fix(evals): open tool evidence in the correct inspector tab

Co-Authored-By: Paperclip <noreply@paperclip.ing>

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";
@@ -333,6 +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");
@@ -572,6 +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]));
@@ -1497,6 +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) => {

packages/paperclip-runner/devtools/issue-thread/src/EvidencePanel.tsx

@@ -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,
@@ -394,7 +397,7 @@ export function EvidencePanel(props: EvidencePanelProps) {
           {devtools === null ? (
             evalReport ? <EvalReportInspector evalReport={evalReport} /> : <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}

packages/paperclip-runner/docs/runner-protocol-live-evals.md

@@ -27,6 +27,9 @@ 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

packages/paperclip-runner/scripts/verify-runner-evalbook-viewer.mjs

@@ -4,7 +4,7 @@ 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 } from "@playwright/test";
+import { chromium, expect } from "@playwright/test";
 
 const arg = (name) => process.argv[process.argv.indexOf(name) + 1];
 if (!process.argv.includes("--report-root"))
@@ -110,6 +110,21 @@ try {
             })
             .count(),
         );
+      else if (payload.devtools) {
+        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();
+        // 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(