system_notice");
   const score = JSON.parse(
     await readFile(join(root, "public-runs", attemptId, "score.json"), "utf8"),
   );
diff --git a/packages/paperclip-runner/scripts/runner-protocol-eval-history-view.mjs b/packages/paperclip-runner/scripts/runner-protocol-eval-history-view.mjs
new file mode 100644
index 0000000000..4bf3a47035
--- /dev/null
+++ b/packages/paperclip-runner/scripts/runner-protocol-eval-history-view.mjs
@@ -0,0 +1,123 @@
+import { compareCampaignAnalytics } from "./runner-protocol-eval-metrics.mjs";
+
+const escape = (value) => String(value ?? "").replaceAll("&", "&amp;").replaceAll("<", "&lt;").replaceAll(">", "&gt;").replaceAll('"', "&quot;").replaceAll("'", "&#39;");
+const date = (value) => new Intl.DateTimeFormat("en-US", { dateStyle: "medium", timeStyle: "short", timeZone: "UTC" }).format(new Date(value));
+const percentage = (run) => run.totals.selected ? 100 * run.totals.passed / run.totals.selected : null;
+const dollars = (value) => `$${(value / 1e9).toFixed(6)}`;
+
+export function costLabel(costs, field = "estimated") {
+  const metric = costs?.[field];
+  if (!Number.isFinite(metric?.nanodollars) || metric.nanodollars < 0) return "Unknown";
+  const incomplete = metric.recordedAttempts < costs.attempts;
+  return `${incomplete ? "≥ " : ""}${dollars(metric.nanodollars)}`;
+}
+
+function costCell(costs) {
+  const coverage = costs?.estimated?.recordedAttempts ?? 0;
+  const attempts = costs?.attempts ?? 0;
+  return `<strong>${escape(costLabel(costs))}</strong><small>Estimated · ${coverage}/${attempts} entries</small><small>Provider list: ${escape(costLabel(costs, "providerReported"))}</small><small>${costs?.scope === "all_attempts" ? "All attempts, including retries" : "Historical final attempts only"}</small>`;
+}
+
+function commit(repository, sha, label) {
+  if (!/^[a-f0-9]{40}$/.test(sha ?? "")) return `<small>${label}: unknown</small>`;
+  return `<small>${label}: <a href="https://github.com/${repository}/commit/${sha}" title="${sha}"><code>${sha.slice(0, 8)}</code></a></small>`;
+}
+
+function sourceLinks(run) {
+  const url = run.source?.workflowRunUrl;
+  const workflow = /^https:\/\/github\.com\/paperclipai\/paperclip\/actions\/runs\/[1-9][0-9]*$/.test(url ?? "")
+    ? `<small><a href="${url}">GitHub Actions ↗</a></small>` : "";
+  return `${commit("paperclipai/paperclip", run.source?.paperclip?.sha, "Paperclip")}${commit("paperclipai/paperclip-evals", run.source?.evals?.sha, "Evals")}${workflow}<small>${escape(run.source?.paperclip?.ref ?? "")}</small>`;
+}
+
+function chart(runs, analytics, kind, id) {
+  const cost = kind === "cost";
+  const label = cost ? "Estimated cost over time (USD)" : "Pass rate over time (%)";
+  const values = runs.map((run) => cost ? analytics[run.campaignId]?.costs?.estimated?.nanodollars : percentage(run));
+  const max = cost ? Math.max(1, ...values.filter(Number.isFinite)) : 100;
+  const timestamps = runs.map((run) => Date.parse(run.generatedAt));
+  const elapsed = timestamps.at(-1) - timestamps[0];
+  const x = (index) => elapsed > 0 ? 48 + 504 * (timestamps[index] - timestamps[0]) / elapsed : 300;
+  const y = (value) => 145 - value / max * 116;
+  const scopes = cost ? ["all_attempts", "final_attempts"] : ["pass"];
+  const series = scopes.map((scope) => {
+    let drawing = false;
+    const path = values.map((value, index) => {
+      const present = Number.isFinite(value) && value >= 0 && (!cost || analytics[runs[index].campaignId]?.costs?.scope === scope);
+      if (!present) { drawing = false; return ""; }
+      const point = `${drawing ? "L" : "M"}${x(index).toFixed(2)},${y(value).toFixed(2)}`;
+      drawing = true;
+      return point;
+    }).join(" ");
+    return `<path class="trend-line ${scope}" d="${path}"/>`;
+  }).join("");
+  const points = values.map((value, index) => {
+    if (!Number.isFinite(value) || value < 0) return "";
+    const run = runs[index];
+    const metric = analytics[run.campaignId];
+    const description = `${date(run.generatedAt)} UTC · ${run.campaignId} · ${cost ? `${costLabel(metric?.costs)} (${metric?.costs?.scope})` : `${value.toFixed(1)}% (${run.totals.passed}/${run.totals.selected})`}`;
+    return `<a href="${escape(run.publicUrl)}" aria-label="${escape(description)}"><circle class="trend-point ${cost ? metric?.costs?.scope : "pass"}" cx="${x(index).toFixed(2)}" cy="${y(value).toFixed(2)}" r="4"><title>${escape(description)}</title></circle></a>`;
+  }).join("");
+  const tick = (run) => `${run.generatedAt.slice(5, 16).replace("T", " ")} UTC`;
+  return `<figure><figcaption>${label}</figcaption><svg class="trend-chart" viewBox="0 0 600 186" role="img" aria-labelledby="${id}"><title id="${id}">${label}. Each point links to its recorded run.</title><path class="trend-axis" d="M48,25V145H552"/><text x="40" y="33" text-anchor="end">${cost ? `$${(max / 1e9).toFixed(2)}` : "100%"}</text><text x="40" y="149" text-anchor="end">0</text>${series}${points}<text x="48" y="176">${escape(tick(runs[0]))}</text><text x="552" y="176" text-anchor="end">${escape(tick(runs.at(-1)))}</text></svg></figure>`;
+}
+
+function changeCell(run, analytics, previous) {
+  if (run.reportRevision) return '<span class="muted">Presentation only</span>';
+  if (!previous) return '<span class="muted">No matching baseline</span>';
+  const change = compareCampaignAnalytics(analytics[run.campaignId], analytics[previous.campaignId]);
+  if (!change) return '<span class="muted">Suite changed</span>';
+  const failures = (cells, destination) => cells.map((cell) => `<li><a href="${escape(destination.publicUrl)}tests/${encodeURIComponent(cell.caseId)}.html">${escape(cell.caseId)}</a> · ${escape(cell.rosterId)}${cell.disposition === "infrastructure_failure" ? " · infrastructure" : ""}</li>`).join("");
+  const counts = `${change.regressions.length} regressions · ${change.recoveries.length} recoveries`;
+  return `<details><summary>${counts}</summary><small>Versus <a href="${escape(previous.publicUrl)}">${escape(previous.campaignId)}</a></small>${change.regressions.length ? `<strong>Previously passing → failing</strong><ul>${failures(change.regressions, run)}</ul>` : ""}${change.recoveries.length ? `<strong>Previously failing → passing</strong><ul>${failures(change.recoveries, run)}</ul>` : ""}</details>`;
+}
+
+export function renderProtocolEvalHistoryIndex(history, stylesheetHref) {
+  if (!/^campaigns\/gha-[a-z0-9-]+\/viewer\/assets\/[A-Za-z0-9._-]+\.css$/.test(stylesheetHref ?? ""))
+    throw new Error("History requires an immutable campaign's Runner Lab stylesheet");
+  for (const run of history.campaigns) {
+    if (!["selected", "passed", "behaviorFailures", "infrastructureFailures"].every((field) => Number.isSafeInteger(run.totals?.[field]) && run.totals[field] >= 0)
+      || !run.rosters.every((roster) => Number.isSafeInteger(roster.selected) && Number.isSafeInteger(roster.passed)))
+      throw new Error("History requires numeric recorded counts");
+    const url = new URL(run.publicUrl);
+    if (url.protocol !== "https:" || url.username || url.password)
+      throw new Error("History report links must be credential-free HTTPS URLs");
+  }
+  const analytics = history.analytics ?? {};
+  const presentations = new Map();
+  for (const refresh of history.campaigns.filter((run) => run.reportRevision)
+    .sort((a, b) => a.reportRevision.renderedAt.localeCompare(b.reportRevision.renderedAt)))
+    presentations.set(refresh.reportRevision.sourceCampaignId, refresh);
+  const measurements = history.campaigns.filter((run) => !run.reportRevision)
+    .map((run) => presentations.has(run.campaignId)
+      ? { ...run, originalPublicUrl: run.publicUrl, publicUrl: presentations.get(run.campaignId).publicUrl }
+      : run)
+    .sort((a, b) => a.generatedAt.localeCompare(b.generatedAt) || a.campaignId.localeCompare(b.campaignId));
+  const groups = new Map();
+  const baselines = new Map();
+  for (const run of measurements) {
+    const key = analytics[run.campaignId]?.suiteKey;
+    if (!key || !run.complete) continue;
+    const group = groups.get(key) ?? [];
+    baselines.set(run.campaignId, group.at(-1));
+    group.push(run);
+    groups.set(key, group);
+  }
+  const ordered = [...groups.entries()].sort(([, a], [, b]) => b.at(-1).totals.selected - a.at(-1).totals.selected || b.at(-1).generatedAt.localeCompare(a.at(-1).generatedAt));
+  const trends = ordered.map(([key, runs], index) => {
+    const latest = runs.at(-1);
+    return `<details class="trend-group" ${index === 0 ? "open" : ""}><summary>${latest.totals.selected} cells · ${latest.rosters.length} configurations · ${runs.length} recorded runs · evals ${escape(latest.source.evals.sha.slice(0, 8))}</summary><div class="trend-grid">${chart(runs, analytics, "pass", `pass-${key}`)}${chart(runs, analytics, "cost", `cost-${key}`)}</div><p class="muted">Cost: solid cyan includes retries; dashed purple is historical final-attempt cost. Missing cost is a gap, not zero. Hover or select a point to inspect its run.</p></details>`;
+  }).join("") || '<p class="muted">Comparable run metadata has not been recorded yet.</p>';
+  const row = (run) => {
+    const metric = analytics[run.reportRevision?.sourceCampaignId ?? run.campaignId];
+    const status = !run.complete ? "incomplete" : run.allPassed ? "passed" : "failed";
+    const models = run.rosters.map((roster) => `<li>${escape(roster.model)} · ${roster.passed}/${roster.selected}<small>${escape(roster.driver)} · ${escape(roster.rosterId)}</small></li>`).join("");
+    const scope = metric?.selection === "maintained_full" ? "Full maintained suite" : metric?.selection === "subset" ? "Selected subset" : `${run.totals.selected} recorded cells`;
+    return `<tr><td><a href="${escape(run.publicUrl)}"><code>${escape(run.campaignId)}</code></a><small>${escape(date(run.generatedAt))} UTC</small>${run.reportRevision ? `<small>Report refresh · no new model calls · source ${escape(run.reportRevision.sourceCampaignId)}</small>` : `<small>${scope}</small>`}<small><a href="${escape(run.publicUrl)}">Open Evalbook →</a></small></td><td><span class="status ${status}">${status}</span><strong class="pass-rate">${run.totals.passed}/${run.totals.selected} · ${percentage(run)?.toFixed(1) ?? "—"}%</strong><small>${run.totals.behaviorFailures} behavior · ${run.totals.infrastructureFailures} infrastructure</small><details><summary>${run.rosters.length} model configurations</summary><ul>${models}</ul></details></td><td>${changeCell(run, analytics, baselines.get(run.campaignId))}</td><td>${run.reportRevision ? '<small>No additional model cost</small>' : costCell(metric?.costs)}</td><td>${sourceLinks(run)}</td></tr>`;
+  };
+  const table = (runs) => `<div class="table history-table" role="region" aria-label="Recorded eval runs" tabindex="0"><table><thead><tr><th>Run</th><th>Pass / fail</th><th>Change vs matching suite</th><th>Cost (USD)</th><th>Exact source</th></tr></thead><tbody>${runs.map(row).join("") || '<tr><td colspan="5">No campaigns have been published yet.</td></tr>'}</tbody></table></div>`;
+  const refreshes = history.campaigns.filter((run) => run.reportRevision);
+  const latest = measurements.find((run) => run.campaignId === history.latestCampaignId);
+  const green = measurements.find((run) => run.campaignId === history.latestGreenCampaignId);
+  return `<!doctype html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width"><title>Runner protocol eval campaigns · Paperclip</title><link rel="stylesheet" href="${escape(stylesheetHref)}"></head><body class="evalbook-site"><main><header class="top"><a href="index.html">paperclip-runner evals</a><span class="badge">Run history</span></header><h1>Runner protocol eval campaigns</h1><p class="muted">Every recorded campaign, its cost, and its exact source. Public chat replays are linked below; full provider evidence remains in access-controlled workflow artifacts.</p><nav class="pointers">${latest ? `<a href="${escape(latest.publicUrl)}">Latest · ${escape(latest.campaignId)}</a>` : ""}${green ? `<a href="${escape(green.publicUrl)}">Latest green · ${escape(green.campaignId)}</a>` : ""}<a href="history.json">Download history JSON</a></nav><h2>Like-for-like trends</h2><p class="muted">Only identical cells, model configurations, and eval-suite SHAs are compared. A changed suite starts a separate series. Report refreshes never count as new measurements. Regressions distinguish model behavior from infrastructure failures.</p>${trends}<h2>All runs · ${measurements.length}</h2><p class="muted">Estimated cost and provider list cost are alternatives, not additive. ≥ means some entries lack usage. Historical final-only cost excludes retry spending. Commit links expose the full SHA on hover.</p>${table([...measurements].reverse())}${refreshes.length ? `<details><summary>Report refreshes · ${refreshes.length} (no new measurements)</summary>${table(refreshes)}</details>` : ""}<footer>Updated ${escape(date(history.updatedAt))} UTC · All run records retained · Immutable campaign bundles</footer></main></body></html>`;
+}
diff --git a/packages/paperclip-runner/scripts/runner-protocol-eval-metrics.mjs b/packages/paperclip-runner/scripts/runner-protocol-eval-metrics.mjs
new file mode 100644
index 0000000000..f258b94bfe
--- /dev/null
+++ b/packages/paperclip-runner/scripts/runner-protocol-eval-metrics.mjs
@@ -0,0 +1,97 @@
+import { createHash } from "node:crypto";
+import { isDeepStrictEqual } from "node:util";
+
+const SHA = /^[a-f0-9]{40}$/;
+const ID = /^[A-Za-z0-9][A-Za-z0-9._-]{0,199}$/;
+
+// Provider list cost and our pricing estimate are alternative measurements,
+// never additive. Missing usage is unknown, not a zero-dollar call.
+export function sumAttemptCosts(usages, scope = "all_attempts") {
+  const metric = (field) => {
+    const values = usages.map((usage) => usage?.[field]).filter((value) =>
+      typeof value === "number" && Number.isFinite(value) && value >= 0);
+    return {
+      nanodollars: values.length ? values.reduce((sum, value) => sum + value, 0) : null,
+      recordedAttempts: values.length,
+    };
+  };
+  return {
+    scope,
+    attempts: usages.length,
+    estimated: metric("estimatedCostNanodollars"),
+    providerReported: metric("providerReportedCostNanodollars"),
+  };
+}
+
+export function campaignAnalytics(campaign) {
+  const results = campaign.results ?? [];
+  const cells = results.map((result) => [result.cellId, result.model, result.provider, result.driver]);
+  cells.sort((a, b) => JSON.stringify(a).localeCompare(JSON.stringify(b)));
+  const comparable = SHA.test(campaign.source?.evals?.sha ?? "")
+    && cells.length > 0 && cells.length === campaign.totals?.selected
+    && results.every((result) => typeof result.passed === "boolean")
+    && results.filter((result) => result.passed).length === campaign.totals.passed
+    && new Set(cells.map(([id]) => id)).size === cells.length
+    && cells.every((cell) => cell.every((value) => typeof value === "string" && value.length > 0));
+  const suiteKey = comparable ? createHash("sha256")
+    .update(JSON.stringify([campaign.source.evals.sha, cells])).digest("hex") : null;
+  const suppliedCosts = campaign.costs;
+  const validCosts = suppliedCosts && ["all_attempts", "final_attempts"].includes(suppliedCosts.scope)
+    && Number.isSafeInteger(suppliedCosts.attempts) && suppliedCosts.attempts >= 0
+    && ["estimated", "providerReported"].every((field) => {
+      const metric = suppliedCosts[field];
+      return Number.isSafeInteger(metric?.recordedAttempts) && metric.recordedAttempts >= 0
+        && metric.recordedAttempts <= suppliedCosts.attempts
+        && (metric.nanodollars === null || typeof metric.nanodollars === "number" && Number.isFinite(metric.nanodollars) && metric.nanodollars >= 0);
+    });
+  return {
+    schema: "paperclip.runner-protocol-eval.analytics/v1",
+    suiteKey,
+    selection: campaign.selection?.kind === "maintained_full" ? "maintained_full"
+      : campaign.selection?.kind === "subset" ? "subset" : "recorded",
+    costs: validCosts ? {
+      scope: suppliedCosts.scope, attempts: suppliedCosts.attempts,
+      estimated: { nanodollars: suppliedCosts.estimated.nanodollars, recordedAttempts: suppliedCosts.estimated.recordedAttempts },
+      providerReported: { nanodollars: suppliedCosts.providerReported.nanodollars, recordedAttempts: suppliedCosts.providerReported.recordedAttempts },
+    } : sumAttemptCosts(results.map((result) => result.usage), "final_attempts"),
+    failedCells: results.filter((result) => !result.passed).map((result) => ({
+      cellId: ID.test(result.cellId) ? result.cellId : "unknown",
+      caseId: ID.test(result.caseId) ? result.caseId : "unknown",
+      rosterId: ID.test(result.rosterId) ? result.rosterId : "unknown",
+      disposition: result.disposition === "behavior_failure" ? "behavior_failure" : "infrastructure_failure",
+    })),
+  };
+}
+
+export function compareCampaignAnalytics(current, previous) {
+  if (!current?.suiteKey || current.suiteKey !== previous?.suiteKey) return null;
+  const before = new Set(previous.failedCells.map((cell) => cell.cellId));
+  const after = new Set(current.failedCells.map((cell) => cell.cellId));
+  return {
+    regressions: current.failedCells.filter((cell) => !before.has(cell.cellId)),
+    recoveries: previous.failedCells.filter((cell) => !after.has(cell.cellId)),
+  };
+}
+
+// History records and campaign bundles stay immutable. This separate, derived
+// projection can be backfilled from old bundles or enriched by a report refresh.
+export async function enrichProtocolEvalHistory(history, { currentCampaign, loadCampaign }) {
+  const analytics = { ...history.analytics };
+  const sourceId = currentCampaign.reportRevision?.sourceCampaignId ?? currentCampaign.campaignId;
+  for (const record of history.campaigns.filter((item) => !item.reportRevision)) {
+    const refresh = record.campaignId === sourceId ? currentCampaign : null;
+    if (!refresh && analytics[record.campaignId]?.schema === "paperclip.runner-protocol-eval.analytics/v1") continue;
+    const campaign = refresh ?? await loadCampaign(record.campaignId);
+    if (!campaign) continue;
+    if (!isDeepStrictEqual(campaign.source, record.source)
+      || !isDeepStrictEqual(campaign.totals, record.totals))
+      throw new Error(`Campaign analytics do not match immutable history: ${record.campaignId}`);
+    const projected = campaignAnalytics(campaign);
+    const previous = analytics[record.campaignId];
+    // Never downgrade an all-attempt measurement with a historical final-only one.
+    if (previous?.costs?.scope === "all_attempts" && projected.costs.scope !== "all_attempts")
+      projected.costs = previous.costs;
+    analytics[record.campaignId] = projected;
+  }
+  return { ...history, analytics };
+}
diff --git a/packages/paperclip-runner/scripts/runner-protocol-eval-metrics.test.mjs b/packages/paperclip-runner/scripts/runner-protocol-eval-metrics.test.mjs
new file mode 100644
index 0000000000..a8fcc13680
--- /dev/null
+++ b/packages/paperclip-runner/scripts/runner-protocol-eval-metrics.test.mjs
@@ -0,0 +1,83 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+import { campaignAnalytics, compareCampaignAnalytics, enrichProtocolEvalHistory, sumAttemptCosts } from "./runner-protocol-eval-metrics.mjs";
+import { costLabel, renderProtocolEvalHistoryIndex } from "./runner-protocol-eval-history-view.mjs";
+import { emptyProtocolEvalHistory, mergeProtocolEvalHistory, protocolEvalHistoryRecord } from "./publish-runner-protocol-eval-history.mjs";
+
+function campaign(id, failed = [], overrides = {}) {
+  const results = ["context", "create", "finish"].map((caseId) => ({
+    cellId: `codex--${caseId}`, caseId, rosterId: "codex", model: "mini", provider: "codex", driver: "codex_app_server",
+    passed: !failed.includes(caseId), disposition: failed.includes(caseId) ? "behavior_failure" : "passed",
+    usage: { estimatedCostNanodollars: 1_000_000, providerReportedCostNanodollars: 2_000_000 },
+  }));
+  return {
+    campaignId: `gha-${id}-1`, generatedAt: `2026-09-${String(id).padStart(2, "0")}T00:00:00.000Z`,
+    source: { paperclip: { sha: "a".repeat(40), ref: "refs/heads/master" }, evals: { sha: "b".repeat(40) }, workflowRunUrl: `https://github.com/paperclipai/paperclip/actions/runs/${id}` },
+    complete: true, allPassed: failed.length === 0, results,
+    selection: { kind: "maintained_full" },
+    totals: { selected: 3, passed: 3 - failed.length, behaviorFailures: failed.length, infrastructureFailures: 0 },
+    rosters: [{ rosterId: "codex", model: "mini", driver: "codex_app_server", selected: 3, passed: 3 - failed.length }],
+    ...overrides,
+  };
+}
+
+test("costs include retries without adding provider list cost to estimates or inventing missing usage", () => {
+  const costs = sumAttemptCosts([{ estimatedCostNanodollars: 2, providerReportedCostNanodollars: 7 }, { estimatedCostNanodollars: 3 }, {}, { estimatedCostNanodollars: -1 }, { estimatedCostNanodollars: Infinity }]);
+  assert.equal(costs.scope, "all_attempts");
+  assert.deepEqual(costs.estimated, { nanodollars: 5, recordedAttempts: 2 });
+  assert.deepEqual(costs.providerReported, { nanodollars: 7, recordedAttempts: 1 });
+  assert.equal(costs.attempts, 5);
+  assert.match(costLabel(costs), /^≥ /);
+  assert.equal(costLabel(sumAttemptCosts([{}, {}])), "Unknown");
+  assert.equal(costLabel(sumAttemptCosts([{ estimatedCostNanodollars: 0 }])), "$0.000000");
+});
+
+test("regressions and recoveries compare exact suite membership and evals SHA, not count alone", () => {
+  const before = campaignAnalytics(campaign(1, ["context"]));
+  const after = campaignAnalytics(campaign(2, ["create"]));
+  const change = compareCampaignAnalytics(after, before);
+  assert.deepEqual(change.regressions.map((cell) => cell.caseId), ["create"]);
+  assert.deepEqual(change.recoveries.map((cell) => cell.caseId), ["context"]);
+  const differentSha = campaign(2, [], { source: { evals: { sha: "c".repeat(40) } } });
+  assert.equal(compareCampaignAnalytics(campaignAnalytics(differentSha), before), null);
+  const changedMembership = campaign(2);
+  changedMembership.results[0].cellId = "codex--different-case";
+  assert.equal(compareCampaignAnalytics(campaignAnalytics(changedMembership), before), null);
+  const reordered = campaign(1, ["context"]);
+  reordered.results.reverse();
+  assert.equal(campaignAnalytics(reordered).suiteKey, before.suiteKey);
+});
+
+test("history analytics backfill without rewriting records and refreshes enrich original costs", async () => {
+  const source = campaign(1);
+  const record = protocolEvalHistoryRecord(source, "https://reports.example/runner-protocol-evals");
+  let history = mergeProtocolEvalHistory(emptyProtocolEvalHistory(), record);
+  history = await enrichProtocolEvalHistory(history, { currentCampaign: source, loadCampaign: () => assert.fail("current campaign already available") });
+  assert.equal(history.analytics[source.campaignId].costs.scope, "final_attempts");
+  const refresh = { ...source, campaignId: "gha-1-1-report-theme", reportRevision: { sourceCampaignId: source.campaignId, renderedAt: "2026-09-04T00:00:00.000Z" }, costs: sumAttemptCosts([...source.results.map((r) => r.usage), { estimatedCostNanodollars: 500_000 }]) };
+  history = mergeProtocolEvalHistory(history, protocolEvalHistoryRecord(refresh, "https://reports.example/runner-protocol-evals"));
+  history = await enrichProtocolEvalHistory(history, { currentCampaign: refresh, loadCampaign: () => assert.fail("refresh already available") });
+  assert.equal(history.analytics[source.campaignId].costs.estimated.nanodollars, 3_500_000);
+  assert.deepEqual(history.campaigns.find((run) => run.campaignId === source.campaignId), record);
+  assert.equal(history.latestCampaignId, source.campaignId);
+  await assert.rejects(enrichProtocolEvalHistory(history, { currentCampaign: { ...refresh, totals: { ...source.totals, passed: 0 } }, loadCampaign: () => null }), /do not match/);
+});
+
+test("history graphs exclude refreshes, link exact SHAs and Actions, and open the latest presentation", async () => {
+  const first = campaign(1, ["context"]);
+  const second = campaign(2, ["create"]);
+  const refresh = { ...second, campaignId: "gha-2-1-report-theme", reportRevision: { sourceCampaignId: second.campaignId, renderedAt: "2026-09-04T00:00:00.000Z" } };
+  let history = emptyProtocolEvalHistory();
+  for (const item of [first, second, refresh]) history = mergeProtocolEvalHistory(history, protocolEvalHistoryRecord(item, "https://reports.example/runner-protocol-evals"));
+  history = await enrichProtocolEvalHistory(history, { currentCampaign: refresh, loadCampaign: (id) => id === first.campaignId ? first : second });
+  const html = renderProtocolEvalHistoryIndex(history, "campaigns/gha-2-1-report-theme/viewer/assets/index.css");
+  assert.match(html, /All runs · 2/);
+  assert.match(html, /2 recorded runs/);
+  assert.match(html, /1 regressions · 1 recoveries/);
+  assert.match(html, /Full maintained suite/);
+  assert.ok(html.includes(`https://github.com/paperclipai/paperclip/commit/${"a".repeat(40)}`));
+  assert.ok(html.includes(`https://github.com/paperclipai/paperclip-evals/commit/${"b".repeat(40)}`));
+  assert.match(html, /actions\/runs\/2/);
+  assert.match(html, /href="https:\/\/reports.example\/runner-protocol-evals\/campaigns\/gha-2-1-report-theme\/">Latest · gha-2-1/);
+  assert.doesNotMatch(html, /<script|NaN|Infinity/);
+});
diff --git a/packages/paperclip-runner/scripts/runner-protocol-eval-workflow-security.test.mjs b/packages/paperclip-runner/scripts/runner-protocol-eval-workflow-security.test.mjs
index 0569facb0a..d35fbd8bc5 100644
--- a/packages/paperclip-runner/scripts/runner-protocol-eval-workflow-security.test.mjs
+++ b/packages/paperclip-runner/scripts/runner-protocol-eval-workflow-security.test.mjs
@@ -136,6 +136,19 @@ test("publishes only the separately sanitized Evalbook through trusted OIDC code
     /Upload access-controlled canonical Evalbook and raw attempts/u,
   );
   assert.match(report, /Upload publisher-only sanitized Evalbook/u);
+  assert.match(
+    report,
+    /verify-runner-evalbook-viewer\.mjs --report-root runner-protocol-merged\/public-report/u,
+  );
+  assert.match(
+    report,
+    /verify-runner-evalbook-viewer\.mjs --report-root runner-protocol-merged\/report/u,
+  );
+  assert.match(
+    report,
+    /--viewer-root runner-protocol-build\/extracted\/dist-issue-thread\s*\\\n\s*--public-viewer/u,
+  );
+  assert.equal([...report.matchAll(/--viewer-root /gu)].length, 2);
 
   const publisher = workflow.slice(workflow.indexOf("  publish_history:"));
   assert.match(publisher, /ref: \$\{\{ github\.sha \}\}/u);
@@ -143,6 +156,10 @@ test("publishes only the separately sanitized Evalbook through trusted OIDC code
   assert.match(publisher, /runner-protocol-eval-public-/u);
   assert.match(publisher, /publish-runner-protocol-eval-history\.mjs/u);
   assert.match(publisher, /runner-protocol-evals/u);
+  assert.match(publisher, /runner-protocol-viewer-/u);
+  assert.match(publisher, /PAPERCLIP_RUNNER_PROTOCOL_EVAL_VIEWER_DIR/u);
+  assert.match(publisher, /url: \$\{\{ steps\.publish\.outputs\.report_url \}\}/u);
+  assert.match(publisher, /Publish versioned report and refresh the root index\n\s+id: publish/u);
   assert.doesNotMatch(publisher, /(?:OPENAI|ANTHROPIC|OPENROUTER)_API_KEY/u);
   assert.doesNotMatch(publisher, /paperclipai\/paperclip-evals/u);
   assert.doesNotMatch(publisher, /downloaded-runner-protocol-evals/u);
diff --git a/packages/paperclip-runner/scripts/verify-runner-evalbook-viewer.mjs b/packages/paperclip-runner/scripts/verify-runner-evalbook-viewer.mjs
new file mode 100644
index 0000000000..d665cfb7f7
--- /dev/null
+++ b/packages/paperclip-runner/scripts/verify-runner-evalbook-viewer.mjs
@@ -0,0 +1,185 @@
+#!/usr/bin/env node
+// Execute the built viewer against actual generated pages, without a runner API.
+import assert from "node:assert/strict";
+import { createServer } from "node:http";
+import { readFile, readdir, mkdir } from "node:fs/promises";
+import { resolve, join, extname, sep } from "node:path";
+import { chromium, expect } from "@playwright/test";
+
+const arg = (name) => process.argv[process.argv.indexOf(name) + 1];
+if (!process.argv.includes("--report-root"))
+  throw new Error("--report-root is required");
+const root = resolve(arg("--report-root"));
+const screenshots = process.argv.includes("--screenshots")
+  ? resolve(arg("--screenshots"))
+  : null;
+const samples = new Map();
+for (const entry of await readdir(join(root, "attempts"), {
+  withFileTypes: true,
+})) {
+  if (!entry.isDirectory()) continue;
+  const route = `attempts/${entry.name}/index.html`;
+  const html = await readFile(join(root, route), "utf8");
+  const encoded =
+    html.match(
+      /<script type="application\/json" id="paperclip-eval-report">([^<]*)<\/script>/u,
+    )?.[1] ??
+    html.match(/window\.__PAPERCLIP_EVAL_REPORT__=(.*?);<\/script>/su)?.[1];
+  assert.ok(encoded, `Attempt lacks canonical viewer payload: ${route}`);
+  const payload = JSON.parse(encoded);
+  const messages = payload.view.turns
+    .flatMap((turn) => turn.items)
+    .filter((item) => ["user_message", "agent_message"].includes(item.kind));
+  const kind = !messages.length
+    ? "missing-recording"
+    : payload.passed
+      ? "passed"
+      : "failed";
+  if (!samples.has(kind)) samples.set(kind, { route, payload });
+}
+assert.ok(samples.size, "No attempt pages to verify");
+const server = createServer(async (req, res) => {
+  try {
+    const url = new URL(req.url, "http://report.invalid");
+    const path = resolve(root, `.${decodeURIComponent(url.pathname)}`);
+    if (!path.startsWith(`${root}${sep}`)) {
+      res.writeHead(403).end();
+      return;
+    }
+    const mime = {
+      ".html": "text/html",
+      ".js": "text/javascript",
+      ".css": "text/css",
+      ".woff2": "font/woff2",
+    };
+    res.writeHead(200, {
+      "Content-Type": mime[extname(path)] ?? "application/octet-stream",
+    });
+    res.end(await readFile(path));
+  } catch {
+    res.writeHead(404).end();
+  }
+});
+await new Promise((done) => server.listen(0, "127.0.0.1", done));
+const origin = `http://127.0.0.1:${server.address().port}`;
+let browser;
+try {
+  browser = await chromium.launch({ headless: true });
+  if (screenshots) await mkdir(screenshots, { recursive: true });
+  for (const [kind, { route, payload }] of samples) {
+    const page = await browser.newPage({
+      viewport: { width: 1440, height: 1000 },
+    });
+    const errors = [];
+    const requests = [];
+    page.on("pageerror", (error) => errors.push(error.message));
+    page.on("request", (request) => requests.push(request.url()));
+    await page.goto(`${origin}/${route}`, { waitUntil: "networkidle" });
+    await page.locator(".pit-thread").waitFor({ state: "visible" });
+    const chatBackground = await page.evaluate(() => getComputedStyle(document.body).backgroundColor);
+    assert.equal(
+      await page.locator("h1").textContent(),
+      payload.view.issue.title,
+    );
+    assert.equal(
+      await page
+        .getByRole("button", { name: "Reset scenario", exact: true })
+        .count(),
+      0,
+    );
+    assert.equal(
+      await page.getByText("Loading company state…", { exact: true }).count(),
+      0,
+    );
+    assert.ok(
+      await page.getByText(payload.run.model, { exact: false }).count(),
+      "Model missing from inspector",
+    );
+    const tool = page
+      .locator('[data-thread-item="tool_activity"] summary')
+      .first();
+    if (await tool.count()) {
+      await tool.click();
+      assert.ok(
+        await page.locator('[data-thread-item="tool_activity"][open]').count(),
+      );
+      if (payload.publication)
+        assert.ok(
+          await page
+            .getByText("Arguments withheld from public replay.", {
+              exact: false,
+            })
+            .count(),
+        );
+      if (payload.devtools || payload.publication) {
+        const evidenceLink = page
+          .locator('[data-thread-item="tool_activity"][open]')
+          .first()
+          .getByRole("button", { name: "View in Evidence", exact: true });
+        const evidenceTab = page.getByRole("tab", { name: "Evidence", exact: true });
+        await evidenceLink.click();
+        await expect(evidenceTab).toHaveAttribute("aria-selected", "true");
+        await expect(page.locator('[data-highlighted="true"]').first()).toBeVisible();
+        await expect(page.getByRole("heading", { name: "Assertions", exact: true })).toHaveCount(0);
+        // Reopening the same record after selecting another tab must work too.
+        await page.getByRole("tab", { name: "Eval", exact: true }).click();
+        await evidenceLink.click();
+        await expect(evidenceTab).toHaveAttribute("aria-selected", "true");
+        await page.getByRole("tab", { name: "Eval", exact: true }).click();
+      }
+    }
+    if (payload.publication) {
+      assert.ok(
+        await page
+          .getByText(payload.publication.notice, { exact: true })
+          .count(),
+      );
+      assert.ok(
+        requests.every(
+          (url) => url.startsWith(origin) && !url.includes("/api/"),
+        ),
+        "Replay attempted a remote/API request",
+      );
+    }
+    assert.deepEqual(errors, [], `Viewer errors for ${kind}`);
+    if (screenshots)
+      await page.screenshot({
+        path: join(screenshots, `${kind}.png`),
+        fullPage: true,
+      });
+    await page
+      .getByRole("link", { name: "← All results", exact: true })
+      .click();
+    assert.equal(new URL(page.url()).pathname, "/index.html");
+    await expect(page.locator("body")).toHaveClass("evalbook-site");
+    const assertSiteTheme = async () => {
+      assert.equal(await page.evaluate(() => getComputedStyle(document.body).backgroundColor), chatBackground);
+      assert.equal(await page.evaluate(() => getComputedStyle(document.documentElement).colorScheme), "dark");
+    };
+    await assertSiteTheme();
+    if (screenshots) await page.screenshot({ path: join(screenshots, "index.png"), fullPage: true });
+    await page.locator(".matrix tbody th a").first().click();
+    await expect(page.getByText("Test design", { exact: true })).toBeVisible();
+    await assertSiteTheme();
+    await page.getByText("Full authored test definition", { exact: true }).click();
+    if (screenshots) await page.screenshot({ path: join(screenshots, "test-design.png"), fullPage: true });
+    await page.getByRole("link", { name: "← All results", exact: true }).click();
+    await page.getByRole("link", { name: "Latest", exact: true }).click();
+    await assertSiteTheme();
+    await page.getByRole("link", { name: "Overview", exact: true }).click();
+    await assertSiteTheme();
+    await page.goto(`${origin}/${route}`, { waitUntil: "networkidle" });
+    await page.reload({ waitUntil: "networkidle" });
+    await page.locator(".pit-thread").waitFor({ state: "visible" });
+    assert.deepEqual(errors, [], `Reload errors for ${kind}`);
+    await page.setViewportSize({ width: 390, height: 844 });
+    await page.locator(".pit-thread").waitFor({ state: "visible" });
+    await page.close();
+    console.log(
+      `Verified ${kind}: chat, read-only controls, navigation, reload and narrow viewport`,
+    );
+  }
+} finally {
+  await browser?.close();
+  await new Promise((done) => server.close(done));
+}